Compare commits
44
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
771cc24fcb | ||
|
|
b3786cc67e | ||
|
|
21954ad1bc | ||
|
|
485eb44de4 | ||
|
|
8f2d22db0c | ||
|
|
cc8a74fce4 | ||
|
|
aa9da94260 | ||
|
|
01f615aa0a | ||
|
|
f501eaca43 | ||
|
|
995f8237ce | ||
|
|
707bfba4ea | ||
|
|
4463991e06 | ||
|
|
4357b3688f | ||
|
|
03927a6f6c | ||
|
|
499ff5c218 | ||
|
|
3d4ad6fefb | ||
|
|
6bf38072ca | ||
|
|
b174d743c0 | ||
|
|
37119ea31f | ||
|
|
af2c6b5e94 | ||
|
|
a929df9b0e | ||
|
|
a3c965b9a0 | ||
|
|
b9ec1919b8 | ||
|
|
d491356f59 | ||
|
|
47e1819101 | ||
|
|
0e25ed7c5a | ||
|
|
79e2923dc8 | ||
|
|
1f3fdf3111 | ||
|
|
9902a3f16c | ||
|
|
11815c0fb3 | ||
|
|
f973cefd7f | ||
|
|
696300b9e2 | ||
|
|
98155e327b | ||
|
|
d6db334840 | ||
|
|
69d016bfdf | ||
|
|
a58b38cee3 | ||
|
|
9d260412b3 | ||
|
|
99610e9569 | ||
|
|
dc06af1f5a | ||
|
|
b62fbeabbf | ||
|
|
373aefd14e | ||
|
|
f66458fe25 | ||
|
|
99da867a98 | ||
|
|
69a67876c2 |
@@ -90,15 +90,6 @@ redis-provisioner-image:
|
||||
@echo
|
||||
@docker image inspect $(REDIS_PROVISIONER_IMAGE) --format 'built {{.RepoTags}} {{.Size}} bytes'
|
||||
|
||||
# The proxy that turns a route grant into traffic reaching a workload.
|
||||
PROXY_IMAGE ?= mesh-route-proxy:$(VERSION)
|
||||
PROXY_DEV_TAG ?= mesh-route-proxy:development
|
||||
|
||||
proxy-image:
|
||||
docker build --build-arg GO_BASE=$(GO_BASE) -f modules/route-proxy/Dockerfile -t $(PROXY_IMAGE) -t $(PROXY_DEV_TAG) .
|
||||
@echo
|
||||
@docker image inspect $(PROXY_IMAGE) --format 'built {{.RepoTags}} {{.Size}} bytes'
|
||||
|
||||
# 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
|
||||
@@ -117,7 +108,7 @@ proxy-image:
|
||||
# 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
|
||||
@sh merge-check.sh ; status=$$? ; docker rm -f -v $(PG_CONTAINER) >/dev/null 2>&1 || true ; exit $$status
|
||||
|
||||
# The unit level alone (untagged: no bus, no store, no other process), which a developer runs continuously. The tests
|
||||
# that need a bus or the store carry `//go:build integration` and run in `check`, not here; without a database the
|
||||
@@ -135,7 +126,7 @@ fmt:
|
||||
if [ -n "$$unformatted" ] ; then echo "not gofmt'd:" ; echo "$$unformatted" ; exit 1 ; fi
|
||||
|
||||
postgres:
|
||||
@docker rm -f $(PG_CONTAINER) >/dev/null 2>&1 || true
|
||||
@docker rm -f -v $(PG_CONTAINER) >/dev/null 2>&1 || true
|
||||
@docker run -d --name $(PG_CONTAINER) -e POSTGRES_PASSWORD=check \
|
||||
-p 127.0.0.1:$(PG_PORT):5432 $(PG_IMAGE) >/dev/null
|
||||
@printf 'waiting for postgres'
|
||||
@@ -147,7 +138,7 @@ postgres:
|
||||
echo ' — never came up' ; docker logs $(PG_CONTAINER) | tail -20 ; exit 1
|
||||
|
||||
postgres-stop:
|
||||
@docker rm -f $(PG_CONTAINER) >/dev/null 2>&1 || true
|
||||
@docker rm -f -v $(PG_CONTAINER) >/dev/null 2>&1 || true
|
||||
|
||||
clean:
|
||||
rm -rf build/
|
||||
|
||||
@@ -6,7 +6,11 @@ import (
|
||||
"os"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
"sync"
|
||||
"sync/atomic"
|
||||
"time"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/builder"
|
||||
)
|
||||
|
||||
// **The build agent says whether it is busy, and being asked drains it** (novox/hq ADR 0335 §1, §5). Its
|
||||
@@ -73,14 +77,77 @@ func drainedTooLong(now time.Time) error {
|
||||
"within %s (novox/hq ADR 0335)", began.UTC().Format(time.RFC3339), drainTooLong)
|
||||
}
|
||||
|
||||
// inHand is true while this process has claimed a build and not yet released it. The mark in the temporary directory
|
||||
// is only believed while it is: a mark with no build of this process behind it is stale (a crash, a fault in an
|
||||
// earlier path) and is removed, because left alone it hands back every ask for ever (issue 1768).
|
||||
var inHand atomic.Bool
|
||||
|
||||
// markRetry is how long an agent that cannot mark a build in hand takes no work, and markFault when it last failed to.
|
||||
// Taking nothing is the point: an ask fetched and handed back at once, many times a second, spends all its deliveries.
|
||||
const markRetry = 30 * time.Second
|
||||
|
||||
var (
|
||||
markMu sync.Mutex
|
||||
markFault time.Time
|
||||
markSaid string
|
||||
)
|
||||
|
||||
// markFaulty says the agent could not mark a build in hand and has not yet been able to since: it takes no work. Once
|
||||
// markRetry has passed it tries the mark itself, with no ask in hand, so that an ask is fetched only when marking works.
|
||||
func markFaulty(now time.Time) bool {
|
||||
markMu.Lock()
|
||||
failed := markFault
|
||||
markMu.Unlock()
|
||||
if failed.IsZero() {
|
||||
return false
|
||||
}
|
||||
if now.Sub(failed) < markRetry {
|
||||
return true
|
||||
}
|
||||
f, err := os.OpenFile(inHandMark(), os.O_WRONLY|os.O_CREATE|os.O_EXCL, 0o644)
|
||||
if err != nil && errors.Is(err, os.ErrExist) && !inHand.Load() {
|
||||
_ = os.Remove(inHandMark())
|
||||
f, err = os.OpenFile(inHandMark(), os.O_WRONLY|os.O_CREATE|os.O_EXCL, 0o644)
|
||||
}
|
||||
if err != nil {
|
||||
markFailed(err)
|
||||
return true
|
||||
}
|
||||
_ = f.Close()
|
||||
_ = os.Remove(inHandMark())
|
||||
markMu.Lock()
|
||||
markFault, markSaid = time.Time{}, ""
|
||||
markMu.Unlock()
|
||||
fmt.Fprintf(os.Stderr, "the mark of a build in hand can be made again (%s): taking builds\n", inHandMark())
|
||||
return false
|
||||
}
|
||||
|
||||
// markFailed notes that a build could not be marked in hand, and says it when it is a new reason.
|
||||
func markFailed(err error) {
|
||||
markMu.Lock()
|
||||
defer markMu.Unlock()
|
||||
markFault = time.Now()
|
||||
if said := err.Error(); said != markSaid {
|
||||
markSaid = said
|
||||
fmt.Fprintf(os.Stderr, "cannot mark a build in hand (%s), so this agent takes no build for %s and tries again: %v\n",
|
||||
inHandMark(), markRetry, err)
|
||||
}
|
||||
}
|
||||
|
||||
// claim marks a request in hand, unless the agent is drained: then nothing is in hand, and the request goes
|
||||
// back to the queue.
|
||||
func claim() bool {
|
||||
if !inHand.Load() {
|
||||
// Nothing of this process is in hand, so a mark already there is stale.
|
||||
if err := os.Remove(inHandMark()); err == nil {
|
||||
fmt.Fprintf(os.Stderr, "removed the mark of a build in hand (%s): no build of this agent is in hand\n", inHandMark())
|
||||
}
|
||||
}
|
||||
// Made, never written over: one build at a time, and a mark already there is a build in hand.
|
||||
f, err := os.OpenFile(inHandMark(), os.O_WRONLY|os.O_CREATE|os.O_EXCL, 0o644)
|
||||
if err != nil {
|
||||
// Unmarked, an ask would say idle while this build runs: the build is not taken.
|
||||
fmt.Fprintf(os.Stderr, "cannot mark a build in hand (%s), so it is handed back: %v\n", inHandMark(), err)
|
||||
markFailed(err)
|
||||
return false
|
||||
}
|
||||
_, err = f.WriteString(time.Now().UTC().Format(time.RFC3339) + "\n")
|
||||
@@ -89,7 +156,7 @@ func claim() bool {
|
||||
}
|
||||
if err != nil {
|
||||
_ = os.Remove(inHandMark())
|
||||
fmt.Fprintf(os.Stderr, "cannot mark a build in hand (%s), so it is handed back: %v\n", inHandMark(), err)
|
||||
markFailed(err)
|
||||
return false
|
||||
}
|
||||
if drained() {
|
||||
@@ -97,6 +164,7 @@ func claim() bool {
|
||||
fmt.Fprintln(os.Stderr, "asked whether busy, so this agent takes no new build: handed back")
|
||||
return false
|
||||
}
|
||||
inHand.Store(true)
|
||||
return true
|
||||
}
|
||||
|
||||
@@ -107,6 +175,7 @@ func holding(what string) {
|
||||
|
||||
// released ends the build in hand.
|
||||
func released() {
|
||||
inHand.Store(false)
|
||||
if err := os.Remove(inHandMark()); err != nil && !errors.Is(err, os.ErrNotExist) {
|
||||
fmt.Fprintf(os.Stderr, "cannot remove the mark of the build in hand (%s): %v\n", inHandMark(), err)
|
||||
}
|
||||
@@ -144,3 +213,23 @@ func busy() (string, error) {
|
||||
}
|
||||
return fmt.Sprintf("busy: %s, in hand since %s; taking no new build", what, since), nil
|
||||
}
|
||||
|
||||
var (
|
||||
roomMu sync.Mutex
|
||||
roomSaid bool
|
||||
)
|
||||
|
||||
// noRoom says this node is under the floor of free space (novox/hq issue 1834): it takes no work, so another build node
|
||||
// takes the ask instead of this one taking it and ending it in an error. Said once when it starts and again when it ends.
|
||||
func noRoom(workspace string) bool {
|
||||
err := builder.RoomToWork("/", workspace)
|
||||
roomMu.Lock()
|
||||
defer roomMu.Unlock()
|
||||
if err != nil && !roomSaid {
|
||||
fmt.Fprintf(os.Stderr, "taking no builds: %v\n", err)
|
||||
} else if err == nil && roomSaid {
|
||||
fmt.Fprintf(os.Stderr, "there is room again: taking builds\n")
|
||||
}
|
||||
roomSaid = err != nil
|
||||
return err != nil
|
||||
}
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"github.com/novox/mesh-controller/internal/builder"
|
||||
"os"
|
||||
"strings"
|
||||
"sync"
|
||||
@@ -160,3 +161,79 @@ func TestAnUnknownCommandFails(t *testing.T) {
|
||||
t.Fatalf("help failed: %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
// 1768/AC2: a mark naming no build of this agent (left by a crash or a fault) is stale: the next ask removes it and is
|
||||
// run, never fetched and handed back in a loop.
|
||||
func TestAStaleInHandMarkIsRemovedAndTheAskRuns(t *testing.T) {
|
||||
t.Setenv("TMPDIR", t.TempDir())
|
||||
inHand.Store(false)
|
||||
if err := undrained(); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := os.WriteFile(inHandMark(), []byte("2026-10-21T18:45:06Z\n"), 0o644); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if !claim() {
|
||||
t.Fatal("a stale in-hand mark made the agent hand back an ask")
|
||||
}
|
||||
// A live one — this agent's own build in hand — is never taken over.
|
||||
if claim() {
|
||||
t.Fatal("a second build was taken while one is in hand")
|
||||
}
|
||||
if _, err := busy(); err != nil {
|
||||
t.Fatalf("the build in hand was lost: %v", err)
|
||||
}
|
||||
released()
|
||||
}
|
||||
|
||||
// 1768/AC3: an agent that cannot mark a build in hand for another reason takes no work, instead of fetching asks and
|
||||
// handing them back; it takes work again once marking works.
|
||||
func TestAnAgentThatCannotMarkABuildTakesNoWorkUntilItCan(t *testing.T) {
|
||||
dir := t.TempDir()
|
||||
t.Setenv("TMPDIR", dir)
|
||||
inHand.Store(false)
|
||||
markFault, markSaid = time.Time{}, ""
|
||||
t.Cleanup(func() { markFault, markSaid = time.Time{}, "" })
|
||||
if err := undrained(); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
// The mark's place is a directory that cannot be removed or made over: a directory named as the mark.
|
||||
if err := os.MkdirAll(inHandMark()+"/x", 0o755); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if claim() {
|
||||
t.Fatal("an agent that cannot mark a build took it")
|
||||
}
|
||||
if !markFaulty(time.Now()) {
|
||||
t.Fatal("an agent that cannot mark a build still takes work")
|
||||
}
|
||||
// Still failing after the retry time: still takes nothing, and no ask was needed to find out.
|
||||
if !markFaulty(time.Now().Add(2 * markRetry)) {
|
||||
t.Fatal("an agent whose mark still cannot be made takes work")
|
||||
}
|
||||
if err := os.RemoveAll(inHandMark()); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if markFaulty(time.Now().Add(4 * markRetry)) {
|
||||
t.Fatal("an agent whose mark can be made again takes no work")
|
||||
}
|
||||
if !claim() {
|
||||
t.Fatal("an agent that can mark takes no build")
|
||||
}
|
||||
released()
|
||||
}
|
||||
|
||||
// 1834/AC4: given a node under the floor of free space, when the taking loop asks, then it takes nothing, and takes again
|
||||
// once there is room.
|
||||
func TestANodeUnderTheFloorOfFreeSpaceTakesNoWork(t *testing.T) {
|
||||
was := builder.FreeBytes
|
||||
t.Cleanup(func() { builder.FreeBytes = was })
|
||||
builder.FreeBytes = func(string) (uint64, error) { return 2 << 30, nil }
|
||||
if !noRoom(t.TempDir()) {
|
||||
t.Error("a node with 2 GiB free took work")
|
||||
}
|
||||
builder.FreeBytes = func(string) (uint64, error) { return 200 << 30, nil }
|
||||
if noRoom(t.TempDir()) {
|
||||
t.Error("a node with 200 GiB free refused work")
|
||||
}
|
||||
}
|
||||
|
||||
@@ -36,3 +36,17 @@ func TestTheSiblingsAnAskNamesReachTheSpecAndTheOutcome(t *testing.T) {
|
||||
t.Fatalf("a request that names none has siblings %+v", plain.Siblings)
|
||||
}
|
||||
}
|
||||
|
||||
// 1826/AC2: the held values a check request carries reach the spec; a request that carries none leaves it empty.
|
||||
func TestTheHeldValuesAnAskCarriesReachTheSpec(t *testing.T) {
|
||||
spec := checkSpecOf(link.BuildRequest{Check: &link.CheckRequest{Owner: "novox", Repo: "mesh-catalog",
|
||||
HeldConfig: []link.HeldConfig{{Pull: "novox/mesh-catalog#434", Head: "a", Node: "ace", Module: "n8n", Key: "media-gid",
|
||||
Value: []byte("2000"), Approved: "the operator"}}}})
|
||||
if len(spec.Held) != 1 || spec.Held[0].Node != "ace" || spec.Held[0].Key != "media-gid" || string(spec.Held[0].Value) != "2000" ||
|
||||
spec.Held[0].Approved != "the operator" {
|
||||
t.Fatalf("the spec reads %+v", spec.Held)
|
||||
}
|
||||
if plain := checkSpecOf(link.BuildRequest{Check: &link.CheckRequest{Owner: "o", Repo: "r"}}); plain.Held != nil {
|
||||
t.Fatalf("a request that carries none has %+v", plain.Held)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -91,7 +91,7 @@ func TestKillEndsTheBuildRunningHereAndNoOther(t *testing.T) {
|
||||
t.Errorf("kill said %q", said)
|
||||
}
|
||||
// Removed at the kill and again once the build had ended: a container made in between is caught.
|
||||
if len(removed) != 4 || !strings.Contains(removed[0], "label=mesh.build=build-1") || !strings.Contains(removed[2], "label=mesh.build=build-1") {
|
||||
if len(removed) != 6 || !strings.Contains(removed[0], "label=mesh.build=build-1") || !strings.Contains(removed[3], "label=mesh.build=build-1") {
|
||||
t.Errorf("removed %v", removed)
|
||||
}
|
||||
if c := h.current(); c.Running != nil {
|
||||
@@ -160,7 +160,7 @@ func TestAHolderStartingRemovesWhatEarlierBuildsLeftHere(t *testing.T) {
|
||||
}
|
||||
return "", nil
|
||||
}
|
||||
if n := h.removeLeftBehind(); n != 2 || len(removed) != 2 || removed[1] != "docker rm -f c1 c2" {
|
||||
if n := h.removeLeftBehind(); n != 2 || len(removed) != 3 || removed[2] != "docker rm -f -v c1 c2" {
|
||||
t.Fatalf("removed %d: %v", n, removed)
|
||||
}
|
||||
h.remove = func(context.Context, string, string, ...string) (string, error) {
|
||||
|
||||
@@ -64,6 +64,8 @@ is dialled except the broker.
