Compare commits
220
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
45a1783ba9 | ||
|
|
84deb530ee | ||
|
|
b3787e4d8e | ||
|
|
a681227af3 | ||
|
|
d8f36a8fb7 | ||
|
|
f0fd7fe886 | ||
|
|
41a9ff15dd | ||
|
|
ba685b17f5 | ||
|
|
d170491256 | ||
|
|
6bb1c9b768 | ||
|
|
f8daec01d3 | ||
|
|
f3c15e00af | ||
|
|
9038d4b0d3 | ||
|
|
f10aedac58 | ||
|
|
875ebc093e | ||
|
|
1e28342ede | ||
|
|
bc623bc1f9 | ||
|
|
ce9dc8e157 | ||
|
|
c672b3df6d | ||
|
|
25deb499bf | ||
|
|
83a9cf6e3a | ||
|
|
7b050abdcb | ||
|
|
c3b4f187e1 | ||
|
|
edd33f21d2 | ||
|
|
5ad36127ee | ||
|
|
a1a6f6493d | ||
|
|
e9f060e0be | ||
|
|
3cfc121670 | ||
|
|
d20b52cb19 | ||
|
|
db7e4869ae | ||
|
|
539a1c16cd | ||
|
|
9eddf36503 | ||
|
|
01fc9e1d73 | ||
|
|
d4de4543cc | ||
|
|
a371de37fe | ||
|
|
77acb40092 | ||
|
|
5facd8b08e | ||
|
|
72edb458cc | ||
|
|
10f76cafc4 | ||
|
|
2843834813 | ||
|
|
3e10ad1535 | ||
|
|
27b13e4586 | ||
|
|
142a5ad71d | ||
|
|
63a99d4323 | ||
|
|
0cd8bc0bfb | ||
|
|
7385d9c092 | ||
|
|
db9e9c5b87 | ||
|
|
4ead5a3df7 | ||
|
|
a23b190747 | ||
|
|
3be6e86f77 | ||
|
|
b0c4b849a7 | ||
|
|
b849af53dd | ||
|
|
74bd90df7e | ||
|
|
30599c1858 | ||
|
|
10d4712f82 | ||
|
|
e737e13bbb | ||
|
|
4b1dee6b79 | ||
|
|
4ab441ce16 | ||
|
|
f996cf7b6b | ||
|
|
bcfcfaaaf3 | ||
|
|
a3181e356b | ||
|
|
dd2fd28c92 | ||
|
|
9d165c7500 | ||
|
|
7630072e63 | ||
|
|
1e9dcf0667 | ||
|
|
cd6610cdf7 | ||
|
|
facc551ff2 | ||
|
|
71b3aeaf2c | ||
|
|
fafa3fd9ef | ||
|
|
6e5a1df575 | ||
|
|
d881f4764d | ||
|
|
61d00a234a | ||
|
|
4d203b5a5d | ||
|
|
6196a4815e | ||
|
|
dcdafd37f0 | ||
|
|
f549647d18 | ||
|
|
0a0f5b4a5a | ||
|
|
22a2f73f7b | ||
|
|
d854598d8c | ||
|
|
ac5d34f613 | ||
|
|
b03ec3b64e | ||
|
|
4aacd98f8d | ||
|
|
ed037784e2 | ||
|
|
47205403d3 | ||
|
|
da1473e9db | ||
|
|
cde0dc287b | ||
|
|
63079e2c67 | ||
|
|
0d08d5c730 | ||
|
|
3bd984c41e | ||
|
|
ed1b106c19 | ||
|
|
6b77dd96f4 | ||
|
|
9460689fff | ||
|
|
96005a8bfd | ||
|
|
b12da96906 | ||
|
|
eba0a301cc | ||
|
|
e6bd8f1dee | ||
|
|
5b9c81bf26 | ||
|
|
d8ec8baa22 | ||
|
|
9c750a80de | ||
|
|
4ee131e990 | ||
|
|
faf8b76b84 | ||
|
|
ad3b4f185b | ||
|
|
db86dd52c8 | ||
|
|
b26499bb9f | ||
|
|
e25fdf776f | ||
|
|
e1953ad3f5 | ||
|
|
6d2138217f | ||
|
|
0e86664191 | ||
|
|
92aa3fb179 | ||
|
|
c2abb3759a | ||
|
|
0fb7de7ef8 | ||
|
|
bc4662d656 | ||
|
|
ece3759647 | ||
|
|
8d73f705af | ||
|
|
0d4d94ff24 | ||
|
|
e2801773c3 | ||
|
|
fae6bd0a87 | ||
|
|
afc7dd8f68 | ||
|
|
201bd28278 | ||
|
|
5446be1abb | ||
|
|
932203df20 | ||
|
|
949990f5a8 | ||
|
|
731143f5b9 | ||
|
|
b555e995b0 | ||
|
|
309475bf6f | ||
|
|
fbfdded74b | ||
|
|
315cbd1f54 | ||
|
|
eb8233ac7c | ||
|
|
3b017b228c | ||
|
|
bf82d30865 | ||
|
|
c432b9b5f6 | ||
|
|
325575b292 | ||
|
|
c385ed2a17 | ||
|
|
7bd61332cb | ||
|
|
0f853e93fa | ||
|
|
78205d7405 | ||
|
|
538c4d5115 | ||
|
|
fbeffb608d | ||
|
|
fad655532d | ||
|
|
e1367d185a | ||
|
|
0c675bcdb5 | ||
|
|
8115f1ac42 | ||
|
|
93289dc88b | ||
|
|
9edc5c758d | ||
|
|
483c387b72 | ||
|
|
174c8b5d53 | ||
|
|
fe2e5e91b5 | ||
|
|
5dd0e3c056 | ||
|
|
51db0b5273 | ||
|
|
313efa826c | ||
|
|
72fde0ee1a | ||
|
|
5c4fa43f8b | ||
|
|
7bd04342b6 | ||
|
|
c494ed03a7 | ||
|
|
02c61b983c | ||
|
|
c14fe2776c | ||
|
|
419d662ad8 | ||
|
|
3b6b54a501 | ||
|
|
83ce19b9c0 | ||
|
|
7758301444 | ||
|
|
094d3d5bc6 | ||
|
|
e7bcc107c8 | ||
|
|
ebca7816bf | ||
|
|
9bed7d6398 | ||
|
|
a330c564ba | ||
|
|
0a2e58c070 | ||
|
|
1747e33923 | ||
|
|
9b6acf0ef5 | ||
|
|
45b4ae92bc | ||
|
|
4f5fab81fe | ||
|
|
4632b6a508 | ||
|
|
9d6a12eb53 | ||
|
|
984d85865d | ||
|
|
ed45cc6415 | ||
|
|
ef551fdfb6 | ||
|
|
7493bd8f18 | ||
|
|
8305e4e3d1 | ||
|
|
fbc7bc976b | ||
|
|
f510b46319 | ||
|
|
926fde2fda | ||
|
|
d5cf3b42fe | ||
|
|
47c7877e8d | ||
|
|
68fbd99e89 | ||
|
|
9a37c143e4 | ||
|
|
eb72075104 | ||
|
|
d6b867a87a | ||
|
|
1dc9961c43 | ||
|
|
11ffab887b | ||
|
|
cfbbad8209 | ||
|
|
d2e9dc6159 | ||
|
|
5557a01f06 | ||
|
|
5bddb16514 | ||
|
|
671e350f56 | ||
|
|
f83fcdc15f | ||
|
|
585caa4371 | ||
|
|
f8d08b0637 | ||
|
|
dc62fd0075 | ||
|
|
525b2c1a11 | ||
|
|
c11222026a | ||
|
|
360c318e85 | ||
|
|
f008fab9d8 | ||
|
|
15a9919df5 | ||
|
|
1390836b73 | ||
|
|
dac7e5f7f6 | ||
|
|
c06a2cd972 | ||
|
|
d5f6b67b94 | ||
|
|
12d4025d30 | ||
|
|
1ca4d8ce60 | ||
|
|
a4f93b52a8 | ||
|
|
a2a671adb7 | ||
|
|
412f11b079 | ||
|
|
5d4eb974ab | ||
|
|
6805e2bcb3 | ||
|
|
c640341c50 | ||
|
|
690b75f659 | ||
|
|
d52de218c8 | ||
|
|
6188e6b1da | ||
|
|
798738cc12 | ||
|
|
babfef4f3a | ||
|
|
96b0966ad8 |
@@ -3,3 +3,8 @@
|
||||
# A built binary. The lab writes one here when pointed at the repository root by mistake;
|
||||
# built artifacts belong in build/, which is already ignored.
|
||||
/mesh-builder
|
||||
/mesh-controller
|
||||
/postgres-provisioner
|
||||
/redis-provisioner
|
||||
# And where `go build` in cmd/mesh-controller leaves it (novox/hq issue 233).
|
||||
/cmd/mesh-controller/mesh-controller
|
||||
|
||||
@@ -99,16 +99,22 @@ proxy-image:
|
||||
@echo
|
||||
@docker image inspect $(PROXY_IMAGE) --format 'built {{.RepoTags}} {{.Size}} bytes'
|
||||
|
||||
# The whole gate. Raises a database, runs everything against it, and takes it down again --
|
||||
# including when the tests fail, which is why the teardown is not conditional.
|
||||
# The whole check. Raises a database, runs the repository's own check against it -- merge-check.sh,
|
||||
# the very script `mesh/repo-check` runs -- and takes the database down again, including when the
|
||||
# check fails, which is why the teardown is not conditional and the script's exit status is the
|
||||
# target's.
|
||||
#
|
||||
# **Packages in parallel, under the race detector, each test on a bus of its own** (internal/testbus).
|
||||
# It was one package at a time against one shared bus, because the live tests assert, read and remove
|
||||
# the mesh's own objects by their fixed names, and two packages at once deleted what the other read; the
|
||||
# suite was red run as Go runs it and read as noise. A bus per test, of the release the mesh runs, made
|
||||
# it the same in any order. The timeout bounds a hang to a failure with a stack, never a stalled gate.
|
||||
check: fmt vet postgres
|
||||
@go test -race -timeout 15m ./... ; status=$$? ; $(MAKE) postgres-stop ; exit $$status
|
||||
# **It calls the script rather than restating it** (novox/hq issue 431): this target used to list its
|
||||
# own steps, its formatting step walked vendor/ where the script's does not, and it failed on
|
||||
# third-party code no change could fix -- so a developer's check and the gate disagreed, and the steps
|
||||
# after formatting never ran through it. The script is the one list of steps; this target only gives it
|
||||
# a database (MESH_TEST_POSTGRES, exported above).
|
||||
#
|
||||
# **Packages in parallel, under the race detector, each test on a bus of its own** (internal/testbus),
|
||||
# as the script runs them: a bus per test, of the release the mesh runs, makes the suite the same in any
|
||||
# order, and the timeout bounds a hang to a failure with a stack, never a stalled gate.
|
||||
check: postgres
|
||||
@sh merge-check.sh ; status=$$? ; docker rm -f $(PG_CONTAINER) >/dev/null 2>&1 || true ; exit $$status
|
||||
|
||||
# Without a database the store's tests skip rather than fail, so this is the honest subset and not
|
||||
# the gate.
|
||||
@@ -118,8 +124,10 @@ test:
|
||||
vet:
|
||||
go vet ./...
|
||||
|
||||
# Quick steps for a developer, not part of `check`. The directories gofmt reads must be the ones
|
||||
# merge-check.sh lists, never `.`, which walks vendor/ (novox/hq issue 431).
|
||||
fmt:
|
||||
@unformatted=$$(gofmt -l . 2>/dev/null) ; \
|
||||
@unformatted=$$(gofmt -l cmd internal examples) ; \
|
||||
if [ -n "$$unformatted" ] ; then echo "not gofmt'd:" ; echo "$$unformatted" ; exit 1 ; fi
|
||||
|
||||
postgres:
|
||||
|
||||
@@ -256,7 +256,13 @@ func answer(ctx context.Context, publisher builder.Publisher, on, workspace stri
|
||||
v, err = builder.Check(building, builder.Command, checkSpecOf(request), workspace, registry, forgeFrom(), say)
|
||||
if err == nil {
|
||||
result.Check = &link.CheckOutcome{Verdict: v.Verdict, Summary: v.Summary, Report: v.Report,
|
||||
Took: v.Took.Round(time.Second).String(), Gate: layerOf(v.Gate), RepoCheck: layerOf(v.Repo)}
|
||||
Took: v.Took.Round(time.Second).String(), Gate: layerOf(v.Gate), RepoCheck: layerOf(v.Repo),
|
||||
Head: v.Head, Trunk: v.Trunk, Beside: v.Beside}
|
||||
// What each of a group's heads was judged as (novox/hq ADR 0323 §6).
|
||||
for _, m := range v.Members {
|
||||
result.Check.Members = append(result.Check.Members, link.CheckedMember{Owner: m.Owner, Repo: m.Repo,
|
||||
Commit: m.Head, Trunk: m.Trunk})
|
||||
}
|
||||
}
|
||||
} else if err == nil {
|
||||
// The package-registry credential is a build input, so it is resolved before the clone: a
|
||||
@@ -354,7 +360,7 @@ func checkSpecOf(request link.BuildRequest) builder.CheckSpec {
|
||||
}
|
||||
for _, m := range c.Members {
|
||||
spec.Group = append(spec.Group, builder.GroupHead{Owner: m.Owner, Repo: m.Repo, Repository: m.Repository,
|
||||
Ref: m.Ref, Paths: m.Paths})
|
||||
Ref: m.Ref, Paths: m.Paths, Base: m.Base})
|
||||
}
|
||||
return spec
|
||||
}
|
||||
|
||||
+67
-15
@@ -4,6 +4,7 @@ import (
|
||||
"context"
|
||||
"fmt"
|
||||
"github.com/novox/mesh-controller/internal/broker"
|
||||
"io"
|
||||
"slices"
|
||||
"sort"
|
||||
"strings"
|
||||
@@ -54,6 +55,9 @@ func assignWith(ctx context.Context, open *stores, node string, opts assignOptio
|
||||
if err := refusedMovingTheController(modules); err != nil {
|
||||
return "", err
|
||||
}
|
||||
// Every line of the answer comes from the one resolution after the write (novox/hq issue 237):
|
||||
// what the reads before it would say about a machine left out is not the answer's.
|
||||
ctx = leftOutSaidBy(ctx, io.Discard)
|
||||
// Held while it is recorded, so it cannot land between a converge's preview and its flip and
|
||||
// be taken without ever having been previewed (novox/hq ADR 0100).
|
||||
ctx, release, err := holdNodes(ctx, open, []string{node})
|
||||
@@ -125,22 +129,28 @@ func assignWith(ctx context.Context, open *stores, node string, opts assignOptio
|
||||
for _, line := range settled {
|
||||
answer += "\n " + line
|
||||
}
|
||||
// What this act changed about this node's unmet seat dependencies, and nothing else (novox/hq
|
||||
// ADR 0207): a dependency of a module just assigned, or one this assignment met. The rest of the
|
||||
// node's list, and every other node's, is `status`'s.
|
||||
for _, line := range unheldChange(shelf, node, before, append(append([]string(nil), before...), added...)) {
|
||||
answer += "\n " + line
|
||||
}
|
||||
// Its bus credential, in the same act (novox/hq issue 203): an assignment pushed before its
|
||||
// credential exists delivers a process that cannot authenticate and crash-loops until somebody
|
||||
// runs a second verb and a second push. Issued here when the module speaks on the bus and has
|
||||
// no credential yet; kept when it has one, so re-assigning rotates nothing.
|
||||
var issued []string
|
||||
for _, module := range added {
|
||||
if line := issueOnAssign(ctx, open, node, module); line != "" {
|
||||
answer += "\n " + line
|
||||
issued = append(issued, line)
|
||||
}
|
||||
}
|
||||
plan, _, err := planFor(ctx, open, node)
|
||||
// **The one resolution the rest of the answer is said from** (novox/hq issue 237), taken after
|
||||
// the write: what this act changed about this node's unmet seat dependencies, and nothing else
|
||||
// (novox/hq ADR 0207) — a dependency of a module just assigned, or one this assignment met; the
|
||||
// rest of the node's list, and every other node's, is `status`'s — and whether the node resolves.
|
||||
after := resolvedAfter(ctx, open, shelf, node)
|
||||
for _, line := range unheldChangeTo(shelf, node, before, after.modules, after.unheld) {
|
||||
answer += "\n " + line
|
||||
}
|
||||
for _, line := range issued {
|
||||
answer += "\n " + line
|
||||
}
|
||||
plan, err := after.plan, after.err
|
||||
if err != nil {
|
||||
// Kept, and still refused. Both halves are the answer, and the rest of the mesh is still
|
||||
// worth reporting: this machine's refusal is rarely the only consequence.
|
||||
@@ -218,6 +228,8 @@ func unassign(ctx context.Context, open *stores, node string, modules ...string)
|
||||
if len(modules) == 0 {
|
||||
return "", fmt.Errorf("unassign %s names no module", node)
|
||||
}
|
||||
// One resolution after the write, as assign's answer (novox/hq issue 237).
|
||||
ctx = leftOutSaidBy(ctx, io.Discard)
|
||||
ctx, release, err := holdNodes(ctx, open, []string{node})
|
||||
if err != nil {
|
||||
return "", err
|
||||
@@ -262,15 +274,22 @@ func unassign(ctx context.Context, open *stores, node string, modules ...string)
|
||||
}
|
||||
answer := fmt.Sprintf("%s no longer runs %s — run `push %s` to make it so",
|
||||
node, strings.Join(modules, ", "), node)
|
||||
var left []string
|
||||
for _, a := range assigned {
|
||||
if !slices.Contains(modules, a) {
|
||||
left = append(left, a)
|
||||
}
|
||||
}
|
||||
for _, line := range unheldChange(shelf, node, assigned, left) {
|
||||
after := resolvedAfter(ctx, open, shelf, node)
|
||||
for _, line := range unheldChangeTo(shelf, node, assigned, after.modules, after.unheld) {
|
||||
answer += "\n " + line
|
||||
}
|
||||
// Whether the node itself still resolves, from the same resolution: before, only the rest of the
|
||||
// mesh's reads said it, on standard error and once per other machine.
|
||||
if after.err != nil {
|
||||
if unresolvable(after.err) {
|
||||
answer += fmt.Sprintf("\n but %s does not resolve now, so nothing will be sent to it:", node)
|
||||
} else {
|
||||
answer += fmt.Sprintf("\n but whether %s still resolves could not be read:", node)
|
||||
}
|
||||
for _, line := range strings.Split(strings.TrimRight(after.err.Error(), "\n"), "\n") {
|
||||
answer += "\n " + strings.TrimSpace(line)
|
||||
}
|
||||
}
|
||||
// What it leaves behind that is irreplaceable is kept and retired, never removed (novox/hq ADR 0233).
|
||||
for _, line := range keptOnUnassign(ctx, open.inventory, node, modules) {
|
||||
answer += "\n " + line
|
||||
@@ -278,6 +297,39 @@ func unassign(ctx context.Context, open *stores, node string, modules ...string)
|
||||
return answer + blockedElsewhere(ctx, open, node), nil
|
||||
}
|
||||
|
||||
// afterAct is the one resolution of a node an act's answer is said from, taken after its write
|
||||
// (novox/hq issue 237): the plan or why there is none, the modules it has on the node, and its unmet
|
||||
// seat dependencies.
|
||||
type afterAct struct {
|
||||
plan catalogue.Resolution
|
||||
err error
|
||||
modules []string
|
||||
unheld []catalogue.Unheld
|
||||
}
|
||||
|
||||
// resolvedAfter resolves the node as `plan` does, once, after the act's write. When the node resolves,
|
||||
// its modules and unmet seat dependencies are the resolution's — the closure, so a holder pulled in by
|
||||
// a requirement counts as `plan` counts it. When it does not, they are judged over the assignments read
|
||||
// after the write, which can only find more unmet than the closure would: a seat said held there is
|
||||
// held in the closure too.
|
||||
func resolvedAfter(ctx context.Context, open *stores, shelf map[string]catalogue.Manifest, node string) afterAct {
|
||||
plan, _, err := planFor(ctx, open, node)
|
||||
if err == nil {
|
||||
out := afterAct{plan: plan, unheld: plan.Unheld}
|
||||
for _, m := range plan.Modules {
|
||||
out.modules = append(out.modules, m.Module)
|
||||
}
|
||||
return out
|
||||
}
|
||||
out := afterAct{err: err}
|
||||
assigned, readErr := open.inventory.Assigned(ctx, node)
|
||||
if readErr != nil {
|
||||
return out
|
||||
}
|
||||
out.modules, out.unheld = assigned, unheldOver(shelf, node, assigned)
|
||||
return out
|
||||
}
|
||||
|
||||
// splitModules is a surface's one `module` field as the modules it names: several, comma-separated,
|
||||
// are one act (novox/hq ADR 0207), so the holders that depend on each other go on together from the
|
||||
// command API and the controller seat's verbs as they do from the command line.
|
||||
|
||||
@@ -408,6 +408,9 @@ func comparisonOf(module string, c comparison, opts takeOptions) (preview string
|
||||
switch {
|
||||
case sec.Origin == inventory.OriginAccepted:
|
||||
fmt.Fprintf(&b, " %s %s: accepted from a person, carried in as it is\n", what, name)
|
||||
case sec.Origin == inventory.OriginIssued:
|
||||
// Taken from the provider's software (novox/hq ADR 0305): the value the running service uses.
|
||||
fmt.Fprintf(&b, " %s %s: issued by the provider's software, carried in as it is\n", what, name)
|
||||
case opts.Mint[sec.Name]:
|
||||
fmt.Fprintf(&b, " %s %s: minted by the mesh; the service takes the new value, as --mint said\n", what, name)
|
||||
case foundData:
|
||||
|
||||
@@ -0,0 +1,180 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/conditions"
|
||||
"github.com/novox/mesh-controller/internal/link"
|
||||
)
|
||||
|
||||
// **A refusal the bus said once is counted once** (novox/hq issue 402). The bus refused the controller
|
||||
// one publish at 18:52:59 UTC on 2026-10-10 and never again, yet S9 looked at the one remembered
|
||||
// advisory every half minute for the hour it is kept, and the condition said "observed 15 time(s), last
|
||||
// 13s ago" with a refusal in its evidence every 30 seconds: two of us read it as a refusal going on and
|
||||
// went looking for a missing grant. The condition counts what the bus said, with when it last said it,
|
||||
// never how often the controller looked.
|
||||
func TestARefusalSaidOnceIsCountedOnceHoweverOftenItIsLookedAt(t *testing.T) {
|
||||
refused := time.Date(2026, 10, 10, 18, 52, 59, 0, time.UTC)
|
||||
now := refused.Add(10 * time.Second)
|
||||
store := conditions.NewInMemory()
|
||||
k := conditions.NewKeeper(t.Context(), conditions.Options{Store: store, History: store,
|
||||
Teller: &conditions.Told{}, Now: func() time.Time { return now }})
|
||||
t.Cleanup(func() { k.Close(t.Context()) })
|
||||
|
||||
// The words the live condition bus.controller.refused carried on 2026-10-10.
|
||||
said := "the bus refused the controller: nats: permissions violation: Permissions Violation for " +
|
||||
`Publish to "mesh.seat.mesh-delivery.tool.times"`
|
||||
advisory := link.Advisory{Kind: link.AdvisoryRefused, ID: "controller", Said: said,
|
||||
First: refused, Last: refused, Count: 1}
|
||||
look := func() conditions.Condition {
|
||||
t.Helper()
|
||||
f := &signalFacts{now: now, host: "novox", advisories: []link.Advisory{advisory}}
|
||||
if err := k.Reconcile(t.Context(), "S9", watchAdvisories(f)); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
c, found, err := conditions.ReadOne(t.Context(), store, "bus.controller.refused")
|
||||
if err != nil || !found {
|
||||
t.Fatalf("bus.controller.refused: found %v, %v", found, err)
|
||||
}
|
||||
return c
|
||||
}
|
||||
|
||||
var c conditions.Condition
|
||||
for range 15 {
|
||||
c = look()
|
||||
now = now.Add(30 * time.Second)
|
||||
}
|
||||
if c.Observations != 1 || len(c.Evidence) != 1 {
|
||||
t.Fatalf("one refusal, looked at 15 times, reads as observed %d time(s) with %d evidence lines: %+v",
|
||||
c.Observations, len(c.Evidence), c.Evidence)
|
||||
}
|
||||
if !c.LastObserved.Equal(refused) || !c.Evidence[0].At.Equal(refused) {
|
||||
t.Fatalf("last observed %s, evidence at %s: the refusal was at %s", c.LastObserved, c.Evidence[0].At, refused)
|
||||
}
|
||||
|
||||
// The bus refuses it three times more between two looks: the condition counts four refusals, says
|
||||
// the newest, and adds one line of evidence for the look that saw them.
|
||||
again := now.Add(-5 * time.Second)
|
||||
advisory.Last, advisory.Count = again, 4
|
||||
c = look()
|
||||
if c.Observations != 4 || len(c.Evidence) != 2 || !c.LastObserved.Equal(again) || !c.Evidence[0].At.Equal(again) {
|
||||
t.Fatalf("four refusals read as observed %d time(s), last %s, evidence %+v", c.Observations, c.LastObserved, c.Evidence)
|
||||
}
|
||||
if !strings.Contains(c.Summary, "(4 times since 18:52 UTC)") {
|
||||
t.Fatalf("summary %q", c.Summary)
|
||||
}
|
||||
now = now.Add(30 * time.Second)
|
||||
if c = look(); c.Observations != 4 || len(c.Evidence) != 2 {
|
||||
t.Fatalf("a look with nothing new counted: observed %d time(s), evidence %+v", c.Observations, c.Evidence)
|
||||
}
|
||||
}
|
||||
|
||||
// **A condition that looks at the present still counts its looks** (novox/hq issue 402 changes only
|
||||
// what reads a record): a machine silent for three looks was observed three times, and says so.
|
||||
func TestAConditionOfThePresentCountsItsLooks(t *testing.T) {
|
||||
now := time.Date(2026, 10, 10, 19, 0, 0, 0, time.UTC)
|
||||
store := conditions.NewInMemory()
|
||||
k := conditions.NewKeeper(t.Context(), conditions.Options{Store: store, History: store,
|
||||
Teller: &conditions.Told{}, Now: func() time.Time { return now }})
|
||||
t.Cleanup(func() { k.Close(t.Context()) })
|
||||
var c conditions.Condition
|
||||
for range 3 {
|
||||
var err error
|
||||
if c, err = k.Observe(t.Context(), conditions.Observation{Scope: conditions.ScopeMachine, ID: "ace",
|
||||
Kind: "silent", Machine: "ace", Severity: conditions.Warning, Summary: "ace has not been heard from",
|
||||
Source: "S1"}); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
now = now.Add(30 * time.Second)
|
||||
}
|
||||
if c.Observations != 3 || len(c.Evidence) != 3 || !c.LastObserved.Equal(now.Add(-30*time.Second)) {
|
||||
t.Fatalf("observed %d time(s), %d evidence lines, last %s", c.Observations, len(c.Evidence), c.LastObserved)
|
||||
}
|
||||
}
|
||||
|
||||
// **One key, one watcher** (novox/hq issue 440). A consumer's max-deliveries condition is said from
|
||||
// DEAD_LETTERS while it holds a message the consumer gave up on (issue 330). A max-deliveries advisory
|
||||
// without a token names the same key; read beside it, each look added an observation and a line of
|
||||
// evidence through the dead-letter half, and the two summaries overwrote each other on every look. The
|
||||
// dead-letter row alone says that key, and counts the messages given up on, never the looks.
|
||||
func TestAHeldDeadLetterIsCountedByWhatWasGivenUpNotByTheLooks(t *testing.T) {
|
||||
gaveUp := time.Date(2026, 10, 10, 21, 4, 0, 0, time.UTC)
|
||||
now := gaveUp.Add(20 * time.Second)
|
||||
store := conditions.NewInMemory()
|
||||
k := conditions.NewKeeper(t.Context(), conditions.Options{Store: store, History: store,
|
||||
Teller: &conditions.Told{}, Now: func() time.Time { return now }})
|
||||
t.Cleanup(func() { k.Close(t.Context()) })
|
||||
|
||||
const key = "bus.EVENTS.media_sonarr.max-deliveries"
|
||||
held := map[string]int{"EVENTS.media_sonarr": 1}
|
||||
newest := map[string]time.Time{"EVENTS.media_sonarr": gaveUp}
|
||||
advisory := link.Advisory{Kind: link.AdvisoryMaxDeliveries, ID: "EVENTS.media_sonarr", Stream: "EVENTS",
|
||||
Consumer: "media_sonarr", Said: "sonarr on media handed message 7 over 5 times and gave up on it",
|
||||
First: gaveUp, Last: gaveUp, Count: 1}
|
||||
look := func() conditions.Condition {
|
||||
t.Helper()
|
||||
f := &signalFacts{now: now, host: "novox", advisories: []link.Advisory{advisory},
|
||||
deadLetters: held, deadLettersNewest: newest}
|
||||
if err := k.Reconcile(t.Context(), "S9", watchAdvisories(f)); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
c, found, err := conditions.ReadOne(t.Context(), store, key)
|
||||
if err != nil || !found {
|
||||
t.Fatalf("%s: found %v, %v", key, found, err)
|
||||
}
|
||||
if !strings.Contains(c.Summary, "dead-letters verb") {
|
||||
t.Fatalf("the summary is not the dead-letter row's: %q", c.Summary)
|
||||
}
|
||||
return c
|
||||
}
|
||||
|
||||
var c conditions.Condition
|
||||
for range 5 {
|
||||
c = look()
|
||||
now = now.Add(30 * time.Second)
|
||||
}
|
||||
if c.Observations != 1 || len(c.Evidence) != 1 || !c.LastObserved.Equal(gaveUp) {
|
||||
t.Fatalf("one message given up on, looked at five times, reads as observed %d time(s), last %s, "+
|
||||
"with %d evidence lines: %+v", c.Observations, c.LastObserved, len(c.Evidence), c.Evidence)
|
||||
}
|
||||
|
||||
// The consumer gives up on a second message between two looks: two given up on, one more line.
|
||||
again := now.Add(-10 * time.Second)
|
||||
held["EVENTS.media_sonarr"], newest["EVENTS.media_sonarr"] = 2, again
|
||||
c = look()
|
||||
if c.Observations != 2 || len(c.Evidence) != 2 || !c.LastObserved.Equal(again) {
|
||||
t.Fatalf("two given up on read as observed %d time(s), last %s, evidence %+v", c.Observations,
|
||||
c.LastObserved, c.Evidence)
|
||||
}
|
||||
now = now.Add(30 * time.Second)
|
||||
if c = look(); c.Observations != 2 || len(c.Evidence) != 2 {
|
||||
t.Fatalf("a look with nothing new counted: observed %d time(s), evidence %+v", c.Observations, c.Evidence)
|
||||
}
|
||||
}
|
||||
|
||||
// The advisory still says the max-deliveries it alone knows: a message given up on that could not be
|
||||
// kept, under a key of its own (issue 330), which issue 440's change leaves as it was.
|
||||
func TestAMessageThatCouldNotBeKeptIsStillSaidFromTheAdvisory(t *testing.T) {
|
||||
at := time.Date(2026, 10, 10, 21, 4, 0, 0, time.UTC)
|
||||
f := &signalFacts{now: at, host: "novox", advisories: []link.Advisory{{Kind: link.AdvisoryMaxDeliveries,
|
||||
ID: "EVENTS.media_sonarr", Stream: "EVENTS", Consumer: "media_sonarr", Token: link.AdvisoryNotKept,
|
||||
Said: "sonarr on media gave up on message 7, and it could not be kept", First: at, Last: at, Count: 1}}}
|
||||
said := watchAdvisories(f)
|
||||
if len(said) != 1 || said[0].Key() != "bus.EVENTS.media_sonarr.not-kept" {
|
||||
t.Fatalf("%+v", said)
|
||||
}
|
||||
}
|
||||
|
||||
// A max-deliveries advisory without a token names a consumer's dead-letter key, which only DEAD_LETTERS
|
||||
// says (novox/hq issues 330 and 440): with nothing held, the advisory alone raises nothing.
|
||||
func TestAMaxDeliveriesAdvisoryAloneRaisesNothing(t *testing.T) {
|
||||
at := time.Date(2026, 10, 10, 21, 4, 0, 0, time.UTC)
|
||||
f := &signalFacts{now: at, host: "novox", advisories: []link.Advisory{{Kind: link.AdvisoryMaxDeliveries,
|
||||
ID: "EVENTS.media_sonarr", Stream: "EVENTS", Consumer: "media_sonarr",
|
||||
Said: "sonarr on media handed message 7 over 5 times and gave up on it", First: at, Last: at, Count: 1}}}
|
||||
if said := watchAdvisories(f); len(said) != 0 {
|
||||
t.Fatalf("said %+v", said)
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,118 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"sort"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/conditions"
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
)
|
||||
|
||||
// kindApplyFailing is S21's kind: a machine whose declarations have been refused, or applied only in part,
|
||||
// for longer than one apply interval (novox/hq issue 233).
|
||||
const kindApplyFailing = "apply-failing"
|
||||
|
||||
// applyEvery is how often a node-engine applies what it was last told when nothing new arrives: its
|
||||
// ReconcileEvery. A failure still there after one more of them is not one the next apply clears.
|
||||
const applyEvery = 5 * time.Minute
|
||||
|
||||
// packageManagerKey is how a node-engine names a package manager that does not answer among what failed
|
||||
// (mesh-host's probe.go): "the package manager (pacman)".
|
||||
const packageManagerKey = "the package manager ("
|
||||
|
||||
// watchApplyFailing is S21: **a machine that does not apply what it was sent is said by the mesh, not only
|
||||
// to someone who asks for `status`** (novox/hq issue 233, issue 187's family). A workstation refused every
|
||||
// declaration for an hour and a half because its package manager did not answer, and the mesh's only word
|
||||
// on it was a line in `status`. Raised once the machine's first report of this failure is older than one apply
|
||||
// interval **while the machine is heard** — judged by time, not by how many reports said it: a node-engine
|
||||
// says a re-apply only when how it went changed, so the same failure is one report however long it lasts.
|
||||
// Names the refusal's or the failure's words; cleared by the clean apply the node-engine then says. Not while
|
||||
// the machine is silent, asleep or not known: S1 says silent, and asleep is not lost.
|
||||
func watchApplyFailing(f *signalFacts) []conditions.Observation {
|
||||
heard := map[string]bool{}
|
||||
for _, m := range f.machines {
|
||||
if !m.asleep() && !m.lastHeard.IsZero() && f.now.Sub(m.lastHeard) <= heartbeatBound(m.every) {
|
||||
heard[m.name] = true
|
||||
}
|
||||
}
|
||||
var out []conditions.Observation
|
||||
for _, d := range f.doing {
|
||||
if !d.Wrong() || d.Since == nil || f.now.Sub(*d.Since) <= applyEvery || !heard[d.Node] {
|
||||
continue
|
||||
}
|
||||
out = append(out, applyFailing(d, f.now))
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// applyFailing is one machine's S21 condition.
|
||||
func applyFailing(d inventory.Doing, now time.Time) conditions.Observation {
|
||||
m := d.Node
|
||||
since := d.Since.UTC().Format("2006-01-02 15:04 MST")
|
||||
o := conditions.Observation{Scope: conditions.ScopeMachine, ID: m, Kind: kindApplyFailing, Machine: m,
|
||||
Severity: conditions.Warning, Said: doingWords(d),
|
||||
Resolved: m + " applies what it is sent again"}
|
||||
how := "refused its declaration whole"
|
||||
if d.Outcome != inventory.OutcomeRefused {
|
||||
how = "applied its declaration only in part"
|
||||
}
|
||||
o.Summary = fmt.Sprintf("%s has %s since %s (bound %s): %s", m, how, since, ago(applyEvery), failedNames(d))
|
||||
o.Headline = m + " is not applying its update"
|
||||
o.Explanation = fmt.Sprintf("%s has %s for %s, and trying again has not helped. The details say what fails.",
|
||||
m, plainHow(d), humanDuration(now.Sub(*d.Since)))
|
||||
if tool := unansweringTool(d); tool != "" {
|
||||
o.Summary = fmt.Sprintf("%s: %s does not answer, so no package reaches it; everything else it was sent "+
|
||||
"is applied, since %s (bound %s)", m, tool, since, ago(applyEvery))
|
||||
o.Headline = fmt.Sprintf("%s cannot install packages", m)
|
||||
o.Explanation = fmt.Sprintf("The package manager on %s (%s) has not answered for %s, so no package reaches "+
|
||||
"it. Everything else is still applied, so an update that repairs it can land; if none does, it needs a "+
|
||||
"look on the machine.", m, tool, humanDuration(now.Sub(*d.Since)))
|
||||
}
|
||||
return o
|
||||
}
|
||||
|
||||
// plainHow is how a machine failed, as the operator reads it.
|
||||
func plainHow(d inventory.Doing) string {
|
||||
if d.Outcome == inventory.OutcomeRefused {
|
||||
return "refused every update"
|
||||
}
|
||||
return "applied its updates only in part"
|
||||
}
|
||||
|
||||
// unansweringTool is the package manager a machine said does not answer, or "".
|
||||
func unansweringTool(d inventory.Doing) string {
|
||||
for _, r := range d.Failed {
|
||||
if rest, ok := strings.CutPrefix(r.ID, packageManagerKey); ok {
|
||||
return strings.TrimSuffix(rest, ")")
|
||||
}
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
// failedNames is what failed, by name: the refusal, or the failed resources' ids.
|
||||
func failedNames(d inventory.Doing) string {
|
||||
if d.Outcome == inventory.OutcomeRefused {
|
||||
return "refused"
|
||||
}
|
||||
ids := make([]string, 0, len(d.Failed))
|
||||
for _, r := range d.Failed {
|
||||
ids = append(ids, r.ID)
|
||||
}
|
||||
sort.Strings(ids)
|
||||
return "failed " + strings.Join(ids, ", ")
|
||||
}
|
||||
|
||||
// doingWords is the machine's own words on what failed: the evidence, kept inside the mesh.
|
||||
func doingWords(d inventory.Doing) string {
|
||||
if d.Outcome == inventory.OutcomeRefused {
|
||||
return "refused: " + oneLine(d.Refused)
|
||||
}
|
||||
var parts []string
|
||||
for _, r := range d.Failed {
|
||||
parts = append(parts, r.ID+": "+oneLine(r.Error))
|
||||
}
|
||||
sort.Strings(parts)
|
||||
return strings.Join(parts, "; ")
|
||||
}
|
||||
@@ -0,0 +1,123 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/conditions"
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
)
|
||||
|
||||
// unansweringPackageManager is anchor's last report as the workstation's read on 2026-10-04, once its
|
||||
// node-engine applies the rest (novox/hq issue 233): the package failed and the package manager did not answer,
|
||||
// the same failure on times reports since for before now.
|
||||
func unansweringPackageManager(now time.Time, forHowLong time.Duration, times int) inventory.Doing {
|
||||
since := now.Add(-forHowLong)
|
||||
return inventory.Doing{Node: "anchor", Outcome: inventory.OutcomeFailed, At: now.Add(-time.Second),
|
||||
Since: &since, Times: times, Applied: 41, Failed: []inventory.FailedResource{
|
||||
{ID: "apply", Error: `applying "pacman.base": nothing can be said about "base": this is the arch host and ` +
|
||||
"pacman does not answer here. Either this machine is not Arch, or its package database is broken: " +
|
||||
"pacman exited 1: error: config file /etc/pacman.conf could not be read: No such file or directory"},
|
||||
{ID: "the package manager (pacman)", Error: "pacman does not answer here, so every package in this " +
|
||||
"declaration fails and the rest of it is applied (novox/hq issue 233): pacman exited 1: error: config " +
|
||||
"file /etc/pacman.conf could not be read: No such file or directory"}}}
|
||||
}
|
||||
|
||||
// **A machine whose package manager does not answer is raised by the mesh itself, naming the tool and the
|
||||
// probe's words** (novox/hq issue 233): the words in the evidence, the path kept out of the summary.
|
||||
func TestAPackageManagerThatDoesNotAnswerIsRaisedNamingItsWords(t *testing.T) {
|
||||
now := time.Date(2026, 10, 4, 14, 0, 0, 0, time.UTC)
|
||||
f := calm(now)
|
||||
f.doing = []inventory.Doing{unansweringPackageManager(now, 90*time.Minute, 18)}
|
||||
got := watchApplyFailing(f)
|
||||
if len(got) != 1 {
|
||||
t.Fatalf("raised %d conditions, want one: %+v", len(got), got)
|
||||
}
|
||||
o := got[0]
|
||||
if o.Key() != "machine.anchor.apply-failing" || o.Machine != "anchor" {
|
||||
t.Errorf("the condition is not the machine's: %s", o.Key())
|
||||
}
|
||||
if !strings.Contains(o.Summary, "pacman does not answer") || !strings.Contains(o.Summary, "since 2026-10-04 12:30") {
|
||||
t.Errorf("the summary does not name the tool and since when: %s", o.Summary)
|
||||
}
|
||||
if strings.Contains(o.Summary, "/etc/") {
|
||||
t.Errorf("the summary carries a path, which belongs in the evidence: %s", o.Summary)
|
||||
}
|
||||
if !strings.Contains(o.Said, "could not be read") {
|
||||
t.Errorf("the evidence does not carry the probe's words: %s", o.Said)
|
||||
}
|
||||
if !strings.Contains(o.Headline, "cannot install packages") || o.Explanation == "" || o.Resolved == "" {
|
||||
t.Errorf("the plain words do not say it: %+v", o)
|
||||
}
|
||||
}
|
||||
|
||||
// **A whole refusal is raised too**, with the node-engine's words: what the workstation's report said before the
|
||||
// node-engine applied the rest.
|
||||
func TestARefusalThatGoesOnIsRaised(t *testing.T) {
|
||||
now := time.Date(2026, 10, 4, 14, 0, 0, 0, time.UTC)
|
||||
since := now.Add(-time.Hour)
|
||||
f := calm(now)
|
||||
f.doing = []inventory.Doing{{Node: "anchor", Outcome: inventory.OutcomeRefused, Since: &since, Times: 12,
|
||||
Refused: "this is the arch host and pacman does not answer here", At: now.Add(-time.Minute)}}
|
||||
got := watchApplyFailing(f)
|
||||
if len(got) != 1 || !strings.Contains(got[0].Summary, "refused its declaration whole") ||
|
||||
!strings.Contains(got[0].Said, "pacman does not answer") {
|
||||
t.Fatalf("a refusal that went on for an hour was not raised with its words: %+v", got)
|
||||
}
|
||||
}
|
||||
|
||||
// **Judged by time while the machine is heard, not by how many reports said it** (review of novox/hq issue 233):
|
||||
// a node-engine says the same failure once, so one report an apply interval old is a fault that goes on; one
|
||||
// younger is not yet; and a silent or sleeping machine is S1's.
|
||||
func TestOneReportOlderThanAnApplyIsRaisedAndAQuietMachineIsNot(t *testing.T) {
|
||||
now := time.Date(2026, 10, 4, 14, 0, 0, 0, time.UTC)
|
||||
f := calm(now)
|
||||
f.doing = []inventory.Doing{unansweringPackageManager(now, 6*time.Minute, 1)}
|
||||
if got := watchApplyFailing(f); len(got) != 1 {
|
||||
t.Errorf("one report of a failure six minutes old was not raised: %+v", got)
|
||||
}
|
||||
f.doing = []inventory.Doing{unansweringPackageManager(now, 4*time.Minute, 1)}
|
||||
if got := watchApplyFailing(f); len(got) != 0 {
|
||||
t.Errorf("a failure four minutes old was raised before one apply could clear it: %+v", got)
|
||||
}
|
||||
f.doing = []inventory.Doing{unansweringPackageManager(now, time.Hour, 1)}
|
||||
f.machines[0].lastHeard = now.Add(-time.Hour)
|
||||
if got := watchApplyFailing(f); len(got) != 0 {
|
||||
t.Errorf("a silent machine was raised for its last report: %+v", got)
|
||||
}
|
||||
f = calm(now)
|
||||
f.doing = []inventory.Doing{unansweringPackageManager(now, time.Hour, 1)}
|
||||
f.doing[0].Node = "a-machine-the-mesh-does-not-know"
|
||||
if got := watchApplyFailing(f); len(got) != 0 {
|
||||
t.Errorf("a machine not heard of was raised: %+v", got)
|
||||
}
|
||||
}
|
||||
|
||||
// **A failed re-apply followed by a clean one clears S21** (review of novox/hq issue 233): the node-engine says
|
||||
// the clean re-apply, the store keeps it as applied with no failure since, and the condition the failure raised
|
||||
// is cleared through the keeper on the next tick.
|
||||
func TestACleanReapplyAfterAFailedOneClearsTheCondition(t *testing.T) {
|
||||
now := time.Date(2026, 10, 4, 14, 0, 0, 0, time.UTC)
|
||||
store := conditions.NewInMemory()
|
||||
k := conditions.NewKeeper(t.Context(), conditions.Options{Store: store, History: store,
|
||||
Teller: &conditions.Told{}, Now: func() time.Time { return now }})
|
||||
defer k.Close(context.Background())
|
||||
w := &watchdogs{keeper: k, started: now.Add(-time.Hour)}
|
||||
|
||||
failing := calm(now)
|
||||
failing.doing = []inventory.Doing{unansweringPackageManager(now, 20*time.Minute, 1)}
|
||||
w.see(t.Context(), failing)
|
||||
open, err := k.Open(t.Context())
|
||||
if err != nil || len(open) != 1 || open[0].Kind != kindApplyFailing {
|
||||
t.Fatalf("the failed re-apply raised %+v (%v), want apply-failing", open, err)
|
||||
}
|
||||
|
||||
clean := calm(now.Add(5 * time.Minute))
|
||||
clean.doing = nil // the clean re-apply recorded: NotDoingWhatTheyWereTold no longer lists the machine
|
||||
w.see(t.Context(), clean)
|
||||
if open, _ := k.Open(t.Context()); len(open) != 0 {
|
||||
t.Fatalf("the condition stayed open after the clean re-apply: %+v", open)
|
||||
}
|
||||
}
|
||||
@@ -213,6 +213,8 @@ type asker struct {
|
||||
|
||||
saidNoRouter bool
|
||||
saidNoGrant bool
|
||||
// saidGrantCaveat is whether a grant held with a caveat was said, so it is said once.
|
||||
saidGrantCaveat bool
|
||||
|
||||
mu sync.Mutex
|
||||
nudged chan struct{}
|
||||
@@ -317,6 +319,13 @@ func (a *asker) reconcile(ctx context.Context) error {
|
||||
}
|
||||
return a.sayUnasked(ctx, unasked, "the bus does not hold the controller's grant to ask yet: "+why)
|
||||
}
|
||||
if why != "" && !a.saidGrantCaveat {
|
||||
// Held, with a caveat worth one line (an older bus module cannot confirm the reload).
|
||||
a.logf("the controller asks: %s", why)
|
||||
a.saidGrantCaveat = true
|
||||
} else if why == "" {
|
||||
a.saidGrantCaveat = false
|
||||
}
|
||||
a.saidNoGrant = false
|
||||
}
|
||||
channels := ""
|
||||
|
||||
@@ -12,6 +12,7 @@ import (
|
||||
|
||||
"git.novox.be/novox/mesh-sdk/go/asks"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/broker"
|
||||
"github.com/novox/mesh-controller/internal/conditions"
|
||||
"github.com/novox/mesh-controller/internal/link"
|
||||
)
|
||||
@@ -808,3 +809,207 @@ func TestARefusalIsAskedAgainAndTheUndeliveredConditionClearsOnceTaken(t *testin
|
||||
t.Errorf("the explanation says its verdict twice: %q", e)
|
||||
}
|
||||
}
|
||||
|
||||
// hq issue 353, the review: the bus holds the controller's grant to ask only when both facts hold — the mesh
|
||||
// composes the controller's own grant, and the bus's module says it is in force on the running server — and
|
||||
// each fact not known is not held, said with why.
|
||||
func TestTheGrantIsHeldOnlyWhenComposedAndInForceOnTheBus(t *testing.T) {
|
||||
yes := func(context.Context) (bool, string, error) { return true, "", nil }
|
||||
no := func(why string) grantJudge {
|
||||
return func(context.Context) (bool, string, error) { return false, why, nil }
|
||||
}
|
||||
broken := func(context.Context) (bool, string, error) { return false, "", errors.New("the store is away") }
|
||||
for _, c := range []struct {
|
||||
name string
|
||||
composed, inForce grantJudge
|
||||
held bool
|
||||
says string
|
||||
}{
|
||||
{"composed and in force", yes, yes, true, ""},
|
||||
{"not composed", no("no router is assigned"), yes, false, "no router is assigned"},
|
||||
{"composed, written, not reloaded", yes, no("the server has not reloaded"), false, "has not reloaded"},
|
||||
{"the composition unknown", broken, yes, false, "could not be worked out: the store is away"},
|
||||
{"the bus unknown", yes, broken, false, "could not be worked out: the store is away"},
|
||||
{"nothing judges the bus", yes, nil, false, "not judged"},
|
||||
} {
|
||||
held, why, err := grantHeldBy(c.composed, c.inForce, time.Now)(context.Background())
|
||||
if err != nil || held != c.held || !strings.Contains(why, c.says) {
|
||||
t.Errorf("%s: held %v (%q, %v)", c.name, held, why, err)
|
||||
}
|
||||
}
|
||||
// Remembered for grantLookEvery, then judged again.
|
||||
now := time.Date(2026, 10, 9, 18, 0, 0, 0, time.UTC)
|
||||
inForce := false
|
||||
judge := grantHeldBy(yes, func(context.Context) (bool, string, error) { return inForce, "not yet", nil },
|
||||
func() time.Time { return now })
|
||||
if held, _, _ := judge(context.Background()); held {
|
||||
t.Fatal("held before the bus enforces it")
|
||||
}
|
||||
inForce = true
|
||||
if held, _, _ := judge(context.Background()); held {
|
||||
t.Error("judged again inside grantLookEvery")
|
||||
}
|
||||
now = now.Add(grantLookEvery)
|
||||
if held, _, _ := judge(context.Background()); !held {
|
||||
t.Error("not judged again after grantLookEvery")
|
||||
}
|
||||
}
|
||||
|
||||
// The controller's own grant, as composed: present while a router that takes asks is assigned, absent
|
||||
// otherwise — whatever else in the user list changes.
|
||||
func TestTheControllersOwnGrantToAskIsReadFromTheComposition(t *testing.T) {
|
||||
router := broker.Declared{Module: "messenger", Holds: []broker.Seat{{Name: broker.AsksSeat, Scope: "mesh",
|
||||
Accepts: []string{"ask", "cancel"}, Emits: []string{"decided"}, ByCaller: []string{"ask", "cancel", "decided"}}}}
|
||||
other := broker.Declared{Module: "dunst"}
|
||||
with := broker.Records{Nodes: []string{"anchor"}, Assigned: map[string][]broker.Declared{"anchor": {router, other}}}
|
||||
without := broker.Records{Nodes: []string{"anchor"}, Assigned: map[string][]broker.Declared{"anchor": {other}}}
|
||||
if may, err := controllerMayAsk(with); err != nil || !may {
|
||||
t.Errorf("with a router assigned: %v %v", may, err)
|
||||
}
|
||||
if may, err := controllerMayAsk(without); err != nil || may {
|
||||
t.Errorf("with no router assigned: %v %v", may, err)
|
||||
}
|
||||
}
|
||||
|
||||
// The bus module's answer, with the record's word on the list sent as the check only where the answer does
|
||||
// not settle it (reviews 22 and 31 of PR 188); each way it is not held names its own remedy.
|
||||
func TestTheBusModulesAnswerNamesTheRemedyForEachCase(t *testing.T) {
|
||||
const (
|
||||
reloaded = `{"allowed":true,"in_force":true,"file_written":"2026-10-09T15:55:56Z","server_loaded":"2026-10-09T15:56:05Z"}`
|
||||
notLoaded = `{"allowed":true,"in_force":false,"why":"the user list on the machine allows it, and the server has not reloaded since it was written","file_written":"2026-10-09T15:55:56Z","server_loaded":"2026-10-09T15:50:00Z"}`
|
||||
noVarz = `{"allowed":true,"in_force":false,"why":"the server's last configuration load could not be read: refused"}`
|
||||
noStat = `{"allowed":true,"in_force":false,"why":"when the bus's user list was written could not be read inside mesh-broker-nats: exit 1"}`
|
||||
notAllowed = `{"allowed":false,"in_force":false,"why":"the user list on the machine does not allow it"}`
|
||||
)
|
||||
current := busListState{Machine: "anchor"}
|
||||
behind := busListState{Machine: "anchor", Behind: true}
|
||||
stepped := busListState{Machine: "anchor", Behind: true, BusStep: "sending anchor would replace the bus; `bus upgrade --why …`"}
|
||||
uncomposed := busListState{Machine: "anchor", Behind: true, Uncomposed: errors.New("module foo requires a provision nobody provides")}
|
||||
for _, c := range []struct {
|
||||
name, answer string
|
||||
askErr error
|
||||
list busListState
|
||||
listErr error
|
||||
held bool
|
||||
says, not string
|
||||
}{
|
||||
{"in force", reloaded, nil, behind, nil, true, "", "push"},
|
||||
{"written, not reloaded", notLoaded, nil, current, nil, false, "within about 5 s", "push"},
|
||||
{"in force not known: varz", noVarz, nil, current, nil, false, "is not known: the server's last configuration load", "wait"},
|
||||
{"in force not known: stat", noStat, nil, current, nil, false, "is not known: when the bus's user list was written", "wait"},
|
||||
{"not allowed, list behind", notAllowed, nil, behind, nil, false, "`push anchor` carries it", "5 s"},
|
||||
{"not allowed, bus step pending", notAllowed, nil, stepped, nil, false, "`bus upgrade", "`push anchor`"},
|
||||
{"not allowed, list uncomposed", notAllowed, nil, uncomposed, nil, false, "`plan anchor`", "`push anchor`"},
|
||||
{"older module, allowed, list current", `{"allowed":true}`, nil, current, nil, true, "not confirmed", "push"},
|
||||
{"older module, allowed, list behind", `{"allowed":true}`, nil, behind, nil, true, "not confirmed", "push"},
|
||||
{"older module, allowed, list unknown", `{"allowed":true}`, nil, current, errors.New("the store is away"), true, "`bus upgrade`", "push"},
|
||||
{"older module, not allowed, list behind", `{"allowed":false}`, nil, behind, nil, false, "`push anchor` carries it", "5 s"},
|
||||
{"module cannot answer, list current", "", errors.New("no responders"), current, nil, true, "could not answer", "push"},
|
||||
{"module cannot answer, list behind", "", errors.New("no responders"), behind, nil, false, "`push anchor` carries it", ""},
|
||||
{"module cannot answer, list unknown", "", errors.New("no responders"), current, errors.New("the store is away"), false, "could not be worked out", ""},
|
||||
{"answer unreadable, list behind", `not json`, nil, behind, nil, false, "could not be read", ""},
|
||||
} {
|
||||
judge := busGrantBy(
|
||||
func(context.Context) (string, json.RawMessage, error) {
|
||||
return "anchor", json.RawMessage(c.answer), c.askErr
|
||||
},
|
||||
func(context.Context) (busListState, error) { return c.list, c.listErr })
|
||||
held, why, _ := judgeGrantOnce(judge)
|
||||
if held != c.held || !strings.Contains(why, c.says) || (c.not != "" && strings.Contains(why, c.not)) {
|
||||
t.Errorf("%s: held %v (%q)", c.name, held, why)
|
||||
}
|
||||
}
|
||||
none := busGrantBy(func(context.Context) (string, json.RawMessage, error) { return "", nil, nil }, nil)
|
||||
if held, why, _ := judgeGrantOnce(none); held || !strings.Contains(why, "no module holds the bus") {
|
||||
t.Errorf("no bus: held %v (%q)", held, why)
|
||||
}
|
||||
}
|
||||
|
||||
// judgeGrantOnce is the whole judgement with the composed grant held, as the asker makes it.
|
||||
func judgeGrantOnce(bus grantJudge) (bool, string, error) {
|
||||
yes := func(context.Context) (bool, string, error) { return true, "", nil }
|
||||
return grantHeldBy(yes, bus, time.Now)(context.Background())
|
||||
}
|
||||
|
||||
// The orders reviews 22 and 31 of PR 188 found: this controller live before the bus module that answers
|
||||
// in_force, with the bus's machine behind on its list — and, after mesh-catalog #166 merged, unpushable until a
|
||||
// person's bus upgrade. An older module that allows the ask asks (once, with the caveat said); a new module that
|
||||
// has not reloaded names the wait, not a push; one that cannot say whether it reloaded names what is not known.
|
||||
func TestAnOlderBusModuleNeitherSilencesTheAsksNorNamesTheWrongRemedy(t *testing.T) {
|
||||
for _, c := range []struct {
|
||||
name, answer string
|
||||
list busListState
|
||||
asks bool
|
||||
says, not string
|
||||
}{
|
||||
{"older module, list current", `{"allowed":true}`, busListState{Machine: "anchor"}, true, "not confirmed", ""},
|
||||
{"older module, list behind, bus step pending", `{"allowed":true}`,
|
||||
busListState{Machine: "anchor", Behind: true, BusStep: "a planned step"}, true, "not confirmed", ""},
|
||||
{"new module, not reloaded",
|
||||
`{"allowed":true,"in_force":false,"why":"not reloaded","file_written":"2026-10-09T15:55:56Z","server_loaded":"2026-10-09T15:50:00Z"}`,
|
||||
busListState{Machine: "anchor"}, false, "within about 5 s", "push"},
|
||||
{"new module, reload not known", `{"allowed":true,"in_force":false,"why":"the server's last configuration load could not be read: refused"}`,
|
||||
busListState{Machine: "anchor"}, false, "is not known", "wait"},
|
||||
} {
|
||||
t.Run(c.name, func(t *testing.T) {
|
||||
r := newAskerRig(t)
|
||||
var said []string
|
||||
r.a.logf = func(f string, a ...any) { said = append(said, fmt.Sprintf(f, a...)) }
|
||||
var raised [][]conditions.Observation
|
||||
r.a.raise = func(_ context.Context, obs []conditions.Observation) error {
|
||||
raised = append(raised, obs)
|
||||
return nil
|
||||
}
|
||||
yes := func(context.Context) (bool, string, error) { return true, "", nil }
|
||||
r.a.grantHeld = grantHeldBy(yes, busGrantBy(
|
||||
func(context.Context) (string, json.RawMessage, error) {
|
||||
return "anchor", json.RawMessage(c.answer), nil
|
||||
},
|
||||
func(context.Context) (busListState, error) { return c.list, nil }),
|
||||
func() time.Time { return r.now })
|
||||
r.open = []conditions.Condition{heldCondition()}
|
||||
_ = r.a.reconcile(context.Background())
|
||||
_ = r.a.reconcile(context.Background())
|
||||
sent := r.asksSent(t)
|
||||
if c.asks {
|
||||
if len(sent) != 1 || sent[0].About != heldCondition().Key {
|
||||
t.Fatalf("not asked: %+v", sent)
|
||||
}
|
||||
n := 0
|
||||
for _, s := range said {
|
||||
if strings.Contains(s, c.says) {
|
||||
n++
|
||||
}
|
||||
}
|
||||
if n != 1 {
|
||||
t.Errorf("the caveat said %d times: %q", n, said)
|
||||
}
|
||||
return
|
||||
}
|
||||
if len(sent) != 0 {
|
||||
t.Fatalf("asked while the bus does not hold the grant: %+v", sent)
|
||||
}
|
||||
if len(raised) == 0 || len(raised[len(raised)-1]) != 1 ||
|
||||
raised[len(raised)-1][0].Kind != "asks-undelivered" {
|
||||
t.Fatalf("not said as undelivered: %+v", raised)
|
||||
}
|
||||
summary := raised[len(raised)-1][0].Summary
|
||||
if !strings.Contains(summary, c.says) || (c.not != "" && strings.Contains(summary, c.not)) {
|
||||
t.Errorf("the condition names the wrong remedy: %q", summary)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// The serving asker is wired to the real judgement: with records and a bus it cannot read, the grant is not
|
||||
// held, and so nothing is asked (a stub saying yes, or no judgement at all, would ask).
|
||||
func TestTheServingAskerJudgesTheGrantForReal(t *testing.T) {
|
||||
a := servingAsker(&stores{}, nil, nil, nil)
|
||||
if a.grantHeld == nil {
|
||||
t.Fatal("the serving asker does not judge the bus's grant")
|
||||
}
|
||||
held, why, err := a.grantHeld(context.Background())
|
||||
if err != nil || held || !strings.Contains(why, "could not be worked out") {
|
||||
t.Errorf("held %v (%q, %v) with nothing to read", held, why, err)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -235,12 +235,27 @@ func routerHereIn(inv *inventory.Inventory) func(ctx context.Context) (bool, err
|
||||
}
|
||||
}
|
||||
|
||||
// grantHeldIn says whether the bus holds the controller's grant to ask (novox/hq issue 353): the user list the
|
||||
// machine holding the bus was last sent is the one the mesh composes now (brokerBehind, the same judgement a
|
||||
// push makes to send that machine first). While it is behind, the controller's ask is refused by the bus,
|
||||
// whatever the record says of the router, so nothing is asked and the operator is told to push that machine.
|
||||
// Judged at most every grantLookEvery: composing the list resolves the bus's machine whole.
|
||||
func grantHeldIn(open *stores) func(ctx context.Context) (bool, string, error) {
|
||||
// grantHeldIn says whether the bus holds the controller's grant to ask (novox/hq issue 353), judged on the two
|
||||
// facts that make it so, and failing closed on each:
|
||||
//
|
||||
// 1. **composed**: the user list the mesh composes now grants the controller itself to publish its ask
|
||||
// (controllerMayAsk) — the controller's own grant, not whether any user of the list changed;
|
||||
// 2. **in force**: the bus's own module, on the machine holding the bus, says the user list there allows it
|
||||
// and the server reloaded after that list was written (the nats module's `nats_user_can`, `in_force`) — a
|
||||
// list sent is not a list the bus enforces until it reloads.
|
||||
//
|
||||
// Anything that cannot be worked out is not held, with why, so the conditions that need the operator are said
|
||||
// as undelivered rather than asked into a refusal.
|
||||
func grantHeldIn(open *stores, conn *nats.Conn) func(ctx context.Context) (bool, string, error) {
|
||||
return grantHeldBy(composedGrantIn(open), busGrantIn(open, conn), time.Now)
|
||||
}
|
||||
|
||||
// grantJudge is one of the two facts: whether it holds, and why not.
|
||||
type grantJudge func(ctx context.Context) (bool, string, error)
|
||||
|
||||
// grantHeldBy is the judgement over the two facts, remembered for grantLookEvery: composing the list resolves
|
||||
// the bus's machine whole, and asking the bus's module is a call.
|
||||
func grantHeldBy(composed, inForce grantJudge, now func() time.Time) func(ctx context.Context) (bool, string, error) {
|
||||
var mu sync.Mutex
|
||||
var at time.Time
|
||||
var held bool
|
||||
@@ -248,22 +263,251 @@ func grantHeldIn(open *stores) func(ctx context.Context) (bool, string, error) {
|
||||
return func(ctx context.Context) (bool, string, error) {
|
||||
mu.Lock()
|
||||
defer mu.Unlock()
|
||||
if !at.IsZero() && time.Since(at) < grantLookEvery {
|
||||
if !at.IsZero() && now().Sub(at) < grantLookEvery {
|
||||
return held, why, nil
|
||||
}
|
||||
machine, behind, err := brokerBehind(ctx, open, nil)
|
||||
held, why = judgeGrant(ctx, composed, inForce)
|
||||
at = now()
|
||||
return held, why, nil
|
||||
}
|
||||
}
|
||||
|
||||
// judgeGrant is held only when both facts hold; an error is a fact not known, never a yes. A fact that holds
|
||||
// with a caveat (a reload not confirmed) gives that caveat as the why of a yes.
|
||||
func judgeGrant(ctx context.Context, composed, inForce grantJudge) (bool, string) {
|
||||
var caveat []string
|
||||
for _, fact := range []struct {
|
||||
judge grantJudge
|
||||
what string
|
||||
}{{composed, "whether the mesh composes the controller a grant to ask"}, {inForce, "whether the bus enforces it"}} {
|
||||
if fact.judge == nil {
|
||||
return false, fact.what + " is not judged here"
|
||||
}
|
||||
ok, why, err := fact.judge(ctx)
|
||||
if err != nil {
|
||||
return false, fact.what + " could not be worked out: " + err.Error()
|
||||
}
|
||||
if !ok {
|
||||
return false, why
|
||||
}
|
||||
if why != "" {
|
||||
caveat = append(caveat, why)
|
||||
}
|
||||
}
|
||||
return true, strings.Join(caveat, "; ")
|
||||
}
|
||||
|
||||
// controllerMayAsk says whether the controller's own grant, as composed from these records, lets it publish its
|
||||
// ask (ADR 0259 §3: composed while a router that takes asks under its asker's name is assigned).
|
||||
func controllerMayAsk(records broker.Records) (bool, error) {
|
||||
users, err := broker.Users(records)
|
||||
if err != nil {
|
||||
return false, err
|
||||
}
|
||||
for _, u := range users {
|
||||
if u.Kind != broker.KindController {
|
||||
continue
|
||||
}
|
||||
perms, err := broker.PermissionsFor(u)
|
||||
if err != nil {
|
||||
return false, err
|
||||
}
|
||||
return broker.MayPublish(perms, asks.AskSubject(askerName)), nil
|
||||
}
|
||||
return false, errors.New("the composition holds no controller")
|
||||
}
|
||||
|
||||
// composedGrantIn is the first fact, from the mesh's records.
|
||||
func composedGrantIn(open *stores) grantJudge {
|
||||
return func(ctx context.Context) (bool, string, error) {
|
||||
if open == nil || open.inventory == nil {
|
||||
return false, "", errors.New("the mesh's records are not open")
|
||||
}
|
||||
records, err := open.inventory.BusRecords(ctx)
|
||||
if err != nil {
|
||||
return false, "", err
|
||||
}
|
||||
at, held, why = time.Now(), !behind, ""
|
||||
if behind {
|
||||
why = fmt.Sprintf("the bus's user list on %s is behind what the mesh composes, so the bus has not been "+
|
||||
"given the controller's grant to ask; `push %s` carries it", machine, machine)
|
||||
may, err := controllerMayAsk(records)
|
||||
if err != nil || may {
|
||||
return may, "", err
|
||||
}
|
||||
return held, why, nil
|
||||
return false, "the mesh composes the controller no grant to ask: no router that takes asks under its " +
|
||||
"asker's name is assigned", nil
|
||||
}
|
||||
}
|
||||
|
||||
// busGrantIn is the second fact, asked of the bus's own module on the machine holding the bus, with the check
|
||||
// main made before it (novox/hq issue 353, PR 186: is the user list sent to the bus's machine the one composed
|
||||
// now) kept for the cases the module's word does not settle.
|
||||
func busGrantIn(open *stores, conn *nats.Conn) grantJudge {
|
||||
ask := func(ctx context.Context) (string, json.RawMessage, error) {
|
||||
if open == nil || open.inventory == nil || conn == nil {
|
||||
return "", nil, errors.New("the mesh's records or the bus are not open")
|
||||
}
|
||||
holders, err := seatHolders(ctx, open.inventory)
|
||||
if err != nil {
|
||||
return "", nil, err
|
||||
}
|
||||
h, held := holders[theBrokerSeat]
|
||||
if !held || h.Node == "" || h.Module == "" {
|
||||
return "", nil, nil
|
||||
}
|
||||
a, err := link.AskModuleToolOn(ctx, conn, h.Module, busUserCanTool, h.Node, map[string]any{
|
||||
"user": broker.ControllerName, "action": "publish", "subject": asks.AskSubject(askerName)}, 15*time.Second)
|
||||
if err != nil {
|
||||
return h.Node, nil, err
|
||||
}
|
||||
if a.Error != "" {
|
||||
return h.Node, nil, errors.New(a.Error)
|
||||
}
|
||||
return h.Node, a.Result, nil
|
||||
}
|
||||
list := func(ctx context.Context) (busListState, error) {
|
||||
if open == nil || open.inventory == nil {
|
||||
return busListState{}, errors.New("the mesh's records are not open")
|
||||
}
|
||||
s, err := brokerListState(ctx, open, nil)
|
||||
if err != nil || s.Machine == "" || !s.Behind {
|
||||
return s, err
|
||||
}
|
||||
step, err := busHeld(ctx, open.inventory, []string{s.Machine})
|
||||
if err != nil {
|
||||
return busListState{}, err
|
||||
}
|
||||
s.BusStep = step[s.Machine]
|
||||
return s, nil
|
||||
}
|
||||
return busGrantBy(ask, list)
|
||||
}
|
||||
|
||||
// busListState is the user list on the bus's machine as the controller's record knows it: whether the list
|
||||
// sent there is behind the one composed now, why it could not be composed, and the bus step a send there waits
|
||||
// on (that machine cannot be pushed until a person's `bus upgrade`).
|
||||
type busListState struct {
|
||||
Machine string
|
||||
Behind bool
|
||||
Uncomposed error
|
||||
BusStep string
|
||||
}
|
||||
|
||||
// remedy is the one thing that sends the bus's machine the list composed now: the plan's own reason when it
|
||||
// cannot be composed, the bus upgrade while sends there wait on it, and otherwise a push of that machine.
|
||||
func (s busListState) remedy(node string) string {
|
||||
if s.Machine != "" {
|
||||
node = s.Machine
|
||||
}
|
||||
switch {
|
||||
case s.Uncomposed != nil:
|
||||
return fmt.Sprintf("the user list for %s cannot be composed (%v); `plan %s` says what to fix first",
|
||||
node, s.Uncomposed, node)
|
||||
case s.BusStep != "":
|
||||
return fmt.Sprintf("sends to %s wait on the bus's planned step, so a push will not carry it: %s", node, s.BusStep)
|
||||
}
|
||||
return fmt.Sprintf("`push %s` carries it", node)
|
||||
}
|
||||
|
||||
// busGrantBy judges the bus's word, and names for each way it is not held the one thing that makes it held:
|
||||
//
|
||||
// - **in force**: held;
|
||||
// - **allowed, from a module older than `in_force`**: held, with the caveat that the reload is not confirmed.
|
||||
// The file allows the publish, and the bus reloads within about 5 s of a change to it, so the worst case is
|
||||
// one ask refused in those seconds, which is asked again (issue 369). The list check is not consulted:
|
||||
// while a bus step is pending the bus's machine cannot be pushed, so any change to the composed list would
|
||||
// read as behind for good and silence every ask until a person's bus upgrade (the review of PR 188);
|
||||
// - **allowed, written, not reloaded** (the module gives both times): wait about 5 s;
|
||||
// - **allowed, in force not known** (the module could not read a time): what is not known, said;
|
||||
// - **not allowed, or the module cannot answer**: the list check decides — the remedy that sends the list
|
||||
// when it is behind (busListState.remedy), and, for a module that cannot answer, held while the list sent
|
||||
// is current, as main judged it.
|
||||
//
|
||||
// ask answers the machine holding the bus and its module's answer ("" when nothing holds the bus); list is the
|
||||
// record's word on the list sent to that machine.
|
||||
func busGrantBy(ask func(ctx context.Context) (string, json.RawMessage, error),
|
||||
list func(ctx context.Context) (busListState, error)) grantJudge {
|
||||
return func(ctx context.Context) (bool, string, error) {
|
||||
node, raw, askErr := ask(ctx)
|
||||
if askErr == nil && node == "" {
|
||||
return false, "no module holds the bus, so nothing says what it enforces", nil
|
||||
}
|
||||
var answer busAnswer
|
||||
if askErr == nil {
|
||||
if answer, askErr = readBusAnswer(raw); askErr != nil {
|
||||
askErr = fmt.Errorf("its answer could not be read: %w", askErr)
|
||||
}
|
||||
}
|
||||
if askErr != nil {
|
||||
if node == "" {
|
||||
node = "the bus's machine"
|
||||
}
|
||||
s, err := list(ctx)
|
||||
if err != nil {
|
||||
return false, "", fmt.Errorf("the bus module on %s could not answer (%v), and whether the list sent "+
|
||||
"there is the one composed now could not be worked out: %w", node, askErr, err)
|
||||
}
|
||||
if s.Behind {
|
||||
return false, fmt.Sprintf("the bus module on %s could not answer (%v), and the user list sent there is "+
|
||||
"behind what the mesh composes; %s", node, askErr, s.remedy(node)), nil
|
||||
}
|
||||
return true, fmt.Sprintf("the bus module on %s could not answer (%v); judged by the user list sent there, "+
|
||||
"which is the one composed now", node, askErr), nil
|
||||
}
|
||||
notAllowed := func(older string) (bool, string, error) {
|
||||
s, err := list(ctx)
|
||||
if err != nil {
|
||||
return false, "", fmt.Errorf("the user list on %s does not allow the controller to ask%s, and whether "+
|
||||
"the list sent there is the one composed now could not be worked out: %w", node, older, err)
|
||||
}
|
||||
if s.Behind {
|
||||
return false, fmt.Sprintf("the user list on %s does not allow the controller to ask%s: it is behind "+
|
||||
"what the mesh composes; %s", node, older, s.remedy(node)), nil
|
||||
}
|
||||
return false, fmt.Sprintf("the user list on %s does not allow the controller to ask%s, though the list "+
|
||||
"sent there is the one composed now; %s again", node, older, s.remedy(node)), nil
|
||||
}
|
||||
switch {
|
||||
case answer.InForce == nil && answer.Allowed:
|
||||
return true, fmt.Sprintf("the user list on %s allows the controller to ask, but its reload is not "+
|
||||
"confirmed: the bus module there is older than the answer whether a grant is in force, and the bus "+
|
||||
"upgrade (`bus upgrade`) carries one that confirms it", node), nil
|
||||
case answer.InForce == nil:
|
||||
return notAllowed(" (the bus module there is older than the answer whether a grant is in force)")
|
||||
case !answer.Allowed:
|
||||
return notAllowed("")
|
||||
case *answer.InForce:
|
||||
return true, "", nil
|
||||
case answer.FileWritten != "" && answer.ServerLoaded != "":
|
||||
return false, fmt.Sprintf("the bus on %s has the controller's grant to ask written (%s) but has not "+
|
||||
"reloaded since (last load %s); it reloads in place within about 5 s, so nothing is to be done but wait",
|
||||
node, answer.FileWritten, answer.ServerLoaded), nil
|
||||
}
|
||||
why := answer.Why
|
||||
if why == "" {
|
||||
why = "it gives no reason"
|
||||
}
|
||||
return false, fmt.Sprintf("the user list on %s allows the controller to ask, but whether the bus enforces it "+
|
||||
"is not known: %s", node, why), nil
|
||||
}
|
||||
}
|
||||
|
||||
// busUserCanTool is the bus module's answer to whether a user may do something, and whether it is in force.
|
||||
const busUserCanTool = "nats_user_can"
|
||||
|
||||
// busAnswer is the bus module's answer to busUserCanTool; InForce is nil from a module older than that field,
|
||||
// and FileWritten and ServerLoaded are given only when it could read both times (mesh-catalog's nats InForce).
|
||||
type busAnswer struct {
|
||||
Allowed bool `json:"allowed"`
|
||||
InForce *bool `json:"in_force"`
|
||||
Why string `json:"why"`
|
||||
FileWritten string `json:"file_written"`
|
||||
ServerLoaded string `json:"server_loaded"`
|
||||
}
|
||||
|
||||
func readBusAnswer(raw json.RawMessage) (busAnswer, error) {
|
||||
var answer busAnswer
|
||||
err := json.Unmarshal(raw, &answer)
|
||||
return answer, err
|
||||
}
|
||||
|
||||
// grantLookEvery is how often the bus's user list is judged against the one its machine was last sent.
|
||||
const grantLookEvery = 30 * time.Second
|
||||
|
||||
@@ -302,7 +546,19 @@ func startAsking(ctx context.Context, open *stores, server *link.Server, conn *n
|
||||
fmt.Printf("the operator cannot be asked: %v\n", err)
|
||||
return
|
||||
}
|
||||
a := &asker{
|
||||
a := servingAsker(open, conn, js, keeper)
|
||||
if err := server.Decides(a); err != nil {
|
||||
fmt.Printf("the operator's answers cannot be heard, so nothing is asked: %v\n", err)
|
||||
return
|
||||
}
|
||||
askerFrom = a
|
||||
go a.keep(ctx)
|
||||
}
|
||||
|
||||
// servingAsker is the serving controller's asker, wired to the mesh: what it reads, publishes, performs and
|
||||
// records, and the judgements it asks by — the bus's grant to ask among them (novox/hq issue 353).
|
||||
func servingAsker(open *stores, conn *nats.Conn, js jetstream.JetStream, keeper *conditions.Keeper) *asker {
|
||||
return &asker{
|
||||
open: keeper.Open,
|
||||
silence: func(ctx context.Context, key string, d time.Duration, by, why string) error {
|
||||
_, err := keeper.Silence(ctx, key, d, by, why)
|
||||
@@ -322,7 +578,7 @@ func startAsking(ctx context.Context, open *stores, server *link.Server, conn *n
|
||||
},
|
||||
routerRecord: routerRecordOf(conn, open.inventory),
|
||||
routerHere: routerHereIn(open.inventory),
|
||||
grantHeld: grantHeldIn(open),
|
||||
grantHeld: grantHeldIn(open, conn),
|
||||
channels: channelsIn(open.inventory),
|
||||
raise: func(ctx context.Context, obs []conditions.Observation) error {
|
||||
return keeper.Reconcile(ctx, sourceAsker, obs)
|
||||
@@ -330,10 +586,4 @@ func startAsking(ctx context.Context, open *stores, server *link.Server, conn *n
|
||||
now: time.Now,
|
||||
logf: func(format string, args ...any) { fmt.Printf(format+"\n", args...) },
|
||||
}
|
||||
if err := server.Decides(a); err != nil {
|
||||
fmt.Printf("the operator's answers cannot be heard, so nothing is asked: %v\n", err)
|
||||
return
|
||||
}
|
||||
askerFrom = a
|
||||
go a.keep(ctx)
|
||||
}
|
||||
|
||||
+330
-17
@@ -37,6 +37,11 @@ import (
|
||||
// own commit, the newest first, one walk each, until one is delivered; the older ones are then answered
|
||||
// by that one.
|
||||
//
|
||||
// **A merge waits only for a batch it shares something with** (novox/hq ADR 0304 decision 1, ADR 0306 decisions
|
||||
// 2 and 3, issue 525): it joins a batch it is related to, and one that is related to none and whose delivery
|
||||
// group has no member still to merge is a batch whose window is closed at once (batchToJoin). Walks stay one at
|
||||
// a time: such a batch is cut when no walk is open, and queued behind the one that is otherwise.
|
||||
//
|
||||
// A merge on the controller's own path (a module whose walk waits for nobody's word) never shares a batch with
|
||||
// one that waits for mesh-delivery's: each kind has a batch of its own, an own-path batch is cut first and folds
|
||||
// no waiting catalogue walk, and a catalogue walk let go while another walk runs starts once it ended — so no
|
||||
@@ -173,6 +178,12 @@ func (f following) hearMerge(ctx context.Context, m link.SourceMoved, now time.T
|
||||
fmt.Printf("%s merged into %s (%.8s); nothing the mesh holds reads it\n", repository, m.Base, m.Commit)
|
||||
return nil
|
||||
}
|
||||
// **Its delivery group's word, before the plans are held** (ADR 0306 decision 2): a slow answer holds up no walk.
|
||||
own := ownPath(touches)
|
||||
waits, err := groupWait(ctx, inv, m, deliverySeatHeld(entries), own)
|
||||
if err != nil {
|
||||
return notNow(err)
|
||||
}
|
||||
release, err := inv.HoldPlans(ctx, true)
|
||||
if err != nil {
|
||||
return notNow(err)
|
||||
@@ -198,7 +209,6 @@ func (f following) hearMerge(ctx context.Context, m link.SourceMoved, now time.T
|
||||
// **A merge on the controller's own path never shares a batch with one that waits for the delivery's
|
||||
// word** (decided during the build, 2026-10-10): batched together, the catalogue's deliveries would start
|
||||
// with the controller's and skip their turn. Each kind has a batch of its own.
|
||||
own := ownPath(touches)
|
||||
if p, ok, err := answeredByALaterMerge(ctx, inv, heard, touches, own, deliverySeatHeld(entries)); err != nil {
|
||||
return notNow(err)
|
||||
} else if ok {
|
||||
@@ -218,7 +228,7 @@ func (f following) hearMerge(ctx context.Context, m link.SourceMoved, now time.T
|
||||
return cutBatchesHeld(ctx, f.open, now)
|
||||
}
|
||||
|
||||
batch, err := theOpenBatch(ctx, inv, heard, now, own)
|
||||
batch, why, err := batchToJoin(ctx, inv, heard, entries, read, now, own, waits)
|
||||
if err != nil {
|
||||
return notNow(err)
|
||||
}
|
||||
@@ -229,7 +239,7 @@ func (f following) hearMerge(ctx context.Context, m link.SourceMoved, now time.T
|
||||
if err := keepBatch(ctx, inv, &batch, now, ""); err != nil {
|
||||
return notNow(err)
|
||||
}
|
||||
fmt.Printf("%s merged into %s (%.8s); it joins %s — %s\n", repository, m.Base, m.Commit, batch.ID,
|
||||
fmt.Printf("%s merged into %s (%.8s); %s, it joins %s — %s\n", repository, m.Base, m.Commit, why, batch.ID,
|
||||
batchWords(batch, now))
|
||||
return cutBatchesHeld(ctx, f.open, now)
|
||||
}
|
||||
@@ -320,22 +330,211 @@ func ownPath(touches []inventory.Entry) bool {
|
||||
return false
|
||||
}
|
||||
|
||||
// theOpenBatch is the batch a merge heard now joins: the one of its kind not yet cut, or a new one.
|
||||
func theOpenBatch(ctx context.Context, inv *inventory.Inventory, first inventory.BatchedMerge, now time.Time, own bool) (inventory.Plan, error) {
|
||||
// **A merge waits only for a batch it shares something with** (novox/hq ADR 0304 decision 1, as ADR 0306
|
||||
// decisions 2 and 3 read it). batchToJoin is the batch a merge heard now joins, and why in words:
|
||||
//
|
||||
// - an assembling or queued batch of its kind it is related to (related.go): it joins it and waits for the
|
||||
// window, which its coming restarts. Related to two or more, the newer are folded into the oldest, which
|
||||
// answers all their merges: a merge never waits in two windows, and what it shares with each walks in one.
|
||||
// - none, and its delivery group has a member still to merge, or mesh-delivery could not say (groupWait, waits
|
||||
// names why): a new batch, which waits for the window, beside the ones it shares nothing with; its words say
|
||||
// why.
|
||||
// - none, and no member of its group is still to merge: a new batch whose window is closed at once. Cut at
|
||||
// once means only that: walks stay one at a time (ADR 0276 decision 4), so with a walk open the batch is
|
||||
// queued behind it as any closed batch is.
|
||||
func batchToJoin(ctx context.Context, inv *inventory.Inventory, heard inventory.BatchedMerge, entries []inventory.Entry,
|
||||
read map[string][]inventory.ReadRepository, now time.Time, own bool, waits string) (inventory.Plan, string, error) {
|
||||
edges, err := inv.Dependencies(ctx)
|
||||
if err != nil {
|
||||
return inventory.Plan{}, "", err
|
||||
}
|
||||
joins, whys, _, err := relatedBatches(ctx, inv, []inventory.BatchedMerge{heard}, own, "", entries, read, edges)
|
||||
if err != nil {
|
||||
return inventory.Plan{}, "", err
|
||||
}
|
||||
if len(joins) > 0 {
|
||||
into := joins[0]
|
||||
why := "related to " + into.ID + " (" + whys[0] + ")"
|
||||
if len(joins) > 1 {
|
||||
plans, moves, err := foldInto(ctx, inv, &into, joins[1:])
|
||||
if err != nil {
|
||||
return inventory.Plan{}, "", err
|
||||
}
|
||||
if err := inv.SavePlansMoving(ctx, plans, moves); err != nil {
|
||||
return inventory.Plan{}, "", err
|
||||
}
|
||||
var folded []string
|
||||
for i, b := range joins[1:] {
|
||||
folded = append(folded, b.ID+" ("+whys[i+1]+")")
|
||||
}
|
||||
why += ", and to " + strings.Join(folded, ", ") + ", folded into it"
|
||||
}
|
||||
into.Delivery.Batch.CutAtOnce = false
|
||||
return into, why, nil
|
||||
}
|
||||
if waits != "" {
|
||||
// Its own window, beside the batches it shares nothing with: waiting is for its group's members, which
|
||||
// are related to it by their head and join it (ADR 0306 decision 2).
|
||||
b, err := newBatch(ctx, inv, heard, now, own, false, waits)
|
||||
return b, waits + ", it waits for the window in a batch of its own", err
|
||||
}
|
||||
b, err := newBatch(ctx, inv, heard, now, own, true, "")
|
||||
return b, "it shares nothing with a batch assembling and no member of a group is still to merge: it is cut at once", err
|
||||
}
|
||||
|
||||
// relatedBatches are the batches not yet cut of a kind, oldest first, parted into those related to merges (with
|
||||
// the first reason of each) and the others. Each batch is judged by what its cut would move (ADR 0306 decision
|
||||
// 3): its merges' moves as they were kept and as they read now — the catalogue may have moved since a merge was
|
||||
// heard — widened to their dependents, and, for a catalogue batch, every walk waiting for its word, which the
|
||||
// cut folds in (cutBatch's carry). A merge kept with no moves leaves its batch unknown, related to everything.
|
||||
// except is a walk not to count as folded: the one being stopped.
|
||||
func relatedBatches(ctx context.Context, inv *inventory.Inventory, merges []inventory.BatchedMerge, own bool,
|
||||
except string, entries []inventory.Entry, read map[string][]inventory.ReadRepository,
|
||||
edges []inventory.Edge) (joins []inventory.Plan, whys []string, others []inventory.Plan, err error) {
|
||||
batches, err := inv.Batches(ctx)
|
||||
if err != nil {
|
||||
return inventory.Plan{}, err
|
||||
return nil, nil, nil, err
|
||||
}
|
||||
var kind []inventory.Plan
|
||||
for _, b := range batches {
|
||||
if b.OwnPath() == own {
|
||||
return b, nil
|
||||
kind = append(kind, b)
|
||||
}
|
||||
}
|
||||
if len(kind) == 0 {
|
||||
return nil, nil, nil, nil
|
||||
}
|
||||
carry := newFootprint()
|
||||
if !own {
|
||||
// An own-path batch folds no waiting walk (cutBatchesHeld); a catalogue batch may fold every one.
|
||||
plans, err := inv.OpenPlans(ctx)
|
||||
if err != nil {
|
||||
return nil, nil, nil, err
|
||||
}
|
||||
for _, p := range plans {
|
||||
if p.Release != nil || !p.Waiting() || p.ID == except {
|
||||
continue
|
||||
}
|
||||
kept, err := inv.MergesOf(ctx, p.ID)
|
||||
if err != nil {
|
||||
return nil, nil, nil, err
|
||||
}
|
||||
carry = unionFootprint(carry, footprintOfWalk(p, kept))
|
||||
}
|
||||
}
|
||||
mine := footprintAsCut(merges, entries, read, edges)
|
||||
for _, b := range kind {
|
||||
held, err := inv.MergesOf(ctx, b.ID)
|
||||
if err != nil {
|
||||
return nil, nil, nil, err
|
||||
}
|
||||
if b.Delivery == nil {
|
||||
b.Delivery = &inventory.PlanDelivery{}
|
||||
}
|
||||
if b.Delivery.Batch == nil {
|
||||
b.Delivery.Batch = &inventory.PlanBatch{Own: own}
|
||||
}
|
||||
if ok, why := related(mine, unionFootprint(footprintAsCut(held, entries, read, edges), carry), edges); ok {
|
||||
joins, whys = append(joins, b), append(whys, why)
|
||||
} else {
|
||||
others = append(others, b)
|
||||
}
|
||||
}
|
||||
return joins, whys, others, nil
|
||||
}
|
||||
|
||||
// footprintAsCut is a batch's footprint as a cut now would read it: footprintOfBatch, widened by the modules each
|
||||
// merge moves as the catalogue reads now (planBatch judges each merge again at the cut, so what it moves may
|
||||
// have changed since it was heard). Both are kept: when in doubt, related.
|
||||
func footprintAsCut(merges []inventory.BatchedMerge, entries []inventory.Entry,
|
||||
read map[string][]inventory.ReadRepository, edges []inventory.Edge) footprint {
|
||||
f := footprintOfBatch(merges, edges)
|
||||
var moved []string
|
||||
for _, m := range merges {
|
||||
s := announcedOf(m).SourceMoved
|
||||
if s.Owner == "" {
|
||||
continue
|
||||
}
|
||||
s.MergedAt = "" // news, whatever a cut marked seen since (as planBatch reads it)
|
||||
for _, e := range wouldMove(s, entries, read) {
|
||||
moved = append(moved, e.Manifest.Module)
|
||||
}
|
||||
}
|
||||
for _, name := range reachableFrom(moved, edges) {
|
||||
f.modules[name] = true
|
||||
}
|
||||
return f
|
||||
}
|
||||
|
||||
// unionFootprint is what two changes reach together.
|
||||
func unionFootprint(a, b footprint) footprint {
|
||||
f := newFootprint()
|
||||
for _, from := range []footprint{a, b} {
|
||||
for k := range from.repos {
|
||||
f.repos[k] = true
|
||||
}
|
||||
for k := range from.modules {
|
||||
f.modules[k] = true
|
||||
}
|
||||
for k := range from.heads {
|
||||
f.heads[k] = true
|
||||
}
|
||||
}
|
||||
f.unknown = a.unknown
|
||||
if f.unknown == "" {
|
||||
f.unknown = b.unknown
|
||||
}
|
||||
return f
|
||||
}
|
||||
|
||||
// foldInto folds batches into the oldest one related to a merge: the plans to write (into first, so no merge
|
||||
// names a plan the store does not hold) and the merges to move, for one SavePlansMoving. The folded batches name
|
||||
// the batch that took them over; a stop's closed window and its withheld modules (ADR 0299) go with their merges.
|
||||
func foldInto(ctx context.Context, inv *inventory.Inventory, into *inventory.Plan, from []inventory.Plan) ([]*inventory.Plan,
|
||||
[]inventory.MergeMove, error) {
|
||||
if into.Delivery == nil {
|
||||
into.Delivery = &inventory.PlanDelivery{}
|
||||
}
|
||||
if into.Delivery.Batch == nil {
|
||||
into.Delivery.Batch = &inventory.PlanBatch{Own: into.OwnPath()}
|
||||
}
|
||||
plans := []*inventory.Plan{into}
|
||||
var moves []inventory.MergeMove
|
||||
for i := range from {
|
||||
f := from[i]
|
||||
merges, err := inv.MergesOf(ctx, f.ID)
|
||||
if err != nil {
|
||||
return nil, nil, err
|
||||
}
|
||||
for _, m := range merges {
|
||||
moves = append(moves, inventory.MergeMove{Repository: m.Repository, Commit: m.Commit, Plan: into.ID, Alone: m.Alone})
|
||||
}
|
||||
if f.Delivery == nil {
|
||||
f.Delivery = &inventory.PlanDelivery{}
|
||||
}
|
||||
if w := f.Delivery.Batch; w != nil {
|
||||
into.Delivery.Batch.Closed = into.Delivery.Batch.Closed || w.Closed
|
||||
into.Delivery.Batch.Withheld = union(into.Delivery.Batch.Withheld, w.Withheld)
|
||||
sort.Strings(into.Delivery.Batch.Withheld)
|
||||
}
|
||||
f.State = inventory.PlanSuperseded
|
||||
f.Delivery.Batch = nil
|
||||
f.Delivery.TakenOverBy = into.ID
|
||||
f.Note = fmt.Sprintf("folded into %s before it was cut: a merge related to both joined it, and %s answers "+
|
||||
"its merges", into.ID, into.ID)
|
||||
plans = append(plans, &f)
|
||||
}
|
||||
return plans, moves, nil
|
||||
}
|
||||
|
||||
// newBatch is a new batch of a kind, kept before its first merge names it: a merge never names a plan the store
|
||||
// does not hold. cutAtOnce closes its window at once; waits says why it waits for its group, when it does.
|
||||
func newBatch(ctx context.Context, inv *inventory.Inventory, first inventory.BatchedMerge, now time.Time, own,
|
||||
cutAtOnce bool, waits string) (inventory.Plan, error) {
|
||||
b := inventory.Plan{ID: fmt.Sprintf("plan-%d", now.UnixNano()), Repository: first.Repository, Branch: first.Branch,
|
||||
Commit: first.Commit, Merged: first.Merged, Created: now, State: inventory.PlanAssembling,
|
||||
Tiers: [][]string{}, Modules: map[string]*inventory.PlanModule{},
|
||||
Delivery: &inventory.PlanDelivery{Batch: &inventory.PlanBatch{Own: own}}}
|
||||
// Kept before its first merge names it: a merge never names a plan the store does not hold.