|
||||
MESH_NPM_TOKEN the token for it, likewise
|
||||
MESH_NPM_SCOPE the scope it answers for (default: @novox)
|
||||
MESH_WORKSPACE where to clone and build (default: a temporary directory)
|
||||
MESH_BUILD_CGROUP_PARENT the slice every container a build or check starts joins, which carries the
|
||||
machine's limits on builds (novox/hq issue 1798; default: the runtime's own)
|
||||
|
||||
It also builds one module and stops, which is how a mesh is raised — before there is a
|
||||
broker to take work from or a registry to publish into:
|
||||
@@ -137,6 +139,10 @@ func run() error {
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
// A build and a check run below the machine's own work (novox/hq issue 1798): the agent itself at the
|
||||
// lowest priority, which its git and go children inherit, and every container in the build slice.
|
||||
_ = syscall.Setpriority(syscall.PRIO_PROCESS, 0, 19)
|
||||
builder.CgroupParent = strings.TrimSpace(os.Getenv("MESH_BUILD_CGROUP_PARENT"))
|
||||
workspace := os.Getenv("MESH_WORKSPACE")
|
||||
if workspace == "" {
|
||||
workspace = os.TempDir() + "/mesh-builder"
|
||||
@@ -184,7 +190,7 @@ func run() error {
|
||||
// Paused or drained, it takes nothing new (novox/hq ADR 0219, ADR 0335): a drained agent finishes the build
|
||||
// in hand and then says idle, and its container is replaced between builds.
|
||||
machine := link.MachineOverNATSWith(js, on, seat, link.MachineOptions{
|
||||
Paused: func() bool { return h.Paused() || drained() },
|
||||
Paused: func() bool { return h.Paused() || drained() || markFaulty(time.Now()) || noRoom(workspace) },
|
||||
Taking: func() { taking(seat) },
|
||||
Claim: claim,
|
||||
})
|
||||
@@ -499,6 +505,10 @@ func checkSpecOf(request link.BuildRequest) builder.CheckSpec {
|
||||
Modules: c.Modules, New: c.New, Manifests: c.Manifests, Judge: c.Judge, Base: c.Base,
|
||||
Toolchain: builder.ToolchainOf(request.Held), Toolchains: builder.ToolchainsOf(request.Held),
|
||||
Tests: c.Tests, StoreOnly: c.StoreOnly, SiblingsUnknown: c.SiblingsUnknown}
|
||||
for _, h := range c.HeldConfig {
|
||||
spec.Held = append(spec.Held, builder.HeldValue{Pull: h.Pull, Head: h.Head, Node: h.Node, Module: h.Module, Key: h.Key,
|
||||
Value: h.Value, Approved: h.Approved, By: h.By, At: h.At})
|
||||
}
|
||||
for _, s := range c.Siblings {
|
||||
spec.Siblings = append(spec.Siblings, builder.Sibling{Repository: s.Repository, Number: s.Number, Head: s.Head,
|
||||
Base: s.Base, Dir: s.Dir})
|
||||
|
||||
@@ -645,6 +645,10 @@ func doesWords(act conditions.Action) string {
|
||||
return "the delivery is stopped"
|
||||
case act.Verb == broker.ControllerSeat+".plans" && act.Arguments["retry"] != "":
|
||||
return "the failed builds are asked again"
|
||||
case act.Verb == broker.ControllerSeat+".push" && act.Arguments["node"] != "":
|
||||
return "the held builds are sent to " + act.Arguments["node"]
|
||||
case act.Verb == broker.ControllerSeat+".upgrade" && act.Arguments["release-backlog"] != "":
|
||||
return "the builds held after the failed delivery are released"
|
||||
case strings.HasSuffix(act.Verb, ".restart"):
|
||||
return "its service is restarted on " + act.Machine
|
||||
}
|
||||
|
||||
@@ -191,6 +191,16 @@ func (f following) pullUpdated(ctx context.Context, p link.PullUpdated, w io.Wri
|
||||
scope.Modules, scope.Dependents, scope.New, scope.Manifests = nil, nil, nil, nil
|
||||
composedGate(&direct)
|
||||
}
|
||||
// **Mesh-config is told what the head declares at every announced head of a pull request in a repository that holds
|
||||
// modules** (novox/hq ADR 0502 clauses 2 and 6, issue 1826), also when the head touches no module: a head that reverts
|
||||
// the change must drop the value held for it. Asked of nothing else here.
|
||||
this := pullAtOf(p)
|
||||
if this.Truncated {
|
||||
this.Paths, this.Truncated = truncatedPaths(entries, p.Owner, p.Repo, scope.Modules), false
|
||||
}
|
||||
if scope.gated() || holdsModules(entries, p.Owner, p.Repo) {
|
||||
tellPullDeclares(ctx, w, []pullAt{this})
|
||||
}
|
||||
switch {
|
||||
case !scope.gated() && !scope.Mesh:
|
||||
fmt.Fprintf(w, "%s/%s#%d (%.8s): %s, and the repository is not the mesh's: said, nothing run\n",
|
||||
@@ -209,6 +219,9 @@ func (f following) pullUpdated(ctx context.Context, p link.PullUpdated, w io.Wri
|
||||
}
|
||||
request.Check.Plan = &plan
|
||||
request.Check.Composed = composed
|
||||
if !composed {
|
||||
carryHeld(ctx, w, &request, []pullAt{this})
|
||||
}
|
||||
// **The group's other open pull requests are read beside it** (novox/hq ADR 0382 §1).
|
||||
siblingsFrom(&request, p, entries, lines, groupsErr)
|
||||
seat := buildSeatHeld(ctx)
|
||||
@@ -594,11 +607,13 @@ func checkedOf(result link.BuildResult) link.Checked {
|
||||
// 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
|
||||
// Every member is named with its trunk commit (novox/hq issue 1106): the seat's word, else the one the forge
|
||||
// announced with the head, so the forge's merge tool never meets a member whose verdict names none.
|
||||
c.Members = append(c.Members, link.CheckedMember{Owner: g.Owner, Repo: g.Repo, Number: g.Number,
|
||||
Commit: result.Ref, Trunk: c.Trunk})
|
||||
Commit: result.Ref, Trunk: firstTrunk(c.Trunk, g.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, Trunk: memberTrunk(result.Check, m)})
|
||||
Commit: m.Ref, Trunk: firstTrunk(memberTrunk(result.Check, m), m.Trunk)})
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -627,6 +642,16 @@ func checkedOf(result link.BuildResult) link.Checked {
|
||||
return c
|
||||
}
|
||||
|
||||
// firstTrunk is the first trunk commit named, as twelve characters; empty when none is.
|
||||
func firstTrunk(named ...string) string {
|
||||
for _, n := range named {
|
||||
if n != "" {
|
||||
return twelve(n)
|
||||
}
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
// 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 {
|
||||
|
||||
@@ -250,6 +250,31 @@ func TestAVerdictNamesTheTrunkCommitItJudged(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// **A group's composed verdict names every member's trunk commit** (novox/hq issue 1106): a member the build seat named no
|
||||
// trunk for (an SDK member whose base the seat did not merge, or a seat from before the rule) is named by the trunk the forge
|
||||
// announced with its head, and the primary the same, so the merge tool never reads "names no trunk commit" on a member
|
||||
// whose trunk did not move.
|
||||
func TestAGroupVerdictNamesEveryMembersTrunkTheSDKMemberToo(t *testing.T) {
|
||||
group := &link.CheckRequest{Owner: "novox", Repo: "mesh-catalog", Number: 7, Base: "main", Group: "feat/x",
|
||||
Trunk: "dddddddddddd0000",
|
||||
Members: []link.GroupMember{
|
||||
{Owner: "novox", Repo: "mesh-sdk", Number: 8, Ref: "cccccccccccc0000", Base: "main", Trunk: "eeeeeeeeeeee0000"},
|
||||
{Owner: "novox", Repo: "mesh-host", Number: 9, Ref: "bbbbbbbbbbbb0000", Base: "main", Trunk: "ffffffffffff0000"}}}
|
||||
c := checkedOf(link.BuildResult{ID: "g", Ref: "aaaaaaaaaaaa0000", Checked: group, Check: &link.CheckOutcome{
|
||||
Verdict: "pass", Head: "aaaaaaaaaaaa", Gate: &link.CheckLayer{Verdict: "pass"},
|
||||
Members: []link.CheckedMember{{Owner: "novox", Repo: "mesh-host", Commit: "bbbbbbbbbbbb", Trunk: "222222222222"}}}})
|
||||
want := []string{"dddddddddddd", "eeeeeeeeeeee", "222222222222"}
|
||||
if len(c.Members) != 3 {
|
||||
t.Fatalf("the composed check names its members %+v", c.Members)
|
||||
}
|
||||
for i, m := range c.Members {
|
||||
if m.Trunk != want[i] {
|
||||
t.Fatalf("member %d (%s/%s) is named with trunk %q, want %q (the seat's word first, else the announced one): %+v",
|
||||
i, m.Owner, m.Repo, m.Trunk, want[i], 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.
|
||||
|
||||
@@ -239,7 +239,11 @@ func markUnresolvable(err error) error {
|
||||
// still names anything foreseen is refused, said, and never sent.
|
||||
func composeSend(ctx context.Context, open *stores, node string) (sendable, error) {
|
||||
declared, _, err := composeSendValidated(ctx, open, node)
|
||||
return declared, err
|
||||
if err != nil {
|
||||
return declared, err
|
||||
}
|
||||
// Never a declaration naming an image the store does not hold (novox/hq issue 1742): that module is left out.
|
||||
return withoutMissingImages(ctx, open, node, declared), nil
|
||||
}
|
||||
|
||||
// composeSendValidated is composeSend and what the node-engine's validator refuses of the declaration it composed, for the
|
||||
|
||||
@@ -0,0 +1,61 @@
|
||||
//go:build integration
|
||||
|
||||
package main
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"testing"
|
||||
|
||||
"git.novox.be/novox/mesh-sdk/go/catalogue"
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
)
|
||||
|
||||
// 1840/AC5 (ADR 0507 §5): the source of the declared-packages mirror composes each node and names, for a package two modules
|
||||
// declare and one declared absent, the modules that declare it; the same records give the same bytes on a second pass, so
|
||||
// the mirror writes nothing; a node with no package has a key that says so.
|
||||
func TestTheDeclaredPackagesMirrorNamesWhatEachNodesModulesDeclare(t *testing.T) {
|
||||
open := aMesh(t)
|
||||
ctx := t.Context()
|
||||
register(t, open, catalogue.Manifest{Module: "viewer", Version: "1", Resources: []map[string]any{
|
||||
{"id": "pkg-curl", "type": "package", "package": "curl"},
|
||||
{"id": "pkg-nano", "type": "package", "package": "nano", "absent": true}}})
|
||||
register(t, open, catalogue.Manifest{Module: "fetcher", Version: "1", Resources: []map[string]any{
|
||||
{"id": "pkg-curl", "type": "package", "package": "curl"}}})
|
||||
for _, module := range []string{"viewer", "fetcher"} {
|
||||
if _, err := assign(ctx, open, "anchor", module); err != nil {
|
||||
t.Fatalf("assign anchor %s: %v", module, err)
|
||||
}
|
||||
}
|
||||
source := declaredPackagesMirror(open)
|
||||
first, err := source(ctx)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
var got inventory.DeclaredPackagesMirrored
|
||||
if err := json.Unmarshal(first["anchor"], &got); err != nil {
|
||||
t.Fatalf("anchor has no value: %v", err)
|
||||
}
|
||||
want := []inventory.PackageDeclared{{Package: "curl", Modules: []string{"fetcher", "viewer"}},
|
||||
{Package: "nano", Modules: []string{"viewer"}, Absent: true}}
|
||||
if len(got.Packages) != len(want) {
|
||||
t.Fatalf("anchor declares %+v, want %+v", got.Packages, want)
|
||||
}
|
||||
for i, p := range want {
|
||||
if g := got.Packages[i]; g.Package != p.Package || g.Absent != p.Absent || len(g.Modules) != len(p.Modules) ||
|
||||
(len(p.Modules) > 0 && g.Modules[0] != p.Modules[0]) {
|
||||
t.Errorf("package %d is %+v, want %+v", i, g, p)
|
||||
}
|
||||
}
|
||||
if string(first["laptop"]) != `{"node":"laptop","packages":[]}` {
|
||||
t.Errorf("a node declaring none is %s", first["laptop"])
|
||||
}
|
||||
second, err := source(ctx)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
for node, value := range first {
|
||||
if string(second[node]) != string(value) {
|
||||
t.Errorf("the value of %s changed between two passes over the same records:\n%s\n%s", node, value, second[node])
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1177,6 +1177,12 @@ func askGroupCheck(ctx context.Context, open *stores, group string, members []or
|
||||
return "", err
|
||||
}
|
||||
request.Check.Group = group
|
||||
// **The values held for the keys the members introduce are told and carried** (novox/hq ADR 0502, issue 1826).
|
||||
var pulls []pullAt
|
||||
for i, s := range changeSourcesOf(members, entries, reach) {
|
||||
pulls = append(pulls, pullAt{changeSource: s, Number: members[i].pull().Number})
|
||||
}
|
||||
withHeldConfig(ctx, os.Stderr, &request, pulls, true)
|
||||
// A group's check is queued as ready when any member's pull request is marked ready.
|
||||
request.Check.Ready = slices.ContainsFunc(members, func(m orderMember) bool { return m.Ready })
|
||||
world, err := restOfTheMesh(ctx, open, shelfOf(entries), "")
|
||||
@@ -1204,7 +1210,7 @@ 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, Base: mp.Base})
|
||||
Number: mp.Number, Repository: url, Ref: mp.Commit, Paths: mp.Paths, Base: mp.Base, Trunk: mp.BaseSHA})
|
||||
}
|
||||
seat := buildSeatHeld(ctx)
|
||||
ask, err := askOverOn(seat)
|
||||
|
||||
@@ -59,6 +59,18 @@ func TestAMergeWaitsForItsDeliverysWordAndThePersonsWordWorksWithoutIt(t *testin
|
||||
}
|
||||
}
|
||||
|
||||
// heardOf has this mesh's own view of the plans take in the plan as the bucket holds it. A verb of the
|
||||
// controller (deliveryCommand, plansCommand) opens an inventory of its own and writes the plan there; this
|
||||
// mesh's inventory learns of the write from the bucket's watch, a moment later, and a loaded machine makes the
|
||||
// moment long enough for advanceHeld to read the plan as it was, still waiting for its word, and ask nothing
|
||||
// (issue 1399). Reading the plan from the bucket puts it into the view at once, with no wait to bound.
|
||||
heardOf := func(id string) {
|
||||
t.Helper()
|
||||
if _, err := inv.PlanByID(ctx, id); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
}
|
||||
|
||||
// No holder on record: the merge starts its walk, as before.
|
||||
p := merge("c1aaaaaaaa", "modules/app/index.ts")
|
||||
if p.Waiting() || len(*asked) != 1 {
|
||||
@@ -90,6 +102,7 @@ func TestAMergeWaitsForItsDeliverysWordAndThePersonsWordWorksWithoutIt(t *testin
|
||||
if err := deliveryCommand(ctx, []string{"go", p.ID}); err == nil {
|
||||
t.Fatal("a walk was let go twice")
|
||||
}
|
||||
heardOf(p.ID)
|
||||
advanceHeld(ctx, open)
|
||||
if len(*asked) != 2 {
|
||||
t.Fatalf("the word did not start the walk: %v", *asked)
|
||||
@@ -119,6 +132,7 @@ func TestAMergeWaitsForItsDeliverysWordAndThePersonsWordWorksWithoutIt(t *testin
|
||||
if err := plansCommand(ctx, []string{"go", p.ID, "--why", "mesh-delivery is down"}); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
heardOf(p.ID)
|
||||
advanceHeld(ctx, open)
|
||||
got, _ = inv.PlanByID(ctx, p.ID)
|
||||
if got.Waiting() || !strings.HasPrefix(got.Delivery.By, "a person") || len(*asked) < 4 {
|
||||
|
||||
@@ -68,7 +68,7 @@ func TestTheForgeNotAnsweringInTimeIsNotAskedAgain(t *testing.T) {
|
||||
// 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,
|
||||
w := waitOut{bound: 100 * time.Millisecond, first: 10 * time.Millisecond, most: 50 * time.Millisecond,
|
||||
now: time.Now, sleep: sleepOrDone}
|
||||
asked := 0
|
||||
began := time.Now()
|
||||
|
||||
@@ -0,0 +1,198 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"sort"
|
||||
"strings"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/conditions"
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
)
|
||||
|
||||
// A move held for a person is asked of the person (novox/hq issue 1732, issue 1320; ADR 0377, ADR 0259).
|
||||
//
|
||||
// **A wait only a person can end is said to that person at once.** ADR 0377 holds a recorded module's move that
|
||||
// recreates a container or touches its data until a person pushes the machine. The walk said so in its note and
|
||||
// ended "done", `status` named the machine behind, and nobody was asked: on 2026-10-21 mailu's new build waited on
|
||||
// novox for 40 minutes behind a plan that read "done, 3 tier(s)", and on 2026-10-19 mssql waited on ace the same way.
|
||||
// Row S24 raises one condition per machine that has such a move, for the operator, with the answer **Release**: the
|
||||
// push of that machine, which the controller's own `push` verb performs on the operator's warrant (ADR 0259). It ends
|
||||
// when the machine no longer waits, whoever pushed it.