|
||||
Delivery: &inventory.PlanDelivery{Batch: &inventory.PlanBatch{Own: own, CutAtOnce: cutAtOnce, Waits: waits}}}
|
||||
if err := inv.SavePlan(ctx, &b); err != nil {
|
||||
return inventory.Plan{}, err
|
||||
}
|
||||
@@ -367,7 +566,16 @@ func keepBatch(ctx context.Context, inv *inventory.Inventory, b *inventory.Plan,
|
||||
}
|
||||
closes, latest := windowOf(merges, b.Created, window, atMost)
|
||||
b.Delivery.Merges = named
|
||||
b.Delivery.Batch = &inventory.PlanBatch{ClosesAt: closes, AtMost: latest, Behind: behind, Own: b.OwnPath()}
|
||||
var closed, cutAtOnce bool
|
||||
var withheld []string
|
||||
var waits string
|
||||
if was := b.Delivery.Batch; was != nil {
|
||||
closed, withheld = was.Closed, was.Withheld // a stop's, which no look takes back (novox/hq ADR 0299)
|
||||
cutAtOnce = was.CutAtOnce // the merge's, until another joins it (ADR 0304 decision 1)
|
||||
waits = was.Waits // its group's, as said when it was made (ADR 0306 decision 2)
|
||||
}
|
||||
b.Delivery.Batch = &inventory.PlanBatch{ClosesAt: closes, AtMost: latest, Behind: behind, Own: b.OwnPath(),
|
||||
Closed: closed, Withheld: withheld, CutAtOnce: cutAtOnce, Waits: waits}
|
||||
b.State = inventory.PlanAssembling
|
||||
if behind != "" && windowClosed(*b, now) {
|
||||
b.State = inventory.PlanQueued
|
||||
@@ -396,13 +604,14 @@ func windowOf(merges []inventory.BatchedMerge, created time.Time, window, atMost
|
||||
return last.Add(window), created.Add(atMost)
|
||||
}
|
||||
|
||||
// windowClosed says a batch's window is closed: no merge for the window's length, or its maximum reached.
|
||||
// windowClosed says a batch's window is closed: closed by a stop, closed at once for a merge that shares
|
||||
// nothing (ADR 0304 decision 1), no merge for the window's length, or its maximum reached.
|
||||
func windowClosed(b inventory.Plan, now time.Time) bool {
|
||||
if b.Delivery == nil || b.Delivery.Batch == nil {
|
||||
return true
|
||||
}
|
||||
w := b.Delivery.Batch
|
||||
return !now.Before(w.ClosesAt) || !now.Before(w.AtMost)
|
||||
return w.Closed || w.CutAtOnce || !now.Before(w.ClosesAt) || !now.Before(w.AtMost)
|
||||
}
|
||||
|
||||
// carriedOf is a set of merges as a walk carries them: the latest merge of each repository's branch, and
|
||||
@@ -478,7 +687,8 @@ func spelledOf(m inventory.BatchedMerge) string {
|
||||
// namedOf is one merge as a walk or batch names it: its commit, and its pull request and moves as announced.
|
||||
func namedOf(m inventory.BatchedMerge, repository string) inventory.PlanMerge {
|
||||
k := announcedOf(m)
|
||||
return inventory.PlanMerge{Repository: repository, Commit: m.Commit, Number: k.Number, Title: k.Title, Moves: k.Moves}
|
||||
return inventory.PlanMerge{Repository: repository, Commit: m.Commit, Number: k.Number, Title: k.Title, Moves: k.Moves,
|
||||
Merged: m.Merged, Heard: m.Heard}
|
||||
}
|
||||
|
||||
// laterMerge says a was merged after b: by the forge's merge time, then by when each was heard.
|
||||
@@ -610,8 +820,9 @@ func cutBatchesHeld(ctx context.Context, open *stores, now time.Time) error {
|
||||
return err
|
||||
}
|
||||
// The oldest batch whose window closed is cut, an own-path one before a catalogue one (it goes first, and
|
||||
// the catalogue batch queues behind it rather than being cut and overtaken); one of each kind at most is
|
||||
// open (theOpenBatch).
|
||||
// the catalogue batch queues behind it rather than being cut and overtaken). Several of a kind may be open
|
||||
// since a merge that shares nothing is cut at once (ADR 0304 decision 1): walks stay one at a time, so one
|
||||
// is cut per look, and once its walk started the others are queued behind it.
|
||||
sort.SliceStable(batches, func(i, j int) bool { return batches[i].OwnPath() && !batches[j].OwnPath() })
|
||||
for i := range batches {
|
||||
b := &batches[i]
|
||||
@@ -761,7 +972,18 @@ func planBatch(ctx context.Context, open *stores, batch *inventory.Plan, carry [
|
||||
}
|
||||
sort.Strings(also)
|
||||
ordered := groupOrderEdges(members, entries, read, edges)
|
||||
var withheld []string
|
||||
plan := planOfMoves(moved, append(append([]inventory.Edge{}, edges...), ordered...))
|
||||
// **Withheld, a stopped merge's modules** (novox/hq ADR 0299): a module is built at its branch, which holds the
|
||||
// merge a stop left out of the walk these merges were walked again from — built here only as a dependent, it
|
||||
// would deliver that merge. One a merge of this batch moves is built: that merge carries the stopped change,
|
||||
// and the stop named it.
|
||||
if batch.Delivery != nil && batch.Delivery.Batch != nil {
|
||||
if out := withhold(&plan, batch.Delivery.Batch.Withheld, moved); len(out) > 0 {
|
||||
withheld = out
|
||||
fmt.Printf(" withheld, a stopped merge's modules built only as dependents: %s\n", strings.Join(out, ", "))
|
||||
}
|
||||
}
|
||||
plan.ID, plan.Revision, plan.Created, plan.Epoch = batch.ID, batch.Revision, now, batch.Epoch
|
||||
plan.Commits = commits
|
||||
newest := newestCommit(commits)
|
||||
@@ -772,6 +994,9 @@ func planBatch(ctx context.Context, open *stores, batch *inventory.Plan, carry [
|
||||
}
|
||||
plan.Delivery.Merges = named
|
||||
plan.Delivery.Alone = batch.Delivery != nil && batch.Delivery.Alone
|
||||
plan.Delivery.Withheld = withheld
|
||||
// **Its moments and its class** (novox/hq ADR 0282 decision 6): measured, never acted on.
|
||||
plan.Times = walkTimesAtCut(*batch, plan, entries, now)
|
||||
if len(moved) == 0 {
|
||||
plan.State = inventory.PlanDone
|
||||
plan.Tiers = [][]string{}
|
||||
@@ -820,6 +1045,86 @@ func planBatch(ctx context.Context, open *stores, batch *inventory.Plan, carry [
|
||||
return nil
|
||||
}
|
||||
|
||||
// withhold takes from a plan every module named that its merges do not move, and the tiers left empty: the
|
||||
// modules taken.
|
||||
func withhold(plan *inventory.Plan, names, moved []string) []string {
|
||||
var out []string
|
||||
for _, n := range names {
|
||||
if _, in := plan.Modules[n]; in && !slices.Contains(moved, n) {
|
||||
delete(plan.Modules, n)
|
||||
out = append(out, n)
|
||||
}
|
||||
}
|
||||
if len(out) == 0 {
|
||||
return nil
|
||||
}
|
||||
var tiers [][]string
|
||||
for _, t := range plan.Tiers {
|
||||
var kept []string
|
||||
for _, n := range t {
|
||||
if !slices.Contains(out, n) {
|
||||
kept = append(kept, n)
|
||||
}
|
||||
}
|
||||
if len(kept) > 0 {
|
||||
tiers = append(tiers, kept)
|
||||
}
|
||||
}
|
||||
if tiers == nil {
|
||||
tiers = [][]string{}
|
||||
}
|
||||
plan.Tiers = tiers
|
||||
sort.Strings(out)
|
||||
return out
|
||||
}
|
||||
|
||||
// walkTimesAtCut is a walk's own moments as it is cut (novox/hq ADR 0282 decision 6): when its batch's window
|
||||
// closed — no merge for the window's length, or its maximum, whichever came first — when it was cut, and its
|
||||
// class. A merge walked alone had no window.
|
||||
func walkTimesAtCut(batch, walk inventory.Plan, entries []inventory.Entry, now time.Time) *inventory.PlanTimes {
|
||||
cut := now
|
||||
t := &inventory.PlanTimes{Cut: &cut, Class: classOf(walk, entries)}
|
||||
if batch.Delivery != nil && batch.Delivery.Batch != nil {
|
||||
w := batch.Delivery.Batch
|
||||
closed := w.ClosesAt
|
||||
if !w.AtMost.IsZero() && w.AtMost.Before(closed) {
|
||||
closed = w.AtMost
|
||||
}
|
||||
if w.CutAtOnce && !batch.Created.IsZero() {
|
||||
closed = batch.Created // closed when it was made (ADR 0304 decision 1)
|
||||
}
|
||||
if !closed.IsZero() {
|
||||
if closed.After(now) {
|
||||
closed = now
|
||||
}
|
||||
t.WindowClosed = &closed
|
||||
}
|
||||
}
|
||||
return t
|
||||
}
|
||||
|
||||
// resolverSeat is the seat of the mesh's resolver: a module claiming it is a core module (ADR 0282 decision 1).
|
||||
const resolverSeat = "mesh-dns-resolver"
|
||||
|
||||
// classOf is a walk's class (novox/hq ADR 0282 decision 1): core when it walks a module on the controller's own
|
||||
// path or one holding the mesh's resolver, leaf otherwise.
|
||||
func classOf(walk inventory.Plan, entries []inventory.Entry) string {
|
||||
resolvers := map[string]bool{}
|
||||
for _, e := range entries {
|
||||
for _, c := range e.Manifest.Claims {
|
||||
if c.Name == resolverSeat {
|
||||
resolvers[e.Manifest.Module] = true
|
||||
}
|
||||
}
|
||||
}
|
||||
for m := range walk.Modules {
|
||||
if _, own := onTheControllersPath[m]; own || resolvers[m] {
|
||||
return inventory.ClassCore
|
||||
}
|
||||
}
|
||||
return inventory.ClassLeaf
|
||||
}
|
||||
|
||||
// combinedMerges is a batch's merges as one merge per repository's branch: the latest, with every file the
|
||||
// merges of it changed and said to be a module's — on a linear trunk the latest contains the others. A file is
|
||||
// removed when the last merge of the batch that changed it removed it. merges are in the order they were made.
|
||||
@@ -1044,6 +1349,10 @@ func batchWords(b inventory.Plan, now time.Time) string {
|
||||
if b.State == inventory.PlanQueued {
|
||||
return fmt.Sprintf("queued behind %s; grouped: %s; plan not yet calculated", w.Behind, grouped)
|
||||
}
|
||||
if w.CutAtOnce {
|
||||
return fmt.Sprintf("cut at once, sharing nothing with a batch assembling; grouped: %s; plan not yet calculated",
|
||||
grouped)
|
||||
}
|
||||
left := w.ClosesAt.Sub(now)
|
||||
if w.AtMost.Before(w.ClosesAt) {
|
||||
left = w.AtMost.Sub(now)
|
||||
@@ -1051,8 +1360,12 @@ func batchWords(b inventory.Plan, now time.Time) string {
|
||||
if left < 0 {
|
||||
left = 0
|
||||
}
|
||||
return fmt.Sprintf("assembling: %s left (at the latest %s); grouped: %s; plan not yet calculated",
|
||||
secondsWords(left), w.AtMost.Local().Format("15:04:05"), grouped)
|
||||
waits := ""
|
||||
if w.Waits != "" {
|
||||
waits = " — " + w.Waits
|
||||
}
|
||||
return fmt.Sprintf("assembling: %s left (at the latest %s)%s; grouped: %s; plan not yet calculated",
|
||||
secondsWords(left), w.AtMost.Local().Format("15:04:05"), waits, grouped)
|
||||
}
|
||||
|
||||
// groupedWords is a batch's commits, each with the earlier merges it answers.
|
||||
|
||||
@@ -34,6 +34,7 @@ func windowed(t *testing.T) *stores {
|
||||
t.Fatal(err)
|
||||
}
|
||||
t.Setenv(mergeWindowFileVar, settings)
|
||||
noGroups(t)
|
||||
if err := inv.RegisterModule(ctx, catalogue.Manifest{Module: "mesh-controller", Version: "1"},
|
||||
inventory.Source{Repository: "novox/mesh-controller", Seat: "git", Ref: "main", BuiltFrom: "c0",
|
||||
Head: "c0"}); err != nil {
|
||||
@@ -58,19 +59,70 @@ func windowed(t *testing.T) *stores {
|
||||
// t0 is the moment a test's clock starts: merges are dated by it, and heard after it.
|
||||
var t0 = time.Now().UTC().Truncate(time.Second)
|
||||
|
||||
// catalogueMerge is a merge of the catalogue changing one module's directory, made at a moment.
|
||||
// catalogueMerge is a merge of the catalogue changing one module's directory, made at a moment, from a pull
|
||||
// request's head branch of its own, as the forge announces every merge. Whether its head names a delivery group
|
||||
// with a member still to merge is mesh-delivery's word, which windowed stubs as no group at all (noGroups); a test
|
||||
// whose merges wait for the window as a group's says so (groupsWaiting).
|
||||
func catalogueMerge(commit, module string, made time.Time) link.SourceMoved {
|
||||
return link.SourceMoved{Owner: "novox", Repo: "mesh-catalog", Base: "main", Commit: commit,
|
||||
return link.SourceMoved{Owner: "novox", Repo: "mesh-catalog", Base: "main", Head: "pr/" + commit, Commit: commit,
|
||||
MergedAt: made.Format(time.RFC3339Nano), Paths: []string{"modules/" + module + "/module.json"},
|
||||
ModuleDirs: []string{"modules/" + module}, ModuleDirsSaid: true}
|
||||
}
|
||||
|
||||
// repoMerge is a merge of a repository of one module's own.
|
||||
// repoMerge is a merge of a repository of one module's own, from a head branch of its own (catalogueMerge).
|
||||
func repoMerge(repo, commit string, made time.Time) link.SourceMoved {
|
||||
return link.SourceMoved{Owner: "novox", Repo: repo, Base: "main", Commit: commit,
|
||||
return link.SourceMoved{Owner: "novox", Repo: repo, Base: "main", Head: "pr/" + commit, Commit: commit,
|
||||
MergedAt: made.Format(time.RFC3339Nano), Paths: []string{"main.go"}}
|
||||
}
|
||||
|
||||
// noGroups stubs mesh-delivery's word on groups for a test: no head names a group.
|
||||
func noGroups(t *testing.T) {
|
||||
t.Helper()
|
||||
was := deliveryGroupOf
|
||||
deliveryGroupOf = func(context.Context, bool, string) ([]groupMember, bool, error) { return nil, false, nil }
|
||||
t.Cleanup(func() { deliveryGroupOf = was })
|
||||
}
|
||||
|
||||
// groupsWaiting stubs mesh-delivery's word on groups for a test: each head named is a group with a member of another
|
||||
// repository whose pull request is open (novox/elsewhere, ready), so a merge from it waits for the window (ADR 0306
|
||||
// decision 2); every other head names no group.
|
||||
func groupsWaiting(t *testing.T, heads ...string) {
|
||||
t.Helper()
|
||||
was := deliveryGroupOf
|
||||
deliveryGroupOf = func(_ context.Context, _ bool, head string) ([]groupMember, bool, error) {
|
||||
if slices.Contains(heads, head) {
|
||||
return []groupMember{{Repository: "novox/elsewhere", State: "ready"}}, true, nil
|
||||
}
|
||||
return nil, false, nil
|
||||
}
|
||||
t.Cleanup(func() { deliveryGroupOf = was })
|
||||
}
|
||||
|
||||
// everyHeadWaits stubs mesh-delivery's word on groups for a test whose merges each wait for the window as they did
|
||||
// before novox/hq ADR 0304: every head is a group with a member of another repository still to merge.
|
||||
func everyHeadWaits(t *testing.T) {
|
||||
t.Helper()
|
||||
was := deliveryGroupOf
|
||||
deliveryGroupOf = func(context.Context, bool, string) ([]groupMember, bool, error) {
|
||||
return []groupMember{{Repository: "novox/elsewhere", State: "ready"}}, true, nil
|
||||
}
|
||||
t.Cleanup(func() { deliveryGroupOf = was })
|
||||
}
|
||||
|
||||
// fromHead is a merge from a head branch a test names: merges from one head are members of one delivery group,
|
||||
// related by it (novox/hq ADR 0304 decision 1), so they share a batch whatever else they share.
|
||||
func fromHead(m link.SourceMoved, head string) link.SourceMoved {
|
||||
m.Head = head
|
||||
return m
|
||||
}
|
||||
|
||||
// lone is a merge that names no head: known to be no delivery group's, it waits for no window unless it is
|
||||
// related to a batch assembling (ADR 0304 decision 1).
|
||||
func lone(m link.SourceMoved) link.SourceMoved {
|
||||
m.Head = ""
|
||||
return m
|
||||
}
|
||||
|
||||
// hear is a merge heard at a moment.
|
||||
func hear(t *testing.T, open *stores, m link.SourceMoved, now time.Time) {
|
||||
t.Helper()
|
||||
@@ -108,6 +160,7 @@ func walks(t *testing.T, open *stores) (walks, batches []inventory.Plan) {
|
||||
// later commit, which names both merges — the earlier carried by the later.
|
||||
func TestTwoMergesSecondsApartAreOneWalkAtTheLaterCommit(t *testing.T) {
|
||||
open := windowed(t)
|
||||
everyHeadWaits(t)
|
||||
asked := asksWithPaths(t)
|
||||
claude := catalogueMerge("553b7191claude", "app", t0)
|
||||
dunst := catalogueMerge("48bda475dunst", "notes", t0.Add(17*time.Second))
|
||||
@@ -152,9 +205,10 @@ func TestTwoMergesSecondsApartAreOneWalkAtTheLaterCommit(t *testing.T) {
|
||||
// Merges of three repositories in one window are one walk, one commit for each.
|
||||
func TestThreeRepositoriesInOneWindowAreOneWalk(t *testing.T) {
|
||||
open := windowed(t)
|
||||
groupsWaiting(t, "feat/three")
|
||||
asksRecorded(t)
|
||||
for i, r := range []string{"one", "two", "three"} {
|
||||
hear(t, open, repoMerge(r, "c-"+r, t0.Add(time.Duration(i)*20*time.Second)),
|
||||
hear(t, open, fromHead(repoMerge(r, "c-"+r, t0.Add(time.Duration(i)*20*time.Second)), "feat/three"),
|
||||
t0.Add(time.Duration(i)*20*time.Second+time.Second))
|
||||
}
|
||||
cutAt(t, open, t0.Add(41*time.Second+90*time.Second))
|
||||
@@ -187,9 +241,10 @@ func TestThreeRepositoriesInOneWindowAreOneWalk(t *testing.T) {
|
||||
// closes at most ten minutes after its first merge however busy.
|
||||
func TestAMergeRestartsTheWindowAndTheMaximumClosesIt(t *testing.T) {
|
||||
open := windowed(t)
|
||||
groupsWaiting(t, "feat/both", "feat/busy")
|
||||
asksWithPaths(t)
|
||||
hear(t, open, repoMerge("one", "c1", t0), t0)
|
||||
hear(t, open, repoMerge("two", "c2", t0.Add(80*time.Second)), t0.Add(80*time.Second))
|
||||
hear(t, open, fromHead(repoMerge("one", "c1", t0), "feat/both"), t0)
|
||||
hear(t, open, fromHead(repoMerge("two", "c2", t0.Add(80*time.Second)), "feat/both"), t0.Add(80*time.Second))
|
||||
cutAt(t, open, t0.Add(100*time.Second))
|
||||
if ws, _ := walks(t, open); len(ws) != 0 {
|
||||
t.Fatal("the window closed 90 seconds after its first merge, not after its last")
|
||||
@@ -200,12 +255,13 @@ func TestAMergeRestartsTheWindowAndTheMaximumClosesIt(t *testing.T) {
|
||||
}
|
||||
|
||||
busy := windowed(t)
|
||||
groupsWaiting(t, "feat/both", "feat/busy")
|
||||
asksWithPaths(t)
|
||||
var last time.Time
|
||||
for i := 0; i < 12; i++ {
|
||||
last = t0.Add(time.Duration(i) * time.Minute)
|
||||
repo := []string{"one", "two", "three"}[i%3]
|
||||
hear(t, busy, repoMerge(repo, "c"+string(rune('a'+i)), last), last)
|
||||
hear(t, busy, fromHead(repoMerge(repo, "c"+string(rune('a'+i)), last), "feat/busy"), last)
|
||||
if ws, _ := walks(t, busy); len(ws) > 0 {
|
||||
if i != 10 {
|
||||
t.Fatalf("a busy window closed at merge %d (minute %d), not at its maximum", i, i)
|
||||
@@ -223,10 +279,11 @@ func TestAMergeRestartsTheWindowAndTheMaximumClosesIt(t *testing.T) {
|
||||
// what is grouped, and that the plan is not yet calculated. It says so on the bus as plan-moved, too.
|
||||
func TestTheAssemblingBatchIsShown(t *testing.T) {
|
||||
open := windowed(t)
|
||||
groupsWaiting(t, "pr/553b7191claude")
|
||||
asksWithPaths(t)
|
||||
var said []inventory.Plan
|
||||
was := inventory.PlanSaved
|
||||
inventory.PlanSaved = func(p inventory.Plan) { said = append(said, p) }
|
||||
inventory.PlanSaved = func(_ *inventory.Inventory, p inventory.Plan) { said = append(said, p) }
|
||||
t.Cleanup(func() { inventory.PlanSaved = was })
|
||||
now := time.Now().UTC()
|
||||
claude := catalogueMerge("553b7191claude", "app", now.Add(-20*time.Second))
|
||||
@@ -235,7 +292,7 @@ func TestTheAssemblingBatchIsShown(t *testing.T) {
|
||||
dunst.Number, dunst.Title = 175, "dunst: the font the operator chose"
|
||||
hear(t, open, claude, now.Add(-19*time.Second))
|
||||
hear(t, open, dunst, now.Add(-time.Second))
|
||||
hear(t, open, repoMerge("one", "a6bc0931one", now), now)
|
||||
hear(t, open, fromHead(repoMerge("one", "a6bc0931one", now), dunst.Head), now)
|
||||
out := captured(t, func() error { return plansCommand(t.Context(), nil) })
|
||||
lines := strings.Split(out, "\n")
|
||||
first := lines[0]
|
||||
@@ -360,6 +417,7 @@ func TestAWaitingWalkIsFoldedIntoTheNextBatch(t *testing.T) {
|
||||
// moves — named at once on a walk done — and joins the next batch when it does not.
|
||||
func TestALateMergeIsAnsweredByTheWalkOfTheLaterOne(t *testing.T) {
|
||||
open := windowed(t)
|
||||
everyHeadWaits(t)
|
||||
asksWithPaths(t)
|
||||
ctx := t.Context()
|
||||
later := catalogueMerge("48bda475dunst", "notes", t0.Add(17*time.Second))
|
||||
@@ -391,6 +449,7 @@ func TestALateMergeIsAnsweredByTheWalkOfTheLaterOne(t *testing.T) {
|
||||
// first; the first delivered answers the older ones, and the search stops.
|
||||
func TestAFailedWalkWalksItsEarlierMergesAlone(t *testing.T) {
|
||||
open := windowed(t)
|
||||
everyHeadWaits(t)
|
||||
asked := asksWithPaths(t)
|
||||
ctx := t.Context()
|
||||
// Made before the cut marks their modules seen, as merges are: walked again, they are news all the same.
|
||||
@@ -459,6 +518,7 @@ func TestAFailedWalkWalksItsEarlierMergesAlone(t *testing.T) {
|
||||
func TestAGroupsOrderBecomesTiersInsideTheWalk(t *testing.T) {
|
||||
for _, grouped := range []bool{true, false} {
|
||||
open := windowed(t)
|
||||
everyHeadWaits(t)
|
||||
asksWithPaths(t)
|
||||
ctx := t.Context()
|
||||
for _, m := range []string{"mesh-host"} {
|
||||
@@ -496,9 +556,10 @@ func TestAGroupsOrderBecomesTiersInsideTheWalk(t *testing.T) {
|
||||
// store, a merge handed over again is not doubled, and the batch is cut when its window closes.
|
||||
func TestABatchSurvivesARestart(t *testing.T) {
|
||||
open := windowed(t)
|
||||
groupsWaiting(t, "feat/both")
|
||||
asksWithPaths(t)
|
||||
hear(t, open, repoMerge("one", "c1", t0), t0)
|
||||
hear(t, open, repoMerge("two", "c2", t0.Add(30*time.Second)), t0.Add(30*time.Second))
|
||||
hear(t, open, fromHead(repoMerge("one", "c1", t0), "feat/both"), t0)
|
||||
hear(t, open, fromHead(repoMerge("two", "c2", t0.Add(30*time.Second)), "feat/both"), t0.Add(30*time.Second))
|
||||
|
||||
// A new controller: nothing of the first one's but the store.
|
||||
again, err := openStores(t.Context())
|
||||
@@ -506,7 +567,7 @@ func TestABatchSurvivesARestart(t *testing.T) {
|
||||
t.Fatal(err)
|
||||
}
|
||||
t.Cleanup(again.Close)
|
||||
hear(t, again, repoMerge("one", "c1", t0), t0.Add(60*time.Second)) // the bus hands it over again
|
||||
hear(t, again, fromHead(repoMerge("one", "c1", t0), "feat/both"), t0.Add(60*time.Second)) // the bus hands it over again
|
||||
cutAt(t, again, t0.Add(119*time.Second))
|
||||
if ws, bs := walks(t, again); len(ws) != 0 || len(bs) != 1 || len(bs[0].Delivery.Merges) != 2 {
|
||||
t.Fatalf("the restarted controller's batch: %d walk(s), %+v", len(ws), bs)
|
||||
@@ -563,6 +624,7 @@ func TestAWaitingWalkNamesTheMergesItAnswers(t *testing.T) {
|
||||
// nothing, and the merge joins the next batch.
|
||||
func TestALateMergeOfAOneModuleRepositoryIsNamed(t *testing.T) {
|
||||
open := windowed(t)
|
||||
everyHeadWaits(t)
|
||||
asksWithPaths(t)
|
||||
ctx := t.Context()
|
||||
c2 := repoMerge("one", "c2", t0.Add(-50*time.Second))
|
||||
@@ -716,6 +778,7 @@ func TestTheCatchUpKeepsWhatACutMadeHistory(t *testing.T) {
|
||||
// still waits for the word, so no catalogue delivery skips its turn.
|
||||
func TestAMergeOnTheControllersPathNeverSharesABatch(t *testing.T) {
|
||||
open := windowed(t)
|
||||
everyHeadWaits(t)
|
||||
asked := asksWithPaths(t)
|
||||
ctx := t.Context()
|
||||
if err := open.inventory.RegisterModule(ctx, catalogue.Manifest{Module: "mesh-delivery", Version: "1",
|
||||
@@ -860,6 +923,7 @@ func sameMerge(a, b inventory.PlanMerge) bool {
|
||||
// its delivery would skip its turn. It joins the next catalogue batch.
|
||||
func TestALateCatalogueMergeIsNotAnsweredByAnOwnPathWalk(t *testing.T) {
|
||||
open := windowed(t)
|
||||
everyHeadWaits(t)
|
||||
asksWithPaths(t)
|
||||
ctx := t.Context()
|
||||
for _, m := range []struct {
|
||||
|
||||
@@ -48,6 +48,10 @@ func gatherBatches(ctx context.Context, inv *inventory.Inventory, now time.Time)
|
||||
if f.atMost.Before(f.closed) {
|
||||
f.closed = f.atMost
|
||||
}
|
||||
if w.Batch.CutAtOnce && !b.Created.IsZero() {
|
||||
// Its window closed when it was made, which is its latest too (ADR 0304 decision 1).
|
||||
f.atMost, f.closed = b.Created, b.Created
|
||||
}
|
||||
}
|
||||
if f.behind != "" {
|
||||
if walk, err := inv.PlanByID(ctx, f.behind); err == nil {
|
||||
|
||||
@@ -0,0 +1,207 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"fmt"
|
||||
"sort"
|
||||
|
||||
"github.com/nats-io/nats.go"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/conditions"
|
||||
)
|
||||
|
||||
// **A filling bucket or log is said before it is full** (novox/hq ADR 0297 §6, issue 501).
|
||||
//
|
||||
// A module's bucket and its log each have a cap on the bus, and when either is full the bus refuses
|
||||
// the next write: the module stops doing what it writes for, and nothing said so before. On
|
||||
// 2026-10-11 the issue tracker's bucket held a sixth of its cap after two days, growing toward a stop
|
||||
// nobody would have heard coming. So the self-check reads every module's bucket and log, and one at
|
||||
// fillRaiseAt of its cap or more raises a condition naming the module, the bucket or log, and how full
|
||||
// it is.
|
||||
//
|
||||
// **Cleared by observation below fillClearBelow, not below fillRaiseAt**: a bucket or log hovering at
|
||||
// its threshold would otherwise be raised and cleared on every run. Between the two, an open condition
|
||||
// is kept and none is raised.
|
||||
//
|
||||
// **One that cannot be read is said, and the rest are still judged.** An unanswered question about one
|
||||
// stream is no reason to know nothing of the others: it is a finding of its own, naming the bucket or
|
||||
// log and why, and a fill condition already open for it is kept, because not knowing is not a pass.
|
||||
|
||||
// The fill thresholds, in percent of a bucket's or log's cap.
|
||||
const (
|
||||
fillRaiseAt = 75
|
||||
fillClearBelow = 70
|
||||
)
|
||||
|
||||
// The conditions the fill probe raises: one filling, and one that could not be read.
|
||||
const (
|
||||
kindBucketOrLogFilling = "bucket-or-log-filling"
|
||||
kindBucketOrLogUnread = "bucket-or-log-unread"
|
||||
)
|
||||
|
||||
// probeFillID is the probe's id in the registry.
|
||||
const probeFillID = "D-fill"
|
||||
|
||||
// bucketOrLog is one module's bucket or log as the fill probe reads it.
|
||||
type bucketOrLog struct {
|
||||
Module string
|
||||
// Kind is `bucket` or `log`; Name its local name; Stream the stream it is on the bus.
|
||||
Kind, Name, Stream string
|
||||
}
|
||||
|
||||
// filled is how full one bucket or log is, read from the bus.
|
||||
type filled struct {
|
||||
Bytes, Max uint64
|
||||
}
|
||||
|
||||
// percent is how full, in whole percent, rounded down.
|
||||
func (f filled) percent() uint64 {
|
||||
if f.Max == 0 {
|
||||
return 0
|
||||
}
|
||||
return f.Bytes * 100 / f.Max
|
||||
}
|
||||
|
||||
// fillKey is where a bucket's or log's fill condition is kept.
|
||||
func fillKey(s bucketOrLog) string { return conditions.Key(conditions.ScopeBus, s.Stream, "filling") }
|
||||
|
||||
// fillObservation is what one bucket's or log's fill says: a finding at fillRaiseAt or above, and,
|
||||
// while its condition is open, at fillClearBelow or above too; nothing otherwise, which is what clears
|
||||
// it. The operator's words are the kind's (plain_words.go); the summary and the evidence name the
|
||||
// module, the bucket or log, and the fill.
|
||||
func fillObservation(s bucketOrLog, f filled, open bool) (conditions.Observation, bool) {
|
||||
if f.Max == 0 {
|
||||
return conditions.Observation{}, false // one with no cap cannot fill
|
||||
}
|
||||
// Compared in bytes, not rounded percent: 74.9% is not 75%.
|
||||
atRaise := f.Bytes*100 >= f.Max*fillRaiseAt
|
||||
aboveClear := f.Bytes*100 >= f.Max*fillClearBelow
|
||||
if !atRaise && !(open && aboveClear) {
|
||||
return conditions.Observation{}, false
|
||||
}
|
||||
pct := f.percent()
|
||||
return conditions.Observation{
|
||||
Scope: conditions.ScopeBus, ID: s.Stream, Token: "filling", Kind: kindBucketOrLogFilling,
|
||||
Severity: conditions.Warning,
|
||||
Summary: fmt.Sprintf("%s's %s %s holds %s of %s, %d%%: at its cap the bus refuses the module's next write",
|
||||
s.Module, s.Kind, s.Name, mibWords(f.Bytes), mibWords(f.Max), pct),
|
||||
Said: fmt.Sprintf("module %s, %s %s (stream %s): %d of %d bytes, %d%%", s.Module, s.Kind, s.Name,
|
||||
s.Stream, f.Bytes, f.Max, pct),
|
||||
}, true
|
||||
}
|
||||
|
||||
// unreadObservation says one bucket or log could not be read, and why. Asked over the network, so one
|
||||
// look can be wrong: raised on the second look in a row (confirm.go).
|
||||
func unreadObservation(s bucketOrLog, why error) conditions.Observation {
|
||||
return conditions.Observation{
|
||||
Scope: conditions.ScopeBus, ID: s.Stream, Token: "unread", Kind: kindBucketOrLogUnread,
|
||||
Severity: conditions.Warning, Confirm: true,
|
||||
Summary: fmt.Sprintf("%s's %s %s could not be read, so how full it is is not known", s.Module, s.Kind, s.Name),
|
||||
Said: fmt.Sprintf("module %s, %s %s (stream %s): %v", s.Module, s.Kind, s.Name, s.Stream, why),
|
||||
}
|
||||
}
|
||||
|
||||
// keptFilling is an open fill condition said again for a bucket or log that could not be read this
|
||||
// time: not knowing how full it is now is no reason to say it has room. Only ever made from a condition
|
||||
// read back as open — its own summary and severity, never words made up for it.
|
||||
func keptFilling(s bucketOrLog, open conditions.Condition, why error) conditions.Observation {
|
||||
return conditions.Observation{
|
||||
Scope: conditions.ScopeBus, ID: s.Stream, Token: "filling", Kind: kindBucketOrLogFilling,
|
||||
Severity: open.Severity, Summary: open.Summary,
|
||||
Said: fmt.Sprintf("module %s, %s %s (stream %s): not read this time (%v); kept open as it was",
|
||||
s.Module, s.Kind, s.Name, s.Stream, why),
|
||||
}
|
||||
}
|
||||
|
||||
// mibWords is a size as a person reads it, in MiB with one decimal.
|
||||
func mibWords(b uint64) string {
|
||||
return fmt.Sprintf("%.1f MiB", float64(b)/(1024*1024))
|
||||
}
|
||||
|
||||
// readFill is how full one bucket or log is on the bus; found false when it is not on the bus.
|
||||
type readFill func(ctx context.Context, s bucketOrLog) (f filled, found bool, err error)
|
||||
|
||||
// openFill is the fill condition open under a key, if one is, or why it could not be read.
|
||||
type openFill func(ctx context.Context, key string) (conditions.Condition, bool, error)
|
||||
|
||||
// judgeFills judges every bucket and log on its own: one that cannot be read is said as unread, with
|
||||
// its fill condition kept only when that condition was read back and is open — when it cannot be read
|
||||
// either, nothing is said of its fill, which the unread finding already covers. Every other is judged
|
||||
// by its fill; for one of those, a condition that cannot be read is taken as open, so an unknown never
|
||||
// clears a fill measured between fillClearBelow and fillRaiseAt.
|
||||
func judgeFills(ctx context.Context, all []bucketOrLog, read readFill, open openFill) []conditions.Observation {
|
||||
var out []conditions.Observation
|
||||
for _, s := range all {
|
||||
f, found, err := read(ctx, s)
|
||||
if err != nil {
|
||||
out = append(out, unreadObservation(s, err))
|
||||
if c, isOpen, cerr := open(ctx, fillKey(s)); cerr == nil && isOpen {
|
||||
out = append(out, keptFilling(s, c, err))
|
||||
}
|
||||
continue
|
||||
}
|
||||
if !found {
|
||||
continue // not on the bus: created on the controller's next raise, and nothing there can fill
|
||||
}
|
||||
_, isOpen, cerr := open(ctx, fillKey(s))
|
||||
isOpen = isOpen || cerr != nil
|
||||
if o, said := fillObservation(s, f, isOpen); said {
|
||||
out = append(out, o)
|
||||
}
|
||||
}
|
||||
sort.SliceStable(out, func(i, j int) bool { return out[i].Key() < out[j].Key() })
|
||||
return out
|
||||
}
|
||||
|
||||
// declaredBucketsAndLogs is every module's bucket and log the catalogue declares, by its stream.
|
||||
func declaredBucketsAndLogs(ctx context.Context, d *doctor) ([]bucketOrLog, error) {
|
||||
buckets, err := d.open.inventory.DeclaredBuckets(ctx)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
logs, err := d.open.inventory.DeclaredLogs(ctx)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
var out []bucketOrLog
|
||||
for _, b := range buckets {
|
||||
out = append(out, bucketOrLog{Module: b.Module, Kind: "bucket", Name: b.Name, Stream: "KV_" + b.Bucket()})
|
||||
}
|
||||
for _, l := range logs {
|
||||
out = append(out, bucketOrLog{Module: l.Module, Kind: "log", Name: l.Name, Stream: l.Stream()})
|
||||
}
|
||||
return out, nil
|
||||
}
|
||||
|
||||
// probeFill reads every module's bucket and log on the bus and says each one filling toward its cap,
|
||||
// and each one that could not be read.
|
||||
func probeFill(ctx context.Context, d *doctor) ([]conditions.Observation, error) {
|
||||
all, err := declaredBucketsAndLogs(ctx, d)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
js := d.js.Context()
|
||||
read := func(ctx context.Context, s bucketOrLog) (filled, bool, error) {
|
||||
if err := ctx.Err(); err != nil {
|
||||
return filled{}, false, err
|
||||
}
|
||||
info, err := js.StreamInfo(s.Stream, nats.Context(ctx))
|
||||
switch {
|
||||
case errors.Is(err, nats.ErrStreamNotFound):
|
||||
return filled{}, false, nil
|
||||
case err != nil:
|
||||
return filled{}, false, err
|
||||
case info.Config.MaxBytes <= 0:
|
||||
return filled{}, true, nil
|
||||
}
|
||||
return filled{Bytes: info.State.Bytes, Max: uint64(info.Config.MaxBytes)}, true, nil
|
||||
}
|
||||
open := func(ctx context.Context, key string) (conditions.Condition, bool, error) {
|
||||
if d.keeper == nil {
|
||||
return conditions.Condition{}, false, nil
|
||||
}
|
||||
return d.keeper.Get(ctx, key)
|
||||
}
|
||||
return judgeFills(ctx, all, read, open), nil
|
||||
}
|
||||
@@ -0,0 +1,165 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/conditions"
|
||||
)
|
||||
|
||||
// **A filling log or bucket is said at three quarters of its cap and cleared below seven tenths**
|
||||
// (novox/hq ADR 0297 §6): raised at 75% naming the module, the bucket or log and its fill; not at 74.9%;
|
||||
// kept between 70% and 75% while it is open, and not raised there when it is not; and cleared — said no
|
||||
// more — once it reads below 70%, open or not.
|
||||
func TestAFillingBucketOrLogIsRaisedAtThreeQuartersAndClearedBelowSevenTenths(t *testing.T) {
|
||||
const mib = 1024 * 1024
|
||||
log := bucketOrLog{Module: "mesh-issues", Kind: "log", Name: "changes", Stream: "LOG_mesh-issues_changes"}
|
||||
bucket := bucketOrLog{Module: "mesh-issues", Kind: "bucket", Name: "issues", Stream: "KV_mesh-issues_issues"}
|
||||
for _, c := range []struct {
|
||||
name string
|
||||
of bucketOrLog
|
||||
bytes uint64
|
||||
max uint64
|
||||
open bool
|
||||
said bool
|
||||
}{
|
||||
{"a log at exactly 75%", log, 768 * mib, 1024 * mib, false, true},
|
||||
{"a bucket at exactly 75%", bucket, 48 * mib, 64 * mib, false, true},
|
||||
{"a bucket full", bucket, 64 * mib, 64 * mib, false, true},
|
||||
{"a log just under 75%", log, 768*mib - 1, 1024 * mib, false, false},
|
||||
{"a bucket at 72%, not open", bucket, 64 * mib * 72 / 100, 64 * mib, false, false},
|
||||
{"a bucket at 72%, open: kept", bucket, 64 * mib * 72 / 100, 64 * mib, true, true},
|
||||
{"a log at exactly 70%, open: kept", log, 700 * mib, 1000 * mib, true, true},
|
||||
{"a log just under 70%, open: cleared", log, 700*mib - 1, 1000 * mib, true, false},
|
||||
{"a bucket at 10%, open: cleared", bucket, 64 * mib / 10, 64 * mib, true, false},
|
||||
{"a bucket with no cap", bucket, 100, 0, true, false},
|
||||
} {
|
||||
o, said := fillObservation(c.of, filled{Bytes: c.bytes, Max: c.max}, c.open)
|
||||
if said != c.said {
|
||||
t.Errorf("%s: said %v, want %v", c.name, said, c.said)
|
||||
continue
|
||||
}
|
||||
if !said {
|
||||
continue
|
||||
}
|
||||
if o.Key() != fillKey(c.of) || o.Kind != kindBucketOrLogFilling || o.Severity != conditions.Warning {
|
||||
t.Errorf("%s: raised as %s (%s, %s)", c.name, o.Key(), o.Kind, o.Severity)
|
||||
}
|
||||
for _, part := range []string{c.of.Module, c.of.Kind + " " + c.of.Name, "%", " of "} {
|
||||
if !strings.Contains(o.Summary, part) {
|
||||
t.Errorf("%s: does not name %q: %q", c.name, part, o.Summary)
|
||||
}
|
||||
}
|
||||
if !strings.Contains(o.Said, "bytes") {
|
||||
t.Errorf("%s: the evidence does not say the fill in bytes: %q", c.name, o.Said)
|
||||
}
|
||||
}
|
||||
o, _ := fillObservation(log, filled{Bytes: 800 * mib, Max: 1024 * mib}, false)
|
||||
if !strings.Contains(o.Summary, "800.0 MiB of 1024.0 MiB, 78%") {
|
||||
t.Errorf("the fill is said as %q", o.Summary)
|
||||
}
|
||||
}
|
||||
|
||||
// **One bucket or log that cannot be read does not stop the others being judged** (review of #231): it is
|
||||
// said as unread with its reason, a fill condition open for it is kept, and every other bucket and log
|
||||
// is judged by its own fill.
|
||||
func TestAnUnreadableBucketOrLogIsSaidAndTheRestAreStillJudged(t *testing.T) {
|
||||
const mib = 1024 * 1024
|
||||
broken := bucketOrLog{Module: "a", Kind: "bucket", Name: "broken", Stream: "KV_a_broken"}
|
||||
brokenOpen := bucketOrLog{Module: "a", Kind: "log", Name: "was-filling", Stream: "LOG_a_was-filling"}
|
||||
full := bucketOrLog{Module: "b", Kind: "log", Name: "changes", Stream: "LOG_b_changes"}
|
||||
empty := bucketOrLog{Module: "c", Kind: "bucket", Name: "quiet", Stream: "KV_c_quiet"}
|
||||
absent := bucketOrLog{Module: "d", Kind: "bucket", Name: "not-yet", Stream: "KV_d_not-yet"}
|
||||
refusal := errors.New("the bus did not answer")
|
||||
read := func(_ context.Context, s bucketOrLog) (filled, bool, error) {
|
||||
switch s {
|
||||
case broken, brokenOpen:
|
||||
return filled{}, false, refusal
|
||||
case full:
|
||||
return filled{Bytes: 900 * mib, Max: 1000 * mib}, true, nil
|
||||
case empty:
|
||||
return filled{Bytes: 1, Max: 64 * mib}, true, nil
|
||||
}
|
||||
return filled{}, false, nil
|
||||
}
|
||||
open := func(_ context.Context, key string) (conditions.Condition, bool, error) {
|
||||
if key == fillKey(brokenOpen) {
|
||||
return conditions.Condition{Key: key, Severity: conditions.Warning,
|
||||
Summary: "a's log was-filling holds 800.0 MiB of 1024.0 MiB, 78%"}, true, nil
|
||||
}
|
||||
return conditions.Condition{}, false, nil
|
||||
}
|
||||
got := map[string]conditions.Observation{}
|
||||
for _, o := range judgeFills(context.Background(), []bucketOrLog{broken, brokenOpen, full, empty, absent}, read, open) {
|
||||
got[o.Key()] = o
|
||||
}
|
||||
for _, s := range []bucketOrLog{broken, brokenOpen} {
|
||||
o, said := got[conditions.Key(conditions.ScopeBus, s.Stream, "unread")]
|
||||
if !said || o.Kind != kindBucketOrLogUnread || !o.Confirm || !strings.Contains(o.Said, refusal.Error()) {
|
||||
t.Errorf("%s could not be read and was said as %+v", s.Stream, o)
|
||||
}
|
||||
}
|
||||
if o, kept := got[fillKey(brokenOpen)]; !kept || !strings.Contains(o.Said, "kept open") {
|
||||
t.Errorf("an open fill condition of a log not read this time was not kept: %+v", o)
|
||||
}
|
||||
if _, said := got[fillKey(broken)]; said {
|
||||
t.Error("a bucket not read and not filling was said filling")
|
||||
}
|
||||
if o, said := got[fillKey(full)]; !said || o.Kind != kindBucketOrLogFilling {
|
||||
t.Errorf("a log at 90%% beside an unreadable one was not judged: %+v", got)
|
||||
}
|
||||
if len(got) != 4 {
|
||||
t.Errorf("said %d findings, want 4 (two unread, one kept, one filling): %v", len(got), got)
|
||||
}
|
||||
}
|
||||
|
||||
// Both kinds have plain words of their own, which hold to the plain rule (novox/hq ADR 0253).
|
||||
func TestAFillingOrUnreadBucketOrLogIsSaidInPlainWords(t *testing.T) {
|
||||
for _, kind := range []string{kindBucketOrLogFilling, kindBucketOrLogUnread} {
|
||||
wording, has := plainWordings[kind]
|
||||
if !has {
|
||||
t.Errorf("%s has no plain words", kind)
|
||||
continue
|
||||
}
|
||||
if why, ok := conditions.PlainWords(wording(conditions.Observation{Kind: kind})); !ok {
|
||||
t.Errorf("%s: %s", kind, why)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// **When neither the bucket or log nor its condition can be read, nothing is said of its fill** (second
|
||||
// review of #231): the unread finding covers it, and no fill is invented for it. For one that is read and
|
||||
// measured between seven tenths and three quarters, a condition that cannot be read is taken as open, so
|
||||
// an unknown never clears it.
|
||||
func TestNothingIsSaidOfAFillWhenNeitherItNorItsConditionCanBeRead(t *testing.T) {
|
||||
const mib = 1024 * 1024
|
||||
broken := bucketOrLog{Module: "a", Kind: "log", Name: "changes", Stream: "LOG_a_changes"}
|
||||
between := bucketOrLog{Module: "b", Kind: "bucket", Name: "issues", Stream: "KV_b_issues"}
|
||||
read := func(_ context.Context, s bucketOrLog) (filled, bool, error) {
|
||||
if s == broken {
|
||||
return filled{}, false, errors.New("the bus did not answer")
|
||||
}
|
||||
return filled{Bytes: 72 * mib, Max: 100 * mib}, true, nil
|
||||
}
|
||||
open := func(context.Context, string) (conditions.Condition, bool, error) {
|
||||
return conditions.Condition{}, false, errors.New("the conditions bucket did not answer")
|
||||
}
|
||||
got := map[string]conditions.Observation{}
|
||||
for _, o := range judgeFills(context.Background(), []bucketOrLog{broken, between}, read, open) {
|
||||
got[o.Key()] = o
|
||||
}
|
||||
if o, said := got[fillKey(broken)]; said {
|
||||
t.Fatalf("a fill was said for a log whose fill and condition could not be read: %+v", o)
|
||||
}
|
||||
if _, said := got[conditions.Key(conditions.ScopeBus, broken.Stream, "unread")]; !said {
|
||||
t.Error("the log that could not be read was not said as unread")
|
||||
}
|
||||
if _, kept := got[fillKey(between)]; !kept {
|
||||
t.Error("a bucket at 72% whose condition could not be read was cleared")
|
||||
}
|
||||
if len(got) != 2 {
|
||||
t.Errorf("said %d findings, want 2: %v", len(got), got)
|
||||
}
|
||||
}
|
||||
@@ -835,6 +835,9 @@ type answers struct {
|
||||
// public name on the machine went dark. The holds were correct; they were recorded only in the
|
||||
// machine's own state file, and the one visible symptom was a count that did not add up.
|
||||
untaken map[string]map[string]int
|
||||
// leftOut is, per machine, every module of its set its composition leaves out, and why (novox/hq issue
|
||||
// 380): assigned and not applied, which every push said only in passing. Not well while there is any.
|
||||
leftOut map[string][]leftOutModule
|
||||
// unheld is every module on a machine whose resources are applied through a seat nothing on
|
||||
// that machine holds (novox/hq ADR 0207), with the modules that could hold it. Reported, not
|
||||
// refused, until the switch — and while there is any, the mesh is not all well: the order the
|
||||
@@ -863,6 +866,10 @@ type answers struct {
|
||||
// applied, is not well: an assignment somebody made is not made yet, or will not be.
|
||||
pending []inventory.PendingAssignment
|
||||
pendingUnread string
|
||||
// lastSent is every machine's last recorded send, by name, with what the machine answered of it (novox/hq
|
||||
// issue 485); lastSentUnread why it could not be read.
|
||||
lastSent map[string]inventory.Send
|
||||
lastSentUnread string
|
||||
}
|
||||
|
||||
// heldBy is every artifact this mesh has built, for a build that may need one as its base.
|
||||
|
||||
@@ -153,8 +153,97 @@ type forgeFacts struct {
|
||||
}
|
||||
|
||||
// askTheForge asks the forge, through its module's tools on the bus, for a repository's id and its branch's
|
||||
// protection. A variable so a test needs no forge.
|
||||
// protection, waiting out a forge not served for a moment (novox/hq issue 486). A variable so a test needs no
|
||||
// forge.
|
||||
var askTheForge = func(ctx context.Context, owner, repo, branch string) (forgeFacts, error) {
|
||||
return forgeWaitedOut(ctx, forgeWait, owner+"/"+repo, func(ctx context.Context) (forgeFacts, error) {
|
||||
return askTheForgeOnce(ctx, owner, repo, branch)
|
||||
})
|
||||
}
|
||||
|
||||
// waitOut bounds how long a question is asked again while its answer is "not now": a pause of first, doubling
|
||||
// to most, for at most bound in all. now and sleep are the clock, so a test waits in no real time.
|
||||
type waitOut struct {
|
||||
bound, first, most time.Duration
|
||||
now func() time.Time
|
||||
sleep func(context.Context, time.Duration) error
|
||||
}
|
||||
|
||||
// forgeWait is the registration's wait for the forge (novox/hq issue 486). On 2026-10-11 a build's registration
|
||||
// asked the forge while node-tools on the control-node re-served after a rollout of the tool runner, heard
|
||||
// "nothing serves gitea.gitea_api", and failed its plan; the forge answered again seconds later. A re-serve takes
|
||||
// about 10 s, so 60 s waits one out with room to spare. It is a cap on the whole wait, an ask in flight included:
|
||||
// the registration holds the controller's one receive loop while it waits, and a loop held two minutes reads as
|
||||
// deaf. The pauses are those the build machine waits the registry with (novox/hq issue 457).
|
||||
var forgeWait = waitOut{bound: 60 * time.Second, first: time.Second, most: 10 * time.Second,
|
||||
now: time.Now, sleep: sleepOrDone}
|
||||
|
||||
// sleepOrDone pauses for d, or less when ctx ends first.
|
||||
func sleepOrDone(ctx context.Context, d time.Duration) error {
|
||||
t := time.NewTimer(d)
|
||||
defer t.Stop()
|
||||
select {
|
||||
case <-ctx.Done():
|
||||
return ctx.Err()
|
||||
case <-t.C:
|
||||
return nil
|
||||
}
|
||||
}
|
||||
|
||||
// forgeNotNow is an answer that says the forge's tool is not served now — the tool runner re-serving — not that
|
||||
// the forge refused. Only that is asked again: a refusal, an unreadable answer or a repository with no id is the
|
||||
// forge's word, and a tool that did not answer in time has already held the receive loop its whole wait.
|
||||
func forgeNotNow(err error) bool { return errors.Is(err, link.ErrNothingServes) }
|
||||
|
||||
// forgeWaitedOut asks the forge about repository, asking again while it answers "not served now", all of it
|
||||
// within w's bound, an ask in flight included (novox/hq issue 486). Past the bound it fails, saying it waited,
|
||||
// for how long, and what the forge last said; when the caller's own context ends, it says that instead.
|
||||
func forgeWaitedOut(ctx context.Context, w waitOut, repository string,
|
||||
ask func(context.Context) (forgeFacts, error)) (forgeFacts, error) {
|
||||
capped, cancel := context.WithTimeout(ctx, w.bound)
|
||||
defer cancel()
|
||||
began := w.now()
|
||||
pause := w.first
|
||||
for asked := 1; ; asked++ {
|
||||
facts, err := ask(capped)
|
||||
if err == nil {
|
||||
if asked > 1 {
|
||||
fmt.Printf("the forge answered about %s again, after %s (novox/hq issue 486)\n", repository,
|
||||
w.now().Sub(began).Round(time.Second))
|
||||
}
|
||||
return facts, nil
|
||||
}
|
||||
if ctx.Err() != nil {
|
||||
return forgeFacts{}, err // the caller's own context ended: no wait of ours to speak of
|
||||
}
|
||||
gaveUp := func() (forgeFacts, error) {
|
||||
return forgeFacts{}, fmt.Errorf("waited %s for the forge to answer about %s, asking %d times, and it "+
|
||||
"did not (novox/hq issue 486): %w", w.now().Sub(began).Round(time.Second), repository, asked, err)
|
||||
}
|
||||
if capped.Err() != nil {
|
||||
return gaveUp() // the bound ended an ask in flight
|
||||
}
|
||||
if !forgeNotNow(err) {
|
||||
return forgeFacts{}, err
|
||||
}
|
||||
if w.now().Sub(began)+pause > w.bound {
|
||||
return gaveUp()
|
||||
}
|
||||
fmt.Printf("the forge cannot be asked about %s now (%v); asking again in %s, for at most %s in all "+
|
||||
"(novox/hq issue 486)\n", repository, err, pause, w.bound)
|
||||
if serr := w.sleep(capped, pause); serr != nil {
|
||||
if ctx.Err() != nil {
|
||||
return forgeFacts{}, fmt.Errorf("stopped waiting for the forge to answer about %s: %w", repository,
|
||||
ctx.Err())
|
||||
}
|
||||
return gaveUp()
|
||||
}
|
||||
pause = min(2*pause, w.most)
|
||||
}
|
||||
}
|
||||
|
||||
// askTheForgeOnce asks the forge once, through its module's tools on the bus.
|
||||
func askTheForgeOnce(ctx context.Context, owner, repo, branch string) (forgeFacts, error) {
|
||||
js, err := aBus()
|
||||
if err != nil {
|
||||
return forgeFacts{}, err
|
||||
|
||||
@@ -151,13 +151,6 @@ func busCommand(ctx context.Context, args []string) error {
|
||||
if len(args) > 0 && !strings.HasPrefix(args[0], "-") {
|
||||
sub, args = args[0], args[1:]
|
||||
}
|
||||
// The view's credential, a terminal line like a person's (bus_view.go).
|
||||
switch sub {
|
||||
case "view-credential":
|
||||
return busViewCredential(ctx, args)
|
||||
case "view-revoke":
|
||||
return busViewRevoke(ctx, args)
|
||||
}
|
||||
set := flag.NewFlagSet("bus", flag.ContinueOnError)
|
||||
snapshot := set.String("snapshot-taken", "", "where the streams' snapshot a person took is, while the mesh takes none itself")
|
||||
reversible := set.Bool("reversible", false, "the new version can be undone by putting the old one back")
|
||||
@@ -167,14 +160,14 @@ func busCommand(ctx context.Context, args []string) error {
|
||||
if rest, err := parseAround(set, args); err != nil {
|
||||
return err
|
||||
} else if len(rest) > 0 {
|
||||
return errors.New(busUsage)
|
||||
return errors.New("bus [upgrade --why … --reversible|--irreversible [--snapshot-taken <where>]]")
|
||||
}
|
||||
switch sub {
|
||||
case "":
|
||||
return busStatus(ctx)
|
||||
case "upgrade":
|
||||
default:
|
||||
return fmt.Errorf("bus says what a bus upgrade would do, or `bus upgrade`, `bus view-credential`, `bus view-revoke` — not %q", sub)
|
||||
return fmt.Errorf("bus says what a bus upgrade would do, or `bus upgrade` — not %q", sub)
|
||||
}
|
||||
// Everything refused before anything is done.
|
||||
if err := why.require("bus upgrade"); err != nil {
|
||||
|
||||
@@ -1,117 +0,0 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"fmt"
|
||||
"net"
|
||||
"strconv"
|
||||
"strings"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/broker"
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
)
|
||||
|
||||
// The view's credential: the one read-only user a page in a browser connects to the bus as, over the
|
||||
// bus module's WebSocket listener (novox/hq research 036, gap G1; broker.KindView).
|
||||
//
|
||||
// **A terminal line, like a person's credential** (operator.go): printed once, never stored — the mesh
|
||||
// keeps a hash — and revoked by forgetting the row, which the next composition of the user list makes
|
||||
// real. There is one view; issuing it again rotates its password.
|
||||
const busUsage = "bus [upgrade --why … --reversible|--irreversible [--snapshot-taken <where>] | view-credential | view-revoke]"
|
||||
|
||||
// busWebSocketPort is the port the bus module's WebSocket listener is published on, mirrored from the
|
||||
// nats module's manifest (its `bus-websocket` opening), because the credential names where to connect
|
||||
// and the controller does not read the module's configuration. Reached across the overlay only: the
|
||||
// opening is from the mesh, and the mesh's filter admits nothing else.
|
||||
const busWebSocketPort = 4223
|
||||
|
||||
func busViewCredential(ctx context.Context, args []string) error {
|
||||
if len(args) != 0 {
|
||||
return errors.New("bus view-credential takes nothing: there is one view, and this prints its credential once")
|
||||
}
|
||||
open, err := openStores(ctx)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
defer open.Close()
|
||||
inv := open.inventory
|
||||
|
||||
// Refused here rather than at the next composition, where it would stop the whole file.
|
||||
if _, err := broker.PermissionsFor(broker.Principal{Kind: broker.KindView, PasswordHash: "x"}); err != nil {
|
||||
return err
|
||||
}
|
||||
password, err := inv.MintBusPassword(ctx, inventory.BusUser{Username: broker.ViewUser, Kind: inventory.BusView})
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
where, err := broker.FromEnvironment()
|
||||
if err != nil && !errors.Is(err, broker.ErrNotConfigured) {
|
||||
return err
|
||||
}
|
||||
host := where.Address
|
||||
if h, _, err := net.SplitHostPort(where.Address); err == nil {
|
||||
host = h
|
||||
}
|
||||
websocket := ""
|
||||
if host != "" {
|
||||
websocket = "ws://" + net.JoinHostPort(host, strconv.Itoa(busWebSocketPort))
|
||||
}
|
||||
held, err := json.Marshal(struct {
|
||||
WebSocket string `json:"websocket,omitempty"`
|
||||
URL string `json:"url,omitempty"`
|
||||
Fingerprint string `json:"fingerprint,omitempty"`
|
||||
User string `json:"user"`
|
||||
Password string `json:"password"`
|
||||
InboxPrefix string `json:"inbox_prefix"`
|
||||
Hears []string `json:"hears"`
|
||||
Reads string `json:"reads"`
|
||||
HowToRead string `json:"how_to_read"`
|
||||
}{
|
||||
WebSocket: websocket, URL: "nats://" + where.Address, Fingerprint: where.Fingerprint,
|
||||
User: broker.ViewUser, Password: password,
|
||||
// The client must make its inboxes under the view's own prefix: its subscribe grant is
|
||||
// `_INBOX.view.>` and no wider (design 25 §4), and a client's default inbox is not under it.
|
||||
InboxPrefix: "_INBOX." + broker.ViewUser,
|
||||
Hears: broker.ViewHears, Reads: broker.ViewBucket,
|
||||
HowToRead: "direct reads only, no watch (a consumer is refused): list with a request to $JS.API.DIRECT.GET.KV_" +
|
||||
broker.ViewBucket + ` carrying {"multi_last":["$KV.` + broker.ViewBucket + `.>"]}, answered until a 204 status; ` +
|
||||
"read one key with $JS.API.DIRECT.GET.KV_" + broker.ViewBucket + ".$KV." + broker.ViewBucket + ".<number> " +
|
||||
"(nats.js: kvm.open(bucket, {allow_direct: true}), never create); re-read the key an event's number names",
|
||||
})
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
fmt.Printf("issued the view, which hears %s and reads the bucket %s, and nothing else\n",
|
||||
strings.Join(broker.ViewHears, ", "), broker.ViewBucket)
|
||||
fmt.Println(" this is the only time the credential is printed; the mesh keeps a hash")
|
||||
fmt.Println(" it works once the bus has been told, which is the next push to the machine holding mesh-broker —")
|
||||
fmt.Println(" and while a new build of the bus module waits for that machine, the next `bus upgrade` a person starts,")
|
||||
fmt.Println(" which is also what brings the WebSocket listener it connects through")
|
||||
fmt.Println()
|
||||
fmt.Println(string(held))
|
||||
return nil
|
||||
}
|
||||
|
||||
func busViewRevoke(ctx context.Context, args []string) error {
|
||||
if len(args) != 0 {
|
||||
return errors.New("bus view-revoke takes nothing: there is one view")
|
||||
}
|
||||
open, err := openStores(ctx)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
defer open.Close()
|
||||
|
||||
if err := open.inventory.ForgetBusUser(ctx, broker.ViewUser); err != nil {
|
||||
return err
|
||||
}
|
||||
// **Revoked at the next composition, not now** — as a person is (operator revoke): the bus's users
|
||||
// are a file, and the credential stops working when the file no longer names it.
|
||||
fmt.Println("the view is forgotten, and its credential stops working at the next composition — " +
|
||||
"push the machine holding mesh-broker to make it so")
|
||||
return nil
|
||||
}
|
||||
@@ -2,6 +2,7 @@ package main
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"slices"
|
||||
"sort"
|
||||
"strings"
|
||||
|
||||
@@ -28,6 +29,14 @@ func changePlanOf(repository, base, head string, r mergeReach, entries []invento
|
||||
for _, e := range entries {
|
||||
byName[e.Manifest.Module] = e
|
||||
}
|
||||
// The machine holding the bus, whose declaration carries every module's grants (novox/hq issue 490).
|
||||
holder := ""
|
||||
for _, e := range entries {
|
||||
if e.Manifest.BusUsers != "" && e.Manifest.ClaimsSeat(catalogue.BrokerSeat) && len(e.On) > 0 {
|
||||
holder = e.On[0]
|
||||
}
|
||||
}
|
||||
var granting []string
|
||||
machines := map[string]*link.MachinePlan{}
|
||||
machine := func(name string) *link.MachinePlan {
|
||||
if machines[name] == nil {
|
||||
@@ -50,6 +59,10 @@ func changePlanOf(repository, base, head string, r mergeReach, entries []invento
|
||||
machine(on).Receives = append(machine(on).Receives, name)
|
||||
}
|
||||
}
|
||||
if !waits && holder != "" && !(len(e.On) == 1 && e.On[0] == holder) && len(e.On) > 0 &&
|
||||
!slices.Contains(granting, name) {
|
||||
granting = append(granting, name)
|
||||
}
|
||||
switch {
|
||||
case (name == "nats" || catalogue.ProvidesBus(e.Manifest)) && len(e.On) > 0:
|
||||
// Said before the merge (novox/hq issue 336): a new bus build holds every send to the bus's machine
|
||||
@@ -76,6 +89,13 @@ func changePlanOf(repository, base, head string, r mergeReach, entries []invento
|
||||
}
|
||||
}
|
||||
}
|
||||
if len(granting) > 0 {
|
||||
// Said before the merge (novox/hq issue 490): what the walk does when the change alters the bus's
|
||||
// user list. Whether it does is known only once the builds are registered, so it is said as a rule.
|
||||
p.Steps = append(p.Steps, fmt.Sprintf("%s: if this changes what the bus's user list says (a new tool, "+
|
||||
"subject or user), %s is sent that list alone, every build there kept, before %s is judged on its first "+
|
||||
"machine", grantsStepWord, holder, strings.Join(granting, ", ")))
|
||||
}
|
||||
var names []string
|
||||
for name := range machines {
|
||||
names = append(names, name)
|
||||
@@ -88,6 +108,10 @@ func changePlanOf(repository, base, head string, r mergeReach, entries []invento
|
||||
return p
|
||||
}
|
||||
|
||||
// grantsStepWord names the grants step (novox/hq issue 490): the bus's user list sent alone to the machine
|
||||
// holding the bus ahead of a walk's gate. Not the bus step, which replaces the bus itself.
|
||||
const grantsStepWord = "grants step"
|
||||
|
||||
// busUpgradeNeeded is how a change plan says that merging it holds the bus's machine for a person's step.
|
||||
const busUpgradeNeeded = "merging this needs a person's bus upgrade"
|
||||
|
||||
|
||||
@@ -179,6 +179,14 @@ func moduleCheckFor(paths []string, longestMachine int, out io.Writer) error {
|
||||
}
|
||||
fmt.Fprintf(out, ", keeps state %s", strings.Join(kept, ", "))
|
||||
}
|
||||
// And the logs it keeps, with their caps (novox/hq ADR 0297).
|
||||
if len(m.Logs) > 0 {
|
||||
kept := make([]string, 0, len(m.Logs))
|
||||
for _, l := range m.Logs {
|
||||
kept = append(kept, fmt.Sprintf("%s (%d MiB)", l.Name, l.Cap()))
|
||||
}
|
||||
fmt.Fprintf(out, ", keeps log %s", strings.Join(kept, ", "))
|
||||
}
|
||||
if len(m.Reads) > 0 {
|
||||
fmt.Fprintf(out, ", reads %s", strings.Join(m.Reads, ", "))
|
||||
}
|
||||
|
||||
@@ -6,8 +6,10 @@ import (
|
||||
"path/filepath"
|
||||
"strings"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/catalogue"
|
||||
"testing"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/beside"
|
||||
"github.com/novox/mesh-controller/internal/catalogue"
|
||||
)
|
||||
|
||||
// The check anybody can run is the check registration runs (novox/hq issue 148, ADR 0037): a manifest
|
||||
@@ -56,10 +58,7 @@ func TestModuleCheckJudgesBetweenTheManifestsGiven(t *testing.T) {
|
||||
|
||||
// The real catalogue passes the command, the way it passes the test that used to be the only check.
|
||||
func TestModuleCheckPassesTheCatalogue(t *testing.T) {
|
||||
root := filepath.Join("..", "..", "..", "mesh-catalog", "modules")
|
||||
if _, err := os.Stat(root); err != nil {
|
||||
t.Skipf("catalogue sibling not present: %v", err)
|
||||
}
|
||||
root := beside.Catalogue(t)
|
||||
paths, err := manifestsUnder(root)
|
||||
if err != nil || len(paths) == 0 {
|
||||
t.Fatalf("no manifests under %s: %v", root, err)
|
||||
|
||||
@@ -5,6 +5,8 @@ import (
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"path"
|
||||
"regexp"
|
||||
"runtime/debug"
|
||||
"slices"
|
||||
"sort"
|
||||
"strings"
|
||||
@@ -159,9 +161,7 @@ func (f following) PullUpdated(ctx context.Context, p link.PullUpdated) error {
|
||||
return u, err == nil
|
||||
})
|
||||
fmt.Print(planText(plan))
|
||||
direct := link.Checked{Owner: p.Owner, Repo: p.Repo, Number: p.Number, Commit: p.Commit,
|
||||
ID: link.NewBuildID(time.Now()), Verdict: "pass", Summary: noModuleTouched,
|
||||
Gate: &link.CheckLayer{Verdict: "pass", Summary: noModuleTouched}, Plan: &plan}
|
||||
direct := directVerdict(p, plan)
|
||||
switch {
|
||||
case !scope.gated() && !scope.Mesh:
|
||||
fmt.Printf("%s/%s#%d (%.8s): %s, and the repository is not the mesh's: said, nothing run\n",
|
||||
@@ -199,6 +199,24 @@ func (f following) PullUpdated(ctx context.Context, p link.PullUpdated) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
// directVerdict is the verdict of a change no build judges — it touches no module, and either the repository is not
|
||||
// the mesh's or the head holds no merge-check.sh. **It names the trunk commit it holds for** (novox/hq ADR 0323 §3):
|
||||
// the base branch's head the forge announced with the head, so the merge tool can weigh it against the trunk's head
|
||||
// and does not refuse it for ever (a verdict naming no trunk is never the trunk's head's). Nothing was built to
|
||||
// judge: the trunk commit is the one the forge said the change was announced against.
|
||||
func directVerdict(p link.PullUpdated, plan link.ChangePlan) link.Checked {
|
||||
trunk := p.BaseSHA
|
||||
if len(trunk) > 12 {
|
||||
trunk = trunk[:12]
|
||||
}
|
||||
if trunk != "" {
|
||||
plan.Trunk = trunk
|
||||
}
|
||||
return link.Checked{Owner: p.Owner, Repo: p.Repo, Number: p.Number, Commit: p.Commit,
|
||||
ID: link.NewBuildID(time.Now()), Verdict: "pass", Summary: noModuleTouched,
|
||||
Gate: &link.CheckLayer{Verdict: "pass", Summary: noModuleTouched}, Plan: &plan, Trunk: trunk}
|
||||
}
|
||||
|
||||
// checkRequestFor is the ask for one pull request's head: the repository as the mesh clones it, the head,
|
||||
// and what is read beside it.
|
||||
func checkRequestFor(ctx context.Context, open *stores, p link.PullUpdated, scope checkScope,
|
||||
@@ -246,9 +264,11 @@ func checkRequestFor(ctx context.Context, open *stores, p link.PullUpdated, scop
|
||||
if dir == "mesh-controller" {
|
||||
beside["mesh-controller-main"] = link.CheckedOut{Repository: url, Ref: refs["mesh-controller-main"]}
|
||||
if e.Source.Seat != "" {
|
||||
if lab, err := clone(inventory.Source{Seat: e.Source.Seat, Repository: siblingOf(e.Source.Repository,
|
||||
"mesh-lab")}); err == nil {
|
||||
beside["mesh-lab"] = link.CheckedOut{Repository: lab, Ref: refs["mesh-lab"]}
|
||||
for _, sibling := range []string{"mesh-lab", "mesh-sdk"} {
|
||||
if url, err := clone(inventory.Source{Seat: e.Source.Seat, Repository: siblingOf(e.Source.Repository,
|
||||
sibling)}); err == nil {
|
||||
beside[sibling] = link.CheckedOut{Repository: url, Ref: refs[sibling]}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -271,17 +291,54 @@ func checkRequestFor(ctx context.Context, open *stores, p link.PullUpdated, scop
|
||||
// catalogue, whose checkout beside is what tests read its files from, at its main, what the next merge
|
||||
// builds from; and beside the controller its main, for a judge the running controller predates, and the
|
||||
// lab's main, whose replays every check runs. **One rule, read by the check the controller asks for and by
|
||||
// the facts snapshot** (Facts.Beside), so a check run by hand clones what the build seat clones.
|
||||
// the facts snapshot** (Facts.Beside), so a check run by hand clones what the build seat clones. Beside the
|
||||
// controller also the SDK, checked out at the commit the running controller's go.mod pins (sdkPinned), not
|
||||
// one a desktop holds (novox/hq issue 449). The checkout only places the clone: the conformance test reads the
|
||||
// fixtures at the pin of the tree under check, from the clone's history, so a pull request moving the SDK is
|
||||
// judged against the SDK it moves to (internal/link/conformance_test.go).
|
||||
func besideRefs(dir, running string) map[string]string {
|
||||
switch dir {
|
||||
case "mesh-catalog":
|
||||
return map[string]string{dir: "main"}
|
||||
case "mesh-controller":
|
||||
return map[string]string{dir: running, "mesh-controller-main": "main", "mesh-lab": "main"}
|
||||
return map[string]string{dir: running, "mesh-controller-main": "main", "mesh-lab": "main",
|
||||
"mesh-sdk": sdkPinned()}
|
||||
}
|
||||
return map[string]string{dir: running}
|
||||
}
|
||||
|
||||
// sdkModule is the Go module of the SDK the controller is built against.
|
||||
const sdkModule = "git.novox.be/novox/mesh-sdk/go"
|
||||
|
||||
// pseudoCommit is the commit a Go pseudo-version names: v0.1.11-0.20261009143344-f047d0a4a970 → f047d0a4a970.
|
||||
var pseudoCommit = regexp.MustCompile(`-([0-9a-f]{12})$`)
|
||||
|
||||
// sdkPinned is the ref of the SDK repository this controller was built from, as its go.mod pins it and its
|
||||
// build records it: a pseudo-version's commit, or a release's tag (the SDK tags its Go module under go/).
|
||||
// "main" only for a binary that records no SDK version — a local replace — which a running controller is
|
||||
// not (novox/hq issue 449).
|
||||
func sdkPinned() string {
|
||||
info, ok := debug.ReadBuildInfo()
|
||||
if !ok {
|
||||
return "main"
|
||||
}
|
||||
for _, dep := range info.Deps {
|
||||
if dep.Path != sdkModule {
|
||||
continue
|
||||
}
|
||||
if dep.Replace != nil {
|
||||
dep = dep.Replace
|
||||
}
|
||||
if m := pseudoCommit.FindStringSubmatch(dep.Version); m != nil {
|
||||
return m[1]
|
||||
}
|
||||
if strings.HasPrefix(dep.Version, "v") {
|
||||
return "go/" + dep.Version
|
||||
}
|
||||
}
|
||||
return "main"
|
||||
}
|
||||
|
||||
// siblingOf is another repository of the same owner: novox/mesh-controller → novox/mesh-lab.
|
||||
func siblingOf(repository, name string) string {
|
||||
if cut := strings.LastIndex(repository, "/"); cut >= 0 {
|
||||
@@ -322,6 +379,9 @@ func checkedOf(result link.BuildResult) link.Checked {
|
||||
case result.Check != nil:
|
||||
c.Verdict, c.Summary, c.Report = result.Check.Verdict, result.Check.Summary, result.Check.Report
|
||||
c.Gate, c.RepoCheck = result.Check.Gate, result.Check.RepoCheck
|
||||
// What was judged (novox/hq ADR 0323 §3): the head merged into the trunk commit, and the commits of the
|
||||
// repositories read beside it.
|
||||
c.Trunk, c.Beside, c.Took = result.Check.Trunk, result.Check.Beside, result.Check.Took
|
||||
if c.Gate == nil {
|
||||
// A build seat from before the layers: its verdict is the gate's.
|
||||
c.Gate = &link.CheckLayer{Verdict: c.Verdict, Summary: c.Summary}
|
||||
@@ -347,14 +407,20 @@ func checkedOf(result link.BuildResult) link.Checked {
|
||||
}
|
||||
if result.Checked != nil {
|
||||
c.Plan = result.Checked.Plan
|
||||
if c.Plan != nil && c.Trunk != "" {
|
||||
// The kept delivery plan records the trunk commit with its other inputs (ADR 0323 §3).
|
||||
plan := *c.Plan
|
||||
plan.Trunk = c.Trunk
|
||||
c.Plan = &plan
|
||||
}
|
||||
// A delivery group's composed check (novox/hq ADR 0239): every head it judged, this one first.
|
||||
if g := result.Checked; g.Group != "" {
|
||||
c.Group = g.Group
|
||||
c.Members = append(c.Members, link.CheckedMember{Owner: g.Owner, Repo: g.Repo, Number: g.Number,
|
||||
Commit: result.Ref})
|
||||
Commit: result.Ref, Trunk: c.Trunk})
|
||||
for _, m := range g.Members {
|
||||
c.Members = append(c.Members, link.CheckedMember{Owner: m.Owner, Repo: m.Repo, Number: m.Number,
|
||||
Commit: m.Ref})
|
||||
Commit: m.Ref, Trunk: memberTrunk(result.Check, m)})
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -369,6 +435,20 @@ func checkedOf(result link.BuildResult) link.Checked {
|
||||
return c
|
||||
}
|
||||
|
||||
// memberTrunk is the trunk commit the build seat merged one of a group's heads into (novox/hq ADR 0323 §6), empty
|
||||
// when it said none.
|
||||
func memberTrunk(outcome *link.CheckOutcome, m link.GroupMember) string {
|
||||
if outcome == nil {
|
||||
return ""
|
||||
}
|
||||
for _, j := range outcome.Members {
|
||||
if strings.EqualFold(j.Owner, m.Owner) && strings.EqualFold(j.Repo, m.Repo) && strings.HasPrefix(m.Ref, j.Commit) {
|
||||
return j.Trunk
|
||||
}
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
func prefixedAll(prefix string, items []string) []string {
|
||||
out := make([]string, 0, len(items))
|
||||
for _, i := range items {
|
||||
@@ -383,8 +463,12 @@ func sayChecked(ctx context.Context, c link.Checked) {
|
||||
if c.RepoCheck != nil {
|
||||
repo = strings.ToUpper(c.RepoCheck.Verdict) + " — " + c.RepoCheck.Summary
|
||||
}
|
||||
fmt.Printf("%s: %s/%s#%d at %.8s checked on %s: gate %s — %s; repository %s\n", c.ID, c.Owner, c.Repo, c.Number,
|
||||
c.Commit, orSomewhere(c.On), strings.ToUpper(c.Verdict), c.Summary, repo)
|
||||
judged := ""
|
||||
if c.Trunk != "" {
|
||||
judged = " merged into trunk " + c.Trunk
|
||||
}
|
||||
fmt.Printf("%s: %s/%s#%d at %.8s%s checked on %s: gate %s — %s; repository %s\n", c.ID, c.Owner, c.Repo, c.Number,
|
||||
c.Commit, judged, orSomewhere(c.On), strings.ToUpper(c.Verdict), c.Summary, repo)
|
||||
if checkEvents == nil {
|
||||
return
|
||||
}
|
||||
|
||||
@@ -210,3 +210,81 @@ func TestABuildOffTheTrunkIsNeverPublished(t *testing.T) {
|
||||
t.Errorf("a build seat that said nothing was refused: %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
// **A verdict names the trunk commit it judged** (novox/hq ADR 0323 §3, issue 341): the controller's `checked`
|
||||
// carries the head and the trunk commit the build seat merged it into, the commits of the repositories read beside
|
||||
// it, how long it took, and the kept delivery plan records the trunk commit with its other inputs. A group's
|
||||
// composed check names, per member, the trunk commit that head was merged into (§6).
|
||||
func TestAVerdictNamesTheTrunkCommitItJudged(t *testing.T) {
|
||||
plan := &link.ChangePlan{Repository: "novox/mesh-host", Base: "main", Head: "dfb1415aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
|
||||
Summary: "builds mesh-host"}
|
||||
asked := &link.CheckRequest{Owner: "novox", Repo: "mesh-host", Number: 66, Base: "main", Plan: plan}
|
||||
c := checkedOf(link.BuildResult{ID: "b", Ref: "dfb1415aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa", Checked: asked,
|
||||
Check: &link.CheckOutcome{Verdict: "pass", Took: "4m12s", Head: "dfb1415aaaaa", Trunk: "d28ca95bbbbb",
|
||||
Gate: &link.CheckLayer{Verdict: "pass"}, RepoCheck: &link.CheckLayer{Verdict: "pass"},
|
||||
Beside: map[string]string{"mesh-catalog": "0123456789ab", "mesh-lab": "ba9876543210"}}})
|
||||
if c.Trunk != "d28ca95bbbbb" || c.Commit != "dfb1415aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa" {
|
||||
t.Fatalf("the verdict names head %s and trunk %q", c.Commit, c.Trunk)
|
||||
}
|
||||
if c.Beside["mesh-catalog"] != "0123456789ab" || c.Beside["mesh-lab"] != "ba9876543210" {
|
||||
t.Fatalf("the verdict names the repositories read beside it as %v", c.Beside)
|
||||
}
|
||||
if c.Took != "4m12s" {
|
||||
t.Fatalf("the verdict says it took %q", c.Took)
|
||||
}
|
||||
if c.Plan == nil || c.Plan.Trunk != "d28ca95bbbbb" || c.Plan.Head != plan.Head {
|
||||
t.Fatalf("the kept plan records %+v", c.Plan)
|
||||
}
|
||||
if plan.Trunk != "" {
|
||||
t.Fatal("the plan the controller asked with was changed: the verdict's is a copy")
|
||||
}
|
||||
|
||||
group := &link.CheckRequest{Owner: "novox", Repo: "mesh-controller", Number: 7, Base: "main", Group: "feat/x",
|
||||
Members: []link.GroupMember{{Owner: "novox", Repo: "mesh-host", Number: 8, Ref: "cccccccccccc0000", Base: "main"}}}
|
||||
c = checkedOf(link.BuildResult{ID: "g", Ref: "aaaaaaaaaaaa0000", Checked: group, Check: &link.CheckOutcome{
|
||||
Verdict: "pass", Head: "aaaaaaaaaaaa", Trunk: "111111111111", Gate: &link.CheckLayer{Verdict: "pass"},
|
||||
Members: []link.CheckedMember{{Owner: "novox", Repo: "mesh-host", Commit: "cccccccccccc", Trunk: "222222222222"}}}})
|
||||
if len(c.Members) != 2 || c.Members[0].Trunk != "111111111111" || c.Members[1].Trunk != "222222222222" ||
|
||||
c.Members[1].Commit != "cccccccccccc0000" {
|
||||
t.Fatalf("the composed check names its members %+v", c.Members)
|
||||
}
|
||||
}
|
||||
|
||||
// **The merge made for a check is never registered** (novox/hq ADR 0323 §2): a build of it — a commit on no branch
|
||||
// of the forge — is refused, naming the trunk. The rule of ADR 0238 §1 stands unchanged; this holds it for the
|
||||
// merge commit a check makes.
|
||||
func TestABuildOfACheckMergeIsRefusedNamingTheTrunk(t *testing.T) {
|
||||
merge := link.BuildResult{ID: "b", Commit: "4b5c6d7e8f90aabbccddeeff0011223344556677", Trunk: "main"}
|
||||
err := publishable(merge, "")
|
||||
if !errors.Is(err, errOffTheTrunk) || !strings.Contains(err.Error(), "not on main") {
|
||||
t.Fatalf("a build of a check's merge was answered %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
// **A verdict no build judges names its trunk commit too** (novox/hq ADR 0323 §3): a change touching no module of a
|
||||
// repository with no merge-check.sh (novox/mesh-tools-go) is answered by the controller itself. Naming no trunk, the
|
||||
// merge tool refused it, asked again, got the same verdict, and refused for ever.
|
||||
func TestADirectVerdictNamesTheTrunkTheForgeAnnounced(t *testing.T) {
|
||||
p := link.PullUpdated{Owner: "novox", Repo: "mesh-tools-go", Number: 3, Base: "main", Commit: "1a2b3c4d5e6f7a8b9c0d",
|
||||
BaseSHA: "7a8b9c0d1e2f3a4b5c6d7e8f9a0b1c2d3e4f5a6b"}
|
||||
c := directVerdict(p, link.ChangePlan{Repository: "novox/mesh-tools-go", Base: "main", Head: p.Commit})
|
||||
if c.Trunk != "7a8b9c0d1e2f" || c.Plan == nil || c.Plan.Trunk != "7a8b9c0d1e2f" {
|
||||
t.Fatalf("the direct verdict names trunk %q, its plan %+v", c.Trunk, c.Plan)
|
||||
}
|
||||
if c.Verdict != "pass" || c.Commit != p.Commit {
|
||||
t.Fatalf("the direct verdict is %+v", c)
|
||||
}
|
||||
if c := directVerdict(link.PullUpdated{Owner: "novox", Repo: "x", Commit: "abc"}, link.ChangePlan{}); c.Trunk != "" {
|
||||
t.Fatalf("a forge that said no base head gave the trunk %q", c.Trunk)
|
||||
}
|
||||
}
|
||||
|
||||
// A head checked again through mesh-delivery (`delivery check --members`, a recheck) reaches the same direct verdict:
|
||||
// it names the base head the forge last announced, kept on the member, or the merge tool would refuse it for ever.
|
||||
func TestARecheckedHeadsDirectVerdictNamesItsTrunk(t *testing.T) {
|
||||
m := orderMember{ID: "novox/mesh-tools-go@1a2b3c4d5e6f", Repository: "novox/mesh-tools-go", Base: "main",
|
||||
Head: "1a2b3c4d5e6f7a8b9c0d", Number: 3, BaseSHA: "7a8b9c0d1e2f3a4b5c6d7e8f9a0b1c2d3e4f5a6b"}
|
||||
if c := directVerdict(m.pull(), link.ChangePlan{}); c.Trunk != "7a8b9c0d1e2f" {
|
||||
t.Fatalf("a rechecked head's direct verdict names trunk %q", c.Trunk)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -0,0 +1,76 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/conditions"
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
)
|
||||
|
||||
// The looks of the open conditions — how often each was observed, when last, its newest evidence — are
|
||||
// kept in the controller's store, not the conditions bucket (novox/hq issue 420, ADR 0289 §1): the bucket
|
||||
// is written when what a condition says changes, never for a look that saw it as it was.
|
||||
|
||||
// storeLooks keeps the conditions' looks in the inventory.
|
||||
type storeLooks struct{ inv *inventory.Inventory }
|
||||
|
||||
func (s storeLooks) KeepLooks(ctx context.Context, key string, l conditions.Looks) error {
|
||||
evidence, err := json.Marshal(l.Evidence)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
return s.inv.KeepConditionLooks(ctx, inventory.ConditionLooks{Key: key, Observations: l.Observations,
|
||||
LastObserved: l.LastObserved, Evidence: evidence})
|
||||
}
|
||||
|
||||
func (s storeLooks) Looked(ctx context.Context, key string) (conditions.Looks, bool, error) {
|
||||
row, kept, err := s.inv.ConditionLooksOf(ctx, key)
|
||||
if err != nil || !kept {
|
||||
return conditions.Looks{}, kept, err
|
||||
}
|
||||
l, err := looksOf(row)
|
||||
return l, err == nil, err
|
||||
}
|
||||
|
||||
func (s storeLooks) AllLooks(ctx context.Context) (map[string]conditions.Looks, error) {
|
||||
rows, err := s.inv.AllConditionLooks(ctx)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
out := make(map[string]conditions.Looks, len(rows))
|
||||
for key, row := range rows {
|
||||
l, err := looksOf(row)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
out[key] = l
|
||||
}
|
||||
return out, nil
|
||||
}
|
||||
|
||||
func (s storeLooks) ForgetLooks(ctx context.Context, key string) error {
|
||||
return s.inv.ForgetConditionLooks(ctx, key)
|
||||
}
|
||||
|
||||
func looksOf(row inventory.ConditionLooks) (conditions.Looks, error) {
|
||||
l := conditions.Looks{Observations: row.Observations, LastObserved: row.LastObserved.UTC()}
|
||||
if len(row.Evidence) > 0 {
|
||||
if err := json.Unmarshal(row.Evidence, &l.Evidence); err != nil {
|
||||
return conditions.Looks{}, fmt.Errorf("the evidence kept for the condition %s cannot be read: %w", row.Key, err)
|
||||
}
|
||||
}
|
||||
return l, nil
|
||||
}
|
||||
|
||||
// looksHere is where a process that is not the serving controller reads the conditions' looks: the store,
|
||||
// opened for it, closed by the function returned. A store that cannot be opened is said on every condition
|
||||
// read through it, never read as none.
|
||||
func looksHere(ctx context.Context) (conditions.LookStore, func()) {
|
||||
inv, err := openInventory(ctx)
|
||||
if err != nil {
|
||||
return conditions.NoLooks{Err: err}, func() {}
|
||||
}
|
||||
return storeLooks{inv}, inv.Close
|
||||
}
|
||||
@@ -0,0 +1,87 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"context"
|
||||
"encoding/json"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/nats-io/nats.go/jetstream"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/broker"
|
||||
"github.com/novox/mesh-controller/internal/conditions"
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
"github.com/novox/mesh-controller/internal/testbus"
|
||||
)
|
||||
|
||||
// **Looks at an unchanged condition write the bucket once, and `conditions` still says how often and when
|
||||
// it was seen** (novox/hq issue 420): the looks are in the controller's store, and the verb, run as a
|
||||
// process of its own, reads them from there. On 2026-10-10 one open condition had rewritten the bucket 7 003
|
||||
// times in two days.
|
||||
func TestTheConditionsVerbReadsTheLooksTheBucketNoLongerHolds(t *testing.T) {
|
||||
inv := inventory.ForTest(t)
|
||||
bus := testbus.Start(t)
|
||||
serving, err := broker.Dial(bus.ClientURL())
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
defer serving.Close()
|
||||
if err := serving.EnsureControllerBuckets(); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
ctx := t.Context()
|
||||
store, history, err := conditions.OnTheBus(ctx, serving.Conn())
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
k := conditions.NewKeeper(ctx, conditions.Options{Store: store, History: history, Looks: storeLooks{inv}})
|
||||
defer k.Close(context.Background())
|
||||
look := conditions.Observation{Scope: conditions.ScopeMachine, ID: "anchor", Kind: "silent", Machine: "anchor",
|
||||
Severity: conditions.Warning, Summary: "anchor has not been heard from", Source: "S1"}
|
||||
for range 4 {
|
||||
if _, err := k.Observe(ctx, look); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
}
|
||||
|
||||
api, err := jetstream.New(serving.Conn())
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
stream, err := api.Stream(ctx, "KV_"+broker.ConditionsBucket)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
info, err := stream.Info(ctx)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if info.State.LastSeq != 1 {
|
||||
t.Fatalf("four looks at one unchanged condition wrote the bucket %d times, want 1", info.State.LastSeq)
|
||||
}
|
||||
|
||||
// The verb as a process other than the serving controller: it reads the bucket and the store.
|
||||
keptBefore := conditionsFrom
|
||||
conditionsFrom = nil
|
||||
defer func() { conditionsFrom = keptBefore }()
|
||||
t.Setenv(broker.NATSVar, bus.ClientURL())
|
||||
t.Setenv(broker.CertificateVar, "")
|
||||
var shown bytes.Buffer
|
||||
if err := showCondition(ctx, []string{"machine.anchor.silent", "--json"}, &shown); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
var c conditions.Condition
|
||||
if err := json.Unmarshal(shown.Bytes(), &c); err != nil {
|
||||
t.Fatalf("%v: %s", err, shown.String())
|
||||
}
|
||||
if c.Observations != 4 || len(c.Evidence) != 4 || c.LastObserved.IsZero() || c.LooksUnread != "" ||
|
||||
time.Since(c.LastObserved) > time.Minute {
|
||||
t.Fatalf("conditions show reads %d observation(s), %d evidence line(s), last %s (%q)", c.Observations,
|
||||
len(c.Evidence), c.LastObserved, c.LooksUnread)
|
||||
}
|
||||
listed, err := openConditions(ctx)
|
||||
if err != nil || len(listed) != 1 || listed[0].Observations != 4 {
|
||||
t.Fatalf("conditions lists %+v: %v", listed, err)
|
||||
}
|
||||
}
|
||||
@@ -24,16 +24,18 @@ import (
|
||||
// **`status` used to be the only place the mesh said it was wrong, and only to whoever asked.** Every
|
||||
// core failure of research 031 was found by a person looking. A condition is the mesh saying it: raised
|
||||
// by a watchdog when a signal is late (signals.go), by a probe when an invariant does not hold
|
||||
// (doctor.go), or by an event a provider sends (standing.go); kept on the bus with since-when and
|
||||
// evidence; said on the bus as it changes, for the operator's channel to carry; and cleared when an
|
||||
// (doctor.go), or by an event a provider sends (standing.go); kept on the bus with since-when, and its
|
||||
// looks — how often, when last, the newest evidence — in the controller's store (condition_looks.go,
|
||||
// novox/hq issue 420); said on the bus as it changes, for the operator's channel to carry; and cleared when an
|
||||
// observation says it is resolved. Nobody resolves one by hand. A person who knows silences it, for a
|
||||
// while, with a reason, and that is recorded as a hand act.
|
||||
|
||||
// conditionsFrom is the serving controller's keeper; nil in any other process, which opens its own.
|
||||
var conditionsFrom *conditions.Keeper
|
||||
|
||||
// keeperOn is a keeper over the store on a connection, saying its transitions on that connection.
|
||||
func keeperOn(ctx context.Context, conn *nats.Conn) (*conditions.Keeper, error) {
|
||||
// keeperOn is a keeper over the store on a connection, saying its transitions on that connection, with
|
||||
// the conditions' looks kept in looks (condition_looks.go).
|
||||
func keeperOn(ctx context.Context, conn *nats.Conn, looks conditions.LookStore) (*conditions.Keeper, error) {
|
||||
store, history, err := conditions.OnTheBus(ctx, conn)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
@@ -42,7 +44,7 @@ func keeperOn(ctx context.Context, conn *nats.Conn) (*conditions.Keeper, error)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return conditions.NewKeeper(ctx, conditions.Options{Store: store, History: history,
|
||||
return conditions.NewKeeper(ctx, conditions.Options{Store: store, History: history, Looks: looks,
|
||||
Teller: link.OverNATS{Conn: conn, JS: js},
|
||||
Say: func(format string, args ...any) { fmt.Fprintf(os.Stderr, format+"\n", args...) },
|
||||
// What status leads with changed: composed again soon (a nudge outside the serving controller
|
||||
@@ -58,8 +60,10 @@ func withKeeper(ctx context.Context, f func(*conditions.Keeper) error) error {
|
||||
if conditionsFrom != nil {
|
||||
return f(conditionsFrom)
|
||||
}
|
||||
looks, closeLooks := looksHere(ctx)
|
||||
defer closeLooks()
|
||||
return onTheBus(func(conn *nats.Conn) error {
|
||||
k, err := keeperOn(ctx, conn)
|
||||
k, err := keeperOn(ctx, conn, looks)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
@@ -82,6 +86,8 @@ func openConditions(ctx context.Context) ([]conditions.Condition, error) {
|
||||
return nil, fmt.Errorf("this process has no bus to read the conditions from: %w", err)
|
||||
}
|
||||
var out []conditions.Condition
|
||||
looks, closeLooks := looksHere(ctx)
|
||||
defer closeLooks()
|
||||
err := onTheBus(func(conn *nats.Conn) error {
|
||||
store, _, err := conditions.OnTheBus(ctx, conn)
|
||||
if err != nil {
|
||||
@@ -89,7 +95,7 @@ func openConditions(ctx context.Context) ([]conditions.Condition, error) {
|
||||
}
|
||||
reading, cancel := context.WithTimeout(ctx, 5*time.Second)
|
||||
defer cancel()
|
||||
out, err = conditions.Read(reading, store)
|
||||
out, err = conditions.ReadWith(reading, store, looks)
|
||||
return err
|
||||
})
|
||||
return out, err
|
||||
@@ -252,12 +258,14 @@ func showCondition(ctx context.Context, args []string, w io.Writer) error {
|
||||
if conditionsFrom != nil {
|
||||
c, found, err = conditionsFrom.Get(ctx, key)
|
||||
} else {
|
||||
looks, closeLooks := looksHere(ctx)
|
||||
defer closeLooks()
|
||||
err = onTheBus(func(conn *nats.Conn) error {
|
||||
store, _, err := conditions.OnTheBus(ctx, conn)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
c, found, err = conditions.ReadOne(ctx, store, key)
|
||||
c, found, err = conditions.ReadOneWith(ctx, store, looks, key)
|
||||
return err
|
||||
})
|
||||
}
|
||||
|
||||
@@ -0,0 +1,215 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"sort"
|
||||
"time"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/conditions"
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
"github.com/novox/mesh-controller/internal/lease"
|
||||
)
|
||||
|
||||
// **No send but a person's `push <node>` and a gate's own put-back moves the mesh's own core to a build older
|
||||
// than the one its machine was last sent** (novox/hq issue 201). Every send made through sendToEach keeps it — a
|
||||
// plan's, a release's, a healer's, a rotation's, and the bus step too, which is a person's act but composes under
|
||||
// sendKeeps like the rest. On 2026-10-02 two merges a minute apart made two plans;
|
||||
// the controller's plan rolled the new controller, which widened its seat's row, and the node-engine's plan then
|
||||
// sent the control node the controller build before it. The older binary read the row it could not serve and the
|
||||
// mesh lost its voice for ten minutes — the thing that would have corrected it was the thing that was down. ADR
|
||||
// 0185 took the outage out of it (a controller behind its row serves what it can); the race is closed here,
|
||||
// without needing its trigger: whatever made the mesh's record older, the send keeps the build.
|
||||
//
|
||||
// **Kept, not refused.** The send composes the controller or the node-engine at the build the machine was last
|
||||
// sent, as a recorded module is kept (ADR 0245), and carries everything else: no other module, secret, healer or
|
||||
// walk waits on it, and nothing is retried. The kept move is no move for a gate either: ungatedIn and gatedSend
|
||||
// leave it out (withoutKept), so a gate judges the other moves of its send. A plan whose own build is the older one finds its gate superseded by
|
||||
// the build kept there (issue 352) and ends. The mesh's record stays older, and a warning condition says so until
|
||||
// a send carries the record — a person's `push <node>` accepts the older build — or the record moves forward: a
|
||||
// newer merge, or `rebuild mesh-controller`.
|
||||
//
|
||||
// Older is by the builds' registration order — when each was asked (novox/hq issue 219) — never by the commits'
|
||||
// dates. So a retry or a rebuild of an old commit, asked anew, counts as newer: it is registered as the module's
|
||||
// current build by the same order, and the guard does not stop that move. A build that failed its gate is never
|
||||
// ahead: the machine was sent it and the record was put back before it (gateFailed), and if the put-back's own
|
||||
// send was refused, the next send completes it rather than keeping the failed build there. A gate's own put-back
|
||||
// carries its modules back whatever the order (sendScope.puttingBack); the controller's is held to the store's
|
||||
// schema already (issue 352).
|
||||
|
||||
// kindCoreDowngrade is a core module kept at the build its machine was last sent, over an older record.
|
||||
const kindCoreDowngrade = "core-downgrade-kept"
|
||||
|
||||
// coreDowngradeSource is the condition's source: the sends, which raise and clear it.
|
||||
const coreDowngradeSource = "sends"
|
||||
|
||||
// downgradeGuarded is the core components a send may not move backwards: the controller, which reads the
|
||||
// store and its seat's row, and the node-engine, which reads what the controller declares.
|
||||
var downgradeGuarded = []string{lease.ComponentController, lease.ComponentEngine}
|
||||
|
||||
// askedBuild is what the order needs of one build of a module: when it was asked, and whether it failed its gate.
|
||||
type askedBuild struct {
|
||||
asked time.Time
|
||||
failedGate bool
|
||||
}
|
||||
|
||||
// buildAsked is the newest build of a module from a commit that worked — when it was asked (or recorded, when
|
||||
// the request time is not known), and whether it failed its gate — and false when the records hold none. A
|
||||
// variable, so a test reads its own order.
|
||||
var buildAsked = func(ctx context.Context, inv *inventory.Inventory, module, commit string) (askedBuild, bool, error) {
|
||||
builds, err := inv.Builds(ctx, module, askedLookBack)
|
||||
if err != nil {
|
||||
return askedBuild{}, false, err
|
||||
}
|
||||
for _, b := range builds {
|
||||
if b.Worked() && sameCommit(b.Commit, commit) {
|
||||
failed, err := inv.GateFailed(ctx, b.ID)
|
||||
if err != nil {
|
||||
return askedBuild{}, false, err
|
||||
}
|
||||
return askedBuild{asked: b.AskedOrAt(), failedGate: failed}, true, nil
|
||||
}
|
||||
}
|
||||
return askedBuild{}, false, nil
|
||||
}
|
||||
|
||||
// askedLookBack is how many of a module's newest builds are read for when a build was asked.
|
||||
const askedLookBack = 50
|
||||
|
||||
// coreDowngrade is one core module a machine was last sent a build of that is newer than the mesh's record.
|
||||
type coreDowngrade struct {
|
||||
module, node, component string
|
||||
// sent is the build the machine was last sent, record the one the mesh holds.
|
||||
sent, record string
|
||||
sentAsked, recordAsked time.Time
|
||||
}
|
||||
|
||||
func (d coreDowngrade) String() string {
|
||||
return fmt.Sprintf("%s was last sent %s %s, and the mesh holds the older %s (asked %s, before %s): a send there "+
|
||||
"keeps %s; `push %s` sends the older build, and a newer merge or `rebuild %s` moves the record forward "+
|
||||
"(novox/hq issue 201)", d.node, d.module, short(d.sent), short(d.record),
|
||||
d.recordAsked.UTC().Format(time.RFC3339), d.sentAsked.UTC().Format(time.RFC3339), short(d.sent), d.node,
|
||||
d.module)
|
||||
}
|
||||
|
||||
// coreDowngrades is, for one machine, each guarded core module whose record is older than the build the machine
|
||||
// was last sent, leaving out what a gate's own put-back puts back and a sent build that failed its gate. A move
|
||||
// whose either build the records do not hold is not proved older and is left to the gate that judges it. Pure
|
||||
// but for asked.
|
||||
func coreDowngrades(node string, sent map[string]string, record map[string]string, scope sendScope,
|
||||
asked func(module, commit string) (askedBuild, bool, error)) ([]coreDowngrade, error) {
|
||||
var out []coreDowngrade
|
||||
for module, was := range sent {
|
||||
component := coreComponent(module)
|
||||
now := record[module]
|
||||
if !guarded(component) || was == "" || now == "" || sameCommit(was, now) {
|
||||
continue
|
||||
}
|
||||
if scope.puttingBack && scope.modules[module] {
|
||||
continue
|
||||
}
|
||||
from, known, err := asked(module, was)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("when %s's build %s was asked cannot be read: %w", module, short(was), err)
|
||||
}
|
||||
if !known || from.failedGate {
|
||||
continue
|
||||
}
|
||||
to, known, err := asked(module, now)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("when %s's build %s was asked cannot be read: %w", module, short(now), err)
|
||||
}
|
||||
if known && to.asked.Before(from.asked) {
|
||||
out = append(out, coreDowngrade{module: module, node: node, component: component, sent: was, record: now,
|
||||
sentAsked: from.asked, recordAsked: to.asked})
|
||||
}
|
||||
}
|
||||
sort.Slice(out, func(i, j int) bool { return out[i].module < out[j].module })
|
||||
return out, nil
|
||||
}
|
||||
|
||||
func guarded(component string) bool {
|
||||
for _, c := range downgradeGuarded {
|
||||
if c == component {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// coreKept is, for a send that keeps (sendKeeps), each guarded core module of a machine to keep at the build it
|
||||
// was last sent, module → commit, each said and raised as a condition.
|
||||
func coreKept(ctx context.Context, inv *inventory.Inventory, node string, sent map[string]string,
|
||||
current map[string]inventory.CurrentBuild) (map[string]string, error) {
|
||||
record := map[string]string{}
|
||||
for m, c := range current {
|
||||
record[m] = c.Commit
|
||||
}
|
||||
found, err := coreDowngrades(node, sent, record, scopeOf(ctx), func(module, commit string) (askedBuild, bool, error) {
|
||||
return buildAsked(ctx, inv, module, commit)
|
||||
})
|
||||
if err != nil || len(found) == 0 {
|
||||
return nil, err
|
||||
}
|
||||
out := map[string]string{}
|
||||
for _, d := range found {
|
||||
out[d.module] = d.sent
|
||||
sayCoreDowngrade(ctx, d)
|
||||
}
|
||||
return out, nil
|
||||
}
|
||||
|
||||
// coreDowngradeObservation is a kept core build as a condition: `core.<component>.<machine>.<kind>`.
|
||||
func coreDowngradeObservation(component, node, summary string) conditions.Observation {
|
||||
return conditions.Observation{Scope: conditions.ScopeCore, ID: component + "." + node, Kind: kindCoreDowngrade,
|
||||
Token: kindCoreDowngrade, Machine: node, Severity: conditions.Warning, Source: coreDowngradeSource,
|
||||
Summary: summary}
|
||||
}
|
||||
|
||||
func sayCoreDowngrade(ctx context.Context, d coreDowngrade) {
|
||||
fmt.Printf("KEPT: %s\n", d)
|
||||
keeper := conditionsFrom
|
||||
if keeper == nil {
|
||||
return
|
||||
}
|
||||
if _, err := keeper.Observe(ctx, coreDowngradeObservation(d.component, d.node, d.String())); err != nil {
|
||||
fmt.Printf("the condition for %s kept on %s could not be raised: %v\n", d.module, d.node, err)
|
||||
}
|
||||
}
|
||||
|
||||
// settleCoreDowngrades clears, after a send to a machine is away, the condition of each guarded core module the
|
||||
// send carried at the mesh's record — a person's push that accepted the older build, or a send after the record
|
||||
// moved forward — or did not carry at all. A send that kept the newer build leaves it open.
|
||||
func settleCoreDowngrades(ctx context.Context, inv *inventory.Inventory, node string, carried map[string]string) {
|
||||
keeper := conditionsFrom
|
||||
if keeper == nil || carried == nil {
|
||||
return
|
||||
}
|
||||
var open []string
|
||||
for _, c := range downgradeGuarded {
|
||||
if _, found, err := keeper.Get(ctx, coreDowngradeObservation(c, node, "").Key()); err == nil && found {
|
||||
open = append(open, c)
|
||||
}
|
||||
}
|
||||
if len(open) == 0 {
|
||||
return
|
||||
}
|
||||
current, err := inv.CurrentBuilds(ctx)
|
||||
if err != nil {
|
||||
fmt.Printf("whether %s still keeps a core build over the mesh's record cannot be read: %v\n", node, err)
|
||||
return
|
||||
}
|
||||
for module, now := range current {
|
||||
component := coreComponent(module)
|
||||
if !guarded(component) {
|
||||
continue
|
||||
}
|
||||
if was, has := carried[module]; has && !sameCommit(was, now.Commit) {
|
||||
continue
|
||||
}
|
||||
key := coreDowngradeObservation(component, node, "").Key()
|
||||
if _, err := keeper.Clear(ctx, key, node+" was sent the "+component+" the mesh holds"); err != nil {
|
||||
fmt.Printf("the condition %s could not be cleared: %v\n", key, err)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -169,6 +169,44 @@ func TestAShrinkOfMoreThanHalfIsUrgent(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// THE FALSE ALARM (issue 368), replayed through the store D13 reads: an agent's home moved from the
|
||||
// operator's own home (94.7 MB) to the agent account's fresh one (490 B), and `data-shrank` was raised
|
||||
// for data that was never lost. A moved item is read against its new path only, so nothing is raised —
|
||||
// and a genuine shrink at the new path, a week of history later, still is.
|
||||
func TestAMovedPathIsNoShrinkAndAShrinkThereStillIs(t *testing.T) {
|
||||
inv := inventory.ForTest(t)
|
||||
ctx := t.Context()
|
||||
shelf := shelfFor(t, houseManifest)
|
||||
declared := []inventory.DeclaredData{{Module: "house", Item: "config", Class: "irreplaceable", Owned: true}}
|
||||
start := time.Now().Add(-6 * time.Hour)
|
||||
measure := func(at time.Time, path string, size int64) []conditions.Observation {
|
||||
t.Helper()
|
||||
if _, err := inv.RecordData(ctx, "home", declared, map[string]map[string]inventory.Measurement{"house": {
|
||||
"config": {Path: path, Size: bytesOf(size), MeasuredAt: when(at), LastWrite: when(at),
|
||||
LastBackup: when(at)}}}, "", at); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
records, err := inv.Data(ctx)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
peaks, err := inv.DataPeaks(ctx, at.Add(-shrinkWindow))
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
return dataFindings(records, peaks, shelf, nil, nil, at)
|
||||
}
|
||||
measure(start, "/home/operator/.claude", 94_700_000)
|
||||
if got := findingsByKind(measure(start.Add(10*time.Minute), "/home/agent/.claude", 490)); got[kindDataShrank].Kind != "" {
|
||||
t.Fatalf("a moved path raised a shrink: %+v", got[kindDataShrank])
|
||||
}
|
||||
measure(start.Add(2*time.Hour), "/home/agent/.claude", 300<<20)
|
||||
got := findingsByKind(measure(start.Add(4*time.Hour), "/home/agent/.claude", 1<<20))[kindDataShrank]
|
||||
if got.Severity != conditions.Urgent || !strings.Contains(got.Summary, "shrank") {
|
||||
t.Fatalf("a genuine shrink at the new path was not raised: %+v", got)
|
||||
}
|
||||
}
|
||||
|
||||
// Data said to be written all the time and not written; data with no backup or an old one — urgent when
|
||||
// irreplaceable, a warning when valuable; and a new item given its bound before it is said.
|
||||
func TestQuietDataAndMissingBackupsAreSaidByClass(t *testing.T) {
|
||||
|
||||
@@ -144,11 +144,15 @@ func actOnDeadLetter(ctx context.Context, on *busHandles, act string, id uint64,
|
||||
}
|
||||
switch act {
|
||||
case "deliver":
|
||||
_, to, err := link.DeliverAgain(on.js, id)
|
||||
delivered, to, err := link.DeliverAgain(on.js, id)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
answer["delivered_on"] = to
|
||||
if delivered.Original != "" {
|
||||
// What became of the ask in its seat's queue (novox/hq issue 334): removed, or left, and why.
|
||||
answer["original"] = delivered.Original
|
||||
}
|
||||
answer["done"] = fmt.Sprintf("dead letter %d was delivered again to %s, and nobody else; it is no longer kept",
|
||||
id, consumerWho(d.Stream, d.Consumer))
|
||||
case "drop":
|
||||
|
||||
+600
-26
@@ -10,6 +10,7 @@ import (
|
||||
"slices"
|
||||
"sort"
|
||||
"strings"
|
||||
"sync"
|
||||
"time"
|
||||
|
||||
"github.com/nats-io/nats.go"
|
||||
@@ -82,6 +83,38 @@ func waitingNote(p inventory.Plan) string {
|
||||
p.Delivery.Awaits, p.ID)
|
||||
}
|
||||
|
||||
// waitingSaid is what a walk waiting for its word says when the delivery's owner said what holds it (novox/hq
|
||||
// issue 529): a delivery held for a person, its reason and the verb that releases it — the person's decision, not
|
||||
// a hand start — or the deliveries not at their turn. Told nothing, it is waitingNote.
|
||||
func waitingSaid(p inventory.Plan, lines []stalledLine) string {
|
||||
if len(lines) == 0 {
|
||||
return waitingNote(p)
|
||||
}
|
||||
var held, unheld, other []string
|
||||
for _, l := range lines {
|
||||
switch l.State {
|
||||
case "held":
|
||||
held = append(held, l.Says)
|
||||
case "unheld":
|
||||
unheld = append(unheld, l.Says)
|
||||
default:
|
||||
other = append(other, l.Says)
|
||||
}
|
||||
}
|
||||
switch {
|
||||
case len(held) > 0:
|
||||
return fmt.Sprintf("published; its walk waits for %s's word, and a delivery it carries is held for a person: %s",
|
||||
p.Delivery.Awaits, strings.Join(held, "; "))
|
||||
case len(other) > 0:
|
||||
// Not at its turn: it goes when its turn comes. A hand start here would skip its group's order (review of
|
||||
// novox/hq issue 529), so none is offered.
|
||||
return fmt.Sprintf("published; its walk waits for %s's word: %s", p.Delivery.Awaits, strings.Join(other, "; "))
|
||||
}
|
||||
// Held by nothing: nothing will give it its word, so the hand start is the way on.
|
||||
return fmt.Sprintf("published; its walk waits for %s's word: %s — `plans go %s --why …` starts it by hand",
|
||||
p.Delivery.Awaits, strings.Join(unheld, "; "), p.ID)
|
||||
}
|
||||
|
||||
// letGo gives a waiting walk its word: by the delivery's owner, or a person. The next advance asks its
|
||||
// first tier. Refused for a walk that does not wait.
|
||||
func letGo(ctx context.Context, inv *inventory.Inventory, id, by, why string) (inventory.Plan, error) {
|
||||
@@ -117,28 +150,419 @@ func letGo(ctx context.Context, inv *inventory.Inventory, id, by, why string) (i
|
||||
// stopWalk ends a walk on its delivery's word: failed, said as stopped by whom, why. What it asked still
|
||||
// builds and registers; nothing further is asked or sent.
|
||||
func stopWalk(ctx context.Context, inv *inventory.Inventory, id, by, why string) (inventory.Plan, error) {
|
||||
p, _, err := stopWalkWithout(ctx, inv, id, by, why, nil, time.Now().UTC())
|
||||
return p, err
|
||||
}
|
||||
|
||||
// stopAnswer is what a stop that leaves merges out says, as data (novox/hq ADR 0299): the record stopped, the
|
||||
// batch that walks its other merges again with those merges, every merge left out, the modules the stopped walk
|
||||
// already sent that stay on the machines named, the modules the batch's walk withholds, and every merge elsewhere
|
||||
// that will deliver a stopped change when it is walked — a later merge of its repository, or one moving its modules.
|
||||
type stopAnswer struct {
|
||||
Stopped string `json:"stopped"`
|
||||
WalkedAgainBy string `json:"walked_again_by,omitempty"`
|
||||
WalkedAgain []string `json:"walked_again,omitempty"`
|
||||
LeftOut []inventory.PlanLeftOut `json:"left_out,omitempty"`
|
||||
Kept []inventory.PlanKept `json:"kept,omitempty"`
|
||||
Withheld []string `json:"withheld,omitempty"`
|
||||
StillCarriedBy []string `json:"still_carried_by,omitempty"`
|
||||
}
|
||||
|
||||
// stopWalkWithout ends a walk on its delivery's word and, given merges to leave out, walks every other merge it
|
||||
// answered again without them (novox/hq issue 459, ADR 0299): one walk carries every merge of its batch, so ending
|
||||
// it for one group member ended every other delivery on it.
|
||||
//
|
||||
// - Left out are the merges named, each later merge of their repository's branch, which contains one, and each
|
||||
// merge moving a module a left-out merge moves: a module is built at its branch, which holds the stopped merge.
|
||||
// - The others join the open batch of their kind — merges heard while the walk ran wait there, and an older
|
||||
// commit never walks after a newer one — or a new batch when none is open; its window is closed, and its walk
|
||||
// withholds the left-out merges' modules where it would build them only as dependents.
|
||||
// - Given a batch not yet cut, the merges left out leave it for a stopped record of their own, and the batch
|
||||
// goes on without them; with nothing left in it, the batch itself is stopped.
|
||||
// - The stopped record, the batch and every merge moved are written in one transaction (decision 7).
|
||||
//
|
||||
// With nothing left to walk, or no merge named, the walk is only ended. A merge named that the record does not
|
||||
// answer refuses the stop whole.
|
||||
func stopWalkWithout(ctx context.Context, inv *inventory.Inventory, id, by, why string, without []string,
|
||||
now time.Time) (inventory.Plan, stopAnswer, error) {
|
||||
said := stopAnswer{Stopped: id}
|
||||
release, err := inv.HoldPlans(ctx, true)
|
||||
if err != nil {
|
||||
return inventory.Plan{}, err
|
||||
return inventory.Plan{}, said, err
|
||||
}
|
||||
defer release()
|
||||
p, err := inv.PlanByID(ctx, id)
|
||||
if err != nil {
|
||||
return inventory.Plan{}, err
|
||||
return inventory.Plan{}, said, err
|
||||
}
|
||||
if !p.Open() {
|
||||
return p, fmt.Errorf("%s is already %s", p.ID, p.State)
|
||||
batch := p.Batch()
|
||||
if !p.Open() && !(batch && len(without) > 0) {
|
||||
return p, said, fmt.Errorf("%s is already %s", p.ID, p.State)
|
||||
}
|
||||
if p.Delivery == nil {
|
||||
p.Delivery = &inventory.PlanDelivery{}
|
||||
var merges, again []inventory.BatchedMerge
|
||||
if len(without) > 0 {
|
||||
if merges, err = inv.MergesOf(ctx, p.ID); err != nil {
|
||||
return p, said, err
|
||||
}
|
||||
if again, said.LeftOut, err = leaveOut(merges, without); err != nil {
|
||||
return p, said, fmt.Errorf("%s is not stopped: %w", p.ID, err)
|
||||
}
|
||||
}
|
||||
p.Delivery.Stopped, p.Delivery.StoppedWhy = by, why
|
||||
p.State = inventory.PlanFailed
|
||||
p.Note = fmt.Sprintf("stopped by %s at tier %d: %s", by, p.Tier, why)
|
||||
if err := inv.SavePlan(ctx, &p); err != nil {
|
||||
return p, err
|
||||
stopped := func(r *inventory.Plan) {
|
||||
if r.Delivery == nil {
|
||||
r.Delivery = &inventory.PlanDelivery{}
|
||||
}
|
||||
r.Delivery.Stopped, r.Delivery.StoppedWhy, r.Delivery.LeftOut = by, why, said.LeftOut
|
||||
r.State = inventory.PlanFailed
|
||||
r.Note = fmt.Sprintf("stopped by %s at tier %d: %s", by, r.Tier, why)
|
||||
}
|
||||
return p, nil
|
||||
withheld := movesOf(leftOutMerges(merges, said.LeftOut))
|
||||
said.Withheld = withheld
|
||||
if said.StillCarriedBy, err = stillCarried(ctx, inv, p.ID, merges, said.LeftOut, withheld); err != nil {
|
||||
return p, said, err
|
||||
}
|
||||
if batch {
|
||||
return p, said, stopInBatch(ctx, inv, &p, merges, again, &said, stopped, now)
|
||||
}
|
||||
entries, err := inv.Catalogued(ctx)
|
||||
if err != nil {
|
||||
return p, said, err
|
||||
}
|
||||
running := map[string][]string{}
|
||||
for _, e := range entries {
|
||||
running[e.Manifest.Module] = e.On
|
||||
}
|
||||
said.Kept = keptOf(p, movesOf(again), running)
|
||||
stopped(&p)
|
||||
p.Delivery.Kept = said.Kept
|
||||
if len(again) == 0 {
|
||||
if len(said.LeftOut) > 0 {
|
||||
p.Note += fmt.Sprintf("; left out %s, nothing else to walk", mergesLeftOutWords(said.LeftOut))
|
||||
}
|
||||
return p, said, inv.SavePlan(ctx, &p)
|
||||
}
|
||||
target, folded, foldMoves, err := batchToWalkAgain(ctx, inv, p.ID, again, now)
|
||||
if err != nil {
|
||||
return p, said, fmt.Errorf("%s is not stopped: %w", p.ID, err)
|
||||
}
|
||||
target.Delivery.Batch.Closed = true
|
||||
target.Delivery.Batch.Withheld = union(target.Delivery.Batch.Withheld, withheld)
|
||||
sort.Strings(target.Delivery.Batch.Withheld)
|
||||
said.WalkedAgainBy = target.ID
|
||||
var moves []inventory.MergeMove
|
||||
for _, m := range again {
|
||||
said.WalkedAgain = append(said.WalkedAgain, m.Repository+"@"+m.Commit)
|
||||
moves = append(moves, inventory.MergeMove{Repository: m.Repository, Commit: m.Commit, Plan: target.ID, Alone: m.Alone})
|
||||
}
|
||||
p.Delivery.WalkedAgainBy = target.ID
|
||||
p.Note += fmt.Sprintf("; its other merges are walked again by %s: %s", target.ID, strings.Join(said.WalkedAgain, ", "))
|
||||
if len(said.LeftOut) > 0 {
|
||||
p.Note += "; left out " + mergesLeftOutWords(said.LeftOut)
|
||||
}
|
||||
if len(said.Kept) > 0 {
|
||||
p.Note += "; " + keptWords(said.Kept)
|
||||
}
|
||||
// The batch first, so no merge names a plan the store does not hold; all of it, or nothing (decision 7) — the
|
||||
// batches folded into it too.
|
||||
if err := inv.SavePlansMoving(ctx, append([]*inventory.Plan{&target, &p}, folded...),
|
||||
append(moves, foldMoves...)); err != nil {
|
||||
return p, said, fmt.Errorf("%s is not stopped, and none of its merges moved: %w", p.ID, err)
|
||||
}
|
||||
// What the batch holds and names now: written again by the cutter's next look should this fail.
|
||||
if err := keepBatch(ctx, inv, &target, now, ""); err != nil {
|
||||
fmt.Printf(" %s holds its merges; its record is written again at the next look: %v\n", target.ID, err)
|
||||
}
|
||||
fmt.Printf("%s stopped by %s; %s walks its other merges again: %s\n", p.ID, by, target.ID,
|
||||
strings.Join(said.WalkedAgain, ", "))
|
||||
return p, said, nil
|
||||
}
|
||||
|
||||
// stopInBatch leaves merges out of a batch not yet cut (ADR 0299): they go to a stopped record of their own, which
|
||||
// names the batch as walking the others, and the batch withholds their modules; a batch left with none is stopped
|
||||
// itself.
|
||||
func stopInBatch(ctx context.Context, inv *inventory.Inventory, b *inventory.Plan, merges, again []inventory.BatchedMerge,
|
||||
said *stopAnswer, stopped func(*inventory.Plan), now time.Time) error {
|
||||
if len(again) == 0 {
|
||||
stopped(b)
|
||||
b.Delivery.Batch = nil
|
||||
b.Note = "a batch whose every merge was left out by a stop: " + b.Note
|
||||
return inv.SavePlan(ctx, b)
|
||||
}
|
||||
left := leftOutMerges(merges, said.LeftOut)
|
||||
first := left[0]
|
||||
r := inventory.Plan{ID: fmt.Sprintf("plan-%d", now.UnixNano()), Repository: first.Repository, Branch: first.Branch,
|
||||
Commit: first.Commit, Merged: first.Merged, Created: now, Tiers: [][]string{},
|
||||
Modules: map[string]*inventory.PlanModule{}}
|
||||
if r.ID == b.ID {
|
||||
r.ID += "-left"
|
||||
}
|
||||
stopped(&r)
|
||||
r.Delivery.WalkedAgainBy = b.ID
|
||||
r.Note += fmt.Sprintf("; left out of %s before it was walked: %s; %s walks the others", b.ID,
|
||||
mergesLeftOutWords(said.LeftOut), b.ID)
|
||||
b.Delivery.Batch.Withheld = union(b.Delivery.Batch.Withheld, said.Withheld)
|
||||
sort.Strings(b.Delivery.Batch.Withheld)
|
||||
var moves []inventory.MergeMove
|
||||
for _, m := range left {
|
||||
moves = append(moves, inventory.MergeMove{Repository: m.Repository, Commit: m.Commit, Plan: r.ID, Alone: m.Alone})
|
||||
}
|
||||
for _, m := range again {
|
||||
said.WalkedAgain = append(said.WalkedAgain, m.Repository+"@"+m.Commit)
|
||||
}
|
||||
said.Stopped, said.WalkedAgainBy = r.ID, b.ID
|
||||
if err := inv.SavePlansMoving(ctx, []*inventory.Plan{&r, b}, moves); err != nil {
|
||||
return fmt.Errorf("%s is not changed, and none of its merges moved: %w", b.ID, err)
|
||||
}
|
||||
if err := keepBatch(ctx, inv, b, now, ""); err != nil {
|
||||
fmt.Printf(" %s holds its merges; its record is written again at the next look: %v\n", b.ID, err)
|
||||
}
|
||||
fmt.Printf("%s: %s left out by a stop, kept by %s\n", b.ID, mergesLeftOutWords(said.LeftOut), r.ID)
|
||||
return nil
|
||||
}
|
||||
|
||||
// batchToWalkAgain is the batch a stopped walk's merges join (novox/hq ADR 0299): a batch of their kind not yet cut
|
||||
// that they are related to (ADR 0304 decision 1, ADR 0306 decision 3), or a new one, not yet written. Related to
|
||||
// two or more, the newer are folded into the oldest: the plans and merge moves that fold them, to be written in
|
||||
// the stop's one act. The kind is read from what the merges moved; the stopped walk itself is no walk a cut folds.
|
||||
func batchToWalkAgain(ctx context.Context, inv *inventory.Inventory, stopping string, again []inventory.BatchedMerge,
|
||||
now time.Time) (inventory.Plan, []*inventory.Plan, []inventory.MergeMove, error) {
|
||||
own := false
|
||||
for _, n := range movesOf(again) {
|
||||
if _, on := onTheControllersPath[n]; on {
|
||||
own = true
|
||||
}
|
||||
}
|
||||
entries, read, edges, err := theGraph(ctx, inv)
|
||||
if err != nil {
|
||||
return inventory.Plan{}, nil, nil, err
|
||||
}
|
||||
joins, _, _, err := relatedBatches(ctx, inv, again, own, stopping, entries, read, edges)
|
||||
if err != nil {
|
||||
return inventory.Plan{}, nil, nil, err
|
||||
}
|
||||
if len(joins) > 0 {
|
||||
into := joins[0]
|
||||
if len(joins) == 1 {
|
||||
return into, nil, nil, nil
|
||||
}
|
||||
plans, moves, err := foldInto(ctx, inv, &into, joins[1:])
|
||||
if err != nil {
|
||||
return inventory.Plan{}, nil, nil, err
|
||||
}
|
||||
return into, plans[1:], moves, nil
|
||||
}
|
||||
first := again[0]
|
||||
return inventory.Plan{ID: fmt.Sprintf("plan-%d", now.UnixNano()), Repository: first.Repository, Branch: first.Branch,
|
||||
Commit: first.Commit, Merged: first.Merged, Created: now, State: inventory.PlanAssembling,
|
||||
Tiers: [][]string{}, Modules: map[string]*inventory.PlanModule{},
|
||||
Delivery: &inventory.PlanDelivery{Batch: &inventory.PlanBatch{Own: own}}}, nil, nil, nil
|
||||
}
|
||||
|
||||
// leaveOut splits a walk's merges by the merges named to leave out, each `<repository>@<commit>` (a commit's
|
||||
// first characters will do): the merges walked again, and those left out — each named one; each later merge of
|
||||
// its repository's branch, which contains it; and each merge moving a module a left-out merge moves, which is
|
||||
// built at its branch and so holds the stopped merge — until none more is. A name the walk does not answer is
|
||||
// refused.
|
||||
func leaveOut(merges []inventory.BatchedMerge, without []string) ([]inventory.BatchedMerge, []inventory.PlanLeftOut, error) {
|
||||
var stopped []inventory.BatchedMerge
|
||||
for _, w := range without {
|
||||
repository, commit, ok := strings.Cut(strings.TrimSpace(w), "@")
|
||||
if !ok || repository == "" || len(commit) < 7 {
|
||||
return nil, nil, fmt.Errorf("%q names no merge: <repository>@<commit>", w)
|
||||
}
|
||||
i := slices.IndexFunc(merges, func(m inventory.BatchedMerge) bool {
|
||||
return strings.EqualFold(m.Repository, repository) && strings.HasPrefix(m.Commit, commit)
|
||||
})
|
||||
if i < 0 {
|
||||
return nil, nil, fmt.Errorf("it answers no merge %s@%s", repository, commit)
|
||||
}
|
||||
stopped = append(stopped, merges[i])
|
||||
}
|
||||
same := func(a, b inventory.BatchedMerge) bool {
|
||||
return strings.EqualFold(a.Repository, b.Repository) && a.Commit == b.Commit
|
||||
}
|
||||
out := map[int]inventory.PlanLeftOut{}
|
||||
for i, m := range merges {
|
||||
if slices.ContainsFunc(stopped, func(s inventory.BatchedMerge) bool { return same(s, m) }) {
|
||||
out[i] = inventory.PlanLeftOut{Repository: m.Repository, Commit: m.Commit}
|
||||
}
|
||||
}
|
||||
for grew := true; grew; {
|
||||
grew = false
|
||||
for i, m := range merges {
|
||||
if _, left := out[i]; left {
|
||||
continue
|
||||
}
|
||||
for j, o := range out {
|
||||
l := merges[j]
|
||||
contains := o.Contains
|
||||
if contains == "" {
|
||||
contains = l.Commit
|
||||
}
|
||||
if strings.EqualFold(l.Repository, m.Repository) && l.Branch == m.Branch && laterMerge(m, l) {
|
||||
out[i] = inventory.PlanLeftOut{Repository: m.Repository, Commit: m.Commit, Contains: contains}
|
||||
} else if shared := sharedMoves(m, l); len(shared) > 0 {
|
||||
out[i] = inventory.PlanLeftOut{Repository: m.Repository, Commit: m.Commit, Contains: contains,
|
||||
Shares: shared}
|
||||
} else {
|
||||
continue
|
||||
}
|
||||
grew = true
|
||||
break
|
||||
}
|
||||
}
|
||||
}
|
||||
var again []inventory.BatchedMerge
|
||||
var left []inventory.PlanLeftOut
|
||||
for i, m := range merges {
|
||||
if o, is := out[i]; is {
|
||||
left = append(left, o)
|
||||
} else {
|
||||
again = append(again, m)
|
||||
}
|
||||
}
|
||||
sort.SliceStable(left, func(i, j int) bool { return left[i].Contains == "" && left[j].Contains != "" })
|
||||
return again, left, nil
|
||||
}
|
||||
|
||||
// sharedMoves are the modules two kept merges both moved when they were heard.
|
||||
func sharedMoves(a, b inventory.BatchedMerge) []string {
|
||||
var out []string
|
||||
theirs := announcedOf(b).Moves
|
||||
for _, n := range announcedOf(a).Moves {
|
||||
if slices.Contains(theirs, n) && !slices.Contains(out, n) {
|
||||
out = append(out, n)
|
||||
}
|
||||
}
|
||||
sort.Strings(out)
|
||||
return out
|
||||
}
|
||||
|
||||
// leftOutMerges are the kept merges a stop left out.
|
||||
func leftOutMerges(merges []inventory.BatchedMerge, out []inventory.PlanLeftOut) []inventory.BatchedMerge {
|
||||
var left []inventory.BatchedMerge
|
||||
for _, m := range merges {
|
||||
if slices.ContainsFunc(out, func(o inventory.PlanLeftOut) bool {
|
||||
return strings.EqualFold(o.Repository, m.Repository) && o.Commit == m.Commit
|
||||
}) {
|
||||
left = append(left, m)
|
||||
}
|
||||
}
|
||||
return left
|
||||
}
|
||||
|
||||
// movesOf is every module kept merges moved when they were heard, sorted.
|
||||
func movesOf(merges []inventory.BatchedMerge) []string {
|
||||
var out []string
|
||||
for _, m := range merges {
|
||||
out = union(out, announcedOf(m).Moves)
|
||||
}
|
||||
sort.Strings(out)
|
||||
return out
|
||||
}
|
||||
|
||||
// keptOf are the modules a stopped walk sent that no merge walked again moves, and the machines each reached:
|
||||
// those keep running the stopped walk's build. A module sent to its first machines reached those, and the rest it
|
||||
// was sent to after them; one sent with no first machine (its policy sends it to all together, or a later tier is
|
||||
// built by it) reached every machine running it.
|
||||
func keptOf(p inventory.Plan, walkedAgain []string, running map[string][]string) []inventory.PlanKept {
|
||||
var out []inventory.PlanKept
|
||||
for name, m := range p.Modules {
|
||||
if m == nil || slices.Contains(walkedAgain, name) {
|
||||
continue
|
||||
}
|
||||
var machines []string
|
||||
if m.FirstAt != nil || m.SentAt != nil {
|
||||
machines = union(machines, m.First)
|
||||
}
|
||||
if m.SentAt != nil && len(m.First) == 0 {
|
||||
machines = union(machines, running[name])
|
||||
}
|
||||
if m.Gate != nil && m.Gate.Since != nil {
|
||||
machines = union(machines, m.Gate.Machines)
|
||||
}
|
||||
for machine := range m.Rest {
|
||||
machines = union(machines, []string{machine})
|
||||
}
|
||||
if len(machines) == 0 {
|
||||
continue
|
||||
}
|
||||
sort.Strings(machines)
|
||||
out = append(out, inventory.PlanKept{Module: name, Machines: machines})
|
||||
}
|
||||
sort.Slice(out, func(i, j int) bool { return out[i].Module < out[j].Module })
|
||||
return out
|
||||
}
|
||||
|
||||
// keptWords is what a stopped walk leaves on the machines, as a person reads it.
|
||||
func keptWords(kept []inventory.PlanKept) string {
|
||||
var words []string
|
||||
for _, k := range kept {
|
||||
words = append(words, k.Module+" on "+strings.Join(k.Machines, ", "))
|
||||
}
|
||||
return "left running the stopped walk's build, which nothing walks again: " + strings.Join(words, "; ")
|
||||
}
|
||||
|
||||
// stillCarried are the merges outside the stopped record, in a batch or an open walk, that will deliver a stopped
|
||||
// change when they are walked: a later merge of its repository's branch, which contains it, or one that moves a
|
||||
// module it moves. Holding a merged change back for good is a revert's (ADR 0299).
|
||||
func stillCarried(ctx context.Context, inv *inventory.Inventory, id string, merges []inventory.BatchedMerge,
|
||||
out []inventory.PlanLeftOut, withheld []string) ([]string, error) {
|
||||
var named []inventory.BatchedMerge
|
||||
for _, m := range leftOutMerges(merges, out) {
|
||||
if slices.ContainsFunc(out, func(o inventory.PlanLeftOut) bool { return o.Commit == m.Commit && o.Contains == "" }) {
|
||||
named = append(named, m)
|
||||
}
|
||||
}
|
||||
if len(named) == 0 {
|
||||
return nil, nil
|
||||
}
|
||||
open, err := inv.OpenPlans(ctx)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
batches, err := inv.Batches(ctx)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
var carried []string
|
||||
for _, p := range append(open, batches...) {
|
||||
if p.ID == id {
|
||||
continue
|
||||
}
|
||||
ms, err := inv.MergesOf(ctx, p.ID)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
for _, m := range ms {
|
||||
later := slices.ContainsFunc(named, func(s inventory.BatchedMerge) bool {
|
||||
return strings.EqualFold(s.Repository, m.Repository) && s.Branch == m.Branch && laterMerge(m, s)
|
||||
})
|
||||
shares := slices.ContainsFunc(announcedOf(m).Moves, func(n string) bool { return slices.Contains(withheld, n) })
|
||||
if later || shares {
|
||||
carried = append(carried, fmt.Sprintf("%s@%s (in %s)", m.Repository, m.Commit, p.ID))
|
||||
}
|
||||
}
|
||||
}
|
||||
sort.Strings(carried)
|
||||
return carried, nil
|
||||
}
|
||||
|
||||
// mergesLeftOutWords is the merges a stop left out, as a person reads them: each that contains a stopped one, or
|
||||
// shares its modules, says so.
|
||||
func mergesLeftOutWords(out []inventory.PlanLeftOut) string {
|
||||
var words []string
|
||||
for _, o := range out {
|
||||
s := o.Repository + "@" + short(o.Commit)
|
||||
switch {
|
||||
case len(o.Shares) > 0:
|
||||
s += " (which moves " + strings.Join(o.Shares, ", ") + " as " + short(o.Contains) + " does)"
|
||||
case o.Contains != "":
|
||||
s += " (which contains " + short(o.Contains) + ")"
|
||||
}
|
||||
words = append(words, s)
|
||||
}
|
||||
return strings.Join(words, ", ")
|
||||
}
|
||||
|
||||
// orderMember is one member of a group, as mesh-delivery says it.
|
||||
@@ -156,6 +580,9 @@ type orderMember struct {
|
||||
CloneURL string `json:"clone_url,omitempty"`
|
||||
// After are the repositories its pull request says it goes after (`after: <repository>`).
|
||||
After []string `json:"after,omitempty"`
|
||||
// BaseSHA is the base branch's head the forge last announced the head with (novox/hq ADR 0323): the trunk commit
|
||||
// a verdict no build judges names when the head is checked again through mesh-delivery.
|
||||
BaseSHA string `json:"base_sha,omitempty"`
|
||||
}
|
||||
|
||||
// pull is the member as the forge announced it.
|
||||
@@ -165,7 +592,7 @@ func (m orderMember) pull() link.PullUpdated {
|
||||
if base == "" {
|
||||
base = "main"
|
||||
}
|
||||
return link.PullUpdated{Owner: owner, Repo: repo, Number: m.Number, Base: base, Commit: m.Head,
|
||||
return link.PullUpdated{Owner: owner, Repo: repo, Number: m.Number, Base: base, Commit: m.Head, BaseSHA: m.BaseSHA,
|
||||
CloneURL: m.CloneURL, Paths: m.Paths, PathsTruncated: m.PathsTruncated, Removed: m.Removed,
|
||||
ModuleDirs: m.ModuleDirs, ModuleDirsSaid: m.ModuleDirsSaid}
|
||||
}
|
||||
@@ -466,6 +893,8 @@ func deliveryCommand(ctx context.Context, args []string) error {
|
||||
group := set.String("group", "", "a delivery group's id")
|
||||
by := set.String("by", catalogue.DeliverySeat, "who says it")
|
||||
why := set.String("why", "", "why")
|
||||
without := set.String("without", "", "merges a stop leaves out, <repository>@<commit>, comma-separated: the walk's "+
|
||||
"other merges are walked again without them (novox/hq ADR 0299)")
|
||||
limit := set.Int("n", 50, "how many ended walks to answer beside the open ones")
|
||||
planID := set.String("plan", "", "one walk")
|
||||
positionals, err := parseAround(set, rest)
|
||||
@@ -523,7 +952,7 @@ func deliveryCommand(ctx context.Context, args []string) error {
|
||||
if *group == "" && len(members) == 1 {
|
||||
// One head, checked again as the forge's announcement would have it (a recheck): the controller's
|
||||
// own path for a pull request, run because the delivery's owner asked.
|
||||
if err := sayingOnTheBus(ctx, func() error { return (following{open}).PullUpdated(ctx, members[0].pull()) }); err != nil {
|
||||
if err := sayingOnTheBus(ctx, inv, func() error { return (following{open}).PullUpdated(ctx, members[0].pull()) }); err != nil {
|
||||
return err
|
||||
}
|
||||
return answer(map[string]any{"rechecked": members[0].ID})
|
||||
@@ -541,7 +970,7 @@ func deliveryCommand(ctx context.Context, args []string) error {
|
||||
return errors.New("delivery go <plan> [--by <who>] [--why <text>]")
|
||||
}
|
||||
var p inventory.Plan
|
||||
if err := sayingOnTheBus(ctx, func() (err error) {
|
||||
if err := sayingOnTheBus(ctx, inv, func() (err error) {
|
||||
p, err = letGo(ctx, inv, positionals[0], *by, strings.TrimSpace(*why))
|
||||
return err
|
||||
}); err != nil {
|
||||
@@ -552,15 +981,21 @@ func deliveryCommand(ctx context.Context, args []string) error {
|
||||
return nil
|
||||
case "stop":
|
||||
if len(positionals) != 1 || strings.TrimSpace(*why) == "" {
|
||||
return errors.New("delivery stop <plan> --why <text> [--by <who>]")
|
||||
return errors.New("delivery stop <plan> --why <text> [--by <who>] [--without <repository>@<commit>,…]")
|
||||
}
|
||||
var p inventory.Plan
|
||||
if err := sayingOnTheBus(ctx, func() (err error) {
|
||||
p, err = stopWalk(ctx, inv, positionals[0], *by, strings.TrimSpace(*why))
|
||||
var said stopAnswer
|
||||
if err := sayingOnTheBus(ctx, inv, func() (err error) {
|
||||
p, said, err = stopWalkWithout(ctx, inv, positionals[0], *by, strings.TrimSpace(*why), splitList(*without),
|
||||
time.Now().UTC())
|
||||
return err
|
||||
}); err != nil {
|
||||
return err
|
||||
}
|
||||
if *without != "" {
|
||||
// What it left out and what it walks again, as data: the delivery's owner reads it (ADR 0299).
|
||||
return answer(said)
|
||||
}
|
||||
fmt.Printf("%s stopped by %s at tier %d of %d; what was asked still builds and registers, nothing further "+
|
||||
"is asked or sent\n", p.ID, *by, p.Tier, len(p.Tiers))
|
||||
return nil
|
||||
@@ -596,12 +1031,81 @@ func deliveryCommand(ctx context.Context, args []string) error {
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
// Each walk's phases, with the rest's reports (novox/hq ADR 0282 decision 6).
|
||||
now := time.Now()
|
||||
for i := range walks {
|
||||
walks[i].Phases = walks[i].WalkPhases(now, appliedFrom(ctx, inv))
|
||||
}
|
||||
return answer(map[string]any{"held": deliverySeatHeld(entries), "walks": walks,
|
||||
"own-path": sortedKeysOf(ownPathWords())})
|
||||
}
|
||||
return fmt.Errorf("delivery %s: plan, order, check, go, stop or walks", sub)
|
||||
}
|
||||
|
||||
// appliedFrom answers a machine's first report after a send from the controller's `apply` durations; a lookup
|
||||
// that fails is a report not read, which leaves the walk's end unknown rather than wrong.
|
||||
func appliedFrom(ctx context.Context, inv *inventory.Inventory) inventory.AppliedLookup {
|
||||
return func(node string, sent time.Time) (inventory.AppliedReport, bool) {
|
||||
r, ok, err := inv.FirstAppliedAfter(ctx, node, sent)
|
||||
if err != nil {
|
||||
fmt.Fprintf(os.Stderr, "the report of %s after %s could not be read: %v\n", node, sent.Format(time.RFC3339), err)
|
||||
return inventory.AppliedReport{}, false
|
||||
}
|
||||
return r, ok
|
||||
}
|
||||
}
|
||||
|
||||
// recordWalkPhases keeps, once, each phase of every walk ended lately whose end is known, as a duration of kind
|
||||
// walk-phase per class (novox/hq ADR 0282 decision 6): what `durations` summarises. A walk whose end is unknown
|
||||
// past ApplySilentAfter keeps its measured phases without its total.
|
||||
func recordWalkPhases(ctx context.Context, inv *inventory.Inventory, now time.Time) error {
|
||||
recent, err := inv.RecentPlans(ctx, 30)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
for _, p := range recent {
|
||||
if p.State != inventory.PlanDone || p.Release != nil || now.Sub(p.Updated) > 2*time.Hour {
|
||||
continue
|
||||
}
|
||||
anyKept, totalKept, err := inv.WalkPhasesKept(ctx, p.ID)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
if totalKept {
|
||||
continue
|
||||
}
|
||||
ph := p.WalkPhases(now, appliedFrom(ctx, inv))
|
||||
if ph != nil && ph.End == nil && anyKept {
|
||||
continue // kept without its end; kept again only once its end is known
|
||||
}
|
||||
if ph == nil || (ph.End == nil && now.Sub(p.Updated) < inventory.ApplySilentAfter+time.Minute) {
|
||||
continue
|
||||
}
|
||||
class := ph.Class
|
||||
if class == "" {
|
||||
class = "unclassed"
|
||||
}
|
||||
for _, x := range ph.Phases {
|
||||
if x.State != inventory.PhaseMeasured || x.Start == nil {
|
||||
continue
|
||||
}
|
||||
if err := inv.RecordDuration(ctx, inventory.Duration{Kind: inventory.DurationWalkPhase,
|
||||
Subject: class + "/" + x.Name, Ref: fmt.Sprintf("%s/%s/%d", p.ID, x.Name, x.Tier), Started: *x.Start,
|
||||
Took: time.Duration(x.TookMS) * time.Millisecond, Detail: p.Named()}); err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
if ph.End != nil && ph.From != nil {
|
||||
if err := inv.RecordDuration(ctx, inventory.Duration{Kind: inventory.DurationWalkPhase,
|
||||
Subject: class + "/total", Ref: p.ID + "/total", Started: *ph.From,
|
||||
Took: time.Duration(ph.TotalMS) * time.Millisecond, Detail: ph.Said}); err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// ownPathWords is the controller's own path as words, for an answer.
|
||||
func ownPathWords() map[string]string { return onTheControllersPath }
|
||||
|
||||
@@ -684,7 +1188,7 @@ func askGroupCheck(ctx context.Context, open *stores, group string, members []or
|
||||
return "", fmt.Errorf("%s cannot be cloned for the group's check: %w", m.ID, err)
|
||||
}
|
||||
request.Check.Members = append(request.Check.Members, link.GroupMember{Owner: mp.Owner, Repo: mp.Repo,
|
||||
Number: mp.Number, Repository: url, Ref: mp.Commit, Paths: mp.Paths})
|
||||
Number: mp.Number, Repository: url, Ref: mp.Commit, Paths: mp.Paths, Base: mp.Base})
|
||||
}
|
||||
seat := buildSeatHeld(ctx)
|
||||
ask, err := askOverOn(seat)
|
||||
@@ -723,12 +1227,19 @@ func shelfOf(entries []inventory.Entry) map[string]catalogue.Manifest {
|
||||
// delivery it walks reads its steps from. Never in the way of the walk: said beside it, and a save that could
|
||||
// not be said is logged — the delivery's owner, which also asks for the walks it follows, finds it by
|
||||
// comparison. Records arriving out of order are told apart by the plan's revision.
|
||||
func sayPlanMoved(ctx context.Context, bus link.Bus, p inventory.Plan) {
|
||||
go publishPlanMoved(ctx, bus, p)
|
||||
//
|
||||
// On the save that starts the walk and the one that ends it, the walk also says what it touches, its bound and,
|
||||
// at the end, its outcome (novox/hq ADR 0308 decision 1, walk_said.go), read from facts; nil facts say only what
|
||||
// the walk recorded.
|
||||
func sayPlanMoved(ctx context.Context, bus link.Bus, facts walkFacts, p inventory.Plan) {
|
||||
go publishPlanMoved(ctx, bus, facts, p)
|
||||
}
|
||||
|
||||
func publishPlanMoved(ctx context.Context, bus link.Bus, p inventory.Plan) {
|
||||
body, err := json.Marshal(p)
|
||||
func publishPlanMoved(ctx context.Context, bus link.Bus, facts walkFacts, p inventory.Plan) {
|
||||
// Its phases so far (novox/hq ADR 0282 decision 6): the rest's reports come after the walk ends, and are
|
||||
// read by whoever asks for the walk (`delivery walks`).
|
||||
p.Phases = p.WalkPhases(time.Now(), nil)
|
||||
body, err := json.Marshal(planMovedBody{Plan: p, walkSaid: sayWalk(ctx, facts, p)})
|
||||
if err != nil {
|
||||
return
|
||||
}
|
||||
@@ -743,7 +1254,7 @@ func publishPlanMoved(ctx context.Context, bus link.Bus, p inventory.Plan) {
|
||||
// controller's, or a connection of the command's own — a verb runs as a command of its own, and what it kept
|
||||
// would otherwise be said by nobody until the delivery's owner read the walks back. Without a bus the command
|
||||
// still runs; what it did is found by comparison.
|
||||
func sayingOnTheBus(ctx context.Context, f func() error) error {
|
||||
func sayingOnTheBus(ctx context.Context, facts walkFacts, f func() error) error {
|
||||
if checkEvents != nil {
|
||||
return f()
|
||||
}
|
||||
@@ -754,9 +1265,10 @@ func sayingOnTheBus(ctx context.Context, f func() error) error {
|
||||
return err
|
||||
}
|
||||
bus := link.OverNATS{Conn: conn, JS: js}
|
||||
was := inventory.PlanSaved
|
||||
checkEvents = bus
|
||||
inventory.PlanSaved = func(p inventory.Plan) { publishPlanMoved(ctx, bus, p) }
|
||||
defer func() { checkEvents, inventory.PlanSaved = nil, nil }()
|
||||
inventory.PlanSaved = func(_ *inventory.Inventory, p inventory.Plan) { publishPlanMoved(ctx, bus, facts, p) }
|
||||
defer func() { checkEvents, inventory.PlanSaved = nil, was }()
|
||||
ran = true
|
||||
return f()
|
||||
})
|
||||
@@ -766,3 +1278,65 @@ func sayingOnTheBus(ctx context.Context, f func() error) error {
|
||||
}
|
||||
return err
|
||||
}
|
||||
|
||||
// sayingWhatAVerbKept is PlanSaved for a process that is not the serving controller: each walk the verb keeps is
|
||||
// said as `plan-moved` before the save returns, with the facts of the inventory that kept it, on the bus the verb
|
||||
// reaches. It reaches the bus on the first save and never for a verb that keeps no walk. When the bus cannot be
|
||||
// reached, a save that started or ended a walk says so on the verb's error output: its mark is kept and no later
|
||||
// save says it, so the router holds what the walk touched until its bound, or not at all for a start. done lets
|
||||
// the bus go and takes the hook back.
|
||||
func sayingWhatAVerbKept(ctx context.Context) (said func(*inventory.Inventory, inventory.Plan), done func()) {
|
||||
var (
|
||||
mu sync.Mutex
|
||||
reached bool
|
||||
bus link.Bus
|
||||
closing func()
|
||||
failed error
|
||||
)
|
||||
said = func(inv *inventory.Inventory, p inventory.Plan) {
|
||||
mu.Lock()
|
||||
defer mu.Unlock()
|
||||
if !reached {
|
||||
reached = true
|
||||
if handActConn != nil {
|
||||
bus, failed = overNATS(handActConn)
|
||||
} else if js, err := aBus(); err != nil {
|
||||
failed = err
|
||||
} else if bus, failed = overNATS(js.Conn()); failed == nil {
|
||||
closing = js.Close
|
||||
} else {
|
||||
js.Close()
|
||||
}
|
||||
}
|
||||
if bus == nil {
|
||||
switch p.WalkSaid {
|
||||
case inventory.WalkStarted:
|
||||
fmt.Fprintf(os.Stderr, "%s: its start is kept and could NOT be said as plan-moved (%v): the router "+
|
||||
"does not hold what it touches\n", p.ID, failed)
|
||||
case inventory.WalkEnded:
|
||||
fmt.Fprintf(os.Stderr, "%s: its end is kept and could NOT be said as plan-moved (%v): the router holds "+
|
||||
"what it touched until its bound\n", p.ID, failed)
|
||||
}
|
||||
return
|
||||
}
|
||||
publishPlanMoved(ctx, bus, inv, p)
|
||||
}
|
||||
done = func() {
|
||||
mu.Lock()
|
||||
defer mu.Unlock()
|
||||
inventory.PlanSaved = nil
|
||||
if closing != nil {
|
||||
closing()
|
||||
}
|
||||
}
|
||||
return said, done
|
||||
}
|
||||
|
||||
// overNATS is the bus a connection carries, with its JetStream.
|
||||
func overNATS(conn *nats.Conn) (link.Bus, error) {
|
||||
js, err := conn.JetStream()
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return link.OverNATS{Conn: conn, JS: js}, nil
|
||||
}
|
||||
|
||||
@@ -37,12 +37,41 @@ type stalledLine struct {
|
||||
// Number is the pull request's, for a line of a head the forge never announced (novox/hq issue 347).
|
||||
Number int `json:"number,omitempty"`
|
||||
State string `json:"state"`
|
||||
For string `json:"for"`
|
||||
Bound string `json:"bound"`
|
||||
H2 string `json:"h2"`
|
||||
Says string `json:"says"`
|
||||
// Walk is the walk a line is about: a waiting walk no live delivery holds, or, asked with `walks`, each walk
|
||||
// waiting for the owner's word and what holds it (novox/hq issues 362, 529).
|
||||
Walk string `json:"walk,omitempty"`
|
||||
// Waiting are the merge checks a line of the state `unanswered` waits on, as mesh-delivery says each:
|
||||
// "mesh/merge-gate pending since <UTC time>", "mesh/repo-check never set" (novox/hq issue 438).
|
||||
Waiting []string `json:"waiting,omitempty"`
|
||||
// Checks are the same merge checks as data, which the controller words in the operator's own time (novox/hq
|
||||
// issue 443): a time inside a finished sentence cannot be said again in another zone. A mesh-delivery from before
|
||||
// says none, and Waiting is said as it reads.
|
||||
Checks []waitingCheck `json:"checks,omitempty"`
|
||||
// Held is the state of the delivery of a line of the state `unanswered`, ready or rejected, when one is held
|
||||
// (novox/hq issues 441, 451): its check answered once, so a recheck is the step. Empty for a head with no
|
||||
// delivery, and from a mesh-delivery that does not say it yet; the words are never read for it.
|
||||
Held string `json:"held,omitempty"`
|
||||
For string `json:"for"`
|
||||
Bound string `json:"bound"`
|
||||
H2 string `json:"h2"`
|
||||
Says string `json:"says"`
|
||||
}
|
||||
|
||||
// waitingCheck is one merge check a stalled line waits on, as mesh-delivery gives it: its context, its state —
|
||||
// "pending", or "never-set" — and, for a pending one, since when in RFC 3339, empty when the forge did not say.
|
||||
type waitingCheck struct {
|
||||
Context string `json:"context"`
|
||||
State string `json:"state"`
|
||||
Since string `json:"since,omitempty"`
|
||||
}
|
||||
|
||||
// wordsNow is the time the words are said at, which says whether a time needs its day; a seam a test replaces.
|
||||
var wordsNow = time.Now
|
||||
|
||||
// wordsZone is the zone a stalled line's times are said in: the controller's local zone, as every other time in its
|
||||
// messages. A seam a test replaces, so that no test writes time.Local, which every goroutine of the package reads.
|
||||
var wordsZone = func() *time.Location { return time.Local }
|
||||
|
||||
// operatorsOnly is whether the table leaves H2 nothing to do for the line: the state is the operator's.
|
||||
func (l stalledLine) operatorsOnly() bool { return l.H2 == "" || strings.HasPrefix(l.H2, "none") }
|
||||
|
||||
@@ -103,6 +132,34 @@ func deliveriesStalled(ctx context.Context, conn *nats.Conn, held bool) ([]stall
|
||||
return lines, nil
|
||||
}
|
||||
|
||||
// walkWaits are, by walk, the lines mesh-delivery says of a walk waiting for its word: what holds it.
|
||||
type walkWaits map[string][]stalledLine
|
||||
|
||||
// walksWaiting asks the delivery's owner what holds each walk waiting for its word (novox/hq issue 529): its
|
||||
// `stalled` asked with `walks`, so a line of `plans` names a held delivery, its reason and the verb that releases
|
||||
// it, instead of pointing at a hand start. Nil when no holder is on record or none answers: the line then reads as
|
||||
// before. An owner from before this answers its stalled lines, of which only those naming a walk are kept.
|
||||
func walksWaiting(ctx context.Context, conn *nats.Conn, held bool) walkWaits {
|
||||
if !held {
|
||||
return nil
|
||||
}
|
||||
raw, err := askDeliveryOwner(ctx, conn, "stalled", map[string]any{"walks": true})
|
||||
if err != nil {
|
||||
return nil
|
||||
}
|
||||
var lines []stalledLine
|
||||
if json.Unmarshal(raw, &lines) != nil {
|
||||
return nil
|
||||
}
|
||||
out := walkWaits{}
|
||||
for _, l := range lines {
|
||||
if l.Walk != "" {
|
||||
out[l.Walk] = append(out[l.Walk], l)
|
||||
}
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// stalledObservations are the conditions of what is stalled.
|
||||
func stalledObservations(lines []stalledLine) []conditions.Observation {
|
||||
out := make([]conditions.Observation, 0, len(lines))
|
||||
|
||||
@@ -119,6 +119,13 @@ func TestTheBusMachineIsBehindByItsUserListAlone(t *testing.T) {
|
||||
if userListBehind("", "") {
|
||||
t.Fatal("a machine sent no list reads as behind")
|
||||
}
|
||||
// A list that could not be composed is behind: not known is never "not behind" (the review of hq issue 353).
|
||||
if !listBehind("", errors.New("the plan cannot be worked out"), digestOf([]byte(list))) {
|
||||
t.Fatal("a list nobody could compose reads as current")
|
||||
}
|
||||
if listBehind(list, nil, digestOf([]byte(list))) || !listBehind(list, nil, "") {
|
||||
t.Fatal("listBehind does not read the digest as userListBehind does")
|
||||
}
|
||||
}
|
||||
|
||||
// The machine holding the bus goes first: its declaration carries the user list the new grants are
|
||||
|
||||
@@ -74,8 +74,12 @@ type probe struct {
|
||||
// probeRegistry is the registry, in to-be 45's order. **The registry is the design's live form**: a
|
||||
// probe added to a design is a row added here.
|
||||
var probeRegistry = []probe{
|
||||
{ID: "D1", Asserts: "every machine's declaration composes, and passes the node-engine's validation",
|
||||
From: "issues 236, 263, 275", Kind: "declaration-refused", Raises: []string{kindAwaitingPush}, Phase: 1,
|
||||
// D1 also says every module assigned and left out of a machine's declaration (novox/hq issue 380), from the
|
||||
// resolution it already makes: needs-operator for a setting nobody gave, left-out for any other cause.
|
||||
{ID: "D1", Asserts: "every machine's declaration composes, and passes the node-engine's validation; no module " +
|
||||
"assigned to a machine is left out of its declaration unsaid",
|
||||
From: "issues 236, 263, 275, 380", Kind: "declaration-refused",
|
||||
Raises: []string{kindAwaitingPush, kindLeftOut, kindNeedsOperator}, Phase: 1,
|
||||
run: probeDeclarations},
|
||||
{ID: "D2", Asserts: "every holder of the mesh's resolver answers a machine name for IPv4, and NODATA for IPv6",
|
||||
From: "issue 262", Kind: "resolver-wrong", Phase: 1, run: probeResolvers},
|
||||
@@ -116,6 +120,11 @@ var probeRegistry = []probe{
|
||||
{ID: probeDeliveriesID, Asserts: "no delivery is held past its state's bound unsaid: mesh-delivery's " +
|
||||
"`stalled`, each with the transition its table lets healer H2 take", From: "ADR 0239",
|
||||
Kind: kindDeliveryStalled, Phase: 3, run: probeDeliveries},
|
||||
// The delivery budgets (novox/hq ADR 0282 decision 7): the newest delivery of each class within its budget,
|
||||
// read from mesh-delivery's `times`; a measurement said, never a delivery held.
|
||||
{ID: probeBudgetsID, Asserts: "the newest delivery of a leaf module ran on every machine within three minutes of " +
|
||||
"its merge, and of a core module within ten: mesh-delivery's `times`", From: "ADR 0282, ADR 0304",
|
||||
Kind: kindOverBudget, Phase: 3, run: probeBudgets},
|
||||
// A client of the bus reconnecting in a loop (novox/hq issue 327), from the server's record of closed
|
||||
// connections, which the bus's own module reads.
|
||||
{ID: probeReconnectsID, Asserts: "no user of the bus had its connection dropped more than twelve times in the " +
|
||||
@@ -131,6 +140,12 @@ var probeRegistry = []probe{
|
||||
{ID: "D-root", Asserts: "no agent can become root without a person on a machine where the router or a channel " +
|
||||
"proving its sender runs: not by its own account, and not through a tool that runs its command as an account " +
|
||||
"that can", From: "ADR 0259 §8", Kind: kindRootNotFree, Phase: 2, run: probeAgentRoot},
|
||||
// A module's bucket or log filling toward its cap (novox/hq ADR 0297 §6): said at three quarters, cleared
|
||||
// below seven tenths, so one at its threshold is not raised and cleared on every run. One that cannot be
|
||||
// read is said on its own, and every other is still judged.
|
||||
{ID: probeFillID, Asserts: "every module's bucket and log holds less than three quarters of its cap; one " +
|
||||
"said filling is cleared once it holds less than seven tenths", From: "ADR 0297, issue 501",
|
||||
Kind: kindBucketOrLogFilling, Raises: []string{kindBucketOrLogUnread}, Phase: 1, run: probeFill},
|
||||
{ID: "DW", Asserts: "the watchdogs of the signals table ran within three of their intervals",
|
||||
From: "ADR 0227 rule 6: the watchers are watched", Kind: "watchdogs-silent", Phase: 1, run: probeWatchdogs},
|
||||
// The core's health definitions (novox/hq to-be 45 §8, ADR 0236): what a core component's new build is
|
||||
@@ -636,7 +651,7 @@ func localDoctor(ctx context.Context) (*doctor, func(), error) {
|
||||
open.Close()
|
||||
return nil, nil, err
|
||||
}
|
||||
k, err := keeperOn(ctx, js.Conn())
|
||||
k, err := keeperOn(ctx, js.Conn(), storeLooks{open.inventory})
|
||||
if err != nil {
|
||||
js.Close()
|
||||
open.Close()
|
||||
|
||||
@@ -514,6 +514,10 @@ func composedAndValidated(ctx context.Context, open *stores, node string, gens m
|
||||
if declared.Epoch, err = open.inventory.SentEpoch(ctx, record.ID); err != nil {
|
||||
return sendable{}, nil, err
|
||||
}
|
||||
// And the generation it was last sent, as the would-send is (novox/hq issue 234).
|
||||
if declared.Generation, err = open.inventory.SentGeneration(ctx, record.ID); err != nil {
|
||||
return sendable{}, nil, err
|
||||
}
|
||||
body, err := declared.Body()
|
||||
if err != nil {
|
||||
return sendable{}, nil, err
|
||||
|
||||
@@ -0,0 +1,66 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/conditions"
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
"github.com/novox/mesh-controller/internal/link"
|
||||
)
|
||||
|
||||
// A provider whose wait fails the controller's check lists who waits on it (novox/hq issue 450).
|
||||
//
|
||||
// A wait that does not check out is judged unhealthy (ADR 0283 decision 3), so the provider raises its unhealthy
|
||||
// condition and its consumers are held under it (ADR 0240 rule 5). What is stored is what the machine said, the
|
||||
// wait unchecked: read as said, the provider seems to wait for the operator, and the held consumers were never
|
||||
// listed on the condition that is open.
|
||||
|
||||
// refusedWait is a wait for a secret the database's manifest does not declare: it fails the check.
|
||||
var refusedWait = inventory.Wait{Part: "postgres-database", Secret: "certificate", What: "the database's certificate"}
|
||||
|
||||
// judgedRefused is the provider's resource as the controller judges it: unhealthy, saying why.
|
||||
func judgedRefused() inventory.ResourceHealth {
|
||||
r := waitingDatabaseFor(refusedWait)
|
||||
r.State, r.Waits = link.StateUnhealthy, nil
|
||||
r.Reason = "says it waits for the secret certificate, which db does not declare"
|
||||
return r
|
||||
}
|
||||
|
||||
// The consumer's statement arrives after the provider's, so it is the consumer's judging (sayWaiters) that must list
|
||||
// it at the provider's unhealthy condition, made urgent by who waits on it.
|
||||
func TestAProviderWhoseWaitFailedItsCheckListsWhoWaitsOnIt(t *testing.T) {
|
||||
k, _ := withConditionsInMemory(t)
|
||||
stored := waitingDatabaseFor(refusedWait)
|
||||
open := judgeBoth(t, k, []inventory.ResourceHealth{judgedRefused()},
|
||||
map[string]inventory.NodeHealth{"anchor": {Node: "anchor", Resources: []inventory.ResourceHealth{stored}}},
|
||||
shopFailingBeside(stored))
|
||||
provider := conditionOf(open, moduleUnhealthyKey("db", "anchor"))
|
||||
if len(open) != 1 || provider == nil {
|
||||
t.Fatalf("a provider whose wait failed its check and a consumer of it raised %v; want the provider's "+
|
||||
"unhealthy alone", openKeysOf(open))
|
||||
}
|
||||
if said := provider.Evidence[0].Said; !strings.Contains(said, "shop on laptop") {
|
||||
t.Fatalf("the provider's unhealthy condition does not list shop on laptop as waiting on it: %s", said)
|
||||
}
|
||||
if provider.Severity != conditions.Urgent {
|
||||
t.Fatalf("the provider's unhealthy condition is %s with a consumer waiting on it; want urgent", provider.Severity)
|
||||
}
|
||||
}
|
||||
|
||||
// A provider that waits for a secret already given is unhealthy to its consumers too, before its own condition opens:
|
||||
// they are held under it as under any unhealthy provider, never as waiting for the operator, and its condition, when
|
||||
// open, is said as unhealthy with who waits on it.
|
||||
func TestAProviderWaitingForASecretAlreadyGivenIsUnhealthyToItsConsumers(t *testing.T) {
|
||||
given := holdingOf(nil, shopFailingBeside(waitingDatabase()), shopOnTheDatabase)
|
||||
given.waits.given["db@anchor"] = map[string]time.Time{"licence": time.Now().Add(-time.Hour)}
|
||||
by, held := given.heldWith("laptop", "shop", []inventory.ResourceHealth{failingConsumer("shop")})
|
||||
if !held || by.provider != theDatabase || len(by.waits) > 0 {
|
||||
t.Fatalf("shop under a database waiting for a licence already given: held %v under %v with waits %v; want "+
|
||||
"held under db on anchor as unhealthy, no waits", held, by.provider, by.waits)
|
||||
}
|
||||
if _, uncovered := given.waitingUncovered("laptop", "shop", []inventory.ResourceHealth{failingConsumer("shop")}); uncovered {
|
||||
t.Fatalf("a provider whose wait failed its check is said as waiting for another part")
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,148 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"fmt"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/link"
|
||||
)
|
||||
|
||||
// A wait on a clock of its own: each pause moves it on, and nothing waits in real time.
|
||||
func aFakeWait(bound time.Duration) (waitOut, *[]time.Duration) {
|
||||
clock := time.Date(2026, 10, 11, 11, 52, 2, 0, time.UTC)
|
||||
var paused []time.Duration
|
||||
return waitOut{bound: bound, first: time.Second, most: 10 * time.Second,
|
||||
now: func() time.Time { return clock },
|
||||
sleep: func(_ context.Context, d time.Duration) error {
|
||||
paused = append(paused, d)
|
||||
clock = clock.Add(d)
|
||||
return nil
|
||||
}}, &paused
|
||||
}
|
||||
|
||||
// notServed is what the bus says while node-tools re-serves, in the words seen on 2026-10-11.
|
||||
func notServed() error {
|
||||
return fmt.Errorf("cannot ask gitea.gitea_api: %w", link.ErrNothingServes)
|
||||
}
|
||||
|
||||
// A registration's forge question that lands while the tool runner re-serves is asked again, and the forge's
|
||||
// answer, seconds later, is the registration's (novox/hq issue 486).
|
||||
func TestTheForgeNotServedForAMomentIsWaitedOut(t *testing.T) {
|
||||
w, paused := aFakeWait(60 * time.Second)
|
||||
asked := 0
|
||||
facts, err := forgeWaitedOut(t.Context(), w, "novox/mesh-catalog", func(context.Context) (forgeFacts, error) {
|
||||
asked++
|
||||
if asked <= 2 {
|
||||
return forgeFacts{}, notServed()
|
||||
}
|
||||
return forgeFacts{ID: 42, Guarded: true}, nil
|
||||
})
|
||||
if err != nil {
|
||||
t.Fatalf("a forge not served for two asks failed the registration: %v", err)
|
||||
}
|
||||
if facts.ID != 42 || !facts.Guarded || asked != 3 {
|
||||
t.Fatalf("the forge's answer was %+v after %d asks, want its answer on the third", facts, asked)
|
||||
}
|
||||
if want := []time.Duration{time.Second, 2 * time.Second}; fmt.Sprint(*paused) != fmt.Sprint(want) {
|
||||
t.Fatalf("paused %v, want %v", *paused, want)
|
||||
}
|
||||
}
|
||||
|
||||
// A tool that did not answer within its wait has held the receive loop that long already: not asked again.
|
||||
func TestTheForgeNotAnsweringInTimeIsNotAskedAgain(t *testing.T) {
|
||||
w, paused := aFakeWait(60 * time.Second)
|
||||
asked := 0
|
||||
_, err := forgeWaitedOut(t.Context(), w, "novox/x", func(context.Context) (forgeFacts, error) {
|
||||
asked++
|
||||
return forgeFacts{}, fmt.Errorf("gitea did not answer: %w", link.ErrNoAnswer)
|
||||
})
|
||||
if !errors.Is(err, link.ErrNoAnswer) || asked != 1 || len(*paused) != 0 {
|
||||
t.Fatalf("a forge that did not answer in time was asked %d times, paused %v: %v", asked, *paused, err)
|
||||
}
|
||||
}
|
||||
|
||||
// An ask that hangs past the bound is cut off at the bound, not at its own wait, and the failure still says it
|
||||
// waited: the receive loop is held no longer than the bound (novox/hq issue 486).
|
||||
func TestAnAskHangingPastTheBoundIsCutOffAtIt(t *testing.T) {
|
||||
w := waitOut{bound: 200 * time.Millisecond, first: 10 * time.Millisecond, most: 50 * time.Millisecond,
|
||||
now: time.Now, sleep: sleepOrDone}
|
||||
asked := 0
|
||||
began := time.Now()
|
||||
_, err := forgeWaitedOut(t.Context(), w, "novox/mesh-catalog", func(ctx context.Context) (forgeFacts, error) {
|
||||
asked++
|
||||
if asked == 1 {
|
||||
return forgeFacts{}, notServed()
|
||||
}
|
||||
select { // link.Ask's own wait is 30 s; the bound must end it first
|
||||
case <-ctx.Done():
|
||||
return forgeFacts{}, fmt.Errorf("gitea did not answer: %w", link.ErrNoAnswer)
|
||||
case <-time.After(30 * time.Second):
|
||||
return forgeFacts{ID: 1, Guarded: true}, nil
|
||||
}
|
||||
})
|
||||
if took := time.Since(began); took > 2*time.Second {
|
||||
t.Fatalf("the wait took %s, past its bound of %s", took, w.bound)
|
||||
}
|
||||
if err == nil || !strings.Contains(err.Error(), "waited") || !strings.Contains(err.Error(), "asking 2 times") ||
|
||||
!strings.Contains(err.Error(), "issue 486") {
|
||||
t.Fatalf("the bound's end does not say it waited: %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
// Past the bound the registration fails, saying it waited, for how long, and what the forge last said.
|
||||
func TestTheForgeNotServedPastTheBoundFailsSayingItWaited(t *testing.T) {
|
||||
w, paused := aFakeWait(60 * time.Second)
|
||||
_, err := forgeWaitedOut(t.Context(), w, "novox/mesh-catalog", func(context.Context) (forgeFacts, error) {
|
||||
return forgeFacts{}, notServed()
|
||||
})
|
||||
if err == nil {
|
||||
t.Fatal("a forge never served was read as an answer")
|
||||
}
|
||||
var waited time.Duration
|
||||
for _, p := range *paused {
|
||||
waited += p
|
||||
}
|
||||
if waited > 60*time.Second || waited < 40*time.Second {
|
||||
t.Fatalf("waited %s in all, want close to and within the bound of 60s", waited)
|
||||
}
|
||||
for _, want := range []string{"waited " + waited.String(), "novox/mesh-catalog", "nothing serves", "issue 486"} {
|
||||
if !strings.Contains(err.Error(), want) {
|
||||
t.Errorf("the failure does not say %q: %v", want, err)
|
||||
}
|
||||
}
|
||||
if !errors.Is(err, link.ErrNothingServes) {
|
||||
t.Errorf("the failure lost what the forge last said: %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
// A refusal is the forge's word: never asked again.
|
||||
func TestARefusalFromTheForgeIsNeverAskedAgain(t *testing.T) {
|
||||
w, paused := aFakeWait(60 * time.Second)
|
||||
asked := 0
|
||||
_, err := forgeWaitedOut(t.Context(), w, "novox/x", func(context.Context) (forgeFacts, error) {
|
||||
asked++
|
||||
return forgeFacts{}, errors.New("gitea.gitea_api: 404 Not Found")
|
||||
})
|
||||
if err == nil || asked != 1 || len(*paused) != 0 {
|
||||
t.Fatalf("a refusal was asked %d times, paused %v: %v", asked, *paused, err)
|
||||
}
|
||||
}
|
||||
|
||||
// A registration whose own context ends stops waiting at once.
|
||||
func TestAWaitForTheForgeEndsWithItsContext(t *testing.T) {
|
||||
w, _ := aFakeWait(60 * time.Second)
|
||||
ctx, cancel := context.WithCancel(t.Context())
|
||||
w.sleep = func(ctx context.Context, d time.Duration) error { cancel(); return sleepOrDone(ctx, d) }
|
||||
asked := 0
|
||||
_, err := forgeWaitedOut(ctx, w, "novox/x", func(context.Context) (forgeFacts, error) {
|
||||
asked++
|
||||
return forgeFacts{}, notServed()
|
||||
})
|
||||
if !errors.Is(err, context.Canceled) || asked != 1 {
|
||||
t.Fatalf("asked %d times after the context ended: %v", asked, err)
|
||||
}
|
||||
}
|
||||
+147
-22
@@ -27,8 +27,10 @@ import (
|
||||
// **"Reported applied" is not enough.** ADR 0218 sent a module to one machine first and the rest once
|
||||
// that machine reported it applied. A build that applies and then does nothing, crashes, serves no
|
||||
// tools, or breaks the machine's word to the mesh passed that test. Now the first machine is judged by
|
||||
// the component's health — the core's health definitions, or a module's own — passing three times over
|
||||
// at least two minutes, within ten minutes of the apply. Only then are the rest sent.
|
||||
// the component's health — the core's health definitions, or a module's own — within ten minutes of the
|
||||
// apply: a core module passing three times over at least two minutes, a leaf module once, as soon as the
|
||||
// node-engine states it healthy (novox/hq ADR 0282 decision 4 as ADR 0304 decision 3 changed it). Only then
|
||||
// are the rest sent.
|
||||
//
|
||||
// **A failing gate stops the plan and puts the previous build back there.** The build is marked failed
|
||||
// at its gate — registration refuses it and nothing sends it again on its own — the module's registered
|
||||
@@ -43,11 +45,38 @@ var (
|
||||
gateSettle = 2 * time.Minute
|
||||
// gateBound is how long after the apply the build may take to become healthy.
|
||||
gateBound = 10 * time.Minute
|
||||
// gatePasses is how many consecutive judgings must find it healthy, gateEvery apart at the least.
|
||||
gatePasses = 3
|
||||
gateEvery = 40 * time.Second
|
||||
// gatePasses is how many consecutive judgings must find a core module healthy, gateEvery apart at the
|
||||
// least, after gateSettle. gateLeafPasses is a leaf module's: one, taken once the node-engine states every
|
||||
// resource of it healthy by its own check, with no settle (novox/hq ADR 0282 decision 4 as ADR 0304
|
||||
// decision 3 changed it, issue 524).
|
||||
gatePasses = 3
|
||||
gateLeafPasses = 1
|
||||
gateLeafSettles = false
|
||||
gateEvery = 40 * time.Second
|
||||
)
|
||||
|
||||
// coreModule is whether a module is judged as the core (novox/hq ADR 0282 decision 1): one on the controller's
|
||||
// own path, or one holding the mesh's resolver. Every other module is a leaf.
|
||||
func coreModule(module string, m catalogue.Manifest) bool {
|
||||
if _, own := onTheControllersPath[module]; own {
|
||||
return true
|
||||
}
|
||||
for _, c := range m.Claims {
|
||||
if c.Name == resolverSeat {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return coreComponent(module) != ""
|
||||
}
|
||||
|
||||
// gateWants is how many passes a module needs, and whether it must stay healthy gateSettle first.
|
||||
func gateWants(module string, m catalogue.Manifest) (passes int, settles bool) {
|
||||
if coreModule(module, m) {
|
||||
return gatePasses, true
|
||||
}
|
||||
return gateLeafPasses, gateLeafSettles
|
||||
}
|
||||
|
||||
// gateProbe is the registry's row for the gate's verdicts and the witnesses' rollbacks: its conditions
|
||||
// are raised by a plan as it judges, and kept or cleared by the probe on every run.
|
||||
const gateProbe = "DG"
|
||||
@@ -121,10 +150,13 @@ type gateFacts struct {
|
||||
health map[string]inventory.NodeHealth
|
||||
healthErr error
|
||||
// heldOn is, per "<module>@<machine>", the provider its findings are held under (ADR 0240 rule 5).
|
||||
heldOn map[string]string
|
||||
heldOn map[string]heldReading
|
||||
// groupsAdded is, per module, whether the move judged puts an account in a group its previous build did
|
||||
// not (issue 318 review): the only move whose wait for a new login is excused.
|
||||
groupsAdded map[string]bool
|
||||
// waits is what the controller holds to check a module's wait for the operator (novox/hq ADR 0283): the
|
||||
// manifest of each module's build judged, and the secrets given on each machine.
|
||||
waits operatorWaitFacts
|
||||
// sent is, per machine, the declaration the gate's own send carried there (novox/hq issue 352): a
|
||||
// report is held against it, never against the send made last. sentBuilds is what each machine was
|
||||
// last sent of every module, and judged the commit of each module this gate judges: a machine last
|
||||
@@ -134,6 +166,29 @@ type gateFacts struct {
|
||||
commits map[string]string
|
||||
}
|
||||
|
||||
// heldReading is the provider a module's findings are held under, as "<module> on <machine>", and, when that
|
||||
// provider only waits for the operator for the part the module needs, its wait in one sentence (novox/hq issue
|
||||
// 405): the module's gate then reads as a wait for a person (ADR 0254), a pass carrying the wait, as ADR 0283
|
||||
// decision 4 reads the waiting provider itself. A walk never waits on the operator's secret, there or here.
|
||||
type heldReading struct {
|
||||
on, waits string
|
||||
}
|
||||
|
||||
// heldReadings is, per "<module>@<machine>" in every machine's newest statement, what its findings are held under.
|
||||
func heldReadings(hold *holding) map[string]heldReading {
|
||||
out := map[string]heldReading{}
|
||||
for machine := range hold.healths {
|
||||
for module, by := range hold.heldModules(machine) {
|
||||
reading := heldReading{on: by.provider.Module + " on " + by.provider.Node}
|
||||
if len(by.waits) > 0 {
|
||||
reading.waits = operatorWaitSaid(by.provider.Module, by.provider.Node, by.waits)
|
||||
}
|
||||
out[module+"@"+machine] = reading
|
||||
}
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// reportedOn says a machine's last report is on what the gate sent it (novox/hq issue 352): on that
|
||||
// declaration, or one it was sent after it — or, for a gate kept before sends were kept on it, on the
|
||||
// declaration last sent. On 2026-10-09 a release's gate read the control node's report against a newer
|
||||
@@ -199,12 +254,7 @@ var gatherGateFacts = func(ctx context.Context, open *stores, component string)
|
||||
// Whose findings wait on an unhealthy provider (ADR 0240 rule 5): their gates wait, not fail.
|
||||
if f.healthErr == nil && f.openErr == nil {
|
||||
if hold, err := readHolding(ctx, inv, f.open); err == nil {
|
||||
f.heldOn = map[string]string{}
|
||||
for machine := range f.health {
|
||||
for module, p := range hold.heldModules(machine) {
|
||||
f.heldOn[module+"@"+machine] = p.Module + " on " + p.Node
|
||||
}
|
||||
}
|
||||
f.heldOn = heldReadings(hold)
|
||||
}
|
||||
}
|
||||
if theLease != nil {
|
||||
@@ -257,10 +307,11 @@ func judgeHealth(module, component string, m catalogue.Manifest, machine string,
|
||||
firstLine(f.openErr.Error())
|
||||
}
|
||||
for _, c := range f.open {
|
||||
// A wait for a person's new login, or for a directory used as found to be handed over, is the module's
|
||||
// reading, not a fault raised since the send: the gate reads it from the statement below (ADR 0254,
|
||||
// novox/hq issue 339).
|
||||
if c.Source == gateProbe || c.OpenAt(since) || c.Kind == kindReloginNeeded || c.Kind == kindUsedAsFound {
|
||||
// A wait for a person's new login, for a directory used as found to be handed over, or for the
|
||||
// operator's secret or setting, is the module's reading, not a fault raised since the send: the gate
|
||||
// reads it from the statement below (ADR 0254, novox/hq issue 339, ADR 0283).
|
||||
if c.Source == gateProbe || c.OpenAt(since) || c.Kind == kindReloginNeeded || c.Kind == kindUsedAsFound ||
|
||||
c.Kind == kindNeedsOperator {
|
||||
continue
|
||||
}
|
||||
onIt := c.Subject.Machine == machine || slices.Contains(c.Subject.Also, machine) ||
|
||||
@@ -477,6 +528,7 @@ func judgeMoves(ctx context.Context, open *stores, g *inventory.PlanGate, pairs
|
||||
return "", err
|
||||
}
|
||||
facts.groupsAdded = movesAddingGroups(ctx, open.inventory, g, pairs, shelf)
|
||||
facts.waits = gateWaitFacts(ctx, open.inventory, g, pairs, shelf, facts.health)
|
||||
facts.sent = g.Sent
|
||||
facts.commits, facts.sentBuilds = judgedCommits(g, pairs), map[string]map[string]string{}
|
||||
// A module this gate put back at once (putBackBroken) was sent its earlier build by the gate itself:
|
||||
@@ -585,8 +637,24 @@ func judgeMoves(ctx context.Context, open *stores, g *inventory.PlanGate, pairs
|
||||
}
|
||||
}
|
||||
settled := now.Sub(*g.Since) >= gateSettle
|
||||
// What the send needs is what its most demanding module needs: a send carrying a core module is judged
|
||||
// as the core.
|
||||
wants, settles := 0, false
|
||||
for _, m := range modules {
|
||||
p, s := gateWants(m, shelf[m])
|
||||
wants, settles = max(wants, p), settles || s
|
||||
}
|
||||
if len(modules) == 0 {
|
||||
// A send judged on no machine of its modules (its first machine not running them) has no class to
|
||||
// be judged by: it is judged as the core, never passed at once without a reading.
|
||||
wants, settles = gatePasses, true
|
||||
}
|
||||
g.Wants = wants
|
||||
// A module's own pass is its own class's: a leaf beside a core module that fails keeps its build after
|
||||
// its one reading, and only what did not pass is put back (issue 318's rule, by class since issue 524).
|
||||
passedAlone := func(m string) bool {
|
||||
return settled && reading[m] <= healthPerson && g.Healthy[m] >= gatePasses
|
||||
p, s := gateWants(m, shelf[m])
|
||||
return (settled || !s) && reading[m] <= healthPerson && g.Healthy[m] >= p
|
||||
}
|
||||
// fail decides the send failed: what passed on its own keeps its pass, everything else is put back.
|
||||
fail := func(why string) {
|
||||
@@ -603,6 +671,7 @@ func judgeMoves(ctx context.Context, open *stores, g *inventory.PlanGate, pairs
|
||||
pastBound := now.Sub(*g.Since) > gateBound
|
||||
switch {
|
||||
case worst == healthBroken:
|
||||
g.Read(now, false, g.BrokenWhy)
|
||||
var judging []string
|
||||
for _, m := range modules {
|
||||
if reading[m] != healthBroken && !passedAlone(m) {
|
||||
@@ -621,8 +690,10 @@ func judgeMoves(ctx context.Context, open *stores, g *inventory.PlanGate, pairs
|
||||
// Waiting on a provider that is unhealthy: not a pass, and not a failure at the bound either —
|
||||
// the provider's own condition says what is wrong (ADR 0240 rule 5).
|
||||
g.Passes, g.LastPass, g.Last, g.Failing = 0, nil, why, failing
|
||||
g.Read(now, false, why)
|
||||
case worst == healthNotYet:
|
||||
g.Passes, g.LastPass, g.Last, g.Failing = 0, nil, why, failing
|
||||
g.Read(now, false, why)
|
||||
if pastBound {
|
||||
fail(fmt.Sprintf("not healthy within %s of its apply: %s", gateBound, why))
|
||||
}
|
||||
@@ -630,7 +701,8 @@ func judgeMoves(ctx context.Context, open *stores, g *inventory.PlanGate, pairs
|
||||
// Healthy, or waiting for a person (ADR 0254): a pass, the wait carried along in the verdict.
|
||||
g.Passes++
|
||||
g.LastPass, g.Last, g.Failing = &now, "", nil
|
||||
if g.Passes >= gatePasses && settled {
|
||||
g.Read(now, true, "")
|
||||
if g.Passes >= wants && (settled || !settles) {
|
||||
decide(g, inventory.GatePassed, fmt.Sprintf("healthy %d times over %s", g.Passes,
|
||||
now.Sub(*g.Since).Round(time.Second))+waitsSaid(g.Waits), now)
|
||||
}
|
||||
@@ -747,6 +819,47 @@ func movesAddingGroups(ctx context.Context, inv *inventory.Inventory, g *invento
|
||||
return out
|
||||
}
|
||||
|
||||
// gateWaitFacts reads what checks the waits for the operator of the modules a gate judges (novox/hq ADR 0283): the
|
||||
// manifest of the build judged — the one it moves to, else the catalogue's — and the secrets given on each machine
|
||||
// that says a module of them waits.
|
||||
func gateWaitFacts(ctx context.Context, inv *inventory.Inventory, g *inventory.PlanGate, pairs []judged,
|
||||
shelf map[string]catalogue.Manifest, health map[string]inventory.NodeHealth) operatorWaitFacts {
|
||||
var f operatorWaitFacts
|
||||
judgedManifests := map[string]catalogue.Manifest{}
|
||||
byMachine := map[string][]string{}
|
||||
for _, j := range pairs {
|
||||
waiting := false
|
||||
for _, r := range health[j.node].Resources {
|
||||
if r.Module == j.module && r.State == link.StateWaiting {
|
||||
waiting = true
|
||||
}
|
||||
}
|
||||
if !waiting {
|
||||
continue
|
||||
}
|
||||
byMachine[j.node] = append(byMachine[j.node], j.module)
|
||||
if _, done := judgedManifests[j.module]; done {
|
||||
continue
|
||||
}
|
||||
to := g.To
|
||||
for _, c := range g.Carried {
|
||||
if c.Module == j.module {
|
||||
to = c.To
|
||||
break
|
||||
}
|
||||
}
|
||||
if m, found, err := inv.ManifestAt(ctx, j.module, to); err == nil && found {
|
||||
judgedManifests[j.module] = m
|
||||
} else if m, known := shelf[j.module]; known {
|
||||
judgedManifests[j.module] = m
|
||||
}
|
||||
}
|
||||
for machine, modules := range byMachine {
|
||||
readWaitFacts(ctx, inv, machine, modules, judgedManifests, &f)
|
||||
}
|
||||
return f
|
||||
}
|
||||
|
||||
// decide sets a gate's verdict.
|
||||
func decide(g *inventory.PlanGate, verdict, why string, now time.Time) {
|
||||
g.Verdict, g.Why, g.JudgedAt = verdict, why, &now
|
||||
@@ -926,7 +1039,7 @@ func gateFailed(ctx context.Context, open *stores, p *inventory.Plan, module str
|
||||
}
|
||||
return
|
||||
}
|
||||
sent, err := sendRollout(withScope(ctx, sendScope{modules: map[string]bool{module: true}}), open, g.Machines)
|
||||
sent, err := sendRollout(withScope(ctx, sendScope{modules: map[string]bool{module: true}, puttingBack: true}), open, g.Machines)
|
||||
if err != nil {
|
||||
notBack(fmt.Sprintf("its registered build is back at %s, and sending it to %s was refused: %v — `push %s` "+
|
||||
"sends it", short(previous.Commit), strings.Join(g.Machines, ", "), err, g.Machines[0]))
|
||||
@@ -1019,7 +1132,7 @@ func sendRollbacks(ctx context.Context, open *stores, p *inventory.Plan, b *roll
|
||||
}
|
||||
inv := open.inventory
|
||||
sort.Strings(b.machines)
|
||||
sent, err := sendRollout(withScope(ctx, sendScope{modules: b.modules}), open, b.machines)
|
||||
sent, err := sendRollout(withScope(ctx, sendScope{modules: b.modules, puttingBack: true}), open, b.machines)
|
||||
var back []string
|
||||
for _, r := range b.pending {
|
||||
if err != nil {
|
||||
@@ -1272,9 +1385,9 @@ func gateLine(g *inventory.PlanGate) string {
|
||||
if g.Why != "" {
|
||||
line += ": " + g.Why
|
||||
} else if g.Last != "" {
|
||||
line += fmt.Sprintf(" (%d of %d passes; wanting: %s)", g.Passes, gatePasses, g.Last)
|
||||
line += fmt.Sprintf(" (%d of %d passes; wanting: %s)", g.Passes, gateWanted(g), g.Last)
|
||||
} else if g.Verdict == "" {
|
||||
line += fmt.Sprintf(" (%d of %d passes)", g.Passes, gatePasses)
|
||||
line += fmt.Sprintf(" (%d of %d passes)", g.Passes, gateWanted(g))
|
||||
}
|
||||
if g.Verdict == "" && len(g.Waits) > 0 {
|
||||
line += waitsSaid(g.Waits)
|
||||
@@ -1285,6 +1398,10 @@ func gateLine(g *inventory.PlanGate) string {
|
||||
if g.Rollback != "" {
|
||||
line += "; " + g.Rollback
|
||||
}
|
||||
// Before the send it judges (novox/hq issue 490).