|
||||
//
|
||||
// A hold a person chose is not asked again — a module they set to `record` with a why, and the bus, whose step has
|
||||
// its own row (S17).
|
||||
|
||||
// kindMovesHeld is S24's kind: machine.<node>.moves-held.
|
||||
const kindMovesHeld = "moves-held"
|
||||
|
||||
// heldFacts is one machine and the moves of recorded modules that wait there for a person.
|
||||
type heldFacts struct {
|
||||
node string
|
||||
moves []heldMove
|
||||
}
|
||||
|
||||
// gatherHeldMoves is, per machine that holds at least one move no person chose to hold, all its held moves, by machine.
|
||||
func gatherHeldMoves(ctx context.Context, inv *inventory.Inventory) ([]heldFacts, error) {
|
||||
nodes, err := inv.Nodes(ctx)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("the machines cannot be read: %w", err)
|
||||
}
|
||||
f, err := readMoveFacts(ctx, inv)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
var out []heldFacts
|
||||
for _, n := range nodes {
|
||||
moves, err := heldMovesOn(ctx, inv, f, n.Name)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
h := heldFacts{node: n.Name, moves: moves}
|
||||
if len(h.asked()) > 0 {
|
||||
out = append(out, h)
|
||||
}
|
||||
}
|
||||
return out, nil
|
||||
}
|
||||
|
||||
// asked are the moves no person chose to hold, and chosen the ones a person did (a module set to record with a why, the bus).
|
||||
func (h heldFacts) asked() []heldMove { return h.byChoice(false) }
|
||||
func (h heldFacts) chosen() []heldMove { return h.byChoice(true) }
|
||||
|
||||
func (h heldFacts) byChoice(chosen bool) []heldMove {
|
||||
var out []heldMove
|
||||
for _, m := range h.moves {
|
||||
if m.Chosen == chosen {
|
||||
out = append(out, m)
|
||||
}
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// modules are the held moves' modules, in order, of all of them.
|
||||
func (h heldFacts) modules() []string { return moduleNames(h.moves) }
|
||||
|
||||
func moduleNames(moves []heldMove) []string {
|
||||
out := make([]string, 0, len(moves))
|
||||
for _, m := range moves {
|
||||
out = append(out, m.Module)
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// releaseAction is the one answer a held move offers: the push of the machine, approved by the operator. The push
|
||||
// names every module whose move waits there as one that may move its data: the operator's Approve is the word
|
||||
// ADR 0217 asks for, and the ask says so. Offered only where no person's own hold is on the machine too: a push
|
||||
// composes every recorded module at its current build, so it would send that move as well, which the ask never named
|
||||
// (ADR 0259 §6), and hold the whole machine if that module's data would move.
|
||||
func (h heldFacts) releaseAction() conditions.Action {
|
||||
return conditions.Action{Label: "Release", Verb: "mesh-controller.push", Level: conditions.LevelApprove,
|
||||
Arguments: map[string]string{"node": h.node, "move": strings.Join(moduleNames(h.asked()), ","), "why": "",
|
||||
"cause": conditions.CauseOperatorAnswer}}
|
||||
}
|
||||
|
||||
// heldWords are the plain words of a machine's held moves: which modules wait, why in general, and what an Approve does.
|
||||
func heldWords(h heldFacts) (headline, explanation, needs string, resolved string) {
|
||||
names := namesWords(moduleNames(h.asked()), 3)
|
||||
headline = clipWords(conditions.Capital(names)+" waits for you on "+h.node, conditions.HeadlineMax)
|
||||
recreates, data := false, false
|
||||
for _, m := range h.asked() {
|
||||
switch {
|
||||
case strings.Contains(m.Why, "recreates"):
|
||||
recreates = true
|
||||
default:
|
||||
data = true
|
||||
}
|
||||
}
|
||||
why := "would change what it runs"
|
||||
switch {
|
||||
case recreates && data:
|
||||
why = "would restart a container or touch its data"
|
||||
case recreates:
|
||||
why = "would restart one of its containers"
|
||||
case data:
|
||||
why = "would touch its files or data"
|
||||
}
|
||||
explanation = clipWords(fmt.Sprintf("The new version of %s %s on %s, so it does not go out with its delivery; "+
|
||||
"it waits for you. Release sends %s everything it is owed, these among it, and lets their data move where it "+
|
||||
"has to. Nothing is sent until you answer.", names, why, h.node, h.node), conditions.ExplanationMax)
|
||||
needs = "release them " + FromMeshMCPServer
|
||||
if chosen := h.chosen(); len(chosen) > 0 {
|
||||
// A push of the machine would send the move a person chose to hold as well: no answer is offered here.
|
||||
explanation = clipWords(fmt.Sprintf("The new version of %s %s on %s, so it does not go out with its delivery; "+
|
||||
"it waits for you. %s is also held there by your own choice, and a push of %s would send that too, so "+
|
||||
"nothing is offered here: the push is yours at the controller's terminal.",
|
||||
names, why, h.node, conditions.Capital(namesWords(moduleNames(chosen), 3)), h.node), conditions.ExplanationMax)
|
||||
needs = fmt.Sprintf("push %s at the controller's terminal, once you have decided about %s.", h.node,
|
||||
namesWords(moduleNames(chosen), 3))
|
||||
}
|
||||
resolved = "Resolved: " + names + " is no longer waiting on " + h.node
|
||||
return
|
||||
}
|
||||
|
||||
// watchMovesHeld is S24: a machine that has moves of recorded modules waiting for a person, said to the operator with the
|
||||
// answer that sends them. The condition ends when the machine no longer waits: it is no longer among the facts.
|
||||
func watchMovesHeld(f *signalFacts) []conditions.Observation {
|
||||
var out []conditions.Observation
|
||||
for _, h := range f.held {
|
||||
var said []string
|
||||
for _, m := range h.moves {
|
||||
said = append(said, fmt.Sprintf("%s %s → %s %s", m.Module, short(m.From), short(m.To), m.Why))
|
||||
}
|
||||
headline, explanation, needs, resolved := heldWords(h)
|
||||
if c := h.chosen(); len(c) > 0 {
|
||||
said = append(said, "held by a person's own choice: "+strings.Join(moduleNames(c), ", "))
|
||||
}
|
||||
var actions []conditions.Action
|
||||
if len(h.chosen()) == 0 {
|
||||
actions = []conditions.Action{h.releaseAction()}
|
||||
}
|
||||
out = append(out, conditions.Observation{Scope: conditions.ScopeMachine, ID: h.node, Kind: kindMovesHeld,
|
||||
Machine: h.node, Severity: conditions.Warning, Resolver: conditions.ResolverOperator,
|
||||
Summary: fmt.Sprintf("%s has %d move(s) of recorded modules waiting for a person's push: %s — `push %s` sends them",
|
||||
h.node, len(h.moves), strings.Join(h.modules(), ", "), h.node),
|
||||
Said: strings.Join(said, "; "),
|
||||
Headline: headline, Explanation: explanation, Needs: needs, Resolved: resolved,
|
||||
Actions: actions})
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// planHeld is, for a plan that ended or is running, the moves its modules carried that a machine still holds for a
|
||||
// person: "module on machine", sorted. The plan's own record says the move waited when it was judged
|
||||
// (PlanModule.Recorded); the machines say whether it still does, and for the build this plan carried, so a plan older
|
||||
// than the build now held is not named.
|
||||
func planHeld(p inventory.Plan, held []heldFacts) []string {
|
||||
var out []string
|
||||
for _, h := range held {
|
||||
for _, m := range h.moves {
|
||||
s := p.Modules[m.Module]
|
||||
if s == nil || !strings.HasPrefix(s.Recorded[h.node], "waits:") || !sameCommit(s.Commit, m.To) {
|
||||
continue
|
||||
}
|
||||
out = append(out, m.Module+" on "+h.node)
|
||||
}
|
||||
}
|
||||
sort.Strings(out)
|
||||
return out
|
||||
}
|
||||
|
||||
// heldSaid is what a plan's line adds when it carries a move that a machine holds for a person (novox/hq issue 1732): a
|
||||
// plan whose module waits for a push is not plainly "done".
|
||||
func heldSaid(p inventory.Plan, held []heldFacts) string {
|
||||
waiting := planHeld(p, held)
|
||||
if len(waiting) == 0 {
|
||||
return ""
|
||||
}
|
||||
return fmt.Sprintf(" — %d held for a person: %s (the operator is asked)", len(waiting), strings.Join(waiting, ", "))
|
||||
}
|
||||
|
||||
// heldNow reads the machines' held moves for a plan's line, nil when they cannot be read: the line then reads as before.
|
||||
func heldNow(ctx context.Context, inv *inventory.Inventory) []heldFacts {
|
||||
held, err := gatherHeldMoves(ctx, inv)
|
||||
if err != nil {
|
||||
return nil // empty-on-error: a plan's line then reads as it did before; the watchdog (S24) says it cannot read
|
||||
}
|
||||
return held
|
||||
}
|
||||
@@ -0,0 +1,92 @@
|
||||
//go:build integration
|
||||
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
)
|
||||
|
||||
func inventoryUpgrade(why string) inventory.Upgrade { return inventory.Upgrade{Why: why, By: "jochen"} }
|
||||
|
||||
func mustMoveFacts(t *testing.T, rm *recordedMesh) moveFacts {
|
||||
t.Helper()
|
||||
f, err := readMoveFacts(t.Context(), rm.open.inventory)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
return f
|
||||
}
|
||||
|
||||
// 1732/AC8 (integration): a mesh running mailu at c1 on two machines, whose registered c2 recreates a container, is read
|
||||
// as two machines each holding mailu's move for a person; a bundle-only c3 on top changes nothing of it; after a machine
|
||||
// is sent c2 (as a push records it) it is no longer among them, and plans that carried c2 say nothing more of it.
|
||||
func TestMachinesHoldingAMoveForAPersonAreReadFromTheRecords(t *testing.T) {
|
||||
rm := aRecordedMesh(t, aMailu(true))
|
||||
c2 := aMailu(true)
|
||||
resourceOf(&c2, "imap")["image"] = "registry.invalid/imap@sha256:2"
|
||||
rm.register(t, c2, "c2", time.Now().Add(-time.Minute))
|
||||
ctx := t.Context()
|
||||
held, err := gatherHeldMoves(ctx, rm.open.inventory)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if len(held) != 2 || held[0].node != "anchor" || held[1].node != "laptop" || len(held[0].moves) != 1 ||
|
||||
held[0].moves[0].Module != "mailu" || held[0].moves[0].To != "c2" || !strings.Contains(held[0].moves[0].Why, "recreates") {
|
||||
t.Fatalf("held %+v", held)
|
||||
}
|
||||
if err := rm.open.inventory.RecordSent(ctx, nodeID(t, rm.open, "anchor"), "d-anchor-c2", map[string]string{"mailu": "c2"}); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
held, err = gatherHeldMoves(ctx, rm.open.inventory)
|
||||
if err != nil || len(held) != 1 || held[0].node != "laptop" {
|
||||
t.Fatalf("after anchor was sent c2: %+v (%v)", held, err)
|
||||
}
|
||||
}
|
||||
|
||||
// 1732/AC9 (integration): a module a person set to record is no ask: they chose the hold.
|
||||
func TestAHoldAPersonChoseIsNotAsked(t *testing.T) {
|
||||
rm := aRecordedMesh(t, aMailu(false))
|
||||
c2 := aMailu(false)
|
||||
c2.Bundles[0].Digest = "sha256:bbb"
|
||||
rm.register(t, c2, "c2", time.Now().Add(-time.Minute))
|
||||
if err := rm.open.inventory.SetUpgradeOf(t.Context(), "mailu", inventoryUpgrade("the migration week")); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
held, err := gatherHeldMoves(t.Context(), rm.open.inventory)
|
||||
if err != nil || len(held) != 0 {
|
||||
t.Fatalf("a machine holding only a person's own hold is asked: %+v (%v)", held, err)
|
||||
}
|
||||
if moves, _ := heldMovesOn(t.Context(), rm.open.inventory, mustMoveFacts(t, rm), "anchor"); len(moves) != 1 || !moves[0].Chosen {
|
||||
t.Fatalf("status still names it, marked as chosen: %+v", moves)
|
||||
}
|
||||
}
|
||||
|
||||
// 1742/AC4 (integration): a registered build naming an image of the store that the store lacks is read as a missing
|
||||
// image on each machine that runs the module; one the store holds is not; and what the store holds is not asked twice.
|
||||
func TestARegisteredBuildNamingAnImageTheStoreLacksIsRead(t *testing.T) {
|
||||
m := aMailu(true)
|
||||
resourceOf(&m, "imap")["image"] = "artifact-store://mailu/imap@sha256:" + strings.Repeat("e", 64)
|
||||
rm := aRecordedMesh(t, m)
|
||||
asked := 0
|
||||
lacking := func(_ context.Context, reference string) (bool, error) { asked++; return false, nil }
|
||||
imagesHeld.Lock()
|
||||
imagesHeld.held = map[string]bool{}
|
||||
imagesHeld.Unlock()
|
||||
got, err := gatherMissingImages(t.Context(), rm.open.inventory, lacking)
|
||||
if err != nil || len(got) != 2 || got[0].Module != "mailu" || got[0].Node != "anchor" || got[1].Node != "laptop" {
|
||||
t.Fatalf("missing %+v (%v)", got, err)
|
||||
}
|
||||
holding := func(_ context.Context, reference string) (bool, error) { asked++; return true, nil }
|
||||
if got, err := gatherMissingImages(t.Context(), rm.open.inventory, holding); err != nil || len(got) != 0 {
|
||||
t.Fatalf("an image the store holds is missing: %+v (%v)", got, err)
|
||||
}
|
||||
before := asked
|
||||
if _, err := gatherMissingImages(t.Context(), rm.open.inventory, lacking); err != nil || asked != before {
|
||||
t.Fatalf("an image the store was found to hold was asked about again (%d, %v)", asked-before, err)
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,237 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"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/inventory"
|
||||
)
|
||||
|
||||
// **A move held for a person is asked of the person** (novox/hq issue 1732, issue 1320; ADR 0377, ADR 0259).
|
||||
|
||||
// aHeldMailu is novox holding mailu's new build because it would recreate a container: the walk's own words.
|
||||
func aHeldMailu() heldFacts {
|
||||
return heldFacts{node: "novox", moves: []heldMove{{Module: "mailu", From: "b2f5ebb2aaaa", To: "3259765dbbbb",
|
||||
Why: "waits: recreates 1 of mailu's 12 container(s) (with a new image: automx)"}}}
|
||||
}
|
||||
|
||||
func heldConditionOn(f *signalFacts) conditions.Condition {
|
||||
o := watchMovesHeld(f)[0]
|
||||
return conditions.Condition{Key: o.Key(), Kind: o.Kind, Severity: o.Severity, Headline: o.Headline,
|
||||
Explanation: conditions.Verdict(o.Needs, o.Explanation), Needs: o.Needs, Actions: o.Actions}
|
||||
}
|
||||
|
||||
// 1732/AC1: a machine holding a move of a recorded module for a person raises one condition for the operator, with
|
||||
// Release as its only answer: the machine's push, approved, naming the modules whose moves wait there.
|
||||
func TestAHeldMoveIsRaisedWithReleaseAsItsOnlyAction(t *testing.T) {
|
||||
f := calm(time.Date(2026, 10, 21, 17, 30, 0, 0, time.UTC))
|
||||
f.held = []heldFacts{aHeldMailu()}
|
||||
got := watchMovesHeld(f)
|
||||
if len(got) != 1 {
|
||||
t.Fatalf("%+v", got)
|
||||
}
|
||||
o := got[0]
|
||||
if o.Kind != "moves-held" || o.Scope != conditions.ScopeMachine || o.ID != "novox" || o.Severity != conditions.Warning ||
|
||||
o.Resolver != conditions.ResolverOperator || o.Key() != "machine.novox.moves-held" {
|
||||
t.Fatalf("kind, scope, subject, severity or resolver: %+v (%s)", o, o.Key())
|
||||
}
|
||||
if len(o.Actions) != 1 {
|
||||
t.Fatalf("actions: %+v", o.Actions)
|
||||
}
|
||||
a := o.Actions[0]
|
||||
if a.Label != "Release" || a.Verb != "mesh-controller.push" || a.Level != conditions.LevelApprove ||
|
||||
a.Arguments["node"] != "novox" || a.Arguments["move"] != "mailu" || a.Arguments["cause"] != conditions.CauseOperatorAnswer {
|
||||
t.Fatalf("the action is not the push of novox: %+v", a)
|
||||
}
|
||||
if _, takes := a.Arguments["why"]; !takes {
|
||||
t.Fatal("the push takes a why, which the asker fills in with the operator's answer")
|
||||
}
|
||||
for _, want := range []string{"mailu", "novox"} {
|
||||
if !strings.Contains(o.Headline+o.Explanation, want) {
|
||||
t.Errorf("the words do not name %q: %q / %q", want, o.Headline, o.Explanation)
|
||||
}
|
||||
}
|
||||
if !strings.Contains(o.Said, "recreates 1 of mailu's 12") {
|
||||
t.Errorf("the evidence does not carry the walk's own words: %q", o.Said)
|
||||
}
|
||||
if w := (conditions.Observation{Headline: o.Headline, Explanation: o.Explanation, Needs: o.Needs, Resolved: o.Resolved}); w.Headline == "" || len(o.Headline) > conditions.HeadlineMax {
|
||||
t.Errorf("headline: %q", o.Headline)
|
||||
}
|
||||
}
|
||||
|
||||
// 1732/AC2: a machine with nothing held raises nothing, so the condition ends the look after the move is sent.