|
||||
if said := grantsSaid(g.Grants); said != "" {
|
||||
line += "; " + said
|
||||
}
|
||||
return line
|
||||
}
|
||||
|
||||
@@ -1313,3 +1430,11 @@ func witnessObservation(node string, r lease.Rollback) conditions.Observation {
|
||||
Summary: fmt.Sprintf("the witness on %s judged the %s %s not healthy %s at %s: %s", node, r.Component,
|
||||
short(r.From), what, r.At.UTC().Format(time.RFC3339), r.Why)}
|
||||
}
|
||||
|
||||
// gateWanted is the passes a gate's send needs, three where the gate was judged before it was said.
|
||||
func gateWanted(g *inventory.PlanGate) int {
|
||||
if g.Wants > 0 {
|
||||
return g.Wants
|
||||
}
|
||||
return gatePasses
|
||||
}
|
||||
|
||||
@@ -53,6 +53,7 @@ func healthyContainer(module string) inventory.ResourceHealth {
|
||||
// tools' witness put its build back at once, and the send waits for the healthy module's own verdict — a pass,
|
||||
// counted over the gate's spacing — before it says its own. The broken one alone is put back.
|
||||
func TestAFaultBeforeTheSettleTimeWaitsForTheModuleBesideIt(t *testing.T) {
|
||||
judgeLeavesAsTheCore(t)
|
||||
open := aMesh(t)
|
||||
ctx := t.Context()
|
||||
withGateBounds(t, 150*time.Millisecond, 20*time.Millisecond, 10*time.Second)
|
||||
@@ -284,6 +285,7 @@ func TestAProviderWaitingForALoginSaysWhoWaitsOnIt(t *testing.T) {
|
||||
// tools are marked and put back in the very judging that found them broken — their registered build is the
|
||||
// one before, and the laptop is sent it — while `app` goes on being judged, recovers, and keeps its own pass.
|
||||
func TestABrokenModuleIsPutBackAtOnceAndTheOneBesideItGetsItsOwnVerdict(t *testing.T) {
|
||||
judgeLeavesAsTheCore(t)
|
||||
open := aMesh(t)
|
||||
ctx := t.Context()
|
||||
inv := open.inventory
|
||||
|
||||
@@ -153,6 +153,7 @@ func (g *gateMesh) plan(t *testing.T) inventory.Plan {
|
||||
// registered and sent to it again — and never reaches the second machine; it is marked, said as a
|
||||
// condition and an event, never registered or rolled back again.
|
||||
func TestABuildThatFailsItsGateIsRolledBackOnItsFirstMachineAndGoesNoFurther(t *testing.T) {
|
||||
judgeLeavesAsTheCore(t)
|
||||
g := aGateMesh(t)
|
||||
ctx := t.Context()
|
||||
inv := g.open.inventory
|
||||
@@ -255,7 +256,7 @@ func TestABuildThatPassesItsGateRollsEverywhereUnattended(t *testing.T) {
|
||||
t.Fatalf("sent %v", g.sent)
|
||||
}
|
||||
gate := p.Modules["app"].Gate
|
||||
if p.State != inventory.PlanDone || gate == nil || gate.Verdict != inventory.GatePassed || gate.Passes < gatePasses {
|
||||
if p.State != inventory.PlanDone || gate == nil || gate.Verdict != inventory.GatePassed || gate.Passes < gateWanted(gate) {
|
||||
t.Fatalf("the plan is %s (%s), its gate %+v", p.State, p.Note, gate)
|
||||
}
|
||||
if v, found, err := g.open.inventory.GateOf(ctx, "build-2"); err != nil || !found || v.Verdict != inventory.GatePassed {
|
||||
@@ -266,8 +267,52 @@ func TestABuildThatPassesItsGateRollsEverywhereUnattended(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// A leaf module passes its gate on one reading, as soon as its first machine is healthy, without waiting out the
|
||||
// core's settle time (novox/hq ADR 0282 decision 4 as ADR 0304 decision 3 changed it, issue 524).
|
||||
func TestALeafModulePassesOnOneHealthyReading(t *testing.T) {
|
||||
g := aGateMesh(t)
|
||||
ctx := t.Context()
|
||||
gateSettle = time.Hour // a core module could not pass for an hour
|
||||
advancePlans(ctx, g.open) // the first machine is sent the new build
|
||||
advancePlans(ctx, g.open) // one healthy judging
|
||||
p := g.plan(t)
|
||||
gate := p.Modules["app"].Gate
|
||||
if gate == nil || gate.Verdict != inventory.GatePassed || gate.Passes != 1 || gate.Wants != 1 {
|
||||
t.Fatalf("a leaf module's gate after one healthy judging: %+v (plan %s: %s)", gate, p.State, p.Note)
|
||||
}
|
||||
if !strings.Contains(gate.Why, "healthy 1 times") {
|
||||
t.Errorf("the verdict says %q", gate.Why)
|
||||
}
|
||||
}
|
||||
|
||||
// Which modules are judged as the core: those on the controller's own path and the resolver's holder, three
|
||||
// readings after the settle time; every other module one (novox/hq ADR 0282 decision 1, ADR 0304 decision 3).
|
||||
func TestAModuleIsJudgedByItsClass(t *testing.T) {
|
||||
for _, c := range []struct {
|
||||
module string
|
||||
claims []catalogue.Claim
|
||||
passes int
|
||||
settles bool
|
||||
}{
|
||||
{"app", nil, 1, false},
|
||||
{"nzbget", nil, 1, false},
|
||||
{"mesh-controller", nil, 3, true},
|
||||
{"mesh-host", nil, 3, true},
|
||||
{"node-tools", nil, 3, true},
|
||||
{"nats", nil, 3, true},
|
||||
{catalogue.DeliverySeat, nil, 3, true},
|
||||
{"dnsmasq", []catalogue.Claim{{Name: resolverSeat}}, 3, true},
|
||||
} {
|
||||
p, s := gateWants(c.module, catalogue.Manifest{Module: c.module, Claims: c.claims})
|
||||
if p != c.passes || s != c.settles {
|
||||
t.Errorf("%s: %d passes, settles %v; want %d, %v", c.module, p, s, c.passes, c.settles)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// A first machine that never becomes healthy fails its gate at the bound, and is put back.
|
||||
func TestABuildNeverHealthyFailsAtTheBound(t *testing.T) {
|
||||
judgeLeavesAsTheCore(t)
|
||||
g := aGateMesh(t)
|
||||
ctx := t.Context()
|
||||
advancePlans(ctx, g.open)
|
||||
@@ -593,3 +638,13 @@ func TestAWitnessesVerdictIsAConditionWhileItsReportsSayIt(t *testing.T) {
|
||||
t.Fatalf("a verdict the reports no longer carry is still said: %+v %v", obs, err)
|
||||
}
|
||||
}
|
||||
|
||||
// judgeLeavesAsTheCore makes a test's leaf modules judged as a core module is, three readings after the settle
|
||||
// time, for a test of the gate's other rules (a fault, the bound, a supersession) that needs a judging still
|
||||
// open after a healthy reading.
|
||||
func judgeLeavesAsTheCore(t *testing.T) {
|
||||
t.Helper()
|
||||
wasPasses, wasSettles := gateLeafPasses, gateLeafSettles
|
||||
gateLeafPasses, gateLeafSettles = gatePasses, true
|
||||
t.Cleanup(func() { gateLeafPasses, gateLeafSettles = wasPasses, wasSettles })
|
||||
}
|
||||
|
||||
@@ -0,0 +1,300 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"io"
|
||||
"os"
|
||||
"sort"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/catalogue"
|
||||
"github.com/novox/mesh-controller/internal/conditions"
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
"github.com/novox/mesh-controller/internal/link"
|
||||
)
|
||||
|
||||
// The assignment generation a declaration was composed from, and the record of every send (novox/hq
|
||||
// issue 234).
|
||||
//
|
||||
// On 2026-10-04 a declaration newer in sequence than every other named four fewer modules than the
|
||||
// assignments held, and a machine applied it and undeclared all four. The sequence orders arrival and
|
||||
// cannot tell a later send that carries an older view of the assignments. So a declaration now carries
|
||||
// the generation of the assignments it was composed from — a counter the store raises in the same
|
||||
// transaction as every assignment change — and a machine refuses one older than it applied, unless it is
|
||||
// a gate's put-back. And every send is written down with who sent it, from which generation and naming
|
||||
// which modules: the controller logged no send then, and which process sent the stale declaration could
|
||||
// not be read back from anything the mesh kept.
|
||||
|
||||
// kindOlderGeneration is S20's kind: a machine refused a send for the generation it was composed from.
|
||||
const kindOlderGeneration = "older-generation"
|
||||
|
||||
// generationRefusalsSaid is how long a refused send is said after its refusal: an hour, as an advisory is.
|
||||
const generationRefusalsSaid = advisoryQuiet
|
||||
|
||||
// stamp gives a composed declaration the order allotted to it before it was composed: its sequence, and
|
||||
// the epoch and generation when the machine reads them — and keeps the generation and acting epoch for the
|
||||
// record of the send whether or not the machine is sent them.
|
||||
//
|
||||
// **No put-back mark is sent.** A gate puts a machine back by composing it again (sendRollout), so its
|
||||
// declaration is allotted here like any other and carries the generation as it stands — never older than
|
||||
// what the machine applied. The node-engine reads a `put_back` key (mesh-host#82); this controller never
|
||||
// needs to send one.
|
||||
func (o order) stamp(d *sendable) {
|
||||
d.Sequence, d.Epoch = o.sequence, o.epoch
|
||||
d.composedFrom, d.actingEpoch = o.generation, o.acting
|
||||
d.Generation = 0
|
||||
if o.readsGeneration && o.generation > 0 {
|
||||
d.Generation = o.generation
|
||||
}
|
||||
}
|
||||
|
||||
// sentRecord is what the record of a send keeps beside its digest.
|
||||
type sentRecord struct {
|
||||
sequence int64
|
||||
epoch uint64
|
||||
generation int64
|
||||
// toldGeneration is the generation on the wire, which the would-send is stamped with: zero for a machine
|
||||
// whose node-engine has not said it reads one.
|
||||
toldGeneration int64
|
||||
sender string
|
||||
modules []string
|
||||
}
|
||||
|
||||
// sentRecordOf is a composed send's record: its sender is the caller this process acts for.
|
||||
func sentRecordOf(ctx context.Context, d sendable) sentRecord {
|
||||
return sentRecord{sequence: d.Sequence, epoch: d.actingEpoch, generation: d.composedFrom,
|
||||
toldGeneration: d.Generation, sender: senderOf(callerOf(ctx)), modules: d.modules}
|
||||
}
|
||||
|
||||
// callerOf is who asked for what this process does: the seat call's caller when ctx belongs to one, the
|
||||
// caller the controller ran this command for, or the account at the shell.
|
||||
func callerOf(ctx context.Context) string {
|
||||
if c := link.CallerIn(ctx); c != "" {
|
||||
return c
|
||||
}
|
||||
return link.Caller()
|
||||
}
|
||||
|
||||
// senderOf is a send's sender in words: who asked, and the process and build that composed it — the
|
||||
// answer issue 234 could not find, because two controllers and a one-shot push were all sending then.
|
||||
func senderOf(caller string) string {
|
||||
host, _ := os.Hostname()
|
||||
return fmt.Sprintf("%s (pid %d on %s, build %s)", caller, os.Getpid(), host, version)
|
||||
}
|
||||
|
||||
// namedModules are the modules a declaration names: its machine's set, less what was left out of it.
|
||||
func namedModules(plan catalogue.Resolution, leftOut map[string]string) []string {
|
||||
out := make([]string, 0, len(plan.Modules))
|
||||
for _, m := range plan.Modules {
|
||||
if _, left := leftOut[m.Module]; !left {
|
||||
out = append(out, m.Module)
|
||||
}
|
||||
}
|
||||
sort.Strings(out)
|
||||
return out
|
||||
}
|
||||
|
||||
// heardGenerationRefusal keeps a machine's refusal of a send for its generation, so S20 names its sender
|
||||
// and says it (novox/hq issue 234): on the send it refused or — when the mesh has no record of sending that
|
||||
// sequence — as a refusal of its own, naming the sender as unknown. Either way S20 is raised: a refusal the
|
||||
// mesh cannot attribute is the louder fact, not a quieter one.
|
||||
//
|
||||
// **And raises the mesh's counter past what the machine applied, when the refused send was composed from
|
||||
// the counter as it stands** (counterBehind): then the sender's view was not stale — the counter is behind
|
||||
// the machine, which is a store put back from a backup — and every send after would be refused for ever. A
|
||||
// stale sender's generation is below the counter, and the counter is left alone for it.
|
||||
//
|
||||
// Nothing is sent from here. This runs in the controller's receive loop, and a push from it would hold that
|
||||
// loop, and the machine's hold, for as long as the push takes — the deaf controller of issues 184 and 185.
|
||||
// S20 names `push <node>` for that case instead.
|
||||
func heardGenerationRefusal(ctx context.Context, inv *inventory.Inventory, report link.Report) {
|
||||
r := report.OlderGeneration
|
||||
if r == nil || inv == nil || report.Node == "" {
|
||||
return
|
||||
}
|
||||
node, err := inv.NodeByName(ctx, report.Node)
|
||||
if err != nil {
|
||||
fmt.Fprintf(os.Stderr, "mesh-controller: %s refused a send for its generation, and the machine cannot be "+
|
||||
"read, so it is not raised: %v\n", report.Node, err)
|
||||
return
|
||||
}
|
||||
var raised int64
|
||||
if now, err := inv.AssignmentGeneration(ctx); err != nil {
|
||||
fmt.Fprintf(os.Stderr, "mesh-controller: %s refused a send for its generation, and the mesh's own cannot be "+
|
||||
"read: %v\n", report.Node, err)
|
||||
} else if counterBehind(*r, now) {
|
||||
if raised, err = inv.RaiseAssignmentGeneration(ctx, r.Applied); err != nil {
|
||||
fmt.Fprintf(os.Stderr, "mesh-controller: the assignment generation (%d) is behind what %s applied (%d), "+
|
||||
"and could not be raised: %v\n", now, report.Node, r.Applied, err)
|
||||
raised = 0
|
||||
} else {
|
||||
fmt.Fprintf(os.Stderr, "mesh-controller: the assignment generation was %d, behind what %s applied (%d) — "+
|
||||
"a store put back from a backup — and is raised to %d; `push %s` sends it what the mesh holds now\n",
|
||||
now, report.Node, r.Applied, raised, report.Node)
|
||||
}
|
||||
}
|
||||
send, found, err := inv.RefusedSend(ctx, node.ID, report.Sequence, r.Applied, raised)
|
||||
if err == nil && !found {
|
||||
send, err = inv.RecordUnrecordedRefusal(ctx, inventory.Send{Node: node.ID, Sequence: report.Sequence,
|
||||
Epoch: report.Epoch, Generation: r.Generation, Digest: report.Declared, RefusedApplied: r.Applied,
|
||||
CounterRaisedTo: raised})
|
||||
}
|
||||
if err != nil {
|
||||
fmt.Fprintf(os.Stderr, "mesh-controller: %s refused send %d for its generation, and the refusal could not be "+
|
||||
"kept, so it is not raised: %v\n", report.Node, report.Sequence, err)
|
||||
return
|
||||
}
|
||||
fmt.Fprintf(os.Stderr, "mesh-controller: %s refused send %d from %s: composed from assignment generation %d, "+
|
||||
"and it applied %d\n", report.Node, report.Sequence, send.Sender, r.Generation, r.Applied)
|
||||
}
|
||||
|
||||
// counterBehind says a refusal shows the mesh's counter behind the machine rather than a stale sender: the
|
||||
// refused send carried the counter as it stands now, and the machine applied more than that.
|
||||
func counterBehind(r link.GenerationRefusal, now int64) bool {
|
||||
return r.Generation >= now && r.Applied > r.Generation
|
||||
}
|
||||
|
||||
// watchGenerationRefusals is S20: every send a machine refused within the hour for the generation it was
|
||||
// composed from, naming who sent it (novox/hq issue 234). One per machine, the newest refusal.
|
||||
func watchGenerationRefusals(f *signalFacts) []conditions.Observation {
|
||||
seen := map[string]bool{}
|
||||
var out []conditions.Observation
|
||||
for _, s := range f.refusedSends {
|
||||
if s.RefusedAt == nil || f.now.Sub(*s.RefusedAt) > generationRefusalsSaid || seen[s.NodeName] {
|
||||
continue
|
||||
}
|
||||
seen[s.NodeName] = true
|
||||
o := conditions.Observation{Scope: conditions.ScopeMachine, ID: s.NodeName, Kind: kindOlderGeneration,
|
||||
Machine: s.NodeName, Severity: conditions.Warning,
|
||||
Summary: fmt.Sprintf("%s refused sequence %d from %s: it was composed from assignment generation %d, and "+
|
||||
"%s applied generation %d — a sender composing from a view of the assignments the mesh has moved "+
|
||||
"past; it named %s", s.NodeName, s.Sequence, s.Sender, s.Generation, s.NodeName, s.RefusedApplied,
|
||||
modulesWords(s.Modules)),
|
||||
Said: fmt.Sprintf("refused at %s", s.RefusedAt.UTC().Format(time.RFC3339)),
|
||||
Headline: fmt.Sprintf("%s refused an out-of-date update", s.NodeName),
|
||||
Explanation: fmt.Sprintf("Something sent %s an update made from an older list of what runs there. %s "+
|
||||
"refused it, so nothing was removed. Nothing for you to do unless it repeats.", s.NodeName, s.NodeName),
|
||||
Resolved: fmt.Sprintf("%s has had no out-of-date update for an hour", s.NodeName)}
|
||||
if s.CounterRaisedTo > 0 {
|
||||
// Not a stale sender: the mesh's counter was behind the machine (a store put back from a backup) and
|
||||
// was raised; nothing has sent the machine its declaration since, so a person is asked to.
|
||||
o.Summary = fmt.Sprintf("%s refused sequence %d from %s: it was composed from assignment generation %d, "+
|
||||
"the mesh's own, and %s applied generation %d — the mesh's counter was behind the machine (a store "+
|
||||
"put back from a backup?) and is raised to %d; `push %s` sends it what the mesh holds now",
|
||||
s.NodeName, s.Sequence, s.Sender, s.Generation, s.NodeName, s.RefusedApplied, s.CounterRaisedTo,
|
||||
s.NodeName)
|
||||
o.Explanation = fmt.Sprintf("Needs you: push %s. The mesh's record was older than %s, so %s refused its "+
|
||||
"update and kept what it had. The record is repaired; a push sends the update again.",
|
||||
s.NodeName, s.NodeName, s.NodeName)
|
||||
}
|
||||
out = append(out, o)
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// modulesWords is a send's modules as a sentence says them.
|
||||
func modulesWords(modules []string) string {
|
||||
if len(modules) == 0 {
|
||||
return "no module the mesh recorded"
|
||||
}
|
||||
return strings.Join(modules, ", ")
|
||||
}
|
||||
|
||||
// writeLastSend says what a machine was last told, by whom and from which generation (novox/hq issue 234), and
|
||||
// what it answered (issue 485): nothing when the mesh has not recorded a send to it.
|
||||
func writeLastSend(ctx context.Context, w io.Writer, inv *inventory.Inventory, node string) error {
|
||||
s, found, err := inv.LastSend(ctx, node)
|
||||
if err != nil || !found {
|
||||
return err
|
||||
}
|
||||
fmt.Fprintf(w, "%s:\n", node)
|
||||
for _, line := range lastSendLines(s) {
|
||||
fmt.Fprintln(w, line)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// lastSendLines is a machine's last send in full, as `node show` and `plan` say it (novox/hq issue 485): when,
|
||||
// by whom, under which lease epoch, from which assignment generation, naming which modules, and what the
|
||||
// machine answered of it — the refusal in its own words.
|
||||
func lastSendLines(s inventory.Send) []string {
|
||||
const stamp = "2006-01-02 15:04:05"
|
||||
epoch := "under no lease epoch"
|
||||
if s.Epoch > 0 {
|
||||
epoch = fmt.Sprintf("under lease epoch %d", s.Epoch)
|
||||
}
|
||||
generation := "no assignment generation recorded"
|
||||
if s.Generation > 0 {
|
||||
generation = fmt.Sprintf("assignment generation %d", s.Generation)
|
||||
}
|
||||
lines := []string{
|
||||
fmt.Sprintf(" last sent sequence %d at %s", s.Sequence, s.SentAt.Local().Format(stamp)),
|
||||
fmt.Sprintf(" by %s", s.Sender),
|
||||
fmt.Sprintf(" %s, composed from %s", epoch, generation),
|
||||
fmt.Sprintf(" naming %s", modulesWords(s.Modules)),
|
||||
}
|
||||
answer := func(words string) { lines = append(lines, " its answer "+words) }
|
||||
switch a := s.Answer; {
|
||||
case s.RefusedAt != nil:
|
||||
// Before the report: a refusal for the generation is kept on the send itself and is the machine's
|
||||
// answer to this send in particular.
|
||||
answer(fmt.Sprintf("refused it at %s: it had applied assignment generation %d, newer than this one",
|
||||
s.RefusedAt.Local().Format(stamp), s.RefusedApplied))
|
||||
case a.Outcome == "" || a.At == nil:
|
||||
answer("the machine has not reported on it yet")
|
||||
case a.Outcome == inventory.OutcomeApplied:
|
||||
answer("applied it at " + a.At.Local().Format(stamp))
|
||||
case a.Outcome == inventory.OutcomeRefused:
|
||||
answer("refused it at " + a.At.Local().Format(stamp) + ", in its words:")
|
||||
for _, line := range strings.Split(strings.TrimRight(a.Refused, "\n"), "\n") {
|
||||
lines = append(lines, " "+strings.TrimSpace(line))
|
||||
}
|
||||
default:
|
||||
answer(fmt.Sprintf("%s at %s: %d resource(s) failed — `status` says which", a.Outcome,
|
||||
a.At.Local().Format(stamp), a.Failed))
|
||||
}
|
||||
return lines
|
||||
}
|
||||
|
||||
// sendAnswerWord is what a machine answered of a send, in a word or few, as status says it in one line.
|
||||
func sendAnswerWord(s inventory.Send) string {
|
||||
switch a := s.Answer; {
|
||||
case s.RefusedAt != nil:
|
||||
return fmt.Sprintf("refused: it had applied generation %d", s.RefusedApplied)
|
||||
case a.Outcome == "" || a.At == nil:
|
||||
return "not reported on yet"
|
||||
case a.Outcome == inventory.OutcomeFailed:
|
||||
return fmt.Sprintf("failed (%d resource(s))", a.Failed)
|
||||
default:
|
||||
return a.Outcome
|
||||
}
|
||||
}
|
||||
|
||||
// printLastSends says, one line per machine, when it was last sent a declaration, by whom, from which assignment
|
||||
// generation and what it answered (novox/hq issue 485). `node show <node>` says the send in full.
|
||||
func printLastSends(nodes []inventory.Node, sends map[string]inventory.Send, unread string) {
|
||||
if unread != "" {
|
||||
fmt.Printf("what each machine was last sent could NOT be read: %s\n\n", unread)
|
||||
return
|
||||
}
|
||||
if len(nodes) == 0 {
|
||||
return
|
||||
}
|
||||
fmt.Println("last sent, per machine:")
|
||||
for _, n := range nodes {
|
||||
s, found := sends[n.Name]
|
||||
if !found {
|
||||
fmt.Printf(" %-12s no send recorded\n", n.Name)
|
||||
continue
|
||||
}
|
||||
generation := "no generation"
|
||||
if s.Generation > 0 {
|
||||
generation = fmt.Sprintf("generation %d", s.Generation)
|
||||
}
|
||||
fmt.Printf(" %-12s %s by %s, %s — %s\n", n.Name, s.SentAt.Local().Format("2006-01-02 15:04"), s.Sender,
|
||||
generation, sendAnswerWord(s))
|
||||
}
|
||||
fmt.Printf("\n `node show <node>` says a machine's last send in full\n\n")
|
||||
}
|
||||
@@ -0,0 +1,148 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
"github.com/novox/mesh-controller/internal/link"
|
||||
)
|
||||
|
||||
// The assignment generation a declaration was composed from (novox/hq issue 234).
|
||||
|
||||
func bodyKeys(t *testing.T, s sendable) map[string]any {
|
||||
t.Helper()
|
||||
raw, err := s.Body()
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
var keys map[string]any
|
||||
if err := json.Unmarshal(raw, &keys); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
return keys
|
||||
}
|
||||
|
||||
// **The generation goes on the wire only to a machine whose node-engine said it reads one**: an older
|
||||
// node-engine decodes strictly and refuses an unknown key, whole. No put-back mark is ever sent: a gate
|
||||
// composes its put-back afresh, with the generation as it stands.
|
||||
func TestTheGenerationIsSentOnlyToAMachineThatReadsOne(t *testing.T) {
|
||||
resources := []map[string]any{{"id": "a", "type": "file", "path": "/etc/a", "content": "x\n"}}
|
||||
reads := order{sequence: 12, epoch: 57, generation: 40, readsGeneration: true, acting: 57}
|
||||
var told sendable
|
||||
told.Resources = resources
|
||||
reads.stamp(&told)
|
||||
keys := bodyKeys(t, told)
|
||||
if keys["generation"] != float64(40) || keys["sequence"] != float64(12) {
|
||||
t.Fatalf("a machine that reads a generation was sent %v", keys)
|
||||
}
|
||||
if _, there := keys["put_back"]; there {
|
||||
t.Fatalf("a put-back mark was sent: %v", keys)
|
||||
}
|
||||
if told.composedFrom != 40 || told.actingEpoch != 57 {
|
||||
t.Errorf("the send does not keep what it was composed from for its record: %+v", told)
|
||||
}
|
||||
|
||||
older := order{sequence: 12, epoch: 57, generation: 40, readsGeneration: false, acting: 57}
|
||||
var untold sendable
|
||||
untold.Resources = resources
|
||||
older.stamp(&untold)
|
||||
if _, there := bodyKeys(t, untold)["generation"]; there {
|
||||
t.Fatal("a machine whose node-engine never said it reads a generation was sent one")
|
||||
}
|
||||
if untold.composedFrom != 40 {
|
||||
t.Errorf("the generation it was composed from is recorded whether or not it was sent: %+v", untold)
|
||||
}
|
||||
}
|
||||
|
||||
// **The sender is named**: the caller of the seat call when there is one, else the shell's account, and the
|
||||
// process and build that composed it.
|
||||
func TestASendNamesItsSender(t *testing.T) {
|
||||
said := senderOf("g14.node-tools, through the mesh-controller seat")
|
||||
if !strings.Contains(said, "g14.node-tools") || !strings.Contains(said, "pid ") || !strings.Contains(said, "build ") {
|
||||
t.Fatalf("the sender reads %q", said)
|
||||
}
|
||||
}
|
||||
|
||||
// refusedSend is a send a machine refused for its generation at a moment.
|
||||
func refusedSend(at time.Time) inventory.Send {
|
||||
return inventory.Send{NodeName: "anchor", Sequence: 12, Epoch: 57, Generation: 38, RefusedApplied: 40,
|
||||
Sender: "a one-shot push by jochen at a shell on anchor (pid 4242 on anchor, build 2026.10.11)",
|
||||
Modules: []string{"docker"}, SentAt: at.Add(-time.Second), RefusedAt: &at, Recorded: true}
|
||||
}
|
||||
|
||||
// **A refused send is raised naming its sender** (novox/hq issue 234): who sent it, from which generation,
|
||||
// against which the machine applied, and its sequence — the facts that took a morning to look for.
|
||||
func TestARefusedSendIsRaisedNamingItsSender(t *testing.T) {
|
||||
now := time.Date(2026, 10, 11, 12, 0, 0, 0, time.UTC)
|
||||
f := calm(now)
|
||||
f.refusedSends = []inventory.Send{refusedSend(now.Add(-time.Minute))}
|
||||
got := watchGenerationRefusals(f)
|
||||
if len(got) != 1 {
|
||||
t.Fatalf("%+v", got)
|
||||
}
|
||||
o := got[0]
|
||||
if o.Key() != "machine.anchor.older-generation" || o.Machine != "anchor" {
|
||||
t.Errorf("raised as %s about %q", o.Key(), o.Machine)
|
||||
}
|
||||
for _, want := range []string{"a one-shot push by jochen", "generation 38", "generation 40", "sequence 12"} {
|
||||
if !strings.Contains(o.Summary, want) {
|
||||
t.Errorf("the summary does not say %q: %s", want, o.Summary)
|
||||
}
|
||||
}
|
||||
if o.Headline == "" || o.Explanation == "" || o.Resolved == "" {
|
||||
t.Errorf("the condition is not worded for the operator: %+v", o)
|
||||
}
|
||||
}
|
||||
|
||||
// **A refusal of a send the mesh has no record of is raised too, its sender said to be unknown** — never
|
||||
// only a line on stderr.
|
||||
func TestARefusalOfAnUnrecordedSendIsRaisedSayingTheSenderIsUnknown(t *testing.T) {
|
||||
now := time.Date(2026, 10, 11, 12, 0, 0, 0, time.UTC)
|
||||
f := calm(now)
|
||||
s := refusedSend(now.Add(-time.Minute))
|
||||
s.Recorded, s.Sender, s.Modules = false, "a sender the mesh has no record of (no send of this sequence was recorded)", nil
|
||||
f.refusedSends = []inventory.Send{s}
|
||||
got := watchGenerationRefusals(f)
|
||||
if len(got) != 1 || !strings.Contains(got[0].Summary, "no record of") {
|
||||
t.Fatalf("an unattributed refusal was not raised as one: %+v", got)
|
||||
}
|
||||
}
|
||||
|
||||
// **When the refusal showed the mesh's counter behind the machine, the condition asks for a push** — it was
|
||||
// raised, and nothing has sent the machine its declaration since — and does not say there is nothing to do.
|
||||
func TestACounterBehindTheMachineAsksForAPush(t *testing.T) {
|
||||
now := time.Date(2026, 10, 11, 12, 0, 0, 0, time.UTC)
|
||||
f := calm(now)
|
||||
s := refusedSend(now.Add(-time.Minute))
|
||||
s.Generation, s.RefusedApplied, s.CounterRaisedTo = 12, 40, 41
|
||||
f.refusedSends = []inventory.Send{s}
|
||||
got := watchGenerationRefusals(f)
|
||||
if len(got) != 1 {
|
||||
t.Fatalf("%+v", got)
|
||||
}
|
||||
if !strings.Contains(got[0].Summary, "`push anchor`") || !strings.Contains(got[0].Explanation, "push anchor") ||
|
||||
strings.Contains(got[0].Explanation, "Nothing for you to do") {
|
||||
t.Errorf("a counter behind the machine does not ask for a push: %s / %s", got[0].Summary, got[0].Explanation)
|
||||
}
|
||||
}
|
||||
|
||||
// **Only a refusal of the counter as it stands is the counter behind**: a stale sender's generation is below
|
||||
// it, and the counter is left alone for that.
|
||||
func TestOnlyARefusalOfTheCounterAsItStandsRaisesIt(t *testing.T) {
|
||||
for _, c := range []struct {
|
||||
refused, applied, now int64
|
||||
behind bool
|
||||
}{
|
||||
{refused: 12, applied: 40, now: 12, behind: true}, // the store was put back: the mesh says 12, the machine had 40
|
||||
{refused: 38, applied: 40, now: 41, behind: false}, // a stale sender: the counter is already past
|
||||
{refused: 38, applied: 40, now: 40, behind: false}, // a stale sender: the counter is where the machine is
|
||||
} {
|
||||
r := link.GenerationRefusal{Generation: c.refused, Applied: c.applied}
|
||||
if got := counterBehind(r, c.now); got != c.behind {
|
||||
t.Errorf("refused %d, applied %d, counter %d: behind %v, want %v", c.refused, c.applied, c.now, got, c.behind)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,198 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/catalogue"
|
||||
"github.com/novox/mesh-controller/internal/identity"
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
"github.com/novox/mesh-controller/internal/link"
|
||||
)
|
||||
|
||||
// The grants step on a store (novox/hq issue 490): the machine holding the bus is sent its new user list,
|
||||
// and nothing else — not the new build of a module it runs, not a module newly assigned there.
|
||||
//
|
||||
// The restic shape: anchor holds the bus and runs restic at c1, as does laptop; restic's c2 gives it a
|
||||
// health tool. The grants step's send to anchor composes restic at c1, carries the user list that grants
|
||||
// laptop's node-engine c2's tool, and records that anchor still runs c1. A module newly assigned to anchor
|
||||
// makes the step fail, said, rather than install it unjudged.
|
||||
func TestTheGrantsStepSendsTheUserListAndNothingElse(t *testing.T) {
|
||||
open := aMesh(t)
|
||||
ctx := t.Context()
|
||||
inv := open.inventory
|
||||
start := time.Now().Add(-time.Hour)
|
||||
build := func(module, commit string, at time.Time, manifest map[string]any) link.BuildResult {
|
||||
manifest["module"], manifest["version"] = module, "1"
|
||||
raw, _ := json.Marshal(manifest)
|
||||
return link.BuildResult{ID: link.NewBuildID(at), Repository: "novox/mesh-catalog", Path: "modules/" + module,
|
||||
On: "anchor", Module: module, Commit: commit, Manifest: raw,
|
||||
Source: &link.SourceOnSeat{Seat: "git", Repository: "novox/mesh-catalog"}}
|
||||
}
|
||||
for _, b := range []link.BuildResult{
|
||||
build("nats", "n1", start, natsFixture()),
|
||||
build("restic", "c1", start.Add(time.Second), resticFixture(false)),
|
||||
build("wallpaper", "w1", start.Add(2*time.Second), wallpaperFixture()),
|
||||
} {
|
||||
if _, _, err := takeIn(ctx, inv, asTheOperator(t, inv, b)); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
}
|
||||
for _, a := range [][2]string{{"anchor", "nats"}, {"anchor", "restic"}, {"laptop", "restic"}} {
|
||||
if _, err := inv.Assign(ctx, a[0], a[1]); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
}
|
||||
for _, n := range []string{"anchor", "laptop"} {
|
||||
if _, err := inv.MintBusPassword(ctx, inventory.BusUser{Username: "node." + n, Kind: inventory.BusNode, Node: n}); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
}
|
||||
|
||||
wasEpoch := epochForActs
|
||||
epochForActs = func(context.Context) (uint64, error) { return 7, nil }
|
||||
t.Cleanup(func() { epochForActs = wasEpoch })
|
||||
|
||||
// A send to anchor composed as sendToEach composes it: numbered, planned, declared, stamped.
|
||||
compose := func(under context.Context) (catalogue.Resolution, sendable) {
|
||||
t.Helper()
|
||||
numbered, err := allot(under, inv, "anchor")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
plan, settings, err := planFor(under, open, "anchor")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
gens, err := generators(under, open)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
declared, err := declarationWith(under, open, "anchor", plan, settings, gens, Allocating)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
numbered.stamp(&declared)
|
||||
return plan, declared
|
||||
}
|
||||
record := func(declared sendable) {
|
||||
t.Helper()
|
||||
body, err := declared.Body()
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if _, err := recordSent(ctx, inv, "anchor", body, declared.Builds, declared.Epoch,
|
||||
sentRecordOf(ctx, declared)); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
}
|
||||
// Kept for anchor alone. laptop is never recorded as sent, on purpose: composing anchor resolves laptop
|
||||
// too (who is on the private network), and a step that kept every machine's builds refused anchor's
|
||||
// composition for want of laptop's last send (repo-check of #230 at 0f853e93).
|
||||
kept := keepingEveryBuild(keepingRecorded(ctx), "anchor")
|
||||
|
||||
// What anchor was last sent: everything at the builds of before the merge, as an ordinary send sends it.
|
||||
_, before := compose(keepingRecorded(ctx))
|
||||
record(before)
|
||||
plan, declared := compose(kept)
|
||||
if only, err := grantsOnlyIn(ctx, open, "anchor", plan, declared); err != nil || only != "" {
|
||||
t.Fatalf("with nothing changed, the step reads %q, %v", only, err)
|
||||
}
|
||||
|
||||
// The merge: restic's c2 gives it a health tool.
|
||||
if _, _, err := takeIn(ctx, inv, build("restic", "c2", start.Add(time.Minute),
|
||||
resticFixture(true))); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
// The step's send to anchor: restic as anchor runs it, c1, and the user list granting c2's tool.
|
||||
generation, err := inv.AssignmentGeneration(ctx)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
plan, declared = compose(kept)
|
||||
for _, m := range plan.Modules {
|
||||
if m.Module == "restic" && len(m.Tools) > 0 {
|
||||
t.Fatalf("the grants step composed restic's new build on anchor: tools %v", m.Tools)
|
||||
}
|
||||
}
|
||||
if declared.Builds["restic"] != "c1" {
|
||||
t.Fatalf("the step's send records it carries restic %q; want c1, which anchor runs", declared.Builds["restic"])
|
||||
}
|
||||
if !strings.Contains(declared.BusUsers, "mesh.mod.restic.tool.backup_health.laptop") {
|
||||
t.Errorf("the step's declaration does not grant laptop's node-engine restic's new tool:\n%s", declared.BusUsers)
|
||||
}
|
||||
// The generation it carries is the current one (novox/hq issue 234), and the step does not raise it.
|
||||
if declared.composedFrom != generation {
|
||||
t.Errorf("the step's send was composed from generation %d; the mesh is at %d", declared.composedFrom, generation)
|
||||
}
|
||||
// The guard, on the very declaration the send sends: only the user list differs from the last send.
|
||||
if only, err := grantsOnlyIn(ctx, open, "anchor", plan, declared); err != nil || only != "" {
|
||||
t.Fatalf("the step reads as changing more than the user list: %q, %v", only, err)
|
||||
}
|
||||
// And the gate's refusal still reads the step's send: it moves nothing there.
|
||||
if names, err := ungatedIn(kept, open, []string{"anchor"}, ""); err != nil || strings.Join(names, ",") != "anchor" {
|
||||
t.Fatalf("the step's send is refused as a move: %v, %v", names, err)
|
||||
}
|
||||
// Recorded as the send records it: anchor still runs restic c1, its gate still to come there.
|
||||
record(declared)
|
||||
if sent, _, err := inv.SentBuilds(ctx, "anchor"); err != nil || sent["restic"] != "c1" {
|
||||
t.Fatalf("after the step anchor reads as sent restic %q (%v); want c1", sent["restic"], err)
|
||||
}
|
||||
if after, err := inv.AssignmentGeneration(ctx); err != nil || after != generation {
|
||||
t.Fatalf("the step moved the assignment generation from %d to %d (%v)", generation, after, err)
|
||||
}
|
||||
|
||||
// A module newly assigned to anchor: the step would install it, unjudged, so it is refused unsent.
|
||||
if _, err := inv.Assign(ctx, "anchor", "wallpaper"); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
plan, declared = compose(kept)
|
||||
only, err := grantsOnlyIn(ctx, open, "anchor", plan, declared)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if !strings.Contains(only, "wallpaper newly assigned") || !strings.Contains(only, "+wallpaper") {
|
||||
t.Fatalf("a new assignment on the bus's machine reads %q; want the step refused, naming it", only)
|
||||
}
|
||||
// And the send itself refuses it, unsent: judged where it is composed, before the bus is dialled.
|
||||
identity.ForTest(t)
|
||||
if _, err := sendToEach(kept, open, []string{"anchor"}); !errors.Is(err, errNotGrantsOnly) ||
|
||||
!strings.Contains(err.Error(), "wallpaper") {
|
||||
t.Fatalf("the grants step's send of a new assignment was not refused by the send: %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
// fixtureImage is the image every fixture container of the grants step's tests runs.
|
||||
var fixtureImage = "registry.invalid:5000/restic/backup@sha256:" + strings.Repeat("b", 64)
|
||||
|
||||
// resticFixture is restic's manifest in the shape of mesh-catalog #210: at c2 (withTool) its backup judged by
|
||||
// its new tool `backup_health`, beside a check of another kind it does not run itself — a tool check alone
|
||||
// is refused (ADR 0227 rule 8, ADR 0240 rule 2) — and at c1 neither.
|
||||
func resticFixture(withTool bool) map[string]any {
|
||||
backup := map[string]any{"id": "backup", "type": "container", "name": "restic-backup", "image": fixtureImage}
|
||||
measure := map[string]any{"id": "measure", "type": "container", "name": "restic-measure", "image": fixtureImage}
|
||||
m := map[string]any{"resources": []any{backup, measure}}
|
||||
if withTool {
|
||||
backup["health"] = map[string]any{"kind": catalogue.HealthTool, "tool": "backup_health"}
|
||||
measure["health"] = map[string]any{"kind": "runtime"}
|
||||
m["tools"] = []string{"backup_health"}
|
||||
}
|
||||
return m
|
||||
}
|
||||
|
||||
// natsFixture is the bus's module: it holds mesh-broker and is sent the user list.
|
||||
func natsFixture() map[string]any {
|
||||
return map[string]any{"bus-users": "/var/lib/nats-module/conf/accounts.conf",
|
||||
"claims": []any{map[string]any{"name": catalogue.BrokerSeat, "scope": catalogue.ScopeMesh}}}
|
||||
}
|
||||
|
||||
// wallpaperFixture is a module the bus's machine is newly assigned.
|
||||
func wallpaperFixture() map[string]any {
|
||||
return map[string]any{"resources": []any{
|
||||
map[string]any{"id": "paper", "type": "container", "name": "wallpaper", "image": fixtureImage}}}
|
||||
}
|
||||
@@ -0,0 +1,226 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"fmt"
|
||||
"slices"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/catalogue"
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
"github.com/novox/mesh-controller/internal/link"
|
||||
)
|
||||
|
||||
// The grants reach the bus before the gate (novox/hq issue 490).
|
||||
//
|
||||
// On 2026-10-11 a merge gave restic, assigned to every machine, a new health tool. Its walk sent restic to
|
||||
// its first machine and judged it there; that machine's node-engine asked the new tool and the bus refused
|
||||
// it, because the grant was in the bus's user list, which only the machine holding the bus carries — and
|
||||
// that machine runs restic too, so it was left out of the send while restic's new build waited there for
|
||||
// the very gate that could not pass. A person pushed it by hand, carrying restic's new build there unjudged.
|
||||
|
||||
// aSend is one send the walk made: to which machines, and whether every build there was kept.
|
||||
type aSend struct {
|
||||
names []string
|
||||
keepsAll bool
|
||||
judged []string
|
||||
}
|
||||
|
||||
// sendsRecorded replaces the walk's send and the reading of the bus's user list for one test: the machine
|
||||
// holding the bus is novox, and its list is behind as behind says.
|
||||
func sendsRecorded(t *testing.T, holder string, behind bool, refuse error) *[]aSend {
|
||||
t.Helper()
|
||||
var sends []aSend
|
||||
wasSend, wasBehind := sendRollout, brokerBehindOf
|
||||
t.Cleanup(func() { sendRollout, brokerBehindOf = wasSend, wasBehind })
|
||||
brokerBehindOf = func(_ context.Context, _ *stores, names []string) (string, bool, error) {
|
||||
if slices.Contains(names, holder) {
|
||||
return holder, false, nil
|
||||
}
|
||||
return holder, behind, nil
|
||||
}
|
||||
sendRollout = func(ctx context.Context, _ *stores, names []string) ([]string, error) {
|
||||
s := aSend{names: append([]string(nil), names...), keepsAll: len(names) == 1 && everyBuildKept(ctx, names[0])}
|
||||
for n := range scopeOf(ctx).judged {
|
||||
s.judged = append(s.judged, n)
|
||||
}
|
||||
sends = append(sends, s)
|
||||
if refuse != nil && s.keepsAll {
|
||||
return nil, refuse
|
||||
}
|
||||
return names, nil
|
||||
}
|
||||
return &sends
|
||||
}
|
||||
|
||||
// The restic shape: a new tool on a module on every machine, its first machine ace, the bus on novox.
|
||||
func TestAWalkSendsTheGrantsToTheBusBeforeTheFirstMachineIsJudged(t *testing.T) {
|
||||
sends := sendsRecorded(t, "novox", true, nil)
|
||||
sent, grants, err := sendJudged(t.Context(), nil, "ace")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if len(*sends) != 2 {
|
||||
t.Fatalf("the walk made %d send(s), want the grants step and then the first machine: %+v", len(*sends), *sends)
|
||||
}
|
||||
first, then := (*sends)[0], (*sends)[1]
|
||||
if strings.Join(first.names, ",") != "novox" || !first.keepsAll || len(first.judged) != 0 {
|
||||
t.Errorf("the first send is %+v, want novox alone, every build there kept, judging nothing", first)
|
||||
}
|
||||
if strings.Join(then.names, ",") != "ace" || then.keepsAll || strings.Join(then.judged, ",") != "ace" {
|
||||
t.Errorf("the second send is %+v, want ace, judged", then)
|
||||
}
|
||||
if strings.Join(sent, ",") != "ace" {
|
||||
t.Errorf("the gate's machines are %v, want ace alone: the bus's machine is not judged", sent)
|
||||
}
|
||||
if grants == nil || grants.Node != "novox" || grants.At == nil || grants.Failed != "" {
|
||||
t.Fatalf("the gate keeps %+v as its grants step", grants)
|
||||
}
|
||||
line := gateLine(&inventory.PlanGate{Machines: sent, Grants: grants})
|
||||
if !strings.Contains(line, "grants step: novox sent the bus's user list first, its builds kept") {
|
||||
t.Errorf("plans says the gate as %q", line)
|
||||
}
|
||||
}
|
||||
|
||||
// Nothing more when there is nothing to carry: the list unchanged, or the first machine holds the bus.
|
||||
func TestAWalkTakesNoGrantsStepWhenTheListIsAlreadyThere(t *testing.T) {
|
||||
for _, c := range []struct {
|
||||
name string
|
||||
node string
|
||||
behind bool
|
||||
}{{"the list unchanged", "ace", false}, {"the first machine holds the bus", "novox", true}} {
|
||||
t.Run(c.name, func(t *testing.T) {
|
||||
sends := sendsRecorded(t, "novox", c.behind, nil)
|
||||
_, grants, err := sendJudged(t.Context(), nil, c.node)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if len(*sends) != 1 || (*sends)[0].keepsAll || grants != nil {
|
||||
t.Errorf("the walk made %+v with grants %+v, want the judged send alone", *sends, grants)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// A grants step that cannot be sent is said on the gate, and the walk goes on as it did before.
|
||||
func TestAGrantsStepThatFailsIsSaidAndTheSendGoesOn(t *testing.T) {
|
||||
sends := sendsRecorded(t, "novox", true, errors.New("a bus upgrade waits for a person"))
|
||||
sent, grants, err := sendJudged(t.Context(), nil, "ace")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if strings.Join(sent, ",") != "ace" || len(*sends) != 2 {
|
||||
t.Errorf("the walk made %+v", *sends)
|
||||
}
|
||||
if grants == nil || grants.Failed == "" || grants.At != nil {
|
||||
t.Fatalf("the gate keeps %+v", grants)
|
||||
}
|
||||
if line := gateLine(&inventory.PlanGate{Machines: sent, Grants: grants}); !strings.Contains(line,
|
||||
"grants step to novox FAILED, sent without it: a bus upgrade waits for a person") {
|
||||
t.Errorf("plans says the gate as %q", line)
|
||||
}
|
||||
}
|
||||
|
||||
// A step whose send would change more than the user list is refused unsent by the send (sendToEach): the
|
||||
// gate says it FAILED with what differed, and the walk goes on.
|
||||
func TestAGrantsStepThatWouldCarryMoreIsNotSent(t *testing.T) {
|
||||
refusal := fmt.Errorf("%w: its send would change more than the bus's user list: -postgres.login-n8n", errNotGrantsOnly)
|
||||
sends := sendsRecorded(t, "novox", true, refusal)
|
||||
sent, grants, err := sendJudged(t.Context(), nil, "ace")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if strings.Join(sent, ",") != "ace" || len(*sends) != 2 {
|
||||
t.Errorf("the walk made %+v, want the refused step and then ace's judged send", *sends)
|
||||
}
|
||||
if grants == nil || grants.At != nil || !strings.Contains(grants.Failed, "-postgres.login-n8n") {
|
||||
t.Fatalf("the gate keeps %+v", grants)
|
||||
}
|
||||
}
|
||||
|
||||
// The step's exemption is the list's content alone: its path or mode moving is a change like any other.
|
||||
func TestOnlyTheUserListsContentIsExempt(t *testing.T) {
|
||||
list := "nats.bus-users"
|
||||
file := func(fields map[string]any) sentResource {
|
||||
r := map[string]any{"id": list, "type": "file", "path": "/conf/accounts.conf", "mode": "0600", "content": "a"}
|
||||
for k, v := range fields {
|
||||
r[k] = v
|
||||
}
|
||||
body, _ := json.Marshal(map[string]any{"resources": []any{r}})
|
||||
s, err := summarize(body)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
return s[0]
|
||||
}
|
||||
was := file(nil)
|
||||
if other := otherThanTheList(diffSent([]sentResource{was}, []sentResource{file(map[string]any{"content": "b"})}), list); len(other) != 0 {
|
||||
t.Errorf("the list's new content reads as more: %v", other)
|
||||
}
|
||||
for _, f := range []map[string]any{{"mode": "0644"}, {"path": "/elsewhere"}, {"content": "b", "owner": "nats"}} {
|
||||
other := otherThanTheList(diffSent([]sentResource{was}, []sentResource{file(f)}), list)
|
||||
if len(other) != 1 || !strings.HasPrefix(other[0], "~"+list) {
|
||||
t.Errorf("the list's resource changed by %v reads %v; want it refused", f, other)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// The step keeps the builds of the machine it sends alone: the others its composition resolves are composed
|
||||
// as any send composes them.
|
||||
func TestTheGrantsStepKeepsOneMachinesBuilds(t *testing.T) {
|
||||
ctx := keepingEveryBuild(t.Context(), "novox")
|
||||
if !everyBuildKept(ctx, "novox") || everyBuildKept(ctx, "ace") || everyBuildKept(t.Context(), "novox") {
|
||||
t.Error("the grants step keeps the builds of a machine it does not send")
|
||||
}
|
||||
}
|
||||
|
||||
// The store test's manifests are manifests the controller takes in: checked here, where no store is needed,
|
||||
// so a fixture the module rules refuse fails before the store test is run (repo-check of #230 at 325575b2).
|
||||
func TestTheGrantsStepFixturesAreManifests(t *testing.T) {
|
||||
for name, m := range map[string]map[string]any{"nats": natsFixture(), "restic-c1": resticFixture(false),
|
||||
"restic-c2": resticFixture(true), "wallpaper": wallpaperFixture()} {
|
||||
m["module"], m["version"] = strings.SplitN(name, "-", 2)[0], "1"
|
||||
raw, err := json.Marshal(m)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if _, err := catalogue.ParseManifest(raw); err != nil {
|
||||
t.Errorf("%s: %v", name, err)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// The delivery plan says the step before the merge.
|
||||
func TestAChangePlanSaysTheGrantsStep(t *testing.T) {
|
||||
const catalogue_ = "http://forge.internal:20000/novox/mesh-catalog.git"
|
||||
entry := func(name string, on ...string) inventory.Entry {
|
||||
e := fromRepo(name, catalogue_, "modules/"+name)
|
||||
e.Source.BuiltFrom = "old"
|
||||
e.On = on
|
||||
return e
|
||||
}
|
||||
nats := entry("nats", "novox")
|
||||
nats.Manifest.BusUsers = "/etc/nats/users.conf"
|
||||
nats.Manifest.Claims = []catalogue.Claim{{Name: catalogue.BrokerSeat, Scope: catalogue.ScopeMesh}}
|
||||
restic := entry("restic", "ace", "novox", "shanks")
|
||||
only := entry("bus-tools", "novox")
|
||||
entries := []inventory.Entry{nats, restic, only}
|
||||
rollsOut := func(string) (inventory.Upgrade, bool) { return inventory.Upgrade{RollOut: true}, true }
|
||||
plan := func(paths ...string) link.ChangePlan {
|
||||
m := link.SourceMoved{Owner: "novox", Repo: "mesh-catalog", Base: "main", Commit: "head", Paths: paths}
|
||||
return changePlanOf("novox/mesh-catalog", "main", "head", reachOfMerge(m, entries, nil, nil), entries, rollsOut)
|
||||
}
|
||||
|
||||
text := planText(plan("modules/restic/module.json"))
|
||||
if !strings.Contains(text, "grants step: if this changes what the bus's user list says (a new tool, subject or "+
|
||||
"user), novox is sent that list alone, every build there kept, before restic is judged on its first machine") {
|
||||
t.Errorf("the change plan does not say the grants step:\n%s", text)
|
||||
}
|
||||
// A module only on the bus's machine goes there with the list in its own send: no step of its own.
|
||||
if text := planText(plan("modules/bus-tools/module.json")); strings.Contains(text, "grants step") {
|
||||
t.Errorf("a module on the bus's machine alone reads:\n%s", text)
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,158 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"fmt"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/catalogue"
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
"github.com/novox/mesh-controller/internal/link"
|
||||
)
|
||||
|
||||
// **A delivery group still assembles** (novox/hq ADR 0306 decision 2): a merge whose delivery group has a member
|
||||
// not yet merged waits for the merge window, whether or not a batch is assembling, so the group's members walk in
|
||||
// one batch, in their order (ADR 0276 decision 5). Which groups exist and where each member stands is
|
||||
// mesh-delivery's record (ADR 0239): a group is the pull requests of two repositories or more sharing a head
|
||||
// branch name, which is its id. The controller asks it, through its `groups` verb, when a merge from a head is
|
||||
// heard; a member whose pull request is open (proposed, checked, ready or rejected) is still to merge. When
|
||||
// mesh-delivery does not answer within groupAskWithin, or answers something unreadable, the merge waits: the safe
|
||||
// error is to wait, and its batch says why.
|
||||
|
||||
// groupAskWithin is how long mesh-delivery is given to say a merge's group, while the merge is being heard.
|
||||
var groupAskWithin = 3 * time.Second
|
||||
|
||||
// openPullStates are the states of a delivery whose pull request is open and not merged (mesh-delivery's table):
|
||||
// a member in one of them is still to merge. Closed unmerged is stopped, final, and waits for nothing.
|
||||
var openPullStates = map[string]bool{"proposed": true, "checked": true, "ready": true, "rejected": true}
|
||||
|
||||
// groupMember is one member of a delivery group as mesh-delivery's `groups` says it: `<owner/repo>@<commit> (state)`.
|
||||
type groupMember struct {
|
||||
Repository, State string
|
||||
}
|
||||
|
||||
// deliveryGroupOf is what mesh-delivery says of the group a head names: its members, and whether the head names a
|
||||
// group at all; an error when it cannot be asked or did not answer. A seam a test replaces.
|
||||
var deliveryGroupOf = func(ctx context.Context, held bool, head string) ([]groupMember, bool, error) {
|
||||
if !held {
|
||||
return nil, false, fmt.Errorf("no holder of %s is on record to say it", catalogue.DeliverySeat)
|
||||
}
|
||||
serving := servingBus.Load()
|
||||
if serving == nil {
|
||||
return nil, false, errors.New("this controller is not on the bus")
|
||||
}
|
||||
asking, cancel := context.WithTimeout(ctx, groupAskWithin)
|
||||
defer cancel()
|
||||
raw, err := askDeliveryOwner(asking, serving.Conn(), "groups", map[string]any{})
|
||||
if err != nil {
|
||||
if errors.Is(err, link.ErrNothingServes) {
|
||||
return nil, false, fmt.Errorf("nothing serves %s.groups", catalogue.DeliverySeat)
|
||||
}
|
||||
return nil, false, err
|
||||
}
|
||||
var lines []struct {
|
||||
ID string `json:"id"`
|
||||
Members []string `json:"members"`
|
||||
}
|
||||
if err := json.Unmarshal(raw, &lines); err != nil {
|
||||
return nil, false, fmt.Errorf("%s.groups answered something unreadable: %w", catalogue.DeliverySeat, err)
|
||||
}
|
||||
for _, l := range lines {
|
||||
if l.ID != head {
|
||||
continue
|
||||
}
|
||||
var members []groupMember
|
||||
for _, s := range l.Members {
|
||||
members = append(members, memberOf(s))
|
||||
}
|
||||
return members, true, nil
|
||||
}
|
||||
return nil, false, nil
|
||||
}
|
||||
|
||||
// memberOf reads one member as `groups` says it: `novox/mesh-sdk@d41d255f28ad (held)`.
|
||||
func memberOf(s string) groupMember {
|
||||
id, state := strings.TrimSpace(s), ""
|
||||
if i := strings.LastIndex(id, " ("); i >= 0 && strings.HasSuffix(id, ")") {
|
||||
id, state = id[:i], id[i+2:len(id)-1]
|
||||
}
|
||||
repository, _, _ := strings.Cut(id, "@")
|
||||
return groupMember{Repository: repository, State: state}
|
||||
}
|
||||
|
||||
// groupWait says whether a merge heard now waits for the window for its delivery group, and why in words; nothing
|
||||
// when it names no head, its head names no group, or every other member is merged or closed. own is the merge's
|
||||
// kind (ownPath).
|
||||
//
|
||||
// A member of another repository whose merge this controller already keeps in a batch not yet cut of the same
|
||||
// kind is merged, whatever mesh-delivery says yet (it marks a member merged once its walk opened): the merge joins
|
||||
// that batch by their head. One kept in a batch of the other kind keeps the merge waiting, whatever mesh-delivery
|
||||
// says (review of #250): kinds never share a batch, so the merge's batch is a new one, and cut at once it would
|
||||
// walk before that member's batch is cut and break the group's order (ADR 0276 decision 5). Waiting, the two
|
||||
// batches are cut in the order their windows close, an own-path one first at one look, as cutBatchesHeld cuts
|
||||
// every pair of kinds.
|
||||
//
|
||||
// Asked before the plans are held: a slow answer holds up no walk.
|
||||
func groupWait(ctx context.Context, inv *inventory.Inventory, m link.SourceMoved, held, own bool) (string, error) {
|
||||
if m.Head == "" {
|
||||
return "", nil
|
||||
}
|
||||
same, other, err := keptFromHead(ctx, inv, m.Head, own)
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
if len(other) > 0 {
|
||||
return "group " + m.Head + " has a member waiting in a batch of the other kind: " + strings.Join(other, ", "), nil
|
||||
}
|
||||
members, isGroup, err := deliveryGroupOf(ctx, held, m.Head)
|
||||
if err != nil {
|
||||
return fmt.Sprintf("%s did not say whether group %s has a member still to merge (%v): it waits for the "+
|
||||
"window, the safe side", catalogue.DeliverySeat, m.Head, err), nil
|
||||
}
|
||||
if !isGroup {
|
||||
return "", nil
|
||||
}
|
||||
var open []string
|
||||
for _, g := range members {
|
||||
if strings.EqualFold(g.Repository, m.Owner+"/"+m.Repo) || same[strings.ToLower(g.Repository)] ||
|
||||
!openPullStates[g.State] {
|
||||
continue
|
||||
}
|
||||
open = append(open, g.Repository+" ("+g.State+")")
|
||||
}
|
||||
if len(open) == 0 {
|
||||
return "", nil
|
||||
}
|
||||
return "group " + m.Head + " has a member still to merge: " + strings.Join(open, ", "), nil
|
||||
}
|
||||
|
||||
// keptFromHead are the merges from a head that batches not yet cut hold: the repositories (lower case) of those in
|
||||
// a batch of the kind own says, and, in words, each of the other kind with its batch.
|
||||
func keptFromHead(ctx context.Context, inv *inventory.Inventory, head string, own bool) (map[string]bool, []string, error) {
|
||||
batches, err := inv.Batches(ctx)
|
||||
if err != nil {
|
||||
return nil, nil, err
|
||||
}
|
||||
same := map[string]bool{}
|
||||
var other []string
|
||||
for _, b := range batches {
|
||||
merges, err := inv.MergesOf(ctx, b.ID)
|
||||
if err != nil {
|
||||
return nil, nil, err
|
||||
}
|
||||
for _, k := range merges {
|
||||
if announcedOf(k).Head != head {
|
||||
continue
|
||||
}
|
||||
if b.OwnPath() == own {
|
||||
same[strings.ToLower(k.Repository)] = true
|
||||
} else {
|
||||
other = append(other, fmt.Sprintf("%s@%s in %s", k.Repository, short(k.Commit), b.ID))
|
||||
}
|
||||
}
|
||||
}
|
||||
return same, other, nil
|
||||
}
|
||||
@@ -84,6 +84,9 @@ var handActVerbs = []handActVerb{
|
||||
"deliberate test, never a repair", DecidedFor: []string{causeDrill}},
|
||||
// A drill: something broken on purpose to see the mesh raise and clear it. A person's test, never a
|
||||
// repair, however often it is run.
|
||||
// A credential a provider's software issued, taken from the provider and kept for its consumers (novox/hq ADR
|
||||
// 0305): the mesh working as decided, however often the software changes it.
|
||||
{Verb: handActIssued, Decision: "a credential the provider's software issued, kept for its consumers (ADR 0305)"},
|
||||
{Verb: "hand-act drill", Decision: "a drill is a person's deliberate test of the mesh, never a repair"},
|
||||
// A person's decisions by design.
|
||||
{Verb: "retire approve", Decision: "nothing is retired past its bound without a person (ADR 0230)"},
|
||||
|
||||
@@ -167,3 +167,54 @@ func TestASetuidSearchAsksOnlyAKnownNodeAndFailsOnARefusal(t *testing.T) {
|
||||
t.Fatalf("a start: %v, printed %q", err, out.String())
|
||||
}
|
||||
}
|
||||
|
||||
// The directory judgement's line asks only a known node, one name and nothing else, fails on a refusal, and says it
|
||||
// changed nothing (novox/hq issue 358).
|
||||
func TestADirectoryJudgementAsksOnlyAKnownNodeAndSaysItIsReadOnly(t *testing.T) {
|
||||
t.Setenv(link.CallerVar, "jo through mesh-cli on anchor")
|
||||
asked := 0
|
||||
ask := func(answer link.HandOverAnswer) func(node, by string) (link.HandOverAnswer, error) {
|
||||
return func(node, by string) (link.HandOverAnswer, error) {
|
||||
asked++
|
||||
if node != "novox" || by != "jo through mesh-cli on anchor" {
|
||||
t.Fatalf("asked %q %q", node, by)
|
||||
}
|
||||
return answer, nil
|
||||
}
|
||||
}
|
||||
known := func(string) error { return nil }
|
||||
var out bytes.Buffer
|
||||
for _, args := range [][]string{nil, {"novox", "extra"}, {"-x"}} {
|
||||
if err := judgeDirectoriesAsked(args, known, ask(link.HandOverAnswer{Said: "x"}), &out); err == nil || asked != 0 {
|
||||
t.Fatalf("%v was asked: %v", args, err)
|
||||
}
|
||||
}
|
||||
if err := judgeDirectoriesAsked([]string{"novox"}, func(string) error { return errors.New("no node called novox") },
|
||||
ask(link.HandOverAnswer{Said: "x"}), &out); err == nil || asked != 0 {
|
||||
t.Fatalf("an unknown node: %v", err)
|
||||
}
|
||||
if err := judgeDirectoriesAsked([]string{"novox"}, known, ask(link.HandOverAnswer{Refused: "no; nothing was judged"}),
|
||||
&out); err == nil || !strings.Contains(err.Error(), "novox refused") || out.Len() != 0 {
|
||||
t.Fatalf("a refusal: %v, printed %q", err, out.String())
|
||||
}
|
||||
said := "2 directories declared: 1 placed, 1 would be refused\n/var/lib/a: placed\n/var/lib/b: would be refused: …"
|
||||
if err := judgeDirectoriesAsked([]string{"novox"}, known, ask(link.HandOverAnswer{Said: said}), &out); err != nil ||
|
||||
out.String() != "novox (read-only: nothing on novox was changed)\n"+said+"\n" {
|
||||
t.Fatalf("a judgement: %v, printed %q", err, out.String())
|
||||
}
|
||||
}
|
||||
|
||||
// The judgement is a seat verb an agent may call — it reads, and changes nothing on the node — and runs exactly
|
||||
// `node judge-directories <node>` (novox/hq issue 358).
|
||||
func TestTheDirectoryJudgementIsAVerbThatOnlyReads(t *testing.T) {
|
||||
argv, err := argvFor("judge-directories", map[string]any{"node": "novox"})
|
||||
if err != nil || strings.Join(argv, " ") != "node judge-directories novox" {
|
||||
t.Fatalf("the verb runs %v, %v", argv, err)
|
||||
}
|
||||
if _, err := argvFor("judge-directories", map[string]any{}); err == nil {
|
||||
t.Fatal("the verb ran with no node")
|
||||
}
|
||||
if !readingVerbs["judge-directories"] {
|
||||
t.Fatal("the judgement is not counted a reading verb")
|
||||
}
|
||||
}
|
||||
|
||||
@@ -128,7 +128,7 @@ func (r *recordedDelivery) grant(context.Context, []readyNode) error { return ni
|
||||
|
||||
func (r *recordedDelivery) declare(ctx context.Context, s readyNode, body []byte) (string, error) {
|
||||
r.declared = append(r.declared, s.node)
|
||||
return recordSent(ctx, r.inv, s.node, body, s.declared.Builds, s.declared.Epoch)
|
||||
return recordSent(ctx, r.inv, s.node, body, s.declared.Builds, s.declared.Epoch, sentRecordOf(ctx, s.declared))
|
||||
}
|
||||
|
||||
// aResolver is a module built from a repository, at a commit, with something on the machine that
|
||||
|
||||
@@ -0,0 +1,259 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/catalogue"
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
"github.com/novox/mesh-controller/internal/lease"
|
||||
)
|
||||
|
||||
// novox/hq issue 201: on 2026-10-02 a plan sent the control node a controller older than the one running there,
|
||||
// whose seat row the newer one had already widened; the older binary refused the row and the mesh went quiet for
|
||||
// ten minutes. No send but a person's push and a gate's own put-back moves the controller or the node-engine back
|
||||
// behind the build its machine was last sent: the send keeps it there, and carries the rest.
|
||||
|
||||
// askedIn answers a build from a fixed table: module@commit → when it was asked; failed names those that failed
|
||||
// their gate.
|
||||
func askedIn(table map[string]time.Time, failed ...string) func(module, commit string) (askedBuild, bool, error) {
|
||||
return func(module, commit string) (askedBuild, bool, error) {
|
||||
at, known := table[module+"@"+commit]
|
||||
b := askedBuild{asked: at}
|
||||
for _, f := range failed {
|
||||
if f == module+"@"+commit {
|
||||
b.failedGate = true
|
||||
}
|
||||
}
|
||||
return b, known, nil
|
||||
}
|
||||
}
|
||||
|
||||
func TestACoreModuleIsKeptOverAnOlderRecord(t *testing.T) {
|
||||
old, now := t0, t0.Add(time.Minute)
|
||||
table := map[string]time.Time{
|
||||
"mesh-controller@c1": old, "mesh-controller@c2": now,
|
||||
"mesh-host@h1": old, "mesh-host@h2": now,
|
||||
"app@a1": old, "app@a2": now,
|
||||
}
|
||||
sent := map[string]string{"mesh-controller": "c2", "mesh-host": "h2", "app": "a2"}
|
||||
record := map[string]string{"mesh-controller": "c1", "mesh-host": "h1", "app": "a1"}
|
||||
found, err := coreDowngrades("anchor", sent, record, sendScope{judged: map[string]bool{"anchor": true}}, askedIn(table))
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if len(found) != 2 || found[0].module != "mesh-controller" || found[0].component != lease.ComponentController ||
|
||||
found[0].sent != "c2" || found[1].module != "mesh-host" || found[1].component != lease.ComponentEngine {
|
||||
t.Fatalf("the controller and the node-engine over an older record are kept, and nothing else: %+v", found)
|
||||
}
|
||||
if said := found[0].String(); !strings.Contains(said, "anchor was last sent mesh-controller c2") ||
|
||||
!strings.Contains(said, "`push anchor`") || !strings.Contains(said, "`rebuild mesh-controller`") {
|
||||
t.Fatalf("it says the machine, the build kept and the two ways out: %s", said)
|
||||
}
|
||||
|
||||
// The record forward, the same build, or a build the records do not hold: nothing kept.
|
||||
for _, c := range [][2]string{{"c1", "c2"}, {"c2", "c2"}, {"c2", "c9"}, {"c9", "c1"}} {
|
||||
found, err := coreDowngrades("anchor", map[string]string{"mesh-controller": c[0]},
|
||||
map[string]string{"mesh-controller": c[1]}, sendScope{}, askedIn(table))
|
||||
if err != nil || len(found) != 0 {
|
||||
t.Fatalf("sent %s, record %s: no downgrade proved, nothing kept: %+v %v", c[0], c[1], found, err)
|
||||
}
|
||||
}
|
||||
|
||||
// A sent build that failed its gate is never ahead: the record put back before it is sent.
|
||||
if found, _ := coreDowngrades("anchor", sent, record, sendScope{}, askedIn(table, "mesh-controller@c2")); len(found) != 1 ||
|
||||
found[0].module != "mesh-host" {
|
||||
t.Fatalf("a controller that failed its gate was kept over the build put back: %+v", found)
|
||||
}
|
||||
|
||||
// A gate's own put-back carries its own modules back, and nothing else.
|
||||
putBack := sendScope{modules: map[string]bool{"mesh-controller": true}, puttingBack: true}
|
||||
if found, _ := coreDowngrades("anchor", sent, record, putBack, askedIn(table)); len(found) != 1 || found[0].module != "mesh-host" {
|
||||
t.Fatalf("a put-back of the controller carries it back, and not the node-engine: %+v", found)
|
||||
}
|
||||
if found, _ := coreDowngrades("anchor", sent, record, sendScope{modules: map[string]bool{"mesh-controller": true}},
|
||||
askedIn(table)); len(found) != 2 {
|
||||
t.Fatalf("a send for the controller that is no put-back carries it back: %+v", found)
|
||||
}
|
||||
}
|
||||
|
||||
// core201 is a mesh whose control node, anchor, was sent the newer controller c2 while the mesh's record of the
|
||||
// controller is the build before it, c1, which passed its gate when it rolled out.
|
||||
func core201(t *testing.T) *stores {
|
||||
t.Helper()
|
||||
open := aMesh(t)
|
||||
ctx := t.Context()
|
||||
inv := open.inventory
|
||||
old, now := time.Now().Add(-2*time.Hour), time.Now().Add(-time.Minute)
|
||||
record := func(commit string, asked time.Time) inventory.Build {
|
||||
manifest, _ := json.Marshal(catalogue.Manifest{Module: "mesh-controller", Version: "1"})
|
||||
b := inventory.Build{ID: "build-mesh-controller-" + commit, Module: "mesh-controller", Commit: commit,
|
||||
Repository: "novox/mesh-controller", Manifest: manifest, Asked: asked, At: asked,
|
||||
Made: []inventory.Artifact{{Name: "x", Kind: "bundle", Reference: "sha256:" + commit + "0000000000000000"}}}
|
||||
if err := inv.RecordBuild(ctx, b); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
return b
|
||||
}
|
||||
before := record("c1aaaaaaaaaa", old)
|
||||
if err := inv.RecordGate(ctx, inventory.GateVerdict{Build: before.ID, Module: "mesh-controller", Commit: before.Commit,
|
||||
Machines: []string{"anchor"}, Verdict: inventory.GatePassed}); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
record("c2bbbbbbbbbb", now)
|
||||
if err := inv.RegisterModule(ctx, catalogue.Manifest{Module: "mesh-controller", Version: "1"}, inventory.Source{
|
||||
Repository: "novox/mesh-controller", BuiltFrom: "c2bbbbbbbbbb", Head: "c2bbbbbbbbbb", Asked: now}); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if _, err := inv.Assign(ctx, "anchor", "mesh-controller"); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := inv.RecordSent(ctx, nodeID(t, open, "anchor"), "d-anchor", map[string]string{"mesh-controller": "c2bbbbbbbbbb"}); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := inv.RestoreModule(ctx, before); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
wasMoves := machineMoves
|
||||
machineMoves = func(ctx context.Context, open *stores, f moveFacts, node string, all bool) ([]inventory.CarriedMove, error) {
|
||||
modules, err := open.inventory.Assigned(ctx, node)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
sent, known, err := open.inventory.SentBuilds(ctx, node)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return f.moves(node, modules, sent, known, all), nil
|
||||
}
|
||||
t.Cleanup(func() { machineMoves = wasMoves })
|
||||
return open
|
||||
}
|
||||
|
||||
// TestReplay201 replays the race on a store: the control node runs the newer controller and the mesh's record is
|
||||
// the build before it. A plan's send there — the node-engine's plan of 2026-10-02 — goes, keeps the newer
|
||||
// controller, and says so as a condition; the gate's own put-back carries it back; a send that carries the record,
|
||||
// as a person's push does, clears the condition.
|
||||
func TestReplay201(t *testing.T) {
|
||||
open := core201(t)
|
||||
ctx := t.Context()
|
||||
k, _ := withConditionsInMemory(t)
|
||||
|
||||
judged := withScope(ctx, sendScope{judged: map[string]bool{"anchor": true}})
|
||||
if kept, err := ungatedIn(judged, open, []string{"anchor"}, ""); err != nil || len(kept) != 1 {
|
||||
t.Fatalf("a plan's send to the machine is made, the rest of it with it: %v %v", kept, err)
|
||||
}
|
||||
keeps, err := recordedKept(keepingRecorded(judged), open, "anchor")
|
||||
if err != nil || keeps["mesh-controller"] != "c2bbbbbbbbbb" {
|
||||
t.Fatalf("the send keeps the newer controller there: %v %v", keeps, err)
|
||||
}
|
||||
shelf := map[string]catalogue.Manifest{"mesh-controller": {Module: "mesh-controller", Version: "old"}}
|
||||
if _, err := keepRecorded(keepingRecorded(judged), open, "anchor", shelf); err != nil || shelf["mesh-controller"].Version != "1" {
|
||||
t.Fatalf("the send composes the kept build's manifest: %+v %v", shelf, err)
|
||||
}
|
||||
key := coreDowngradeObservation(lease.ComponentController, "anchor", "").Key()
|
||||
if c, found, err := k.Get(ctx, key); err != nil || !found || !strings.Contains(c.Summary, "c2bbbbbb") {
|
||||
t.Fatalf("the condition %s is raised, saying the build kept: %+v %v %v", key, c, found, err)
|
||||
}
|
||||
|
||||
putBack := keepingRecorded(withScope(ctx, sendScope{modules: map[string]bool{"mesh-controller": true}, puttingBack: true}))
|
||||
if keeps, err := recordedKept(putBack, open, "anchor"); err != nil || len(keeps) != 0 {
|
||||
t.Fatalf("the gate's own put-back of the controller carries it back: %v %v", keeps, err)
|
||||
}
|
||||
|
||||
settleCoreDowngrades(ctx, open.inventory, "anchor", map[string]string{"mesh-controller": "c2bbbbbbbbbb"})
|
||||
if _, found, _ := k.Get(ctx, key); !found {
|
||||
t.Fatal("a send that kept the newer controller cleared the condition")
|
||||
}
|
||||
settleCoreDowngrades(ctx, open.inventory, "anchor", map[string]string{"mesh-controller": "c1aaaaaaaaaa"})
|
||||
if _, found, _ := k.Get(ctx, key); found {
|
||||
t.Fatal("a send carrying the mesh's record — a person's push — leaves the condition open")
|
||||
}
|
||||
}
|
||||
|
||||
// The review of #273: a gate failed the newer controller, put the record back, and the put-back's own send was
|
||||
// refused. The next automatic send — a healer's, which judges nothing — completes the put-back: a build that
|
||||
// failed its gate is never kept.
|
||||
func TestARollbackWhoseSendWasRefusedIsCompletedByTheNextSend(t *testing.T) {
|
||||
open := core201(t)
|
||||
ctx := t.Context()
|
||||
k, _ := withConditionsInMemory(t)
|
||||
if err := open.inventory.RecordGate(ctx, inventory.GateVerdict{Build: "build-mesh-controller-c2bbbbbbbbbb",
|
||||
Module: "mesh-controller", Commit: "c2bbbbbbbbbb", Previous: "c1aaaaaaaaaa", Machines: []string{"anchor"},
|
||||
Verdict: inventory.GateFailed, Rollback: inventory.NotRolledBack}); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
healer := withScope(ctx, sendScope{})
|
||||
if kept, err := ungatedIn(healer, open, []string{"anchor"}, ""); err != nil || len(kept) != 1 {
|
||||
t.Fatalf("the healer's send is made: %v %v", kept, err)
|
||||
}
|
||||
if keeps, err := recordedKept(keepingRecorded(healer), open, "anchor"); err != nil || len(keeps) != 0 {
|
||||
t.Fatalf("the failed controller was kept over the build put back: %v %v", keeps, err)
|
||||
}
|
||||
if open, _ := k.Open(ctx); len(open) != 0 {
|
||||
t.Fatalf("a completed put-back raised a condition: %+v", open)
|
||||
}
|
||||
}
|
||||
|
||||
// Review 91 of #273: a gated send to a machine whose controller is kept over an older record leaves the kept
|
||||
// controller out of what its gate judges. Judged as moving back to the record, the gate would read the send's own
|
||||
// kept controller as another build sent there after it (issue 352) and be superseded, judging nothing.
|
||||
func TestAGateJudgesTheOtherMovesBesideAKeptCore(t *testing.T) {
|
||||
open := core201(t)
|
||||
ctx := t.Context()
|
||||
withConditionsInMemory(t)
|
||||
inv := open.inventory
|
||||
old, now := time.Now().Add(-2*time.Hour), time.Now().Add(-time.Minute)
|
||||
for _, b := range []struct {
|
||||
commit string
|
||||
at time.Time
|
||||
}{{"a1aaaaaaaaaa", old}, {"a2bbbbbbbbbb", now}} {
|
||||
manifest, _ := json.Marshal(catalogue.Manifest{Module: "app", Version: "1"})
|
||||
if err := inv.RecordBuild(ctx, inventory.Build{ID: "build-app-" + b.commit, Module: "app", Commit: b.commit,
|
||||
Repository: "novox/mesh-catalog", Path: "modules/app", Manifest: manifest, Asked: b.at, At: b.at,
|
||||
Made: []inventory.Artifact{{Name: "x", Kind: "bundle", Reference: "sha256:app-" + b.commit}}}); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := inv.RegisterModule(ctx, catalogue.Manifest{Module: "app", Version: "1"}, inventory.Source{
|
||||
Repository: "novox/mesh-catalog", Seat: "git", Path: "modules/app", BuiltFrom: b.commit, Head: b.commit,
|
||||
Asked: b.at}); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
}
|
||||
if _, err := inv.Assign(ctx, "anchor", "app"); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := inv.RecordSent(ctx, nodeID(t, open, "anchor"), "d-anchor-2",
|
||||
map[string]string{"mesh-controller": "c2bbbbbbbbbb", "app": "a1aaaaaaaaaa"}); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
// The send as it is made: the controller kept at c2, the app moved to the record.
|
||||
wasSend := sendRollout
|
||||
sendRollout = func(ctx context.Context, open *stores, names []string) ([]string, error) {
|
||||
return names, open.inventory.RecordSent(ctx, nodeID(t, open, "anchor"), "d-anchor-3",
|
||||
map[string]string{"mesh-controller": "c2bbbbbbbbbb", "app": "a2bbbbbbbbbb"})
|
||||
}
|
||||
t.Cleanup(func() { sendRollout = wasSend })
|
||||
|
||||
moves, sent, _, err := gatedSend(ctx, open, "anchor", nil)
|
||||
if err != nil || len(sent) != 1 {
|
||||
t.Fatalf("the gated send is made: %v %v", sent, err)
|
||||
}
|
||||
if len(moves) != 1 || moves[0].Module != "app" || moves[0].To != "a2bbbbbbbbbb" {
|
||||
t.Fatalf("the gate judges the app's move and not the kept controller: %+v", moves)
|
||||
}
|
||||
builds, _, err := inv.SentBuilds(ctx, "anchor")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
g := &inventory.PlanGate{Carried: moves}
|
||||
f := gateFacts{commits: judgedCommits(g, nil), sentBuilds: map[string]map[string]string{"anchor": builds}}
|
||||
for _, m := range []string{"app", "mesh-controller"} {
|
||||
if why, superseded := f.supersededOn(m, "anchor"); superseded {
|
||||
t.Fatalf("the gate is superseded by its own send: %s", why)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -25,6 +25,7 @@ import (
|
||||
// another send reaches anchor, unreported; the gate still passes. And a send that moves a judged module
|
||||
// to another build supersedes the judging: no verdict, nothing put back.
|
||||
func TestReplay352(t *testing.T) {
|
||||
judgeLeavesAsTheCore(t)
|
||||
t.Run("a newer send to the judged machine does not unreport the gate's", testANewerSendDoesNotUnreportTheGatesOwn)
|
||||
t.Run("a send that moves the module supersedes the judging", testASendThatMovesTheModuleSupersedesTheJudging)
|
||||
}
|
||||
@@ -66,10 +67,11 @@ func testANewerSendDoesNotUnreportTheGatesOwn(t *testing.T) {
|
||||
|
||||
// A plan's own first send waits while a release judges the same module on that machine with another build.
|
||||
func TestAPlansFirstSendWaitsForAReleaseJudgingTheModuleThere(t *testing.T) {
|
||||
judgeLeavesAsTheCore(t)
|
||||
b := aBacklog(t)
|
||||
ctx := t.Context()
|
||||
advancePlans(ctx, b.open) // the release judges app c2 on anchor
|
||||
_, _, err := gatedSend(ctx, b.open, "anchor", []inventory.CarriedMove{{Module: "app", Node: "anchor", From: "c2", To: "c3", Build: "build-app-c3"}})
|
||||
_, _, _, err := gatedSend(ctx, b.open, "anchor", []inventory.CarriedMove{{Module: "app", Node: "anchor", From: "c2", To: "c3", Build: "build-app-c3"}})
|
||||
if !errors.Is(err, errWalkedElsewhere) || !strings.Contains(err.Error(), "release-") {
|
||||
t.Fatalf("a newer build of a judged module was sent under the release's gate: %v", err)
|
||||
}
|
||||
@@ -80,6 +82,7 @@ func TestAPlansFirstSendWaitsForAReleaseJudgingTheModuleThere(t *testing.T) {
|
||||
|
||||
// A merge plan's judging is superseded the same way: another send moved its module on the first machine.
|
||||
func TestAPlansJudgingIsSupersededByASendThatMovesItsModule(t *testing.T) {
|
||||
judgeLeavesAsTheCore(t)
|
||||
g := aGateMesh(t)
|
||||
ctx := t.Context()
|
||||
inv := g.open.inventory
|
||||
|
||||
@@ -0,0 +1,433 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"fmt"
|
||||
"reflect"
|
||||
"slices"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
)
|
||||
|
||||
// novox/hq issue 459, ADR 0299: since the merge window one walk carries every merge of its batch, so a stop of one
|
||||
// group member through `delivery-stop` ended the walk of every other delivery in it. The stop now names the merges
|
||||
// to leave out: the walk is ended, and every other merge it answered is walked again in a fresh batch without them
|
||||
// — the stopped merge, and each later merge of its repository's branch, which contains it and ends with it.
|
||||
|
||||
// endsItsLine ends, as the test ends, a line the controller's output left open (a walk's ask prints " tier N: " and
|
||||
// the asked build the rest, which the tests' fake ask never prints): `go test -v` would put the test's "--- PASS"
|
||||
// after it, and the store-tests step of merge-check.sh, which reads that marker at a line's start, would say the
|
||||
// test never ran.
|
||||
func endsItsLine(t *testing.T) {
|
||||
t.Cleanup(func() { fmt.Println() })
|
||||
}
|
||||
|
||||
// leaved is a kept merge of a repository, made at a moment.
|
||||
func leaved(repository, commit string, made time.Time) inventory.BatchedMerge {
|
||||
return inventory.BatchedMerge{Repository: repository, Branch: "main", Commit: commit, Merged: made, Heard: made}
|
||||
}
|
||||
|
||||
// The stopped merge is left out, and so is each later merge of its repository's branch, naming the merge it
|
||||
// contains; an earlier merge of that repository and every other repository's merge are walked again.
|
||||
func TestLeftOutAreTheStoppedMergeAndTheMergesThatContainIt(t *testing.T) {
|
||||
c1 := leaved("novox/mesh-catalog", "c1aaaaaaaaaa", t0)
|
||||
c2 := leaved("novox/mesh-catalog", "c2bbbbbbbbbb", t0.Add(10*time.Second))
|
||||
c3 := leaved("novox/mesh-catalog", "c3cccccccccc", t0.Add(20*time.Second))
|
||||
o1 := leaved("novox/one", "o1dddddddddd", t0.Add(5*time.Second))
|
||||
again, out, err := leaveOut([]inventory.BatchedMerge{c1, o1, c2, c3}, []string{"novox/Mesh-Catalog@c2bbbbbbbbbb"})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
var walked []string
|
||||
for _, m := range again {
|
||||
walked = append(walked, m.Commit)
|
||||
}
|
||||
if !reflect.DeepEqual(walked, []string{c1.Commit, o1.Commit}) {
|
||||
t.Fatalf("walked again: %v; want the earlier catalogue merge and the other repository's", walked)
|
||||
}
|
||||
want := []inventory.PlanLeftOut{{Repository: "novox/mesh-catalog", Commit: c2.Commit},
|
||||
{Repository: "novox/mesh-catalog", Commit: c3.Commit, Contains: c2.Commit}}
|
||||
if !reflect.DeepEqual(out, want) {
|
||||
t.Fatalf("left out: %+v; want %+v", out, want)
|
||||
}
|
||||
// A merge the walk does not answer is refused, naming it: nothing ends.
|
||||
if _, _, err := leaveOut([]inventory.BatchedMerge{c1, o1}, []string{"novox/mesh-catalog@ffffffffffff"}); err == nil ||
|
||||
!strings.Contains(err.Error(), "ffffffffffff") {
|
||||
t.Fatalf("a merge the walk does not answer was left out: %v", err)
|
||||
}
|
||||
if _, _, err := leaveOut([]inventory.BatchedMerge{c1}, []string{"no-commit"}); err == nil {
|
||||
t.Fatal("a merge without its commit was taken")
|
||||
}
|
||||
}
|
||||
|
||||
// moving is a kept merge that moved modules when it was heard.
|
||||
func moving(m inventory.BatchedMerge, modules ...string) inventory.BatchedMerge {
|
||||
m.Event, _ = json.Marshal(keptMerge{Moves: modules})
|
||||
return m
|
||||
}
|
||||
|
||||
// A merge of another repository that moves a module the stopped merge moves is left out too, naming the modules
|
||||
// it shares: the module is built at its branch, which holds the stopped merge (review of #232). And so on, until
|
||||
// none more is: a merge sharing a module with that one is left out as well.
|
||||
func TestAMergeSharingAStoppedMergesModuleIsLeftOut(t *testing.T) {
|
||||
stopped := moving(leaved("novox/mesh-catalog", "c1aaaaaaaaaa", t0), "app")
|
||||
reader := moving(leaved("novox/one", "o1bbbbbbbbbb", t0.Add(time.Second)), "app", "one")
|
||||
next := moving(leaved("novox/two", "t1cccccccccc", t0.Add(2*time.Second)), "one")
|
||||
free := moving(leaved("novox/three", "h1dddddddddd", t0.Add(3*time.Second)), "three")
|
||||
again, out, err := leaveOut([]inventory.BatchedMerge{stopped, reader, next, free}, []string{"novox/mesh-catalog@c1aaaaaaa"})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if len(again) != 1 || again[0].Commit != free.Commit {
|
||||
t.Fatalf("walked again: %+v; want the merge that shares nothing alone", again)
|
||||
}
|
||||
want := []inventory.PlanLeftOut{{Repository: "novox/mesh-catalog", Commit: stopped.Commit},
|
||||
{Repository: "novox/one", Commit: reader.Commit, Contains: stopped.Commit, Shares: []string{"app"}},
|
||||
{Repository: "novox/two", Commit: next.Commit, Contains: stopped.Commit, Shares: []string{"one"}}}
|
||||
if !reflect.DeepEqual(out, want) {
|
||||
t.Fatalf("left out %+v; want %+v", out, want)
|
||||
}
|
||||
}
|
||||
|
||||
// A walk withholds a module a stopped merge moved where it would build it only as a dependent; one a merge of its
|
||||
// own batch moves is built, and empty tiers go.
|
||||
func TestAWalkWithholdsAStoppedMergesDependents(t *testing.T) {
|
||||
plan := inventory.Plan{Tiers: [][]string{{"one"}, {"app"}, {"notes", "app2"}},
|
||||
Modules: map[string]*inventory.PlanModule{"one": {}, "app": {}, "notes": {}, "app2": {}}}
|
||||
got := withhold(&plan, []string{"app", "notes", "absent"}, []string{"notes"})
|
||||
if !reflect.DeepEqual(got, []string{"app"}) || !reflect.DeepEqual(plan.Tiers, [][]string{{"one"}, {"notes", "app2"}}) {
|
||||
t.Fatalf("withheld %v, tiers %v", got, plan.Tiers)
|
||||
}
|
||||
if _, in := plan.Modules["app"]; in {
|
||||
t.Fatal("a withheld module is still in the plan")
|
||||
}
|
||||
}
|
||||
|
||||
// The seat verb passes the merges to leave out to the command.
|
||||
func TestDeliveryStopTakesTheMergesToLeaveOut(t *testing.T) {
|
||||
got, err := argvFor("delivery-stop", map[string]any{"plan": "plan-1", "why": "w", "by": "jochen",
|
||||
"without": "novox/mesh-lab@b1,novox/mesh-lab@b2"})
|
||||
want := []string{"delivery", "stop", "plan-1", "--why", "w", "--by", "mesh-delivery for jochen",
|
||||
"--without", "novox/mesh-lab@b1,novox/mesh-lab@b2"}
|
||||
if err != nil || !reflect.DeepEqual(got, want) {
|
||||
t.Fatalf("delivery-stop with without → %v %v, wanted %v", got, err, want)
|
||||
}
|
||||
}
|
||||
|
||||
// A walk of the catalogue's merge and another repository's is stopped without the catalogue's: it ends stopped,
|
||||
// names the batch that walks the other merge again and the merge it left out, and that batch is cut into a walk
|
||||
// that builds the other repository's module alone.
|
||||
func TestAStopWithoutAMergeWalksTheOthersAgain(t *testing.T) {
|
||||
open := windowed(t)
|
||||
groupsWaiting(t, "pr/cat1aaaaaaaa")
|
||||
endsItsLine(t)
|
||||
asksRecorded(t)
|
||||
ctx := t.Context()
|
||||
cat := catalogueMerge("cat1aaaaaaaa", "app", t0)
|
||||
one := fromHead(repoMerge("one", "one1bbbbbbbb", t0.Add(5*time.Second)), cat.Head)
|
||||
hear(t, open, cat, t0.Add(time.Second))
|
||||
hear(t, open, one, t0.Add(6*time.Second))
|
||||
cutAt(t, open, t0.Add(2*time.Minute))
|
||||
ws, _ := walks(t, open)
|
||||
if len(ws) != 1 || !ws[0].Open() {
|
||||
t.Fatalf("no open walk to stop: %+v", ws)
|
||||
}
|
||||
stopped := ws[0]
|
||||
p, said, err := stopWalkWithout(ctx, open.inventory, stopped.ID, "mesh-delivery for jochen", "its group stopped",
|
||||
[]string{"novox/mesh-catalog@" + cat.Commit}, t0.Add(3*time.Minute))
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if p.State != inventory.PlanFailed || p.Delivery.Stopped == "" || p.Delivery.WalkedAgainBy == "" ||
|
||||
!reflect.DeepEqual(p.Delivery.LeftOut, []inventory.PlanLeftOut{{Repository: "novox/mesh-catalog", Commit: cat.Commit}}) {
|
||||
t.Fatalf("the stopped walk reads %s %+v", p.State, p.Delivery)
|
||||
}
|
||||
if said.WalkedAgainBy != p.Delivery.WalkedAgainBy || !reflect.DeepEqual(said.WalkedAgain, []string{"novox/one@" + one.Commit}) {
|
||||
t.Fatalf("the stop answered %+v", said)
|
||||
}
|
||||
again, err := open.inventory.MergesOf(ctx, p.Delivery.WalkedAgainBy)
|
||||
if err != nil || len(again) != 1 || again[0].Commit != one.Commit {
|
||||
t.Fatalf("the fresh batch answers %+v (%v); want the other repository's merge alone", again, err)
|
||||
}
|
||||
if left, _ := open.inventory.MergesOf(ctx, stopped.ID); len(left) != 1 || left[0].Commit != cat.Commit {
|
||||
t.Fatalf("the stopped walk still answers %+v; want the left-out merge alone", left)
|
||||
}
|
||||
cutAt(t, open, t0.Add(4*time.Minute))
|
||||
fresh, err := open.inventory.PlanByID(ctx, p.Delivery.WalkedAgainBy)
|
||||
if err != nil || fresh.Batch() || !fresh.Open() {
|
||||
t.Fatalf("the fresh batch was not cut into a walk: %s %v", fresh.State, err)
|
||||
}
|
||||
if _, in := fresh.Modules["one"]; !in {
|
||||
t.Fatalf("the fresh walk does not build one: %v", fresh.Modules)
|
||||
}
|
||||
if _, in := fresh.Modules["app"]; in {
|
||||
t.Fatalf("the fresh walk builds app, whose merge was left out: %v", fresh.Modules)
|
||||
}
|
||||
if len(fresh.Delivery.Merges) != 1 || fresh.Delivery.Merges[0].Commit != one.Commit {
|
||||
t.Fatalf("the fresh walk answers %+v", fresh.Delivery.Merges)
|
||||
}
|
||||
// A stopped walk starts no search of its own (ADR 0276 decision 3 is for a failed one).
|
||||
cutAt(t, open, t0.Add(5*time.Minute))
|
||||
if alone, _ := open.inventory.AloneMerges(ctx); len(alone) != 0 {
|
||||
t.Fatalf("a merge of the stopped walk waits to be walked alone: %+v", alone)
|
||||
}
|
||||
}
|
||||
|
||||
// A later merge of the stopped merge's repository contains it: it is left out too, named with the merge it
|
||||
// contains, and only the other repository's merge is walked again. With nothing left to walk, the walk is only
|
||||
// ended. A merge the walk does not answer is refused, and nothing ends.
|
||||
func TestAStopWithoutAMergeEndsTheMergesThatContainIt(t *testing.T) {
|
||||
open := windowed(t)
|
||||
groupsWaiting(t, "pr/cat1aaaaaaaa")
|
||||
endsItsLine(t)
|
||||
asksRecorded(t)
|
||||
ctx := t.Context()
|
||||
first := catalogueMerge("cat1aaaaaaaa", "app", t0)
|
||||
later := catalogueMerge("cat2cccccccc", "notes", t0.Add(10*time.Second))
|
||||
one := fromHead(repoMerge("one", "one1bbbbbbbb", t0.Add(5*time.Second)), first.Head)
|
||||
hear(t, open, first, t0.Add(time.Second))
|
||||
hear(t, open, one, t0.Add(6*time.Second))
|
||||
hear(t, open, later, t0.Add(11*time.Second))
|
||||
cutAt(t, open, t0.Add(2*time.Minute))
|
||||
ws, _ := walks(t, open)
|
||||
walk := ws[0]
|
||||
|
||||
if _, _, err := stopWalkWithout(ctx, open.inventory, walk.ID, "mesh-delivery for jochen", "x",
|
||||
[]string{"novox/mesh-catalog@ffffffffffff"}, t0.Add(3*time.Minute)); err == nil {
|
||||
t.Fatal("a stop leaving out a merge the walk does not answer was taken")
|
||||
}
|
||||
if p, _ := open.inventory.PlanByID(ctx, walk.ID); !p.Open() {
|
||||
t.Fatalf("a refused stop ended the walk: %s", p.State)
|
||||
}
|
||||
|
||||
p, said, err := stopWalkWithout(ctx, open.inventory, walk.ID, "mesh-delivery for jochen", "its group stopped",
|
||||
[]string{"novox/mesh-catalog@" + first.Commit}, t0.Add(3*time.Minute))
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
want := []inventory.PlanLeftOut{{Repository: "novox/mesh-catalog", Commit: first.Commit},
|
||||
{Repository: "novox/mesh-catalog", Commit: later.Commit, Contains: first.Commit}}
|
||||
if !reflect.DeepEqual(p.Delivery.LeftOut, want) || !reflect.DeepEqual(said.LeftOut, want) {
|
||||
t.Fatalf("left out %+v, said %+v; want %+v", p.Delivery.LeftOut, said.LeftOut, want)
|
||||
}
|
||||
if !strings.Contains(p.Note, later.Commit[:8]) || !strings.Contains(p.Note, p.Delivery.WalkedAgainBy) {
|
||||
t.Fatalf("the stopped walk's note does not name the merge ended with it and the fresh batch: %q", p.Note)
|
||||
}
|
||||
again, _ := open.inventory.MergesOf(ctx, p.Delivery.WalkedAgainBy)
|
||||
if len(again) != 1 || again[0].Commit != one.Commit {
|
||||
t.Fatalf("walked again: %+v; want the other repository's merge alone", again)
|
||||
}
|
||||
|
||||
// Nothing left once the other repository's merge is left out too: the fresh walk is stopped, and nothing more.
|
||||
cutAt(t, open, t0.Add(4*time.Minute))
|
||||
fresh, _ := open.inventory.PlanByID(ctx, p.Delivery.WalkedAgainBy)
|
||||
q, said, err := stopWalkWithout(ctx, open.inventory, fresh.ID, "mesh-delivery for jochen", "that one too",
|
||||
[]string{"novox/one@" + one.Commit}, t0.Add(5*time.Minute))
|
||||
if err != nil || q.State != inventory.PlanFailed || q.Delivery.WalkedAgainBy != "" || said.WalkedAgainBy != "" {
|
||||
t.Fatalf("a stop leaving nothing to walk: %s %+v %+v %v", q.State, q.Delivery, said, err)
|
||||
}
|
||||
if _, bs := walks(t, open); len(bs) != 0 {
|
||||
t.Fatalf("a batch of nothing was made: %+v", bs)
|
||||
}
|
||||
}
|
||||
|
||||
// A merge heard while the walk ran waits in the open batch, at a later commit of the same repository. The merge
|
||||
// walked again joins that batch, never a batch of its own that would walk the older commit after the newer one
|
||||
// (review of #232): its window closes, and its walk is at the newer commit, answering both.
|
||||
func TestAStopWalksTheOthersAgainInTheOpenBatch(t *testing.T) {
|
||||
open := windowed(t)
|
||||
groupsWaiting(t, "pr/cat1aaaaaaaa")
|
||||
endsItsLine(t)
|
||||
asksRecorded(t)
|
||||
ctx := t.Context()
|
||||
cat := catalogueMerge("cat1aaaaaaaa", "app", t0)
|
||||
one1 := fromHead(repoMerge("one", "one1bbbbbbbb", t0.Add(5*time.Second)), cat.Head)
|
||||
hear(t, open, cat, t0.Add(time.Second))
|
||||
hear(t, open, one1, t0.Add(6*time.Second))
|
||||
cutAt(t, open, t0.Add(2*time.Minute))
|
||||
ws, _ := walks(t, open)
|
||||
walk := ws[0]
|
||||
one2 := repoMerge("one", "one2cccccccc", t0.Add(3*time.Minute))
|
||||
hear(t, open, one2, t0.Add(3*time.Minute))
|
||||
_, bs := walks(t, open)
|
||||
if len(bs) != 1 {
|
||||
t.Fatalf("the merge heard while the walk ran is in %d batches", len(bs))
|
||||
}
|
||||
waiting := bs[0]
|
||||
p, said, err := stopWalkWithout(ctx, open.inventory, walk.ID, "mesh-delivery for jochen", "its group stopped",
|
||||
[]string{"novox/mesh-catalog@" + cat.Commit}, t0.Add(3*time.Minute+10*time.Second))
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if p.Delivery.WalkedAgainBy != waiting.ID || said.WalkedAgainBy != waiting.ID {
|
||||
t.Fatalf("walked again by %q (said %q); want the open batch %s", p.Delivery.WalkedAgainBy, said.WalkedAgainBy, waiting.ID)
|
||||
}
|
||||
if _, bs := walks(t, open); len(bs) != 1 {
|
||||
t.Fatalf("%d batches; want the open one alone", len(bs))
|
||||
}
|
||||
b, _ := open.inventory.PlanByID(ctx, waiting.ID)
|
||||
if b.Delivery.Batch == nil || !b.Delivery.Batch.Closed || !slices.Contains(b.Delivery.Batch.Withheld, "app") {
|
||||
t.Fatalf("the open batch reads %+v; want its window closed and app withheld", b.Delivery.Batch)
|
||||
}
|
||||
// Its window closed by the stop, not by the clock: cut at once.
|
||||
cutAt(t, open, t0.Add(3*time.Minute+11*time.Second))
|
||||
fresh, _ := open.inventory.PlanByID(ctx, waiting.ID)
|
||||
if fresh.Batch() || fresh.CommitOf("novox/one") != one2.Commit {
|
||||
t.Fatalf("the batch is %s at %q; want it cut, walking the newer commit", fresh.State, fresh.CommitOf("novox/one"))
|
||||
}
|
||||
var answered []string
|
||||
for _, m := range fresh.Delivery.Merges {
|
||||
answered = append(answered, m.Commit+">"+m.Carried)
|
||||
}
|
||||
if !slices.Contains(answered, one1.Commit+">"+one2.Commit) || !slices.Contains(answered, one2.Commit+">") {
|
||||
t.Fatalf("the walk answers %v; want the earlier merge carried by the later", answered)
|
||||
}
|
||||
}
|
||||
|
||||
// A stop names what the stopped walk already sent and nothing walks again, on which machines; and a later merge of
|
||||
// the stopped merge's repository that waits in a batch, which will deliver the stopped change. A stopped walk
|
||||
// that walked its merges again is refused a retry, saying why.
|
||||
func TestAStopNamesWhatStaysOnTheMachinesAndWhatStillCarriesIt(t *testing.T) {
|
||||
open := windowed(t)
|
||||
groupsWaiting(t, "pr/cat1aaaaaaaa")
|
||||
endsItsLine(t)
|
||||
asksRecorded(t)
|
||||
ctx := t.Context()
|
||||
cat := catalogueMerge("cat1aaaaaaaa", "app", t0)
|
||||
one1 := fromHead(repoMerge("one", "one1bbbbbbbb", t0.Add(5*time.Second)), cat.Head)
|
||||
hear(t, open, cat, t0.Add(time.Second))
|
||||
hear(t, open, one1, t0.Add(6*time.Second))
|
||||
cutAt(t, open, t0.Add(2*time.Minute))
|
||||
ws, _ := walks(t, open)
|
||||
walk := ws[0]
|
||||
sent := t0.Add(150 * time.Second)
|
||||
for name, m := range walk.Modules {
|
||||
if name == "app" || name == "one" {
|
||||
m.First, m.FirstAt = []string{"anchor"}, &sent
|
||||
}
|
||||
}
|
||||
if err := open.inventory.SavePlan(ctx, &walk); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
cat2 := catalogueMerge("cat2dddddddd", "notes", t0.Add(3*time.Minute))
|
||||
hear(t, open, cat2, t0.Add(3*time.Minute))
|
||||
_, said, err := stopWalkWithout(ctx, open.inventory, walk.ID, "mesh-delivery for jochen", "its group stopped",
|
||||
[]string{"novox/mesh-catalog@" + cat.Commit}, t0.Add(3*time.Minute+10*time.Second))
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if !reflect.DeepEqual(said.Kept, []inventory.PlanKept{{Module: "app", Machines: []string{"anchor"}}}) {
|
||||
t.Fatalf("kept %+v; want app on anchor alone (one is walked again)", said.Kept)
|
||||
}
|
||||
p, _ := open.inventory.PlanByID(ctx, walk.ID)
|
||||
if !reflect.DeepEqual(p.Delivery.Kept, said.Kept) || !strings.Contains(p.Note, "app on anchor") {
|
||||
t.Fatalf("the stopped walk's record does not name what stays: %+v %q", p.Delivery.Kept, p.Note)
|
||||
}
|
||||
if len(said.StillCarriedBy) != 1 || !strings.Contains(said.StillCarriedBy[0], cat2.Commit) {
|
||||
t.Fatalf("still carried by %v; want the later catalogue merge waiting in the batch", said.StillCarriedBy)
|
||||
}
|
||||
if _, err := retryPlan(ctx, open, walk.ID); err == nil || !strings.Contains(err.Error(), "was stopped without") {
|
||||
t.Fatalf("a walk stopped without some merges was retried, or refused for another reason: %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
// A batch not yet cut is stopped without a merge: the merge goes to a stopped record of its own, the batch goes on
|
||||
// with the others and withholds the stopped merge's modules; with every merge left out, the batch is stopped.
|
||||
func TestAStopWithoutAMergeLeavesItOutOfABatch(t *testing.T) {
|
||||
open := windowed(t)
|
||||
everyHeadWaits(t)
|
||||
endsItsLine(t)
|
||||
asksRecorded(t)
|
||||
ctx := t.Context()
|
||||
cat := catalogueMerge("cat1aaaaaaaa", "app", t0)
|
||||
one := fromHead(repoMerge("one", "one1bbbbbbbb", t0.Add(5*time.Second)), cat.Head)
|
||||
hear(t, open, cat, t0.Add(time.Second))
|
||||
hear(t, open, one, t0.Add(6*time.Second))
|
||||
_, bs := walks(t, open)
|
||||
b := bs[0]
|
||||
r, said, err := stopWalkWithout(ctx, open.inventory, b.ID, "mesh-delivery for jochen", "its group stopped",
|
||||
[]string{"novox/mesh-catalog@" + cat.Commit}, t0.Add(10*time.Second))
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if said.WalkedAgainBy != b.ID || said.Stopped == b.ID {
|
||||
t.Fatalf("said %+v; want a stopped record of its own, and the batch walking the others", said)
|
||||
}
|
||||
if left, _ := open.inventory.MergesOf(ctx, said.Stopped); len(left) != 1 || left[0].Commit != cat.Commit {
|
||||
t.Fatalf("the stopped record holds %+v", left)
|
||||
}
|
||||
if stopped, _ := open.inventory.PlanByID(ctx, said.Stopped); stopped.State != inventory.PlanFailed ||
|
||||
stopped.Delivery.Stopped == "" || stopped.Delivery.WalkedAgainBy != b.ID {
|
||||
t.Fatalf("the stopped record reads %s %+v", stopped.State, stopped.Delivery)
|
||||
}
|
||||
_ = r
|
||||
cutAt(t, open, t0.Add(3*time.Minute))
|
||||
w, _ := open.inventory.PlanByID(ctx, b.ID)
|
||||
if _, in := w.Modules["app"]; in || w.Batch() {
|
||||
t.Fatalf("the batch's walk is %s and builds %v; want it cut without app", w.State, w.Modules)
|
||||
}
|
||||
// A batch whose every merge is left out is stopped itself.
|
||||
hear(t, open, catalogueMerge("cat3eeeeeeee", "notes", t0.Add(4*time.Minute)), t0.Add(4*time.Minute))
|
||||
_, bs = walks(t, open)
|
||||
last := bs[0]
|
||||
if _, said, err := stopWalkWithout(ctx, open.inventory, last.ID, "mesh-delivery for jochen", "x",
|
||||
[]string{"novox/mesh-catalog@cat3eeeeeeee"}, t0.Add(4*time.Minute+time.Second)); err != nil || said.Stopped != last.ID {
|
||||
t.Fatalf("a batch left with nothing: %+v %v", said, err)
|
||||
}
|
||||
if p, _ := open.inventory.PlanByID(ctx, last.ID); p.State != inventory.PlanFailed || p.Batch() {
|
||||
t.Fatalf("the emptied batch is %s", p.State)
|
||||
}
|
||||
}
|
||||
|
||||
// The stopped walk, the batch and the merges moved are one act (ADR 0299 decision 7): a plan written by somebody
|
||||
// else since it was read refuses all of it, and no merge moves, no plan is written.
|
||||
func TestSavingPlansAndMovingMergesIsOneAct(t *testing.T) {
|
||||
open := windowed(t)
|
||||
everyHeadWaits(t)
|
||||
endsItsLine(t)
|
||||
ctx := t.Context()
|
||||
hear(t, open, catalogueMerge("cat1aaaaaaaa", "app", t0), t0.Add(time.Second))
|
||||
_, bs := walks(t, open)
|
||||
stale := bs[0]
|
||||
moved := stale
|
||||
moved.Note = "written by somebody else"
|
||||
if err := open.inventory.SavePlan(ctx, &moved); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
fresh := inventory.Plan{ID: "plan-fresh", Repository: "novox/mesh-catalog", Branch: "main", Commit: "x", Created: t0,
|
||||
State: inventory.PlanAssembling, Tiers: [][]string{}, Modules: map[string]*inventory.PlanModule{}}
|
||||
err := open.inventory.SavePlansMoving(ctx, []*inventory.Plan{&fresh, &stale},
|
||||
[]inventory.MergeMove{{Repository: "novox/mesh-catalog", Commit: "cat1aaaaaaaa", Plan: "plan-fresh"}})
|
||||
if !errors.Is(err, inventory.ErrPlanMoved) {
|
||||
t.Fatalf("a stale plan in the act: %v", err)
|
||||
}
|
||||
if _, err := open.inventory.PlanByID(ctx, "plan-fresh"); err == nil {
|
||||
t.Fatal("the new plan was written though the act was refused")
|
||||
}
|
||||
if m, _, _ := open.inventory.MergeOf(ctx, "novox/mesh-catalog", "cat1aaaaaaaa"); m.Plan != stale.ID {
|
||||
t.Fatalf("the merge moved to %q though the act was refused", m.Plan)
|
||||
}
|
||||
}
|
||||
|
||||
// What a stopped walk leaves on the machines names every machine its sends reached (review of #232): a module sent
|
||||
// with no first machine reached every machine running it; one sent first reached those, and the rest it was sent
|
||||
// to; a module a merge walked again moves is sent again, and is not named.
|
||||
func TestKeptNamesEveryMachineASendReached(t *testing.T) {
|
||||
at := t0
|
||||
p := inventory.Plan{Modules: map[string]*inventory.PlanModule{
|
||||
"together": {SentAt: &at},
|
||||
"first": {First: []string{"anchor"}, FirstAt: &at, Rest: map[string]inventory.SentDeclaration{"laptop": {}}},
|
||||
"again": {SentAt: &at},
|
||||
"unsent": {},
|
||||
}}
|
||||
got := keptOf(p, []string{"again"}, map[string][]string{"together": {"laptop", "anchor"}, "again": {"anchor"}})
|
||||
want := []inventory.PlanKept{{Module: "first", Machines: []string{"anchor", "laptop"}},
|
||||
{Module: "together", Machines: []string{"anchor", "laptop"}}}
|
||||
if !reflect.DeepEqual(got, want) {
|
||||
t.Fatalf("kept %+v; want %+v", got, want)
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,102 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/nats-io/nats.go"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
)
|
||||
|
||||
// novox/hq issue 529: a walk waiting because its delivery is held for a person said only "its walk waits for
|
||||
// mesh-delivery's word — `plans go … --why …` starts it by hand", pointing a reader at a hand start instead of at
|
||||
// the person's decision. The line names what mesh-delivery says holds the walk: the held delivery, its reason and
|
||||
// `mesh-delivery.release`; or the delivery not at its turn.
|
||||
|
||||
func waitingWalk(now time.Time) inventory.Plan {
|
||||
return inventory.Plan{ID: "plan-1791793277221379309", Repository: "novox/mesh-sdk", Branch: "main",
|
||||
Commit: "9747f3e1b1ac", State: inventory.PlanBuilding, Tiers: [][]string{{"mesh-sdk"}},
|
||||
Created: now.Add(-9 * time.Minute), Modules: map[string]*inventory.PlanModule{},
|
||||
Delivery: &inventory.PlanDelivery{Awaits: "mesh-delivery"}}
|
||||
}
|
||||
|
||||
func TestAWalkWaitingOnAHeldDeliveryNamesTheHold(t *testing.T) {
|
||||
now := time.Date(2026, 10, 12, 8, 35, 0, 0, time.UTC)
|
||||
p := waitingWalk(now)
|
||||
held := "novox/mesh-sdk@d41d255f28ad held since 2026-10-12T08:23:00Z: its group adr-0307-state-history's composed " +
|
||||
"check did not pass for the heads that merged — a person decides: `mesh-delivery.release` (id " +
|
||||
"novox/mesh-sdk@d41d255f28ad, why) lets it go, `mesh-delivery.stop` ends it"
|
||||
waits := walkWaits{p.ID: {{ID: "novox/mesh-sdk@d41d255f28ad", State: "held", Walk: p.ID, Says: held}}}
|
||||
line := planLineSaid(p, now, pauseView{}, tierAtLeast, nil, waits)
|
||||
for _, want := range []string{"held for a person", "composed check did not pass", "mesh-delivery.release"} {
|
||||
if !strings.Contains(line, want) {
|
||||
t.Fatalf("the line does not say %q: %q", want, line)
|
||||
}
|
||||
}
|
||||
if strings.Contains(line, "starts it by hand") {
|
||||
t.Fatalf("a held walk's line points at a hand start: %q", line)
|
||||
}
|
||||
// Told nothing — an older mesh-delivery, or none answering — it reads as before.
|
||||
if line := planLineSaid(p, now, pauseView{}, tierAtLeast, nil, nil); !strings.Contains(line, "starts it by hand") {
|
||||
t.Fatalf("told nothing, the line reads %q", line)
|
||||
}
|
||||
}
|
||||
|
||||
func TestAWalkWaitingOnADeliveryNotAtItsTurnSaysSo(t *testing.T) {
|
||||
now := time.Date(2026, 10, 12, 8, 57, 0, 0, time.UTC)
|
||||
p := waitingWalk(now)
|
||||
waits := walkWaits{p.ID: {{ID: "novox/mesh-sdk@9747f3e1b1ac", State: "published", Walk: p.ID,
|
||||
Says: "not let go yet: novox/mesh-tools@3f0c1a6cec18 (published) carried by it not at its turn"}}}
|
||||
line := planLineSaid(p, now, pauseView{}, tierAtLeast, nil, waits)
|
||||
if !strings.Contains(line, "not at its turn") || !strings.Contains(line, "novox/mesh-tools@3f0c1a6cec18") {
|
||||
t.Fatalf("the line reads %q", line)
|
||||
}
|
||||
// No hand start offered: it would skip the group's order (review of issue 529).
|
||||
if strings.Contains(line, "plans go") {
|
||||
t.Fatalf("a walk not at its turn points at a hand start: %q", line)
|
||||
}
|
||||
}
|
||||
|
||||
// A walk nothing holds — the nzbgeek case, its merges' deliveries ended as nothing-to-move — is said so, and the hand
|
||||
// start is the way on.
|
||||
func TestAWalkHeldByNothingSaysWhyAndTheHandStart(t *testing.T) {
|
||||
now := time.Date(2026, 10, 11, 20, 30, 0, 0, time.UTC)
|
||||
p := waitingWalk(now)
|
||||
waits := walkWaits{p.ID: {{ID: "novox/mesh-media-catalog@cdcdcdcd0000", State: "unheld", Walk: p.ID,
|
||||
Says: "held by nothing: its merges' deliveries ended as nothing-to-move (novox/mesh-media-catalog@abababab0000), " +
|
||||
"yet the walk moves nzbgeek, nzbget — nothing gives it its word"}}}
|
||||
line := planLineSaid(p, now, pauseView{}, tierAtLeast, nil, waits)
|
||||
if !strings.Contains(line, "ended as nothing-to-move") || !strings.Contains(line, "plans go "+p.ID) {
|
||||
t.Fatalf("the line reads %q", line)
|
||||
}
|
||||
}
|
||||
|
||||
// What holds each waiting walk is asked of mesh-delivery's `stalled` with `walks`, a verb the controller's grant
|
||||
// already names; only lines naming a walk are kept, by walk.
|
||||
func TestWhatHoldsTheWaitingWalksIsAskedOfTheDeliveryOwner(t *testing.T) {
|
||||
was := askDeliveryOwner
|
||||
defer func() { askDeliveryOwner = was }()
|
||||
var asked map[string]any
|
||||
askDeliveryOwner = func(_ context.Context, _ *nats.Conn, verb string, args map[string]any) (json.RawMessage, error) {
|
||||
if verb != "stalled" {
|
||||
t.Fatalf("asked %s", verb)
|
||||
}
|
||||
asked = args
|
||||
return json.Marshal([]stalledLine{{ID: "novox/a@1", State: "held", Walk: "plan-1", Says: "held: why"},
|
||||
{ID: "novox/b@2", State: "held", Says: "a delivery past its bound, no walk"}})
|
||||
}
|
||||
got := walksWaiting(t.Context(), nil, true)
|
||||
if asked["walks"] != true {
|
||||
t.Fatalf("stalled was asked with %v", asked)
|
||||
}
|
||||
if len(got) != 1 || len(got["plan-1"]) != 1 || got["plan-1"][0].Says != "held: why" {
|
||||
t.Fatalf("the waiting walks are %+v", got)
|
||||
}
|
||||
if got := walksWaiting(t.Context(), nil, false); got != nil {
|
||||
t.Fatalf("with no holder on record it asked: %+v", got)
|
||||
}
|
||||
}
|
||||
@@ -77,7 +77,7 @@ func TestASendIsRecordedEvenWhenTheSenderIsBeingCancelled(t *testing.T) {
|
||||
}
|
||||
cancel() // the sender is going away: its context is cancelled between the send and the record
|
||||
body := []byte(`{"declaration":1,"resources":[]}`)
|
||||
digest, err := recordSent(ctx, inv, "anchor", body, nil, 0)
|
||||
digest, err := recordSent(ctx, inv, "anchor", body, nil, 0, sentRecord{sender: "a test"})
|
||||
if err != nil {
|
||||
// NodeByName on the cancelled context may itself refuse; the record must still be possible
|
||||
// through the detached context, so look the node up again on a live one.
|
||||
|
||||
@@ -0,0 +1,272 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"fmt"
|
||||
"sort"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/nats-io/nats.go"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/broker"
|
||||
"github.com/novox/mesh-controller/internal/catalogue"
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
"github.com/novox/mesh-controller/internal/link"
|
||||
"github.com/novox/mesh-controller/internal/secrets"
|
||||
)
|
||||
|
||||
// `secret issued <provision>`: the credential a provider's software issued, taken from the provider and kept as
|
||||
// the provision's one credential for every consumer (novox/hq ADR 0305, issue 526).
|
||||
//
|
||||
// **The value comes from the provider, never from whoever asks.** A module served by its machine's runtime calls
|
||||
// under the runtime's one bus account, which carries that machine's agents' calls too, so a value handed to a
|
||||
// verb could be anybody's. This line carries none: it asks the provider's own tool, on the provider's machine, in
|
||||
// the controller's own name — the subject that names its caller, which the bus lets the controller alone publish
|
||||
// (issue 365) — with a sealing key made for this one call. The tool answers only the controller, the value sealed
|
||||
// to that key; the controller opens it, seals it to every holder and forgets it, as the desk's value is (ADR 0277
|
||||
// §23). Asking again fetches the same value again, and a value every holder already holds is not sealed anew.
|
||||
//
|
||||
// **What this trusts: the provider's machine.** The answer is taken from whoever answers the provider's tool
|
||||
// subject on the provider's machine first. On that machine its runtime serves the subject for every module it
|
||||
// carries, so anything that runtime runs, or anything else granted that subject there, could answer before the
|
||||
// provider does and hand the controller a value of its own. ADR 0305 accepts that by trusting the provider's
|
||||
// machine, as the provider itself is trusted; the bus keeps every other machine from answering it.
|
||||
|
||||
// handActIssued is the verb a change of an issued value is recorded under: the mesh working as decided.
|
||||
const handActIssued = "secret issued"
|
||||
|
||||
// issuedAsk is how long the provider's tool is given to answer.
|
||||
const issuedAsk = 20 * time.Second
|
||||
|
||||
// issuedProvider is one assignment of a module whose offer says its software issues the provision's credential.
|
||||
type issuedProvider struct {
|
||||
Node, Module, Tool string
|
||||
}
|
||||
|
||||
// issuedTaker is the line's work, with what it reaches handed in: the store, the bus and the sends.
|
||||
type issuedTaker struct {
|
||||
// providers are the assignments to ask, and whether any module offers the provision so at all.
|
||||
providers func(provision string) ([]issuedProvider, bool, error)
|
||||
ask func(p issuedProvider, args map[string]any) (link.Answer, error)
|
||||
keep func(provision, provider, value string) (inventory.IssuedKept, error)
|
||||
record func(act link.HandAct) error
|
||||
send func(machines []string) error
|
||||
}
|
||||
|
||||
// take asks every provider of the provision for its software's value and keeps each; it answers what it did, in
|
||||
// words that never carry the value or its fingerprint.
|
||||
func (t issuedTaker) take(provision string) (string, error) {
|
||||
providers, offered, err := t.providers(provision)
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
if !offered {
|
||||
return "", fmt.Errorf("no module offers %q with a credential its software issues (\"credential\": "+
|
||||
"{\"issued-by\": \"software\", \"tool\": …}, ADR 0305), so there is nothing to take from a provider; "+
|
||||
"nothing was asked", provision)
|
||||
}
|
||||
if len(providers) == 0 {
|
||||
return fmt.Sprintf("no consumer holds %s from a provider whose software issues it yet, so there is nothing "+
|
||||
"to seal; a consumer that binds holds a value the mesh made until the provider next asks", provision), nil
|
||||
}
|
||||
var said []string
|
||||
var failed []string
|
||||
for _, p := range providers {
|
||||
words, err := t.takeFrom(provision, p)
|
||||
if err != nil {
|
||||
failed = append(failed, fmt.Sprintf("%s on %s: %v", p.Module, p.Node, err))
|
||||
continue
|
||||
}
|
||||
said = append(said, words)
|
||||
}
|
||||
out := strings.Join(said, "\n")
|
||||
if len(failed) > 0 {
|
||||
return out, fmt.Errorf("%s was not taken from every provider:\n %s", provision, strings.Join(failed, "\n "))
|
||||
}
|
||||
return out, nil
|
||||
}
|
||||
|
||||
// takeFrom is one provider: asked, opened, kept, recorded and sent when it changed.
|
||||
func (t issuedTaker) takeFrom(provision string, p issuedProvider) (string, error) {
|
||||
public, private, err := secrets.Keypair()
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("no key could be made to take the value: %w", err)
|
||||
}
|
||||
answer, err := t.ask(p, map[string]any{"provision": provision, "seal_to": public})
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("its tool %s could not be asked: %w", p.Tool, err)
|
||||
}
|
||||
if answer.Error != "" {
|
||||
return "", fmt.Errorf("its tool %s refused: %s", p.Tool, answer.Error)
|
||||
}
|
||||
var given struct {
|
||||
Sealed string `json:"sealed"`
|
||||
}
|
||||
if err := unmarshalAnswer(answer, &given); err != nil || given.Sealed == "" {
|
||||
return "", fmt.Errorf("its tool %s answered no sealed value", p.Tool)
|
||||
}
|
||||
opened, err := secrets.Open(private, given.Sealed)
|
||||
if err != nil {
|
||||
// Never the value, never what failed to open: only that it was not sealed to this call.
|
||||
return "", fmt.Errorf("its tool %s answered a value not sealed to this call; nothing was taken", p.Tool)
|
||||
}
|
||||
value := strings.TrimSpace(string(opened))
|
||||
for i := range opened {
|
||||
opened[i] = 0
|
||||
}
|
||||
if value == "" {
|
||||
return "", fmt.Errorf("its tool %s answered an empty value; nothing was taken", p.Tool)
|
||||
}
|
||||
kept, err := t.keep(provision, p.Node, value)
|
||||
value = ""
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
holders := make([]string, 0, len(kept.Holders))
|
||||
for _, h := range kept.Holders {
|
||||
holders = append(holders, fmt.Sprintf("%s on %s%s", h.ConsumerModule, h.Consumer, asLocal(h.Local)))
|
||||
}
|
||||
words := ""
|
||||
if len(kept.Unsealable) > 0 {
|
||||
var names []string
|
||||
for _, h := range kept.Unsealable {
|
||||
names = append(names, fmt.Sprintf("%s on %s", h.ConsumerModule, h.Consumer))
|
||||
}
|
||||
words = fmt.Sprintf("\n not sealed to %s: no sealing key on that machine", strings.Join(names, ", "))
|
||||
}
|
||||
if !kept.Changed {
|
||||
return fmt.Sprintf("%s from %s on %s: every holder already holds the value its software issued (%s); "+
|
||||
"nothing was sent%s", provision, p.Module, p.Node, strings.Join(holders, ", "), words), nil
|
||||
}
|
||||
sealedTo := make([]string, 0, len(kept.Sealed))
|
||||
for _, h := range kept.Sealed {
|
||||
sealedTo = append(sealedTo, fmt.Sprintf("%s on %s%s", h.ConsumerModule, h.Consumer, asLocal(h.Local)))
|
||||
}
|
||||
recorded := ""
|
||||
if err := t.record(link.HandAct{Verb: handActIssued, Args: []string{provision},
|
||||
Why: fmt.Sprintf("%s on %s gave the credential its software issued for %s; sealed to %s", p.Module, p.Node,
|
||||
provision, strings.Join(sealedTo, ", ")),
|
||||
Cause: "issued-by-software"}); err != nil {
|
||||
recorded = fmt.Sprintf("\n this was NOT recorded in the hand-act log, and is done anyway: %v", err)
|
||||
}
|
||||
if err := t.send(kept.Machines); err != nil {
|
||||
return "", fmt.Errorf("%s from %s on %s is sealed to %s and could not be sent: %w; `push --behind` sends it",
|
||||
provision, p.Module, p.Node, strings.Join(sealedTo, ", "), err)
|
||||
}
|
||||
return fmt.Sprintf("%s from %s on %s: the value its software issued is sealed to %s; sent %s, and each of "+
|
||||
"them starts again on it%s%s", provision, p.Module, p.Node, strings.Join(sealedTo, ", "),
|
||||
strings.Join(kept.Machines, ", "), words, recorded), nil
|
||||
}
|
||||
|
||||
// issuedProvidersOf are the assignments to ask for a provision: every machine providing it to a pair the mesh
|
||||
// holds, and on it the assigned module whose offer says its software issues the credential (ADR 0305 §1).
|
||||
func issuedProvidersOf(ctx context.Context, inv *inventory.Inventory, provision string) ([]issuedProvider, bool, error) {
|
||||
shelf, err := inv.Catalogue(ctx)
|
||||
if err != nil {
|
||||
return nil, false, err
|
||||
}
|
||||
if !offersIssued(shelf, provision) {
|
||||
return nil, false, nil
|
||||
}
|
||||
holders, err := inv.HoldersOf(ctx, provision, "")
|
||||
if err != nil {
|
||||
return nil, true, err
|
||||
}
|
||||
nodes := map[string]bool{}
|
||||
for _, h := range holders {
|
||||
nodes[h.Provider] = true
|
||||
}
|
||||
names := make([]string, 0, len(nodes))
|
||||
for n := range nodes {
|
||||
names = append(names, n)
|
||||
}
|
||||
sort.Strings(names)
|
||||
var out []issuedProvider
|
||||
for _, node := range names {
|
||||
assigned, err := inv.Assigned(ctx, node)
|
||||
if err != nil {
|
||||
return nil, true, err
|
||||
}
|
||||
out = append(out, issuedOn(shelf, node, assigned, provision)...)
|
||||
}
|
||||
return out, true, nil
|
||||
}
|
||||
|
||||
// offersIssued is whether any module offers the provision with a credential its software issues.
|
||||
func offersIssued(shelf map[string]catalogue.Manifest, provision string) bool {
|
||||
for _, m := range shelf {
|
||||
if _, issued := m.IssuedCredentialOf(provision); issued {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// issuedOn are the modules assigned to one machine whose offer says their software issues the provision's
|
||||
// credential, each with the tool that answers it.
|
||||
func issuedOn(shelf map[string]catalogue.Manifest, node string, assigned []string, provision string) []issuedProvider {
|
||||
var out []issuedProvider
|
||||
for _, module := range assigned {
|
||||
if tool, issued := shelf[module].IssuedCredentialOf(provision); issued {
|
||||
out = append(out, issuedProvider{Node: node, Module: module, Tool: tool})
|
||||
}
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// issuedRefusesRotation refuses `rotate` of a provision its provider's software issues (ADR 0305 §9): a value the
|
||||
// mesh made would replace one the software holds, and every consumer would hold a dead credential until the
|
||||
// provider next asks.
|
||||
func issuedRefusesRotation(shelf map[string]catalogue.Manifest, provision string) error {
|
||||
if !offersIssued(shelf, provision) {
|
||||
return nil
|
||||
}
|
||||
return fmt.Errorf("%s's credential is issued by its provider's software, which the mesh cannot make or "+
|
||||
"rotate (ADR 0305): change it in that software, and `secret issued %s` takes the value it holds now. "+
|
||||
"Nothing was rotated", provision, provision)
|
||||
}
|
||||
|
||||
// secretIssued is `secret issued <provision>`, on this controller's stores and bus.
|
||||
func secretIssued(ctx context.Context, args []string) error {
|
||||
if len(args) != 1 || args[0] == "" || strings.HasPrefix(args[0], "-") {
|
||||
return errors.New("secret issued <provision>")
|
||||
}
|
||||
provision := args[0]
|
||||
open, err := openStores(ctx)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
defer open.Close()
|
||||
t := issuedTaker{
|
||||
providers: func(provision string) ([]issuedProvider, bool, error) {
|
||||
return issuedProvidersOf(ctx, open.inventory, provision)
|
||||
},
|
||||
ask: func(p issuedProvider, args map[string]any) (link.Answer, error) {
|
||||
var answer link.Answer
|
||||
err := onTheBus(func(conn *nats.Conn) error {
|
||||
var err error
|
||||
answer, err = link.AskModuleToolOnAs(ctx, conn, broker.ControllerName, p.Module, p.Tool, p.Node,
|
||||
args, issuedAsk)
|
||||
return err
|
||||
})
|
||||
return answer, err
|
||||
},
|
||||
keep: func(provision, provider, value string) (inventory.IssuedKept, error) {
|
||||
return open.inventory.KeepIssuedSecret(ctx, provision, provider, value)
|
||||
},
|
||||
record: func(act link.HandAct) error {
|
||||
return onTheBus(func(conn *nats.Conn) error {
|
||||
_, err := link.RecordHandAct(ctx, conn, act)
|
||||
return err
|
||||
})
|
||||
},
|
||||
send: func(machines []string) error { return sendTo(ctx, open, machines) },
|
||||
}
|
||||
words, err := t.take(provision)
|
||||
if words != "" {
|
||||
fmt.Println(words)
|
||||
}
|
||||
return err
|
||||
}
|
||||
@@ -0,0 +1,218 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/catalogue"
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
"github.com/novox/mesh-controller/internal/link"
|
||||
"github.com/novox/mesh-controller/internal/secrets"
|
||||
)
|
||||
|
||||
// The `issued` verb runs `secret issued <provision>` and nothing else, and that line is the one `secret` line
|
||||
// beside rotate and the desk's that a verb may run (novox/hq ADR 0305 §3, §10, issue 526).
|
||||
func TestTheIssuedVerbRunsTheOneLineThatCarriesNoValue(t *testing.T) {
|
||||
argv, err := argvFor("issued", map[string]any{"provision": "plex-api"})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if strings.Join(argv, " ") != "secret issued plex-api" {
|
||||
t.Fatalf("the verb composed %q", argv)
|
||||
}
|
||||
if _, err := argvFor("issued", map[string]any{}); err == nil {
|
||||
t.Fatal("the verb ran with no provision")
|
||||
}
|
||||
if _, err := argvFor("issued", map[string]any{"provision": "plex-api", "secret": "a value"}); err == nil {
|
||||
t.Fatal("the verb took a value beside the provision")
|
||||
}
|
||||
for _, line := range [][]string{
|
||||
{"secret", "issued", "plex-api", "--from", "/tmp/x"},
|
||||
{"secret", "issued", "--from"},
|
||||
{"secret", "issued"},
|
||||
{"secret", "accept", "ace", "kometa", "plex-api", "--provider", "ace"},
|
||||
{"secret", "recover", "ace", "kometa", "plex-api"},
|
||||
} {
|
||||
if err := terminalOnly(line); err == nil {
|
||||
t.Errorf("%q ran through a verb", line)
|
||||
}
|
||||
}
|
||||
if err := terminalOnly([]string{"secret", "issued", "plex-api"}); err != nil {
|
||||
t.Fatalf("the issued line was refused through its verb: %v", err)
|
||||
}
|
||||
found := false
|
||||
for _, v := range catalogue.ControllerVerbs {
|
||||
if v.Name == "issued" {
|
||||
found = true
|
||||
}
|
||||
}
|
||||
if !found {
|
||||
t.Fatal("the controller's seat does not declare the issued verb")
|
||||
}
|
||||
}
|
||||
|
||||
// A provider's tool answering the value sealed to the call's key: what a provider does (ADR 0305 §2).
|
||||
func issuedSealed(t *testing.T, value string) func(issuedProvider, map[string]any) (link.Answer, error) {
|
||||
return func(_ issuedProvider, args map[string]any) (link.Answer, error) {
|
||||
key, _ := args["seal_to"].(string)
|
||||
if key == "" {
|
||||
t.Fatal("the provider was asked without a key to seal to")
|
||||
}
|
||||
if _, carried := args["value"]; carried {
|
||||
t.Fatal("the ask carried a value")
|
||||
}
|
||||
sealed, err := secrets.Seal(key, []byte(value))
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
raw, _ := json.Marshal(map[string]string{"sealed": sealed})
|
||||
return link.Answer{Result: raw}, nil
|
||||
}
|
||||
}
|
||||
|
||||
type issuedRecorder struct {
|
||||
kept []string
|
||||
acts []link.HandAct
|
||||
sent [][]string
|
||||
again bool // the value is held by every holder already
|
||||
}
|
||||
|
||||
func (r *issuedRecorder) taker(t *testing.T, ask func(issuedProvider, map[string]any) (link.Answer, error)) issuedTaker {
|
||||
return issuedTaker{
|
||||
providers: func(provision string) ([]issuedProvider, bool, error) {
|
||||
return []issuedProvider{{Node: "ace", Module: "plex", Tool: "plex_issued_credential"}}, true, nil
|
||||
},
|
||||
ask: ask,
|
||||
keep: func(provision, provider, value string) (inventory.IssuedKept, error) {
|
||||
r.kept = append(r.kept, value)
|
||||
holders := []inventory.Holder{{Provision: provision, Consumer: "ace", ConsumerModule: "kometa", Provider: provider},
|
||||
{Provision: provision, Consumer: "ace", ConsumerModule: "tautulli", Provider: provider}}
|
||||
if r.again {
|
||||
return inventory.IssuedKept{Holders: holders}, nil
|
||||
}
|
||||
return inventory.IssuedKept{Changed: true, Holders: holders, Sealed: holders, Machines: []string{"ace"}}, nil
|
||||
},
|
||||
record: func(act link.HandAct) error { r.acts = append(r.acts, act); return nil },
|
||||
send: func(machines []string) error { r.sent = append(r.sent, machines); return nil },
|
||||
}
|
||||
}
|
||||
|
||||
// The value the provider's tool sealed to the call is kept, recorded and sent, and the answer never says it.
|
||||
func TestAnIssuedValueIsTakenSealedFromTheProviderAndSent(t *testing.T) {
|
||||
var r issuedRecorder
|
||||
words, err := r.taker(t, issuedSealed(t, "the-servers-own-token")).take("plex-api")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if len(r.kept) != 1 || r.kept[0] != "the-servers-own-token" {
|
||||
t.Fatalf("the provider's value was not kept: %d kept", len(r.kept))
|
||||
}
|
||||
if len(r.sent) != 1 || strings.Join(r.sent[0], ",") != "ace" {
|
||||
t.Fatalf("the holders' machines were not sent: %v", r.sent)
|
||||
}
|
||||
if len(r.acts) != 1 || r.acts[0].Verb != handActIssued {
|
||||
t.Fatalf("the change was not recorded in the hand-act log: %+v", r.acts)
|
||||
}
|
||||
for _, said := range []string{words, r.acts[0].Why, strings.Join(r.acts[0].Args, " ")} {
|
||||
if strings.Contains(said, "the-servers-own-token") || strings.Contains(said, inventory.IssuedStamp("the-servers-own-token")) {
|
||||
t.Fatalf("the value or its fingerprint was said: %q", said)
|
||||
}
|
||||
}
|
||||
if !strings.Contains(words, "kometa on ace") || !strings.Contains(words, "tautulli on ace") {
|
||||
t.Fatalf("the answer does not name the holders: %q", words)
|
||||
}
|
||||
}
|
||||
|
||||
// The same value again writes nothing, records nothing and sends nobody (ADR 0305 §5).
|
||||
func TestAnIssuedValueEveryHolderHoldsSendsNobody(t *testing.T) {
|
||||
r := issuedRecorder{again: true}
|
||||
words, err := r.taker(t, issuedSealed(t, "the-servers-own-token")).take("plex-api")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if len(r.sent) != 0 || len(r.acts) != 0 {
|
||||
t.Fatalf("an unchanged value was sent or recorded: %v %v", r.sent, r.acts)
|
||||
}
|
||||
if !strings.Contains(words, "nothing was sent") {
|
||||
t.Fatalf("the answer does not say nothing was sent: %q", words)
|
||||
}
|
||||
}
|
||||
|
||||
// A value not sealed to the call's key is not taken, nor is a refusal, nor an empty answer (ADR 0305 §2).
|
||||
func TestOnlyAValueSealedToTheCallIsTaken(t *testing.T) {
|
||||
other, _, _ := secrets.Keypair()
|
||||
elsewhere, _ := secrets.Seal(other, []byte("somebody's value"))
|
||||
raw, _ := json.Marshal(map[string]string{"sealed": elsewhere})
|
||||
plain, _ := json.Marshal(map[string]string{"value": "the-servers-own-token"})
|
||||
for name, ask := range map[string]func(issuedProvider, map[string]any) (link.Answer, error){
|
||||
"sealed to another key": func(issuedProvider, map[string]any) (link.Answer, error) { return link.Answer{Result: raw}, nil },
|
||||
"answered in the clear": func(issuedProvider, map[string]any) (link.Answer, error) { return link.Answer{Result: plain}, nil },
|
||||
"refused": func(issuedProvider, map[string]any) (link.Answer, error) {
|
||||
return link.Answer{Error: "the controller alone"}, nil
|
||||
},
|
||||
"not reached": func(issuedProvider, map[string]any) (link.Answer, error) {
|
||||
return link.Answer{}, errors.New("503 no responders")
|
||||
},
|
||||
"sealed empty": issuedSealed(t, " "),
|
||||
} {
|
||||
var r issuedRecorder
|
||||
if _, err := r.taker(t, ask).take("plex-api"); err == nil {
|
||||
t.Errorf("%s: taken", name)
|
||||
}
|
||||
if len(r.kept) != 0 || len(r.sent) != 0 {
|
||||
t.Errorf("%s: something was kept or sent", name)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// A provision no offer says its software issues is refused before anything is asked.
|
||||
func TestAProvisionNoOfferSaysIsIssuedIsRefused(t *testing.T) {
|
||||
asked := false
|
||||
taker := issuedTaker{
|
||||
providers: func(string) ([]issuedProvider, bool, error) { return nil, false, nil },
|
||||
ask: func(issuedProvider, map[string]any) (link.Answer, error) {
|
||||
asked = true
|
||||
return link.Answer{}, nil
|
||||
},
|
||||
}
|
||||
if _, err := taker.take("postgres-database"); err == nil || !strings.Contains(err.Error(), "ADR 0305") {
|
||||
t.Fatalf("expected a refusal naming the record, got %v", err)
|
||||
}
|
||||
if asked {
|
||||
t.Fatal("a provider was asked for a provision no offer says its software issues")
|
||||
}
|
||||
}
|
||||
|
||||
// Which assignments are asked: the modules on the providing machine whose offer says so, with their tool.
|
||||
func TestTheProvidersAskedAreTheOffersThatSaySo(t *testing.T) {
|
||||
shelf := map[string]catalogue.Manifest{
|
||||
"plex": {Module: "plex", Provides: []catalogue.Offer{{Name: "plex-api", Credential: &catalogue.OfferCredential{
|
||||
IssuedBy: catalogue.IssuedBySoftware, Tool: "plex_issued_credential"}}}},
|
||||
"jellyfin": {Module: "jellyfin", Provides: []catalogue.Offer{{Name: "plex-api"}}},
|
||||
}
|
||||
got := issuedOn(shelf, "ace", []string{"jellyfin", "plex", "kometa"}, "plex-api")
|
||||
if len(got) != 1 || got[0] != (issuedProvider{Node: "ace", Module: "plex", Tool: "plex_issued_credential"}) {
|
||||
t.Fatalf("the providers asked: %+v", got)
|
||||
}
|
||||
if err := issuedRefusesRotation(shelf, "plex-api"); err == nil || !strings.Contains(err.Error(), "secret issued plex-api") {
|
||||
t.Fatalf("rotate of an issued provision was not refused with the way to take it: %v", err)
|
||||
}
|
||||
if err := issuedRefusesRotation(shelf, "postgres-database"); err != nil {
|
||||
t.Fatalf("rotate of an ordinary provision was refused: %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
// A change of an issued value is the mesh working as decided, never a repair (ADR 0305 §8).
|
||||
func TestAnIssuedValueIsADecisionInTheHandActLog(t *testing.T) {
|
||||
for _, v := range handActVerbs {
|
||||
if v.Verb == handActIssued {
|
||||
if v.Decision == "" {
|
||||
t.Fatal("secret issued counts as a repair")
|
||||
}
|
||||
return
|
||||
}
|
||||
}
|
||||
t.Fatal("secret issued is not in the hand-act table")
|
||||
}
|
||||
@@ -0,0 +1,160 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
)
|
||||
|
||||
// novox/hq issue 485: the mesh records every send — sender, lease epoch, generation, modules — and only `plan`
|
||||
// said it. `status` says per machine when it was last sent a declaration and by whom, in one line; `node show`
|
||||
// says the last send in full and what the machine answered; and `status --json` carries it as fields, since
|
||||
// the store's reader may not read the controller's tables and these verbs are the only window onto them.
|
||||
|
||||
func aLastSend(answer inventory.SendAnswer) inventory.Send {
|
||||
sent := time.Date(2026, 10, 11, 18, 40, 5, 0, time.Local)
|
||||
return inventory.Send{NodeName: "laptop", Sequence: 12, Epoch: 57,
|
||||
Sender: "a one-shot push by jochen at a shell on anchor", Generation: 40, Digest: "d12",
|
||||
Modules: []string{"docker", "sudo"}, SentAt: sent, Recorded: true, Answer: answer}
|
||||
}
|
||||
|
||||
func TestStatusSaysEachMachinesLastSendInOneLine(t *testing.T) {
|
||||
at := time.Date(2026, 10, 11, 18, 41, 0, 0, time.Local)
|
||||
asked := answers{
|
||||
nodes: []inventory.Node{{Name: "anchor", LastSeen: time.Now()}, {Name: "laptop", LastSeen: time.Now()}},
|
||||
lastSent: map[string]inventory.Send{"laptop": aLastSend(inventory.SendAnswer{
|
||||
Outcome: inventory.OutcomeApplied, At: &at})},
|
||||
}
|
||||
shown := printed(t, func() error { return printStatus(asked) })
|
||||
var laptop, anchor []string
|
||||
for _, line := range strings.Split(shown, "\n") {
|
||||
fields := strings.Fields(line)
|
||||
if len(fields) > 0 && fields[0] == "laptop" {
|
||||
laptop = append(laptop, line)
|
||||
}
|
||||
if len(fields) > 0 && fields[0] == "anchor" {
|
||||
anchor = append(anchor, line)
|
||||
}
|
||||
}
|
||||
if len(laptop) != 1 || !strings.Contains(laptop[0], "2026-10-11 18:40") ||
|
||||
!strings.Contains(laptop[0], "by a one-shot push by jochen at a shell on anchor") ||
|
||||
!strings.Contains(laptop[0], "generation 40") || !strings.Contains(laptop[0], "applied") {
|
||||
t.Fatalf("status does not say laptop's last send in one line:\n%s", shown)
|
||||
}
|
||||
if len(anchor) != 1 || !strings.Contains(anchor[0], "no send recorded") {
|
||||
t.Fatalf("status does not say anchor has no send recorded, in one line:\n%s", shown)
|
||||
}
|
||||
}
|
||||
|
||||
func TestStatusSaysTheLastSendsCouldNotBeRead(t *testing.T) {
|
||||
asked := answers{nodes: []inventory.Node{{Name: "laptop", LastSeen: time.Now()}},
|
||||
lastSentUnread: "the store went away"}
|
||||
if shown := printed(t, func() error { return printStatus(asked) }); !strings.Contains(shown, "the store went away") {
|
||||
t.Fatalf("a record of sends that could not be read is not said:\n%s", shown)
|
||||
}
|
||||
if asked.well() {
|
||||
t.Error("a mesh whose sends could not be read is called well")
|
||||
}
|
||||
}
|
||||
|
||||
func TestNodeShowSaysTheLastSendInFull(t *testing.T) {
|
||||
at := time.Date(2026, 10, 11, 18, 41, 0, 0, time.Local)
|
||||
refused := strings.Join(lastSendLines(aLastSend(inventory.SendAnswer{Outcome: inventory.OutcomeRefused,
|
||||
Refused: "unknown field \"generation\"\nsecond line", At: &at})), "\n")
|
||||
for _, want := range []string{"sequence 12", "2026-10-11 18:40:05", "a one-shot push by jochen at a shell on anchor",
|
||||
"lease epoch 57", "generation 40", "docker, sudo", "refused", "unknown field \"generation\""} {
|
||||
if !strings.Contains(refused, want) {
|
||||
t.Errorf("node show's last send does not say %q:\n%s", want, refused)
|
||||
}
|
||||
}
|
||||
if applied := strings.Join(lastSendLines(aLastSend(inventory.SendAnswer{Outcome: inventory.OutcomeApplied,
|
||||
At: &at})), "\n"); !strings.Contains(applied, "applied it at 2026-10-11 18:41:00") {
|
||||
t.Errorf("an applied send is not said applied:\n%s", applied)
|
||||
}
|
||||
if waiting := strings.Join(lastSendLines(aLastSend(inventory.SendAnswer{})), "\n"); !strings.Contains(waiting,
|
||||
"not reported on it yet") {
|
||||
t.Errorf("a send not reported on is not said so:\n%s", waiting)
|
||||
}
|
||||
stale := aLastSend(inventory.SendAnswer{})
|
||||
when := at
|
||||
stale.RefusedAt, stale.RefusedApplied = &when, 44
|
||||
if s := strings.Join(lastSendLines(stale), "\n"); !strings.Contains(s, "refused it at 2026-10-11 18:41:00") ||
|
||||
!strings.Contains(s, "generation 44") {
|
||||
t.Errorf("a send refused for its generation is not said so:\n%s", s)
|
||||
}
|
||||
}
|
||||
|
||||
func TestStatusJSONCarriesEachMachinesLastSend(t *testing.T) {
|
||||
at := time.Date(2026, 10, 11, 18, 41, 0, 0, time.UTC)
|
||||
asked := answers{nodes: []inventory.Node{{Name: "anchor"}, {Name: "laptop"}},
|
||||
lastSent: map[string]inventory.Send{"laptop": aLastSend(inventory.SendAnswer{Outcome: inventory.OutcomeRefused,
|
||||
Refused: "unknown field", At: &at})}}
|
||||
body, err := statusAsJSON(asked)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
var got struct {
|
||||
LastSent []map[string]any `json:"lastSent"`
|
||||
}
|
||||
if err := json.Unmarshal(body, &got); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if len(got.LastSent) != 1 {
|
||||
t.Fatalf("status --json carries %d last sends, want laptop's only:\n%s", len(got.LastSent), body)
|
||||
}
|
||||
s := got.LastSent[0]
|
||||
if s["node"] != "laptop" || s["sequence"] != float64(12) || s["epoch"] != float64(57) ||
|
||||
s["generation"] != float64(40) || s["sender"] != "a one-shot push by jochen at a shell on anchor" ||
|
||||
s["digest"] != "d12" || s["sentAt"] == nil || s["answer"] != "refused" || s["refused"] != "unknown field" ||
|
||||
s["answeredAt"] == nil {
|
||||
t.Fatalf("laptop's last send reads %v", s)
|
||||
}
|
||||
if modules, _ := s["modules"].([]any); len(modules) != 2 || modules[0] != "docker" {
|
||||
t.Fatalf("the modules it named read %v", s["modules"])
|
||||
}
|
||||
}
|
||||
|
||||
// And through the store: a send recorded and refused by the machine is what `node show` and `status --json`
|
||||
// read back.
|
||||
func TestNodeShowAndStatusReadTheLastSendFromTheStore(t *testing.T) {
|
||||
open := aMesh(t)
|
||||
ctx := t.Context()
|
||||
record, err := open.inventory.NodeByName(ctx, "laptop")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := open.inventory.RecordSentWith(ctx, record.ID, "d12", nil, 57, 40, inventory.Send{Sequence: 12,
|
||||
Epoch: 57, Sender: "a one-shot push by jochen at a shell on anchor", Generation: 40, Digest: "d12",
|
||||
Modules: []string{"docker", "sudo"}}); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if _, err := open.inventory.RecordDoing(ctx, record.ID, inventory.Doing{Outcome: inventory.OutcomeRefused,
|
||||
Declared: "d12", Refused: "unknown field \"generation\""}); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
shown := printed(t, func() error { return showNode(ctx, open, "laptop") })
|
||||
for _, want := range []string{"a one-shot push by jochen at a shell on anchor", "lease epoch 57", "generation 40",
|
||||
"docker, sudo", "unknown field \"generation\""} {
|
||||
if !strings.Contains(shown, want) {
|
||||
t.Errorf("node show laptop does not say %q:\n%s", want, shown)
|
||||
}
|
||||
}
|
||||
body := printed(t, func() error { return statusFor(ctx, open, true) })
|
||||
var got struct {
|
||||
LastSent []struct {
|
||||
Node string `json:"node"`
|
||||
Sender string `json:"sender"`
|
||||
Answer string `json:"answer"`
|
||||
} `json:"lastSent"`
|
||||
}
|
||||
if err := json.Unmarshal([]byte(body), &got); err != nil {
|
||||
t.Fatalf("%v:\n%s", err, body)
|
||||
}
|
||||
if len(got.LastSent) != 1 || got.LastSent[0].Node != "laptop" || got.LastSent[0].Answer != "refused" ||
|
||||
got.LastSent[0].Sender != "a one-shot push by jochen at a shell on anchor" {
|
||||
t.Fatalf("status --json's last sends read %+v", got.LastSent)
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,222 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"fmt"
|
||||
"sort"
|
||||
"strings"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/catalogue"
|
||||
"github.com/novox/mesh-controller/internal/conditions"
|
||||
)
|
||||
|
||||
// A module assigned to a machine and left out of its declaration is said (novox/hq issue 380).
|
||||
//
|
||||
// **An omission is a finding, never a refusal of the push** (ADR 0163, rule 6): the machine is sent everything
|
||||
// else, and the module's held things are kept. Until issue 380 the only place it showed was `plan`: nfs-server was
|
||||
// assigned to the home server for days, every send left it out for a setting nobody gave, and the operator believed
|
||||
// it ran. So the self-check (D1) judges every machine as the next send would (Resolution.LeftOutBecause, the send's
|
||||
// own judgement) and raises a condition on that machine for each module it leaves out:
|
||||
//
|
||||
// - a setting nobody gave (catalogue.UnsetSettingError) is the operator's to give: kind needs-operator, naming
|
||||
// the module, the setting and the command that sets it;
|
||||
// - any other cause is said as a module not working is: kind left-out, a warning with the reason as evidence.
|
||||
//
|
||||
// Never urgent and never escalated by age (as ADR 0283 decision 5): nothing the machine ran was undone. It clears
|
||||
// on the first run that no longer finds it — the module composed again, or no longer assigned. `status` and
|
||||
// `node show` list the same modules under "assigned, not applied" with the same reason.
|
||||
//
|
||||
// A module left out because its stored manifest has a key this controller does not know is not raised here: the
|
||||
// catalogue's own unknown-field condition says it once for the whole mesh (ADR 0262); it is still listed.
|
||||
|
||||
const (
|
||||
// probeLeftOutID is the self-check's probe that raises and clears these conditions: D1, which already
|
||||
// resolves every machine (probeDeclarations), so the judgement costs no resolution of its own.
|
||||
probeLeftOutID = "D1"
|
||||
// kindLeftOut is a module left out for any cause but a setting nobody gave; it is also every such condition's
|
||||
// token, whichever its kind, so a cause that changes is the same condition said anew.
|
||||
kindLeftOut = "left-out"
|
||||
)
|
||||
|
||||
// leftOutModule is one module of a machine's set that its declaration leaves out, and why.
|
||||
type leftOutModule struct {
|
||||
Module string
|
||||
// Setting is the setting nobody gave, when that is the cause.
|
||||
Setting string
|
||||
// Why is the declaration's own reason, whole.
|
||||
Why string
|
||||
// Unread is a stored manifest this controller cannot read whole (said by the catalogue's condition).
|
||||
Unread bool
|
||||
}
|
||||
|
||||
// leftOutOf is every module of a machine's resolution that a push would leave out, sorted. Pure: the judgement
|
||||
// the push makes (catalogue.Resolution.LeftOutBecause), nothing allocated.
|
||||
func leftOutOf(plan catalogue.Resolution, settings catalogue.SettingsBy, adopted bool) []leftOutModule {
|
||||
because := plan.LeftOutBecause(settings, adopted)
|
||||
out := make([]leftOutModule, 0, len(because))
|
||||
for module, why := range because {
|
||||
l := leftOutModule{Module: module, Why: oneLine(why.Error())}
|
||||
var unset *catalogue.UnsetSettingError
|
||||
var unread *catalogue.UnreadManifestError
|
||||
switch {
|
||||
case errors.As(why, &unset):
|
||||
l.Setting = unset.Setting
|
||||
case errors.As(why, &unread):
|
||||
l.Unread = true
|
||||
}
|
||||
out = append(out, l)
|
||||
}
|
||||
sort.Slice(out, func(i, j int) bool { return out[i].Module < out[j].Module })
|
||||
return out
|
||||
}
|
||||
|
||||
// settingCommand is the command that gives a module's setting on one machine.
|
||||
func settingCommand(module, setting, node string) string {
|
||||
return fmt.Sprintf("`settings set %s '{%q: …}' --node %s`", module, setting, node)
|
||||
}
|
||||
|
||||
// reason is why a module is left out, as `status`, `node show` and the condition's summary say it: for a setting
|
||||
// nobody gave, the setting and the command that gives it; otherwise the declaration's own words.
|
||||
func (l leftOutModule) reason(node string) string {
|
||||
if l.Setting != "" {
|
||||
return fmt.Sprintf("nothing sets its setting %q, so every send leaves it out of its declaration — %s sets it", l.Setting,
|
||||
settingCommand(l.Module, l.Setting, node))
|
||||
}
|
||||
return "every send leaves it out of its declaration: " + l.Why
|
||||
}
|
||||
|
||||
// leftOutObservations are the conditions a machine's left-out modules raise, one each.
|
||||
func leftOutObservations(node string, left []leftOutModule) []conditions.Observation {
|
||||
var out []conditions.Observation
|
||||
for _, l := range left {
|
||||
if l.Unread {
|
||||
continue
|
||||
}
|
||||
out = append(out, leftOutObservation(node, l))
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// leftOutObservation is one module left out of one machine's declaration: needs-operator for a setting nobody
|
||||
// gave, left-out otherwise; a warning either way, the operator's to resolve.
|
||||
func leftOutObservation(node string, l leftOutModule) conditions.Observation {
|
||||
o := conditions.Observation{Scope: conditions.ScopeModule, ID: l.Module + "." + node, Token: kindLeftOut,
|
||||
Kind: kindLeftOut, Machine: node, Severity: conditions.Warning, Resolver: conditions.ResolverOperator,
|
||||
Summary: fmt.Sprintf("%s is assigned to %s and not applied: %s", l.Module, node, l.reason(node)),
|
||||
Said: l.Why}
|
||||
w := leftOutWords(l.Module, node, l.Setting)
|
||||
if l.Setting != "" {
|
||||
o.Kind = kindNeedsOperator
|
||||
} else {
|
||||
// The words of why may name a path or an address, which the operator's channel withholds: the
|
||||
// summary sends them to the evidence, and `plan` says them in full.
|
||||
o.Summary = fmt.Sprintf("%s is assigned to %s and not applied: every send leaves it out of its declaration, "+
|
||||
"because what is set for it does not fit its manifest — the evidence and `plan %s` say why", l.Module, node, node)
|
||||
}
|
||||
o.Headline, o.Explanation, o.Needs, o.Resolved = w.Headline, w.Explanation, w.Needs, w.Resolved
|
||||
return o
|
||||
}
|
||||
|
||||
// leftOutWords is what the operator reads of a module left out (ADR 0253): plain, the act named.
|
||||
func leftOutWords(module, node, setting string) words {
|
||||
w := words{
|
||||
Headline: fmt.Sprintf("%s is not applied on %s", module, node),
|
||||
Explanation: fmt.Sprintf("%s is assigned to %s, and every send to %s leaves it out of the declaration because what "+
|
||||
"is set for it does not fit its manifest. Nothing of it changes there; the rest of %s is sent as usual.",
|
||||
module, node, node, node),
|
||||
Needs: fmt.Sprintf("read why in the details, then change what is set for %s or unassign it.", module),
|
||||
Resolved: fmt.Sprintf("%s on %s is no longer left out", module, node),
|
||||
}
|
||||
if setting != "" {
|
||||
w.Explanation = fmt.Sprintf("%s is assigned to %s, and every send to %s leaves it out of the declaration because "+
|
||||
"nothing sets its setting %s. Nothing of it runs there until it is set; the rest of %s is sent as usual.",
|
||||
module, node, node, setting, node)
|
||||
w.Needs = fmt.Sprintf("set %s for %s on %s, or approve it when it is proposed to you.", setting, module, node)
|
||||
// A setting's name that is not plain (a dotted key) is in the summary instead.
|
||||
if _, ok := conditions.PlainWords(w, node); !ok {
|
||||
w.Explanation = fmt.Sprintf("%s is assigned to %s, and every send to %s leaves it out of the declaration because a "+
|
||||
"setting it needs is not set. Nothing of it runs there until it is set; the details name it.",
|
||||
module, node, node)
|
||||
w.Needs = fmt.Sprintf("set what %s needs on %s; the details name the setting.", module, node)
|
||||
}
|
||||
}
|
||||
return w
|
||||
}
|
||||
|
||||
// notAppliedLines is a machine's "assigned, not applied" as `node show` prints it: one line a module, with the
|
||||
// reason its condition says.
|
||||
func notAppliedLines(node string, left []leftOutModule) []string {
|
||||
if len(left) == 0 {
|
||||
return nil
|
||||
}
|
||||
lines := []string{"", " assigned, not applied:"}
|
||||
for _, l := range left {
|
||||
lines = append(lines, fmt.Sprintf(" %-22s %s", l.Module, l.reason(node)))
|
||||
}
|
||||
return lines
|
||||
}
|
||||
|
||||
// machineNotApplied is one module assigned to a machine and left out of its declaration, in `status --json`.
|
||||
type machineNotApplied struct {
|
||||
Node string `json:"node"`
|
||||
Module string `json:"module"`
|
||||
Setting string `json:"setting,omitempty"`
|
||||
Reason string `json:"reason"`
|
||||
// UnreadManifest is a module left out because this controller cannot read its manifest whole: it raises no
|
||||
// condition of its own on the machine, since the catalogue's unknown-field condition says it once (ADR 0262).
|
||||
UnreadManifest bool `json:"unread-manifest,omitempty"`
|
||||
}
|
||||
|
||||
// notApplied is every machine's left-out modules, in a stated order, as `status --json` carries them.
|
||||
func notApplied(left map[string][]leftOutModule) []machineNotApplied {
|
||||
names := make([]string, 0, len(left))
|
||||
for name := range left {
|
||||
names = append(names, name)
|
||||
}
|
||||
sort.Strings(names)
|
||||
var out []machineNotApplied
|
||||
for _, name := range names {
|
||||
for _, l := range left[name] {
|
||||
out = append(out, machineNotApplied{Node: name, Module: l.Module, Setting: l.Setting, Reason: l.reason(name),
|
||||
UnreadManifest: l.Unread})
|
||||
}
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// printNotApplied is status's "assigned, not applied", every machine's.
|
||||
func printNotApplied(left map[string][]leftOutModule) {
|
||||
rows := notApplied(left)
|
||||
if len(rows) == 0 {
|
||||
return
|
||||
}
|
||||
unread := 0
|
||||
for _, r := range rows {
|
||||
if r.UnreadManifest {
|
||||
unread++
|
||||
}
|
||||
}
|
||||
// Which raise a condition is said, not implied (review of #223): one whose manifest this controller cannot
|
||||
// read is listed here and raises none of its own on the machine — the catalogue's condition says it.
|
||||
raises := "each raises a condition on its machine"
|
||||
switch {
|
||||
case unread == len(rows):
|
||||
raises = "none raises a condition on its machine: this controller cannot read their manifests, which the " +
|
||||
"catalogue's own condition says"
|
||||
case unread > 0:
|
||||
raises += fmt.Sprintf(", except the %d whose manifest this controller cannot read, which the catalogue's own "+
|
||||
"condition says", unread)
|
||||
}
|
||||
fmt.Printf("%d module(s) assigned, not applied — every send leaves them out of their declaration; %s:\n",
|
||||
len(rows), raises)
|
||||
for _, r := range rows {
|
||||
fmt.Printf(" %-12s %-22s %s\n", r.Node, r.Module, r.Reason)
|
||||
}
|
||||
fmt.Println()
|
||||
}
|
||||
|
||||
// isLeftOutCondition is whether a condition is a module left out of its declaration, which the machine's health
|
||||
// statements neither raise nor clear: by its token, which every one carries whatever its kind.
|
||||
func isLeftOutCondition(c conditions.Condition) bool {
|
||||
return c.Subject.Scope == conditions.ScopeModule && strings.HasSuffix(c.Key, "."+kindLeftOut)
|
||||
}
|
||||
@@ -0,0 +1,259 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"os"
|
||||
"slices"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/catalogue"
|
||||
"github.com/novox/mesh-controller/internal/conditions"
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
"github.com/novox/mesh-controller/internal/link"
|
||||
)
|
||||
|
||||
// novox/hq issue 380: nfs-server was assigned to the home server for days and every send left it out — "nfs-server
|
||||
// has a file that says ${setting:shares}, and nothing sets shares for it" — and nothing but `plan` said so. The
|
||||
// manifest is the catalogue's own at the commit that added it (mesh-catalog 48fba44), which still says
|
||||
// ${setting:shares}; the reason below is the one the live push printed.
|
||||
|
||||
// leftOutNFS is the resolution of a machine assigned that nfs-server, with the settings given.
|
||||
func leftOutNFS(t *testing.T) catalogue.Resolution {
|
||||
t.Helper()
|
||||
raw, err := os.ReadFile("testdata/left-out/nfs-server.json")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
m, err := catalogue.ParseManifest(raw)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
return catalogue.Resolution{Modules: []catalogue.Manifest{m}}
|
||||
}
|
||||
|
||||
// sharesGiven is the operator's setting for it on the machine.
|
||||
func sharesGiven(value string) catalogue.SettingsBy {
|
||||
return catalogue.SettingsBy{"nfs-server": {{From: "anchor", Values: map[string]any{"shares": value}}}}
|
||||
}
|
||||
|
||||
func TestAModuleLeftOutForASettingNobodyGaveNeedsTheOperatorNamingTheSettingAndTheCommand(t *testing.T) {
|
||||
left := leftOutOf(leftOutNFS(t), nil, false)
|
||||
if len(left) != 1 || left[0].Module != "nfs-server" || left[0].Setting != "shares" {
|
||||
t.Fatalf("left out: %+v", left)
|
||||
}
|
||||
if !strings.Contains(left[0].Why, `nothing sets "shares" for it`) {
|
||||
t.Fatalf("the reason is not the push's own: %s", left[0].Why)
|
||||
}
|
||||
obs := leftOutObservations("anchor", left)
|
||||
if len(obs) != 1 {
|
||||
t.Fatalf("raised %+v", obs)
|
||||
}
|
||||
o := obs[0]
|
||||
if o.Key() != "module.nfs-server.anchor.left-out" || o.Kind != kindNeedsOperator || o.Machine != "anchor" ||
|
||||
o.Severity != conditions.Warning || o.Resolver != conditions.ResolverOperator {
|
||||
t.Fatalf("raised %s as %s, %s, by %s, on %q", o.Key(), o.Kind, o.Severity, o.Resolver, o.Machine)
|
||||
}
|
||||
for _, want := range []string{"nfs-server", "anchor", `"shares"`, "`settings set nfs-server '{\"shares\": …}' --node anchor`"} {
|
||||
if !strings.Contains(o.Summary, want) {
|
||||
t.Errorf("the summary does not name %s: %s", want, o.Summary)
|
||||
}
|
||||
}
|
||||
if o.Said != left[0].Why {
|
||||
t.Errorf("the evidence is not the reason the send gives: %s", o.Said)
|
||||
}
|
||||
plainExample(t, o, "nfs-server is not applied on anchor",
|
||||
"Needs you: set shares for nfs-server on anchor, or approve it when it is proposed to you. nfs-server is assigned to "+
|
||||
"anchor, and every send to anchor leaves it out of the declaration because nothing sets its setting shares. "+
|
||||
"Nothing of it runs there until it is set; the rest of anchor is sent as usual.")
|
||||
}
|
||||
|
||||
func TestAModuleLeftOutForAnotherCauseIsAWarningWithTheReasonAsEvidence(t *testing.T) {
|
||||
// A setting stored that its manifest can no longer take: one with a line break (issue 339).
|
||||
left := leftOutOf(leftOutNFS(t), sharesGiven("library=/srv/library\nmedia=/srv/media"), false)
|
||||
if len(left) != 1 || left[0].Setting != "" {
|
||||
t.Fatalf("left out: %+v", left)
|
||||
}
|
||||
obs := leftOutObservations("anchor", left)
|
||||
if len(obs) != 1 {
|
||||
t.Fatalf("raised %+v", obs)
|
||||
}
|
||||
o := obs[0]
|
||||
if o.Key() != "module.nfs-server.anchor.left-out" || o.Kind != kindLeftOut || o.Severity != conditions.Warning {
|
||||
t.Fatalf("raised %s as %s, %s", o.Key(), o.Kind, o.Severity)
|
||||
}
|
||||
if !strings.Contains(o.Said, "holds a line break") || strings.Contains(o.Summary, "/srv/") {
|
||||
t.Fatalf("the reason is not the evidence, or the summary carries it to the channel:\n%s\n%s", o.Summary, o.Said)
|
||||
}
|
||||
plainExample(t, o, "nfs-server is not applied on anchor",
|
||||
"Needs you: read why in the details, then change what is set for nfs-server or unassign it. nfs-server is assigned to "+
|
||||
"anchor, and every send to anchor leaves it out of the declaration because what is set for it does not fit "+
|
||||
"its manifest. Nothing of it changes there; the rest of anchor is sent as usual.")
|
||||
}
|
||||
|
||||
// The self-check raises it, keeps it a warning however long it stands, and clears it when the module composes
|
||||
// again or is no longer assigned; a machine's health statement neither clears nor raises it.
|
||||
func TestALeftOutModulesConditionClearsWhenItComposesAgainOrIsUnassigned(t *testing.T) {
|
||||
plan, settings := leftOutNFS(t), catalogue.SettingsBy(nil)
|
||||
withProbes(t, probe{ID: probeLeftOutID, Asserts: "the test's", Kind: kindLeftOut, Phase: 1,
|
||||
run: func(context.Context, *doctor) ([]conditions.Observation, error) {
|
||||
return leftOutObservations("anchor", leftOutOf(plan, settings, false)), nil
|
||||
}})
|
||||
store := conditions.NewInMemory()
|
||||
k := conditions.NewKeeper(t.Context(), conditions.Options{Store: store, History: store})
|
||||
defer k.Close(context.Background())
|
||||
d := &doctor{keeper: k, teller: &conditions.Told{}, host: "anchor"}
|
||||
key := "module.nfs-server.anchor.left-out"
|
||||
openOnes := func() map[string]conditions.Condition {
|
||||
t.Helper()
|
||||
open, err := k.Open(t.Context())
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
out := map[string]conditions.Condition{}
|
||||
for _, c := range open {
|
||||
out[c.Key] = c
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
d.runOnce(t.Context(), "a test")
|
||||
c, raised := openOnes()[key]
|
||||
if !raised || c.Kind != kindNeedsOperator || c.Severity != conditions.Warning {
|
||||
t.Fatalf("a module left out raised %+v", openOnes())
|
||||
}
|
||||
// A statement from the machine that says nothing of it — the module runs nothing there — leaves it open.
|
||||
if err := judgeModuleHealth(t.Context(), nil, k, "anchor", map[string][]inventory.ResourceHealth{}, nil,
|
||||
time.Now().Add(72*time.Hour)); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if _, still := openOnes()[key]; !still {
|
||||
t.Fatal("a health statement that says nothing of the module cleared its left-out condition")
|
||||
}
|
||||
d.runOnce(t.Context(), "a test")
|
||||
if c := openOnes()[key]; c.Severity != conditions.Warning {
|
||||
t.Fatalf("after a health statement and days, it is %+v", openOnes())
|
||||
}
|
||||
|
||||
// The setting given: it composes, and the condition clears.
|
||||
settings = sharesGiven("library=/srv/library")
|
||||
d.runOnce(t.Context(), "a test")
|
||||
if _, still := openOnes()[key]; still {
|
||||
t.Fatalf("composed again, still open: %+v", openOnes())
|
||||
}
|
||||
|
||||
// Left out again, then unassigned: no longer in the machine's set, and it clears.
|
||||
settings = nil
|
||||
d.runOnce(t.Context(), "a test")
|
||||
if _, raised := openOnes()[key]; !raised {
|
||||
t.Fatal("left out again and not raised")
|
||||
}
|
||||
plan = catalogue.Resolution{}
|
||||
d.runOnce(t.Context(), "a test")
|
||||
if _, still := openOnes()[key]; still {
|
||||
t.Fatalf("unassigned, still open: %+v", openOnes())
|
||||
}
|
||||
}
|
||||
|
||||
func TestTheLeftOutProbeIsInTheRegistry(t *testing.T) {
|
||||
for _, p := range probeRegistry {
|
||||
if p.ID == probeLeftOutID {
|
||||
if p.run == nil || !slices.Contains(p.Raises, kindLeftOut) || !slices.Contains(p.Raises, kindNeedsOperator) {
|
||||
t.Fatalf("%+v", p)
|
||||
}
|
||||
return
|
||||
}
|
||||
}
|
||||
t.Fatalf("no probe %s: a module left out is said nowhere", probeLeftOutID)
|
||||
}
|
||||
|
||||
// status and node show list it under "assigned, not applied" with the reason the condition says, and status is
|
||||
// not well while there is one.
|
||||
func TestStatusAndNodeListAModuleAssignedAndNotApplied(t *testing.T) {
|
||||
left := map[string][]leftOutModule{"anchor": leftOutOf(leftOutNFS(t), nil, false)}
|
||||
reason := leftOutObservations("anchor", left["anchor"])[0].Summary
|
||||
asked := answers{leftOut: left}
|
||||
if asked.well() {
|
||||
t.Fatal("a mesh with a module assigned and not applied is called well")
|
||||
}
|
||||
shown := printed(t, func() error { return printStatus(asked) })
|
||||
if !strings.Contains(shown, "1 module(s) assigned, not applied") || !strings.Contains(shown, "nfs-server") ||
|
||||
!strings.Contains(shown, "`settings set nfs-server '{\"shares\": …}' --node anchor` sets it") {
|
||||
t.Fatalf("status says:\n%s", shown)
|
||||
}
|
||||
if !strings.Contains(reason, left["anchor"][0].reason("anchor")) {
|
||||
t.Fatalf("status and the condition say different reasons:\n%s\n%s", shown, reason)
|
||||
}
|
||||
body, err := statusAsJSON(asked)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
var doc struct {
|
||||
NotApplied []machineNotApplied `json:"not-applied"`
|
||||
}
|
||||
if err := json.Unmarshal(body, &doc); err != nil || len(doc.NotApplied) != 1 ||
|
||||
doc.NotApplied[0].Setting != "shares" || doc.NotApplied[0].Node != "anchor" {
|
||||
t.Fatalf("status --json: %v %s", err, body)
|
||||
}
|
||||
lines := strings.Join(notAppliedLines("anchor", left["anchor"]), "\n")
|
||||
if !strings.Contains(lines, "assigned, not applied:") || !strings.Contains(lines, "nfs-server") ||
|
||||
!strings.Contains(lines, `nothing sets its setting "shares"`) {
|
||||
t.Fatalf("node show says:\n%s", lines)
|
||||
}
|
||||
}
|
||||
|
||||
// The skip is this probe's alone (review of #223): a part waiting for the operator (ADR 0283) keeps its own
|
||||
// needs-operator condition, `module.<m>.<node>.needs-operator`, which still clears on the first statement that no
|
||||
// longer names it — beside a left-out condition on the same machine, which stays.
|
||||
func TestAWaitsNeedsOperatorStillClearsWhenItsStatementStopsNamingItBesideALeftOutOne(t *testing.T) {
|
||||
store := conditions.NewInMemory()
|
||||
k := conditions.NewKeeper(t.Context(), conditions.Options{Store: store, History: store})
|
||||
defer k.Close(context.Background())
|
||||
left := leftOutObservations("anchor", leftOutOf(leftOutNFS(t), nil, false))
|
||||
if err := k.Reconcile(t.Context(), probeLeftOutID, left); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
waiting := map[string][]inventory.ResourceHealth{"notes": {{Module: "notes", Resource: "server", State: link.StateWaiting,
|
||||
Waits: []inventory.Wait{{Setting: "domain", What: "the domain it serves"}}}}}
|
||||
if err := judgeModuleHealth(t.Context(), nil, k, "anchor", waiting, map[string]int{"notes": 2}, time.Now()); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
waitKey, leftKey := needsOperatorKey("notes", "anchor"), "module.nfs-server.anchor.left-out"
|
||||
open := func() map[string]conditions.Condition {
|
||||
t.Helper()
|
||||
list, err := k.Open(t.Context())
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
out := map[string]conditions.Condition{}
|
||||
for _, c := range list {
|
||||
out[c.Key] = c
|
||||
}
|
||||
return out
|
||||
}
|
||||
if c, raised := open()[waitKey]; !raised || c.Kind != kindNeedsOperator {
|
||||
t.Fatalf("the wait raised %+v", open())
|
||||
}
|
||||
if c := open()[leftKey]; c.Kind != kindNeedsOperator {
|
||||
t.Fatalf("the left-out condition is not open as needs-operator: %+v", open())
|
||||
}
|
||||
// D1 runs again and still finds nfs-server left out: its reconcile clears only what D1 raised, never the wait,
|
||||
// which the machine's statement raised.
|
||||
if err := k.Reconcile(t.Context(), probeLeftOutID, left); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if _, still := open()[waitKey]; !still {
|
||||
t.Fatalf("D1's reconcile cleared the wait's needs-operator: %+v", open())
|
||||
}
|
||||
if err := judgeModuleHealth(t.Context(), nil, k, "anchor", map[string][]inventory.ResourceHealth{}, nil, time.Now()); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if _, still := open()[waitKey]; still {
|
||||
t.Fatalf("the statement no longer names the wait, and its needs-operator is still open: %+v", open())
|
||||
}
|
||||
if _, still := open()[leftKey]; !still {
|
||||
t.Fatalf("the left-out condition was cleared by a health statement: %+v", open())
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,398 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/catalogue"
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
)
|
||||
|
||||
// The tests of novox/hq issue 525's window skip: a merge waits for the merge window only when a batch assembling
|
||||
// holds a merge related to it, or its delivery group may have a member still to merge (ADR 0304 decision 1, ADR
|
||||
// 0306 decisions 2 and 3). Walks stay one at a time.
|
||||
|
||||
// A merge from no head that shares nothing, with no walk open, is cut into its walk when it is heard: no window.
|
||||
func TestALoneMergeSharingNothingIsCutAtOnce(t *testing.T) {
|
||||
open := windowed(t)
|
||||
asksWithPaths(t)
|
||||
hear(t, open, lone(repoMerge("one", "c1", t0)), t0)
|
||||
ws, bs := walks(t, open)
|
||||
if len(ws) != 1 || len(bs) != 0 || !ws[0].Open() || ws[0].Commit != "c1" {
|
||||
t.Fatalf("a lone merge sharing nothing: %d walk(s) %+v, %d batch(es)", len(ws), ws, len(bs))
|
||||
}
|
||||
if ws[0].Times == nil || ws[0].Times.WindowClosed == nil || !ws[0].Times.WindowClosed.Equal(t0) {
|
||||
t.Fatalf("its window closed at %+v; want when it was heard, %s", ws[0].Times, t0)
|
||||
}
|
||||
}
|
||||
|
||||
// A merge related to the batch assembling joins it and waits for the window, which its coming restarts: by its
|
||||
// repository, by a module in common (a dependent of what the batch moves), by an edge of the module graph between
|
||||
// their modules (one that widens nothing), or by its delivery group's head.
|
||||
func TestARelatedMergeJoinsTheBatchAndWaitsForTheWindow(t *testing.T) {
|
||||
ctx := t.Context()
|
||||
for _, c := range []string{"same repository", "a module in common", "an edge of the graph", "the same group head"} {
|
||||
t.Run(c, func(t *testing.T) {
|
||||
open := windowed(t)
|
||||
groupsWaiting(t, "pr/c1")
|
||||
asksWithPaths(t)
|
||||
inv := open.inventory
|
||||
first := repoMerge("one", "c1", t0)
|
||||
second := lone(repoMerge("two", "c2", t0.Add(10*time.Second)))
|
||||
why := map[string]string{"same repository": "both change novox/one", "a module in common": "both move two",
|
||||
"an edge of the graph": "two depends on builder (built-by)",
|
||||
"the same group head": "both are members of group " + first.Head}[c]
|
||||
switch c {
|
||||
case "same repository":
|
||||
second = lone(repoMerge("one", "c2", t0.Add(10*time.Second)))
|
||||
case "a module in common":
|
||||
// two is built on one: a merge of one moves two too.
|
||||
if err := inv.RegisterModule(ctx, catalogue.Manifest{Module: "two", Version: "1",
|
||||
Build: &catalogue.Build{On: []catalogue.BuildsOn{{Arg: "BASE", Module: "one"}}}},
|
||||
inventory.Source{Repository: "novox/two", Seat: "git", Ref: "main", BuiltFrom: "c0", Head: "c0"}); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
case "an edge of the graph":
|
||||
// two is built by the build machine: an edge that orders and widens nothing.
|
||||
if err := inv.RegisterModule(ctx, catalogue.Manifest{Module: "builder", Version: "1",
|
||||
Claims: []catalogue.Claim{{Name: "mesh-build-machine", Scope: catalogue.ScopeMesh}}},
|
||||
inventory.Source{Repository: "novox/builder", Seat: "git", Ref: "main", BuiltFrom: "c0", Head: "c0"}); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
first = repoMerge("builder", "c1", t0)
|
||||
case "the same group head":
|
||||
second = fromHead(repoMerge("two", "c2", t0.Add(10*time.Second)), first.Head)
|
||||
}
|
||||
hear(t, open, first, t0)
|
||||
said := captured(t, func() error {
|
||||
return (following{open: open}).hearMerge(ctx, second, t0.Add(10*time.Second))
|
||||
})
|
||||
if !strings.Contains(said, "("+why+")") {
|
||||
t.Fatalf("the merge was not said related by %q: %s", why, said)
|
||||
}
|
||||
ws, bs := walks(t, open)
|
||||
if len(ws) != 0 || len(bs) != 1 || len(bs[0].Delivery.Merges) != 2 {
|
||||
t.Fatalf("the related merge: %d walk(s), batches %+v", len(ws), bs)
|
||||
}
|
||||
if bs[0].Delivery.Batch.CutAtOnce {
|
||||
t.Fatal("a batch a related merge joined is cut at once")
|
||||
}
|
||||
cutAt(t, open, t0.Add(99*time.Second))
|
||||
if ws, _ := walks(t, open); len(ws) != 0 {
|
||||
t.Fatalf("cut before the window the related merge restarted closed: %+v", ws)
|
||||
}
|
||||
cutAt(t, open, t0.Add(100*time.Second))
|
||||
ws, bs = walks(t, open)
|
||||
if len(ws) != 1 || len(bs) != 0 || len(ws[0].Delivery.Merges) != 2 {
|
||||
t.Fatalf("after the window: %d walk(s), %d batch(es)", len(ws), len(bs))
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// A merge from a head whose delivery group has a member still to merge waits for the window, even with no batch
|
||||
// assembling, and says why; its sibling joins the same batch by their head (ADR 0306 decision 2). A merge from a
|
||||
// head that names no group shares nothing and is cut at once, as one from no head is.
|
||||
func TestAMergeOfAGroupWaitsEvenAlone(t *testing.T) {
|
||||
open := windowed(t)
|
||||
asksWithPaths(t)
|
||||
groupsWaiting(t, "feat/x")
|
||||
hear(t, open, fromHead(repoMerge("one", "c1", t0), "feat/x"), t0)
|
||||
ws, bs := walks(t, open)
|
||||
if len(ws) != 0 || len(bs) != 1 || bs[0].Delivery.Batch.CutAtOnce || windowClosed(bs[0], t0) {
|
||||
t.Fatalf("a group's merge alone: %d walk(s), batches %+v", len(ws), bs)
|
||||
}
|
||||
if words := batchWords(bs[0], t0); !strings.HasPrefix(words, "assembling: 90 s left") ||
|
||||
!strings.Contains(words, "group feat/x has a member still to merge: novox/elsewhere (ready)") {
|
||||
t.Fatalf("it reads %q", words)
|
||||
}
|
||||
hear(t, open, fromHead(repoMerge("two", "c2", t0.Add(5*time.Second)), "feat/x"), t0.Add(5*time.Second))
|
||||
if _, bs := walks(t, open); len(bs) != 1 || len(bs[0].Delivery.Merges) != 2 {
|
||||
t.Fatalf("the group's second member did not join the first: %+v", bs)
|
||||
}
|
||||
cutAt(t, open, t0.Add(94*time.Second))
|
||||
if ws, _ := walks(t, open); len(ws) != 0 {
|
||||
t.Fatalf("cut before its window closed: %+v", ws)
|
||||
}
|
||||
cutAt(t, open, t0.Add(95*time.Second))
|
||||
ws, bs = walks(t, open)
|
||||
if len(ws) != 1 || len(bs) != 0 || ws[0].CommitOf("novox/one") != "c1" || ws[0].CommitOf("novox/two") != "c2" {
|
||||
t.Fatalf("at its window: %d walk(s) %+v, %d batch(es)", len(ws), ws, len(bs))
|
||||
}
|
||||
}
|
||||
|
||||
// A merge from a head that names no group, sharing nothing, with no walk open, is cut at once.
|
||||
func TestAHeadedMergeInNoGroupIsCutAtOnce(t *testing.T) {
|
||||
open := windowed(t)
|
||||
asksWithPaths(t)
|
||||
hear(t, open, fromHead(repoMerge("one", "c1", t0), "fix/alone"), t0)
|
||||
if ws, bs := walks(t, open); len(ws) != 1 || len(bs) != 0 || !ws[0].Open() {
|
||||
t.Fatalf("a headed merge in no group: %d walk(s), %d batch(es)", len(ws), len(bs))
|
||||
}
|
||||
}
|
||||
|
||||
// When mesh-delivery cannot say a head's group, the merge waits for the window, the safe side, and its batch says
|
||||
// why.
|
||||
func TestAGroupNobodyCanSayWaits(t *testing.T) {
|
||||
open := windowed(t)
|
||||
asksWithPaths(t)
|
||||
was := deliveryGroupOf
|
||||
deliveryGroupOf = func(context.Context, bool, string) ([]groupMember, bool, error) {
|
||||
return nil, false, errors.New("nothing serves mesh-delivery.groups")
|
||||
}
|
||||
t.Cleanup(func() { deliveryGroupOf = was })
|
||||
hear(t, open, fromHead(repoMerge("one", "c1", t0), "feat/x"), t0)
|
||||
ws, bs := walks(t, open)
|
||||
if len(ws) != 0 || len(bs) != 1 || bs[0].Delivery.Batch.CutAtOnce {
|
||||
t.Fatalf("a merge whose group nobody could say: %d walk(s), batches %+v", len(ws), bs)
|
||||
}
|
||||
if words := batchWords(bs[0], t0); !strings.Contains(words, "mesh-delivery did not say whether group feat/x has a "+
|
||||
"member still to merge (nothing serves mesh-delivery.groups): it waits for the window, the safe side") {
|
||||
t.Fatalf("it reads %q", words)
|
||||
}
|
||||
}
|
||||
|
||||
// A member counts as still to merge only while its pull request is open, and not once this controller keeps its
|
||||
// merge: a group whose other members are merged or closed makes nobody wait.
|
||||
func TestAGroupsMergedOrClosedMembersMakeNobodyWait(t *testing.T) {
|
||||
open := windowed(t)
|
||||
asksWithPaths(t)
|
||||
ctx := t.Context()
|
||||
members := []groupMember{{Repository: "novox/one", State: "ready"}, {Repository: "novox/two", State: "published"},
|
||||
{Repository: "novox/three", State: "stopped"}}
|
||||
was := deliveryGroupOf
|
||||
deliveryGroupOf = func(context.Context, bool, string) ([]groupMember, bool, error) { return members, true, nil }
|
||||
t.Cleanup(func() { deliveryGroupOf = was })
|
||||
m := fromHead(repoMerge("one", "c1", t0), "feat/x")
|
||||
if why, err := groupWait(ctx, open.inventory, m, true, false); err != nil || why != "" {
|
||||
t.Fatalf("the group's other members are merged or closed, yet: %q %v", why, err)
|
||||
}
|
||||
members = append(members, groupMember{Repository: "novox/four", State: "checked"})
|
||||
if why, _ := groupWait(ctx, open.inventory, m, true, false); !strings.Contains(why, "novox/four (checked)") {
|
||||
t.Fatalf("an open member: %q", why)
|
||||
}
|
||||
// novox/four's merge is kept in a batch already: merged, whatever mesh-delivery says yet.
|
||||
hear(t, open, fromHead(repoMerge("two", "c4", t0), "feat/x"), t0)
|
||||
members[3].Repository = "novox/two"
|
||||
if why, _ := groupWait(ctx, open.inventory, m, true, false); why != "" {
|
||||
t.Fatalf("a member this controller keeps the merge of still waits: %q", why)
|
||||
}
|
||||
if got := memberOf("novox/mesh-sdk@d41d255f28ad (held)"); got != (groupMember{Repository: "novox/mesh-sdk", State: "held"}) {
|
||||
t.Fatalf("a member reads %+v", got)
|
||||
}
|
||||
}
|
||||
|
||||
// A merge related to two batches assembling folds the newer into the older, which answers every merge of both
|
||||
// and names nothing twice; the folded one names the batch that took it over.