|
||||
func TestAMachineHoldingNothingRaisesNoHeldMoveCondition(t *testing.T) {
|
||||
f := calm(time.Date(2026, 10, 21, 17, 30, 0, 0, time.UTC))
|
||||
if got := watchMovesHeld(f); len(got) != 0 {
|
||||
t.Fatalf("%+v", got)
|
||||
}
|
||||
}
|
||||
|
||||
// 1732/AC3: the condition is asked on a channel at the approve level in words that say what Release does, and the
|
||||
// operator's warrant calls the controller's own push with the machine and the modules, once.
|
||||
func TestAHeldMovesReleaseIsAskedAndAWarrantPushesTheMachine(t *testing.T) {
|
||||
f := calm(time.Date(2026, 10, 21, 17, 30, 0, 0, time.UTC))
|
||||
f.held = []heldFacts{aHeldMailu()}
|
||||
c := heldConditionOn(f)
|
||||
r := newAskerRig(t)
|
||||
r.open = []conditions.Condition{c}
|
||||
if err := r.a.reconcile(context.Background()); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
sent := r.asksSent(t)
|
||||
if len(sent) != 1 || len(sent[0].Options) != 1 {
|
||||
t.Fatalf("asked %+v", sent)
|
||||
}
|
||||
o := sent[0].Options[0]
|
||||
if o.Label != "Release" || o.Level != asks.Approve || o.Does != "the held builds are sent to novox" {
|
||||
t.Errorf("the option is %+v", o)
|
||||
}
|
||||
if err := sent[0].Check(r.now); err != nil {
|
||||
t.Errorf("the ask is refused as made: %v", err)
|
||||
}
|
||||
w := r.warrantFor(t, c.Key, "Release")
|
||||
answerWith(t, r, w)
|
||||
answerWith(t, r, w)
|
||||
if len(r.called) != 1 || !strings.HasPrefix(r.called[0], "mesh-controller.push@ ") ||
|
||||
!strings.Contains(r.called[0], `"node":"novox"`) || !strings.Contains(r.called[0], `"move":"mailu"`) ||
|
||||
!strings.Contains(r.called[0], `"cause":"`+conditions.CauseOperatorAnswer+`"`) ||
|
||||
!strings.Contains(r.called[0], "chose Release") {
|
||||
t.Fatalf("called %v", r.called)
|
||||
}
|
||||
}
|
||||
|
||||
// 1732/AC4: the controller may call its own push and upgrade verbs on a warrant: the grant names them.
|
||||
func TestTheControllerMayActOnAWarrantForPushAndUpgrade(t *testing.T) {
|
||||
for _, verb := range []string{"push", "upgrade"} {
|
||||
granted := false
|
||||
for _, v := range broker.VerbsTheControllerActsOnAWarrant {
|
||||
granted = granted || (v.Seat == broker.ControllerSeat && v.Verb == verb)
|
||||
}
|
||||
if !granted {
|
||||
t.Errorf("the controller may not act on a warrant for %s", verb)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func aDoneMailuPlan() inventory.Plan {
|
||||
return inventory.Plan{ID: "plan-1792585970446304628", Repository: "novox/mesh-catalog", State: inventory.PlanDone,
|
||||
Tiers: [][]string{{"a"}, {"b"}, {"mailu"}},
|
||||
Modules: map[string]*inventory.PlanModule{"mailu": {State: "built", Commit: "3259765dbbbbcccc",
|
||||
Recorded: map[string]string{"novox": "waits: recreates 1 of mailu's 12 container(s)"}}}}
|
||||
}
|
||||
|
||||
// 1732/AC5: a done plan that carries a move a machine still holds for a person says so on its line; once the machine
|
||||
// no longer holds it, or holds another build of the module, the line says nothing more.
|
||||
func TestADonePlanSaysWhatItHoldsForAPerson(t *testing.T) {
|
||||
p := aDoneMailuPlan()
|
||||
line := planLine(p, time.Date(2026, 10, 21, 16, 0, 0, 0, time.UTC)) + heldSaid(p, []heldFacts{aHeldMailu()})
|
||||
if !strings.Contains(line, "done, 3 tier(s)") || !strings.Contains(line, "1 held for a person: mailu on novox") {
|
||||
t.Errorf("the line: %q", line)
|
||||
}
|
||||
if said := heldSaid(p, nil); said != "" {
|
||||
t.Errorf("a plan whose moves were sent says %q", said)
|
||||
}
|
||||
other := aHeldMailu()
|
||||
other.moves[0].To = "9999999ffff"
|
||||
if said := heldSaid(p, []heldFacts{other}); said != "" {
|
||||
t.Errorf("a plan older than the build now held says %q", said)
|
||||
}
|
||||
p.Modules["mailu"].Recorded = map[string]string{"novox": recordedRollsWhy}
|
||||
if said := heldSaid(p, []heldFacts{aHeldMailu()}); said != "" {
|
||||
t.Errorf("a move the plan sent says %q", said)
|
||||
}
|
||||
}
|
||||
|
||||
// 1732/AC6: the builds held after a failed release are asked of the operator: the held-release condition offers
|
||||
// Release, which calls the controller's own `upgrade` with release-backlog and nothing else, once, on a warrant.
|
||||
func TestTheBuildsHeldAfterAFailedReleaseAreAskedAndReleasedOnAWarrant(t *testing.T) {
|
||||
saved := backlogNow
|
||||
t.Cleanup(func() { backlogNow = saved })
|
||||
backlogNow.held = "release-1792595552499982311 failed (failed on novox); what waits is released again by a person"
|
||||
backlogNow.waiting = map[string][]inventory.CarriedMove{"novox": {{Module: "indexer"}, {Module: "nextcloud"}}}
|
||||
got := backlogObservation()
|
||||
if len(got) != 1 || len(got[0].Actions) != 1 {
|
||||
t.Fatalf("raised %+v", got)
|
||||
}
|
||||
a := got[0].Actions[0]
|
||||
if a.Label != "Release" || a.Verb != "mesh-controller.upgrade" || a.Level != conditions.LevelApprove ||
|
||||
a.Arguments["release-backlog"] != "true" || a.Arguments["cause"] != conditions.CauseOperatorAnswer {
|
||||
t.Fatalf("the action: %+v", a)
|
||||
}
|
||||
o := got[0]
|
||||
c := conditions.Condition{Key: o.Key(), Kind: o.Kind, Severity: o.Severity, Headline: o.Headline,
|
||||
Explanation: conditions.Verdict(o.Needs, o.Explanation), Needs: o.Needs, Actions: o.Actions}
|
||||
r := newAskerRig(t)
|
||||
r.open = []conditions.Condition{c}
|
||||
if err := r.a.reconcile(context.Background()); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
sent := r.asksSent(t)
|
||||
if len(sent) != 1 || len(sent[0].Options) != 1 || sent[0].Options[0].Does != "the builds held after the failed delivery are released" {
|
||||
t.Fatalf("asked %+v", sent)
|
||||
}
|
||||
w := r.warrantFor(t, c.Key, "Release")
|
||||
answerWith(t, r, w)
|
||||
answerWith(t, r, w)
|
||||
if len(r.called) != 1 || !strings.HasPrefix(r.called[0], "mesh-controller.upgrade@ ") ||
|
||||
!strings.Contains(r.called[0], `"release-backlog":"true"`) || !strings.Contains(r.called[0], "chose Release") {
|
||||
t.Fatalf("called %v", r.called)
|
||||
}
|
||||
}
|
||||
|
||||
// 1732/AC7: a plan whose send waits for a gate while the builds are held after a failed release reads as waiting for
|
||||
// a person to release them, not "building ... LATE"; with nothing held it still reads as the wait it is.
|
||||
func TestAPlanWaitingForAGateBehindAFailedReleaseIsNotLate(t *testing.T) {
|
||||
saved := backlogNow
|
||||
t.Cleanup(func() { backlogNow = saved })
|
||||
now := time.Date(2026, 10, 21, 18, 50, 0, 0, time.UTC)
|
||||
p := inventory.Plan{ID: "plan-1", Repository: "novox/mesh-sdk", Commit: "c0ffee00", State: inventory.PlanBuilding,
|
||||
Tiers: [][]string{{"indexer"}}, TierEntered: now.Add(-100 * time.Minute), Created: now.Add(-110 * time.Minute),
|
||||
Modules: map[string]*inventory.PlanModule{"indexer": {State: "built"}},
|
||||
Note: refusalNote(0, errors.New("a build waits there for its gate: novox"))}
|
||||
backlogNow.held = ""
|
||||
if line := planLine(p, now); !strings.Contains(line, "a build waits there for its gate: novox") {
|
||||
t.Errorf("the wait is not said: %q", line)
|
||||
}
|
||||
backlogNow.held = "release-1 failed (failed on novox); what waits is released again by a person"
|
||||
line := planLine(p, now)
|
||||
if strings.Contains(line, "LATE") || strings.Contains(line, "building") ||
|
||||
!strings.Contains(line, "until a person releases it") {
|
||||
t.Errorf("a plan held behind a failed release reads %q", line)
|
||||
}
|
||||
}
|
||||
|
||||
// 1732/AC10: a machine that also holds a move a person chose to hold gets no Release, since a push would send that move
|
||||
// too; the condition names both and says the push is the controller's terminal. A machine with only asked moves keeps it.
|
||||
func TestAMachineAlsoHoldingAPersonsOwnHoldIsOfferedNoRelease(t *testing.T) {
|
||||
f := calm(time.Date(2026, 10, 21, 17, 30, 0, 0, time.UTC))
|
||||
h := aHeldMailu()
|
||||
h.moves = append(h.moves, heldMove{Module: "nftables", From: "n1aaaa", To: "n2bbbb",
|
||||
Why: "waits: a person set it to record, and holds every move of it until they push", Chosen: true})
|
||||
f.held = []heldFacts{h}
|
||||
got := watchMovesHeld(f)
|
||||
if len(got) != 1 || len(got[0].Actions) != 0 {
|
||||
t.Fatalf("%+v", got)
|
||||
}
|
||||
o := got[0]
|
||||
text := o.Headline + o.Explanation + o.Needs + o.Summary + o.Said
|
||||
for _, want := range []string{"mailu", "nftables", "terminal", "push novox"} {
|
||||
if !strings.Contains(text, want) {
|
||||
t.Errorf("does not say %q: %q", want, text)
|
||||
}
|
||||
}
|
||||
w := conditions.Words{Headline: o.Headline, Explanation: o.Explanation, Resolved: o.Resolved, Needs: o.Needs}
|
||||
if why, ok := conditions.PlainWords(w, "novox"); !ok {
|
||||
t.Errorf("not plain: %s", why)
|
||||
}
|
||||
f.held = []heldFacts{aHeldMailu()}
|
||||
if got := watchMovesHeld(f); len(got) != 1 || len(got[0].Actions) != 1 || got[0].Actions[0].Arguments["move"] != "mailu" {
|
||||
t.Fatalf("a machine with only asked moves: %+v", got)
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,245 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"slices"
|
||||
"sort"
|
||||
"strings"
|
||||
"sync"
|
||||
|
||||
"git.novox.be/novox/mesh-sdk/go/catalogue"
|
||||
"github.com/novox/mesh-controller/internal/artifacts"
|
||||
"github.com/novox/mesh-controller/internal/conditions"
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
)
|
||||
|
||||
// No declaration is sent that names an image the artifact store does not hold (novox/hq issue 1742).
|
||||
//
|
||||
// On 2026-10-21 at 17:13 a send to novox named `mailu/automx@sha256:c62150b8…`; the build record keeps that digest
|
||||
// ("recent-build") and the store did not hold it. The node-engine removed the running container, then could not pull
|
||||
// the replacement, and every later apply on novox failed for the next hour while the mail clients' autoconfiguration
|
||||
// had no backend. The node-engine's half (pull first, replace after) is its own change; this is the controller's: **a
|
||||
// module whose image the store lacks is left out of the declaration**, as a module whose setting nobody gave is
|
||||
// (ADR 0163, rule 6) — the node-engine keeps what it has of it and touches none of its containers — and **it is said**,
|
||||
// row S25: a condition naming the module, the machine and the image, until the store holds the image again (a new build
|
||||
// of the module, or the copy put back).
|
||||
//
|
||||
// Judged only for an image the store's own address names, from the send's own resources; an image of another registry
|
||||
// is no business of the store's. A store that cannot be asked judges nothing: a send is not refused for a question
|
||||
// that did not answer.
|
||||
|
||||
// kindImageMissing is S25's kind: module.<module>.<machine>.image-missing.
|
||||
const kindImageMissing = "image-missing"
|
||||
|
||||
// missingImage is a module held out of a machine's declaration because the store lacks an image it names.
|
||||
type missingImage struct {
|
||||
Node, Module, Image string
|
||||
}
|
||||
|
||||
// storeHolds is whether the store holds the manifest an image reference at its address names.
|
||||
type storeHolds func(ctx context.Context, reference string) (bool, error)
|
||||
|
||||
// imageInStore is the artifact-store reference of an image the store's address names, "" for any other.
|
||||
func imageInStore(image, address string) string {
|
||||
if address == "" || !strings.HasPrefix(image, address+"/") || !strings.Contains(image, "@sha256:") {
|
||||
return ""
|
||||
}
|
||||
reference := catalogue.Recorded(image)
|
||||
if _, ours := catalogue.InArtifactStore(reference); !ours {
|
||||
return ""
|
||||
}
|
||||
return reference
|
||||
}
|
||||
|
||||
// holdBackMissingImages leaves out of the declaration every module that names an image the store does not hold,
|
||||
// and answers what it left out. The module's resources go, it joins LeftOut with the reason, and its build stays the
|
||||
// one the machine was last sent (`was`).
|
||||
func holdBackMissingImages(ctx context.Context, node string, s *sendable, address string, holds storeHolds,
|
||||
was map[string]string) []missingImage {
|
||||
lacks := map[string]bool{} // reference → the store does not hold it; absent: not asked, or no answer
|
||||
asked := map[string]bool{}
|
||||
lacking := map[string]string{} // module → the image
|
||||
for _, r := range s.Resources {
|
||||
if fmt.Sprint(r["type"]) != "container" {
|
||||
continue
|
||||
}
|
||||
image, _ := r["image"].(string)
|
||||
reference := imageInStore(image, address)
|
||||
module := s.moduleOf[fmt.Sprint(r["id"])]
|
||||
if reference == "" || module == "" || lacking[module] != "" {
|
||||
continue
|
||||
}
|
||||
if !asked[reference] {
|
||||
asked[reference] = true
|
||||
held, err := holds(ctx, reference)
|
||||
// empty-on-error: the store did not answer, so nothing is held back for a question unanswered
|
||||
lacks[reference] = err == nil && !held
|
||||
}
|
||||
if lacks[reference] {
|
||||
lacking[module] = image
|
||||
}
|
||||
}
|
||||
if len(lacking) == 0 {
|
||||
return nil
|
||||
}
|
||||
kept := s.Resources[:0:0]
|
||||
for _, r := range s.Resources {
|
||||
if _, out := lacking[s.moduleOf[fmt.Sprint(r["id"])]]; !out {
|
||||
kept = append(kept, r)
|
||||
}
|
||||
}
|
||||
s.Resources = kept
|
||||
if s.leftOutWhy == nil {
|
||||
s.leftOutWhy = map[string]string{}
|
||||
}
|
||||
var found []missingImage
|
||||
for module, image := range lacking {
|
||||
s.leftOutWhy[module] = "its image " + image + " is not in the artifact store"
|
||||
if !slices.Contains(s.LeftOut, module) {
|
||||
s.LeftOut = append(s.LeftOut, module)
|
||||
}
|
||||
if s.Builds != nil {
|
||||
if prior, sent := was[module]; sent {
|
||||
s.Builds[module] = prior
|
||||
} else {
|
||||
delete(s.Builds, module)
|
||||
}
|
||||
}
|
||||
found = append(found, missingImage{Node: node, Module: module, Image: image})
|
||||
}
|
||||
sort.Strings(s.LeftOut)
|
||||
sort.Slice(found, func(i, j int) bool { return found[i].Module < found[j].Module })
|
||||
return found
|
||||
}
|
||||
|
||||
// withoutMissingImages is composeSend's last step: the store asked about the images the declaration names, the modules
|
||||
// whose image it lacks left out and kept in the ledger S25 reads. A store that cannot be found or asked leaves the
|
||||
// declaration as composed.
|
||||
func withoutMissingImages(ctx context.Context, open *stores, node string, s sendable) sendable {
|
||||
inv := open.inventory
|
||||
shelf, err := inv.Catalogue(ctx)
|
||||
if err != nil {
|
||||
return s
|
||||
}
|
||||
address, err := artifactStoreAddress(ctx, inv, shelf, node)
|
||||
if err != nil || address == "" {
|
||||
return s
|
||||
}
|
||||
sent, known, err := inv.SentBuilds(ctx, node)
|
||||
if err != nil || !known {
|
||||
sent = nil
|
||||
}
|
||||
store := artifacts.Store{Address: address}
|
||||
found := holdBackMissingImages(ctx, node, &s, address, store.HoldsManifest, sent)
|
||||
for _, m := range found {
|
||||
fmt.Printf("%s: %s is left out of the declaration: its image %s is not in the artifact store\n", node, m.Module, m.Image)
|
||||
}
|
||||
return s
|
||||
}
|
||||
|
||||
// imageFacts are the images S25 raises: a module whose registered build names an image the store lacks, on each machine
|
||||
// that runs it.
|
||||
type imageFacts struct {
|
||||
missingImage
|
||||
}
|
||||
|
||||
// imagesHeld remembers the images the store was found to hold: a stored image is named by its digest and stays what it
|
||||
// is, so it is asked about once; one it lacks is asked again at every look.
|
||||
var imagesHeld = struct {
|
||||
sync.Mutex
|
||||
held map[string]bool
|
||||
}{held: map[string]bool{}}
|
||||
|
||||
// gatherMissingImages is every machine's module whose registered build — the one a send would carry — names an image of
|
||||
// the artifact store that the store does not hold. Read from the catalogue and the store, never from what a send did:
|
||||
// a push is a command of its own, and the serving controller's watchdog hears nothing of it.
|
||||
func gatherMissingImages(ctx context.Context, inv *inventory.Inventory, holds storeHolds) ([]imageFacts, error) {
|
||||
shelf, err := inv.Catalogue(ctx)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("the catalogue cannot be read: %w", err)
|
||||
}
|
||||
var out []imageFacts
|
||||
for _, module := range sortedKeysOf(modulesOf(shelf)) {
|
||||
for _, r := range shelf[module].Resources {
|
||||
if fmt.Sprint(r["type"]) != "container" {
|
||||
continue
|
||||
}
|
||||
image, _ := r["image"].(string)
|
||||
if _, ours := catalogue.InArtifactStore(image); !ours || !strings.Contains(image, "@sha256:") {
|
||||
continue
|
||||
}
|
||||
imagesHeld.Lock()
|
||||
known := imagesHeld.held[image]
|
||||
imagesHeld.Unlock()
|
||||
if !known {
|
||||
held, err := holds(ctx, image)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("the artifact store cannot be asked about %s: %w", image, err)
|
||||
}
|
||||
if held {
|
||||
imagesHeld.Lock()
|
||||
imagesHeld.held[image] = true
|
||||
imagesHeld.Unlock()
|
||||
continue
|
||||
}
|
||||
} else {
|
||||
continue
|
||||
}
|
||||
running, err := inv.Running(ctx, module)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
for _, node := range running {
|
||||
out = append(out, imageFacts{missingImage{Node: node, Module: module, Image: image}})
|
||||
}
|
||||
}
|
||||
}
|
||||
return out, nil
|
||||
}
|
||||
|
||||
// modulesOf is the shelf's modules as a map of names, for sortedKeysOf.
|
||||
func modulesOf(shelf map[string]catalogue.Manifest) map[string]string {
|
||||
out := make(map[string]string, len(shelf))
|
||||
for m := range shelf {
|
||||
out[m] = m
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// watchMissingImages is S25: a module left out of a machine's declaration because the store lacks its image, said at
|
||||
// once. The condition ends when the store holds the image, or a send names another.
|
||||
func watchMissingImages(f *signalFacts) []conditions.Observation {
|
||||
var out []conditions.Observation
|
||||
for _, m := range f.images {
|
||||
out = append(out, conditions.Observation{Scope: conditions.ScopeModule, ID: m.Module + "." + m.Node, Kind: kindImageMissing,
|
||||
Machine: m.Node, Severity: conditions.Warning, Resolver: conditions.ResolverOperator,
|
||||
Summary: fmt.Sprintf("%s is left out of every send to %s: its declaration names an image that the artifact store does "+
|
||||
"not hold (the evidence names it); the running container is untouched", m.Module, m.Node),
|
||||
Said: "image " + m.Image + " is not in the store",
|
||||
Headline: clipWords(conditions.Capital(m.Module)+" is not updated on "+m.Node, conditions.HeadlineMax),
|
||||
Explanation: clipWords(fmt.Sprintf("The new version of %s names a container image that the mesh's store does not "+
|
||||
"hold, so it was not sent to %s. What runs there is untouched, and the rest of %s is sent as usual.",
|
||||
m.Module, m.Node, m.Node), conditions.ExplanationMax),
|
||||
Needs: fmt.Sprintf("build %s again; the details name the image.", m.Module),
|
||||
Resolved: "Resolved: the store holds the image of " + m.Module + " again"})
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// gatherMissingImagesHere is gatherMissingImages asking the mesh's own artifact store; nothing to ask where the mesh has
|
||||
// none on its network yet.
|
||||
func gatherMissingImagesHere(ctx context.Context, inv *inventory.Inventory) ([]imageFacts, error) {
|
||||
shelf, err := inv.Catalogue(ctx)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("the catalogue cannot be read: %w", err)
|
||||
}
|
||||
address, err := artifactStoreAddress(ctx, inv, shelf, "")
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if address == "" {
|
||||
return nil, nil
|
||||
}
|
||||
return gatherMissingImages(ctx, inv, artifacts.Store{Address: address}.HoldsManifest)
|
||||
}
|
||||
@@ -0,0 +1,125 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/conditions"
|
||||
)
|
||||
|
||||
// **No declaration is sent that names an image the artifact store does not hold** (novox/hq issue 1742).
|
||||
|
||||
const storeAt = "novox.internal:5100"
|
||||
|
||||
// automx is the image the send of 2026-10-21 17:13 named and the store lacked; the others are held.
|
||||
const (
|
||||
automxImage = storeAt + "/mailu/automx@sha256:c62150b8e2cbcc18cb911b098c2877f928761a1e6251667f39ea18251ea35591"
|
||||
imapImage = storeAt + "/mailu/imap@sha256:aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa"
|
||||
)
|
||||
|
||||
func aMailSend() sendable {
|
||||
return sendable{
|
||||
Resources: []map[string]any{
|
||||
{"id": "mailu.automx", "type": "container", "image": automxImage},
|
||||
{"id": "mailu.automx-config", "type": "file", "path": "/etc/automx.conf"},
|
||||
{"id": "mailu.imap", "type": "container", "image": imapImage},
|
||||
{"id": "other.web", "type": "container", "image": "docker.io/library/nginx@sha256:" + strings.Repeat("b", 64)},
|
||||
{"id": "dns.dnsmasq", "type": "container", "image": storeAt + "/dnsmasq/main@sha256:" + strings.Repeat("c", 64)},
|
||||
},
|
||||
moduleOf: map[string]string{"mailu.automx": "automx", "mailu.automx-config": "automx", "mailu.imap": "mailu",
|
||||
"other.web": "other", "dns.dnsmasq": "dnsmasq"},
|
||||
Builds: map[string]string{"automx": "b2f5ebb2new", "mailu": "m2", "other": "o1", "dnsmasq": "d1"},
|
||||
}
|
||||
}
|
||||
|
||||
func storeHolding(missing ...string) (storeHolds, *[]string) {
|
||||
var asked []string
|
||||
return func(_ context.Context, reference string) (bool, error) {
|
||||
asked = append(asked, reference)
|
||||
for _, m := range missing {
|
||||
if strings.Contains(reference, m) {
|
||||
return false, nil
|
||||
}
|
||||
}
|
||||
return true, nil
|
||||
}, &asked
|
||||
}
|
||||
|
||||
// 1742/AC1: given a send naming automx's image, which the store does not hold, when the declaration is judged, then
|
||||
// every resource of automx is out of it, automx is among the modules left out with the reason, its build is the one the
|
||||
// machine was last sent, and every other module — an image of another registry among them — is as composed.
|
||||
func TestAModuleWhoseImageTheStoreLacksIsLeftOutOfTheSend(t *testing.T) {
|
||||
s := aMailSend()
|
||||
holds, asked := storeHolding("mailu/automx@")
|
||||
found := holdBackMissingImages(t.Context(), "novox", &s, storeAt, holds, map[string]string{"automx": "b2f5ebb2old"})
|
||||
if len(found) != 1 || found[0].Module != "automx" || found[0].Node != "novox" || found[0].Image != automxImage {
|
||||
t.Fatalf("found %+v", found)
|
||||
}
|
||||
var ids []string
|
||||
for _, r := range s.Resources {
|
||||
ids = append(ids, r["id"].(string))
|
||||
}
|
||||
if got := strings.Join(ids, ","); got != "mailu.imap,other.web,dns.dnsmasq" {
|
||||
t.Errorf("the declaration keeps %s", got)
|
||||
}
|
||||
if len(s.LeftOut) != 1 || s.LeftOut[0] != "automx" || !strings.Contains(s.leftOutWhy["automx"], "not in the artifact store") {
|
||||
t.Errorf("left out %v because %v", s.LeftOut, s.leftOutWhy)
|
||||
}
|
||||
if s.Builds["automx"] != "b2f5ebb2old" || s.Builds["mailu"] != "m2" || s.Builds["other"] != "o1" {
|
||||
t.Errorf("builds %v", s.Builds)
|
||||
}
|
||||
for _, a := range *asked {
|
||||
if strings.Contains(a, "docker.io") {
|
||||
t.Errorf("the store was asked about an image of another registry: %s", a)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// 1742/AC2: given a module never sent to the machine, when its image is missing, then it has no build in the record of the
|
||||
// send; given the store does not answer, then nothing is held back for a question unanswered.
|
||||
func TestAnUnansweredStoreHoldsNothingBackAndANewModuleHasNoBuild(t *testing.T) {
|
||||
s := aMailSend()
|
||||
holds, _ := storeHolding("mailu/automx@")
|
||||
found := holdBackMissingImages(t.Context(), "novox", &s, storeAt, holds, nil)
|
||||
if len(found) != 1 {
|
||||
t.Fatalf("%+v", found)
|
||||
}
|
||||
if _, has := s.Builds["automx"]; has {
|
||||
t.Errorf("a module never sent is recorded as sent: %v", s.Builds)
|
||||
}
|
||||
s = aMailSend()
|
||||
silent := func(context.Context, string) (bool, error) { return false, errors.New("registry: connection refused") }
|
||||
if found := holdBackMissingImages(t.Context(), "novox", &s, storeAt, silent, nil); len(found) != 0 || len(s.LeftOut) != 0 ||
|
||||
len(s.Resources) != 5 {
|
||||
t.Errorf("an unanswered store held back %+v, left out %v", found, s.LeftOut)
|
||||
}
|
||||
}
|
||||
|
||||
// 1742/AC3: a module left out for its image raises a condition for the operator naming the module, the machine and the
|
||||
// image in the evidence, plain words, and no answer to give; a mesh whose images are all held raises nothing.
|
||||
func TestAMissingImageIsRaisedForTheOperator(t *testing.T) {
|
||||
f := calm(time.Date(2026, 10, 21, 17, 40, 0, 0, time.UTC))
|
||||
if got := watchMissingImages(f); len(got) != 0 {
|
||||
t.Fatalf("%+v", got)
|
||||
}
|
||||
f.images = []imageFacts{{missingImage{Node: "novox", Module: "automx", Image: automxImage}}}
|
||||
got := watchMissingImages(f)
|
||||
if len(got) != 1 {
|
||||
t.Fatalf("%+v", got)
|
||||
}
|
||||
o := got[0]
|
||||
if o.Kind != "image-missing" || o.Key() != "module.automx.novox.image-missing" || o.Resolver != conditions.ResolverOperator ||
|
||||
o.Severity != conditions.Warning || o.Machine != "novox" {
|
||||
t.Fatalf("%+v (%s)", o, o.Key())
|
||||
}
|
||||
if !strings.Contains(o.Said, "c62150b8") || !strings.Contains(o.Headline+o.Explanation, "automx") {
|
||||
t.Errorf("words: %q / %q / %q", o.Headline, o.Explanation, o.Said)
|
||||
}
|
||||
w := conditions.Words{Headline: o.Headline, Explanation: o.Explanation, Resolved: o.Resolved, Needs: o.Needs}
|
||||
if why, ok := conditions.PlainWords(w, "novox"); !ok {
|
||||
t.Errorf("not plain: %s", why)
|
||||
}
|
||||
}
|
||||
@@ -35,7 +35,7 @@ func TestAMergeSaysTheModulesWhoseBuildSourceItLeftUnchanged(t *testing.T) {
|
||||
{Own: true, Paths: []string{"modules/build-agent/Dockerfile", "modules/build-agent/module.json"}},
|
||||
},
|
||||
"route-proxy": {
|
||||
{Repository: "novox/mesh-controller", Ref: "main", Paths: []string{"go.mod", "examples/route-proxy/"}},
|
||||
{Repository: "novox/mesh-controller", Ref: "main", Paths: []string{"go.mod", "modules/route-proxy/cmd/route-proxy/"}},
|
||||
{Own: true, Paths: []string{"modules/route-proxy/Dockerfile", "modules/route-proxy/module.json"}},
|
||||
},
|
||||
}
|
||||
|
||||
@@ -65,6 +65,9 @@ type mergeCheckInput struct {
|
||||
// group are the other heads of a delivery group composed with this one (novox/hq ADR 0239), each laid
|
||||
// over the mesh after the one before: the group judged as one future state.
|
||||
group []groupChange
|
||||
// held are the approved config values held for the keys the pull requests introduce (novox/hq ADR 0502 clause 4),
|
||||
// laid over the composition with the change only.
|
||||
held []heldValue
|
||||
// admin is a PostgreSQL the gate may create and drop databases in.
|
||||
admin string
|
||||
// beside is the directory holding the core clones beside the check (MESH_CHECK_BESIDE), for finding moves.
|
||||
@@ -189,6 +192,8 @@ func mergeGateCommand(ctx context.Context, args []string) error {
|
||||
"--changed, for a list too long for an argument (novox/hq issue 1247)")
|
||||
group := set.String("group", "", "a delivery group's other heads, as JSON [{repository, tree, changed}], composed "+
|
||||
"with this one as one future state (novox/hq ADR 0239)")
|
||||
heldFile := set.String("held", "", "a file of the config values approved for keys the change's pull requests introduce, as JSON "+
|
||||
"[{pull, node, module, key, value, approved_by}], laid over the composition with the change (novox/hq ADR 0502)")
|
||||
asJSON := set.Bool("json", false, "print the verdict as JSON")
|
||||
if _, err := parseAround(set, args); err != nil {
|
||||
return err
|
||||
@@ -208,6 +213,10 @@ func mergeGateCommand(ctx context.Context, args []string) error {
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
held, err := readHeld(*heldFile)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
out := io.Writer(os.Stdout)
|
||||
stdout := os.Stdout
|
||||
if *asJSON {
|
||||
@@ -223,7 +232,7 @@ func mergeGateCommand(ctx context.Context, args []string) error {
|
||||
return err
|
||||
}
|
||||
v, err := judgeChange(ctx, mergeCheckInput{facts: f, repository: *repository, tree: *tree, changed: changedList,
|
||||
group: others, admin: *admin, say: out, beside: os.Getenv("MESH_CHECK_BESIDE")})
|
||||
group: others, held: held, admin: *admin, say: out, beside: os.Getenv("MESH_CHECK_BESIDE")})
|
||||
os.Stdout = stdout
|
||||
if err != nil {
|
||||
return err
|
||||
@@ -387,7 +396,16 @@ func judgeChange(ctx context.Context, in mergeCheckInput) (mergeVerdict, error)
|
||||
}
|
||||
}
|
||||
sort.Strings(added)
|
||||
after, tried, notes, err := composeEveryMachine(ctx, in, change, changeSources, added)
|
||||
// **The held values are laid in this composition only** (novox/hq ADR 0502 clause 4): the mesh as it is does not
|
||||
// declare their keys, so the base composition would refuse them.
|
||||
withHeld := in
|
||||
var heldNotes []string
|
||||
withHeld.facts, heldNotes = layHeld(in.facts, in.held, change)
|
||||
for _, n := range heldNotes {
|
||||
say("%s", n)
|
||||
}
|
||||
v.Notes = append(v.Notes, heldNotes...)
|
||||
after, tried, notes, err := composeEveryMachine(ctx, withHeld, change, changeSources, added)
|
||||
if err != nil {
|
||||
return v, fmt.Errorf("the mesh with the change could not be raised: %w", err)
|
||||
}
|
||||
|
||||
@@ -0,0 +1,135 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"os"
|
||||
"sort"
|
||||
"strings"
|
||||
|
||||
"git.novox.be/novox/mesh-sdk/go/catalogue"
|
||||
snapshot "git.novox.be/novox/mesh-sdk/go/facts"
|
||||
)
|
||||
|
||||
// Config values held for the keys an open pull request introduces (novox/hq ADR 0502 clause 4, issue 1826): the gate
|
||||
// lays each approved one over its module's values on its node in the composition with the change, and in that one
|
||||
// only. In the mesh as it is the key is not declared, so the value would be refused there.
|
||||
|
||||
// heldValue is one approved held value as the build agent writes it (--held): the value of Key for Module on Node,
|
||||
// a machine's real name, which the snapshot holds only as a pseudonym.
|
||||
type heldValue struct {
|
||||
Pull string `json:"pull"`
|
||||
Head string `json:"head,omitempty"`
|
||||
Node string `json:"node"`
|
||||
Module string `json:"module"`
|
||||
Key string `json:"key"`
|
||||
Value json.RawMessage `json:"value"`
|
||||
Approved string `json:"approved,omitempty"`
|
||||
By string `json:"by,omitempty"`
|
||||
At string `json:"at,omitempty"`
|
||||
}
|
||||
|
||||
// readHeld reads the file --held names; none named, none held.