|
||||
func TestAMergeRelatedToTwoBatchesFoldsThem(t *testing.T) {
|
||||
open := windowed(t)
|
||||
groupsWaiting(t, "feat/a", "feat/b")
|
||||
asksWithPaths(t)
|
||||
ctx := t.Context()
|
||||
hear(t, open, fromHead(repoMerge("one", "c1", t0), "feat/a"), t0)
|
||||
hear(t, open, fromHead(repoMerge("two", "c2", t0.Add(5*time.Second)), "feat/b"), t0.Add(5*time.Second))
|
||||
_, bs := walks(t, open)
|
||||
if len(bs) != 2 {
|
||||
t.Fatalf("two merges sharing nothing: %d batch(es)", len(bs))
|
||||
}
|
||||
older, newer := bs[1], bs[0] // newest first
|
||||
// Of one's repository and from two's head: related to both.
|
||||
hear(t, open, fromHead(repoMerge("one", "c3", t0.Add(10*time.Second)), "feat/b"), t0.Add(10*time.Second))
|
||||
_, bs = walks(t, open)
|
||||
if len(bs) != 1 || bs[0].ID != older.ID || len(bs[0].Delivery.Merges) != 3 {
|
||||
t.Fatalf("after a merge related to both: batches %+v; want %s answering three merges", bs, older.ID)
|
||||
}
|
||||
folded, err := open.inventory.PlanByID(ctx, newer.ID)
|
||||
if err != nil || folded.State != inventory.PlanSuperseded || folded.Delivery == nil ||
|
||||
folded.Delivery.TakenOverBy != older.ID {
|
||||
t.Fatalf("the newer batch reads %s %+v (%v)", folded.State, folded.Delivery, err)
|
||||
}
|
||||
if left, _ := open.inventory.MergesOf(ctx, newer.ID); len(left) != 0 {
|
||||
t.Fatalf("the folded batch still answers %+v", left)
|
||||
}
|
||||
cutAt(t, open, t0.Add(100*time.Second))
|
||||
ws, bs := walks(t, open)
|
||||
var cut []inventory.Plan
|
||||
for _, w := range ws {
|
||||
if w.State != inventory.PlanSuperseded {
|
||||
cut = append(cut, w)
|
||||
}
|
||||
}
|
||||
if len(cut) != 1 || len(bs) != 0 || cut[0].ID != older.ID || cut[0].CommitOf("novox/one") != "c3" ||
|
||||
cut[0].CommitOf("novox/two") != "c2" {
|
||||
t.Fatalf("the folded batch's walk: %+v, %d batch(es)", cut, len(bs))
|
||||
}
|
||||
}
|
||||
|
||||
// With a walk open, a batch cut at once still waits for it, said queued behind it (walks stay one at a time, ADR
|
||||
// 0276 decision 4); it is cut once that walk ended, with no window to wait for.
|
||||
func TestACutAtOnceBatchQueuesBehindAnOpenWalk(t *testing.T) {
|
||||
open := windowed(t)
|
||||
groupsWaiting(t, "pr/c1")
|
||||
asksWithPaths(t)
|
||||
hear(t, open, repoMerge("one", "c1", t0), t0)
|
||||
cutAt(t, open, t0.Add(90*time.Second))
|
||||
ws, _ := walks(t, open)
|
||||
if len(ws) != 1 || !ws[0].Open() {
|
||||
t.Fatalf("no walk open: %+v", ws)
|
||||
}
|
||||
first := ws[0]
|
||||
heard := t0.Add(100 * time.Second)
|
||||
hear(t, open, lone(repoMerge("two", "c2", heard)), heard)
|
||||
ws, bs := walks(t, open)
|
||||
if len(ws) != 1 || len(bs) != 1 || bs[0].State != inventory.PlanQueued || bs[0].Delivery.Batch.Behind != first.ID ||
|
||||
!bs[0].Delivery.Batch.CutAtOnce {
|
||||
t.Fatalf("a lone merge during a walk: %d walk(s), batches %+v", len(ws), bs)
|
||||
}
|
||||
if !strings.HasPrefix(batchWords(bs[0], heard), "queued behind "+first.ID) {
|
||||
t.Fatalf("it reads %q", batchWords(bs[0], heard))
|
||||
}
|
||||
first.State = inventory.PlanDone
|
||||
if err := open.inventory.SavePlan(t.Context(), &first); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
cutAt(t, open, heard.Add(time.Second))
|
||||
ws, bs = walks(t, open)
|
||||
if len(ws) != 2 || len(bs) != 0 || ws[0].Commit != "c2" {
|
||||
t.Fatalf("the queued batch was not cut once the walk ended: %+v %+v", ws, bs)
|
||||
}
|
||||
if ws[0].Times == nil || ws[0].Times.WindowClosed == nil || !ws[0].Times.WindowClosed.Equal(heard) {
|
||||
t.Fatalf("its window closed at %+v; want when its merge was heard, %s", ws[0].Times, heard)
|
||||
}
|
||||
}
|
||||
|
||||
// A stopped walk's other merges are walked again in a batch they are related to, and a batch of their own when
|
||||
// they share nothing with the one assembling (ADR 0299, ADR 0304 decision 1): never in a batch of another
|
||||
// change, whose window the stop would close.
|
||||
func TestAStopWalksTheOthersAgainInABatchOfTheirOwnWhenTheyShareNothing(t *testing.T) {
|
||||
open := windowed(t)
|
||||
groupsWaiting(t, "pr/cat1aaaaaaaa")
|
||||
endsItsLine(t)
|
||||
asksRecorded(t)
|
||||
ctx := t.Context()
|
||||
cat := catalogueMerge("cat1aaaaaaaa", "app", t0)
|
||||
one := fromHead(repoMerge("one", "one1bbbbbbbb", t0.Add(5*time.Second)), cat.Head)
|
||||
hear(t, open, cat, t0.Add(time.Second))
|
||||
hear(t, open, one, t0.Add(6*time.Second))
|
||||
cutAt(t, open, t0.Add(2*time.Minute))
|
||||
ws, _ := walks(t, open)
|
||||
walk := ws[0]
|
||||
hear(t, open, repoMerge("two", "two1cccccccc", t0.Add(3*time.Minute)), t0.Add(3*time.Minute))
|
||||
_, bs := walks(t, open)
|
||||
if len(bs) != 1 {
|
||||
t.Fatalf("the merge heard while the walk ran is in %d batches", len(bs))
|
||||
}
|
||||
other := bs[0]
|
||||
_, said, err := stopWalkWithout(ctx, open.inventory, walk.ID, "mesh-delivery for jochen", "its group stopped",
|
||||
[]string{"novox/mesh-catalog@" + cat.Commit}, t0.Add(3*time.Minute+10*time.Second))
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if said.WalkedAgainBy == "" || said.WalkedAgainBy == other.ID {
|
||||
t.Fatalf("walked again by %q; want a batch of its own, not %s", said.WalkedAgainBy, other.ID)
|
||||
}
|
||||
b, _ := open.inventory.PlanByID(ctx, other.ID)
|
||||
if b.Delivery.Batch == nil || b.Delivery.Batch.Closed || len(b.Delivery.Merges) != 1 {
|
||||
t.Fatalf("the other change's batch reads %+v; want it untouched by the stop", b.Delivery)
|
||||
}
|
||||
}
|
||||
|
||||
// A catalogue batch's cut folds in every walk waiting for its delivery's word (cutBatch's carry), so what that
|
||||
// walk moves is the batch's too: a lone merge related to the waiting walk joins the batch assembling and waits for
|
||||
// its window, rather than being cut at once as sharing nothing with what the batch's own merges move.
|
||||
func TestALoneMergeRelatedToAWalkTheCutFoldsJoinsTheBatch(t *testing.T) {
|
||||
open := windowed(t)
|
||||
groupsWaiting(t, "pr/c3")
|
||||
asksWithPaths(t)
|
||||
ctx := t.Context()
|
||||
if err := open.inventory.RegisterModule(ctx, catalogue.Manifest{Module: "mesh-delivery", Version: "1",
|
||||
Claims: []catalogue.Claim{{Name: catalogue.DeliverySeat, Scope: catalogue.ScopeMesh}}},
|
||||
inventory.Source{Repository: "novox/mesh-catalog", Seat: "git", Path: "modules/mesh-delivery", Ref: "main",
|
||||
BuiltFrom: "c0", Head: "c0"}); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if _, err := open.inventory.Assign(ctx, "anchor", "mesh-delivery"); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
hear(t, open, repoMerge("one", "c1", t0), t0)
|
||||
cutAt(t, open, t0.Add(90*time.Second))
|
||||
if ws, _ := walks(t, open); len(ws) != 1 || !ws[0].Waiting() {
|
||||
t.Fatalf("the walk does not wait for its word: %+v", ws)
|
||||
}
|
||||
hear(t, open, repoMerge("three", "c3", t0.Add(2*time.Minute)), t0.Add(2*time.Minute))
|
||||
hear(t, open, lone(repoMerge("one", "c2", t0.Add(2*time.Minute+5*time.Second))), t0.Add(2*time.Minute+5*time.Second))
|
||||
_, bs := walks(t, open)
|
||||
if len(bs) != 1 || len(bs[0].Delivery.Merges) != 2 || bs[0].Delivery.Batch.CutAtOnce {
|
||||
t.Fatalf("a lone merge related to the waiting walk: batches %+v", bs)
|
||||
}
|
||||
}
|
||||
|
||||
// A delivery group with a member of each kind (review of #250): a merge on the controller's own path and a
|
||||
// catalogue merge never share a batch, so the later member cannot join the earlier one's. Kept in a batch of the
|
||||
// other kind, the earlier member keeps the later one waiting, whatever mesh-delivery says yet — never cut at once
|
||||
// to walk before it. The two batches are then cut in the order their windows close (cutBatchesHeld: the oldest
|
||||
// closed batch first, an own-path one first at one look, and the other queued behind a walk that started): the
|
||||
// earlier member's window closes first, so it walks first, in both orders.
|
||||
func TestAGroupAcrossBothKindsKeepsItsOrder(t *testing.T) {
|
||||
for _, ownFirst := range []bool{true, false} {
|
||||
name := "catalogue member first"
|
||||
if ownFirst {
|
||||
name = "controller member first"
|
||||
}
|
||||
t.Run(name, func(t *testing.T) {
|
||||
open := windowed(t)
|
||||
asksWithPaths(t)
|
||||
ctx := t.Context()
|
||||
was := deliveryGroupOf
|
||||
// mesh-delivery still says both members ready: it marks one merged only once its walk opened.
|
||||
deliveryGroupOf = func(context.Context, bool, string) ([]groupMember, bool, error) {
|
||||
return []groupMember{{Repository: "novox/mesh-controller", State: "ready"},
|
||||
{Repository: "novox/mesh-catalog", State: "ready"}}, true, nil
|
||||
}
|
||||
t.Cleanup(func() { deliveryGroupOf = was })
|
||||
own := fromHead(repoMerge("mesh-controller", "k1", t0), "feat/both-kinds")
|
||||
cat := fromHead(catalogueMerge("cat1aaaaaaaa", "app", t0), "feat/both-kinds")
|
||||
first, second := cat, own
|
||||
if ownFirst {
|
||||
first, second = own, cat
|
||||
}
|
||||
second.MergedAt = t0.Add(10 * time.Second).Format(time.RFC3339Nano)
|
||||
hear(t, open, first, t0)
|
||||
hear(t, open, second, t0.Add(10*time.Second))
|
||||
ws, bs := walks(t, open)
|
||||
if len(ws) != 0 || len(bs) != 2 {
|
||||
t.Fatalf("both members heard: %d walk(s), %d batch(es); want two batches, nothing cut", len(ws), len(bs))
|
||||
}
|
||||
later := bs[0] // newest first
|
||||
if later.Delivery.Batch.CutAtOnce || !strings.Contains(later.Delivery.Batch.Waits,
|
||||
"has a member waiting in a batch of the other kind: novox/"+first.Repo+"@") {
|
||||
t.Fatalf("the later member's batch reads %+v; want it waiting for the earlier member", later.Delivery.Batch)
|
||||
}
|
||||
// The earlier member's window closes first: its batch alone is cut.
|
||||
cutAt(t, open, t0.Add(90*time.Second))
|
||||
ws, bs = walks(t, open)
|
||||
if len(ws) != 1 || !ws[0].Open() || ws[0].CommitOf("novox/"+first.Repo) != first.Commit || len(bs) != 1 ||
|
||||
bs[0].ID != later.ID {
|
||||
t.Fatalf("at the earlier window: walks %+v, batches %+v; want the earlier member alone cut", ws, bs)
|
||||
}
|
||||
earlier := ws[0]
|
||||
// The later member's window closes while the earlier walk runs: it queues behind it.
|
||||
cutAt(t, open, t0.Add(100*time.Second))
|
||||
if _, bs := walks(t, open); len(bs) != 1 || bs[0].State != inventory.PlanQueued || bs[0].Delivery.Batch.Behind != earlier.ID {
|
||||
t.Fatalf("the later member's batch does not queue behind the earlier walk: %+v", bs)
|
||||
}
|
||||
earlier.State = inventory.PlanDone
|
||||
if err := open.inventory.SavePlan(ctx, &earlier); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
cutAt(t, open, t0.Add(101*time.Second))
|
||||
got, err := open.inventory.PlanByID(ctx, later.ID)
|
||||
if err != nil || got.Batch() || got.CommitOf("novox/"+second.Repo) != second.Commit {
|
||||
t.Fatalf("the later member was not walked after the earlier: %s %v", got.State, err)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
@@ -63,6 +63,15 @@ func run() error {
|
||||
// 45 §6), so the next controller takes it at once rather than after its age.
|
||||
defer theLease.release()
|
||||
|
||||
// Every walk a verb keeps is said on the bus, whichever verb kept it (novox/hq ADR 0308 decision 1): the save
|
||||
// that starts or ends a walk keeps its mark, and no later save says it again. The serving controller says its
|
||||
// own saves.
|
||||
if args[0] != "serve" {
|
||||
said, done := sayingWhatAVerbKept(ctx)
|
||||
inventory.PlanSaved = said
|
||||
defer done()
|
||||
}
|
||||
|
||||
switch args[0] {
|
||||
case "build":
|
||||
return buildCommand(ctx, args[1:])
|
||||
@@ -311,7 +320,7 @@ func usage() {
|
||||
the self-check: the last verdict, a run now, the probes, the signals' ages
|
||||
healers [--days N] [--json] the healers, what they did lately, and their brake (to-be 45 §7)
|
||||
durations [--kind K] [--days N] [--json]
|
||||
apply, heartbeat, plan-tier and build durations, per machine or module
|
||||
apply, heartbeat, plan-tier, build and walk-phase durations
|
||||
collection [--json] kept archives held/unheld by a manifest, and what the sweep may let go
|
||||
builder issue <name> a broker account for a build machine, scoped to build work,
|
||||
delivered as the builder module's broker secret (module add it first)
|
||||
|
||||
@@ -390,9 +390,10 @@ func TestAWithheldPathIsStoodInForByAPath(t *testing.T) {
|
||||
// controller's ask and by the facts — and finds the repository it checks from its origin.
|
||||
func TestACheckByHandClonesWhatTheSeatClones(t *testing.T) {
|
||||
for dir, refs := range map[string]map[string]string{
|
||||
"mesh-catalog": {"mesh-catalog": "main"},
|
||||
"mesh-host": {"mesh-host": "c0ffee"},
|
||||
"mesh-controller": {"mesh-controller": "c0ffee", "mesh-controller-main": "main", "mesh-lab": "main"},
|
||||
"mesh-catalog": {"mesh-catalog": "main"},
|
||||
"mesh-host": {"mesh-host": "c0ffee"},
|
||||
"mesh-controller": {"mesh-controller": "c0ffee", "mesh-controller-main": "main", "mesh-lab": "main",
|
||||
"mesh-sdk": sdkPinnedByGoMod(t)},
|
||||
} {
|
||||
got := besideRefs(dir, "c0ffee")
|
||||
for d, ref := range refs {
|
||||
@@ -412,3 +413,24 @@ func TestACheckByHandClonesWhatTheSeatClones(t *testing.T) {
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// sdkPinnedByGoMod is the SDK commit this tree's go.mod pins, read from the file rather than the build, so
|
||||
// sdkPinned is held to what the repository says (novox/hq issue 449).
|
||||
func sdkPinnedByGoMod(t *testing.T) string {
|
||||
t.Helper()
|
||||
raw, err := os.ReadFile(filepath.Join("..", "..", "go.mod"))
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
for _, line := range strings.Split(string(raw), "\n") {
|
||||
fields := strings.Fields(line)
|
||||
if len(fields) >= 2 && fields[0] == sdkModule {
|
||||
if m := pseudoCommit.FindStringSubmatch(fields[1]); m != nil {
|
||||
return m[1]
|
||||
}
|
||||
return "go/" + fields[1]
|
||||
}
|
||||
}
|
||||
t.Fatalf("go.mod requires no %s", sdkModule)
|
||||
return ""
|
||||
}
|
||||
|
||||
@@ -74,9 +74,21 @@ func stateHealth(ctx context.Context, inv *inventory.Inventory, k *conditions.Ke
|
||||
kept := inventory.ResourceHealth{Module: r.Module, Resource: r.Resource, Kind: r.Kind, Target: r.Target,
|
||||
State: r.State, Reason: r.Reason, Since: r.Since, Streak: r.Streak, Restarts: r.Restarts,
|
||||
Check: r.Check, Needs: r.Needs, Account: r.Account, Root: r.Root}
|
||||
for _, w := range r.Waits {
|
||||
kept.Waits = append(kept.Waits, inventory.Wait{Part: w.Part, Secret: w.Secret, Setting: w.Setting, What: w.What})
|
||||
}
|
||||
resources = append(resources, kept)
|
||||
if r.State == link.StateUnhealthy && r.Module != "" {
|
||||
unhealthy[r.Module] = append(unhealthy[r.Module], kept)
|
||||
}
|
||||
// **A wait for the operator is checked before it is excused** (novox/hq ADR 0283): a waiting resource whose
|
||||
// wait does not check out is judged unhealthy, saying why; one that does is kept beside the unhealthy ones, so
|
||||
// judgeModuleHealth can say it as needs-operator. What is stored is what the machine said.
|
||||
var wf operatorWaitFacts
|
||||
if mods := waitingModules(resources); len(mods) > 0 {
|
||||
readWaitFacts(ctx, inv, node, mods, nil, &wf)
|
||||
}
|
||||
for _, r := range checkWaiting(node, resources, wf) {
|
||||
if (r.State == link.StateUnhealthy || r.State == link.StateWaiting) && r.Module != "" {
|
||||
unhealthy[r.Module] = append(unhealthy[r.Module], r)
|
||||
}
|
||||
}
|
||||
streaks := map[string]int{}
|
||||
@@ -135,16 +147,17 @@ func judgeModuleHealth(ctx context.Context, inv *inventory.Inventory, k *conditi
|
||||
}
|
||||
standing := map[string]conditions.Condition{}
|
||||
for _, c := range open {
|
||||
if (c.Kind == kindModuleUnhealthy || c.Kind == kindReloginNeeded || c.Kind == kindUsedAsFound) &&
|
||||
c.Subject.Machine == node {
|
||||
// A module left out of the composition is the self-check's to raise and clear, never a statement's
|
||||
// (novox/hq issue 380): its needs-operator is not cleared for not being in what the machine runs.
|
||||
if (c.Kind == kindModuleUnhealthy || c.Kind == kindReloginNeeded || c.Kind == kindUsedAsFound ||
|
||||
c.Kind == kindNeedsOperator) &&
|
||||
c.Subject.Machine == node && !isLeftOutCondition(c) {
|
||||
standing[c.Key] = c
|
||||
}
|
||||
}
|
||||
var hold *holding
|
||||
if inv != nil {
|
||||
if hold, err = readHolding(ctx, inv, open); err != nil {
|
||||
return err
|
||||
}
|
||||
hold, err := readHoldingFor(ctx, inv, open)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
var problems []string
|
||||
modules := make([]string, 0, len(unhealthy))
|
||||
@@ -159,6 +172,39 @@ func judgeModuleHealth(ctx context.Context, inv *inventory.Inventory, k *conditi
|
||||
heldOn := map[string]string{}
|
||||
providers := map[catalogue.Chosen]bool{}
|
||||
for _, m := range modules {
|
||||
// **A part that waits for the operator is said as that** (novox/hq ADR 0283): its waits already checked,
|
||||
// the operator's, never urgent, its words naming the act.
|
||||
if waits, waiting := operatorWait(m, unhealthy[m]); waiting {
|
||||
o := needsOperatorObservation(m, node, waits, unhealthy[m])
|
||||
// **A provider waiting for the operator says who waits on it** (novox/hq issue 405), as one waiting for a
|
||||
// login does: its consumers are held under it.
|
||||
if hold != nil {
|
||||
sayWaitingOn(&o, hold.waitersOn(catalogue.Chosen{Node: node, Module: m}))
|
||||
}
|
||||
seen[o.Key()] = true
|
||||
became[m] = kindNeedsOperator
|
||||
if _, isOpen := standing[o.Key()]; streaks[m] < moduleUnhealthyAfter && !isOpen {
|
||||
continue
|
||||
}
|
||||
if _, err := k.Observe(ctx, o); err != nil {
|
||||
problems = append(problems, err.Error())
|
||||
}
|
||||
continue
|
||||
}
|
||||
// **A wait for the operator beside anything else is said too** (novox/hq issue 405): a module with a checked
|
||||
// wait beside a new login owed, a directory used as found or a fault of its own is said as that, and the
|
||||
// operator's secret or setting it waits for was not mentioned until the other cleared. Its needs-operator
|
||||
// condition stands beside the other, on the same looks; what follows judges the rest without the wait.
|
||||
if waits, rest := besideAWait(m, unhealthy[m]); len(waits) > 0 {
|
||||
o := needsOperatorObservation(m, node, waits, waitingOf(m, unhealthy[m]))
|
||||
seen[o.Key()] = true
|
||||
if _, isOpen := standing[o.Key()]; streaks[m] >= moduleUnhealthyAfter || isOpen {
|
||||
if _, err := k.Observe(ctx, o); err != nil {
|
||||
problems = append(problems, err.Error())
|
||||
}
|
||||
}
|
||||
unhealthy[m] = rest
|
||||
}
|
||||
// **A directory used as found is said as that** (novox/hq issue 339): the operator's to hand over at the
|
||||
// machine, never urgent — nothing is broken by the wait that a person was not told of — and its own kind,
|
||||
// so the gate never reads it as a fault of the build that happened to be sent beside it.
|
||||
@@ -195,13 +241,24 @@ func judgeModuleHealth(ctx context.Context, inv *inventory.Inventory, k *conditi
|
||||
}
|
||||
o := moduleUnhealthyObservation(m, node, unhealthy[m])
|
||||
if hold != nil {
|
||||
if p, held := hold.heldUnder(node, m, unhealthy[m]); held {
|
||||
// Held under the provider's condition: nothing of its own, and the provider's says it waits.
|
||||
heldOn[o.Key()] = p.Module + " on " + p.Node
|
||||
if by, held := hold.heldWith(node, m, unhealthy[m]); held {
|
||||
// Held under the provider's condition: nothing of its own, and the provider's says it waits. The
|
||||
// clearing line says which the provider is: unhealthy, or waiting for the operator (issue 405).
|
||||
p := by.provider
|
||||
heldOn[o.Key()] = p.Module + " on " + p.Node + ", which is unhealthy"
|
||||
if len(by.waits) > 0 {
|
||||
heldOn[o.Key()] = p.Module + " on " + p.Node + ", which waits for you"
|
||||
}
|
||||
providers[p] = true
|
||||
continue
|
||||
}
|
||||
sayWaitingOn(&o, hold.waitersOn(catalogue.Chosen{Node: node, Module: m}))
|
||||
// A provider that waits for the operator for a part this finding cannot be matched to does not hold it
|
||||
// (novox/hq issue 405): raised as its own, and saying the provider waits, so neither is hidden.
|
||||
if p, waiting := hold.waitingUncovered(node, m, unhealthy[m]); waiting {
|
||||
o.Said += fmt.Sprintf("; %s on %s waits for you, but not for anything %s is known to need, so %s's "+
|
||||
"fault is said on its own", p.Module, p.Node, m, m)
|
||||
}
|
||||
}
|
||||
seen[o.Key()] = true
|
||||
became[m] = kindModuleUnhealthy
|
||||
@@ -228,8 +285,11 @@ func judgeModuleHealth(ctx context.Context, inv *inventory.Inventory, k *conditi
|
||||
if c.Kind == kindUsedAsFound {
|
||||
why = fmt.Sprintf("%s says no directory of %s is used as found any more", node, module)
|
||||
}
|
||||
if c.Kind == kindNeedsOperator {
|
||||
why = fmt.Sprintf("%s says %s no longer waits for the operator", node, module)
|
||||
}
|
||||
if on, held := heldOn[key]; held {
|
||||
why = fmt.Sprintf("what %s finds on %s waits on %s, which is unhealthy: held under its condition", module, node, on)
|
||||
why = fmt.Sprintf("what %s finds on %s waits on %s: held under its condition", module, node, on)
|
||||
}
|
||||
// **A condition that became the other kind** is not "working again" (issue 318 review): its clearing
|
||||
// line says what it became.
|
||||
@@ -238,6 +298,12 @@ func judgeModuleHealth(ctx context.Context, inv *inventory.Inventory, k *conditi
|
||||
case c.Kind == kindModuleUnhealthy && became[module] == kindReloginNeeded:
|
||||
why = fmt.Sprintf("%s on %s now waits only for a new login", module, node)
|
||||
resolved = fmt.Sprintf("%s on %s now waits only for a new login", module, node)
|
||||
case c.Kind == kindModuleUnhealthy && became[module] == kindNeedsOperator:
|
||||
why = fmt.Sprintf("%s on %s now only waits for the operator", module, node)
|
||||
resolved = fmt.Sprintf("%s on %s now only waits for you", module, node)
|
||||
case c.Kind == kindNeedsOperator && became[module] == kindModuleUnhealthy:
|
||||
why = fmt.Sprintf("%s on %s no longer only waits for the operator, and is not healthy", module, node)
|
||||
resolved = fmt.Sprintf("What %s on %s waited for is given, and it still does not work", module, node)
|
||||
case c.Kind == kindReloginNeeded && became[module] == kindModuleUnhealthy:
|
||||
why = fmt.Sprintf("%s on %s no longer waits for a new login, and is not healthy", module, node)
|
||||
resolved = fmt.Sprintf("The new login on %s is done, and %s still does not work", node, module)
|
||||
@@ -262,36 +328,74 @@ func judgeModuleHealth(ctx context.Context, inv *inventory.Inventory, k *conditi
|
||||
// sayWaiters observes a provider's open condition again, with who waits on it, from its machine's newest
|
||||
// statement. Nothing when its condition is not open: it is raised by its own statements, on its own looks.
|
||||
func sayWaiters(ctx context.Context, k *conditions.Keeper, hold *holding, p catalogue.Chosen, now time.Time) error {
|
||||
var raisedAt *conditions.Condition
|
||||
for i, c := range hold.open {
|
||||
if c.Key == moduleUnhealthyKey(p.Module, p.Node) || c.Key == reloginKey(p.Module, p.Node) {
|
||||
raisedAt = &hold.open[i]
|
||||
}
|
||||
}
|
||||
if raisedAt == nil {
|
||||
return nil
|
||||
}
|
||||
// Its statement as it was judged, its waits checked (novox/hq issue 450): a wait that failed the check is
|
||||
// unhealthy, so the condition built here is the one its own statement raised, and who waits on it is listed.
|
||||
var rs []inventory.ResourceHealth
|
||||
for _, r := range hold.healths[p.Node].Resources {
|
||||
if r.Module == p.Module && r.State == link.StateUnhealthy {
|
||||
for _, r := range hold.checked(p.Node) {
|
||||
if r.Module == p.Module && (r.State == link.StateUnhealthy || r.State == link.StateWaiting) {
|
||||
rs = append(rs, r)
|
||||
}
|
||||
}
|
||||
if len(rs) == 0 {
|
||||
return nil
|
||||
}
|
||||
o := moduleUnhealthyObservation(p.Module, p.Node, rs)
|
||||
if said, waits := personWait(p.Module, p.Node, rs); waits {
|
||||
o = reloginObservation(p.Module, p.Node, said, operatorOn(ctx, hold.inv, p.Node), rs)
|
||||
// The condition its own statement says it under: needs-operator while it only waits for the operator (novox/hq
|
||||
// issue 405), else that for the rest of it, a wait beside it said on its own.
|
||||
var o conditions.Observation
|
||||
if waits, waiting := operatorWait(p.Module, rs); waiting {
|
||||
o = needsOperatorObservation(p.Module, p.Node, waits, rs)
|
||||
} else {
|
||||
_, rest := besideAWait(p.Module, rs)
|
||||
o = moduleUnhealthyObservation(p.Module, p.Node, rest)
|
||||
if said, waits := personWait(p.Module, p.Node, rest); waits {
|
||||
o = reloginObservation(p.Module, p.Node, said, operatorOn(ctx, hold.inv, p.Node), rest)
|
||||
}
|
||||
}
|
||||
if o.Key() != raisedAt.Key {
|
||||
return nil // its own statement says it next
|
||||
raised := false
|
||||
for _, c := range hold.open {
|
||||
raised = raised || c.Key == o.Key()
|
||||
}
|
||||
if !raised {
|
||||
return nil // not open yet, or open as another kind: its own statement says it next
|
||||
}
|
||||
sayWaitingOn(&o, hold.waitersOn(p))
|
||||
_, err := k.Observe(ctx, o)
|
||||
return err
|
||||
}
|
||||
|
||||
// besideAWait is, for a module with something not healthy beside a part waiting for the operator, the waits (checked
|
||||
// already) and the rest without the waiting parts (novox/hq issue 405); no waits when nothing waits, or when the
|
||||
// module only waits (operatorWait says that whole). Pure.
|
||||
func besideAWait(module string, rs []inventory.ResourceHealth) ([]inventory.Wait, []inventory.ResourceHealth) {
|
||||
if _, only := operatorWait(module, rs); only {
|
||||
return nil, rs
|
||||
}
|
||||
var waits []inventory.Wait
|
||||
var rest []inventory.ResourceHealth
|
||||
for _, r := range rs {
|
||||
if r.Module == module && r.State == link.StateWaiting {
|
||||
waits = append(waits, r.Waits...)
|
||||
continue
|
||||
}
|
||||
rest = append(rest, r)
|
||||
}
|
||||
if len(waits) == 0 {
|
||||
return nil, rs
|
||||
}
|
||||
return waits, rest
|
||||
}
|
||||
|
||||
// waitingOf is a module's waiting resources: the evidence of its wait.
|
||||
func waitingOf(module string, rs []inventory.ResourceHealth) []inventory.ResourceHealth {
|
||||
var out []inventory.ResourceHealth
|
||||
for _, r := range rs {
|
||||
if r.Module == module && r.State == link.StateWaiting {
|
||||
out = append(out, r)
|
||||
}
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// reloginKey is a module's relogin-needed condition on a machine.
|
||||
func reloginKey(module, node string) string {
|
||||
return conditions.Key(conditions.ScopeModule, module+"."+node, kindReloginNeeded)
|
||||
@@ -363,12 +467,15 @@ func waitingAccounts(module string, rs []inventory.ResourceHealth) []string {
|
||||
}
|
||||
|
||||
// sayWaitingOn adds to a module's condition the consumers held under it (to-be 48 §6): urgent while anyone
|
||||
// waits on it, whether it is not working or waits for a new login.
|
||||
// waits on it, whether it is not working or waits for a new login. **A wait for the operator's secret or setting
|
||||
// stays a warning** (ADR 0283 decision 5, novox/hq issue 405): who waits on it is listed, and nothing escalates it.
|
||||
func sayWaitingOn(o *conditions.Observation, waiters []string) {
|
||||
if len(waiters) == 0 {
|
||||
return
|
||||
}
|
||||
o.Severity = conditions.Urgent
|
||||
if o.Kind != kindNeedsOperator {
|
||||
o.Severity = conditions.Urgent
|
||||
}
|
||||
o.Said += "; " + waitingWords(waiters)
|
||||
o.Summary += fmt.Sprintf("; %d consumer(s) wait on it", len(waiters))
|
||||
o.Explanation += fmt.Sprintf(" %d module(s) that depend on it wait for it.", len(waiters))
|
||||
@@ -390,9 +497,11 @@ func moduleUnhealthyObservation(module, node string, rs []inventory.ResourceHeal
|
||||
continue
|
||||
}
|
||||
words = append(words, fmt.Sprintf("its %s %s %s", r.Kind, r.Resource, reasonWords(r)))
|
||||
said = append(said, fmt.Sprintf("%s (%s %s): %s, %d look(s) in a row, %d restart(s) counted, since %s",
|
||||
r.Resource, r.Kind, r.Target, orNotSaid(r.Reason), r.Streak, r.Restarts,
|
||||
r.Since.UTC().Format("2006-01-02 15:04:05 MST")))
|
||||
// The restart count runs from when the engine began watching it, not from the state's since (novox/hq
|
||||
// issue 458).
|
||||
said = append(said, fmt.Sprintf("%s (%s %s): %s, since %s, %d look(s) in a row, %s",
|
||||
r.Resource, r.Kind, r.Target, orNotSaid(r.Reason), r.Since.UTC().Format("2006-01-02 15:04:05 MST"),
|
||||
r.Streak, restartsWords(r.Restarts)))
|
||||
}
|
||||
return conditions.Observation{Scope: conditions.ScopeModule, ID: module + "." + node, Token: "unhealthy",
|
||||
Kind: kindModuleUnhealthy, Machine: node, Severity: conditions.Warning, Source: sourceHealth,
|
||||
@@ -406,6 +515,15 @@ func moduleUnhealthyObservation(module, node string, rs []inventory.ResourceHeal
|
||||
Resolved: fmt.Sprintf("%s works again on %s", module, node)}
|
||||
}
|
||||
|
||||
// restartsWords is a restart count as what it is (novox/hq issue 458). The engine reports its own count
|
||||
// (mesh-host's liveness judge, kept.Counted): every rise of systemd's NRestarts or the runtime's RestartCount
|
||||
// after a start's grace, so only restarts by the Restart= setting or the restart policy. It keeps the count
|
||||
// across a recreate, a start by hand and its own restarts, and forgets it only when the resource is no longer
|
||||
// declared. So it counts automatic restarts since the engine began watching it, never since a state's "since".
|
||||
func restartsWords(n int) string {
|
||||
return fmt.Sprintf("%d automatic restart(s) since the node-engine began watching it", n)
|
||||
}
|
||||
|
||||
// reasonWords is why a resource is unhealthy, as a person reads it.
|
||||
func reasonWords(r inventory.ResourceHealth) string {
|
||||
// An account waiting for a new login (ADR 0252) is said in the mesh's words, not the engine's.
|
||||
@@ -414,12 +532,17 @@ func reasonWords(r inventory.ResourceHealth) string {
|
||||
}
|
||||
switch r.Reason {
|
||||
case "restarting":
|
||||
return fmt.Sprintf("keeps restarting (%d restart(s) counted)", r.Restarts)
|
||||
return fmt.Sprintf("keeps restarting (%s)", restartsWords(r.Restarts))
|
||||
case "down":
|
||||
return "is not running"
|
||||
case "":
|
||||
return "is unhealthy"
|
||||
}
|
||||
// A wait for the operator that did not check out is said as the controller found it (ADR 0283): names of
|
||||
// secrets and settings only, never what the check itself said.
|
||||
if strings.HasPrefix(r.Reason, waitRefusedPrefix) {
|
||||
return r.Reason
|
||||
}
|
||||
// What a declared check found says an endpoint, a path or an address: evidence, never the summary the
|
||||
// operator's channel carries (ADR 0234 §6). The summary names the check.
|
||||
if r.Check != "" {
|
||||
@@ -511,7 +634,9 @@ func moduleHealthWord(module, machine string, since time.Time, f gateFacts) (hea
|
||||
if h.HeardAt.Before(since) {
|
||||
return healthNotYet, fmt.Sprintf("%s has not said how what %s runs is since it was sent", machine, module)
|
||||
}
|
||||
wait, waits := personWait(module, machine, h.Resources)
|
||||
// **A wait for the operator is checked first** (novox/hq ADR 0283): one that does not check out is unhealthy.
|
||||
resources := checkWaiting(machine, h.Resources, f.waits)
|
||||
wait, waits := personWait(module, machine, resources)
|
||||
// **Only a build whose own send put the account in a new group is excused** (issue 318 review): read from
|
||||
// what the controller sent, never from when the machine says the wait began — that time is the engine's
|
||||
// memory, reset by its restart and moved by a change of words. A build that adds no account group cannot
|
||||
@@ -519,11 +644,18 @@ func moduleHealthWord(module, machine string, since time.Time, f gateFacts) (hea
|
||||
if waits && !f.groupsAdded[module] {
|
||||
waits = false
|
||||
}
|
||||
var found []string
|
||||
for _, r := range h.Resources {
|
||||
var found, onWaiting []string
|
||||
var forOperator []inventory.Wait
|
||||
for _, r := range resources {
|
||||
if r.Module != module {
|
||||
continue
|
||||
}
|
||||
// **Any build is excused while its wait for the operator checks out** (ADR 0283 decision 4): a secret not
|
||||
// given is owed by every build alike, so it is no fault of this one, and the verdict carries it.
|
||||
if r.State == link.StateWaiting {
|
||||
forOperator = append(forOperator, r.Waits...)
|
||||
continue
|
||||
}
|
||||
if waits && r.State == link.StateUnhealthy {
|
||||
continue
|
||||
}
|
||||
@@ -541,8 +673,16 @@ func moduleHealthWord(module, machine string, since time.Time, f gateFacts) (hea
|
||||
return healthNotYet, fmt.Sprintf("its %s %s on %s is still starting", r.Kind, r.Resource, machine)
|
||||
case link.StateUnhealthy:
|
||||
if on, held := f.heldOn[module+"@"+machine]; held {
|
||||
// **Held under a provider that only waits for the operator** (novox/hq issue 405): a wait for a
|
||||
// person, a pass carrying the wait (ADR 0254, ADR 0283 decision 4) — the walk never waits for the
|
||||
// operator's secret, whichever module owes it.
|
||||
if on.waits != "" {
|
||||
onWaiting = append(onWaiting, fmt.Sprintf("its %s %s on %s waits on %s, which waits for you: %s",
|
||||
r.Kind, r.Resource, machine, on.on, on.waits))
|
||||
continue
|
||||
}
|
||||
return healthWaiting, fmt.Sprintf("its %s %s on %s waits on %s, which is unhealthy", r.Kind,
|
||||
r.Resource, machine, on)
|
||||
r.Resource, machine, on.on)
|
||||
}
|
||||
return healthNotYet, fmt.Sprintf("its %s %s on %s %s", r.Kind, r.Resource, machine, reasonWords(r))
|
||||
default:
|
||||
@@ -550,11 +690,14 @@ func moduleHealthWord(module, machine string, since time.Time, f gateFacts) (hea
|
||||
reasonAfter(r.Reason))
|
||||
}
|
||||
}
|
||||
if waits || len(found) > 0 {
|
||||
var said []string
|
||||
if waits || len(found) > 0 || len(forOperator) > 0 || len(onWaiting) > 0 {
|
||||
said := onWaiting
|
||||
if waits {
|
||||
said = append(said, wait)
|
||||
}
|
||||
if len(forOperator) > 0 {
|
||||
said = append(said, operatorWaitSaid(module, machine, forOperator))
|
||||
}
|
||||
if len(found) > 0 {
|
||||
said = append(said, fmt.Sprintf("on %s, %s uses %s as found and waits for the operator to hand it over "+
|
||||
"(`nox node hand-over %s <directory>` on the control-node)", machine, module, strings.Join(found, ", "), machine))
|
||||
@@ -593,7 +736,7 @@ func healthLines(h inventory.NodeHealth, had bool, now time.Time) []string {
|
||||
line += " — " + r.Reason
|
||||
}
|
||||
if r.Restarts > 0 {
|
||||
line += fmt.Sprintf(", %d restart(s) counted", r.Restarts)
|
||||
line += ", " + restartsWords(r.Restarts)
|
||||
}
|
||||
if r.State == link.StateUnhealthy && h.Streaks[r.Module] < moduleUnhealthyAfter {
|
||||
line += " (unconfirmed: said once)"
|
||||
|
||||
@@ -3,10 +3,12 @@ package main
|
||||
import (
|
||||
"context"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"reflect"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/beside"
|
||||
"github.com/novox/mesh-controller/internal/catalogue"
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
"github.com/novox/mesh-controller/internal/overlay"
|
||||
@@ -239,13 +241,12 @@ func TestATakeoverIsNotComposedForAHubPlacedOffItsTunnel(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// theResolver is the catalogue's dnsmasq module as it is, or the test is skipped where the
|
||||
// catalogue is not beside this checkout.
|
||||
// theResolver is the catalogue's dnsmasq module as it is (internal/beside).
|
||||
func theResolver(t *testing.T) catalogue.Manifest {
|
||||
t.Helper()
|
||||
raw, err := os.ReadFile("../../../mesh-catalog/modules/dnsmasq/module.json")
|
||||
raw, err := os.ReadFile(filepath.Join(beside.Catalogue(t), "dnsmasq", "module.json"))
|
||||
if err != nil {
|
||||
t.Skipf("the catalogue is not beside this checkout: %v", err)
|
||||
t.Fatal(err)
|
||||
}
|
||||
m, err := catalogue.ParseManifest(raw)
|
||||
if err != nil {
|
||||
|
||||
@@ -44,7 +44,7 @@ func nodeCommand(ctx context.Context, args []string) error {
|
||||
if len(args) != 2 {
|
||||
return errors.New("node show <name>")
|
||||
}
|
||||
return showNode(ctx, inv, args[1])
|
||||
return showNode(ctx, open, args[1])
|
||||
case "add":
|
||||
return addNode(ctx, inv, args[1:])
|
||||
|
||||
@@ -127,9 +127,14 @@ func nodeCommand(ctx context.Context, args []string) error {
|
||||
// and whoever may call a verb includes agents.
|
||||
return nodeSetuidSearch(ctx, open, args[1:])
|
||||
|
||||
case "judge-directories":
|
||||
// Which of a node's declared directories the walk that follows no link another account could make would
|
||||
// refuse (novox/hq issue 358). Read-only on the node and here, so a verb may run it too.
|
||||
return nodeJudgeDirectories(ctx, open, args[1:])
|
||||
|
||||
default:
|
||||
return fmt.Errorf("node has no %q; it has add, list, show, public-domain, account, agent-account, hand-over "+
|
||||
"and setuid-search", args[0])
|
||||
return fmt.Errorf("node has no %q; it has add, list, show, public-domain, account, agent-account, hand-over, "+
|
||||
"setuid-search and judge-directories", args[0])
|
||||
}
|
||||
}
|
||||
|
||||
@@ -787,7 +792,8 @@ func roughly(d time.Duration) string {
|
||||
//
|
||||
// It is also where "what should it be configured as" is read. The same line that gates an
|
||||
// assignment carries `card1-DP-1`, and a person composing settings for that machine needs it.
|
||||
func showNode(ctx context.Context, inv *inventory.Inventory, name string) error {
|
||||
func showNode(ctx context.Context, stored *stores, name string) error {
|
||||
inv := stored.inventory
|
||||
node, err := inv.NodeByName(ctx, name)
|
||||
if err != nil {
|
||||
return err
|
||||
@@ -803,6 +809,19 @@ func showNode(ctx context.Context, inv *inventory.Inventory, name string) error
|
||||
if err := showMode(ctx, inv, node); err != nil {
|
||||
return err
|
||||
}
|
||||
// What it was last sent, by whom, under which epoch, from which generation, naming which modules, and what
|
||||
// it answered (novox/hq issue 485): the record of sends is read through this verb, never the store's reader.
|
||||
// Unreadable is said, not taken for none.
|
||||
switch last, found, err := inv.LastSend(ctx, name); {
|
||||
case err != nil:
|
||||
fmt.Printf(" what it was last sent could NOT be read: %v\n", err)
|
||||
case !found:
|
||||
fmt.Printf(" last sent no send recorded since the mesh began keeping them\n")
|
||||
default:
|
||||
for _, line := range lastSendLines(last) {
|
||||
fmt.Println(line)
|
||||
}
|
||||
}
|
||||
// Whom agents run as here, and whether that account can become root without a person (ADR 0266).
|
||||
for _, line := range agentAccountLines(ctx, inv, node) {
|
||||
fmt.Println(line)
|
||||
@@ -889,6 +908,17 @@ func showNode(ctx context.Context, inv *inventory.Inventory, name string) error
|
||||
if len(assigned) > 0 {
|
||||
fmt.Printf("\n assigned: %s\n", strings.Join(assigned, ", "))
|
||||
}
|
||||
// And which of them a push leaves out, and why (novox/hq issue 380): judged as the push judges it, the same
|
||||
// reason its condition says. Not computable is said, never read as "all applied".
|
||||
plan, settings, err := planFor(ctx, stored, name)
|
||||
switch {
|
||||
case err != nil:
|
||||
fmt.Printf("\n whether a send leaves any assigned module out is NOT known: %s\n", oneLine(err.Error()))
|
||||
default:
|
||||
for _, line := range notAppliedLines(name, leftOutOf(plan, settings, node.Adopted)) {
|
||||
fmt.Println(line)
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
@@ -912,3 +942,57 @@ func printJSONTo(w io.Writer, v any) error {
|
||||
fmt.Fprintln(w, string(body))
|
||||
return nil
|
||||
}
|
||||
|
||||
const judgeDirectoriesUsage = "node judge-directories <node> — read-only: which of the directories <node> is " +
|
||||
"declared the node-engine's walk that follows no link another account could make would refuse, one line each " +
|
||||
"(novox/hq issue 358). Nothing is made, chmodded or chowned"
|
||||
|
||||
// nodeJudgeDirectories asks the node's engine to judge its declared directories, signed with the mesh's key as a
|
||||
// hand-over is. Read-only: the engine changes nothing and keeps nothing.
|
||||
func nodeJudgeDirectories(ctx context.Context, open *stores, args []string) error {
|
||||
known := func(node string) error {
|
||||
_, err := open.inventory.NodeByName(ctx, node)
|
||||
return err
|
||||
}
|
||||
ask := func(node, by string) (link.HandOverAnswer, error) {
|
||||
ident, err := open.Identity(ctx)
|
||||
if err != nil {
|
||||
return link.HandOverAnswer{}, fmt.Errorf("the mesh's signing key cannot be read, so nothing was asked of %s: %w",
|
||||
node, err)
|
||||
}
|
||||
address, err := broker.BusAddress()
|
||||
if err != nil {
|
||||
return link.HandOverAnswer{}, err
|
||||
}
|
||||
js, err := broker.Dial(address)
|
||||
if err != nil {
|
||||
return link.HandOverAnswer{}, fmt.Errorf("cannot reach the bus, so nothing was asked of %s: %w", node, err)
|
||||
}
|
||||
defer js.Close()
|
||||
return link.AskJudgeDirectories(ctx, js.Conn(), ident, node, by, link.HandOverWithin)
|
||||
}
|
||||
return judgeDirectoriesAsked(args, known, ask, os.Stdout)
|
||||
}
|
||||
|
||||
// judgeDirectoriesAsked is the line with its two acts given: whether the mesh knows the node, and the ask. The
|
||||
// engine's refusal is this command's failure.
|
||||
func judgeDirectoriesAsked(args []string, known func(node string) error,
|
||||
ask func(node, by string) (link.HandOverAnswer, error), out io.Writer) error {
|
||||
if len(args) != 1 || args[0] == "" || strings.HasPrefix(args[0], "-") {
|
||||
return errors.New(judgeDirectoriesUsage)
|
||||
}
|
||||
node := args[0]
|
||||
if err := known(node); err != nil {
|
||||
return fmt.Errorf("nothing was asked: %w", err)
|
||||
}
|
||||
answer, err := ask(node, handOverBy())
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
if answer.Refused != "" {
|
||||
return fmt.Errorf("%s refused: %s", node, answer.Refused)
|
||||
}
|
||||
fmt.Fprintf(out, "%s (read-only: nothing on %s was changed)\n", node, node)
|
||||
fmt.Fprintln(out, answer.Said)
|
||||
return nil
|
||||
}
|
||||
|
||||
@@ -0,0 +1,112 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"context"
|
||||
"errors"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/catalogue"
|
||||
)
|
||||
|
||||
// novox/hq issue 237: every line of an act's answer comes from one resolution of the node taken after
|
||||
// its write, so the answer agrees with `plan` for the node right after.
|
||||
|
||||
func aProviderAndItsConsumer(t *testing.T, open *stores) {
|
||||
t.Helper()
|
||||
register(t, open, catalogue.Manifest{Module: "db", Version: "1",
|
||||
Provides: []catalogue.Offer{{Name: "rows", Scope: catalogue.ScopeNode}}})
|
||||
register(t, open, catalogue.Manifest{Module: "app", Version: "1", Requires: []string{"rows"}})
|
||||
}
|
||||
|
||||
// twoRivalsAndANote is a node that does not resolve — two modules claim one node seat there — and a
|
||||
// module beside them that changes nothing about it.
|
||||
func twoRivalsAndANote(t *testing.T, open *stores) {
|
||||
t.Helper()
|
||||
one, two := rivals()
|
||||
register(t, open, one)
|
||||
register(t, open, two)
|
||||
register(t, open, catalogue.Manifest{Module: "notes", Version: "1"})
|
||||
}
|
||||
|
||||
func TestAnUnassignThatLeavesItsNodeUnresolvedSaysSoOnceInItsAnswer(t *testing.T) {
|
||||
open := aMesh(t)
|
||||
ctx := t.Context()
|
||||
twoRivalsAndANote(t, open)
|
||||
// Straight into the store, as a node that came to this before the act.
|
||||
for _, m := range []string{"rival-one", "rival-two", "notes"} {
|
||||
if _, err := open.inventory.Assign(ctx, "laptop", m); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
}
|
||||
|
||||
said := answered(t, func() error { return assignCommand(ctx, "unassign", []string{"laptop", "notes"}) })
|
||||
|
||||
if _, _, err := planFor(ctx, open, "laptop"); err == nil || !unresolvable(err) {
|
||||
t.Fatalf("laptop resolves with two claimants of one seat: %v", err)
|
||||
}
|
||||
if n := strings.Count(said, "laptop does not resolve now"); n != 1 {
|
||||
t.Errorf("the answer says laptop does not resolve %d times, want once:\n%s", n, said)
|
||||
}
|
||||
if strings.Contains(said, "is left out of the rest of the mesh") {
|
||||
t.Errorf("the answer carries a line from a read that is not its resolution:\n%s", said)
|
||||
}
|
||||
}
|
||||
|
||||
func TestAnUnassignThatLeavesItsNodeResolvedSaysNothingOfIt(t *testing.T) {
|
||||
open := aMesh(t)
|
||||
ctx := t.Context()
|
||||
aProviderAndItsConsumer(t, open)
|
||||
if _, err := assign(ctx, open, "laptop", "db", "app"); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
said, err := unassign(ctx, open, "laptop", "app")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if _, _, err := planFor(ctx, open, "laptop"); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if strings.Contains(said, "does not resolve") || strings.Contains(said, "could not be read") {
|
||||
t.Errorf("a node that resolves is said not to:\n%s", said)
|
||||
}
|
||||
}
|
||||
|
||||
func TestAnAssignThatLeavesItsNodeUnresolvedSaysOnlyThePlansRefusal(t *testing.T) {
|
||||
open := aMesh(t)
|
||||
ctx := t.Context()
|
||||
twoRivalsAndANote(t, open)
|
||||
if _, err := assign(ctx, open, "laptop", "rival-one"); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
// Kept and not resolvable: a second claimant of the seat, which assignment keeps.
|
||||
said, err := assign(ctx, open, "laptop", "rival-two")
|
||||
if err == nil {
|
||||
t.Fatalf("two claimants of one node seat resolved:\n%s", said)
|
||||
}
|
||||
_, _, planErr := planFor(ctx, open, "laptop")
|
||||
if planErr == nil || planErr.Error() != err.Error() {
|
||||
t.Errorf("the act's refusal is not the plan's right after:\nact: %v\nplan: %v", err, planErr)
|
||||
}
|
||||
if strings.Contains(said, "now has") {
|
||||
t.Errorf("the answer says a seat is now held on a node that does not resolve:\n%s", said)
|
||||
}
|
||||
}
|
||||
|
||||
// The other readers of the whole mesh still say a machine they leave out, on standard error (novox/hq
|
||||
// issue 188); an act sends it elsewhere.
|
||||
func TestAMachineLeftOutIsSaidWhereTheContextSays(t *testing.T) {
|
||||
var buf bytes.Buffer
|
||||
sayLeftOut(leftOutSaidBy(context.Background(), &buf), "laptop", errors.New("why"))
|
||||
if buf.String() != "laptop is left out of the rest of the mesh: it does not resolve: why\n" {
|
||||
t.Errorf("said %q", buf.String())
|
||||
}
|
||||
got := answered(t, func() error {
|
||||
sayLeftOut(context.Background(), "laptop", errors.New("why"))
|
||||
return nil
|
||||
})
|
||||
if !strings.Contains(got, "laptop is left out") {
|
||||
t.Errorf("without an act's writer the line did not reach standard error: %q", got)
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,261 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"sort"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/catalogue"
|
||||
"github.com/novox/mesh-controller/internal/conditions"
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
"github.com/novox/mesh-controller/internal/link"
|
||||
)
|
||||
|
||||
// A part that waits for the operator's secret or setting (novox/hq ADR 0283, issue 386).
|
||||
//
|
||||
// **A module's tool check may say it waits**: nothing of it is wrong but a part that cannot work until the operator
|
||||
// gives one of its own secrets or one of its settings. The node-engine states such a resource `waiting`, with what
|
||||
// it waits for. A module saying so is an assertion, so **the controller checks each wait before it excuses it**:
|
||||
//
|
||||
// - a wait for a secret names an own secret the module's manifest declares — by its name, or as a member of a
|
||||
// secret family — said `"issued-by": "outside"`, and the store holds no value a person gave for it on that
|
||||
// machine;
|
||||
// - a wait for a setting names a setting the manifest declares (checked by name only: the controller cannot tell
|
||||
// whether a free-form value covers a part, and the needs-operator condition is where a false one shows).
|
||||
//
|
||||
// An excused wait is read by the first-node gate as *waits for a person* (ADR 0254), a pass carried in the verdict,
|
||||
// for any build of the module — a secret not given is owed by every build alike. It is said to the operator as
|
||||
// `module.<module>.<machine>.needs-operator`, naming the act. A wait that fails the check is judged unhealthy, saying
|
||||
// why, and raises the module's `unhealthy` condition.
|
||||
|
||||
// kindNeedsOperator is a module's condition while a part of it waits for the operator's secret or setting.
|
||||
const kindNeedsOperator = "needs-operator"
|
||||
|
||||
// needsOperatorKey is a module's needs-operator condition on a machine.
|
||||
func needsOperatorKey(module, node string) string {
|
||||
return conditions.Key(conditions.ScopeModule, module+"."+node, kindNeedsOperator)
|
||||
}
|
||||
|
||||
// operatorWaitFacts is what the controller holds to check a module's waits: the manifest judged per module, and per
|
||||
// "<module>@<machine>" the own secrets a person gave there, with when. A module or a machine absent is not known,
|
||||
// and no wait of it is excused.
|
||||
type operatorWaitFacts struct {
|
||||
manifests map[string]catalogue.Manifest
|
||||
given map[string]map[string]time.Time
|
||||
}
|
||||
|
||||
// checkWait is nil when a wait is excused, and otherwise why not, in words. Pure.
|
||||
func checkWait(module, machine string, w inventory.Wait, f operatorWaitFacts) error {
|
||||
m, known := f.manifests[module]
|
||||
if !known {
|
||||
return fmt.Errorf("says it waits for %s, and the mesh holds no manifest of %s to check it against", waitNames(w), module)
|
||||
}
|
||||
switch {
|
||||
case w.Secret != "" && w.Setting != "", w.Secret == "" && w.Setting == "":
|
||||
return fmt.Errorf("says it waits, naming %s, where a wait names one secret or one setting", waitNames(w))
|
||||
case w.Setting != "":
|
||||
if _, declared := m.Settings[w.Setting]; !declared {
|
||||
return fmt.Errorf("says it waits for the setting %s, which %s does not declare", w.Setting, module)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
own, _, declared := m.OwnSecrets.Lookup(w.Secret)
|
||||
if !declared {
|
||||
return fmt.Errorf("says it waits for the secret %s, which %s does not declare", w.Secret, module)
|
||||
}
|
||||
if own.IssuedBy != catalogue.IssuedOutside {
|
||||
return fmt.Errorf("says it waits for the secret %s, which the mesh makes itself: only a secret issued outside "+
|
||||
"the mesh waits for the operator", w.Secret)
|
||||
}
|
||||
given, readable := f.given[module+"@"+machine]
|
||||
if !readable {
|
||||
return fmt.Errorf("says it waits for the secret %s, and what was given on %s could not be read", w.Secret, machine)
|
||||
}
|
||||
if at, was := given[w.Secret]; was {
|
||||
return fmt.Errorf("says it waits for the secret %s, which was given at %s", w.Secret,
|
||||
at.UTC().Format("2006-01-02 15:04 MST"))
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// waitRefusedPrefix opens every reason checkWait gives, so the words of a refused wait are told from a check's own.
|
||||
const waitRefusedPrefix = "says it waits"
|
||||
|
||||
// waitNames is what a wait names, as "the secret x" or "the setting y".
|
||||
func waitNames(w inventory.Wait) string {
|
||||
switch {
|
||||
case w.Secret != "" && w.Setting != "":
|
||||
return "the secret " + w.Secret + " and the setting " + w.Setting
|
||||
case w.Secret != "":
|
||||
return "the secret " + w.Secret
|
||||
case w.Setting != "":
|
||||
return "the setting " + w.Setting
|
||||
}
|
||||
return "nothing"
|
||||
}
|
||||
|
||||
// checkWaiting reads one machine's resources against the facts: every waiting resource whose waits all check out is
|
||||
// kept as said; one with a wait that does not, or with no wait at all, is answered as unhealthy with why. Pure; the
|
||||
// statement as kept is not changed.
|
||||
func checkWaiting(machine string, rs []inventory.ResourceHealth, f operatorWaitFacts) []inventory.ResourceHealth {
|
||||
out := make([]inventory.ResourceHealth, 0, len(rs))
|
||||
for _, r := range rs {
|
||||
if r.State == link.StateWaiting {
|
||||
var why error
|
||||
if len(r.Waits) == 0 {
|
||||
why = fmt.Errorf("says it waits, and names nothing it waits for")
|
||||
}
|
||||
for _, w := range r.Waits {
|
||||
if why == nil {
|
||||
why = checkWait(r.Module, machine, w, f)
|
||||
}
|
||||
}
|
||||
if why != nil {
|
||||
r.State, r.Reason = link.StateUnhealthy, why.Error()
|
||||
}
|
||||
}
|
||||
out = append(out, r)
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// operatorWait is whether everything not healthy of a module on a machine is waiting with its waits checked
|
||||
// (checkWaiting already applied), and those waits. A module with anything unhealthy, starting or unknown beside it
|
||||
// does not wait: it is judged as before.
|
||||
func operatorWait(module string, rs []inventory.ResourceHealth) ([]inventory.Wait, bool) {
|
||||
var waits []inventory.Wait
|
||||
for _, r := range rs {
|
||||
if r.Module != module {
|
||||
continue
|
||||
}
|
||||
switch r.State {
|
||||
case link.StateHealthy:
|
||||
case link.StateWaiting:
|
||||
waits = append(waits, r.Waits...)
|
||||
default:
|
||||
return nil, false
|
||||
}
|
||||
}
|
||||
return waits, len(waits) > 0
|
||||
}
|
||||
|
||||
// operatorWaitSaid is a module's wait for the operator in one sentence, for the gate's verdict and the condition's
|
||||
// summary: what the operator gives and what it names, and for a secret the line that opens the desk prompt.
|
||||
func operatorWaitSaid(module, machine string, waits []inventory.Wait) string {
|
||||
var parts []string
|
||||
for _, w := range waits {
|
||||
part := fmt.Sprintf("%s (%s", w.What, waitNames(w))
|
||||
if w.Secret != "" {
|
||||
part += fmt.Sprintf(", given with `nox secret ask %s %s %s`", machine, module, w.Secret)
|
||||
}
|
||||
parts = append(parts, part+")")
|
||||
}
|
||||
return fmt.Sprintf("%s on %s waits for the operator: %s", module, machine, strings.Join(parts, "; "))
|
||||
}
|
||||
|
||||
// needsOperatorObservation is a module whose only parts not healthy wait for the operator (ADR 0283): the operator's,
|
||||
// a warning however long it stands, its plain words naming the act and never saying there is nothing to do.
|
||||
func needsOperatorObservation(module, node string, waits []inventory.Wait, rs []inventory.ResourceHealth) conditions.Observation {
|
||||
o := moduleUnhealthyObservation(module, node, rs)
|
||||
o.Token, o.Kind, o.Resolver, o.Severity = kindNeedsOperator, kindNeedsOperator, conditions.ResolverOperator, conditions.Warning
|
||||
o.Summary = operatorWaitSaid(module, node, waits)
|
||||
w := needsOperatorWords(module, node, waits)
|
||||
o.Headline, o.Explanation, o.Needs, o.Resolved, o.Actions = w.Headline, w.Explanation, w.Needs, w.Resolved, nil
|
||||
return o
|
||||
}
|
||||
|
||||
// needsOperatorWords is what the operator reads of a module waiting for them (ADR 0253, ADR 0283): the act, for a
|
||||
// secret typed at the machine's desk prompt and for a setting approved when an agent proposes it. The secret's and
|
||||
// the setting's names, and the line, are in the summary for whoever looks closer.
|
||||
func needsOperatorWords(module, node string, waits []inventory.Wait) words {
|
||||
var acts []string
|
||||
seen := map[string]bool{}
|
||||
secret := false
|
||||
for _, w := range waits {
|
||||
var act string
|
||||
switch {
|
||||
case w.Secret != "":
|
||||
act, secret = fmt.Sprintf("type %s at %s's desk prompt", w.What, node), true
|
||||
case w.Setting != "":
|
||||
act = fmt.Sprintf("approve %s of %s on %s when it is proposed to you", w.Setting, module, node)
|
||||
}
|
||||
if act != "" && !seen[act] {
|
||||
seen[act] = true
|
||||
acts = append(acts, act)
|
||||
}
|
||||
}
|
||||
needs := strings.Join(acts, "; and ") + "."
|
||||
// Plain words hold one sentence of at most conditions.NeedsMax characters: several acts are named in the
|
||||
// summary instead.
|
||||
if len(acts) == 0 || len(needs) > conditions.NeedsMax {
|
||||
needs = fmt.Sprintf("give what %s waits for on %s; the details name each secret and setting.", module, node)
|
||||
}
|
||||
explanation := fmt.Sprintf("Part of %s on %s cannot work until you give what it waits for.", module, node)
|
||||
if secret {
|
||||
explanation += " A hidden prompt opens at the desk when the secret is asked for, and what you type there " +
|
||||
"is sealed to the machine."
|
||||
}
|
||||
explanation += " Its update is in place and nothing was undone; it carries on by itself once it is given."
|
||||
return words{
|
||||
Headline: fmt.Sprintf("%s waits for you on %s", module, node),
|
||||
Needs: needs,
|
||||
Explanation: explanation,
|
||||
Resolved: fmt.Sprintf("%s on %s no longer waits for you", module, node),
|
||||
}
|
||||
}
|
||||
|
||||
// readWaitFacts reads what the controller holds to check the waits of the modules named on one machine: the
|
||||
// manifests (the catalogue's, or those given) and the secrets given there. A read that fails leaves that module
|
||||
// unknown, so none of its waits is excused.
|
||||
func readWaitFacts(ctx context.Context, inv *inventory.Inventory, machine string, modules []string,
|
||||
manifests map[string]catalogue.Manifest, f *operatorWaitFacts) {
|
||||
if f.manifests == nil {
|
||||
f.manifests = map[string]catalogue.Manifest{}
|
||||
}
|
||||
if f.given == nil {
|
||||
f.given = map[string]map[string]time.Time{}
|
||||
}
|
||||
if inv == nil {
|
||||
return
|
||||
}
|
||||
var shelf map[string]catalogue.Manifest
|
||||
sort.Strings(modules)
|
||||
for _, module := range modules {
|
||||
if _, has := f.manifests[module]; !has {
|
||||
if m, given := manifests[module]; given {
|
||||
f.manifests[module] = m
|
||||
} else {
|
||||
if shelf == nil {
|
||||
var err error
|
||||
if shelf, err = inv.Catalogue(ctx); err != nil {
|
||||
shelf = map[string]catalogue.Manifest{}
|
||||
}
|
||||
}
|
||||
if m, known := shelf[module]; known {
|
||||
f.manifests[module] = m
|
||||
}
|
||||
}
|
||||
}
|
||||
if _, read := f.given[module+"@"+machine]; read {
|
||||
continue
|
||||
}
|
||||
if given, err := inv.GivenOwnSecrets(ctx, machine, module); err == nil {
|
||||
f.given[module+"@"+machine] = given
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// waitingModules is every module with a waiting resource in a statement.
|
||||
func waitingModules(rs []inventory.ResourceHealth) []string {
|
||||
seen := map[string]bool{}
|
||||
var out []string
|
||||
for _, r := range rs {
|
||||
if r.State == link.StateWaiting && r.Module != "" && !seen[r.Module] {
|
||||
seen[r.Module] = true
|
||||
out = append(out, r.Module)
|
||||
}
|
||||
}
|
||||
return out
|
||||
}
|
||||
@@ -0,0 +1,264 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/catalogue"
|
||||
"github.com/novox/mesh-controller/internal/conditions"
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
"github.com/novox/mesh-controller/internal/link"
|
||||
)
|
||||
|
||||
// A part that waits for the operator's secret or setting (novox/hq ADR 0283, issue 386).
|
||||
|
||||
var mountsManifest = catalogue.Manifest{Module: "mounts", Version: "1",
|
||||
Settings: map[string]catalogue.SettingDeclaration{"smb-users": {}, "sources": {}},
|
||||
OwnSecrets: catalogue.OwnSecrets{
|
||||
"smb-password-*": {Path: "/s/smb-password-*.secret", IssuedBy: catalogue.IssuedOutside},
|
||||
"broker": {Path: "/s/broker"},
|
||||
"made": {Path: "/s/made", Taken: catalogue.TakenAtStart},
|
||||
"licence": {Path: "/s/licence", IssuedBy: catalogue.IssuedOutside},
|
||||
}}
|
||||
|
||||
var passwordWait = inventory.Wait{Part: "the source games", Secret: "smb-password-games",
|
||||
What: "the password of the source games"}
|
||||
|
||||
var usernameWait = inventory.Wait{Part: "the source games", Setting: "smb-users", What: "the username of the source games"}
|
||||
|
||||
func waitingResource(waits ...inventory.Wait) inventory.ResourceHealth {
|
||||
return inventory.ResourceHealth{Module: "mounts", Resource: "mounts.watch", Kind: "process",
|
||||
Target: "mesh-mounts-watch.service", State: link.StateWaiting, Check: "tool",
|
||||
Reason: "the source games waits for its password", Waits: waits}
|
||||
}
|
||||
|
||||
func factsGiven(given map[string]time.Time) operatorWaitFacts {
|
||||
return operatorWaitFacts{manifests: map[string]catalogue.Manifest{"mounts": mountsManifest},
|
||||
given: map[string]map[string]time.Time{"mounts@workstation": given}}
|
||||
}
|
||||
|
||||
// Rule 3: a wait is excused only when what it names is the module's, issued outside the mesh, and not given there.
|
||||
func TestAWaitIsExcusedOnlyWhenItChecksOut(t *testing.T) {
|
||||
at := time.Date(2026, 10, 10, 15, 8, 0, 0, time.UTC)
|
||||
for _, c := range []struct {
|
||||
name string
|
||||
w inventory.Wait
|
||||
f operatorWaitFacts
|
||||
says string // "" when excused
|
||||
}{
|
||||
{"a member of an outside family, not given", passwordWait, factsGiven(nil), ""},
|
||||
{"an outside secret by name, not given", inventory.Wait{Part: "p", Secret: "licence", What: "w"}, factsGiven(nil), ""},
|
||||
{"a declared setting", usernameWait, factsGiven(nil), ""},
|
||||
{"a member given", passwordWait, factsGiven(map[string]time.Time{"smb-password-games": at}), "was given at 2026-10-10 15:08"},
|
||||
{"a secret not declared", inventory.Wait{Part: "p", Secret: "smb-credentials", What: "w"}, factsGiven(nil), "does not declare"},
|
||||
{"a secret the mesh makes", inventory.Wait{Part: "p", Secret: "made", What: "w"}, factsGiven(nil), "mesh makes itself"},
|
||||
{"the bus account", inventory.Wait{Part: "p", Secret: "broker", What: "w"}, factsGiven(nil), "mesh makes itself"},
|
||||
{"a setting not declared", inventory.Wait{Part: "p", Setting: "logins", What: "w"}, factsGiven(nil), "does not declare"},
|
||||
{"both", inventory.Wait{Part: "p", Secret: "licence", Setting: "smb-users", What: "w"}, factsGiven(nil), "one secret or one setting"},
|
||||
{"neither", inventory.Wait{Part: "p", What: "w"}, factsGiven(nil), "one secret or one setting"},
|
||||
{"no manifest known", passwordWait, operatorWaitFacts{}, "no manifest"},
|
||||
{"what was given cannot be read", passwordWait,
|
||||
operatorWaitFacts{manifests: map[string]catalogue.Manifest{"mounts": mountsManifest}}, "could not be read"},
|
||||
} {
|
||||
err := checkWait("mounts", "workstation", c.w, c.f)
|
||||
switch {
|
||||
case c.says == "" && err != nil:
|
||||
t.Errorf("%s: refused: %v", c.name, err)
|
||||
case c.says != "" && (err == nil || !strings.Contains(err.Error(), c.says)):
|
||||
t.Errorf("%s: %v; want a refusal saying %q", c.name, err, c.says)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// A waiting resource whose wait does not check out, or that names nothing, is judged unhealthy, saying why.
|
||||
func TestAWaitThatFailsItsCheckIsUnhealthy(t *testing.T) {
|
||||
given := factsGiven(map[string]time.Time{"smb-password-games": time.Now()})
|
||||
got := checkWaiting("workstation", []inventory.ResourceHealth{waitingResource(passwordWait)}, given)
|
||||
if got[0].State != link.StateUnhealthy || !strings.Contains(got[0].Reason, "was given") {
|
||||
t.Fatalf("a wait for a secret given: %+v", got[0])
|
||||
}
|
||||
got = checkWaiting("workstation", []inventory.ResourceHealth{waitingResource()}, factsGiven(nil))
|
||||
if got[0].State != link.StateUnhealthy || !strings.Contains(got[0].Reason, "names nothing") {
|
||||
t.Fatalf("a wait naming nothing: %+v", got[0])
|
||||
}
|
||||
got = checkWaiting("workstation", []inventory.ResourceHealth{waitingResource(passwordWait, usernameWait)}, factsGiven(nil))
|
||||
if got[0].State != link.StateWaiting {
|
||||
t.Fatalf("two waits that check out: %+v", got[0])
|
||||
}
|
||||
}
|
||||
|
||||
// Rule 4: the gate passes a module whose only parts not healthy wait for the operator, carrying the wait; anything
|
||||
// else beside it is judged as before; and any build is excused, not only one that added something.
|
||||
func TestTheGatePassesAWaitForTheOperatorCarriedAlong(t *testing.T) {
|
||||
now := time.Now()
|
||||
since := now.Add(-time.Minute)
|
||||
healthy := inventory.ResourceHealth{Module: "mounts", Resource: "mounts.apply", Kind: "process",
|
||||
Target: "mesh-mounts-apply.service", State: link.StateHealthy}
|
||||
f := gateFacts{now: now, waits: factsGiven(nil), groupsAdded: map[string]bool{"mounts": false},
|
||||
health: map[string]inventory.NodeHealth{"workstation": {Node: "workstation", HeardAt: now,
|
||||
Resources: []inventory.ResourceHealth{healthy, waitingResource(passwordWait)}}}}
|
||||
h, why := moduleHealthWord("mounts", "workstation", since, f)
|
||||
if h != healthPerson || !strings.Contains(why, "waits for the operator: the password of the source games") ||
|
||||
!strings.Contains(why, "nox secret ask workstation mounts smb-password-games") {
|
||||
t.Fatalf("an excused wait reads %v %q; want a wait for a person naming the act", h, why)
|
||||
}
|
||||
// A second resource unhealthy beside it: not yet, as before.
|
||||
down := healthy
|
||||
down.State, down.Reason = link.StateUnhealthy, "down"
|
||||
f.health["workstation"] = inventory.NodeHealth{Node: "workstation", HeardAt: now,
|
||||
Resources: []inventory.ResourceHealth{down, waitingResource(passwordWait)}}
|
||||
if h, why := moduleHealthWord("mounts", "workstation", since, f); h != healthNotYet {
|
||||
t.Fatalf("a resource down beside the wait reads %v %q", h, why)
|
||||
}
|
||||
// The password given and the module still saying it waits: not excused.
|
||||
f.waits = factsGiven(map[string]time.Time{"smb-password-games": now})
|
||||
f.health["workstation"] = inventory.NodeHealth{Node: "workstation", HeardAt: now,
|
||||
Resources: []inventory.ResourceHealth{healthy, waitingResource(passwordWait)}}
|
||||
if h, why := moduleHealthWord("mounts", "workstation", since, f); h != healthNotYet || !strings.Contains(why, "was given") {
|
||||
t.Fatalf("a wait for a secret given reads %v %q", h, why)
|
||||
}
|
||||
// Facts never read (no manifest): never excused.
|
||||
f.waits = operatorWaitFacts{}
|
||||
if h, _ := moduleHealthWord("mounts", "workstation", since, f); h != healthNotYet {
|
||||
t.Fatalf("a wait nothing could check reads %v", h)
|
||||
}
|
||||
}
|
||||
|
||||
func needsOperatorOpen(t *testing.T, k *conditions.Keeper) (*conditions.Condition, []conditions.Condition) {
|
||||
t.Helper()
|
||||
open, err := k.Open(t.Context())
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
for i, c := range open {
|
||||
if c.Key == needsOperatorKey("mounts", "workstation") {
|
||||
return &open[i], open
|
||||
}
|
||||
}
|
||||
return nil, open
|
||||
}
|
||||
|
||||
// Rule 5: two statements of an excused wait raise needs-operator, the operator's, a warning however long, naming the
|
||||
// act; a statement without it clears it.
|
||||
func TestTheNeedsOperatorConditionNamesTheAct(t *testing.T) {
|
||||
k, _ := withConditionsInMemory(t)
|
||||
ctx := t.Context()
|
||||
rs := map[string][]inventory.ResourceHealth{"mounts": {waitingResource(passwordWait)}}
|
||||
if err := judgeModuleHealth(ctx, nil, k, "workstation", rs, map[string]int{"mounts": 1}, time.Now()); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if got, _ := needsOperatorOpen(t, k); got != nil {
|
||||
t.Fatal("raised on one statement")
|
||||
}
|
||||
if err := judgeModuleHealth(ctx, nil, k, "workstation", rs, map[string]int{"mounts": 2}, time.Now()); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
got, open := needsOperatorOpen(t, k)
|
||||
if got == nil {
|
||||
t.Fatalf("not raised on two statements: %+v", open)
|
||||
}
|
||||
for _, c := range open {
|
||||
if c.Kind == kindModuleUnhealthy {
|
||||
t.Fatalf("raised as a fault too: %+v", c)
|
||||
}
|
||||
}
|
||||
if got.Kind != kindNeedsOperator || got.Resolver != conditions.ResolverOperator || got.Severity != conditions.Warning {
|
||||
t.Fatalf("the condition: %+v", got)
|
||||
}
|
||||
if !strings.Contains(got.Needs, "type the password of the source games at workstation's desk prompt") ||
|
||||
!strings.Contains(got.Explanation, "hidden prompt opens at the desk") {
|
||||
t.Fatalf("its needs do not name the act: %q", got.Needs)
|
||||
}
|
||||
if strings.Contains(strings.ToLower(got.Explanation), "nothing for you") || !strings.Contains(got.Explanation, "nothing was undone") {
|
||||
t.Fatalf("its explanation: %q", got.Explanation)
|
||||
}
|
||||
if !strings.Contains(got.Summary, "smb-password-games") || !strings.Contains(got.Summary, "nox secret ask workstation mounts smb-password-games") {
|
||||
t.Fatalf("its summary does not name the secret and the line: %q", got.Summary)
|
||||
}
|
||||
// Long open is still a warning: only the operator can end it.
|
||||
if err := judgeModuleHealth(ctx, nil, k, "workstation", rs, map[string]int{"mounts": 3}, time.Now().Add(48*time.Hour)); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if got, _ := needsOperatorOpen(t, k); got == nil || got.Severity == conditions.Urgent {
|
||||
t.Fatalf("after two days: %+v", got)
|
||||
}
|
||||
// Given: the next statement does not say it, and it clears.
|
||||
if err := judgeModuleHealth(ctx, nil, k, "workstation", map[string][]inventory.ResourceHealth{}, nil, time.Now()); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if got, _ := needsOperatorOpen(t, k); got != nil {
|
||||
t.Fatal("not cleared once given")
|
||||
}
|
||||
}
|
||||
|
||||
func TestASettingsWaitAsksForTheApproval(t *testing.T) {
|
||||
k, _ := withConditionsInMemory(t)
|
||||
ctx := t.Context()
|
||||
rs := map[string][]inventory.ResourceHealth{"mounts": {waitingResource(usernameWait)}}
|
||||
for i := 1; i <= 2; i++ {
|
||||
if err := judgeModuleHealth(ctx, nil, k, "workstation", rs, map[string]int{"mounts": i}, time.Now()); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
}
|
||||
got, _ := needsOperatorOpen(t, k)
|
||||
if got == nil || !strings.Contains(got.Needs, "approve smb-users of mounts on workstation when it is proposed to you") {
|
||||
t.Fatalf("the condition: %+v", got)
|
||||
}
|
||||
}
|
||||
|
||||
// A wait that fails its check is the module's own fault: unhealthy, with why, and no needs-operator.
|
||||
func TestAWaitThatFailsItsCheckRaisesUnhealthy(t *testing.T) {
|
||||
k, _ := withConditionsInMemory(t)
|
||||
ctx := t.Context()
|
||||
checked := checkWaiting("workstation", []inventory.ResourceHealth{waitingResource(passwordWait)},
|
||||
factsGiven(map[string]time.Time{"smb-password-games": time.Now()}))
|
||||
rs := map[string][]inventory.ResourceHealth{"mounts": checked}
|
||||
for i := 1; i <= 2; i++ {
|
||||
if err := judgeModuleHealth(ctx, nil, k, "workstation", rs, map[string]int{"mounts": i}, time.Now()); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
}
|
||||
got, open := needsOperatorOpen(t, k)
|
||||
if got != nil {
|
||||
t.Fatalf("a wait for a secret given raised needs-operator: %+v", got)
|
||||
}
|
||||
unhealthy := false
|
||||
for _, c := range open {
|
||||
unhealthy = unhealthy || c.Key == moduleUnhealthyKey("mounts", "workstation")
|
||||
}
|
||||
if !unhealthy {
|
||||
t.Fatalf("not raised as unhealthy: %+v", open)
|
||||
}
|
||||
}
|
||||
|
||||
// A module that waited and is then broken says so when the wait clears, and the other way round.
|
||||
func TestANeedsOperatorThatBecameUnhealthySaysSo(t *testing.T) {
|
||||
k, _ := withConditionsInMemory(t)
|
||||
ctx := t.Context()
|
||||
waiting := map[string][]inventory.ResourceHealth{"mounts": {waitingResource(passwordWait)}}
|
||||
for i := 1; i <= 2; i++ {
|
||||
if err := judgeModuleHealth(ctx, nil, k, "workstation", waiting, map[string]int{"mounts": i}, time.Now()); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
}
|
||||
broken := waitingResource()
|
||||
broken.State, broken.Reason, broken.Waits = link.StateUnhealthy, "the source games refused its login", nil
|
||||
for i := 3; i <= 4; i++ {
|
||||
if err := judgeModuleHealth(ctx, nil, k, "workstation", map[string][]inventory.ResourceHealth{"mounts": {broken}},
|
||||
map[string]int{"mounts": i}, time.Now()); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
}
|
||||
got, open := needsOperatorOpen(t, k)
|
||||
if got != nil {
|
||||
t.Fatal("needs-operator still open after it became a fault")
|
||||
}
|
||||
found := false
|
||||
for _, c := range open {
|
||||
found = found || c.Key == moduleUnhealthyKey("mounts", "workstation")
|
||||
}
|
||||
if !found {
|
||||
t.Fatalf("the fault is not raised: %+v", open)
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,120 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"testing"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/catalogue"
|
||||
)
|
||||
|
||||
// An own secret issued outside the mesh that nobody gave is never made (novox/hq issue 401, ADR 0228). Seen on
|
||||
// 2026-10-10: the send made a random value for the mounts module's smb-credentials and placed it, and the module read
|
||||
// it as a credential given and wrong. The send now makes none, places none, and places a value only once a person
|
||||
// gave one — and a value the mesh made for it before is not placed either.
|
||||
|
||||
// anAssistant is a module with a secret the mesh makes and one only an outside party issues.
|
||||
func anAssistant() catalogue.Manifest {
|
||||
return catalogue.Manifest{Module: "assistant", Version: "1",
|
||||
OwnSecrets: catalogue.OwnSecrets{
|
||||
"password": {Path: "/var/lib/mesh/assistant/password", Taken: catalogue.TakenAtStart},
|
||||
"vendor-key": {Path: "/var/lib/mesh/assistant/vendor-key", Taken: catalogue.TakenAtStart, IssuedBy: catalogue.IssuedOutside},
|
||||
},
|
||||
Resources: []map[string]any{
|
||||
{"id": "state", "type": "directory", "path": "/var/lib/mesh/assistant", "mode": "0700"},
|
||||
}}
|
||||
}
|
||||
|
||||
// sentTo composes what a push sends to a machine, on the send path.
|
||||
func sentTo(t *testing.T, open *stores, node string) []map[string]any {
|
||||
t.Helper()
|
||||
plan, settings, err := planFor(t.Context(), open, node)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
declared, err := declarationFor(t.Context(), open, node, plan, settings)
|
||||
if err != nil {
|
||||
t.Fatalf("the send to %s did not compose: %v", node, err)
|
||||
}
|
||||
return declared.Resources
|
||||
}
|
||||
|
||||
func placedAt(resources []map[string]any, path string) map[string]any {
|
||||
for _, r := range resources {
|
||||
if r["path"] == path && r["sealed"] != nil {
|
||||
return r
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func TestTheSendMakesNoValueForAnOutsideSecretNobodyGave(t *testing.T) {
|
||||
open := aMesh(t)
|
||||
ctx := t.Context()
|
||||
register(t, open, anAssistant())
|
||||
if _, err := assign(ctx, open, "laptop", "assistant"); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
sent := sentTo(t, open, "laptop")
|
||||
if placedAt(sent, "/var/lib/mesh/assistant/password") == nil {
|
||||
t.Fatal("the secret the mesh makes was not placed")
|
||||
}
|
||||
if got := placedAt(sent, "/var/lib/mesh/assistant/vendor-key"); got != nil {
|
||||
t.Fatalf("a secret nobody gave was placed: %v", got)
|
||||
}
|
||||
if _, held, err := open.inventory.ModuleSecretIfIssued(ctx, "laptop", "assistant", "vendor-key"); err != nil || held {
|
||||
t.Fatalf("the send made a value for a secret issued outside the mesh (held %v, %v)", held, err)
|
||||
}
|
||||
|
||||
// A value the mesh made before this rule is not one a person gave: it is not placed.
|
||||
if _, err := open.inventory.SecretForModule(ctx, "laptop", "assistant", "vendor-key"); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if got := placedAt(sentTo(t, open, "laptop"), "/var/lib/mesh/assistant/vendor-key"); got != nil {
|
||||
t.Fatalf("a value the mesh made for a secret issued outside was placed: %v", got)
|
||||
}
|
||||
|
||||
// Given, it is placed.
|
||||
if err := open.inventory.AcceptSecretForModule(ctx, "laptop", "assistant", "vendor-key", "the vendor's key"); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
given, ok, err := open.inventory.GivenOwnSecret(ctx, "laptop", "assistant", "vendor-key")
|
||||
if err != nil || !ok || !given.Current {
|
||||
t.Fatalf("the value given is not read as given: %+v %v %v", given, ok, err)
|
||||
}
|
||||
placed := placedAt(sentTo(t, open, "laptop"), "/var/lib/mesh/assistant/vendor-key")
|
||||
if placed == nil || placed["sealed"] != given.Sealed {
|
||||
t.Fatalf("the value given is placed as %v", placed)
|
||||
}
|
||||
}
|
||||
|
||||
// The read paths answer as the send does: a question about the machine composes without the secret nobody gave, and
|
||||
// asking writes nothing.
|
||||
func TestAQuestionComposesWithoutAnOutsideSecretNobodyGave(t *testing.T) {
|
||||
open := aMesh(t)
|
||||
ctx := t.Context()
|
||||
register(t, open, anAssistant())
|
||||
if _, err := assign(ctx, open, "laptop", "assistant"); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
pushedBy(t, open, "laptop") // the mesh's own secret is made by the send
|
||||
plan, settings, err := planFor(ctx, open, "laptop")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
gens, err := generators(ctx, open)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
for _, choosing := range []Choosing{Reading, Foreseeing} {
|
||||
got, err := declarationWith(ctx, open, "laptop", plan, settings, gens, choosing)
|
||||
if err != nil {
|
||||
t.Fatalf("%v: %v", choosing, err)
|
||||
}
|
||||
if placedAt(got.Resources, "/var/lib/mesh/assistant/vendor-key") != nil || len(got.foreseen) != 0 {
|
||||
t.Fatalf("%v: a secret nobody gave is composed (foreseen %v)", choosing, got.foreseen)
|
||||
}
|
||||
}
|
||||
if _, held, err := open.inventory.ModuleSecretIfIssued(ctx, "laptop", "assistant", "vendor-key"); err != nil || held {
|
||||
t.Fatalf("a question made a value (held %v, %v)", held, err)
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,125 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"fmt"
|
||||
"time"
|
||||
|
||||
"github.com/nats-io/nats.go"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/catalogue"
|
||||
"github.com/novox/mesh-controller/internal/conditions"
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
"github.com/novox/mesh-controller/internal/link"
|
||||
)
|
||||
|
||||
// A delivery over its budget is loud (novox/hq ADR 0282 decision 7, issue 382): the self-check reads
|
||||
// mesh-delivery's `times` and raises the warning `delivery.<class>.over-budget` when the newest delivery of a
|
||||
// class whose delivery time is known took longer than its class's budget — three minutes for a leaf module (ADR
|
||||
// 0304 decision 4), ten for a core module — naming the delivery and its longest phase. It clears when the next delivery of that class
|
||||
// lands within its budget. Measurement only: the condition says, it never holds or acts on a delivery.
|
||||
|
||||
// probeBudgetsID is the probe that reads the delivery times.
|
||||
const probeBudgetsID = "D16"
|
||||
|
||||
// kindOverBudget is what a delivery over its class's budget raises.
|
||||
const kindOverBudget = "over-budget"
|
||||
|
||||
// deliveryBudgets are the budgets by class (ADR 0282 decision 1, the leaf's as ADR 0304 decision 4 changed it);
|
||||
// the probe raises nothing for another class.
|
||||
var deliveryBudgets = map[string]time.Duration{inventory.ClassLeaf: 3 * time.Minute, inventory.ClassCore: 10 * time.Minute}
|
||||
|
||||
// timesAnswer is what mesh-delivery's `times` answers, as far as the probe reads it.
|
||||
type timesAnswer struct {
|
||||
Classes []timesClass `json:"classes"`
|
||||
}
|
||||
|
||||
// timesClass is one class's line of `times`.
|
||||
type timesClass struct {
|
||||
Class string `json:"class"`
|
||||
Latest *timesLatest `json:"latest,omitempty"`
|
||||
}
|
||||
|
||||
// timesLatest is the newest delivery of a class whose delivery time is known.
|
||||
type timesLatest struct {
|
||||
ID string `json:"id"`
|
||||
TookMS int64 `json:"took_ms"`
|
||||
Longest string `json:"longest,omitempty"`
|
||||
Landed string `json:"landed,omitempty"`
|
||||
}
|
||||
|
||||
// deliveryTimes is what the delivery's owner says of its delivery times; nothing when no holder is on record or
|
||||
// none answers (D3 says that one).
|
||||
func deliveryTimes(ctx context.Context, conn *nats.Conn, held bool) (*timesAnswer, error) {
|
||||
if !held {
|
||||
return nil, nil
|
||||
}
|
||||
raw, err := askDeliveryOwner(ctx, conn, "times", map[string]any{})
|
||||
if errors.Is(err, link.ErrNothingServes) {
|
||||
return nil, nil
|
||||
}
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
var a timesAnswer
|
||||
if err := json.Unmarshal(raw, &a); err != nil {
|
||||
return nil, fmt.Errorf("%s.times answered something unreadable: %w", catalogue.DeliverySeat, err)
|
||||
}
|
||||
return &a, nil
|
||||
}
|
||||
|
||||
// overBudgetObservations are the conditions of the classes whose newest delivery took longer than its budget:
|
||||
// strictly longer, so a delivery of exactly its budget is within it.
|
||||
func overBudgetObservations(a *timesAnswer) []conditions.Observation {
|
||||
if a == nil {
|
||||
return nil
|
||||
}
|
||||
var out []conditions.Observation
|
||||
for _, c := range a.Classes {
|
||||
budget, ok := deliveryBudgets[c.Class]
|
||||
if !ok || c.Latest == nil {
|
||||
continue
|
||||
}
|
||||
took := time.Duration(c.Latest.TookMS) * time.Millisecond
|
||||
if took <= budget {
|
||||
continue
|
||||
}
|
||||
longest := c.Latest.Longest
|
||||
if longest == "" {
|
||||
longest = "not known"
|
||||
}
|
||||
out = append(out, conditions.Observation{Scope: conditions.ScopeDelivery, ID: c.Class, Kind: kindOverBudget,
|
||||
Severity: conditions.Warning,
|
||||
Summary: fmt.Sprintf("the %s delivery %s took %s from its merge to running everywhere, over its budget of %s; "+
|
||||
"its longest phase: %s — `mesh-delivery.times`", c.Class, c.Latest.ID, humanDuration(took),
|
||||
humanDuration(budget), longest),
|
||||
Said: fmt.Sprintf("%s took %s (budget %s), longest phase %s", c.Latest.ID, took.Round(time.Second), budget, longest),
|
||||
Headline: fmt.Sprintf("A %s delivery took %s, over its %s budget", c.Class, humanDuration(took),
|
||||
humanDuration(budget)),
|
||||
Explanation: fmt.Sprintf("The delivery %s took %s from its merge until every machine ran it; a %s module is "+
|
||||
"held to %s (ADR 0282). Most of the time went to %s. Nothing was held or changed because of this: it is "+
|
||||
"a measurement.", c.Latest.ID, humanDuration(took), c.Class, humanDuration(budget), longest),
|
||||
Resolved: fmt.Sprintf("the next %s delivery lands within %s", c.Class, humanDuration(budget)),
|
||||
})
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// probeBudgets is D16: the newest delivery of each class lands within its class's budget.
|
||||
func probeBudgets(ctx context.Context, d *doctor) ([]conditions.Observation, error) {
|
||||
entries, err := d.open.inventory.Catalogued(ctx)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
var conn *nats.Conn
|
||||
if d.js != nil {
|
||||
conn = d.js.Conn()
|
||||
}
|
||||
a, err := deliveryTimes(ctx, conn, deliverySeatHeld(entries))
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return overBudgetObservations(a), nil
|
||||
}
|
||||
@@ -0,0 +1,112 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/broker"
|
||||
"github.com/novox/mesh-controller/internal/catalogue"
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
)
|
||||
|
||||
// A leaf delivery of 3 minutes 10 seconds raises delivery.leaf.over-budget naming its longest phase; one of
|
||||
// exactly three minutes, a core one of nine and a class without a budget raise nothing (ADR 0282 decision 7,
|
||||
// the leaf's budget as ADR 0304 decision 4 changed it).
|
||||
func TestADeliveryOverItsBudgetIsLoud(t *testing.T) {
|
||||
a := ×Answer{Classes: []timesClass{
|
||||
{Class: inventory.ClassLeaf, Latest: ×Latest{ID: "novox/mesh-catalog@abc", TookMS: (3*time.Minute + 10*time.Second).Milliseconds(),
|
||||
Longest: "judgement 2m40s"}},
|
||||
{Class: inventory.ClassCore, Latest: ×Latest{ID: "novox/mesh-controller@def", TookMS: (9 * time.Minute).Milliseconds(),
|
||||
Longest: "build 1m"}},
|
||||
{Class: "unclassed", Latest: ×Latest{ID: "x@y", TookMS: time.Hour.Milliseconds()}},
|
||||
}}
|
||||
obs := overBudgetObservations(a)
|
||||
if len(obs) != 1 {
|
||||
t.Fatalf("one class over its budget, got %d: %+v", len(obs), obs)
|
||||
}
|
||||
o := obs[0]
|
||||
if o.Key() != "delivery.leaf.over-budget" || !strings.Contains(o.Summary, "judgement 2m40s") ||
|
||||
!strings.Contains(o.Summary, "novox/mesh-catalog@abc") {
|
||||
t.Fatalf("the condition names its delivery and longest phase: %s — %s", o.Key(), o.Summary)
|
||||
}
|
||||
// The next leaf delivery within its budget clears it: the probe raises nothing for the class.