|
||||
func readHeld(path string) ([]heldValue, error) {
|
||||
if path == "" {
|
||||
return nil, nil
|
||||
}
|
||||
raw, err := os.ReadFile(path)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
var held []heldValue
|
||||
if err := json.Unmarshal(raw, &held); err != nil {
|
||||
return nil, fmt.Errorf("the held values are not readable: %w", err)
|
||||
}
|
||||
for _, h := range held {
|
||||
if h.Node == "" || h.Module == "" || h.Key == "" || len(h.Value) == 0 {
|
||||
return nil, fmt.Errorf("a held value of %s names no node, module, key or value", h.Pull)
|
||||
}
|
||||
}
|
||||
return held, nil
|
||||
}
|
||||
|
||||
// layHeld is the snapshot with each held value laid as the value of its key in its node's layer of its module, and what
|
||||
// it said of them. The snapshot given is not changed. **A held value for a machine the snapshot does not hold, or a
|
||||
// module the change does not define, is said and not laid**, never dropped silently; one for a module not assigned to
|
||||
// its machine is laid and said. The notes name machines as the snapshot does (roles and pseudonym), not by their names.
|
||||
func layHeld(f snapshot.Facts, held []heldValue, shelf map[string]catalogue.Manifest) (snapshot.Facts, []string) {
|
||||
if len(held) == 0 {
|
||||
return f, nil
|
||||
}
|
||||
out := f
|
||||
out.Machines = make([]snapshot.Machine, len(f.Machines))
|
||||
copy(out.Machines, f.Machines)
|
||||
var notes, laid []string
|
||||
pulls := map[string]bool{}
|
||||
for _, h := range held {
|
||||
at := -1
|
||||
pseudonym := snapshot.Pseudonym("machine", h.Node)
|
||||
for i, m := range out.Machines {
|
||||
if m.Name == pseudonym {
|
||||
at = i
|
||||
}
|
||||
}
|
||||
if at < 0 {
|
||||
notes = append(notes, fmt.Sprintf("the value held for %s of %s (%s=%s) is not composed: the snapshot holds no machine %s",
|
||||
h.Module, h.Pull, h.Key, h.Value, pseudonym))
|
||||
continue
|
||||
}
|
||||
if _, defined := shelf[h.Module]; !defined {
|
||||
notes = append(notes, fmt.Sprintf("the value held for %s of %s (%s=%s) is not composed: the change defines no module %s",
|
||||
h.Module, h.Pull, h.Key, h.Value, h.Module))
|
||||
continue
|
||||
}
|
||||
var value any
|
||||
if err := json.Unmarshal(h.Value, &value); err != nil {
|
||||
notes = append(notes, fmt.Sprintf("the value held for %s of %s (%s) is not composed: it is not a value: %v",
|
||||
h.Module, h.Pull, h.Key, err))
|
||||
continue
|
||||
}
|
||||
m := &out.Machines[at]
|
||||
layers := make([]snapshot.Settings, len(m.Settings))
|
||||
copy(layers, m.Settings)
|
||||
found := false
|
||||
for i := range layers {
|
||||
if layers[i].Module == h.Module {
|
||||
values := make(map[string]any, len(layers[i].Values)+1)
|
||||
for k, v := range layers[i].Values {
|
||||
values[k] = v
|
||||
}
|
||||
values[h.Key] = value
|
||||
layers[i].Values = values
|
||||
found = true
|
||||
}
|
||||
}
|
||||
if !found {
|
||||
layers = append(layers, snapshot.Settings{Module: h.Module, Values: map[string]any{h.Key: value}})
|
||||
sort.Slice(layers, func(a, b int) bool { return layers[a].Module < layers[b].Module })
|
||||
}
|
||||
m.Settings = layers
|
||||
assigned := false
|
||||
for _, a := range m.Assigned {
|
||||
assigned = assigned || a == h.Module
|
||||
}
|
||||
by := ""
|
||||
if h.Approved != "" {
|
||||
by = ", approved by " + h.Approved
|
||||
}
|
||||
line := fmt.Sprintf("%s on %s %s=%s%s", h.Module, m.Described(), h.Key, h.Value, by)
|
||||
if !assigned {
|
||||
line += " (not assigned there in the snapshot)"
|
||||
}
|
||||
laid = append(laid, line)
|
||||
pulls[h.Pull] = true
|
||||
}
|
||||
if len(laid) > 0 {
|
||||
var names []string
|
||||
for p := range pulls {
|
||||
names = append(names, p)
|
||||
}
|
||||
sort.Strings(names)
|
||||
notes = append([]string{fmt.Sprintf("composed with %d value(s) held for %s: %s", len(laid), strings.Join(names, ", "),
|
||||
strings.Join(laid, "; "))}, notes...)
|
||||
}
|
||||
return out, notes
|
||||
}
|
||||
@@ -0,0 +1,85 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"os"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"git.novox.be/novox/mesh-sdk/go/catalogue"
|
||||
snapshot "git.novox.be/novox/mesh-sdk/go/facts"
|
||||
)
|
||||
|
||||
func heldGateFacts() snapshot.Facts {
|
||||
return snapshot.Facts{Machines: []snapshot.Machine{
|
||||
{Name: snapshot.Pseudonym("machine", "ace"), Roles: []string{"the build node"}, Assigned: []string{"n8n"},
|
||||
Settings: []snapshot.Settings{{Module: "n8n", Values: map[string]any{"port": 5678.0}}}},
|
||||
{Name: snapshot.Pseudonym("machine", "g14")},
|
||||
}}
|
||||
}
|
||||
|
||||
var heldShelf = map[string]catalogue.Manifest{"n8n": {Module: "n8n"}}
|
||||
|
||||
// 1826/AC3: a held value is laid in its node's layer of its module, beside what the layer holds, and said.
|
||||
func TestAHeldValueIsLaidOverItsNodesLayerAndSaid(t *testing.T) {
|
||||
f := heldGateFacts()
|
||||
got, notes := layHeld(f, []heldValue{{Pull: "novox/mesh-catalog#434", Node: "ace", Module: "n8n", Key: "media-gid",
|
||||
Value: []byte("2000"), Approved: "the operator"}}, heldShelf)
|
||||
layer := got.Machines[0].Settings[0].Values
|
||||
if layer["media-gid"] != 2000.0 || layer["port"] != 5678.0 {
|
||||
t.Fatalf("the layer holds %v", layer)
|
||||
}
|
||||
if _, has := f.Machines[0].Settings[0].Values["media-gid"]; has {
|
||||
t.Fatal("the snapshot given was changed")
|
||||
}
|
||||
if len(notes) != 1 || !strings.Contains(notes[0], "composed with 1 value(s) held for novox/mesh-catalog#434") ||
|
||||
!strings.Contains(notes[0], "media-gid=2000") || !strings.Contains(notes[0], "approved by the operator") ||
|
||||
strings.Contains(notes[0], "ace") {
|
||||
t.Fatalf("said %q", notes)
|
||||
}
|
||||
}
|
||||
|
||||
// 1826/AC3: a machine with no layer of the module gets one.
|
||||
func TestAHeldValueMakesTheLayerAMachineLacks(t *testing.T) {
|
||||
got, _ := layHeld(heldGateFacts(), []heldValue{{Pull: "p", Node: "g14", Module: "n8n", Key: "k", Value: []byte(`"x"`)}}, heldShelf)
|
||||
s := got.Machines[1].Settings
|
||||
if len(s) != 1 || s[0].Module != "n8n" || s[0].Values["k"] != "x" {
|
||||
t.Fatalf("layers %+v", s)
|
||||
}
|
||||
}
|
||||
|
||||
// 1826/AC3: a held value for a machine or a module the snapshot or the change does not hold is said, never laid.
|
||||
func TestAHeldValueForWhatIsNotHeldIsSaidNotLaid(t *testing.T) {
|
||||
f := heldGateFacts()
|
||||
got, notes := layHeld(f, []heldValue{
|
||||
{Pull: "p", Node: "nowhere", Module: "n8n", Key: "k", Value: []byte("1")},
|
||||
{Pull: "p", Node: "ace", Module: "ghost", Key: "k", Value: []byte("1")},
|
||||
}, heldShelf)
|
||||
if len(notes) != 2 || !strings.Contains(notes[0], "holds no machine") || !strings.Contains(notes[1], "defines no module ghost") {
|
||||
t.Fatalf("said %q", notes)
|
||||
}
|
||||
if _, has := got.Machines[0].Settings[0].Values["k"]; has {
|
||||
t.Fatal("laid")
|
||||
}
|
||||
}
|
||||
|
||||
// 1826/AC3: none held lays nothing and says nothing; the file is read and refuses a value without a node.
|
||||
func TestNoHeldValuesLayNothingAndTheFileIsRead(t *testing.T) {
|
||||
if got, notes := layHeld(heldGateFacts(), nil, heldShelf); len(notes) != 0 || len(got.Machines) != 2 {
|
||||
t.Fatalf("%v %v", got, notes)
|
||||
}
|
||||
dir := t.TempDir()
|
||||
good := filepath.Join(dir, "good.json")
|
||||
os.WriteFile(good, []byte(`[{"pull":"p","node":"ace","module":"n8n","key":"k","value":1}]`), 0o644)
|
||||
if h, err := readHeld(good); err != nil || len(h) != 1 || h[0].Key != "k" {
|
||||
t.Fatalf("%v %v", h, err)
|
||||
}
|
||||
bad := filepath.Join(dir, "bad.json")
|
||||
os.WriteFile(bad, []byte(`[{"pull":"p","module":"n8n","key":"k","value":1}]`), 0o644)
|
||||
if _, err := readHeld(bad); err == nil {
|
||||
t.Fatal("a value without a node was read")
|
||||
}
|
||||
if h, err := readHeld(""); h != nil || err != nil {
|
||||
t.Fatalf("%v %v", h, err)
|
||||
}
|
||||
}
|
||||
@@ -526,3 +526,57 @@ func TestAMemberJudgedAloneSeesAMoveThroughTheClonesBeside(t *testing.T) {
|
||||
t.Errorf("nothing beside, yet moves %v", got)
|
||||
}
|
||||
}
|
||||
|
||||
// 1826/AC3 (integration level, a throwaway store): a change whose container says ${config:media-gid} fails the gate for
|
||||
// want of the value, passes it with the value the operator approved held for its pull request, and the mesh as it is
|
||||
// composes the same either way.
|
||||
func TestAChangeNeedingAHeldValueFailsWithoutItAndPassesWithIt(t *testing.T) {
|
||||
open := aMesh(t)
|
||||
ctx := t.Context()
|
||||
trunk := `{"module":"n8n","version":"1","resources":[{"id":"server","type":"container","name":"n8n",
|
||||
"image":"n8nio/n8n@sha256:4846eb2f4b874ab04cde7fc1e249d2ddaec66e9aea64439beb2972cfea88e3c0"}]}`
|
||||
m, err := catalogue.ParseManifest([]byte(trunk))
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := open.inventory.RegisterModule(ctx, m, inventory.Source{Repository: "novox/mesh-catalog",
|
||||
Path: "modules/n8n", BuiltFrom: "c0ffee"}); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if _, err := assign(ctx, open, "laptop", "n8n"); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
f, err := gatherFacts(ctx, open, "2.11.17")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
for i := range f.Machines {
|
||||
f.Machines[i].Capabilities = append(f.Machines[i].Capabilities, snapshot.Capability{Name: "container-groups", Present: true})
|
||||
}
|
||||
tree := aTree(t, map[string]string{"n8n": n8nWithAGroup})
|
||||
judge := func(held []heldValue) mergeVerdict {
|
||||
v, err := judgeChange(t.Context(), mergeCheckInput{facts: f, admin: os.Getenv("MESH_TEST_POSTGRES"),
|
||||
repository: "novox/mesh-catalog", tree: tree, changed: []string{"modules/n8n/module.json"}, held: held})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
return v
|
||||
}
|
||||
without := judge(nil)
|
||||
if without.Verdict != "fail" || !strings.Contains(without.Report(), "media-gid") {
|
||||
t.Fatalf("a required value nothing sets passed, or failed for another reason:\n%s", without.Report())
|
||||
}
|
||||
with := judge([]heldValue{{Pull: "novox/mesh-catalog#434", Node: "laptop", Module: "n8n", Key: "media-gid",
|
||||
Value: []byte("2000"), Approved: "the operator"}})
|
||||
if with.Verdict == "fail" || with.Verdict == "error" {
|
||||
t.Fatalf("the held value did not make it compose:\n%s", with.Report())
|
||||
}
|
||||
if !strings.Contains(with.Report(), "composed with 1 value(s) held for novox/mesh-catalog#434") {
|
||||
t.Fatalf("the value laid is not said:\n%s", with.Report())
|
||||
}
|
||||
for i := range with.Machines {
|
||||
if with.Machines[i].Base.Composes != without.Machines[i].Base.Composes {
|
||||
t.Fatalf("the mesh as it is composes differently with a held value: %+v / %+v", with.Machines[i].Base, without.Machines[i].Base)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -457,6 +457,18 @@ var plainWordings = map[string]func(conditions.Observation) words{
|
||||
Explanation: "A delivery did not finish. Nothing is tried again until you say so.",
|
||||
Resolved: "Resolved: the delivery is no longer failed"}
|
||||
}),
|
||||
kindMovesHeld: worded(func(o conditions.Observation) words {
|
||||
return words{Headline: "An update waits for you",
|
||||
Explanation: "A new version of a module would restart a container or touch its data, so it waits for you.",
|
||||
Resolved: "Resolved: the update is no longer waiting"}
|
||||
}),
|
||||
kindImageMissing: worded(func(o conditions.Observation) words {
|
||||
return words{Headline: "A module is not updated",
|
||||
Explanation: "The new version of a module names a container image that the mesh's store does not hold, so it " +
|
||||
"was not sent. What runs is untouched.",
|
||||
Needs: "build the module again; the details name the image.",
|
||||
Resolved: "Resolved: the store holds the image again"}
|
||||
}),
|
||||
"ask-lost": worded(func(o conditions.Observation) words {
|
||||
return words{Headline: "A build has no result",
|
||||
Explanation: "A build was asked for and never answered. It is asked again with the next delivery.",
|
||||
|
||||
@@ -260,7 +260,7 @@ func TestUpdatesHeldNameWhatWaitsAndWhereItIsReleased(t *testing.T) {
|
||||
plainExample(t, got[0], "Updates of openrazer and sensors wait for your release",
|
||||
"Needs you: release them from the mesh MCP server; this notification cannot do it. Updates of openrazer and "+
|
||||
"sensors on g14 and shanks wait for a person to release them, because the last walk failed. "+
|
||||
"They are not delivered until then, and stay held if you leave them.")
|
||||
"They are not delivered until then, and stay held if you leave them.", "Release")
|
||||
}
|
||||
|
||||
// **What held them is said in the glossary's words** (2026-10-08 review): the backlog is held after any
|
||||
|
||||
@@ -31,7 +31,8 @@ func TestNoPlanIsWrittenButThroughSavePlansMoving(t *testing.T) {
|
||||
return err
|
||||
}
|
||||
text := string(raw)
|
||||
if write.MatchString(text) {
|
||||
// The regular expression is the costly part of reading every source: only a file that names the table can match.
|
||||
if strings.Contains(strings.ToLower(text), "release_plan") && write.MatchString(text) {
|
||||
found = append(found, path+" writes the plan table")
|
||||
}
|
||||
// A plan record is written by the bucket's raw create and update, which only the plans' own file calls.
|
||||
|
||||
@@ -52,7 +52,7 @@ func TestASharedRepositoryIsPlannedFromTheRecordedBuildSources(t *testing.T) {
|
||||
{Repository: "novox/mesh-controller", Ref: "main", Paths: append([]string{"cmd/mesh-builder/", "internal/broker/"}, gomod...)}}
|
||||
sourcesOf["route-proxy"] = []inventory.BuildSource{
|
||||
{Paths: []string{"modules/route-proxy/Dockerfile", "modules/route-proxy/module.json"}},
|
||||
{Repository: "novox/mesh-controller", Ref: "main", Paths: append([]string{"examples/route-proxy/", "internal/broker/"}, gomod...)}}
|
||||
{Repository: "novox/mesh-controller", Ref: "main", Paths: append([]string{"modules/route-proxy/cmd/route-proxy/", "internal/broker/"}, gomod...)}}
|
||||
register(catalogue.Manifest{Module: "mesh-controller", Version: "1"}, "novox/mesh-controller", "", nil, nil)
|
||||
register(agent, "novox/mesh-catalog", "modules/build-agent", nil, controllerRead)
|
||||
register(catalogue.Manifest{Module: "route-proxy", Version: "1"}, "novox/mesh-catalog", "modules/route-proxy", nil, controllerRead)
|
||||
@@ -133,7 +133,7 @@ func TestASharedRepositoryIsPlannedFromTheRecordedBuildSources(t *testing.T) {
|
||||
{"a package only the controller builds from: the controller alone", "mesh-controller",
|
||||
[]string{"internal/conditions/condition.go"}, "mesh-controller", true},
|
||||
{"the route proxy's program: the route proxy alone", "mesh-controller",
|
||||
[]string{"examples/route-proxy/main.go"}, "route-proxy", true},
|
||||
[]string{"modules/route-proxy/cmd/route-proxy/main.go"}, "route-proxy", true},
|
||||
{"a package all three build from: all three", "mesh-controller",
|
||||
[]string{"internal/broker/broker.go"}, "mesh-controller,route-proxy | build-agent", false},
|
||||
{"the route proxy's directory in the catalogue: it alone", "mesh-catalog",
|
||||
|
||||
@@ -259,7 +259,7 @@ func TestASharedRepositoryMovesOnlyWhatItsBuildSourceHolds(t *testing.T) {
|
||||
{Own: true, Paths: []string{"modules/build-agent/Dockerfile", "modules/build-agent/module.json"}},
|
||||
},
|
||||
"route-proxy": {
|
||||
{Repository: "novox/mesh-controller", Ref: "main", Paths: with("examples/route-proxy/", "internal/broker/",
|
||||
{Repository: "novox/mesh-controller", Ref: "main", Paths: with("modules/route-proxy/cmd/route-proxy/", "internal/broker/",
|
||||
"vendor/github.com/nats-io/nats.go/")},
|
||||
{Own: true, Paths: []string{"modules/route-proxy/Dockerfile", "modules/route-proxy/module.json"}},
|
||||
},
|
||||
@@ -288,7 +288,7 @@ func TestASharedRepositoryMovesOnlyWhatItsBuildSourceHolds(t *testing.T) {
|
||||
{"a README of the controller's repository: no module (338)", "mesh-controller",
|
||||
[]string{"README.md"}, read, "", "README.md"},
|
||||
{"the route proxy's program alone: the route proxy alone (338)", "mesh-controller",
|
||||
[]string{"examples/route-proxy/main.go"}, read, "route-proxy", ""},
|
||||
[]string{"modules/route-proxy/cmd/route-proxy/main.go"}, read, "route-proxy", ""},
|
||||
{"the build seat's program alone: its holder alone", "mesh-controller",
|
||||
[]string{"cmd/mesh-builder/main.go"}, read, "build-agent", ""},
|
||||
{"a package the build seat's program and the controller build from: both", "mesh-controller",
|
||||
@@ -305,7 +305,7 @@ func TestASharedRepositoryMovesOnlyWhatItsBuildSourceHolds(t *testing.T) {
|
||||
{"go.sum: all three", "mesh-controller",
|
||||
[]string{"go.sum"}, read, "mesh-controller,route-proxy | build-agent", ""},
|
||||
{"a file added to the proxy's package: the proxy", "mesh-controller",
|
||||
[]string{"examples/route-proxy/new.go"}, read, "route-proxy", ""},
|
||||
[]string{"modules/route-proxy/cmd/route-proxy/new.go"}, read, "route-proxy", ""},
|
||||
// Before any build source is said: as before.
|
||||
{"no build source said: a README moves all three, as before", "mesh-controller",
|
||||
[]string{"README.md"}, unsaid, "mesh-controller,route-proxy | build-agent", ""},
|
||||
@@ -345,7 +345,7 @@ func TestAModuleAPlanOvertookIsReadWhole(t *testing.T) {
|
||||
built := time.Date(2026, 10, 10, 1, 0, 0, 0, time.UTC)
|
||||
read := map[string][]inventory.ReadRepository{
|
||||
"route-proxy": {
|
||||
{Repository: "novox/mesh-controller", Ref: "main", Paths: []string{"examples/route-proxy/", "go.mod"}, Built: built},
|
||||
{Repository: "novox/mesh-controller", Ref: "main", Paths: []string{"modules/route-proxy/cmd/route-proxy/", "go.mod"}, Built: built},
|
||||
{Own: true, Paths: []string{"modules/route-proxy/module.json"}, Built: built},
|
||||
},
|
||||
"mesh-controller": {{Own: true, Paths: []string{"module.json", "cmd/mesh-controller/"}, Built: built}},
|
||||
@@ -396,11 +396,11 @@ func TestAMissedMergeMovingOnlyAPackagingModuleIsActedOnOnce(t *testing.T) {
|
||||
}
|
||||
read := map[string][]inventory.ReadRepository{
|
||||
"mesh-controller": {{Own: true, Paths: []string{"module.json", "cmd/mesh-controller/"}, Built: merged.Add(-time.Hour)}},
|
||||
"route-proxy": {{Repository: "novox/mesh-controller", Ref: "main", Paths: []string{"examples/route-proxy/"},
|
||||
"route-proxy": {{Repository: "novox/mesh-controller", Ref: "main", Paths: []string{"modules/route-proxy/cmd/route-proxy/"},
|
||||
Built: merged.Add(-time.Hour), Looked: merged.Add(-time.Hour)}},
|
||||
}
|
||||
m := link.SourceMoved{Owner: "novox", Repo: "mesh-controller", Base: "main", Commit: "c1",
|
||||
MergedAt: merged.Format(time.RFC3339), Paths: []string{"examples/route-proxy/main.go"}}
|
||||
MergedAt: merged.Format(time.RFC3339), Paths: []string{"modules/route-proxy/cmd/route-proxy/main.go"}}
|
||||
if got := wouldMove(m, entries, planningView(read, nil)); len(got) != 1 || got[0].Manifest.Module != "route-proxy" {
|
||||
t.Fatalf("a missed merge of the proxy's program would move %v", got)
|
||||
}
|
||||
@@ -599,14 +599,14 @@ func TestTheGatePlansFromTheBuildSourcesTheSnapshotCarries(t *testing.T) {
|
||||
Sources: []snapshot.BuildSource{{Own: true, Paths: []string{"module.json", "cmd/mesh-controller/", "internal/broker/"}}}},
|
||||
{Name: "route-proxy", Repository: "novox/mesh-catalog", Path: "modules/route-proxy", Manifest: manifest("route-proxy"),
|
||||
Reads: []string{"novox/mesh-controller"},
|
||||
Sources: []snapshot.BuildSource{{Repository: "novox/mesh-controller", Paths: []string{"examples/route-proxy/", "internal/broker/"}},
|
||||
Sources: []snapshot.BuildSource{{Repository: "novox/mesh-controller", Paths: []string{"modules/route-proxy/cmd/route-proxy/", "internal/broker/"}},
|
||||
{Own: true, Paths: []string{"modules/route-proxy/module.json"}}}},
|
||||
}}
|
||||
for paths, want := range map[string]string{
|
||||
"cmd/mesh-controller/main.go": "mesh-controller",
|
||||
"examples/route-proxy/main.go": "route-proxy",
|
||||
"internal/broker/broker.go": "mesh-controller,route-proxy",
|
||||
"README.md": "",
|
||||
"cmd/mesh-controller/main.go": "mesh-controller",
|
||||
"modules/route-proxy/cmd/route-proxy/main.go": "route-proxy",
|
||||
"internal/broker/broker.go": "mesh-controller,route-proxy",
|
||||
"README.md": "",
|
||||
} {
|
||||
r, err := reachOfChange(facts, "novox/mesh-controller", []string{paths}, "")
|
||||
if err != nil {
|
||||
|
||||
@@ -153,7 +153,7 @@ func planWaitCommand(ctx context.Context, inv *inventory.Inventory, id, untilAsk
|
||||
line := planLineSaid(p, now, pause, bounds.of(p.Repository), func(module string) []string {
|
||||
on, _ := inv.Running(ctx, module)
|
||||
return on
|
||||
}, waitsOf(ctx, inv, one))
|
||||
}, waitsOf(ctx, inv, one)) + heldSaid(p, heldNow(ctx, inv))
|
||||
doc := planWaitedDoc(p, planStatuses(one, now, pause, bounds)[0], until, came, now.Sub(began), line)
|
||||
return json.NewEncoder(os.Stdout).Encode(doc)
|
||||
}
|
||||
|
||||
@@ -0,0 +1,211 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"io"
|
||||
"path"
|
||||
"reflect"
|
||||
"slices"
|
||||
"time"
|
||||
|
||||
"github.com/nats-io/nats.go"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/broker"
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
"github.com/novox/mesh-controller/internal/link"
|
||||
)
|
||||
|
||||
// What the controller tells mesh-config of an open pull request, and asks it back (novox/hq ADR 0502 clauses 2 and 4,
|
||||
// issue 1826): a config key a pull request introduces is not declared on the trunk, so a value for it can be judged
|
||||
// only against the pull request's own declaration, which the core reads from the forge and mesh-config never does
|
||||
// (ADR 0495 §1). The call is mesh-config's `config` verb in the controller's own name, actions `pull-declares` and
|
||||
// `held`; the shapes are those of the interface the two sides agreed.
|
||||
|
||||
// meshConfigWait is how long the controller waits for mesh-config before it goes on without: a check is never held up
|
||||
// by a module that does not answer.
|
||||
const meshConfigWait = 10 * time.Second
|
||||
|
||||
// meshConfigAsk is one call of mesh-config's `config` verb in the controller's own name, answering its result. A
|
||||
// variable so a test needs no bus.
|
||||
var meshConfigAsk = func(ctx context.Context, args map[string]any) ([]byte, error) {
|
||||
var result []byte
|
||||
err := onTheBus(func(conn *nats.Conn) error {
|
||||
answer, err := link.AskMeshSeatToolAs(ctx, conn, broker.ControllerName, "mesh-config", "config", args, meshConfigWait)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
if answer.Error != "" {
|
||||
return fmt.Errorf("%s", answer.Error)
|
||||
}
|
||||
result = answer.Result
|
||||
return nil
|
||||
})
|
||||
return result, err
|
||||
}
|
||||
|
||||
// pullAt is an open pull request at a head: the change to read, and its number.
|
||||
type pullAt struct {
|
||||
changeSource
|
||||
Number int
|
||||
}
|
||||
|
||||
// pullAtOf is a pull request announced, as the change it makes over what it merges into.
|
||||
func pullAtOf(p link.PullUpdated) pullAt {
|
||||
old := p.BaseSHA
|
||||
if old == "" {
|
||||
old = p.Base
|
||||
}
|
||||
return pullAt{Number: p.Number, changeSource: changeSource{Owner: p.Owner, Repo: p.Repo, New: p.Commit, Old: old,
|
||||
Paths: p.Paths, Truncated: p.PathsTruncated, Removed: p.Removed}}
|
||||
}
|
||||
|
||||
func pullKey(owner, repo string, number int) string {
|
||||
return fmt.Sprintf("%s/%s#%d", owner, repo, number)
|
||||
}
|
||||
|
||||
func (p pullAt) key() string { return pullKey(p.Owner, p.Repo, p.Number) }
|
||||
|
||||
// pullDeclarations are the config declarations a pull request's head adds or changes over what it merges into, by
|
||||
// module, in the shape of the declared-config mirror. The bool says the head could be read: false for a pull request whose
|
||||
// paths are cut (the caller cuts them to the manifests of the modules it moves) or whose base is unknown, which is then
|
||||
// told nothing, never an empty set.
|
||||
func pullDeclarations(ctx context.Context, p pullAt) ([]inventory.DeclaredConfigMirrored, bool, error) {
|
||||
var out []inventory.DeclaredConfigMirrored
|
||||
if p.Truncated || p.Old == "" {
|
||||
return nil, false, nil
|
||||
}
|
||||
for _, file := range p.Paths {
|
||||
if path.Base(file) != moduleManifestFile || slices.Contains(p.Removed, file) {
|
||||
continue
|
||||
}
|
||||
now, exists, err := manifestCached(ctx, p.Owner, p.Repo, file, p.New)
|
||||
if err != nil {
|
||||
return nil, false, err
|
||||
}
|
||||
if !exists || now.Module == "" {
|
||||
continue
|
||||
}
|
||||
was, _, err := manifestCached(ctx, p.Owner, p.Repo, file, p.Old)
|
||||
if err != nil {
|
||||
return nil, false, err
|
||||
}
|
||||
have, err := inventory.DeclaredOf(now.Settings)
|
||||
if err != nil {
|
||||
return nil, false, fmt.Errorf("%s at %.8s: %w", file, p.New, err)
|
||||
}
|
||||
had, err := inventory.DeclaredOf(was.Settings)
|
||||
if err != nil {
|
||||
return nil, false, fmt.Errorf("%s at %.8s: %w", file, p.Old, err)
|
||||
}
|
||||
changed := map[string]inventory.DeclaredMirrored{}
|
||||
for key, d := range have {
|
||||
if before, there := had[key]; !there || !reflect.DeepEqual(before, d) {
|
||||
changed[key] = d
|
||||
}
|
||||
}
|
||||
if len(changed) > 0 {
|
||||
out = append(out, inventory.DeclaredConfigMirrored{Module: now.Module, Settings: changed})
|
||||
}
|
||||
}
|
||||
return out, true, nil
|
||||
}
|
||||
|
||||
// tellPullDeclares tells mesh-config, for each pull request at every announced head, what the head declares, an empty set
|
||||
// when it declares nothing new: mesh-config re-judges the values held at every head, so a head that reverts the change
|
||||
// drops them (ADR 0502 clause 6). A
|
||||
// failure is said to w and the check goes on: the held values are then none (ADR 0502 clause 2).
|
||||
func tellPullDeclares(ctx context.Context, w io.Writer, pulls []pullAt) {
|
||||
for _, p := range pulls {
|
||||
mods, readable, err := pullDeclarations(ctx, p)
|
||||
if err != nil {
|
||||
fmt.Fprintf(w, "%s: what its head declares cannot be read, so mesh-config is told nothing: %v\n", p.key(), err)
|
||||
continue
|
||||
}
|
||||
if !readable {
|
||||
continue
|
||||
}
|
||||
declares := map[string]map[string]inventory.DeclaredMirrored{}
|
||||
for _, m := range mods {
|
||||
declares[m.Module] = m.Settings
|
||||
}
|
||||
if _, err := meshConfigAsk(ctx, map[string]any{"action": "pull-declares", "pull": p.key(), "head": p.New,
|
||||
"declares": declares}); err != nil {
|
||||
fmt.Fprintf(w, "%s: mesh-config cannot be told what its head declares (%v); the check goes on without held values\n",
|
||||
p.key(), err)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// heldFor asks mesh-config for the approved held values of these pull requests at their heads (ADR 0502 clause 4). Only
|
||||
// those of the pull requests asked about are carried. A failure is said to w and answers none.
|
||||
func heldFor(ctx context.Context, w io.Writer, pulls []pullAt) []link.HeldConfig {
|
||||
if len(pulls) == 0 {
|
||||
return nil
|
||||
}
|
||||
type pullHead struct {
|
||||
Pull string `json:"pull"`
|
||||
Head string `json:"head"`
|
||||
}
|
||||
asked := make([]pullHead, 0, len(pulls))
|
||||
for _, p := range pulls {
|
||||
asked = append(asked, pullHead{p.key(), p.New})
|
||||
}
|
||||
raw, err := meshConfigAsk(ctx, map[string]any{"action": "held", "pulls": asked})
|
||||
if err != nil {
|
||||
fmt.Fprintf(w, "mesh-config cannot say what it holds for these pull requests (%v); the check goes on without held values\n", err)
|
||||
return nil // empty-on-error: said above; a check without held values fails for want of the value and says so, it never passes on a guess
|
||||
}
|
||||
var answer struct {
|
||||
Held []link.HeldConfig `json:"held"`
|
||||
Skipped []struct {
|
||||
Pull string `json:"pull"`
|
||||
Why string `json:"why"`
|
||||
} `json:"skipped"`
|
||||
}
|
||||
if len(raw) == 0 {
|
||||
return nil
|
||||
}
|
||||
if err := json.Unmarshal(raw, &answer); err != nil {
|
||||
fmt.Fprintf(w, "mesh-config's held values cannot be read (%v); the check goes on without them\n", err)
|
||||
return nil // empty-on-error: said above; a check without held values fails for want of the value and says so, it never passes on a guess
|
||||
}
|
||||
for _, s := range answer.Skipped {
|
||||
fmt.Fprintf(w, "%s: mesh-config holds a value it does not carry: %s\n", s.Pull, s.Why)
|
||||
}
|
||||
var out []link.HeldConfig
|
||||
for _, h := range answer.Held {
|
||||
for _, p := range pulls {
|
||||
if h.Pull == p.key() {
|
||||
out = append(out, h)
|
||||
break
|
||||
}
|
||||
}
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// withHeldConfig tells mesh-config what these pull requests declare and puts the approved held values of them on the
|
||||
// check request (ADR 0502 clause 4). With carry false, a member of a group whose composed check composes, only the
|
||||
// declarations are told.
|
||||
func withHeldConfig(ctx context.Context, w io.Writer, request *link.BuildRequest, pulls []pullAt, carry bool) {
|
||||
tellPullDeclares(ctx, w, pulls)
|
||||
if carry {
|
||||
carryHeld(ctx, w, request, pulls)
|
||||
}
|
||||
}
|
||||
|
||||
// carryHeld puts the approved held values of these pull requests on the check request.
|
||||
func carryHeld(ctx context.Context, w io.Writer, request *link.BuildRequest, pulls []pullAt) {
|
||||
if request.Check != nil {
|
||||
request.Check.HeldConfig = heldFor(ctx, w, pulls)
|
||||
}
|
||||
}
|
||||
|
||||
// holdsModules is whether a module of the mesh is built from this repository.
|
||||
func holdsModules(entries []inventory.Entry, owner, repo string) bool {
|
||||
return slices.ContainsFunc(entries, func(e inventory.Entry) bool {
|
||||
return sameRepository(e.Source.Repository, link.SourceMoved{Owner: owner, Repo: repo})
|
||||
})
|
||||
}
|
||||
@@ -0,0 +1,209 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"io"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"git.novox.be/novox/mesh-sdk/go/catalogue"
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
"github.com/novox/mesh-controller/internal/link"
|
||||
)
|
||||
|
||||
const (
|
||||
headSHA = "2222222222222222222222222222222222222222"
|
||||
baseSHA = "1111111111111111111111111111111111111111"
|
||||
)
|
||||
|
||||
// fakeManifests serves manifests by ref, and counts what the forge was asked. Issue 1826/AC1 (unit level).
|
||||
func fakeManifests(t *testing.T, at map[string]*catalogue.Manifest) {
|
||||
t.Helper()
|
||||
was := manifestAt
|
||||
t.Cleanup(func() { manifestAt = was })
|
||||
manifestsReadMu.Lock()
|
||||
clear(manifestsRead)
|
||||
manifestsReadMu.Unlock()
|
||||
manifestAt = func(_ context.Context, _, _, _, ref string) (catalogue.Manifest, bool, error) {
|
||||
if m := at[ref]; m != nil {
|
||||
return *m, true, nil
|
||||
}
|
||||
return catalogue.Manifest{}, false, nil
|
||||
}
|
||||
}
|
||||
|
||||
// fakeConfig records the calls to mesh-config and answers each action from answers.