|
||||
a.Classes[0].Latest = ×Latest{ID: "novox/mesh-catalog@ghi", TookMS: (3 * time.Minute).Milliseconds()}
|
||||
if obs := overBudgetObservations(a); len(obs) != 0 {
|
||||
t.Fatalf("a delivery of exactly its budget is within it: %+v", obs)
|
||||
}
|
||||
a.Classes[1].Latest.TookMS = (10*time.Minute + time.Second).Milliseconds()
|
||||
if obs := overBudgetObservations(a); len(obs) != 1 || obs[0].Key() != "delivery.core.over-budget" {
|
||||
t.Fatalf("a core delivery over ten minutes: %+v", obs)
|
||||
}
|
||||
if obs := overBudgetObservations(nil); obs != nil {
|
||||
t.Fatal("no answer raises nothing")
|
||||
}
|
||||
// No delivery of a class with a known time yet: nothing said of it.
|
||||
if obs := overBudgetObservations(×Answer{Classes: []timesClass{{Class: inventory.ClassLeaf}}}); len(obs) != 0 {
|
||||
t.Fatalf("a class with no delivery: %+v", obs)
|
||||
}
|
||||
}
|
||||
|
||||
// The probe's question is one the controller's grant names: a question the bus refuses checks nothing.
|
||||
func TestTheControllerMayAskForTheDeliveryTimes(t *testing.T) {
|
||||
found := false
|
||||
for _, v := range broker.VerbsTheControllerAsksTheDeliveryOwner {
|
||||
found = found || (v.Seat == catalogue.DeliverySeat && v.Verb == "times")
|
||||
}
|
||||
if !found {
|
||||
t.Fatal("the grant does not name mesh-delivery.times")
|
||||
}
|
||||
}
|
||||
|
||||
// A walk's class is core when it walks a module of the controller's own path or one holding the mesh's resolver,
|
||||
// leaf otherwise; its window closed at its batch's window, or its maximum, never after its cut.
|
||||
func TestAWalksClassAndWindowAreReadAtItsCut(t *testing.T) {
|
||||
entries := []inventory.Entry{
|
||||
{Manifest: catalogue.Manifest{Module: "dnsmasq", Claims: []catalogue.Claim{{Name: resolverSeat}}}},
|
||||
{Manifest: catalogue.Manifest{Module: "gitea"}},
|
||||
}
|
||||
walk := func(modules ...string) inventory.Plan {
|
||||
p := inventory.Plan{Modules: map[string]*inventory.PlanModule{}}
|
||||
for _, m := range modules {
|
||||
p.Modules[m] = &inventory.PlanModule{}
|
||||
}
|
||||
return p
|
||||
}
|
||||
for want, w := range map[string]inventory.Plan{
|
||||
inventory.ClassLeaf: walk("gitea"), inventory.ClassCore: walk("gitea", "mesh-controller"),
|
||||
} {
|
||||
if got := classOf(w, entries); got != want {
|
||||
t.Errorf("%v: %s, want %s", w.Modules, got, want)
|
||||
}
|
||||
}
|
||||
if got := classOf(walk("dnsmasq"), entries); got != inventory.ClassCore {
|
||||
t.Errorf("the resolver's holder is core: %s", got)
|
||||
}
|
||||
now := time.Date(2026, 10, 10, 18, 0, 0, 0, time.UTC)
|
||||
batch := inventory.Plan{Delivery: &inventory.PlanDelivery{Batch: &inventory.PlanBatch{
|
||||
ClosesAt: now.Add(-20 * time.Second), AtMost: now.Add(5 * time.Minute)}}}
|
||||
times := walkTimesAtCut(batch, walk("gitea"), entries, now)
|
||||
if times.Cut == nil || !times.Cut.Equal(now) || times.WindowClosed == nil || !times.WindowClosed.Equal(now.Add(-20*time.Second)) ||
|
||||
times.Class != inventory.ClassLeaf {
|
||||
t.Fatalf("times at the cut: %+v", times)
|
||||
}
|
||||
batch.Delivery.Batch.AtMost = now.Add(-time.Minute)
|
||||
if times := walkTimesAtCut(batch, walk("gitea"), entries, now); !times.WindowClosed.Equal(now.Add(-time.Minute)) {
|
||||
t.Fatalf("a window closed at its maximum: %v", times.WindowClosed)
|
||||
}
|
||||
if times := walkTimesAtCut(inventory.Plan{Delivery: &inventory.PlanDelivery{Alone: true}}, walk("gitea"), entries, now); times.WindowClosed != nil {
|
||||
t.Fatalf("a merge walked alone had no window: %v", times.WindowClosed)
|
||||
}
|
||||
}
|
||||
|
||||
// What each machine of the rest was sent is kept only for the machines the send reached.
|
||||
func TestTheRestIsKeptForTheMachinesTheSendReached(t *testing.T) {
|
||||
got := restOf([]string{"ace", "g14"}, []string{"ace", "shanks"}, map[string]inventory.SentDeclaration{"ace": {Digest: "d1"}})
|
||||
if len(got) != 1 || got["ace"].Digest != "d1" {
|
||||
t.Fatalf("rest: %+v", got)
|
||||
}
|
||||
if restOf([]string{"g14"}, []string{"ace"}, nil) != nil {
|
||||
t.Fatal("no machine reached: nothing kept")
|
||||
}
|
||||
}
|
||||
@@ -81,6 +81,13 @@ var plainWordings = map[string]func(conditions.Observation) words{
|
||||
"It usually catches up by itself.", m, m),
|
||||
Resolved: m + " applied the change"}
|
||||
}),
|
||||
kindApplyFailing: worded(func(o conditions.Observation) words {
|
||||
m := machineOr(o, "a machine")
|
||||
return words{Headline: m + " is not applying its update",
|
||||
Explanation: fmt.Sprintf("%s has refused or only partly applied what the mesh sent it, again and again. "+
|
||||
"The details say what fails.", conditions.Capital(m)),
|
||||
Resolved: m + " applies what it is sent again"}
|
||||
}),
|
||||
"tools-silent": worded(func(o conditions.Observation) words {
|
||||
m := machineOr(o, "a machine")
|
||||
return words{Headline: "Tools on " + m + " are not answering",
|
||||
@@ -175,6 +182,20 @@ var plainWordings = map[string]func(conditions.Observation) words{
|
||||
"register it, so it was not made.", module, m),
|
||||
Resolved: "Resolved: " + module + " on " + m + " is settled"}
|
||||
}),
|
||||
// The controller or the node-engine kept at the build a machine was last sent, over an older record (novox/hq
|
||||
// issue 201).
|
||||
kindCoreDowngrade: worded(func(o conditions.Observation) words {
|
||||
m := machineOr(o, "a machine")
|
||||
component := idPart(o, 0)
|
||||
if o.Scope != conditions.ScopeCore || !guarded(component) {
|
||||
component = "core component"
|
||||
}
|
||||
return words{Headline: m + " keeps a newer " + component + " than the mesh holds",
|
||||
Needs: fmt.Sprintf("push %s to take the older build, or a newer merge or rebuild moves the record forward.", m),
|
||||
Explanation: fmt.Sprintf("The mesh's record of its own %s is older than the build %s was last sent, so "+
|
||||
"the mesh's sends keep the newer one there rather than put it back.", component, m),
|
||||
Resolved: "Resolved: " + m + " runs the " + component + " the mesh holds"}
|
||||
}),
|
||||
kindBindingKept: worded(func(o conditions.Observation) words {
|
||||
m := machineOr(o, "a machine")
|
||||
return words{Headline: "A module's data source is held on " + m,
|
||||
@@ -221,6 +242,24 @@ var plainWordings = map[string]func(conditions.Observation) words{
|
||||
w := usedAsFoundObservation(orModule(module), machineOr(o, "a machine"), o.Summary, nil)
|
||||
return words{Headline: w.Headline, Explanation: w.Explanation, Needs: w.Needs, Resolved: w.Resolved}
|
||||
}),
|
||||
kindNeedsOperator: worded(func(o conditions.Observation) words {
|
||||
// The observation carries the act itself (ADR 0283); these are its words when only the kind is known.
|
||||
module := ""
|
||||
if o.Scope == conditions.ScopeModule && o.Machine != "" {
|
||||
module = strings.TrimSuffix(o.ID, "."+o.Machine)
|
||||
}
|
||||
node := machineOr(o, "a machine")
|
||||
w := needsOperatorWords(orModule(module), node, nil)
|
||||
return w
|
||||
}),
|
||||
kindLeftOut: worded(func(o conditions.Observation) words {
|
||||
// The observation carries its own words (novox/hq issue 380); these are its kind's alone.
|
||||
module := ""
|
||||
if o.Scope == conditions.ScopeModule && o.Machine != "" {
|
||||
module = strings.TrimSuffix(o.ID, "."+o.Machine)
|
||||
}
|
||||
return leftOutWords(orModule(module), machineOr(o, "a machine"), "")
|
||||
}),
|
||||
kindProviderFailing: worded(func(o conditions.Observation) words {
|
||||
thing, consumer := conditions.ThingWords(o), idPart(o, 2)
|
||||
if consumer == "" {
|
||||
@@ -596,6 +635,19 @@ var plainWordings = map[string]func(conditions.Observation) words{
|
||||
Explanation: "The bus refused messages from a part of the mesh, so what they carried did not happen.",
|
||||
Resolved: "Resolved: the bus takes the messages again"}
|
||||
}),
|
||||
kindBucketOrLogFilling: worded(func(o conditions.Observation) words {
|
||||
return words{Headline: "A module's bucket or log on the bus is filling up",
|
||||
Needs: "decide whether to raise its cap or have the module keep less.",
|
||||
Explanation: "A bucket or log a module keeps on the bus holds three quarters of its cap or more. When it " +
|
||||
"is full, the bus refuses what the module writes there.",
|
||||
Resolved: "It has room again"}
|
||||
}),
|
||||
kindBucketOrLogUnread: worded(func(o conditions.Observation) words {
|
||||
return words{Headline: "A module's bucket or log could not be read",
|
||||
Explanation: "The controller could not read how full a bucket or log a module keeps on the bus is, so it " +
|
||||
"cannot say whether it is filling up. It asks again at its next check.",
|
||||
Resolved: "It can be read again"}
|
||||
}),
|
||||
"stream-wrong": worded(func(o conditions.Observation) words {
|
||||
return words{Headline: "Part of the bus's storage is wrong",
|
||||
Needs: "check the machine the bus runs on; the details say what is missing.",
|
||||
@@ -818,6 +870,9 @@ func stalledWords(l stalledLine, o conditions.Observation) (headline, explanatio
|
||||
"to check it: the forge never announced it. It cannot merge until it is checked.", pull, long),
|
||||
fmt.Sprintf("%s has a merge check now, or is closed", pull), needs, nil
|
||||
}
|
||||
if l.State == "unanswered" {
|
||||
return unansweredWords(l, o)
|
||||
}
|
||||
held := l.State
|
||||
if held == "" {
|
||||
held = "held"
|
||||
@@ -847,6 +902,89 @@ func stalledWords(l stalledLine, o conditions.Observation) (headline, explanatio
|
||||
fmt.Sprintf("Delivery of %s is no longer %s", name, held), needs, actions
|
||||
}
|
||||
|
||||
// unansweredWords are the plain words of a pull request's head whose merge check was asked and has not answered
|
||||
// within its bound (novox/hq issue 438): mesh-delivery holds no delivery of it, so there is nothing to stop, release
|
||||
// or close, and no action is offered. The operator's acts are a new commit, which asks the check again, or a look
|
||||
// at the build queue, where a check that never ran may still wait.
|
||||
//
|
||||
// A head whose delivery is held in ready or rejected is said the same way (novox/hq issue 441), and mesh-delivery
|
||||
// names that state as data (Held). Its check answered once, so the build queue is the wrong place to look: the step
|
||||
// is a recheck of the delivery, named by its id, which asks the check again (novox/hq issue 451). It is advised, not
|
||||
// offered as an action, since the controller is not granted the recheck.
|
||||
func unansweredWords(l stalledLine, o conditions.Observation) (headline, explanation, resolved, needs string,
|
||||
actions []conditions.Action) {
|
||||
repository, _, _ := strings.Cut(l.ID, "@")
|
||||
pull := "A pull request of " + repoName(repository)
|
||||
if l.Number > 0 {
|
||||
pull = fmt.Sprintf("Pull request %s #%d", repoName(repository), l.Number)
|
||||
}
|
||||
long, limit := "for too long", ""
|
||||
if d, err := time.ParseDuration(l.For); err == nil {
|
||||
long = "for " + humanDuration(d)
|
||||
}
|
||||
if d, err := time.ParseDuration(l.Bound); err == nil {
|
||||
limit = ", past its limit of " + humanDuration(d)
|
||||
}
|
||||
check := "merge check"
|
||||
if said := uncheckedWaitWords(l); len(said) > 0 {
|
||||
check = "merge check (" + strings.Join(said, ", ") + ")"
|
||||
}
|
||||
which := "Its " + check
|
||||
switch l.Held {
|
||||
case "ready", "rejected":
|
||||
which = "Its delivery is " + l.Held + ", but on the forge its " + check
|
||||
if o.Resolver == conditions.ResolverOperator {
|
||||
needs = "recheck its delivery, which asks its check again — mesh-delivery.recheck with id " + l.ID +
|
||||
" and why — or push a new commit to its branch, " + FromMeshMCPServer
|
||||
}
|
||||
default:
|
||||
if o.Resolver == conditions.ResolverOperator {
|
||||
needs = "push a new commit to its branch, which asks the check again, or see whether its check still " +
|
||||
"waits in the build queue: mesh-controller.queue."
|
||||
}
|
||||
}
|
||||
return fmt.Sprintf("%s's merge check has not answered %s", pull, long),
|
||||
fmt.Sprintf("%s is open on a branch that requires the merge check. %s was asked and has not answered %s%s. "+
|
||||
"It cannot merge until its check answers.", pull, which, long, limit),
|
||||
fmt.Sprintf("%s has an answer from its merge check, or is closed", pull), needs, nil
|
||||
}
|
||||
|
||||
// uncheckedWaitWords are the merge checks an unanswered line waits on, as the operator reads them: from the checks
|
||||
// given as data, each time in the controller's local zone, as every other time in a message — "mesh/merge-gate
|
||||
// pending since 02:11" — never the UTC time inside mesh-delivery's finished words, which cannot be said again in
|
||||
// another zone (novox/hq issue 443). A line from a mesh-delivery that gives no such data is said by its words.
|
||||
func uncheckedWaitWords(l stalledLine) []string {
|
||||
if len(l.Checks) == 0 {
|
||||
return l.Waiting
|
||||
}
|
||||
out := make([]string, 0, len(l.Checks))
|
||||
for _, c := range l.Checks {
|
||||
switch c.State {
|
||||
case "never-set":
|
||||
out = append(out, c.Context+" never set")
|
||||
case "pending":
|
||||
out = append(out, c.Context+" pending"+sinceWords(c.Since))
|
||||
default:
|
||||
out = append(out, c.Context+" not answered")
|
||||
}
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// sinceWords is " since 02:11" in the controller's local zone, with its day when that is not today ("since 23:05 on
|
||||
// 9 Oct"), so the time stays absolute; a time not given, or not readable, is said so and never made up.
|
||||
func sinceWords(since string) string {
|
||||
at, err := time.Parse(time.RFC3339, since)
|
||||
if err != nil {
|
||||
return ", since a time the forge did not say"
|
||||
}
|
||||
local, today := at.In(wordsZone()), wordsNow().In(wordsZone())
|
||||
if local.YearDay() == today.YearDay() && local.Year() == today.Year() {
|
||||
return " since " + local.Format("15:04")
|
||||
}
|
||||
return " since " + local.Format("15:04 on 2 Jan")
|
||||
}
|
||||
|
||||
// causeWords is a hand-act's cause as a person says it.
|
||||
func causeWords(cause string) string {
|
||||
return strings.NewReplacer(".", " ", "_", " ").Replace(cause)
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"regexp"
|
||||
"strings"
|
||||
"testing"
|
||||
@@ -347,3 +348,153 @@ func TestAnUnannouncedPullRequestSaysToPushANewCommit(t *testing.T) {
|
||||
t.Fatalf("it reads %q / %q", o.Headline, o.Explanation)
|
||||
}
|
||||
}
|
||||
|
||||
// **A pull request whose merge check never answered says which check, since when, and what to do** (novox/hq issue
|
||||
// 438): mesh-delivery says one as a stalled line in state `unanswered`, the line below exactly as its test makes it.
|
||||
// No delivery of the head is held, so there is nothing to stop, release or close: no action is offered, and the
|
||||
// operator's acts are a new commit, which asks the check again, or a look at the build queue.
|
||||
func TestAnUnansweredMergeCheckSaysWhichCheckAndWhatToDo(t *testing.T) {
|
||||
var l stalledLine
|
||||
if err := json.Unmarshal([]byte(`{"id":"novox/mesh-controller@c11222026a3b","number":212,"state":"unanswered",`+
|
||||
`"waiting":["mesh/merge-gate pending since 2026-10-11T00:11:39Z","mesh/repo-check never set"],"for":"1h1m0s",`+
|
||||
`"bound":"1h0m0s","h2":"none: no delivery of it is held here, so there is none to close — the operator's",`+
|
||||
`"says":"novox/mesh-controller#212 is open on main, which requires the merge check, and its head's check `+
|
||||
`started and never answered: mesh/merge-gate pending since 2026-10-11T00:11:39Z, mesh/repo-check never set. `+
|
||||
`No delivery of it is held here, so nothing asks it again. A new commit on its branch announces it and asks `+
|
||||
`its check"}`), &l); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
obs := stalledObservations([]stalledLine{l})
|
||||
if len(obs) != 1 || obs[0].Resolver != conditions.ResolverOperator {
|
||||
t.Fatalf("an unanswered merge check is not the operator's: %+v", obs)
|
||||
}
|
||||
o := obs[0]
|
||||
t.Logf("headline: %s\nexplanation: %s\nneeds: %s\nresolved: %s", o.Headline, o.Explanation, o.Needs, o.Resolved)
|
||||
if len(o.Actions) != 0 {
|
||||
t.Fatalf("it offers an action a head with no delivery cannot take: %+v", o.Actions)
|
||||
}
|
||||
if strings.Contains(o.Needs, "stop") || strings.Contains(o.Needs, "release") || !strings.Contains(o.Needs, "commit") ||
|
||||
!strings.Contains(o.Needs, "in the build queue: mesh-controller.queue") || strings.Contains(o.Needs, "build seat") {
|
||||
t.Fatalf("it says to %q", o.Needs)
|
||||
}
|
||||
if o.Headline != "Pull request mesh-controller #212's merge check has not answered for 61 minutes" {
|
||||
t.Fatalf("its headline reads %q", o.Headline)
|
||||
}
|
||||
for _, want := range []string{"mesh/merge-gate pending since 2026-10-11T00:11:39Z", "mesh/repo-check never set",
|
||||
"past its limit of 60 minutes"} {
|
||||
if !strings.Contains(o.Explanation, want) {
|
||||
t.Fatalf("its explanation does not say %q: %q", want, o.Explanation)
|
||||
}
|
||||
}
|
||||
if strings.Contains(o.Explanation, "never asked") || strings.Contains(o.Explanation, "never announced") {
|
||||
t.Fatalf("it says the mesh was never asked, of a head whose check started: %q", o.Explanation)
|
||||
}
|
||||
|
||||
// A line from a mesh-delivery that names no checks still says the check did not answer, and offers nothing.
|
||||
var bare stalledLine
|
||||
if err := json.Unmarshal([]byte(`{"id":"novox/mesh-controller@c11222026a3b","number":212,"state":"unanswered",`+
|
||||
`"for":"1h1m0s","bound":"1h0m0s","h2":"none: no delivery of it is held here, so there is none to close — the operator's"}`),
|
||||
&bare); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
o = stalledObservations([]stalledLine{bare})[0]
|
||||
if len(o.Actions) != 0 || !strings.Contains(o.Explanation, "has not answered") || strings.Contains(o.Headline, "Delivery of") {
|
||||
t.Fatalf("a line naming no checks reads %q / %q, actions %+v", o.Headline, o.Explanation, o.Actions)
|
||||
}
|
||||
}
|
||||
|
||||
// **An unanswered merge check's time reaches the operator in their own time, never as raw UTC** (novox/hq issue
|
||||
// 443): mesh-delivery says each check waited on as data — its context, its state and since when, in RFC 3339 — beside
|
||||
// the finished words it gave before, and the controller words it in its local zone, as every other time in a message.
|
||||
// The line is the one mesh-delivery says, as in the report of issue 443, with the checks it now carries.
|
||||
func TestAnUnansweredMergeChecksTimeIsSaidInLocalTime(t *testing.T) {
|
||||
// The operator's zone given through the seam, never by writing time.Local: other tests' goroutines read it, and
|
||||
// the build seat runs the suite under the race detector.
|
||||
wasZone, wasNow := wordsZone, wordsNow
|
||||
wordsZone = func() *time.Location { return time.FixedZone("CEST", 2*60*60) }
|
||||
wordsNow = func() time.Time { return time.Date(2026, 10, 11, 1, 12, 39, 0, time.UTC) }
|
||||
t.Cleanup(func() { wordsZone, wordsNow = wasZone, wasNow })
|
||||
|
||||
var l stalledLine
|
||||
if err := json.Unmarshal([]byte(`{"id":"novox/mesh-controller@c11222026a3b","number":212,"state":"unanswered",`+
|
||||
`"waiting":["mesh/merge-gate pending since 2026-10-11T00:11:39Z","mesh/repo-check never set"],`+
|
||||
`"checks":[{"context":"mesh/merge-gate","state":"pending","since":"2026-10-11T00:11:39Z"},`+
|
||||
`{"context":"mesh/repo-check","state":"never-set"}],"for":"1h1m0s",`+
|
||||
`"bound":"1h0m0s","h2":"none: no delivery of it is held here, so there is none to close — the operator's",`+
|
||||
`"says":"novox/mesh-controller#212 is open on main, which requires the merge check, and its head's check `+
|
||||
`started and never answered: mesh/merge-gate pending since 2026-10-11T00:11:39Z, mesh/repo-check never set. `+
|
||||
`No delivery of it is held here, so nothing asks it again. A new commit on its branch announces it and asks `+
|
||||
`its check"}`), &l); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
o := stalledObservations([]stalledLine{l})[0]
|
||||
t.Logf("explanation: %s", o.Explanation)
|
||||
for _, raw := range []string{"2026-10-11T00:11:39Z", "00:11", "UTC"} {
|
||||
if strings.Contains(o.Explanation, raw) || strings.Contains(o.Headline, raw) {
|
||||
t.Fatalf("the operator reads %q: %q / %q", raw, o.Headline, o.Explanation)
|
||||
}
|
||||
}
|
||||
for _, want := range []string{"mesh/merge-gate pending since 02:11", "mesh/repo-check never set"} {
|
||||
if !strings.Contains(o.Explanation, want) {
|
||||
t.Fatalf("its explanation does not say %q: %q", want, o.Explanation)
|
||||
}
|
||||
}
|
||||
|
||||
// A check pending since another day than today says which day, so the time stays absolute.
|
||||
l.Checks[0].Since = "2026-10-09T21:05:00Z"
|
||||
if o = stalledObservations([]stalledLine{l})[0]; !strings.Contains(o.Explanation, "mesh/merge-gate pending since 23:05 on 9 Oct") {
|
||||
t.Fatalf("a check pending since an earlier day reads %q", o.Explanation)
|
||||
}
|
||||
|
||||
// A pending check whose time the forge did not say is said so, with no time made up.
|
||||
l.Checks[0].Since = ""
|
||||
if o = stalledObservations([]stalledLine{l})[0]; !strings.Contains(o.Explanation, "mesh/merge-gate pending, since a time the forge did not say") {
|
||||
t.Fatalf("a pending check without its time reads %q", o.Explanation)
|
||||
}
|
||||
}
|
||||
|
||||
// **An unanswered merge check on a ready or rejected delivery is told to recheck it** (novox/hq issue 451):
|
||||
// mesh-delivery says such a line too (issue 441) and names the delivery's state as data, `held`. That check already
|
||||
// answered once, so the build queue is the wrong place to look; a recheck of the delivery, named by its id, asks the
|
||||
// check again. A line with no delivery held keeps the advice of issue 438, and so does a line from a mesh-delivery
|
||||
// that does not say `held` yet: the controller never guesses the state from the words.
|
||||
func TestAnUnansweredMergeCheckOnAReadyOrRejectedDeliveryOffersARecheck(t *testing.T) {
|
||||
line := func(held string) stalledLine {
|
||||
var l stalledLine
|
||||
raw := `{"id":"novox/mesh-controller@c11222026a3b","number":212,"state":"unanswered",` +
|
||||
`"waiting":["mesh/merge-gate pending since 2026-10-11T00:11:39Z"],"for":"1h1m0s","bound":"1h0m0s",` +
|
||||
`"h2":"none: its delivery is ` + held + `, a state the operator moves — the operator's",` +
|
||||
`"says":"novox/mesh-controller#212 is open on main, which requires the merge check, and its delivery is ` +
|
||||
held + ` here, but on the forge its check has not answered: mesh/merge-gate pending since ` +
|
||||
`2026-10-11T00:11:39Z. The pull request waits on that status and nothing asks it again. A recheck of the ` +
|
||||
`delivery asks its check again, as does a new commit on its branch"`
|
||||
if held != "" {
|
||||
raw += `,"held":"` + held + `"`
|
||||
}
|
||||
if err := json.Unmarshal([]byte(raw+`}`), &l); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
return l
|
||||
}
|
||||
for _, held := range []string{"ready", "rejected"} {
|
||||
o := stalledObservations([]stalledLine{line(held)})[0]
|
||||
t.Logf("%s: %s\nneeds: %s", held, o.Explanation, o.Needs)
|
||||
if !strings.Contains(o.Needs, "mesh-delivery.recheck") || !strings.Contains(o.Needs, "novox/mesh-controller@c11222026a3b") {
|
||||
t.Fatalf("a %s delivery's unanswered check is not offered its recheck: %q", held, o.Needs)
|
||||
}
|
||||
if strings.Contains(o.Needs, "build queue") || strings.Contains(o.Needs, "mesh-controller.queue") {
|
||||
t.Fatalf("a %s delivery's unanswered check, which answered once, is sent to the build queue: %q", held, o.Needs)
|
||||
}
|
||||
if !strings.Contains(o.Explanation, "Its delivery is "+held) {
|
||||
t.Fatalf("a %s delivery's explanation does not say its state: %q", held, o.Explanation)
|
||||
}
|
||||
if len(o.Actions) != 0 {
|
||||
t.Fatalf("it offers an action the controller is not granted: %+v", o.Actions)
|
||||
}
|
||||
}
|
||||
// No delivery held, or a mesh-delivery that does not say: the advice of issue 438, and no recheck.
|
||||
o := stalledObservations([]stalledLine{line("")})[0]
|
||||
if !strings.Contains(o.Needs, "in the build queue: mesh-controller.queue") || strings.Contains(o.Needs, "recheck") {
|
||||
t.Fatalf("a line with no delivery held says to %q", o.Needs)
|
||||
}
|
||||
}
|
||||
|
||||
+148
-29
@@ -7,6 +7,7 @@ import (
|
||||
"errors"
|
||||
"flag"
|
||||
"fmt"
|
||||
"io"
|
||||
"os"
|
||||
"slices"
|
||||
"sort"
|
||||
@@ -291,7 +292,7 @@ func theRestOfTheMesh(ctx context.Context, inv *inventory.Inventory,
|
||||
if err != nil {
|
||||
// Said, not skipped: a machine dropped here offers nothing and holds nothing as far
|
||||
// as every other machine's plan can tell (novox/hq issue 188).
|
||||
fmt.Fprintf(os.Stderr, "%s is left out of the rest of the mesh: it does not resolve: %v\n", o.node.Name, err)
|
||||
sayLeftOut(ctx, o.node.Name, err)
|
||||
continue
|
||||
}
|
||||
firstHeld = append(firstHeld, got.Claims...)
|
||||
@@ -336,7 +337,7 @@ func theRestOfTheMesh(ctx context.Context, inv *inventory.Inventory,
|
||||
// resolved without its offers, and one that consumes them cannot resolve here by
|
||||
// design — that is not the machine being dropped, it is the view being partial.
|
||||
if exclude == "" {
|
||||
fmt.Fprintf(os.Stderr, "%s is left out of the rest of the mesh: it does not resolve: %v\n", o.node.Name, err)
|
||||
sayLeftOut(ctx, o.node.Name, err)
|
||||
}
|
||||
continue
|
||||
}
|
||||
@@ -346,6 +347,35 @@ func theRestOfTheMesh(ctx context.Context, inv *inventory.Inventory,
|
||||
return world, nil
|
||||
}
|
||||
|
||||
// leftOutKey carries where theRestOfTheMesh says a machine it leaves out, for an act that answers with
|
||||
// its own resolution instead (novox/hq issue 237).
|
||||
type leftOutKey struct{}
|
||||
|
||||
// leftOutSaidBy is ctx with theRestOfTheMesh's "left out" lines written to w rather than to standard
|
||||
// error.
|
||||
//
|
||||
// **An act's answer is one resolution taken after its write** (novox/hq issue 237, decided 2026-10-11).
|
||||
// `assign` read the whole mesh once before its write — to record the seats held by derivation — and that
|
||||
// read said, on standard error, that the node did not resolve for lack of the seat the act was about to
|
||||
// give it. The controller seat's verb answers with both streams, so the stale line came last, after the
|
||||
// act's own "now has it held", and named as its remedy the assignment just made. An act gives io.Discard
|
||||
// here: what the node resolves to after the write is said by its own planFor, and every other machine
|
||||
// that does not resolve by blockedElsewhere, both read after the write.
|
||||
func leftOutSaidBy(ctx context.Context, w io.Writer) context.Context {
|
||||
return context.WithValue(ctx, leftOutKey{}, w)
|
||||
}
|
||||
|
||||
// sayLeftOut says that a machine is left out of the rest of the mesh, where ctx says to: standard
|
||||
// error unless an act said otherwise. Said, not skipped: a machine dropped there offers nothing and
|
||||
// holds nothing as far as every other machine's plan can tell (novox/hq issue 188).
|
||||
func sayLeftOut(ctx context.Context, node string, err error) {
|
||||
w, ok := ctx.Value(leftOutKey{}).(io.Writer)
|
||||
if !ok {
|
||||
w = os.Stderr
|
||||
}
|
||||
fmt.Fprintf(w, "%s is left out of the rest of the mesh: it does not resolve: %v\n", node, err)
|
||||
}
|
||||
|
||||
// declarationFor is everything a node would be sent.
|
||||
//
|
||||
// One place, because there were three and one of them was written before credentials existed and
|
||||
@@ -420,7 +450,8 @@ func declarationWith(ctx context.Context, open *stores, node string,
|
||||
out := sendable{Resources: composed.Resources, Adoption: adoption,
|
||||
Received: composed.Received, Mesh: with.Mesh, BusUsers: with.BusUsers,
|
||||
LeftOut: sortedKeysOf(composed.LeftOut), leftOutWhy: composed.LeftOut, withheld: with.Withheld,
|
||||
unbound: with.Unbound, foreseen: composed.Foreseen, unplaced: composed.Unplaced}
|
||||
unbound: with.Unbound, foreseen: composed.Foreseen, unplaced: composed.Unplaced,
|
||||
modules: namedModules(plan, composed.LeftOut)}
|
||||
// And which build of each module it carries, for the send to record (novox/hq issue 259, ADR
|
||||
// 0221). Read only on the send path: a question about what would be sent records nothing.
|
||||
if choosing == Allocating {
|
||||
@@ -559,6 +590,13 @@ func busCredentialIssued(ctx context.Context, inv *inventory.Inventory, node, mo
|
||||
return nil
|
||||
}
|
||||
|
||||
// givenUnderAnOldKey is the refusal for a value a person gave — a family's member, or an own secret issued outside
|
||||
// the mesh — sealed to a key the machine no longer holds: the mesh cannot make another, so it is given again.
|
||||
func givenUnderAnOldKey(module, node, name string) error {
|
||||
return fmt.Errorf("%s on %s holds %q, which was given to the mesh rather than made by it, and %s has "+
|
||||
"since generated a new sealing key. The mesh cannot make another; give it again", module, node, name, node)
|
||||
}
|
||||
|
||||
// renderingFor is everything a node's declaration is composed with, and the node's record.
|
||||
func renderingFor(ctx context.Context, open *stores, node string,
|
||||
plan catalogue.Resolution, settings catalogue.SettingsBy,
|
||||
@@ -664,7 +702,54 @@ func renderingFor(ctx context.Context, open *stores, node string,
|
||||
needed := map[string]map[string]string{}
|
||||
foreseen := map[string]map[string]bool{}
|
||||
for _, m := range plan.Modules {
|
||||
for name := range m.OwnSecrets {
|
||||
// **A secret family is never made** (novox/hq ADR 0283): each member a person gave on this machine is
|
||||
// placed, and one not given is nothing — the module says it waits for it.
|
||||
for _, family := range m.OwnSecrets.Families() {
|
||||
members, err := inv.GivenMembers(ctx, node, m.Module, family)
|
||||
if err != nil {
|
||||
return catalogue.Rendering{}, inventory.Node{}, err
|
||||
}
|
||||
for _, g := range members {
|
||||
if _, fam, ok := m.OwnSecrets.Lookup(g.Name); !ok || fam != family {
|
||||
continue // a longer family's member, or a name no longer of this family
|
||||
}
|
||||
if !g.Current {
|
||||
if choosing == Allocating {
|
||||
return catalogue.Rendering{}, inventory.Node{}, givenUnderAnOldKey(m.Module, node, g.Name)
|
||||
}
|
||||
continue
|
||||
}
|
||||
if needed[m.Module] == nil {
|
||||
needed[m.Module] = map[string]string{}
|
||||
}
|
||||
needed[m.Module][g.Name] = g.Sealed
|
||||
}
|
||||
}
|
||||
for name, own := range m.OwnSecrets.Plain() {
|
||||
// **An own secret issued outside the mesh is never made** (novox/hq issue 401, ADR 0228; ADR 0283 for
|
||||
// a family): only a value a person gave is placed. One not given is nothing — no file, and an empty
|
||||
// value where a file of the module names it — so the module can tell it was not given, where a value
|
||||
// the mesh made looked given and wrong. A value the mesh made for it before is not one either.
|
||||
if own.IssuedBy == catalogue.IssuedOutside {
|
||||
g, given, err := inv.GivenOwnSecret(ctx, node, m.Module, name)
|
||||
if err != nil {
|
||||
return catalogue.Rendering{}, inventory.Node{}, err
|
||||
}
|
||||
if !given {
|
||||
continue
|
||||
}
|
||||
if !g.Current {
|
||||
if choosing == Allocating {
|
||||
return catalogue.Rendering{}, inventory.Node{}, givenUnderAnOldKey(m.Module, node, name)
|
||||
}
|
||||
continue
|
||||
}
|
||||
if needed[m.Module] == nil {
|
||||
needed[m.Module] = map[string]string{}
|
||||
}
|
||||
needed[m.Module][name] = g.Sealed
|
||||
continue
|
||||
}
|
||||
// Minted on the send path and only read on every other. Making one is an insert, and
|
||||
// a question that writes is a question that can block against the machine it is about.
|
||||
var sealed string
|
||||
@@ -1264,6 +1349,11 @@ func planCommand(ctx context.Context, args []string) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
// What the machine was last told, by whom and from which assignment generation (novox/hq issue 234),
|
||||
// beside what it would be told now. A record that cannot be read is said, not taken for none.
|
||||
if err := writeLastSend(ctx, os.Stdout, open.inventory, args[0]); err != nil {
|
||||
fmt.Printf("what %s was last sent could not be read: %v\n", args[0], err)
|
||||
}
|
||||
// Which modules a push would leave out, and why — said before the plan, since the plan is of
|
||||
// what the machine would be told (novox/hq ADR 0163, rule 6). Judged, never composed: `plan`
|
||||
// without --json allocates nothing.
|
||||
@@ -1659,17 +1749,27 @@ func providerModuleOf(resolved catalogue.Resolution, open *stores, ctx context.C
|
||||
return ""
|
||||
}
|
||||
|
||||
// unheldLogged is what was last logged about each node's unmet seat dependencies, so the log says
|
||||
// each change once (novox/hq ADR 0207), on stderr so `status --json` stays a document.
|
||||
// unheldLogger remembers what was last logged about each node's unmet seat dependencies, so the
|
||||
// log says each change once (novox/hq ADR 0207), on stderr so `status --json` stays a document.
|
||||
// A test gives its own writer and memory, and no longer shares the process's (novox/hq issue 486).
|
||||
//
|
||||
// **The serving controller's log only.** planFor runs for every node on every push, assignment and
|
||||
// status — `blockedElsewhere` alone resolves the whole mesh — and a one-shot command starts with an
|
||||
// empty memory, so every node's report was "a change" and a push printed the whole mesh's list,
|
||||
// burying the line about the node it acted on. A command says what concerns its own act instead
|
||||
// (unheldChange, reportUnheldPushed); the full list is `status`'s.
|
||||
type unheldLogger struct {
|
||||
mu sync.Mutex
|
||||
logged map[string]string
|
||||
out io.Writer
|
||||
}
|
||||
|
||||
func newUnheldLogger(out io.Writer) *unheldLogger {
|
||||
return &unheldLogger{logged: map[string]string{}, out: out}
|
||||
}
|
||||
|
||||
var (
|
||||
unheldLogged = map[string]string{}
|
||||
unheldLoggedMu sync.Mutex
|
||||
unheldLog = newUnheldLogger(os.Stderr)
|
||||
logUnheldChanges bool
|
||||
)
|
||||
|
||||
@@ -1679,23 +1779,27 @@ func logUnheld(node string, unheld []catalogue.Unheld) {
|
||||
if !logUnheldChanges {
|
||||
return
|
||||
}
|
||||
unheldLog.log(node, unheld)
|
||||
}
|
||||
|
||||
func (l *unheldLogger) log(node string, unheld []catalogue.Unheld) {
|
||||
lines := make([]string, 0, len(unheld))
|
||||
for _, u := range unheld {
|
||||
lines = append(lines, u.String())
|
||||
}
|
||||
now := strings.Join(lines, "\n")
|
||||
unheldLoggedMu.Lock()
|
||||
before, seen := unheldLogged[node]
|
||||
unheldLogged[node] = now
|
||||
unheldLoggedMu.Unlock()
|
||||
l.mu.Lock()
|
||||
defer l.mu.Unlock()
|
||||
before, seen := l.logged[node]
|
||||
l.logged[node] = now
|
||||
if (seen && before == now) || (!seen && now == "") {
|
||||
return
|
||||
}
|
||||
if now == "" {
|
||||
fmt.Fprintf(os.Stderr, "%s: every seat its modules depend on is held (novox/hq ADR 0207)\n", node)
|
||||
fmt.Fprintf(l.out, "%s: every seat its modules depend on is held (novox/hq ADR 0207)\n", node)
|
||||
return
|
||||
}
|
||||
fmt.Fprintf(os.Stderr, "%s: %d unmet seat dependenc(ies), reported and not refused (novox/hq ADR 0207):\n %s\n",
|
||||
fmt.Fprintf(l.out, "%s: %d unmet seat dependenc(ies), reported and not refused (novox/hq ADR 0207):\n %s\n",
|
||||
node, len(lines), strings.Join(lines, "\n "))
|
||||
}
|
||||
|
||||
@@ -1704,28 +1808,43 @@ func logUnheld(node string, unheld []catalogue.Unheld) {
|
||||
// which includes every one of a module just assigned — and each now met that was not. Nothing about
|
||||
// any other node, and nothing that was already true before the act.
|
||||
func unheldChange(shelf map[string]catalogue.Manifest, node string, before, after []string) []string {
|
||||
judge := func(names []string) map[string]catalogue.Unheld {
|
||||
var set []catalogue.Manifest
|
||||
for _, n := range names {
|
||||
if m, known := shelf[n]; known {
|
||||
set = append(set, m)
|
||||
}
|
||||
return unheldChangeTo(shelf, node, before, after, unheldOver(shelf, node, after))
|
||||
}
|
||||
|
||||
// unheldOver is the node's unmet seat dependencies judged over a set of module names alone.
|
||||
func unheldOver(shelf map[string]catalogue.Manifest, node string, names []string) []catalogue.Unheld {
|
||||
var set []catalogue.Manifest
|
||||
for _, n := range names {
|
||||
if m, known := shelf[n]; known {
|
||||
set = append(set, m)
|
||||
}
|
||||
out := map[string]catalogue.Unheld{}
|
||||
for _, u := range catalogue.UnheldDependencies(shelf, node, set, nil) {
|
||||
out[u.Module+" "+u.Seat] = u
|
||||
}
|
||||
return out
|
||||
}
|
||||
was, now := judge(before), judge(after)
|
||||
return catalogue.UnheldDependencies(shelf, node, set, nil)
|
||||
}
|
||||
|
||||
// unheldChangeTo is unheldChange with the node's dependencies as they now stand given: `now` is what
|
||||
// the act's one resolution after its write says is unmet, and `after` the modules that resolution has
|
||||
// on the node (novox/hq issue 237). A line about how things stand after the act is never judged from
|
||||
// anything else, so it cannot disagree with `plan` for the node.
|
||||
func unheldChangeTo(shelf map[string]catalogue.Manifest, node string, before, after []string,
|
||||
now []catalogue.Unheld) []string {
|
||||
key := func(u catalogue.Unheld) string { return u.Module + " " + u.Seat }
|
||||
was := map[string]catalogue.Unheld{}
|
||||
for _, u := range unheldOver(shelf, node, before) {
|
||||
was[key(u)] = u
|
||||
}
|
||||
is := map[string]catalogue.Unheld{}
|
||||
for _, u := range now {
|
||||
is[key(u)] = u
|
||||
}
|
||||
var lines []string
|
||||
for _, k := range sortedNames(now) {
|
||||
for _, k := range sortedNames(is) {
|
||||
if _, already := was[k]; !already {
|
||||
lines = append(lines, "but "+now[k].String())
|
||||
lines = append(lines, "but "+is[k].String())
|
||||
}
|
||||
}
|
||||
for _, k := range sortedNames(was) {
|
||||
if _, still := now[k]; still {
|
||||
if _, still := is[k]; still {
|
||||
continue
|
||||
}
|
||||
u := was[k]
|
||||
|
||||
@@ -0,0 +1,26 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"regexp"
|
||||
)
|
||||
|
||||
// planID is every id the mesh gives a plan: a merge's walk or batch (plan-<nanoseconds>) or a release
|
||||
// (release-<nanoseconds>).
|
||||
var planID = regexp.MustCompile(`^(plan|release)-[0-9]+$`)
|
||||
|
||||
// planIDArguments are the arguments of plans that name a plan. wait is among them for when it is declared
|
||||
// (novox/hq issue 229); an argument not declared is refused before this is asked.
|
||||
var planIDArguments = []string{"id", "wait", "stop", "close", "retry", "go"}
|
||||
|
||||
// plainPlanIDs refuses a plans call naming a plan by anything but a plan's id (novox/hq issue 561): checked
|
||||
// once, where the call becomes a command line, so nothing else a caller sent reaches a command or the store.
|
||||
func plainPlanIDs(given map[string]string) error {
|
||||
for _, arg := range planIDArguments {
|
||||
if id, named := given[arg]; named && !planID.MatchString(id) {
|
||||
return fmt.Errorf("plans %s: %q is not a plan's id (plan-<digits> or release-<digits>, as `plans` "+
|
||||
"lists them); nothing was done", arg, id)
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
@@ -0,0 +1,37 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"strings"
|
||||
"testing"
|
||||
)
|
||||
|
||||
// **A plan's id is checked once, where a call becomes a command line** (novox/hq issue 561): every argument of
|
||||
// plans that names a plan is refused unless it is an id the mesh gives a plan, so a quote never reaches a
|
||||
// command, nor the store behind it.
|
||||
func TestAPlanIdThatIsNoPlansIdIsRefusedBeforeACommandStarts(t *testing.T) {
|
||||
for _, arg := range []string{"id", "stop", "close", "retry", "go"} {
|
||||
for _, bad := range []string{"x' or '1'='1", "plan-1'", "plan-", "plan-1 2", "batch-1", "PLAN-1"} {
|
||||
args := map[string]any{arg: bad}
|
||||
if arg == "stop" || arg == "close" || arg == "go" {
|
||||
args["why"] = "a test"
|
||||
}
|
||||
argv, err := argvFor("plans", args)
|
||||
if err == nil {
|
||||
t.Errorf("plans %s %q was composed: %v", arg, bad, argv)
|
||||
continue
|
||||
}
|
||||
if !strings.Contains(err.Error(), "is not a plan's id") {
|
||||
t.Errorf("plans %s %q was refused for another reason: %v", arg, bad, err)
|
||||
}
|
||||
}
|
||||
for _, good := range []string{"plan-1791813626034291775", "release-1791811938267404408"} {
|
||||
args := map[string]any{arg: good}
|
||||
if arg == "stop" || arg == "close" || arg == "go" {
|
||||
args["why"] = "a test"
|
||||
}
|
||||
if _, err := argvFor("plans", args); err != nil {
|
||||
t.Errorf("plans %s %q was refused: %v", arg, good, err)
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -251,6 +251,16 @@ func resumed(p *inventory.Plan, why string) {
|
||||
if p.State == inventory.PlanFailed && len(failedIn(*p)) == 0 {
|
||||
p.State = inventory.PlanBuilding
|
||||
p.Note = why
|
||||
goesOnAgain(p)
|
||||
}
|
||||
}
|
||||
|
||||
// goesOnAgain clears a stop from a walk that walks again: a stop said why the walk ended, and a walk resumed has
|
||||
// not ended. Kept, it would end a retried walk that fails again as stopped, not failed (novox/hq ADR 0308
|
||||
// decision 1), and keep the search for the merge that brought the failure from running (searchAfterFailures).
|
||||
func goesOnAgain(p *inventory.Plan) {
|
||||
if p.Delivery != nil {
|
||||
p.Delivery.Stopped, p.Delivery.StoppedWhy = "", ""
|
||||
}
|
||||
}
|
||||
|
||||
@@ -278,6 +288,13 @@ func retryPlan(ctx context.Context, open *stores, id string) (string, error) {
|
||||
plans = append(plans, recent...)
|
||||
// **A failed walk whose earlier merges are walked alone is not retried** (novox/hq ADR 0276): the search for
|
||||
// the merge that brought the failure answers them now, and a retried walk would name them twice.
|
||||
// **A walk stopped without some merges is not retried** (novox/hq ADR 0299): the merges it left out were stopped,
|
||||
// and the others are another walk's now.
|
||||
if p.Delivery != nil && (p.Delivery.WalkedAgainBy != "" || len(p.Delivery.LeftOut) > 0) {
|
||||
return "", fmt.Errorf("%s was stopped without %s: those merges were stopped, and %s walks the others; a "+
|
||||
"newer merge, or `rebuild <module>`, builds again", p.ID, mergesLeftOutWords(p.Delivery.LeftOut),
|
||||
orWords(p.Delivery.WalkedAgainBy, "nothing"))
|
||||
}
|
||||
if p.Delivery != nil && len(p.Delivery.Merges) > 0 {
|
||||
kept, err := inv.MergesOf(ctx, p.ID)
|
||||
if err != nil {
|
||||
@@ -288,13 +305,24 @@ func retryPlan(ctx context.Context, open *stores, id string) (string, error) {
|
||||
"those walks answer them; a newer merge, or `rebuild <module>`, builds again", p.ID)
|
||||
}
|
||||
}
|
||||
// Settled from the build records before anything is judged (novox/hq issue 457): a build of the tier
|
||||
// that failed after the plan did is as failed as the one that failed it. What toRetry says is the
|
||||
// failed set every step below works from.
|
||||
var failed []string
|
||||
if p.Tier < len(p.Tiers) {
|
||||
recorded, byID, err := recordsOfAsked(ctx, inv, &p, p.Tiers[p.Tier])
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
failed = toRetry(&p, recorded, byID)
|
||||
}
|
||||
if err := retryRefusal(p, plans); err != nil {
|
||||
return "", err
|
||||
}
|
||||
if again := unjudgedAtGate(p); len(failedIn(p)) == 0 && len(again) > 0 {
|
||||
if again := unjudgedAtGate(p); len(failed) == 0 && len(again) > 0 {
|
||||
return retryTierWhole(ctx, open, &p, again)
|
||||
}
|
||||
if len(failedIn(p)) == 0 {
|
||||
if len(failed) == 0 {
|
||||
return retryRollouts(ctx, open, &p)
|
||||
}
|
||||
entries, err := inv.Catalogued(ctx)
|
||||
@@ -305,7 +333,6 @@ func retryPlan(ctx context.Context, open *stores, id string) (string, error) {
|
||||
for _, e := range entries {
|
||||
byName[e.Manifest.Module] = e
|
||||
}
|
||||
failed := failedIn(p)
|
||||
var asked []string
|
||||
for _, m := range failed {
|
||||
askModule(ctx, &p, m, byName)
|
||||
@@ -443,6 +470,7 @@ func retryRollouts(ctx context.Context, open *stores, p *inventory.Plan) (string
|
||||
said = append(said, m+" to "+strings.Join(again, ", "))
|
||||
}
|
||||
p.State = inventory.PlanRolling
|
||||
goesOnAgain(p)
|
||||
p.Note = fmt.Sprintf("tier %d retried by hand; sent %s first again", p.Tier, strings.Join(said, "; "))
|
||||
if err := open.inventory.SavePlan(ctx, p); err != nil {
|
||||
return "", err
|
||||
@@ -508,6 +536,7 @@ func retryTierWhole(ctx context.Context, open *stores, p *inventory.Plan, again
|
||||
}
|
||||
if p.State == inventory.PlanFailed && len(failedIn(*p)) == 0 {
|
||||
p.State = inventory.PlanBuilding
|
||||
goesOnAgain(p)
|
||||
p.Note = fmt.Sprintf("tier %d retried by hand: %s asked again; %s sent again with the tier", p.Tier,
|
||||
strings.Join(again, ", "), orNone(strings.Join(resent, ", ")))
|
||||
}
|
||||
@@ -525,3 +554,16 @@ func retryTierWhole(ctx context.Context, open *stores, p *inventory.Plan, again
|
||||
func sendAgain(s *inventory.PlanModule) {
|
||||
s.First, s.FirstAt, s.Gate, s.GatedBy, s.Previous, s.Why = nil, nil, nil, "", "", ""
|
||||
}
|
||||
|
||||
// toRetry is the modules a retry asks again: every one of the tier that failed, the plan's state
|
||||
// settled from the build records first (novox/hq issue 457). A plan fails on the first failure in its
|
||||
// tier, and an outcome arriving after that finds no open plan to answer — it is kept only in the build
|
||||
// records. Read from the plan alone, a retry asked only the build that failed first, and the records
|
||||
// then failed the plan again on the next: each failed build of a tier took a retry of its own. What
|
||||
// still runs is left asked, and its outcome is the plan's once the retry sets it building.
|
||||
func toRetry(p *inventory.Plan, recorded map[string][]inventory.Build, byID map[string]inventory.Build) []string {
|
||||
if p.Tier < len(p.Tiers) {
|
||||
settleFromRecords(p, p.Tiers[p.Tier], recorded, byID)
|
||||
}
|
||||
return failedIn(*p)
|
||||
}
|
||||
|
||||
@@ -0,0 +1,57 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"reflect"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
)
|
||||
|
||||
// A retry asks every failed build of the tier, not one (novox/hq issue 457). Seen 2026-10-11: gitea
|
||||
// and plex both failed in tier 0 while the registry was held still; gitea's failure failed the plan,
|
||||
// and plex's, arriving after, found no open plan and was kept only in the build records. The first
|
||||
// retry asked gitea alone, the records then failed the plan again on plex, and a second retry asked
|
||||
// plex.
|
||||
func TestARetryAsksEveryFailedBuildOfTheTier(t *testing.T) {
|
||||
asked := time.Date(2026, 10, 11, 1, 29, 0, 0, time.UTC)
|
||||
failedAt := asked.Add(2 * time.Minute)
|
||||
p := inventory.Plan{ID: "plan-457", State: inventory.PlanFailed, Tier: 0,
|
||||
Tiers: [][]string{{"gitea", "plex"}}, Note: "gitea failed to build in tier 0",
|
||||
Modules: map[string]*inventory.PlanModule{
|
||||
"gitea": {State: "failed", AskedAt: &asked, Build: "build-gitea", Why: "cannot reach the registry"},
|
||||
"plex": {State: "asked", AskedAt: &asked, Build: "build-plex"},
|
||||
}}
|
||||
byID := map[string]inventory.Build{
|
||||
"build-plex": {ID: "build-plex", Module: "plex", At: failedAt, Failed: "cannot reach the registry"},
|
||||
}
|
||||
|
||||
if got := toRetry(&p, nil, byID); !reflect.DeepEqual(got, []string{"gitea", "plex"}) {
|
||||
t.Fatalf("a retry of a tier where gitea and plex failed asks %v", got)
|
||||
}
|
||||
}
|
||||
|
||||
// A build of the tier still running when the plan failed is not asked again: its outcome is the plan's
|
||||
// once the retry sets it building, and one that is recorded built is taken as built.
|
||||
func TestARetryLeavesABuildThatRunsOrWorked(t *testing.T) {
|
||||
asked := time.Date(2026, 10, 11, 1, 29, 0, 0, time.UTC)
|
||||
builtAt := asked.Add(3 * time.Minute)
|
||||
p := inventory.Plan{ID: "plan-457", State: inventory.PlanFailed, Tier: 0,
|
||||
Tiers: [][]string{{"a", "b", "c"}},
|
||||
Modules: map[string]*inventory.PlanModule{
|
||||
"a": {State: "failed", AskedAt: &asked, Build: "build-a", Why: "broken"},
|
||||
"b": {State: "asked", AskedAt: &asked, Build: "build-b"},
|
||||
"c": {State: "asked", AskedAt: &asked, Build: "build-c"},
|
||||
}}
|
||||
byID := map[string]inventory.Build{"build-c": {ID: "build-c", Module: "c", At: builtAt, Commit: "c0ffee"}}
|
||||
|
||||
if got := toRetry(&p, nil, byID); !reflect.DeepEqual(got, []string{"a"}) {
|
||||
t.Fatalf("asks %v, want a alone", got)
|
||||
}
|
||||
if s := p.Modules["c"]; s.State != "built" || s.Commit != "c0ffee" {
|
||||
t.Errorf("c, recorded built, is %+v", s)
|
||||
}
|
||||
if s := p.Modules["b"]; s.State != "asked" {
|
||||
t.Errorf("b, still building, is %+v", s)
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,158 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"os"
|
||||
"strconv"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
"github.com/novox/mesh-controller/internal/link"
|
||||
)
|
||||
|
||||
// Following a plan (novox/hq issue 229): `plans wait <id>` holds its answer until the plan moves, reaches its
|
||||
// next tier or ends, or until its bound passes, and says which. Before it, an agent following a rollout had
|
||||
// `plans` answer once, in prose, and wrote a loop of its own round the mesh's tools to be told the plan moved.
|
||||
//
|
||||
// **No wait is longer than a call is answered within** (link.LongestAnswer, inside the console's thirty
|
||||
// seconds): a longer one would answer "still running" and leave its caller to ask `calls` — the loop again.
|
||||
// So a caller following a plan to its end asks again; each call answers the moment the plan moves.
|
||||
|
||||
// maxPlanWait is the longest bound a wait takes, and the bound when none is given: what a call is answered
|
||||
// within, less the time a verb's command takes to start and read the store.
|
||||
var maxPlanWait = link.LongestAnswer - planWaitStart
|
||||
|
||||
// planWaitStart is what the verb's window allows beyond the bound: starting the command and opening the stores.
|
||||
// A store slow enough to push the read and the answer past it degrades as any long call does: the caller is
|
||||
// answered that the call is still running, and `calls` with its id says what came of it.
|
||||
const planWaitStart = 5 * time.Second
|
||||
|
||||
// planWaitEvery is how often a wait reads the plan again.
|
||||
const planWaitEvery = time.Second
|
||||
|
||||
// The things a wait waits until.
|
||||
var planWaitUntil = []string{"moved", "tier", "done"}
|
||||
|
||||
// planWaitAsked checks what a wait is asked for: until (moved when empty) and a bound (a duration, or a number
|
||||
// of seconds; maxPlanWait when empty).
|
||||
func planWaitAsked(until, bound string) (string, time.Duration, error) {
|
||||
if until == "" {
|
||||
until = "moved"
|
||||
}
|
||||
known := false
|
||||
for _, u := range planWaitUntil {
|
||||
known = known || u == until
|
||||
}
|
||||
if !known {
|
||||
return "", 0, fmt.Errorf("a wait is until %s, not %q", strings.Join(planWaitUntil, ", "), until)
|
||||
}
|
||||
d := maxPlanWait
|
||||
if bound = strings.TrimSpace(bound); bound != "" {
|
||||
var err error
|
||||
if secs, isNumber := strconv.Atoi(bound); isNumber == nil {
|
||||
d = time.Duration(secs) * time.Second
|
||||
} else if d, err = time.ParseDuration(bound); err != nil {
|
||||
return "", 0, fmt.Errorf("the bound %q is not a duration (such as 20s) or a number of seconds", bound)
|
||||
}
|
||||
if d <= 0 || d > maxPlanWait {
|
||||
return "", 0, fmt.Errorf("the bound is at most %s, the longest a call is answered within; %s was asked "+
|
||||
"— to follow a plan longer, ask again: each call answers the moment the plan moves", maxPlanWait, d)
|
||||
}
|
||||
}
|
||||
return until, d, nil
|
||||
}
|
||||
|
||||
// planEnded is a plan that will not move again: done, failed or superseded. A batch being assembled is not one.
|
||||
func planEnded(p inventory.Plan) bool { return !p.Open() && !p.Batch() }
|
||||
|
||||
// waitOnPlan reads the plan until what it waits for happens or the bound passes, and answers the plan as last
|
||||
// read and what ended the wait: moved (any save of it), tier (its tier changed), done (it ended — which ends
|
||||
// every wait, since nothing comes after it), or bound. Moved and tier are judged against the plan as first read.
|
||||
func waitOnPlan(ctx context.Context, read func(context.Context) (inventory.Plan, error), until string,
|
||||
bound, every time.Duration) (inventory.Plan, string, error) {
|
||||
first, err := read(ctx)
|
||||
if err != nil {
|
||||
return inventory.Plan{}, "", err
|
||||
}
|
||||
if planEnded(first) {
|
||||
return first, "done", nil
|
||||
}
|
||||
deadline := time.Now().Add(bound)
|
||||
tick := time.NewTicker(every)
|
||||
defer tick.Stop()
|
||||
last := first
|
||||
for {
|
||||
select {
|
||||
case <-ctx.Done():
|
||||
return last, "", ctx.Err()
|
||||
case <-tick.C:
|
||||
}
|
||||
if !time.Now().Before(deadline) {
|
||||
return last, "bound", nil
|
||||
}
|
||||
p, err := read(ctx)
|
||||
if err != nil {
|
||||
return last, "", err
|
||||
}
|
||||
last = p
|
||||
switch {
|
||||
case planEnded(p):
|
||||
return p, "done", nil
|
||||
case until == "moved" && p.Revision != first.Revision:
|
||||
return p, "moved", nil
|
||||
case until == "tier" && p.Tier != first.Tier:
|
||||
return p, "tier", nil
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// planWaited is what `plans wait` answers: the plan, what ended the wait, and the line a person reads (`text`,
|
||||
// which the verb answers as its output and not again in the data).
|
||||
type planWaited struct {
|
||||
// Came is what ended the wait: moved, tier, done, or bound when nothing did.
|
||||
Came string `json:"came"`
|
||||
Until string `json:"until"`
|
||||
Waited string `json:"waited"`
|
||||
Plan planStatus `json:"plan"`
|
||||
// Revision is the plan's as read: a caller asking again with the same plan sees whether it moved since.
|
||||
Revision int64 `json:"revision"`
|
||||
Text string `json:"text"`
|
||||
}
|
||||
|
||||
func planWaitedDoc(p inventory.Plan, st planStatus, until, came string, waited time.Duration, line string) planWaited {
|
||||
said := map[string]string{
|
||||
"moved": "moved", "tier": "reached another tier", "done": "ended",
|
||||
"bound": "did not " + map[string]string{"moved": "move", "tier": "reach another tier", "done": "end"}[until],
|
||||
}[came]
|
||||
text := fmt.Sprintf("%s %s in %s (waited until %s)\n%s — %s\n", p.ID, said, waited.Round(time.Second), until,
|
||||
p.ID, line)
|
||||
return planWaited{Came: came, Until: until, Waited: waited.Round(time.Millisecond).String(), Plan: st,
|
||||
Revision: p.Revision, Text: text}
|
||||
}
|
||||
|
||||
// planWaitCommand is `plans wait <id>`: the plan followed until it moves, or the bound passes.
|
||||
func planWaitCommand(ctx context.Context, inv *inventory.Inventory, id, untilAsked, boundAsked string) error {
|
||||
until, bound, err := planWaitAsked(untilAsked, boundAsked)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
began := time.Now()
|
||||
p, came, err := waitOnPlan(ctx, func(ctx context.Context) (inventory.Plan, error) {
|
||||
return inv.PlanByID(ctx, id)
|
||||
}, until, bound, planWaitEvery)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
// Said as `plans <id>` says its first line, and as `status` says the plan.
|
||||
now, one := time.Now(), []inventory.Plan{p}
|
||||
bounds, pause := readTierBounds(ctx, inv, now), buildSeatPause(ctx, inv, one)
|
||||
line := planLineSaid(p, now, pause, bounds.of(p.Repository), func(module string) []string {
|
||||
on, _ := inv.Running(ctx, module)
|
||||
return on
|
||||
}, waitsOf(ctx, inv, one))
|
||||
doc := planWaitedDoc(p, planStatuses(one, now, pause, bounds)[0], until, came, now.Sub(began), line)
|
||||
return json.NewEncoder(os.Stdout).Encode(doc)
|
||||
}
|
||||
@@ -0,0 +1,196 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
)
|
||||
|
||||
// A plan as the store would answer it at each read: the reads are counted, and each answers the next.
|
||||
type planReads struct {
|
||||
plans []inventory.Plan
|
||||
n int
|
||||
}
|
||||
|
||||
func (r *planReads) read(context.Context) (inventory.Plan, error) {
|
||||
p := r.plans[min(r.n, len(r.plans)-1)]
|
||||
r.n++
|
||||
return p, nil
|
||||
}
|
||||
|
||||
func followedPlan(rev int64, state string, tier int) inventory.Plan {
|
||||
return inventory.Plan{ID: "plan-1", Repository: "novox/x", Commit: "abc", State: state, Tier: tier,
|
||||
Tiers: [][]string{{"a"}, {"b"}}, Revision: rev}
|
||||
}
|
||||
|
||||
// **`plans` waits for a plan, and says what ended the wait** (novox/hq issue 229): an agent following a
|
||||
// rollout is told when the plan moved, reached its next tier or ended, or that the bound passed — in one
|
||||
// call, without a loop of its own.
|
||||
func TestAWaitForAPlanEndsWhenWhatItWaitsForHappens(t *testing.T) {
|
||||
cases := []struct {
|
||||
name string
|
||||
until string
|
||||
reads []inventory.Plan
|
||||
came string
|
||||
times int
|
||||
}{
|
||||
{"moved: any save", "moved", []inventory.Plan{
|
||||
followedPlan(1, inventory.PlanBuilding, 0), followedPlan(1, inventory.PlanBuilding, 0),
|
||||
followedPlan(2, inventory.PlanBuilding, 0)}, "moved", 3},
|
||||
{"tier: a save inside the tier is not enough", "tier", []inventory.Plan{
|
||||
followedPlan(1, inventory.PlanBuilding, 0), followedPlan(2, inventory.PlanBuilding, 0),
|
||||
followedPlan(3, inventory.PlanRolling, 1)}, "tier", 3},
|
||||
{"tier: a plan that ended has no next tier to wait for", "tier", []inventory.Plan{
|
||||
followedPlan(1, inventory.PlanBuilding, 0), followedPlan(2, inventory.PlanFailed, 0)}, "done", 2},
|
||||
{"done: a new tier is not the end", "done", []inventory.Plan{
|
||||
followedPlan(1, inventory.PlanBuilding, 0), followedPlan(2, inventory.PlanRolling, 1),
|
||||
followedPlan(3, inventory.PlanDone, 1)}, "done", 3},
|
||||
{"done: a plan already ended answers at once", "done", []inventory.Plan{
|
||||
followedPlan(4, inventory.PlanSuperseded, 1)}, "done", 1},
|
||||
{"the bound passes", "moved", []inventory.Plan{followedPlan(1, inventory.PlanBuilding, 0)}, "bound", -1},
|
||||
}
|
||||
for _, c := range cases {
|
||||
t.Run(c.name, func(t *testing.T) {
|
||||
r := &planReads{plans: c.reads}
|
||||
p, came, err := waitOnPlan(context.Background(), r.read, c.until, 50*time.Millisecond, time.Millisecond)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if came != c.came {
|
||||
t.Fatalf("the wait ended as %q, want %q", came, c.came)
|
||||
}
|
||||
if c.times > 0 && r.n != c.times {
|
||||
t.Errorf("read the plan %d times, want %d: it answered before or after what it waited for", r.n, c.times)
|
||||
}
|
||||
if want := c.reads[min(r.n, len(c.reads))-1]; p.Revision != want.Revision {
|
||||
t.Errorf("answered revision %d, not the plan as it was last read (%d)", p.Revision, want.Revision)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// What a wait is asked for is checked before anything is read: what it waits until, and a bound no longer than
|
||||
// a call is answered within.
|
||||
func TestAWaitIsRefusedWhatItCannotDo(t *testing.T) {
|
||||
for _, bad := range []struct{ until, bound string }{{"landed", ""}, {"", "1h"}, {"", "-3s"}, {"", "soon"}} {
|
||||
if _, _, err := planWaitAsked(bad.until, bad.bound); err == nil {
|
||||
t.Errorf("until %q, bound %q was taken", bad.until, bad.bound)
|
||||
}
|
||||
}
|
||||
until, bound, err := planWaitAsked("", "")
|
||||
if err != nil || until != "moved" || bound != maxPlanWait {
|
||||
t.Fatalf("the defaults are %q %s %v, want moved and %s", until, bound, err, maxPlanWait)
|
||||
}
|
||||
if _, bound, _ := planWaitAsked("tier", "12"); bound != 12*time.Second {
|
||||
t.Errorf("a bare number is seconds; read %s", bound)
|
||||
}
|
||||
}
|
||||
|
||||
// **The answer is data, with its prose as a field beside it** (novox/hq issue 229): the verb's `answer` carries
|
||||
// the plan and what ended the wait, and its output is the line a person reads — never JSON inside a string.
|
||||
func TestAWaitForAPlanAnswersAsData(t *testing.T) {
|
||||
p := followedPlan(7, inventory.PlanRolling, 1)
|
||||
st := planStatuses([]inventory.Plan{p}, time.Now(), pauseView{}, tierBounds{})[0]
|
||||
doc := planWaitedDoc(p, st, "tier", "tier", 3*time.Second, "rolling, tier 2 of 2")
|
||||
stdout, _ := json.Marshal(doc)
|
||||
a := answerOf([]string{"plans", "wait", "plan-1"}, stdout, "", true)
|
||||
data, ok := a.Answer.(map[string]any)
|
||||
if !ok {
|
||||
t.Fatalf("the answer is not data: %v", a.Answer)
|
||||
}
|
||||
if data["came"] != "tier" || data["revision"] != float64(7) {
|
||||
t.Errorf("the data does not say what ended the wait: %v", data)
|
||||
}
|
||||
if plan, _ := data["plan"].(map[string]any); plan["state"] != "rolling" || plan["tier"] != float64(1) {
|
||||
t.Errorf("the data does not carry the plan: %v", data["plan"])
|
||||
}
|
||||
if _, text := data["text"]; text {
|
||||
t.Errorf("the prose is in the data too: %v", data)
|
||||
}
|
||||
if strings.Contains(a.Output, "{") || !strings.Contains(a.Output, "plan-1") || !strings.Contains(a.Output, "tier") {
|
||||
t.Errorf("the output is not the line a person reads: %q", a.Output)
|
||||
}
|
||||
}
|
||||
|
||||
// The verb composes the wait, and asks for a window as long as its bound.
|
||||
func TestThePlansVerbComposesAWait(t *testing.T) {
|
||||
argv, err := argvFor("plans", map[string]any{"wait": "plan-1", "until": "done", "bound": "15s"})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if got := strings.Join(argv, " "); got != "plans wait plan-1 --until done --bound 15s" {
|
||||
t.Fatalf("composed %q", got)
|
||||
}
|
||||
if _, err := argvFor("plans", map[string]any{"until": "done"}); err == nil {
|
||||
t.Error("until without wait was taken")
|
||||
}
|
||||
if _, err := argvFor("plans", map[string]any{"wait": "plan-1", "bound": "1h"}); err == nil {
|
||||
t.Error("a bound past what a call can wait was taken")
|
||||
}
|
||||
}
|
||||
|
||||
// Live, with the store: `plans wait` run as the verb runs it answers when the plan reaches its next tier, as
|
||||
// data, and says the bound passed when nothing moved (novox/hq issue 229).
|
||||
func TestAPlanFollowedFromTheStoreAnswersWhenItMoves(t *testing.T) {
|
||||
open := aMesh(t)
|
||||
ctx := t.Context()
|
||||
now := time.Now().UTC()
|
||||
walk := inventory.Plan{ID: "plan-229", Repository: "novox/mesh-catalog", Branch: "main", Commit: "c229c229",
|
||||
Created: now, State: inventory.PlanBuilding, Tiers: [][]string{{"a"}, {"b"}},
|
||||
Modules: map[string]*inventory.PlanModule{"a": {}, "b": {}}}
|
||||
if err := open.inventory.SavePlan(ctx, &walk); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
moved := make(chan error, 1)
|
||||
go func() {
|
||||
time.Sleep(1500 * time.Millisecond)
|
||||
p, err := open.inventory.PlanByID(ctx, walk.ID)
|
||||
if err == nil {
|
||||
p.Tier, p.State = 1, inventory.PlanRolling
|
||||
err = open.inventory.SavePlan(ctx, &p)
|
||||
}
|
||||
moved <- err
|
||||
}()
|
||||
began := time.Now()
|
||||
var got planWaited
|
||||
out := printed(t, func() error {
|
||||
return plansCommand(ctx, []string{"wait", walk.ID, "--until", "tier", "--bound", "15s"})
|
||||
})
|
||||
if err := <-moved; err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := json.Unmarshal([]byte(out), &got); err != nil {
|
||||
t.Fatalf("plans wait did not answer data: %v: %q", err, out)
|
||||
}
|
||||
if got.Came != "tier" || got.Plan.Tier != 1 || got.Plan.State != inventory.PlanRolling {
|
||||
t.Fatalf("the wait answered %+v", got)
|
||||
}
|
||||
if waited := time.Since(began); waited > 10*time.Second {
|
||||
t.Errorf("it answered after %s, not when the plan moved", waited)
|
||||
}
|
||||
out = printed(t, func() error {
|
||||
return plansCommand(ctx, []string{"wait", walk.ID, "--bound", "2"})
|
||||
})
|
||||
if err := json.Unmarshal([]byte(out), &got); err != nil || got.Came != "bound" || got.Until != "moved" {
|
||||
t.Fatalf("a plan that did not move answered %+v (%v)", got, err)
|
||||
}
|
||||
}
|
||||
|
||||
// The verb's schema says the longest bound in words, and the words are the value (review 75 on #266): the
|
||||
// catalogue cannot read maxPlanWait, so this holds them together.
|
||||
func TestThePlansSchemaSaysTheLongestBoundThereIs(t *testing.T) {
|
||||
v, ok := controllerVerb("plans")
|
||||
if !ok {
|
||||
t.Fatal("no plans verb")
|
||||
}
|
||||
props, _ := v.Input["properties"].(map[string]any)
|
||||
bound, _ := props["bound"].(map[string]any)
|
||||
said, _ := bound["description"].(string)
|
||||
if !strings.Contains(said, maxPlanWait.String()+", the default, is the longest") {
|
||||
t.Fatalf("the schema says %q; the longest bound is %s", said, maxPlanWait)
|
||||
}
|
||||
}
|
||||
@@ -78,6 +78,11 @@ func probeDeclarations(ctx context.Context, d *doctor) ([]conditions.Observation
|
||||
return nil, fmt.Errorf("%s cannot be worked out: %w", n.Name, err)
|
||||
}
|
||||
var problems, foreseen []string
|
||||
// Each module the next send leaves out of this machine's declaration (novox/hq issue 380), judged from this
|
||||
// resolution as the send judges it: a finding, never a refusal.
|
||||
if err == nil {
|
||||
out = append(out, leftOutObservations(n.Name, leftOutOf(plan, settings, n.Adopted))...)
|
||||
}
|
||||
if err == nil && gensErr == nil {
|
||||
var declared sendable
|
||||
if declared, err = declarationWith(ctx, open, n.Name, plan, settings, gens, Foreseeing); err == nil {
|
||||
|
||||
@@ -591,7 +591,7 @@ func proposeCommand(ctx context.Context, module, node, valuesArg string, clear,
|
||||
return err
|
||||
},
|
||||
routerHere: routerHereIn(open.inventory),
|
||||
grantHeld: grantHeldIn(open),
|
||||
grantHeld: grantHeldIn(open, conn),
|
||||
routerRecord: func(ctx context.Context, id string) (string, error) {
|
||||
bucket, err := asksRecords(ctx, open.inventory)
|
||||
if err != nil || bucket == "" {
|
||||
|
||||
@@ -37,6 +37,32 @@ type holding struct {
|
||||
shelf map[string]catalogue.Manifest
|
||||
// providers memoises providerFor by machine, consumer and provision.
|
||||
providers map[string]providerLookup
|
||||
// waits is what the waits of a statement are checked against, read as they are asked for (novox/hq issue 450).
|
||||
waits operatorWaitFacts
|
||||
}
|
||||
|
||||
// checked is a machine's newest statement as the controller judges it: each wait checked (ADR 0283 decision 3), so
|
||||
// a wait that does not check out reads as unhealthy, as it did when the statement was judged (novox/hq issue 450).
|
||||
// What is stored is what the machine said, the waits unchecked; read as stored, a provider whose wait failed its
|
||||
// check seems to wait for the operator while its unhealthy condition is open.
|
||||
func (h *holding) checked(machine string) []inventory.ResourceHealth {
|
||||
rs := h.healths[machine].Resources
|
||||
mods := waitingModules(rs)
|
||||
if len(mods) == 0 {
|
||||
return rs
|
||||
}
|
||||
if h.waits.manifests == nil {
|
||||
h.waits.manifests = map[string]catalogue.Manifest{}
|
||||
}
|
||||
for _, module := range mods {
|
||||
if _, has := h.waits.manifests[module]; !has {
|
||||
if m, ok := h.manifestOf(module); ok {
|
||||
h.waits.manifests[module] = m
|
||||
}
|
||||
}
|
||||
}
|
||||
readWaitFacts(h.ctx, h.inv, machine, mods, nil, &h.waits)
|
||||
return checkWaiting(machine, rs, h.waits)
|
||||
}
|
||||
|
||||
type providerLookup struct {
|
||||
@@ -53,6 +79,15 @@ func readHolding(ctx context.Context, inv *inventory.Inventory, open []condition
|
||||
return &holding{ctx: ctx, inv: inv, healths: healths, open: open, providers: map[string]providerLookup{}}, nil
|
||||
}
|
||||
|
||||
// readHoldingFor is how a judging reads its holding: nothing without a store. A variable so a test can hand a
|
||||
// judging the record it holds under (novox/hq issue 405).
|
||||
var readHoldingFor = func(ctx context.Context, inv *inventory.Inventory, open []conditions.Condition) (*holding, error) {
|
||||
if inv == nil {
|
||||
return nil, nil
|
||||
}
|
||||
return readHolding(ctx, inv, open)
|
||||
}
|
||||
|
||||
// heldFinding says a resource's state is a finding of its declared check that names a provision: what
|
||||
// may be held. Down and restarting are liveness, the resource's own.
|
||||
func heldFinding(r inventory.ResourceHealth) bool {
|
||||
@@ -106,42 +141,137 @@ func (h *holding) lookUpProvider(machine, consumer, provision string) (catalogue
|
||||
return catalogue.Chosen{}, false
|
||||
}
|
||||
|
||||
// unhealthy says a provider is unhealthy on the record: its condition is open, or its machine's newest
|
||||
// statement says a resource of it is unhealthy.
|
||||
func (h *holding) unhealthy(p catalogue.Chosen) bool {
|
||||
key := moduleUnhealthyKey(p.Module, p.Node)
|
||||
// providerState is how a provider stands on the record: unhealthy when its unhealthy condition is open or its
|
||||
// machine's newest statement says a resource of it is unhealthy; else waiting for the operator when that statement
|
||||
// says a resource of it waits, with the waits it names, or its needs-operator condition is open (waits then
|
||||
// unknown); else healthy.
|
||||
func (h *holding) providerState(p catalogue.Chosen) (unhealthy, waiting bool, waits []inventory.Wait) {
|
||||
for _, c := range h.open {
|
||||
if c.Key == key {
|
||||
return true
|
||||
if c.Key == moduleUnhealthyKey(p.Module, p.Node) {
|
||||
return true, false, nil
|
||||
}
|
||||
}
|
||||
for _, r := range h.healths[p.Node].Resources {
|
||||
if r.Module == p.Module && r.State == link.StateUnhealthy {
|
||||
return true
|
||||
for _, r := range h.checked(p.Node) {
|
||||
if r.Module != p.Module {
|
||||
continue
|
||||
}
|
||||
switch r.State {
|
||||
case link.StateUnhealthy:
|
||||
return true, false, nil
|
||||
case link.StateWaiting:
|
||||
waiting = true
|
||||
waits = append(waits, r.Waits...)
|
||||
}
|
||||
}
|
||||
return false
|
||||
if !waiting {
|
||||
for _, c := range h.open {
|
||||
waiting = waiting || c.Key == needsOperatorKey(p.Module, p.Node)
|
||||
}
|
||||
}
|
||||
return false, waiting, waits
|
||||
}
|
||||
|
||||
// manifestOf is a module's manifest from the catalogue, read once; false when it cannot be read.
|
||||
func (h *holding) manifestOf(module string) (catalogue.Manifest, bool) {
|
||||
if h.shelf == nil && h.inv != nil {
|
||||
shelf, err := h.inv.Catalogue(h.ctx)
|
||||
if err != nil {
|
||||
return catalogue.Manifest{}, false
|
||||
}
|
||||
h.shelf = shelf
|
||||
}
|
||||
m, ok := h.shelf[module]
|
||||
return m, ok
|
||||
}
|
||||
|
||||
// covering is the waits of a provider that cover a provision it gives (novox/hq issue 405): a module that waits
|
||||
// says nothing else of it is wrong and names each part that waits (ADR 0283 decision 1), so only a consumer of
|
||||
// the waiting part waits on it. A wait covers a provision when its part is that provision, or the secret it waits
|
||||
// for is the provision's shared credential (ADR 0158). Nothing when no wait can be matched: a consumer failing
|
||||
// then is not held, since holding it would hide a fault that may be its own.
|
||||
func (h *holding) covering(p catalogue.Chosen, provision string, waits []inventory.Wait) []inventory.Wait {
|
||||
credential := ""
|
||||
if m, ok := h.manifestOf(p.Module); ok {
|
||||
credential, _ = m.SharedCredentialOf(provision)
|
||||
}
|
||||
var out []inventory.Wait
|
||||
for _, w := range waits {
|
||||
if w.Part == provision || (w.Secret != "" && w.Secret == credential) {
|
||||
out = append(out, w)
|
||||
}
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// heldUnderProvider is the provider a consumer's findings are held under, and — when that provider only waits for the
|
||||
// operator, for the part the consumer needs — the waits that hold it.
|
||||
type heldUnderProvider struct {
|
||||
provider catalogue.Chosen
|
||||
// waits is set when every finding held waits on a provider that only waits for the operator: the consumer's
|
||||
// gate then reads as ADR 0254's waits for a person, a pass with the wait carried (ADR 0283 decision 4).
|
||||
waits []inventory.Wait
|
||||
}
|
||||
|
||||
// heldUnder is the provider a consumer's unhealthy resources wait on: when every one of them is a finding
|
||||
// of a check naming a provision whose provider for this consumer is unhealthy on the record. False when any
|
||||
// is the consumer's own.
|
||||
// of a check naming a provision whose provider for this consumer is unhealthy on the record, or waits for the
|
||||
// operator for the part that gives it (novox/hq issue 405). False when any is the consumer's own.
|
||||
func (h *holding) heldUnder(machine, module string, rs []inventory.ResourceHealth) (catalogue.Chosen, bool) {
|
||||
var on catalogue.Chosen
|
||||
by, held := h.heldWith(machine, module, rs)
|
||||
return by.provider, held
|
||||
}
|
||||
|
||||
func (h *holding) heldWith(machine, module string, rs []inventory.ResourceHealth) (heldUnderProvider, bool) {
|
||||
var on heldUnderProvider
|
||||
onlyWaits := true
|
||||
for _, r := range rs {
|
||||
if r.State != link.StateUnhealthy {
|
||||
continue
|
||||
}
|
||||
if !heldFinding(r) {
|
||||
return catalogue.Chosen{}, false
|
||||
return heldUnderProvider{}, false
|
||||
}
|
||||
p, ok := h.providerFor(machine, module, r.Needs)
|
||||
if !ok || (p.Node == machine && p.Module == module) || !h.unhealthy(p) {
|
||||
return catalogue.Chosen{}, false
|
||||
if !ok || (p.Node == machine && p.Module == module) {
|
||||
return heldUnderProvider{}, false
|
||||
}
|
||||
on = p
|
||||
unhealthy, waiting, waits := h.providerState(p)
|
||||
switch {
|
||||
case unhealthy:
|
||||
onlyWaits = false
|
||||
case waiting:
|
||||
covered := h.covering(p, r.Needs, waits)
|
||||
if len(covered) == 0 {
|
||||
return heldUnderProvider{}, false
|
||||
}
|
||||
on.waits = append(on.waits, covered...)
|
||||
default:
|
||||
return heldUnderProvider{}, false
|
||||
}
|
||||
on.provider = p
|
||||
}
|
||||
return on, on.Module != ""
|
||||
if !onlyWaits {
|
||||
on.waits = nil
|
||||
}
|
||||
return on, on.provider.Module != ""
|
||||
}
|
||||
|
||||
// waitingUncovered is a provider of a consumer's failing finding that waits for the operator for a part the
|
||||
// finding cannot be matched to (novox/hq issue 405): the consumer is raised on its own, and its condition says
|
||||
// the provider waits, so neither is hidden.
|
||||
func (h *holding) waitingUncovered(machine, module string, rs []inventory.ResourceHealth) (catalogue.Chosen, bool) {
|
||||
for _, r := range rs {
|
||||
if r.State != link.StateUnhealthy || !heldFinding(r) {
|
||||
continue
|
||||
}
|
||||
p, ok := h.providerFor(machine, module, r.Needs)
|
||||
if !ok || (p.Node == machine && p.Module == module) {
|
||||
continue
|
||||
}
|
||||
if unhealthy, waiting, waits := h.providerState(p); !unhealthy && waiting && len(h.covering(p, r.Needs, waits)) == 0 {
|
||||
return p, true
|
||||
}
|
||||
}
|
||||
return catalogue.Chosen{}, false
|
||||
}
|
||||
|
||||
// waitersOn is every consumer held under a provider, as "<module> on <machine>", sorted.
|
||||
@@ -165,8 +295,8 @@ func (h *holding) waitersOn(p catalogue.Chosen) []string {
|
||||
}
|
||||
|
||||
// heldModules is, for one machine's statement, each module whose finding is held, with the provider.
|
||||
func (h *holding) heldModules(machine string) map[string]catalogue.Chosen {
|
||||
out := map[string]catalogue.Chosen{}
|
||||
func (h *holding) heldModules(machine string) map[string]heldUnderProvider {
|
||||
out := map[string]heldUnderProvider{}
|
||||
byModule := map[string][]inventory.ResourceHealth{}
|
||||
for _, r := range h.healths[machine].Resources {
|
||||
if r.Module != "" && r.State == link.StateUnhealthy {
|
||||
@@ -174,7 +304,7 @@ func (h *holding) heldModules(machine string) map[string]catalogue.Chosen {
|
||||
}
|
||||
}
|
||||
for module, rs := range byModule {
|
||||
if on, held := h.heldUnder(machine, module, rs); held {
|
||||
if on, held := h.heldWith(machine, module, rs); held {
|
||||
out[module] = on
|
||||
}
|
||||
}
|
||||
|
||||
+123
-23
@@ -249,7 +249,7 @@ func serve(ctx context.Context) (err error) {
|
||||
// (novox/hq to-be 45 §9).
|
||||
checkEvents = bus
|
||||
// And every walk this controller keeps in a new state, for the delivery it walks (novox/hq ADR 0239).
|
||||
inventory.PlanSaved = func(p inventory.Plan) { sayPlanMoved(ctx, bus, p) }
|
||||
inventory.PlanSaved = func(_ *inventory.Inventory, p inventory.Plan) { sayPlanMoved(ctx, bus, open.inventory, p) }
|
||||
if err := server.Checks(following{open}); err != nil {
|
||||
return err
|
||||
}
|
||||
@@ -356,10 +356,16 @@ func declare(ctx context.Context, args []string) error {
|
||||
// the mesh did not compose it, so a push that does not name this machine treats it as held.
|
||||
// The epoch it carried, if a person wrote one in, is what the machine heard.
|
||||
var carried struct {
|
||||
Epoch uint64 `json:"epoch"`
|
||||
Epoch uint64 `json:"epoch"`
|
||||
Sequence int64 `json:"sequence"`
|
||||
Generation int64 `json:"generation"`
|
||||
}
|
||||
_ = json.Unmarshal(raw, &carried)
|
||||
if _, err := recordSent(ctx, inv, node, raw, nil, carried.Epoch); err != nil {
|
||||
// And recorded as every send is (novox/hq issue 234): by hand, from what it carried; the modules it
|
||||
// named are not known, since the mesh did not compose it.
|
||||
if _, err := recordSent(ctx, inv, node, raw, nil, carried.Epoch, sentRecord{sequence: carried.Sequence,
|
||||
epoch: carried.Epoch, generation: carried.Generation, toldGeneration: carried.Generation,
|
||||
sender: senderOf(callerOf(ctx)) + ", a declaration sent by hand"}); err != nil {
|
||||
return err
|
||||
}
|
||||
fmt.Printf("sent %s a signed declaration (%d bytes)\n", node, len(raw))
|
||||
@@ -798,7 +804,7 @@ func composeEach(names []string, allot func(node string) (order, error),
|
||||
refusals = append(refusals, fmt.Sprintf("%s:\n%v", name, err))
|
||||
continue
|
||||
}
|
||||
declared.Sequence, declared.Epoch = numbered.sequence, numbered.epoch
|
||||
numbered.stamp(&declared)
|
||||
if len(declared.Resources) == 0 {
|
||||
// Sent, not skipped (novox/hq issue 127). A node whose declaration composes to
|
||||
// nothing may have HELD something before — the broker opening a placement gave it,
|
||||
@@ -1016,10 +1022,14 @@ func (b overTheBus) declare(ctx context.Context, s readyNode, body []byte) (stri
|
||||
}
|
||||
// After it is away, not before. A digest recorded for something that failed to send would make
|
||||
// the machine look current for a declaration it never received.
|
||||
digest, err := recordSent(ctx, b.open.inventory, s.node, body, s.declared.Builds, s.declared.Epoch)
|
||||
digest, err := recordSent(ctx, b.open.inventory, s.node, body, s.declared.Builds, s.declared.Epoch,
|
||||
sentRecordOf(ctx, s.declared))
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
// A send that carried the mesh's record of the controller and the node-engine — a person's push included —
|
||||
// ends the condition of one kept over it (novox/hq issue 201).
|
||||
settleCoreDowngrades(ctx, b.open.inventory, s.node, s.declared.Builds)
|
||||
if len(s.declared.Bindings) > 0 {
|
||||
// And where it bound each consumer of a provision that keeps its data (novox/hq ADR 0232):
|
||||
// what the next resolution keeps it at. On the same outliving context as the send's record.
|
||||
@@ -1077,42 +1087,58 @@ func brokerFirst(names []string, holder string, behind bool) []string {
|
||||
// send anywhere, and a module running there always put it in its first wave. A digest of the list
|
||||
// last sent is kept for this (ADR 0043: the list is composed on each push, never kept itself).
|
||||
func brokerBehind(ctx context.Context, open *stores, names []string) (string, bool, error) {
|
||||
s, err := brokerListState(ctx, open, names)
|
||||
return s.Machine, s.Behind, err
|
||||
}
|
||||
|
||||
// brokerListState is brokerBehind with why the list could not be composed, when it could not: the plan's own
|
||||
// reason, which a remedy names rather than a push that would fail on it (the review of hq issue 353).
|
||||
func brokerListState(ctx context.Context, open *stores, names []string) (busListState, error) {
|
||||
inv := open.inventory
|
||||
holders, err := seatHolders(ctx, inv)
|
||||
if err != nil {
|
||||
return "", false, err
|
||||
return busListState{}, err
|
||||
}
|
||||
h, held := holders[theBrokerSeat]
|
||||
if !held || h.Node == "" {
|
||||
return "", false, nil
|
||||
return busListState{}, nil
|
||||
}
|
||||
shelf, err := inv.Catalogue(ctx)
|
||||
if err != nil {
|
||||
return "", false, err
|
||||
return busListState{}, err
|
||||
}
|
||||
if m, known := shelf[h.Module]; !known || m.BusUsers == "" {
|
||||
// A holder that is sent no user list carries no grant: nothing to send first.
|
||||
return "", false, nil
|
||||
return busListState{}, nil
|
||||
}
|
||||
for _, n := range names {
|
||||
if n == h.Node {
|
||||
return h.Node, false, nil
|
||||
return busListState{Machine: h.Node}, nil
|
||||
}
|
||||
}
|
||||
// **What cannot be worked out is behind** (the review of hq issue 353). The list it would be sent cannot be
|
||||
// composed, so whether it carries the grants a send relies on is not known; it is taken as behind, so a push
|
||||
// sends that machine first and says why it cannot (`plan` says it too), and a rollout that needs the list
|
||||
// refuses rather than sending code whose grants the bus may not hold. It said "not behind" until then: a
|
||||
// send went ahead as if the bus held a list nobody could compose.
|
||||
list, composeErr := "", error(nil)
|
||||
plan, _, err := planFor(ctx, open, h.Node)
|
||||
if err != nil {
|
||||
// It cannot be worked out: sending it would refuse the whole send, and `plan` says why.
|
||||
return h.Node, false, nil
|
||||
}
|
||||
list, _, err := busUserList(ctx, inv, plan.Modules)
|
||||
if err != nil {
|
||||
return h.Node, false, nil
|
||||
composeErr = err
|
||||
} else if list, _, err = busUserList(ctx, inv, plan.Modules); err != nil {
|
||||
composeErr = err
|
||||
}
|
||||
sent, err := inv.SentBusUsers(ctx, h.Node)
|
||||
if err != nil {
|
||||
return "", false, err
|
||||
return busListState{}, err
|
||||
}
|
||||
return h.Node, userListBehind(list, sent), nil
|
||||
return busListState{Machine: h.Node, Behind: listBehind(list, composeErr, sent), Uncomposed: composeErr}, nil
|
||||
}
|
||||
|
||||
// listBehind is whether the bus's machine is behind: the list composed now is not the one last sent, or it
|
||||
// could not be composed at all — not known is behind, never "not behind".
|
||||
func listBehind(list string, composeErr error, sentDigest string) bool {
|
||||
return composeErr != nil || userListBehind(list, sentDigest)
|
||||
}
|
||||
|
||||
// userListBehind is whether the user list composed now is not the one last sent, by its digest. An
|
||||
@@ -1228,7 +1254,18 @@ func sendToEach(ctx context.Context, open *stores, names []string) ([]string, er
|
||||
refusals = append(refusals, fmt.Sprintf("%s:\n%v", name, err))
|
||||
continue
|
||||
}
|
||||
declared.Sequence, declared.Epoch = numbered.sequence, numbered.epoch
|
||||
numbered.stamp(&declared)
|
||||
// **The grants step sends the user list and nothing else** (novox/hq issue 490): judged on this very
|
||||
// declaration, the one sent, so nothing composed between a check and the send can slip through.
|
||||
if everyBuildKept(ctx, name) {
|
||||
other, err := grantsOnlyIn(ctx, open, name, plan, declared)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if other != "" {
|
||||
return nil, fmt.Errorf("%w: %s", errNotGrantsOnly, other)
|
||||
}
|
||||
}
|
||||
reportLeftOut(name, declared)
|
||||
sending = append(sending, readyNode{name, declared})
|
||||
}
|
||||
@@ -1293,6 +1330,15 @@ func issueMemberships(ctx context.Context, open *stores, server *link.Server, se
|
||||
if _, err := broker.RaiseBuckets(broker.OnConn(bus.Conn), buckets); err != nil {
|
||||
return fmt.Errorf("the modules' state could not be asserted on the bus: %w", err)
|
||||
}
|
||||
// **And every declared log, for the same reason** (novox/hq ADR 0297 §2): a membership names its
|
||||
// logs, and a module whose log does not exist fails its first append.
|
||||
logs, err := open.inventory.DeclaredLogs(ctx)
|
||||
if err != nil {
|
||||
return fmt.Errorf("the modules' logs could not be read, so no log was asserted: %w", err)
|
||||
}
|
||||
if _, err := broker.RaiseLogs(broker.OnConn(bus.Conn), logs); err != nil {
|
||||
return fmt.Errorf("the modules' logs could not be asserted on the bus: %w", err)
|
||||
}
|
||||
// Every membership is tried, and the first failure named once.
|
||||
issued := 0
|
||||
refused := map[string]error{}
|
||||
@@ -1393,6 +1439,11 @@ func wouldSendFrom(ctx context.Context, open *stores,
|
||||
if declared.Epoch, err = open.inventory.SentEpoch(ctx, n.ID); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
// And the generation it was last sent, for the same reason (novox/hq issue 234): an assignment
|
||||
// elsewhere in the mesh is not a change of this machine.
|
||||
if declared.Generation, err = open.inventory.SentGeneration(ctx, n.ID); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
body, err := declared.Body()
|
||||
if err != nil {
|
||||
return nil, err
|
||||
@@ -1471,13 +1522,28 @@ func raiseTheBus(ctx context.Context, inv *inventory.Inventory, address string)
|
||||
fmt.Printf("the bus holds state nothing declares any more, kept because it is data: %s — "+
|
||||
"removing it is a person's act\n", strings.Join(undeclared, ", "))
|
||||
}
|
||||
// Every module's log (novox/hq ADR 0297), from the catalogue, as its buckets: one that nothing
|
||||
// declares any more is said and kept — a log is a module's record, and no path of the mesh removes it.
|
||||
logs, err := inv.DeclaredLogs(ctx)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
unlogged, err := broker.RaiseLogs(js, logs)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
if len(unlogged) > 0 {
|
||||
fmt.Printf("the bus holds logs nothing declares any more, kept because they are data: %s — "+
|
||||
"removing one is a person's act\n", strings.Join(unlogged, ", "))
|
||||
}
|
||||
// And how every module hears what it consumes: asserted with the rest above, counted here.
|
||||
hearing, err := moduleConsumerCount(ctx, inv)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
fmt.Printf("the bus at %s has its streams, %d machine(s) can hear a declaration, %d module(s) "+
|
||||
"can hear what they consume, and %d bucket(s) of state\n", broker.BareAddress(address), len(names), hearing, len(buckets))
|
||||
"can hear what they consume, %d bucket(s) of state and %d log(s)\n", broker.BareAddress(address), len(names), hearing,
|
||||
len(buckets), len(logs))
|
||||
return nil
|
||||
}
|
||||
|
||||
@@ -1531,6 +1597,12 @@ var epochForActs = func(ctx context.Context) (uint64, error) { return theLease.e
|
||||
type order struct {
|
||||
sequence int64
|
||||
epoch uint64
|
||||
// generation is the assignment generation read before the composition, and readsGeneration whether the
|
||||
// machine's node-engine said it reads one (novox/hq issue 234); acting is the lease epoch the sender acts
|
||||
// under, whether or not the machine is sent it — both kept for the record of the send.
|
||||
generation int64
|
||||
readsGeneration bool
|
||||
acting uint64
|
||||
}
|
||||
|
||||
// allot takes the next sequence for a machine — the number its next declaration carries — under the
|
||||
@@ -1544,6 +1616,7 @@ func allot(ctx context.Context, inv *inventory.Inventory, node string) (order, e
|
||||
if err != nil {
|
||||
return order{}, err
|
||||
}
|
||||
acting := epoch
|
||||
if epoch > 0 {
|
||||
reads, err := inv.ReadsEpoch(ctx, record.ID)
|
||||
if err != nil {
|
||||
@@ -1553,11 +1626,24 @@ func allot(ctx context.Context, inv *inventory.Inventory, node string) (order, e
|
||||
epoch = 0
|
||||
}
|
||||
}
|
||||
// **The generation is read here, before the composition reads a single assignment** (novox/hq issue
|
||||
// 234). A generation only grows, so one read before is never newer than the view composed after it:
|
||||
// the declaration may claim a generation older than its content, never newer — and a claim newer than
|
||||
// the content is exactly the stale send the machine must be able to refuse.
|
||||
generation, err := inv.AssignmentGeneration(ctx)
|
||||
if err != nil {
|
||||
return order{}, err
|
||||
}
|
||||
readsGeneration, err := inv.ReadsGeneration(ctx, record.ID)
|
||||
if err != nil {
|
||||
return order{}, err
|
||||
}
|
||||
seq, err := inv.NextSequence(ctx, record.ID)
|
||||
if err != nil {
|
||||
return order{}, err
|
||||
}
|
||||
return order{sequence: seq, epoch: epoch}, nil
|
||||
return order{sequence: seq, epoch: epoch, generation: generation, readsGeneration: readsGeneration,
|
||||
acting: acting}, nil
|
||||
}
|
||||
|
||||
// recordSent writes down what a machine was just sent, and returns the digest.
|
||||
@@ -1572,7 +1658,7 @@ func allot(ctx context.Context, inv *inventory.Inventory, node string) (order, e
|
||||
// And the build of each module it carried (novox/hq issue 259, ADR 0221), nil when that is not known:
|
||||
// what tells a machine held back by a policy or a plan from one a push left behind.
|
||||
func recordSent(ctx context.Context, inv *inventory.Inventory, node string, body []byte,
|
||||
builds map[string]string, epoch uint64) (string, error) {
|
||||
builds map[string]string, epoch uint64, sent sentRecord) (string, error) {
|
||||
kept, cancel := context.WithTimeout(context.WithoutCancel(ctx), 10*time.Second)
|
||||
defer cancel()
|
||||
record, err := inv.NodeByName(kept, node)
|
||||
@@ -1580,7 +1666,21 @@ func recordSent(ctx context.Context, inv *inventory.Inventory, node string, body
|
||||
return "", err
|
||||
}
|
||||
digest := digestOf(body)
|
||||
if err := inv.RecordSentUnder(kept, record.ID, digest, builds, epoch); err != nil {
|
||||
// The digest and the generation it carried are written in one transaction (novox/hq issue 234), so the
|
||||
// would-send is never stamped with a generation the machine was not sent; and the send itself, who sent
|
||||
// it and from which generation, beside them. A record of the send that cannot be written does not make a
|
||||
// send that is away look failed: it is said, loudly, and the machine's own record stands.
|
||||
err = inv.RecordSentWith(kept, record.ID, digest, builds, epoch, sent.toldGeneration, inventory.Send{
|
||||
Sequence: sent.sequence, Epoch: int64(sent.epoch), Sender: sent.sender, Generation: sent.generation,
|
||||
Digest: digest, Modules: sent.modules})
|
||||
var unrecorded *inventory.SendNotRecordedError
|
||||
switch {
|
||||
case errors.As(err, &unrecorded):
|
||||
fmt.Fprintf(os.Stderr, "mesh-controller: SEND NOT RECORDED: %s was sent declaration %s (sequence %d), and who "+
|
||||
"sent it and from which generation could not be written down, so a refusal of it will name no sender "+
|
||||
"(novox/hq issue 234): %v\n", node, short(digest), sent.sequence, unrecorded.Err)
|
||||
fmt.Printf("%s: sent, and the record of who sent it could NOT be written: %v\n", node, unrecorded.Err)
|
||||
case err != nil:
|
||||
return "", err
|
||||
}
|
||||
// And what it was, summarised, so the next push can be compared with it (novox/hq ADR 0217).
|
||||
|
||||
@@ -8,6 +8,7 @@ import (
|
||||
"fmt"
|
||||
"io"
|
||||
"os"
|
||||
"regexp"
|
||||
"sort"
|
||||
"strings"
|
||||
"time"
|
||||
@@ -67,18 +68,95 @@ func listQueue(ctx context.Context, args []string, w io.Writer) error {
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
now := time.Now()
|
||||
if *asJSON {
|
||||
body, err := json.MarshalIndent(q, "", " ")
|
||||
body, err := json.MarshalIndent(queueAnswerOf(q, now), "", " ")
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
fmt.Fprintln(w, string(body))
|
||||
return nil
|
||||
}
|
||||
fmt.Fprint(w, queueText(q, time.Now()))
|
||||
fmt.Fprint(w, queueText(q, now))
|
||||
return nil
|
||||
}
|
||||
|
||||
// queueAnswer is the queue as data (novox/hq issue 455): what a caller reads to say how far back an ask
|
||||
// waits — "waiting in the build queue behind 2" — which the table alone could not tell it. Text is the
|
||||
// table, written from the same read: the verb answers it as its output and the rest as its answer, so the
|
||||
// two never disagree.
|
||||
type queueAnswer struct {
|
||||
Seat string `json:"seat"`
|
||||
Waiting int `json:"waiting"`
|
||||
InFlight int `json:"in-flight"`
|
||||
Dead int `json:"dead"`
|
||||
MaxDeliver int `json:"max-deliver"`
|
||||
Asks []queuedAnswer `json:"asks"`
|
||||
Text string `json:"text"`
|
||||
}
|
||||
|
||||
// queuedAnswer is one ask as data. Never what the request carries beyond its source — not `held`, every
|
||||
// artifact the mesh has built, nor a check's checkouts beside it.
|
||||
type queuedAnswer struct {
|
||||
ID string `json:"id"`
|
||||
State string `json:"state"`
|
||||
// Kind is "check" for a pull request's merge check, "build" for anything else.
|
||||
Kind string `json:"kind"`
|
||||
Repository string `json:"repository"`
|
||||
Path string `json:"path,omitempty"`
|
||||
Ref string `json:"ref,omitempty"`
|
||||
// Commit is the ref when it names a commit; empty when the ask follows a branch or the default.
|
||||
Commit string `json:"commit,omitempty"`
|
||||
// Machine is the one building an ask in flight; WasOn the one that started it and handed it back.
|
||||
Machine string `json:"machine,omitempty"`
|
||||
WasOn string `json:"was-on,omitempty"`
|
||||
AskedAt time.Time `json:"asked-at,omitzero"`
|
||||
// Since is when the ask came to its state: its start on the machine for one in flight that a
|
||||
// machine said it started, otherwise when it was asked.
|
||||
Since time.Time `json:"since,omitzero"`
|
||||
// Position is its place among the waiting, 1 being handed out next; 0 for an ask not waiting.
|
||||
Position int `json:"position,omitempty"`
|
||||
Seq uint64 `json:"seq"`
|
||||
}
|
||||
|
||||
// aCommitRef is a ref that names a commit by its full hash (SHA-1 or SHA-256).
|
||||
var aCommitRef = regexp.MustCompile(`^(?:[0-9a-f]{40}|[0-9a-f]{64})$`)
|
||||
|
||||
// queueAnswerOf is the queue as data, in the table's order: in flight, the waiting from the next one to
|
||||
// be handed out, then the dead. A pure function of one read (novox/hq issue 455).
|
||||
func queueAnswerOf(q link.Queue, now time.Time) queueAnswer {
|
||||
waiting, running, dead := q.Of(link.AskWaiting), q.Of(link.AskInFlight), q.Of(link.AskDead)
|
||||
out := queueAnswer{Seat: q.Seat, Waiting: len(waiting), InFlight: len(running), Dead: len(dead),
|
||||
MaxDeliver: q.MaxDeliver, Asks: []queuedAnswer{}, Text: queueText(q, now)}
|
||||
one := func(a link.QueuedAsk, position int) queuedAnswer {
|
||||
kind := "build"
|
||||
if a.Request.Check != nil {
|
||||
kind = "check"
|
||||
}
|
||||
since := a.AskedAt
|
||||
if a.State == link.AskInFlight && a.On != "" && !a.Started.IsZero() {
|
||||
since = a.Started
|
||||
}
|
||||
commit := ""
|
||||
if aCommitRef.MatchString(a.Ref) {
|
||||
commit = a.Ref
|
||||
}
|
||||
return queuedAnswer{ID: a.ID, State: a.State, Kind: kind, Repository: link.WithoutPassword(a.Repository), Path: a.Path,
|
||||
Ref: a.Ref, Commit: commit, Machine: a.On, WasOn: a.Was, AskedAt: a.AskedAt, Since: since,
|
||||
Position: position, Seq: a.Seq}
|
||||
}
|
||||
for _, a := range running {
|
||||
out.Asks = append(out.Asks, one(a, 0))
|
||||
}
|
||||
for i, a := range waiting {
|
||||
out.Asks = append(out.Asks, one(a, i+1))
|
||||
}
|
||||
for _, a := range dead {
|
||||
out.Asks = append(out.Asks, one(a, 0))
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// queueText is the queue as a person reads it: a summary line, then each kind in queue order.
|
||||
// Never what an ask carries as `held` — that is every artifact the mesh has built.
|
||||
func queueText(q link.Queue, now time.Time) string {
|
||||
@@ -92,7 +170,7 @@ func queueText(q link.Queue, now time.Time) string {
|
||||
return "asked " + now.Sub(t).Round(time.Second).String() + " ago"
|
||||
}
|
||||
what := func(a link.QueuedAsk) string {
|
||||
s := a.Repository
|
||||
s := link.WithoutPassword(a.Repository)
|
||||
if a.Path != "" {
|
||||
s += " at " + a.Path
|
||||
}
|
||||
|
||||
@@ -0,0 +1,137 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"reflect"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/link"
|
||||
)
|
||||
|
||||
// The queue answers as data as well as text (novox/hq issue 455): each ask's repository, commit, kind,
|
||||
// machine, since and position among the waiting, read from the same queue the table is written from.
|
||||
|
||||
const aCommit = "0123456789abcdef0123456789abcdef01234567"
|
||||
|
||||
func aQueueOfEachKind(now time.Time) link.Queue {
|
||||
asked := now.Add(-5 * time.Minute)
|
||||
started := now.Add(-2 * time.Minute)
|
||||
return link.Queue{Seat: link.TheBuildMachine, Delivered: 2, AckPending: 1, MaxDeliver: 5, Asks: []link.QueuedAsk{
|
||||
{Seq: 1, ID: "build-dead", Repository: "ssh://forge/novox/x", AskedAt: asked, State: link.AskDead},
|
||||
{Seq: 2, ID: "build-running", Repository: "ssh://forge/novox/mesh-host", Ref: aCommit, AskedAt: asked,
|
||||
State: link.AskInFlight, On: "ace", Started: started,
|
||||
Request: link.BuildRequest{ID: "build-running", Check: &link.CheckRequest{Owner: "novox", Repo: "mesh-host"}}},
|
||||
{Seq: 3, ID: "build-first", Repository: "ssh://forge/novox/mesh-catalog", Ref: "main", AskedAt: asked,
|
||||
State: link.AskWaiting},
|
||||
{Seq: 4, ID: "build-second", Repository: "ssh://forge/novox/mesh-catalog", Path: "modules/gitea", Ref: aCommit,
|
||||
AskedAt: now.Add(-time.Minute), State: link.AskWaiting,
|
||||
Request: link.BuildRequest{ID: "build-second", Check: &link.CheckRequest{Owner: "novox", Repo: "mesh-catalog"}}},
|
||||
}}
|
||||
}
|
||||
|
||||
func TestTheQueueVerbAnswersEachAskAsData(t *testing.T) {
|
||||
now := time.Date(2026, 10, 12, 12, 0, 0, 0, time.UTC)
|
||||
q := aQueueOfEachKind(now)
|
||||
got := queueAnswerOf(q, now)
|
||||
if got.Waiting != 2 || got.InFlight != 1 || got.Dead != 1 || got.Seat != link.TheBuildMachine {
|
||||
t.Fatalf("counts: %+v", got)
|
||||
}
|
||||
if got.Text != queueText(q, now) {
|
||||
t.Fatalf("the data's text is not the table read from the same queue:\n%s", got.Text)
|
||||
}
|
||||
byID := map[string]queuedAnswer{}
|
||||
for _, a := range got.Asks {
|
||||
byID[a.ID] = a
|
||||
}
|
||||
running := byID["build-running"]
|
||||
if running.Kind != "check" || running.Machine != "ace" || running.Commit != aCommit || running.Position != 0 ||
|
||||
!running.Since.Equal(now.Add(-2*time.Minute)) || running.State != link.AskInFlight {
|
||||
t.Errorf("in flight: %+v", running)
|
||||
}
|
||||
first, second := byID["build-first"], byID["build-second"]
|
||||
if first.Position != 1 || first.Kind != "build" || first.Commit != "" || first.Ref != "main" || first.Machine != "" ||
|
||||
!first.Since.Equal(now.Add(-5*time.Minute)) {
|
||||
t.Errorf("first waiting: %+v", first)
|
||||
}
|
||||
if second.Position != 2 || second.Kind != "check" || second.Commit != aCommit || second.Path != "modules/gitea" ||
|
||||
second.Repository != "ssh://forge/novox/mesh-catalog" {
|
||||
t.Errorf("second waiting: %+v", second)
|
||||
}
|
||||
if dead := byID["build-dead"]; dead.Position != 0 || dead.State != link.AskDead {
|
||||
t.Errorf("dead: %+v", dead)
|
||||
}
|
||||
// In the table's order: in flight, then the waiting by position, then the dead.
|
||||
var order []string
|
||||
for _, a := range got.Asks {
|
||||
order = append(order, a.ID)
|
||||
}
|
||||
if want := []string{"build-running", "build-first", "build-second", "build-dead"}; !reflect.DeepEqual(order, want) {
|
||||
t.Errorf("order %v, want %v", order, want)
|
||||
}
|
||||
}
|
||||
|
||||
// The verb asks its command for JSON, and its answer carries the data while its output stays the table a
|
||||
// person reads, so a text caller reads what it always did.
|
||||
func TestTheQueueVerbKeepsTheTableAndCarriesTheData(t *testing.T) {
|
||||
argv, err := argvFor("queue", nil)
|
||||
if err != nil || !reflect.DeepEqual(argv, []string{"queue", "--json"}) {
|
||||
t.Fatalf("queue's command line: %v %v", argv, err)
|
||||
}
|
||||
now := time.Now()
|
||||
q := aQueueOfEachKind(now)
|
||||
body, err := json.Marshal(queueAnswerOf(q, now))
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
answer := answerOf(argv, body, "", true)
|
||||
if answer.Output != queueText(q, now) {
|
||||
t.Fatalf("the output is not the table:\n%s", answer.Output)
|
||||
}
|
||||
data, ok := answer.Answer.(map[string]any)
|
||||
if !ok {
|
||||
t.Fatalf("no data: %#v", answer.Answer)
|
||||
}
|
||||
if _, doubled := data["text"]; doubled {
|
||||
t.Error("the table is said twice: once as the output and again inside the data")
|
||||
}
|
||||
asks, _ := data["asks"].([]any)
|
||||
if len(asks) != 4 || data["waiting"] != float64(2) {
|
||||
t.Fatalf("data: %v", data)
|
||||
}
|
||||
second := asks[2].(map[string]any)
|
||||
if second["position"] != float64(2) || second["kind"] != "check" || second["commit"] != aCommit {
|
||||
t.Errorf("second waiting: %v", second)
|
||||
}
|
||||
for _, a := range asks {
|
||||
if _, held := a.(map[string]any)["held"]; held {
|
||||
t.Error("an ask carries what the mesh holds")
|
||||
}
|
||||
}
|
||||
// A failure is said as text, as before.
|
||||
failed := answerOf(argv, nil, "mesh-controller: the bus cannot be reached\n", false)
|
||||
if failed.Answer != nil || !strings.Contains(failed.Output, "cannot be reached") {
|
||||
t.Errorf("a failure: %+v", failed)
|
||||
}
|
||||
}
|
||||
|
||||
// A repository named with a password never shows it, in the table or the data.
|
||||
func TestTheQueueNeverShowsARepositorysPassword(t *testing.T) {
|
||||
if got := link.WithoutPassword("https://agent:s3cret@forge.example/novox/x.git"); strings.Contains(got, "s3cret") ||
|
||||
!strings.Contains(got, "agent@forge.example/novox/x.git") {
|
||||
t.Errorf("redacted: %s", got)
|
||||
}
|
||||
now := time.Now()
|
||||
q := link.Queue{Seat: link.TheBuildMachine, Asks: []link.QueuedAsk{{Seq: 1, ID: "build-1",
|
||||
Repository: "https://agent:s3cret@forge.example/novox/x.git", State: link.AskWaiting}}}
|
||||
body, _ := json.Marshal(queueAnswerOf(q, now))
|
||||
if strings.Contains(string(body), "s3cret") {
|
||||
t.Errorf("the queue said a password: %s", body)
|
||||
}
|
||||
for _, kept := range []string{"ssh://git@forge:222/novox/x.git", "novox/x", "git@forge:novox/x.git", ""} {
|
||||
if got := link.WithoutPassword(kept); got != kept {
|
||||
t.Errorf("%q became %q", kept, got)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -326,7 +326,7 @@ func TestTheQueueVerbsRunTheirCommands(t *testing.T) {
|
||||
args map[string]any
|
||||
want []string
|
||||
}{
|
||||
{"queue", nil, []string{"queue"}},
|
||||
{"queue", nil, []string{"queue", "--json"}},
|
||||
{"cancel", map[string]any{"id": "build-1"}, []string{"cancel", "build-1"}},
|
||||
{"clear", nil, []string{"clear"}},
|
||||
{"clear", map[string]any{"dead": "true"}, []string{"clear", "--dead"}},
|
||||
|
||||
@@ -69,6 +69,9 @@ type meshStatus struct {
|
||||
// **A document without this said an outage was a well mesh.** Read from what each machine
|
||||
// reported, so it is the machine's account and not the mesh's take-time listing.
|
||||
Untaken []machineUntaken `json:"untaken,omitempty"`
|
||||
// NotApplied is every module assigned to a machine and left out of its composition, with why (novox/hq
|
||||
// issue 380). Absent when every module composes.
|
||||
NotApplied []machineNotApplied `json:"not-applied,omitempty"`
|
||||
// Filtered is every converged machine that is not filtered by the mesh alone (novox/hq ADR
|
||||
// 0168), one entry per rule set the mesh did not write — the found firewall in force again,
|
||||
// or a chain nobody speaks for. Absent when every converged machine is filtered by the mesh
|
||||
@@ -106,6 +109,33 @@ type meshStatus struct {
|
||||
// why they could not be read.
|
||||
Pending []pendingStatus `json:"pending,omitempty"`
|
||||
PendingUnread string `json:"pendingUnread,omitempty"`
|
||||
// LastSent is every machine's last recorded send — who sent it, under which lease epoch, from which
|
||||
// assignment generation, naming which modules — and what the machine answered of it (novox/hq issue 485).
|
||||
// A machine the mesh has recorded no send to is absent. LastSentUnread says why it could not be read.
|
||||
LastSent []machineLastSent `json:"lastSent"`
|
||||
LastSentUnread string `json:"lastSentUnread,omitempty"`
|
||||
}
|
||||
|
||||
// machineLastSent is one machine's last send as status says it.
|
||||
type machineLastSent struct {
|
||||
Node string `json:"node"`
|
||||
Sequence int64 `json:"sequence"`
|
||||
SentAt time.Time `json:"sentAt"`
|
||||
Sender string `json:"sender"`
|
||||
Epoch int64 `json:"epoch"`
|
||||
Generation int64 `json:"generation"`
|
||||
Digest string `json:"digest"`
|
||||
Modules []string `json:"modules"`
|
||||
// Answer is what the machine said of it: applied, failed or refused, as its report has it; empty when it
|
||||
// has not reported on it. Refused is its words when it refused it whole, Failed how many resources failed.
|
||||
Answer string `json:"answer"`
|
||||
Refused string `json:"refused,omitempty"`
|
||||
Failed int `json:"failed,omitempty"`
|
||||
AnsweredAt *time.Time `json:"answeredAt,omitempty"`
|
||||
// RefusedForGeneration is when the machine refused it for coming from an older assignment generation than
|
||||
// it applied, and AppliedGeneration that generation; absent when it did not.
|
||||
RefusedForGeneration *time.Time `json:"refusedForGeneration,omitempty"`
|
||||
AppliedGeneration int64 `json:"appliedGeneration,omitempty"`
|
||||
}
|
||||
|
||||
// pendingStatus is one pending assignment as status says it.
|
||||
@@ -251,6 +281,7 @@ func statusAsJSON(asked answers) ([]byte, error) {
|
||||
}
|
||||
}
|
||||
out.Unheld = asked.unheld
|
||||
out.NotApplied = notApplied(asked.leftOut)
|
||||
out.HandActsThisWeek, out.HandActsUnread = asked.handActs, asked.handActsUnread
|
||||
out.HealsThisWeek, out.HealsUnread = asked.heals, asked.healsUnread
|
||||
// In brief, as `conditions` lists them: status leads with every open condition, and their whole
|
||||
@@ -263,6 +294,7 @@ func statusAsJSON(asked answers) ([]byte, error) {
|
||||
out.Pending = append(out.Pending, pendingStatus{Node: p.Node, Module: p.Module, State: p.State,
|
||||
Build: p.Build, Repository: p.Repository, Path: p.Path, Since: p.Since, Settled: p.Settled, Note: p.Note})
|
||||
}
|
||||
out.LastSent, out.LastSentUnread = lastSentStatus(asked.lastSent), asked.lastSentUnread
|
||||
for name := range asked.refused {
|
||||
out.Unresolved = append(out.Unresolved, machineUnresolved{
|
||||
Node: name, Problem: asked.refused[name]})
|
||||
@@ -319,3 +351,20 @@ func say(value any) error {
|
||||
fmt.Println(string(body))
|
||||
return nil
|
||||
}
|
||||
|
||||
// lastSentStatus is every machine's last send as status --json says it, by machine name (novox/hq issue 485).
|
||||
func lastSentStatus(sends map[string]inventory.Send) []machineLastSent {
|
||||
out := []machineLastSent{}
|
||||
for _, s := range sends {
|
||||
modules := s.Modules
|
||||
if modules == nil {
|
||||
modules = []string{}
|
||||
}
|
||||
out = append(out, machineLastSent{Node: s.NodeName, Sequence: s.Sequence, SentAt: s.SentAt, Sender: s.Sender,
|
||||
Epoch: s.Epoch, Generation: s.Generation, Digest: s.Digest, Modules: modules, Answer: s.Answer.Outcome,
|
||||
Refused: s.Answer.Refused, Failed: s.Answer.Failed, AnsweredAt: s.Answer.At,
|
||||
RefusedForGeneration: s.RefusedAt, AppliedGeneration: s.RefusedApplied})
|
||||
}
|
||||
sort.Slice(out, func(i, j int) bool { return out[i].Node < out[j].Node })
|
||||
return out
|
||||
}
|
||||
|
||||
@@ -80,7 +80,7 @@ func TestAVerbsOwnProcessNamesItsConnection(t *testing.T) {
|
||||
// A silence acts, so it is still its own process; it dials, and finds no such condition.
|
||||
_, _ = handlers["conditions"](context.Background(),
|
||||
json.RawMessage(`{"silence":"bus.nothing.here","for":"1h","why":"a test"}`))
|
||||
names := closedNames(t, bus)
|
||||
names := closedNames(t, bus, "mesh-controller verb conditions")
|
||||
found := false
|
||||
for _, n := range names {
|
||||
found = found || n == "mesh-controller verb conditions"
|
||||
|
||||
@@ -61,20 +61,57 @@ func keptExcept(ctx context.Context) (map[string]bool, bool) {
|
||||
return skip, on
|
||||
}
|
||||
|
||||
type keepEveryBuildKey struct{}
|
||||
|
||||
// keepingEveryBuild is a context whose sends compose every module of one machine — recorded or rolling out —
|
||||
// at the build that machine was last sent (novox/hq issue 490): the grants step, which sends the machine
|
||||
// holding the bus its new user list and nothing of any module's new code. That code waits there for a gate
|
||||
// like any other move; the list must not, or the first machine's gate is judged against a bus that refuses
|
||||
// what the change newly grants.
|
||||
//
|
||||
// **That machine alone.** Composing one machine resolves the others too — who is on the private network,
|
||||
// who answers a requirement — on the same context, and those are no part of the step's send: they are
|
||||
// composed as any send composes them. Kept for every machine, a machine whose last send is not known
|
||||
// refused the bus's machine's composition.
|
||||
func keepingEveryBuild(ctx context.Context, node string) context.Context {
|
||||
return context.WithValue(ctx, keepEveryBuildKey{}, node)
|
||||
}
|
||||
|
||||
// everyBuildKept is whether this context keeps every module of this machine at the build it runs.
|
||||
func everyBuildKept(ctx context.Context, node string) bool {
|
||||
on, _ := ctx.Value(keepEveryBuildKey{}).(string)
|
||||
return on != "" && on == node
|
||||
}
|
||||
|
||||
// recordedKept is, for a send under keepingRecorded, every recorded module the machine was last sent a
|
||||
// build of that the mesh's build is not identical to: module → the commit it keeps. Nil when the context
|
||||
// keeps nothing, or when what the machine was last sent is not known (it is then held whole elsewhere —
|
||||
// ADR 0221).
|
||||
//
|
||||
// Under keepingEveryBuild, every module the machine was sent is kept, whatever its policy (novox/hq issue
|
||||
// 490), and a machine whose last send is not known refuses the send: there is nothing to keep it at, and
|
||||
// composing the mesh's builds would be the very move the grants step must not make.
|
||||
func recordedKept(ctx context.Context, open *stores, node string) (map[string]string, error) {
|
||||
every := everyBuildKept(ctx, node)
|
||||
skip, on := keptExcept(ctx)
|
||||
if !on {
|
||||
if !on && !every {
|
||||
return nil, nil
|
||||
}
|
||||
if every {
|
||||
skip = nil
|
||||
}
|
||||
inv := open.inventory
|
||||
sent, known, err := inv.SentBuilds(ctx, node)
|
||||
if err != nil || !known {
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if !known {
|
||||
if every {
|
||||
return nil, fmt.Errorf("what %s was last sent is not known, so the bus's user list cannot be sent "+
|
||||
"there alone with every build kept (novox/hq issue 490)", node)
|
||||
}
|
||||
return nil, nil
|
||||
}
|
||||
current, err := inv.CurrentBuilds(ctx)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
@@ -83,7 +120,7 @@ func recordedKept(ctx context.Context, open *stores, node string) (map[string]st
|
||||
out := map[string]string{}
|
||||
for m, was := range sent {
|
||||
now, held := current[m]
|
||||
if !held || now.RollOut || skip[m] || was == "" || sameCommit(was, now.Commit) {
|
||||
if !held || (now.RollOut && !every) || skip[m] || was == "" || sameCommit(was, now.Commit) {
|
||||
continue
|
||||
}
|
||||
if f == nil {
|
||||
@@ -98,6 +135,17 @@ func recordedKept(ctx context.Context, open *stores, node string) (map[string]st
|
||||
}
|
||||
out[m] = was
|
||||
}
|
||||
// **And the controller and the node-engine at the build the machine was last sent, over an older record**
|
||||
// (novox/hq issue 201, core_downgrade.go). Under keepingEveryBuild they are kept already.
|
||||
if !every {
|
||||
core, err := coreKept(ctx, inv, node, sent, current)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
for m, was := range core {
|
||||
out[m] = was
|
||||
}
|
||||
}
|
||||
return out, nil
|
||||
}
|
||||
|
||||
@@ -118,6 +166,16 @@ func keepRecorded(ctx context.Context, open *stores, node string, shelf map[stri
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if !found && everyBuildKept(ctx, node) {
|
||||
return nil, fmt.Errorf("%s runs %s's build %s, which the build records no longer hold: the bus's user "+
|
||||
"list cannot be sent there alone with it kept (novox/hq issue 490)", node, m, short(kept[m]))
|
||||
}
|
||||
if !found && guarded(coreComponent(m)) {
|
||||
return nil, fmt.Errorf("%s was last sent %s's build %s, newer than the one the mesh holds, and the build records "+
|
||||
"no longer hold it: this send cannot keep it and does not move it back — `push %s` sends the older build on "+
|
||||
"a person's word, and a newer merge or `rebuild %s` moves the record forward (novox/hq issue 201)",
|
||||
node, m, short(kept[m]), node, m)
|
||||
}
|
||||
if !found {
|
||||
return nil, fmt.Errorf("%s records rather than rolls out, and %s runs its build %s, which the build "+
|
||||
"records no longer hold: this send cannot keep it and does not move it — `push %s` sends the new "+
|
||||
|
||||
@@ -0,0 +1,111 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"sort"
|
||||
"strings"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
)
|
||||
|
||||
// What relates two changes (novox/hq ADR 0304 decision 1, as ADR 0306 decision 3 reads it): two changes are
|
||||
// related when they share a repository, a module, a delivery group's head, or an edge of the module graph
|
||||
// between their modules. A module is every one the walk builds or sends: the modules its merges moved and the
|
||||
// modules that depend on them, not only the ones the merges touched. Unrelated changes may walk beside each
|
||||
// other (ADR 0304 decision 2, ADR 0282 decision 3); nothing walks so yet, and nothing but tests reads this.
|
||||
|
||||
// footprint is what one change reaches: its repositories (lower case), its modules, and its delivery group
|
||||
// heads (the head branch names of its merges). unknown says a merge of it was kept without the modules it
|
||||
// moves, so what it reaches is not known: it is related to every change, never wrongly to none.
|
||||
type footprint struct {
|
||||
repos, modules, heads map[string]bool
|
||||
unknown string
|
||||
}
|
||||
|
||||
func newFootprint() footprint {
|
||||
return footprint{repos: map[string]bool{}, modules: map[string]bool{}, heads: map[string]bool{}}
|
||||
}
|
||||
|
||||
// footprintOfWalk is a walk's footprint: the repositories it carries and the modules it plans. A walk keeps no
|
||||
// head of its merges; kept are the merges the record holds for it, whose announcements say their heads, and
|
||||
// may be nil.
|
||||
func footprintOfWalk(p inventory.Plan, kept []inventory.BatchedMerge) footprint {
|
||||
f := newFootprint()
|
||||
for _, c := range p.Carried() {
|
||||
f.repos[strings.ToLower(c.Repository)] = true
|
||||
}
|
||||
for name := range p.Modules {
|
||||
f.modules[name] = true
|
||||
}
|
||||
for _, m := range kept {
|
||||
f.repos[strings.ToLower(m.Repository)] = true
|
||||
if h := announcedOf(m).Head; h != "" {
|
||||
f.heads[h] = true
|
||||
}
|
||||
}
|
||||
return f
|
||||
}
|
||||
|
||||
// footprintOfBatch is an assembling batch's footprint: each merge's repository and head, and the modules its
|
||||
// merges moved when heard, widened to their dependents (planOfMoves). A merge kept with no moves (one owed a
|
||||
// later look, or kept for its packaging) is judged again at the cut and may move anything then: its batch is
|
||||
// unknown, related to everything.
|
||||
func footprintOfBatch(merges []inventory.BatchedMerge, edges []inventory.Edge) footprint {
|
||||
f := newFootprint()
|
||||
var moved []string
|
||||
for _, m := range merges {
|
||||
k := announcedOf(m)
|
||||
f.repos[strings.ToLower(m.Repository)] = true
|
||||
if k.Head != "" {
|
||||
f.heads[k.Head] = true
|
||||
}
|
||||
if len(k.Moves) == 0 && f.unknown == "" {
|
||||
f.unknown = "the modules a merge of " + m.Repository + " moves are not known until its batch is cut"
|
||||
}
|
||||
moved = append(moved, k.Moves...)
|
||||
}
|
||||
for _, name := range reachableFrom(moved, edges) {
|
||||
f.modules[name] = true
|
||||
}
|
||||
return f
|
||||
}
|
||||
|
||||
// related says whether two changes are related, and the first reason in plain words; false and empty when
|
||||
// they are not.
|
||||
func related(a, b footprint, edges []inventory.Edge) (bool, string) {
|
||||
if a.unknown != "" {
|
||||
return true, a.unknown
|
||||
}
|
||||
if b.unknown != "" {
|
||||
return true, b.unknown
|
||||
}
|
||||
if r := firstShared(a.repos, b.repos); r != "" {
|
||||
return true, "both change " + r
|
||||
}
|
||||
if m := firstShared(a.modules, b.modules); m != "" {
|
||||
return true, "both move " + m
|
||||
}
|
||||
if h := firstShared(a.heads, b.heads); h != "" {
|
||||
return true, "both are members of group " + h
|
||||
}
|
||||
for _, e := range edges {
|
||||
if a.modules[e.From] && b.modules[e.To] || b.modules[e.From] && a.modules[e.To] {
|
||||
return true, e.From + " depends on " + e.To + " (" + e.Kind + ")"
|
||||
}
|
||||
}
|
||||
return false, ""
|
||||
}
|
||||
|
||||
// firstShared is the first key, in order, both sets hold; empty when none.
|
||||
func firstShared(a, b map[string]bool) string {
|
||||
var both []string
|
||||
for k := range a {
|
||||
if b[k] {
|
||||
both = append(both, k)
|
||||
}
|
||||
}
|
||||
if len(both) == 0 {
|
||||
return ""
|
||||
}
|
||||
sort.Strings(both)
|
||||
return both[0]
|
||||
}
|
||||
@@ -0,0 +1,110 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
"github.com/novox/mesh-controller/internal/link"
|
||||
)
|
||||
|
||||
// heardMerge is a kept merge of a repository from a head branch that moved modules.
|
||||
func heardMerge(repository, head string, moves ...string) inventory.BatchedMerge {
|
||||
m := inventory.BatchedMerge{Repository: repository, Branch: "main", Commit: "c-" + repository}
|
||||
m.Event, _ = json.Marshal(keptMerge{SourceMoved: link.SourceMoved{Head: head}, Moves: moves})
|
||||
return m
|
||||
}
|
||||
|
||||
// walkOf is a walk carrying one repository's commit and planning modules.
|
||||
func walkOf(repository string, modules ...string) inventory.Plan {
|
||||
p := inventory.Plan{Repository: repository, Commit: "w-" + repository, Modules: map[string]*inventory.PlanModule{}}
|
||||
for _, name := range modules {
|
||||
p.Modules[name] = &inventory.PlanModule{}
|
||||
}
|
||||
return p
|
||||
}
|
||||
|
||||
// TestRelatedChanges: two changes are related by a repository, a module, a group head or a graph edge between
|
||||
// their modules, and by a module reached only through dependents (novox/hq ADR 0304 decision 1, ADR 0306
|
||||
// decision 3); otherwise they are not.
|
||||
func TestRelatedChanges(t *testing.T) {
|
||||
edges := []inventory.Edge{
|
||||
{From: "nzbget", To: "base-image", Kind: inventory.EdgeStandsOn},
|
||||
{From: "app", To: "build-machine", Kind: inventory.EdgeBuiltBy},
|
||||
}
|
||||
cases := []struct {
|
||||
name string
|
||||
a, b footprint
|
||||
why string
|
||||
}{
|
||||
{"repository, case aside",
|
||||
footprintOfWalk(walkOf("novox/Mesh-Catalog", "notes"), nil),
|
||||
footprintOfBatch([]inventory.BatchedMerge{heardMerge("NOVOX/mesh-catalog", "fix/a", "app")}, nil),
|
||||
"both change novox/mesh-catalog"},
|
||||
{"module",
|
||||
footprintOfWalk(walkOf("novox/one", "nzbget"), nil),
|
||||
footprintOfBatch([]inventory.BatchedMerge{heardMerge("novox/two", "fix/b", "nzbget")}, nil),
|
||||
"both move nzbget"},
|
||||
{"edge, walk depends on batch",
|
||||
footprintOfWalk(walkOf("novox/one", "nzbget"), nil),
|
||||
footprintOfBatch([]inventory.BatchedMerge{heardMerge("novox/two", "fix/b", "base-image")}, nil),
|
||||
"nzbget depends on base-image (stands-on)"},
|
||||
{"edge, batch depends on walk",
|
||||
footprintOfWalk(walkOf("novox/one", "build-machine"), nil),
|
||||
footprintOfBatch([]inventory.BatchedMerge{heardMerge("novox/two", "fix/b", "app")}, nil),
|
||||
"app depends on build-machine (built-by)"},
|
||||
{"group head",
|
||||
footprintOfWalk(walkOf("novox/one", "notes"), []inventory.BatchedMerge{heardMerge("novox/one", "feat/x")}),
|
||||
footprintOfBatch([]inventory.BatchedMerge{heardMerge("novox/two", "feat/x", "app")}, nil),
|
||||
"both are members of group feat/x"},
|
||||
{"module reached through dependents",
|
||||
footprintOfWalk(walkOf("novox/one", "nzbget"), nil),
|
||||
footprintOfBatch([]inventory.BatchedMerge{heardMerge("novox/two", "fix/b", "base-image")}, edges),
|
||||
"both move nzbget"},
|
||||
{"unrelated",
|
||||
footprintOfWalk(walkOf("novox/one", "notes"), []inventory.BatchedMerge{heardMerge("novox/one", "feat/x")}),
|
||||
footprintOfBatch([]inventory.BatchedMerge{heardMerge("novox/two", "feat/y", "app")}, edges),
|
||||
""},
|
||||
}
|
||||
for _, c := range cases {
|
||||
t.Run(c.name, func(t *testing.T) {
|
||||
for _, pair := range [][2]footprint{{c.a, c.b}, {c.b, c.a}} {
|
||||
is, why := related(pair[0], pair[1], edges)
|
||||
if is != (c.why != "") || why != c.why {
|
||||
t.Errorf("related = %v, %q; want %q", is, why, c.why)
|
||||
}
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// TestFootprintOfBatchWidensToDependents: a batch's modules are what its merges moved and every module that
|
||||
// depends on them, along the edges that widen a walk.
|
||||
func TestFootprintOfBatchWidensToDependents(t *testing.T) {
|
||||
edges := []inventory.Edge{
|
||||
{From: "nzbget", To: "base-image", Kind: inventory.EdgeStandsOn},
|
||||
{From: "base-image", To: "build-machine", Kind: inventory.EdgeBuiltBy},
|
||||
}
|
||||
f := footprintOfBatch([]inventory.BatchedMerge{heardMerge("novox/two", "", "base-image")}, edges)
|
||||
if !f.modules["base-image"] || !f.modules["nzbget"] || f.modules["build-machine"] || len(f.heads) != 0 {
|
||||
t.Errorf("footprint = %+v; want base-image and nzbget, no head", f)
|
||||
}
|
||||
}
|
||||
|
||||
// A batch holding a merge kept with no moves (one owed a later look, judged again at the cut) is related to
|
||||
// every change, in both orders: what it will move is not known, and an unknown change is never unrelated
|
||||
// (issue 525 review).
|
||||
func TestABatchWhoseMovesAreNotKnownIsRelatedToEverything(t *testing.T) {
|
||||
unknown := footprintOfBatch([]inventory.BatchedMerge{heardMerge("novox/one", "fix/a", "app"), heardMerge("novox/two", "fix/b")}, nil)
|
||||
other := footprintOfWalk(walkOf("novox/three", "nzbget"), nil)
|
||||
for _, pair := range [][2]footprint{{unknown, other}, {other, unknown}} {
|
||||
if ok, why := related(pair[0], pair[1], nil); !ok || !strings.Contains(why, "not known") {
|
||||
t.Fatalf("an unknown batch read as %v (%q)", ok, why)
|
||||
}
|
||||
}
|
||||
known := footprintOfBatch([]inventory.BatchedMerge{heardMerge("novox/one", "fix/a", "app")}, nil)
|
||||
if ok, why := related(known, other, nil); ok {
|
||||
t.Fatalf("a known, unrelated batch read as related: %q", why)
|
||||
}
|
||||
}
|
||||
+228
-19
@@ -2,6 +2,7 @@ package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"flag"
|
||||
"fmt"
|
||||
@@ -50,6 +51,9 @@ type sendScope struct {
|
||||
modules map[string]bool
|
||||
// person is a person's act: it carries what it carries.
|
||||
person bool
|
||||
// puttingBack is a gate's own put-back of its modules: the one send that may carry a core module to a build
|
||||
// older than the one its machine runs (novox/hq issue 201).
|
||||
puttingBack bool
|
||||
}
|
||||
|
||||
type sendScopeKey struct{}
|
||||
@@ -236,6 +240,32 @@ var machineMoves = func(ctx context.Context, open *stores, f moveFacts, node str
|
||||
return f.moves(node, modules, sent, known, all), nil
|
||||
}
|
||||
|
||||
// withoutKept is a machine's moves less those its send keeps at the build the machine was last sent, and so does
|
||||
// not make: the grants step keeps every module (novox/hq issue 490), and every send keeps the controller and the
|
||||
// node-engine over an older record (issue 201). Read as the send composes it (sendKeeps, set after the checks that
|
||||
// call this), so a move it could not keep is still counted.
|
||||
func withoutKept(ctx context.Context, open *stores, node string, moves []inventory.CarriedMove) ([]inventory.CarriedMove, error) {
|
||||
if len(moves) == 0 {
|
||||
return moves, nil
|
||||
}
|
||||
keeping := ctx
|
||||
if _, on := keptExcept(ctx); !on {
|
||||
keeping = keepingRecorded(ctx)
|
||||
}
|
||||
keeps, err := recordedKept(keeping, open, node)
|
||||
if err != nil || len(keeps) == 0 {
|
||||
return moves, err
|
||||
}
|
||||
var out []inventory.CarriedMove
|
||||
for _, mv := range moves {
|
||||
if was, kept := keeps[mv.Module]; kept && sameCommit(was, mv.From) {
|
||||
continue
|
||||
}
|
||||
out = append(out, mv)
|
||||
}
|
||||
return out, nil
|
||||
}
|
||||
|
||||
// ungatedIn refuses a send whose machines would move a build no gate has seen, outside its scope: the
|
||||
// machines named, and why; the machine holding the bus, added only for its user list, is left instead.
|
||||
func ungatedIn(ctx context.Context, open *stores, names []string, addedHolder string) ([]string, error) {
|
||||
@@ -253,6 +283,9 @@ func ungatedIn(ctx context.Context, open *stores, names []string, addedHolder st
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if moves, err = withoutKept(ctx, open, n, moves); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
var waiting []string
|
||||
for _, mv := range moves {
|
||||
if !scope.judged[n] && !scope.modules[mv.Module] {
|
||||
@@ -283,15 +316,23 @@ func ungatedIn(ctx context.Context, open *stores, names []string, addedHolder st
|
||||
// owns are the moves the send exists for — every module of a plan's tier whose first machine this is, in
|
||||
// one send (novox/hq issue 281): a send carries the machine's whole declaration (ADR 0221), so a send per
|
||||
// module was the same declaration sent again and again, each one setting aside the one before.
|
||||
func gatedSend(ctx context.Context, open *stores, node string, owns []inventory.CarriedMove) ([]inventory.CarriedMove, []string, error) {
|
||||
//
|
||||
// And the grants step first, when the send changes what the bus's user list must say (novox/hq issue 490):
|
||||
// answered for the gate to keep, nil when there was none.
|
||||
func gatedSend(ctx context.Context, open *stores, node string, owns []inventory.CarriedMove) ([]inventory.CarriedMove, []string, *inventory.GrantsStep, error) {
|
||||
inv := open.inventory
|
||||
f, err := readMoveFacts(ctx, inv)
|
||||
if err != nil {
|
||||
return nil, nil, err
|
||||
return nil, nil, nil, err
|
||||
}
|
||||
moves, err := machineMoves(ctx, open, f, node, true)
|
||||
if err != nil {
|
||||
return nil, nil, err
|
||||
return nil, nil, nil, err
|
||||
}
|
||||
// A move the send keeps is not made, and is no move for the gate to judge (novox/hq issue 201): a core module
|
||||
// kept over an older record judged as moving back to it would read the gate as superseded by its own send.
|
||||
if moves, err = withoutKept(ctx, open, node, moves); err != nil {
|
||||
return nil, nil, nil, err
|
||||
}
|
||||
own := func(module string) bool {
|
||||
return slices.ContainsFunc(owns, func(o inventory.CarriedMove) bool { return o.Module == module })
|
||||
@@ -301,7 +342,7 @@ func gatedSend(ctx context.Context, open *stores, node string, owns []inventory.
|
||||
continue
|
||||
}
|
||||
if id := f.walkedBy(mv.Module, node, mv.To); id != "" {
|
||||
return nil, nil, fmt.Errorf("%w: %s's build %s waits on %s, which %s is walking", errWalkedElsewhere,
|
||||
return nil, nil, nil, fmt.Errorf("%w: %s's build %s waits on %s, which %s is walking", errWalkedElsewhere,
|
||||
mv.Module, short(mv.To), node, id)
|
||||
}
|
||||
}
|
||||
@@ -309,7 +350,7 @@ func gatedSend(ctx context.Context, open *stores, node string, owns []inventory.
|
||||
// plan, or a release, on this machine is not crossed with a newer build; this send waits for its gate.
|
||||
for _, o := range owns {
|
||||
if id := f.walkedBy(o.Module, node, o.To); id != "" {
|
||||
return nil, nil, fmt.Errorf("%w: %s's build %s waits on %s, which %s is walking", errWalkedElsewhere,
|
||||
return nil, nil, nil, fmt.Errorf("%w: %s's build %s waits on %s, which %s is walking", errWalkedElsewhere,
|
||||
o.Module, short(o.To), node, id)
|
||||
}
|
||||
}
|
||||
@@ -323,22 +364,22 @@ func gatedSend(ctx context.Context, open *stores, node string, owns []inventory.
|
||||
}
|
||||
}
|
||||
if len(moves) == 0 && len(owns) == 0 {
|
||||
return nil, nil, nil
|
||||
return nil, nil, nil, nil
|
||||
}
|
||||
for i := range moves {
|
||||
if moves[i].Build == "" {
|
||||
if moves[i].Build, err = inv.BuildOf(ctx, moves[i].Module, moves[i].To); err != nil {
|
||||
return nil, nil, err
|
||||
return nil, nil, nil, err
|
||||
}
|
||||
}
|
||||
}
|
||||
sort.Slice(moves, func(i, j int) bool { return moves[i].Module < moves[j].Module })
|
||||
sayRecreations(ctx, open, moves)
|
||||
sent, err := sendRollout(withScope(ctx, sendScope{judged: map[string]bool{node: true}}), open, []string{node})
|
||||
sent, grants, err := sendJudged(ctx, open, node)
|
||||
if err != nil {
|
||||
return nil, nil, err
|
||||
return nil, nil, nil, err
|
||||
}
|
||||
return moves, sent, nil
|
||||
return moves, sent, grants, nil
|
||||
}
|
||||
|
||||
// passCarried keeps a pass as the verdict of every build the gate judged beside its own module.
|
||||
@@ -674,7 +715,7 @@ func advanceRelease(ctx context.Context, open *stores, p *inventory.Plan) (bool,
|
||||
r.Next++
|
||||
continue
|
||||
}
|
||||
moves, sent, err := gatedSend(ctx, open, node, nil)
|
||||
moves, sent, grants, err := gatedSend(ctx, open, node, nil)
|
||||
if errors.Is(err, errWalkedElsewhere) {
|
||||
note := fmt.Sprintf("waiting before %s: %v", node, err)
|
||||
changed := p.Note != note
|
||||
@@ -689,8 +730,12 @@ func advanceRelease(ctx context.Context, open *stores, p *inventory.Plan) (bool,
|
||||
r.Next++
|
||||
continue
|
||||
}
|
||||
r.Gate = &inventory.PlanGate{Machines: sent, Since: &now, Carried: moves, Sent: sentNow(ctx, open.inventory, sent)}
|
||||
r.Gate = &inventory.PlanGate{Machines: sent, Since: &now, Carried: moves, Sent: sentNow(ctx, open.inventory, sent),
|
||||
Grants: grants}
|
||||
p.Note = fmt.Sprintf("sent %s %d build(s) that waited for a gate; judging them there", node, len(moves))
|
||||
if said := grantsSaid(grants); said != "" {
|
||||
p.Note += "; " + said
|
||||
}
|
||||
if said := recreationsSaid(moves); said != "" {
|
||||
p.Note += "; " + said
|
||||
}
|
||||
@@ -793,14 +838,19 @@ func backlogCommand(ctx context.Context, sub string, args []string) error {
|
||||
}
|
||||
defer open.Close()
|
||||
if sub == "release-backlog" {
|
||||
release, err := open.inventory.HoldPlans(ctx, true)
|
||||
if err != nil {
|
||||
// Said on the bus (novox/hq ADR 0308 decision 1): the release plan starts walking here, and its start is
|
||||
// said by the verb that opens it.
|
||||
var p *inventory.Plan
|
||||
if err := sayingOnTheBus(ctx, open.inventory, func() error {
|
||||
release, err := open.inventory.HoldPlans(ctx, true)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
defer release()
|
||||
why.record(ctx, "upgrade release-backlog", nil)
|
||||
p, err = releaseBacklog(ctx, open, link.Caller())
|
||||
return err
|
||||
}
|
||||
defer release()
|
||||
why.record(ctx, "upgrade release-backlog", nil)
|
||||
p, err := releaseBacklog(ctx, open, link.Caller())
|
||||
if err != nil {
|
||||
}); err != nil {
|
||||
return err
|
||||
}
|
||||
if p == nil {
|
||||
@@ -916,3 +966,162 @@ func recreationsSaid(moves []inventory.CarriedMove) string {
|
||||
}
|
||||
return strings.Join(said, "; ")
|
||||
}
|
||||
|
||||
// The grants step (novox/hq issue 490).
|
||||
//
|
||||
// The bus's user list — every module's grants, composed mesh-wide from the catalogue — travels only in the
|
||||
// declaration of the machine holding the bus. A send to any other machine that changed it put that machine
|
||||
// first (issue 249), unless a build waited there for a gate: then ungatedIn left it out, and said so. On
|
||||
// 2026-10-11 a merge gave restic a new health tool; its walk sent restic to its first machine and judged it
|
||||
// there, the machine's node-engine asked the tool and the bus refused it ("this host's grant does not name
|
||||
// …"), because the machine holding the bus also runs restic, whose new build waited for that very gate. The
|
||||
// gate could not pass; a person pushed the bus's machine by hand, which carried restic's new build there
|
||||
// unjudged.
|
||||
//
|
||||
// So before a gated send, when the user list composed now is not the one the machine holding the bus was
|
||||
// last sent, that machine is sent its declaration with **every build kept at the one it runs**: the new
|
||||
// list, and nothing of any module's new code. Said on the gate (`plans`), and, when it cannot be sent, said
|
||||
// with why and passed over: the send goes on as it did before, and its gate says what it finds.
|
||||
|
||||
// brokerBehindOf is brokerBehind: a variable so a test of the walk needs no store.
|
||||
var brokerBehindOf = brokerBehind
|
||||
|
||||
// grantsStep sends the machine holding the bus its user list alone, ahead of a gated send to node, when the
|
||||
// list changed; answers what it did, or nil when there was nothing to send.
|
||||
func grantsStep(ctx context.Context, open *stores, node string) *inventory.GrantsStep {
|
||||
holder, behind, err := brokerBehindOf(ctx, open, []string{node})
|
||||
if err != nil {
|
||||
fmt.Printf("grants step before %s: whether the bus's user list changed could not be read: %v\n", node, err)
|
||||
return &inventory.GrantsStep{Node: "the machine holding the bus", Failed: err.Error()}
|
||||
}
|
||||
if holder == "" || holder == node || !behind {
|
||||
// No bus with a user list, the gate's own machine holds it (its send carries the list first), or the
|
||||
// list is the one already sent.
|
||||
return nil
|
||||
}
|
||||
if _, err := sendRollout(keepingEveryBuild(withScope(ctx, sendScope{}), holder), open, []string{holder}); err != nil {
|
||||
fmt.Printf("grants step: the bus's user list could not be sent to %s ahead of %s, which is sent without "+
|
||||
"it — the bus may refuse what the send newly grants: %v\n", holder, node, err)
|
||||
return &inventory.GrantsStep{Node: holder, Failed: err.Error()}
|
||||
}
|
||||
now := time.Now().UTC()
|
||||
fmt.Printf("grants step: %s sent the bus's user list alone, every build there kept, before %s is judged\n",
|
||||
holder, node)
|
||||
return &inventory.GrantsStep{Node: holder, At: &now}
|
||||
}
|
||||
|
||||
// errNotGrantsOnly is a grants step refused unsent: its declaration would change more than the user list.
|
||||
var errNotGrantsOnly = errors.New("the grants step would change more than the bus's user list, and is not sent")
|
||||
|
||||
// grantsOnlyIn is what a grants step's declaration, composed for sending, would change on the machine holding
|
||||
// the bus besides its user list, against what it was last sent (novox/hq issue 490); empty when nothing else.
|
||||
// Judged by sendToEach on the very declaration it then sends — one composition, judged, then sent or refused
|
||||
// unsent. Kept builds are not the whole of a declaration: a new assignment, a settings change, an assignment
|
||||
// taken away, a provision's logins are composed as the mesh holds them now, and a step that carried any of
|
||||
// it would be the unjudged change this step exists to avoid. Compared resource by resource with the summary
|
||||
// the last send kept (ADR 0217): exact, rather than a list of the cases that can differ. A module there that
|
||||
// was never sent is a new assignment, refused whatever its resources.
|
||||
func grantsOnlyIn(ctx context.Context, open *stores, holder string, plan catalogue.Resolution, declared sendable) (string, error) {
|
||||
inv := open.inventory
|
||||
sent, known, err := inv.SentBuilds(ctx, holder)
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
if !known {
|
||||
return fmt.Sprintf("what %s was last sent is not known", holder), nil
|
||||
}
|
||||
var other []string
|
||||
listID := ""
|
||||
for _, m := range plan.Modules {
|
||||
if _, was := sent[m.Module]; !was {
|
||||
other = append(other, m.Module+" newly assigned")
|
||||
}
|
||||
if m.BusUsers != "" && m.ClaimsSeat(catalogue.BrokerSeat) {
|
||||
listID = m.Module + "." + catalogue.BusUsersID()
|
||||
}
|
||||
}
|
||||
var facts *moveFacts
|
||||
for m, was := range sent {
|
||||
now, carried := declared.Builds[m]
|
||||
if !carried || sameCommit(now, was) {
|
||||
continue
|
||||
}
|
||||
if facts == nil {
|
||||
f, err := readMoveFacts(ctx, inv)
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
facts = &f
|
||||
}
|
||||
if !facts.identical(m, was, now) {
|
||||
other = append(other, fmt.Sprintf("%s %s → %s", m, short(was), short(now)))
|
||||
}
|
||||
}
|
||||
for _, f := range declared.foreseen {
|
||||
other = append(other, f+" would be minted")
|
||||
}
|
||||
body, err := declared.Body()
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
after, err := summarize(body)
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
prev, err := inv.SentSummary(ctx, holder)
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
if len(prev) == 0 {
|
||||
return fmt.Sprintf("what %s was last sent is not kept for comparison", holder), nil
|
||||
}
|
||||
var before []sentResource
|
||||
if err := json.Unmarshal(prev, &before); err != nil {
|
||||
return "", fmt.Errorf("what %s was last sent is kept in a form this version does not read: %w", holder, err)
|
||||
}
|
||||
other = append(other, otherThanTheList(diffSent(before, after), listID)...)
|
||||
sort.Strings(other)
|
||||
if len(other) == 0 {
|
||||
return "", nil
|
||||
}
|
||||
return "its send would change more than the bus's user list: " + strings.Join(other, "; "), nil
|
||||
}
|
||||
|
||||
// otherThanTheList is what a diff against the last send changes besides the user list's content: every
|
||||
// resource added, removed or changed, but the list's own resource when its content is all that changed —
|
||||
// its path, mode and every other field must be as last sent (novox/hq issue 490).
|
||||
func otherThanTheList(d sentDiff, listID string) []string {
|
||||
var other []string
|
||||
for _, id := range d.Added {
|
||||
other = append(other, "+"+id)
|
||||
}
|
||||
for _, id := range d.Removed {
|
||||
other = append(other, "-"+id)
|
||||
}
|
||||
for _, c := range d.Changed {
|
||||
if c.ID == listID && len(c.Fields) == 1 && c.Fields[0] == "content" {
|
||||
continue
|
||||
}
|
||||
other = append(other, fmt.Sprintf("~%s (%s)", c.ID, strings.Join(c.Fields, ", ")))
|
||||
}
|
||||
return other
|
||||
}
|
||||
|
||||
// sendJudged is a gated send's sends: the grants step when the user list changed, then the machine judged.
|
||||
func sendJudged(ctx context.Context, open *stores, node string) ([]string, *inventory.GrantsStep, error) {
|
||||
grants := grantsStep(ctx, open, node)
|
||||
sent, err := sendRollout(withScope(ctx, sendScope{judged: map[string]bool{node: true}}), open, []string{node})
|
||||
return sent, grants, err
|
||||
}
|
||||
|
||||
// grantsSaid is a grants step as `plans` and a walk's note say it.
|
||||
func grantsSaid(g *inventory.GrantsStep) string {
|
||||
switch {
|
||||
case g == nil:
|
||||
return ""
|
||||
case g.Failed != "":
|
||||
return fmt.Sprintf(grantsStepWord+" to %s FAILED, sent without it: %s", g.Node, g.Failed)
|
||||
default:
|
||||
return fmt.Sprintf(grantsStepWord+": %s sent the bus's user list first, its builds kept", g.Node)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -11,6 +11,8 @@ import (
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/nats-io/nats.go"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
"github.com/novox/mesh-controller/internal/link"
|
||||
)
|
||||
@@ -510,6 +512,14 @@ func advancePlans(ctx context.Context, open *stores) {
|
||||
advanceHeld(ctx, open)
|
||||
}
|
||||
|
||||
// keepWalkPhases keeps where the walks that ended lately spent their time (novox/hq ADR 0282), outside the hold
|
||||
// on the plans so it never lengthens it: measured, never acted on, and an error only said.
|
||||
func keepWalkPhases(ctx context.Context, open *stores) {
|
||||
if err := recordWalkPhases(ctx, open.inventory, time.Now()); err != nil {
|
||||
fmt.Printf("plans: the phases of the walks ended lately could not be kept: %v\n", err)
|
||||
}
|
||||
}
|
||||
|
||||
// advanceHeld is advancePlans for a caller already holding the plans.
|
||||
func advanceHeld(ctx context.Context, open *stores) {
|
||||
inv := open.inventory
|
||||
@@ -641,26 +651,9 @@ func advanceOnce(ctx context.Context, open *stores, p *inventory.Plan,
|
||||
// the controller in its first tier: the build that produced the new one is recorded, and the
|
||||
// plan never hears it. The record is the fact; a build recorded after the ask is that tier's
|
||||
// outcome, whoever was listening.
|
||||
recorded := map[string][]inventory.Build{}
|
||||
byID := map[string]inventory.Build{}
|
||||
for _, m := range tier {
|
||||
if s := p.Modules[m]; s != nil && s.State == "asked" {
|
||||
builds, err := inv.Builds(ctx, m, 5)
|
||||
if err != nil {
|
||||
return false, err
|
||||
}
|
||||
recorded[m] = builds
|
||||
// Its own ask's record, by id — found even when the outcome named no module (ADR 0219).
|
||||
if s.Build != "" {
|
||||
b, found, err := inv.BuildByID(ctx, s.Build)
|
||||
if err != nil {
|
||||
return false, err
|
||||
}
|
||||
if found {
|
||||
byID[s.Build] = b
|
||||
}
|
||||
}
|
||||
}
|
||||
recorded, byID, err := recordsOfAsked(ctx, inv, p, tier)
|
||||
if err != nil {
|
||||
return false, err
|
||||
}
|
||||
if settleFromRecords(p, tier, recorded, byID) {
|
||||
return true, nil
|
||||
@@ -864,8 +857,12 @@ func advanceOnce(ctx context.Context, open *stores, p *inventory.Plan,
|
||||
strings.Join(machines, ", "), p.Tier, err)
|
||||
}
|
||||
now := time.Now().UTC()
|
||||
// What each machine of the rest was sent, kept for when it reports it applied (novox/hq ADR 0282 decision
|
||||
// 6): measured, never acted on.
|
||||
sentWhat := sentNow(ctx, open.inventory, sent)
|
||||
for _, m := range rest {
|
||||
p.Modules[m].SentAt = &now
|
||||
p.Modules[m].Rest = restOf(restTo[m], sent, sentWhat)
|
||||
}
|
||||
fmt.Printf("%s: tier %d built; sent %s to %s, one send each\n", p.ID, p.Tier, strings.Join(rest, ", "),
|
||||
strings.Join(sent, ", "))
|
||||
@@ -946,6 +943,20 @@ func advanceOnce(ctx context.Context, open *stores, p *inventory.Plan,
|
||||
return true, nil
|
||||
}
|
||||
|
||||
// restOf is, for one module, every machine of its rest that the send reached and what it carried there.
|
||||
func restOf(to, sent []string, what map[string]inventory.SentDeclaration) map[string]inventory.SentDeclaration {
|
||||
out := map[string]inventory.SentDeclaration{}
|
||||
for _, n := range to {
|
||||
if slices.Contains(sent, n) {
|
||||
out[n] = what[n]
|
||||
}
|
||||
}
|
||||
if len(out) == 0 {
|
||||
return nil
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// firstSend sends one machine, in one send, every module of the plan's tier whose first machine it is
|
||||
// (novox/hq issue 281), and records the send on each: what that machine ran of it before — read once,
|
||||
// before the send, so a module the same send carries is never read as already moved — the machines it
|
||||
@@ -962,7 +973,7 @@ func firstSend(ctx context.Context, open *stores, p *inventory.Plan, node string
|
||||
}
|
||||
// A gated send (ADR 0236): everything waiting on the machine goes with the tier, and the gate judges
|
||||
// all of it there.
|
||||
carried, sent, err := gatedSend(ctx, open, node, owns)
|
||||
carried, sent, grants, err := gatedSend(ctx, open, node, owns)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
@@ -983,6 +994,7 @@ func firstSend(ctx context.Context, open *stores, p *inventory.Plan, node string
|
||||
s.GatedBy = ""
|
||||
if m == lead {
|
||||
s.Gate.Carried = carried
|
||||
s.Gate.Grants = grants
|
||||
} else {
|
||||
s.GatedBy = lead
|
||||
}
|
||||
@@ -992,6 +1004,10 @@ func firstSend(ctx context.Context, open *stores, p *inventory.Plan, node string
|
||||
strings.Join(sent, ", "))
|
||||
fmt.Printf("%s: tier %d built; sent %d module(s) to %s first in one send (%s), the rest once its gate passes\n",
|
||||
p.ID, p.Tier, len(modules), strings.Join(sent, ", "), strings.Join(modules, ", "))
|
||||
// The grants step taken before it (novox/hq issue 490), said with it.
|
||||
if said := grantsSaid(grants); said != "" {
|
||||
p.Note += "; " + said
|
||||
}
|
||||
// What the send recreates, said with it (novox/hq ADR 0245).
|
||||
if said := recreationsSaid(carried); said != "" {
|
||||
p.Note += "; " + said
|
||||
@@ -1193,6 +1209,7 @@ func sayUnsent(p *inventory.Plan, rollsOut func(string) bool) {
|
||||
// planTicker advances open plans on a timer, for the steps outcomes alone cannot take.
|
||||
func planTicker(ctx context.Context, open *stores) {
|
||||
advancePlans(ctx, open)
|
||||
keepWalkPhases(ctx, open)
|
||||
tick := time.NewTicker(30 * time.Second)
|
||||
defer tick.Stop()
|
||||
for {
|
||||
@@ -1201,6 +1218,7 @@ func planTicker(ctx context.Context, open *stores) {
|
||||
return
|
||||
case <-tick.C:
|
||||
advancePlans(ctx, open)
|
||||
keepWalkPhases(ctx, open)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1242,6 +1260,13 @@ func planLineWith(p inventory.Plan, now time.Time, pause pauseView, bound time.D
|
||||
// planLineOn is planLineWith naming the plan by what it moves and where (planHeadline), given what runs each
|
||||
// module; nil names no machine.
|
||||
func planLineOn(p inventory.Plan, now time.Time, pause pauseView, bound time.Duration, running func(string) []string) string {
|
||||
return planLineSaid(p, now, pause, bound, running, nil)
|
||||
}
|
||||
|
||||
// planLineSaid is planLineOn saying, of a walk waiting for its delivery's word, what the delivery's owner says
|
||||
// holds it (novox/hq issue 529); nil waits says it as before.
|
||||
func planLineSaid(p inventory.Plan, now time.Time, pause pauseView, bound time.Duration, running func(string) []string,
|
||||
waits walkWaits) string {
|
||||
name := planHeadline(p, running)
|
||||
where := fmt.Sprintf("tier %d of %d", min(p.Tier+1, len(p.Tiers)), len(p.Tiers))
|
||||
switch p.State {
|
||||
@@ -1258,7 +1283,7 @@ func planLineOn(p inventory.Plan, now time.Time, pause pauseView, bound time.Dur
|
||||
since := now.Sub(inTierSince(p)).Round(time.Second)
|
||||
if p.Waiting() {
|
||||
// Waiting for its delivery's word is no lateness of the walk's (novox/hq ADR 0239).
|
||||
return fmt.Sprintf("%s · %s, %s, for %s", name, where, waitingNote(p), since)
|
||||
return fmt.Sprintf("%s · %s, %s, for %s", name, where, waitingSaid(p, waits[p.ID]), since)
|
||||
}
|
||||
if deferred(p) {
|
||||
// Nor is waiting for the walk before it to end (one walk at a time, novox/hq ADR 0276).
|
||||
@@ -1438,6 +1463,10 @@ func plansCommand(ctx context.Context, args []string) error {
|
||||
modules := set.String("modules", "", "or the modules it would change, comma-separated")
|
||||
moduleDirs := set.String("module-dirs", "", "with --paths: the directories holding a module.json at the commit, "+
|
||||
"comma-separated, as the forge's announcer says them (novox/hq issue 278)")
|
||||
// Following a plan (novox/hq issue 229): `plans wait <id>`.
|
||||
until := set.String("until", "", "with wait: what to wait for — moved (any change), tier (its next tier) or done (its end)")
|
||||
bound := set.String("bound", "", "with wait: how long to wait at most, as 15s or seconds (default and at most the "+
|
||||
"longest a call is answered within)")
|
||||
// Ending a plan by hand is a repair, and says why (novox/hq to-be 45 §7).
|
||||
why := addHandActFlags(set)
|
||||
positionals, err := parseAround(set, args)
|
||||
@@ -1457,17 +1486,20 @@ func plansCommand(ctx context.Context, args []string) error {
|
||||
defer open.Close()
|
||||
inv := open.inventory
|
||||
now := time.Now()
|
||||
if len(positionals) == 2 && positionals[0] == "wait" {
|
||||
return planWaitCommand(ctx, inv, positionals[1], *until, *bound)
|
||||
}
|
||||
if len(positionals) == 1 {
|
||||
p, err := inv.PlanByID(ctx, positionals[0])
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
bounds := readTierBounds(ctx, inv, now)
|
||||
fmt.Printf("%s — %s\n", p.ID, planLineOn(p, now, buildSeatPause(ctx, inv, []inventory.Plan{p}),
|
||||
fmt.Printf("%s — %s\n", p.ID, planLineSaid(p, now, buildSeatPause(ctx, inv, []inventory.Plan{p}),
|
||||
bounds.of(p.Repository), func(module string) []string {
|
||||
on, _ := inv.Running(ctx, module)
|
||||
return on
|
||||
}))
|
||||
}, waitsOf(ctx, inv, []inventory.Plan{p})))
|
||||
if r := p.Release; r != nil {
|
||||
// A release plan's walk (ADR 0236): machines done, the one judged, those to come.
|
||||
fmt.Printf(" machines in order: %s; done: %s; skipped: %s\n", strings.Join(r.Order, ", "),
|
||||
@@ -1534,7 +1566,7 @@ func plansCommand(ctx context.Context, args []string) error {
|
||||
if len(positionals) == 2 && positionals[0] == "go" {
|
||||
why.record(ctx, "plans go", positionals[1:])
|
||||
var p inventory.Plan
|
||||
if err := sayingOnTheBus(ctx, func() (err error) {
|
||||
if err := sayingOnTheBus(ctx, inv, func() (err error) {
|
||||
p, err = letGo(ctx, inv, positionals[1], "a person ("+whoAsked()+")", strings.TrimSpace(*why.why))
|
||||
return err
|
||||
}); err != nil {
|
||||
@@ -1546,8 +1578,13 @@ func plansCommand(ctx context.Context, args []string) error {
|
||||
}
|
||||
// `retry` (novox/hq ADR 0219): a failed plan's failed builds asked again, and the plan goes on.
|
||||
if len(positionals) == 2 && positionals[0] == "retry" {
|
||||
said, err := retryPlan(ctx, open, positionals[1])
|
||||
if err != nil {
|
||||
// Said on the bus (novox/hq ADR 0308 decision 1): a retried walk starts again, and its start is said
|
||||
// by the verb that starts it.
|
||||
var said string
|
||||
if err := sayingOnTheBus(ctx, inv, func() (err error) {
|
||||
said, err = retryPlan(ctx, open, positionals[1])
|
||||
return err
|
||||
}); err != nil {
|
||||
return err
|
||||
}
|
||||
fmt.Println(said)
|
||||
@@ -1561,26 +1598,29 @@ func plansCommand(ctx context.Context, args []string) error {
|
||||
if positionals[0] == "close" {
|
||||
how = "closed"
|
||||
}
|
||||
release, err := inv.HoldPlans(ctx, true)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
defer release()
|
||||
p, err := inv.PlanByID(ctx, positionals[1])
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
if !p.Open() {
|
||||
return fmt.Errorf("%s is already %s", p.ID, p.State)
|
||||
}
|
||||
why.record(ctx, "plans "+positionals[0], positionals[1:])
|
||||
p.State = inventory.PlanFailed
|
||||
p.Note = how + " by hand at tier " + fmt.Sprint(p.Tier) + ": " + strings.TrimSpace(*why.why)
|
||||
sayUnsent(&p, func(m string) bool {
|
||||
u, err := inv.UpgradeOf(ctx, m)
|
||||
return err == nil && u.RollOut
|
||||
})
|
||||
if err := inv.SavePlan(ctx, &p); err != nil {
|
||||
// Said on the bus (novox/hq ADR 0308 decision 1): the walk's end, outcome stopped, is said by the verb
|
||||
// that ends it, so what it touched is not held until its bound.
|
||||
var p inventory.Plan
|
||||
if err := sayingOnTheBus(ctx, inv, func() error {
|
||||
release, err := inv.HoldPlans(ctx, true)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
defer release()
|
||||
if p, err = inv.PlanByID(ctx, positionals[1]); err != nil {
|
||||
return err
|
||||
}
|
||||
if !p.Open() {
|
||||
return fmt.Errorf("%s is already %s", p.ID, p.State)
|
||||
}
|
||||
why.record(ctx, "plans "+positionals[0], positionals[1:])
|
||||
stopByHand(&p, how, "a person ("+whoAsked()+")", strings.TrimSpace(*why.why))
|
||||
sayUnsent(&p, func(m string) bool {
|
||||
u, err := inv.UpgradeOf(ctx, m)
|
||||
return err == nil && u.RollOut
|
||||
})
|
||||
return inv.SavePlan(ctx, &p)
|
||||
}); err != nil {
|
||||
return err
|
||||
}
|
||||
fmt.Printf("%s %s at tier %d of %d; what was asked still builds and registers, nothing further is asked\n",
|
||||
@@ -1614,15 +1654,41 @@ func plansCommand(ctx context.Context, args []string) error {
|
||||
on, _ := inv.Running(ctx, module)
|
||||
return on
|
||||
}
|
||||
waits := waitsOf(ctx, inv, plans)
|
||||
for _, p := range plans {
|
||||
if p.Batch() {
|
||||
continue
|
||||
}
|
||||
fmt.Printf("%-28s %s\n", p.ID, planLineOn(p, now, pause, bounds.of(p.Repository), running))
|
||||
fmt.Printf("%-28s %s\n", p.ID, planLineSaid(p, now, pause, bounds.of(p.Repository), running, waits))
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// waitsOf asks the delivery's owner what holds the walks among these that wait for its word (novox/hq issue 529),
|
||||
// once, and only when one waits; nil when none waits, no holder is on record, or the bus or the owner does not
|
||||
// answer within a few seconds — the lines then read as before.
|
||||
func waitsOf(ctx context.Context, inv *inventory.Inventory, plans []inventory.Plan) walkWaits {
|
||||
waiting := false
|
||||
for _, p := range plans {
|
||||
waiting = waiting || p.Open() && p.Waiting()
|
||||
}
|
||||
if !waiting {
|
||||
return nil
|
||||
}
|
||||
entries, err := inv.Catalogued(ctx)
|
||||
if err != nil {
|
||||
return nil
|
||||
}
|
||||
ctx, cancel := context.WithTimeout(ctx, 3*time.Second)
|
||||
defer cancel()
|
||||
var waits walkWaits
|
||||
_ = onTheBus(func(conn *nats.Conn) error {
|
||||
waits = walksWaiting(ctx, conn, deliverySeatHeld(entries))
|
||||
return nil
|
||||
})
|
||||
return waits
|
||||
}
|
||||
|
||||
// planWhatIf is the plan a merge would produce, computed the way the merge handler computes one
|
||||
// and saved nowhere: the modules the repository's changed files touch (or the modules named), what
|
||||
// packages their source, everything reachable from them, in tiers. For reading before merging.
|
||||
@@ -1748,6 +1814,34 @@ func splitList(s string) []string {
|
||||
return out
|
||||
}
|
||||
|
||||
// recordsOfAsked is what settleFromRecords reads: for every module of the tier still `asked`, its last
|
||||
// builds and the record of its own ask, by id.
|
||||
func recordsOfAsked(ctx context.Context, inv *inventory.Inventory, p *inventory.Plan, tier []string) (
|
||||
map[string][]inventory.Build, map[string]inventory.Build, error) {
|
||||
recorded := map[string][]inventory.Build{}
|
||||
byID := map[string]inventory.Build{}
|
||||
for _, m := range tier {
|
||||
if s := p.Modules[m]; s != nil && s.State == "asked" {
|
||||
builds, err := inv.Builds(ctx, m, 5)
|
||||
if err != nil {
|
||||
return nil, nil, err
|
||||
}
|
||||
recorded[m] = builds
|
||||
// Its own ask's record, by id — found even when the outcome named no module (ADR 0219).
|
||||
if s.Build != "" {
|
||||
b, found, err := inv.BuildByID(ctx, s.Build)
|
||||
if err != nil {
|
||||
return nil, nil, err
|
||||
}
|
||||
if found {
|
||||
byID[s.Build] = b
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
return recorded, byID, nil
|
||||
}
|
||||
|
||||
// settleFromRecords marks every module of the tier still `asked` built — or failed — from a build
|
||||
// recorded after it was asked, and says whether it changed anything (novox/hq 04-ISSUES/214).
|
||||
// Newest first, as Builds answers: the first record after the ask is the outcome of that ask.
|
||||
@@ -1845,3 +1939,15 @@ func forgetDeleted(ctx context.Context, inv *inventory.Inventory, module string,
|
||||
"`module forget %s`: %v\n", p.ID, module, module, firstLine(err.Error()))
|
||||
}
|
||||
}
|
||||
|
||||
// stopByHand ends a walk a person stopped or closed (`plans stop|close`): failed, with who stopped it and why
|
||||
// kept as the delivery's owner keeps its own stop, so the walk ends with outcome stopped, not failed (novox/hq
|
||||
// ADR 0308 decision 1).
|
||||
func stopByHand(p *inventory.Plan, how, by, why string) {
|
||||
p.State = inventory.PlanFailed
|
||||
p.Note = how + " by hand at tier " + fmt.Sprint(p.Tier) + ": " + why
|
||||
if p.Delivery == nil {
|
||||
p.Delivery = &inventory.PlanDelivery{}
|
||||
}
|
||||
p.Delivery.Stopped, p.Delivery.StoppedWhy = by, why
|
||||
}
|
||||
|
||||
@@ -160,6 +160,7 @@ func (b *backlogMesh) release(t *testing.T) inventory.Plan {
|
||||
// The backlog goes out one machine at a time: the first judged before the second is sent, each build's
|
||||
// pass kept; a rebuild with the same bytes is no move at all; and a send outside a gate is refused.
|
||||
func TestTheBacklogIsReleasedOneMachineAtATimeEachJudged(t *testing.T) {
|
||||
judgeLeavesAsTheCore(t)
|
||||
b := aBacklog(t)
|
||||
ctx := t.Context()
|
||||
inv := b.open.inventory
|
||||
|
||||
@@ -0,0 +1,90 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/catalogue"
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
)
|
||||
|
||||
// TestReplay201ThePlansSend replays novox/hq issue 201 (2026-10-02): two merges a minute apart made two plans; the
|
||||
// controller's plan rolled the newer controller onto the control node, and the node-engine's plan then sent that
|
||||
// machine the controller build before it, whose binary refused the seat row the newer one had widened. Here the
|
||||
// control node, anchor, was last sent the newer controller c2 while the mesh's record of the controller is the
|
||||
// build before it, c1, which passed its gate. The outcome asserted: a send that is no person's push — composed as a
|
||||
// plan's send composes it (keepingRecorded, what sendKeeps gives every send through sendToEach) — carries the
|
||||
// controller at c2, the build the machine was last sent, and not the older record; a person's push still carries
|
||||
// the record. Written with only what the controller had before its fix (mesh-controller #273) — the inventory's
|
||||
// build, gate, assignment and send records, keepingRecorded, planFor and declarationFor — so it is laid over the
|
||||
// commit before; the fix's own TestReplay201 reads what the fix added. Needs the store (MESH_TEST_POSTGRES), and
|
||||
// is named in testdata/store-tests.
|
||||
func TestReplay201ThePlansSend(t *testing.T) {
|
||||
open := aMesh(t)
|
||||
ctx := t.Context()
|
||||
inv := open.inventory
|
||||
const older, newer = "c1aaaaaaaaaa", "c2bbbbbbbbbb"
|
||||
old, now := time.Now().Add(-2*time.Hour), time.Now().Add(-time.Minute)
|
||||
record := func(commit string, asked time.Time) inventory.Build {
|
||||
t.Helper()
|
||||
manifest, _ := json.Marshal(catalogue.Manifest{Module: "mesh-controller", Version: "1"})
|
||||
b := inventory.Build{ID: "build-mesh-controller-" + commit, Module: "mesh-controller", Commit: commit,
|
||||
Repository: "novox/mesh-controller", Manifest: manifest, Asked: asked, At: asked,
|
||||
Made: []inventory.Artifact{{Name: "x", Kind: "bundle", Reference: "sha256:" + commit + "0000000000000000"}}}
|
||||
if err := inv.RecordBuild(ctx, b); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
return b
|
||||
}
|
||||
|
||||
// The older controller rolled out and passed its gate; the newer one was asked after it and registered.
|
||||
before := record(older, old)
|
||||
if err := inv.RecordGate(ctx, inventory.GateVerdict{Build: before.ID, Module: "mesh-controller", Commit: older,
|
||||
Machines: []string{"anchor"}, Verdict: inventory.GatePassed}); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
record(newer, now)
|
||||
if err := inv.RegisterModule(ctx, catalogue.Manifest{Module: "mesh-controller", Version: "1"}, inventory.Source{
|
||||
Repository: "novox/mesh-controller", BuiltFrom: newer, Head: newer, Asked: now}); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if _, err := inv.Assign(ctx, "anchor", "mesh-controller"); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
// The controller's plan sent anchor the newer controller.
|
||||
if err := inv.RecordSent(ctx, nodeID(t, open, "anchor"), "d-anchor", map[string]string{"mesh-controller": newer}); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
// And the mesh's record of the controller is the build before it — whatever made it so.
|
||||
if err := inv.RestoreModule(ctx, before); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
// The controller each send to anchor carries: a plan's send keeps recorded builds (keepingRecorded, what
|
||||
// sendKeeps gives every send but a person's push); a person's push composes the mesh's record.
|
||||
controllerSent := func(sends string, keeping bool) string {
|
||||
t.Helper()
|
||||
c := ctx
|
||||
if keeping {
|
||||
c = keepingRecorded(ctx)
|
||||
}
|
||||
plan, settings, err := planFor(c, open, "anchor")
|
||||
if err != nil {
|
||||
t.Fatalf("%s to anchor did not compose: %v", sends, err)
|
||||
}
|
||||
declared, err := declarationFor(c, open, "anchor", plan, settings)
|
||||
if err != nil {
|
||||
t.Fatalf("%s to anchor did not compose: %v", sends, err)
|
||||
}
|
||||
return declared.Builds["mesh-controller"]
|
||||
}
|
||||
|
||||
if got := controllerSent("a plan's send", true); got != newer {
|
||||
t.Fatalf("a plan's send carried anchor the controller %s, older than the %s anchor was last sent: the "+
|
||||
"older binary would read the row its successor widened", short(got), short(newer))
|
||||
}
|
||||
if got := controllerSent("a person's push", false); got != older {
|
||||
t.Fatalf("a person's push carried the controller %s, not the mesh's record %s", short(got), short(older))
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,85 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"io"
|
||||
"os"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/catalogue"
|
||||
)
|
||||
|
||||
// TestReplay237 replays novox/hq issue 237 (2026-10-04): a workstation already ran a module that
|
||||
// depends on a node seat nothing there held, and the module holding that seat was assigned to it. The
|
||||
// answer said the seat was now held, and then that the workstation was left out of the rest of the mesh
|
||||
// for lack of it, naming as the remedy the assignment just made. `plan` for the node, right after,
|
||||
// resolved. The outcome asserted: every line of the answer, as the controller seat's verb gives it
|
||||
// (standard output, then standard error), agrees with `plan` for the node right after the act. Written
|
||||
// with only what the controller had before its fix — register, assign's command, planFor — so it is laid
|
||||
// over the commit before.
|
||||
func TestReplay237(t *testing.T) {
|
||||
open := aMesh(t)
|
||||
ctx := t.Context()
|
||||
register(t, open, aContainer("web"))
|
||||
register(t, open, catalogue.Manifest{Module: "docker", Version: "1",
|
||||
Claims: []catalogue.Claim{{Name: catalogue.ContainerRuntimeSeat, Scope: catalogue.ScopeNode}}})
|
||||
// Already on the node, from before the rule refused it: the node does not resolve until the
|
||||
// holder comes.
|
||||
if _, err := open.inventory.Assign(ctx, "laptop", "web"); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
said := answered(t, func() error { return assignCommand(ctx, "assign", []string{"laptop", "docker"}) })
|
||||
|
||||
if _, _, err := planFor(ctx, open, "laptop"); err != nil {
|
||||
t.Fatalf("laptop does not resolve right after the act: %v\nthe answer was:\n%s", err, said)
|
||||
}
|
||||
if !strings.Contains(said, "web on laptop now has "+catalogue.ContainerRuntimeSeat+" held") {
|
||||
t.Errorf("the answer does not say the seat is now held:\n%s", said)
|
||||
}
|
||||
for _, not := range []string{"laptop is left out", "does not resolve", "which nothing on laptop holds"} {
|
||||
if strings.Contains(said, not) {
|
||||
t.Errorf("the answer says %q, which `plan` right after contradicts:\n%s", not, said)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// answered is what a command says as the controller seat's verb answers it: standard output, then
|
||||
// standard error (answerOf).
|
||||
func answered(t *testing.T, f func() error) string {
|
||||
t.Helper()
|
||||
read := func(w **os.File) (func() string, error) {
|
||||
old := *w
|
||||
r, pw, err := os.Pipe()
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
*w = pw
|
||||
got := make(chan string)
|
||||
go func() {
|
||||
var buf bytes.Buffer
|
||||
_, _ = io.Copy(&buf, r)
|
||||
got <- buf.String()
|
||||
}()
|
||||
return func() string {
|
||||
_ = pw.Close()
|
||||
*w = old
|
||||
return <-got
|
||||
}, nil
|
||||
}
|
||||
stdout, err := read(&os.Stdout)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
stderr, err := read(&os.Stderr)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
runErr := f()
|
||||
said := stdout() + stderr()
|
||||
if runErr != nil {
|
||||
t.Fatalf("%v\n%s", runErr, said)
|
||||
}
|
||||
return said
|
||||
}
|
||||
@@ -11,6 +11,7 @@ import (
|
||||
"github.com/nats-io/nats-server/v2/server"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/broker"
|
||||
"github.com/novox/mesh-controller/internal/conditions"
|
||||
"github.com/novox/mesh-controller/internal/testbus"
|
||||
)
|
||||
|
||||
@@ -30,7 +31,7 @@ func TestReplay327(t *testing.T) {
|
||||
if err := serving.EnsureControllerBuckets(); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
keeper, err := keeperOn(context.Background(), serving.Conn())
|
||||
keeper, err := keeperOn(context.Background(), serving.Conn(), conditions.NewMemoryLooks())
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
@@ -83,8 +84,12 @@ func asAProcess(t *testing.T, url string) {
|
||||
t.Setenv(broker.CertificateVar, "")
|
||||
}
|
||||
|
||||
// closedNames are the names of the connections the bus saw closed.
|
||||
func closedNames(t *testing.T, bus *server.Server) []string {
|
||||
// closedNames are the names of the connections the bus saw closed, waited for by want's own name: the
|
||||
// bus can register another connection's close first (the test's own setup connection, say), so returning
|
||||
// on the first non-empty list names whichever closed first, not necessarily the one being waited for
|
||||
// (novox/hq issue 543). closedNames instead waits until want itself appears among the closed connections,
|
||||
// or the deadline passes, and returns whatever names it last saw either way.
|
||||
func closedNames(t *testing.T, bus *server.Server, want string) []string {
|
||||
t.Helper()
|
||||
deadline := time.Now().Add(5 * time.Second)
|
||||
var names []string
|
||||
@@ -94,10 +99,14 @@ func closedNames(t *testing.T, bus *server.Server) []string {
|
||||
t.Fatal(err)
|
||||
}
|
||||
names = names[:0]
|
||||
found := false
|
||||
for _, c := range connz.Conns {
|
||||
names = append(names, c.Name)
|
||||
if c.Name == want {
|
||||
found = true
|
||||
}
|
||||
}
|
||||
if len(names) > 0 {
|
||||
if found {
|
||||
return names
|
||||
}
|
||||
time.Sleep(50 * time.Millisecond)
|
||||
|
||||
@@ -77,6 +77,7 @@ func testAWalkStoppedAfterItsGatePassedKeepsThePass(t *testing.T) {
|
||||
// the first send is older than the wait for a first machine's report. Read before the pass is taken over, the
|
||||
// carried module's step said the first machine never applied it, and the passed build was put back.
|
||||
func TestACarriedModuleTakesItsLeadsPassBeforeItsStepIsRead(t *testing.T) {
|
||||
judgeLeavesAsTheCore(t)
|
||||
tm := aTierMesh(t, "m01", "m02")
|
||||
ctx := t.Context()
|
||||
inv := tm.open.inventory
|
||||
|
||||
@@ -0,0 +1,83 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"testing"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/catalogue"
|
||||
)
|
||||
|
||||
// TestReplay401 replays novox/hq issue 401 (2026-10-10): the mounts module's smb-credentials, an own secret
|
||||
// only an outside party issues, was given by nobody, and the send made a random value for it and placed it on
|
||||
// the machine; the module read it as a credential given and wrong. The outcome asserted (ADR 0228): the send
|
||||
// makes no value for an own secret issued outside the mesh that nobody gave and places none, and a value the
|
||||
// mesh made for it before is not placed either; once a person gives one, that value is placed. Written with
|
||||
// only what the controller had before its fix (mesh-controller #262) — register, assign, planFor,
|
||||
// declarationFor and the inventory's secret reads — so it is laid over the commit before. Needs the store
|
||||
// (MESH_TEST_POSTGRES), and is named in testdata/store-tests.
|
||||
func TestReplay401(t *testing.T) {
|
||||
open := aMesh(t)
|
||||
ctx := t.Context()
|
||||
const made, outside = "/var/lib/mesh/mounts/password", "/var/lib/mesh/mounts/smb-credentials"
|
||||
register(t, open, catalogue.Manifest{Module: "mounts", Version: "1",
|
||||
OwnSecrets: catalogue.OwnSecrets{
|
||||
"password": {Path: made, Taken: catalogue.TakenAtStart},
|
||||
"smb-credentials": {Path: outside, Taken: catalogue.TakenAtStart, IssuedBy: catalogue.IssuedOutside},
|
||||
},
|
||||
Resources: []map[string]any{
|
||||
{"id": "state", "type": "directory", "path": "/var/lib/mesh/mounts", "mode": "0700"},
|
||||
}})
|
||||
if _, err := assign(ctx, open, "laptop", "mounts"); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
sent := func() []map[string]any {
|
||||
t.Helper()
|
||||
plan, settings, err := planFor(ctx, open, "laptop")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
declared, err := declarationFor(ctx, open, "laptop", plan, settings)
|
||||
if err != nil {
|
||||
t.Fatalf("the send to laptop did not compose: %v", err)
|
||||
}
|
||||
return declared.Resources
|
||||
}
|
||||
placed := func(resources []map[string]any, path string) map[string]any {
|
||||
for _, r := range resources {
|
||||
if r["path"] == path && r["sealed"] != nil {
|
||||
return r
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
first := sent()
|
||||
if placed(first, made) == nil {
|
||||
t.Fatal("the secret the mesh makes was not placed")
|
||||
}
|
||||
if got := placed(first, outside); got != nil {
|
||||
t.Errorf("the send placed a value for smb-credentials, which nobody gave: %v", got)
|
||||
}
|
||||
if _, held, err := open.inventory.ModuleSecretIfIssued(ctx, "laptop", "mounts", "smb-credentials"); err != nil || held {
|
||||
t.Fatalf("the send made a value for a secret issued outside the mesh (held %v, %v)", held, err)
|
||||
}
|
||||
|
||||
// A value the mesh made for it before the rule is not one a person gave: it is not placed.
|
||||
if _, err := open.inventory.SecretForModule(ctx, "laptop", "mounts", "smb-credentials"); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if got := placed(sent(), outside); got != nil {
|
||||
t.Fatalf("a value the mesh made for a secret issued outside was placed: %v", got)
|
||||
}
|
||||
|
||||
// Given by a person, it is placed, as given.
|
||||
if err := open.inventory.AcceptSecretForModule(ctx, "laptop", "mounts", "smb-credentials", "the share's credentials"); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
given, held, err := open.inventory.ModuleSecretIfIssued(ctx, "laptop", "mounts", "smb-credentials")
|
||||
if err != nil || !held {
|
||||
t.Fatalf("the value given is not held (%v)", err)
|
||||
}
|
||||
if got := placed(sent(), outside); got == nil || got["sealed"] != given {
|
||||
t.Fatalf("the value given is placed as %v", got)
|
||||
}
|
||||
}
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user