|
||||
func fakeConfig(t *testing.T, answers map[string]string) *[]map[string]any {
|
||||
t.Helper()
|
||||
var calls []map[string]any
|
||||
was := meshConfigAsk
|
||||
t.Cleanup(func() { meshConfigAsk = was })
|
||||
meshConfigAsk = func(_ context.Context, args map[string]any) ([]byte, error) {
|
||||
calls = append(calls, args)
|
||||
return []byte(answers[args["action"].(string)]), nil
|
||||
}
|
||||
return &calls
|
||||
}
|
||||
|
||||
func manifest(module string, keys map[string]catalogue.SettingDeclaration) *catalogue.Manifest {
|
||||
return &catalogue.Manifest{Module: module, Settings: keys}
|
||||
}
|
||||
|
||||
func thePull() pullAt {
|
||||
return pullAt{Number: 434, changeSource: changeSource{Owner: "novox", Repo: "mesh-catalog", New: headSHA, Old: baseSHA,
|
||||
Paths: []string{"modules/n8n/module.json", "modules/n8n/README.md"}}}
|
||||
}
|
||||
|
||||
// 1826/AC1: a key the head adds is sent with its declaration, under the pull request and the head.
|
||||
func TestAKeyThePullRequestAddsIsToldToMeshConfig(t *testing.T) {
|
||||
fakeManifests(t, map[string]*catalogue.Manifest{
|
||||
baseSHA: manifest("n8n", map[string]catalogue.SettingDeclaration{"port": {Type: "number"}}),
|
||||
headSHA: manifest("n8n", map[string]catalogue.SettingDeclaration{"port": {Type: "number"},
|
||||
"media-gid": {Type: "number", Required: true}}),
|
||||
})
|
||||
calls := fakeConfig(t, map[string]string{"pull-declares": `{"kept":1}`})
|
||||
tellPullDeclares(context.Background(), io.Discard, []pullAt{thePull()})
|
||||
if len(*calls) != 1 {
|
||||
t.Fatalf("mesh-config was asked %d times: %v", len(*calls), *calls)
|
||||
}
|
||||
c := (*calls)[0]
|
||||
if c["action"] != "pull-declares" || c["pull"] != "novox/mesh-catalog#434" || c["head"] != headSHA {
|
||||
t.Fatalf("the call is %v", c)
|
||||
}
|
||||
body, _ := json.Marshal(c["declares"])
|
||||
var declares map[string]map[string]inventory.DeclaredMirrored
|
||||
if err := json.Unmarshal(body, &declares); err != nil || len(declares) != 1 || declares["n8n"] == nil {
|
||||
t.Fatalf("declares %s: %v", body, err)
|
||||
}
|
||||
mods := []inventory.DeclaredConfigMirrored{{Module: "n8n", Settings: declares["n8n"]}}
|
||||
if _, has := mods[0].Settings["port"]; has || len(mods[0].Settings) != 1 {
|
||||
t.Fatalf("only the added key is told, got %v", mods[0].Settings)
|
||||
}
|
||||
d := mods[0].Settings["media-gid"]
|
||||
if d.Type != "number" || !d.Required {
|
||||
t.Fatalf("the declaration is %+v", d)
|
||||
}
|
||||
}
|
||||
|
||||
// 1826/AC1: a key whose declaration the head changes is sent; one it leaves as it was is not.
|
||||
func TestAnUnchangedKeyIsNotToldAndAChangedOneIs(t *testing.T) {
|
||||
fakeManifests(t, map[string]*catalogue.Manifest{
|
||||
baseSHA: manifest("n8n", map[string]catalogue.SettingDeclaration{"port": {Type: "number"}, "x": {Type: "string"}}),
|
||||
headSHA: manifest("n8n", map[string]catalogue.SettingDeclaration{"port": {Type: "number"}, "x": {Type: "string", Pattern: "a+"}}),
|
||||
})
|
||||
mods, touched, err := pullDeclarations(context.Background(), thePull())
|
||||
if err != nil || !touched || len(mods) != 1 || len(mods[0].Settings) != 1 || mods[0].Settings["x"].Pattern != "a+" {
|
||||
t.Fatalf("%+v %v %v", mods, touched, err)
|
||||
}
|
||||
}
|
||||
|
||||
// 1826/AC1: a head that changes no module.json, or removes it, is still told, with declares {}: mesh-config re-judges at every
|
||||
// head, so a head that reverts the change drops the value held for it (review round 1, finding 1).
|
||||
func TestAHeadThatDeclaresNothingIsToldAsEmpty(t *testing.T) {
|
||||
fakeManifests(t, map[string]*catalogue.Manifest{baseSHA: manifest("n8n", nil), headSHA: manifest("n8n", nil)})
|
||||
calls := fakeConfig(t, nil)
|
||||
p := thePull()
|
||||
p.Paths = []string{"modules/n8n/README.md"}
|
||||
tellPullDeclares(context.Background(), io.Discard, []pullAt{p})
|
||||
p = thePull()
|
||||
p.Removed = p.Paths
|
||||
tellPullDeclares(context.Background(), io.Discard, []pullAt{p})
|
||||
if len(*calls) != 2 {
|
||||
t.Fatalf("mesh-config was told %v", *calls)
|
||||
}
|
||||
for _, c := range *calls {
|
||||
if d, _ := json.Marshal(c["declares"]); string(d) != "{}" || c["head"] != headSHA {
|
||||
t.Fatalf("told %v", c)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// 1826/AC1: a head whose paths are cut, or whose base is unknown, cannot be read: nothing is told, never an empty set.
|
||||
func TestAHeadThatCannotBeReadIsNotToldAsEmpty(t *testing.T) {
|
||||
calls := fakeConfig(t, nil)
|
||||
p := thePull()
|
||||
p.Truncated = true
|
||||
tellPullDeclares(context.Background(), io.Discard, []pullAt{p})
|
||||
if len(*calls) != 0 {
|
||||
t.Fatalf("told %v", *calls)
|
||||
}
|
||||
}
|
||||
|
||||
// 1826/AC1: a module.json changed without a declaration changing is told as an empty set, so mesh-config re-judges what it holds.
|
||||
func TestAChangedManifestWithNoNewDeclarationIsToldAsEmpty(t *testing.T) {
|
||||
m := manifest("n8n", map[string]catalogue.SettingDeclaration{"port": {Type: "number"}})
|
||||
fakeManifests(t, map[string]*catalogue.Manifest{baseSHA: m, headSHA: m})
|
||||
calls := fakeConfig(t, nil)
|
||||
tellPullDeclares(context.Background(), io.Discard, []pullAt{thePull()})
|
||||
if len(*calls) != 1 {
|
||||
t.Fatalf("calls %v", *calls)
|
||||
}
|
||||
if d, _ := json.Marshal((*calls)[0]["declares"]); string(d) != "{}" {
|
||||
t.Fatalf("declares %s", d)
|
||||
}
|
||||
}
|
||||
|
||||
// 1826/AC1: mesh-config not answering is said and goes on; the check is not stopped.
|
||||
func TestMeshConfigNotAnsweringIsSaidAndGoneOn(t *testing.T) {
|
||||
fakeManifests(t, map[string]*catalogue.Manifest{baseSHA: manifest("n8n", nil),
|
||||
headSHA: manifest("n8n", map[string]catalogue.SettingDeclaration{"k": {Type: "string"}})})
|
||||
was := meshConfigAsk
|
||||
t.Cleanup(func() { meshConfigAsk = was })
|
||||
meshConfigAsk = func(context.Context, map[string]any) ([]byte, error) { return nil, io.ErrUnexpectedEOF }
|
||||
var said strings.Builder
|
||||
tellPullDeclares(context.Background(), &said, []pullAt{thePull()})
|
||||
got := heldFor(context.Background(), &said, []pullAt{thePull()})
|
||||
if len(got) != 0 || !strings.Contains(said.String(), "mesh-config") {
|
||||
t.Fatalf("held %v, said %q", got, said.String())
|
||||
}
|
||||
}
|
||||
|
||||
// 1826/AC2: the held values mesh-config answers for the check's pull requests are what the check request carries.
|
||||
func TestTheHeldValuesOfTheChecksPullRequestsAreAsked(t *testing.T) {
|
||||
calls := fakeConfig(t, map[string]string{"held": `{"held":[{"pull":"novox/mesh-catalog#434","head":"` + headSHA +
|
||||
`","node":"ace","module":"n8n","key":"media-gid","value":2000,"approved":"the operator"}]}`})
|
||||
other := pullAt{Number: 7, changeSource: changeSource{Owner: "novox", Repo: "mesh-controller", New: baseSHA}}
|
||||
got := heldFor(context.Background(), io.Discard, []pullAt{thePull(), other})
|
||||
if len(got) != 1 || got[0].Node != "ace" || got[0].Key != "media-gid" || string(got[0].Value) != "2000" {
|
||||
t.Fatalf("got %+v", got)
|
||||
}
|
||||
c := (*calls)[0]
|
||||
pulls, _ := json.Marshal(c["pulls"])
|
||||
if c["action"] != "held" || string(pulls) != `[{"pull":"novox/mesh-catalog#434","head":"`+headSHA+
|
||||
`"},{"pull":"novox/mesh-controller#7","head":"`+baseSHA+`"}]` {
|
||||
t.Fatalf("asked %v %s", c, pulls)
|
||||
}
|
||||
}
|
||||
|
||||
// 1826/AC2: a value held for a pull request the check is not of is never carried.
|
||||
func TestAHeldValueOfAnotherPullRequestIsNotCarried(t *testing.T) {
|
||||
fakeConfig(t, map[string]string{"held": `{"held":[{"pull":"novox/mesh-catalog#999","head":"x","node":"ace","module":"n8n","key":"k","value":1}]}`})
|
||||
if got := heldFor(context.Background(), io.Discard, []pullAt{thePull()}); len(got) != 0 {
|
||||
t.Fatalf("carried %+v", got)
|
||||
}
|
||||
}
|
||||
|
||||
// 1826/AC2: the check request carries what mesh-config answered; a member of a composed group asks none.
|
||||
func TestTheCheckRequestCarriesTheHeldValues(t *testing.T) {
|
||||
fakeManifests(t, map[string]*catalogue.Manifest{baseSHA: manifest("n8n", nil), headSHA: manifest("n8n", nil)})
|
||||
fakeConfig(t, map[string]string{"held": `{"held":[{"pull":"novox/mesh-catalog#434","node":"ace","module":"n8n","key":"media-gid","value":2000}]}`})
|
||||
request := link.BuildRequest{Check: &link.CheckRequest{}}
|
||||
withHeldConfig(context.Background(), io.Discard, &request, []pullAt{thePull()}, true)
|
||||
if len(request.Check.HeldConfig) != 1 || request.Check.HeldConfig[0].Key != "media-gid" {
|
||||
t.Fatalf("the request carries %+v", request.Check.HeldConfig)
|
||||
}
|
||||
request = link.BuildRequest{Check: &link.CheckRequest{}}
|
||||
withHeldConfig(context.Background(), io.Discard, &request, []pullAt{thePull()}, false)
|
||||
if len(request.Check.HeldConfig) != 0 {
|
||||
t.Fatalf("a composed member carries %+v", request.Check.HeldConfig)
|
||||
}
|
||||
}
|
||||
|
||||
// 1826/AC1: a repository that builds a module of the mesh holds modules; another does not.
|
||||
func TestARepositoryThatBuildsAModuleHoldsModules(t *testing.T) {
|
||||
entries := []inventory.Entry{{Manifest: catalogue.Manifest{Module: "a"}, Source: inventory.Source{Repository: "novox/mesh-catalog", Path: "modules/a"}}}
|
||||
if !holdsModules(entries, "novox", "mesh-catalog") || holdsModules(entries, "novox", "hq") {
|
||||
t.Fatal("wrong")
|
||||
}
|
||||
}
|
||||
@@ -281,7 +281,7 @@ func serve(ctx context.Context) (err error) {
|
||||
// The provisioner's plan of each handed module, as its machine was last sent it (design 57 P6), in the module's
|
||||
// assignment.
|
||||
inv.SetProvisioningPlans(inv.SentProvisioningPlans)
|
||||
go mirroringRecords(ctx, inv, bus.Conn, bus)
|
||||
go mirroringRecords(ctx, open, inv, bus.Conn, bus)
|
||||
// And the bucket of the files that travel by digest, judged against what each machine's latest declaration names (ADR 0486 §3).
|
||||
go sweepingDeclarationFiles(ctx, inv, bus.Conn)
|
||||
// And the key of each plan in its build phase, which holds the build seat's checks while a delivery builds (ADR 0483 clause 2).
|
||||
|
||||
@@ -7,6 +7,7 @@ import (
|
||||
"sort"
|
||||
"time"
|
||||
|
||||
"git.novox.be/novox/mesh-sdk/go/compose"
|
||||
"github.com/nats-io/nats.go"
|
||||
"github.com/nats-io/nats.go/jetstream"
|
||||
|
||||
@@ -29,7 +30,7 @@ import (
|
||||
const mirrorEvery = 10 * time.Second
|
||||
|
||||
// mirroringRecords keeps the mirrors current for as long as this controller serves: ctx ends when it stops.
|
||||
func mirroringRecords(ctx context.Context, inv *inventory.Inventory, conn *nats.Conn, announce recordmirror.Announcer) {
|
||||
func mirroringRecords(ctx context.Context, open *stores, inv *inventory.Inventory, conn *nats.Conn, announce recordmirror.Announcer) {
|
||||
api, err := jetstream.New(conn)
|
||||
if err != nil {
|
||||
fmt.Printf("the record mirrors are not kept: %v\n", err)
|
||||
@@ -44,8 +45,9 @@ func mirroringRecords(ctx context.Context, inv *inventory.Inventory, conn *nats.
|
||||
return e
|
||||
}
|
||||
sources := map[string]func(context.Context) (map[string][]byte, error){
|
||||
recordmirror.DeclaredConfig.Name: inv.DeclaredConfigMirror,
|
||||
recordmirror.Predefined.Name: inv.PredefinedMirror,
|
||||
recordmirror.DeclaredConfig.Name: inv.DeclaredConfigMirror,
|
||||
recordmirror.Predefined.Name: inv.PredefinedMirror,
|
||||
recordmirror.DeclaredPackages.Name: declaredPackagesMirror(open),
|
||||
}
|
||||
writers := map[string]*recordmirror.Writer{}
|
||||
failing := map[string]string{}
|
||||
@@ -176,3 +178,36 @@ func keepingAssignments(ctx context.Context, inv *inventory.Inventory, announce
|
||||
}
|
||||
events.known = now
|
||||
}
|
||||
|
||||
// declaredPackagesMirror is the source of the declared-packages mirror (ADR 0507 §5): each node's composition, asked as a
|
||||
// question that makes nothing, and the packages it declares with the modules that declare them. A node whose own set does
|
||||
// not compose has no key, and any other failure to read is the pass's error, so a key is never purged for a store that
|
||||
// could not be read.
|
||||
func declaredPackagesMirror(open *stores) func(context.Context) (map[string][]byte, error) {
|
||||
return func(ctx context.Context) (map[string][]byte, error) {
|
||||
in, err := inputFor(ctx, open)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
// Which module owns each resource is carried only for a node-engine that reads it, so every node is asked as one that does.
|
||||
asked := in.Input
|
||||
asked.Nodes = append([]compose.Node(nil), in.Nodes...)
|
||||
for i := range asked.Nodes {
|
||||
asked.Nodes[i].ReadsModules = true
|
||||
}
|
||||
out := map[string][]byte{}
|
||||
for _, n := range in.sortedNodes() {
|
||||
d, _, err := compose.ComposeIn(asked, n.Name, compose.Foreseeing)
|
||||
if compose.IsUnresolvable(err) {
|
||||
continue
|
||||
}
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("the packages %s declares cannot be read: %w", n.Name, err)
|
||||
}
|
||||
if out[n.Name], err = inventory.DeclaredPackagesValue(n.Name, d.Resources, d.ModuleOf); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
}
|
||||
return out, nil
|
||||
}
|
||||
}
|
||||
|
||||
@@ -181,15 +181,24 @@ func planModuleNames(p inventory.Plan) map[string]string {
|
||||
return out
|
||||
}
|
||||
|
||||
// recordedWaiting is, on one machine, every move of a recorded module that waits for a person, each said with why
|
||||
// (ADR 0377 §6): what `status` names the machine behind for, with `push <node>` as the remedy. A move under a
|
||||
// module's own `record` that recreates nothing and moves no data is not among them: it goes with its walk.
|
||||
func recordedWaiting(ctx context.Context, inv *inventory.Inventory, f moveFacts, node string) ([]string, error) {
|
||||
// heldMove is one move of a recorded module that waits for a person on one machine (ADR 0377 §6).
|
||||
type heldMove struct {
|
||||
Module string
|
||||
From, To string
|
||||
// Why is the walk's own word for it: "waits: " and the recreate words, the data change, or the hold.
|
||||
Why string
|
||||
// Chosen is whether a person's own choice holds it — a module they set to record, or the bus's step — which the
|
||||
// operator is not asked about again: they chose that hold, and the bus has its own condition (S17).
|
||||
Chosen bool
|
||||
}
|
||||
|
||||
// heldMovesOn is, on one machine, every move of a recorded module that waits for a person, in module order.
|
||||
func heldMovesOn(ctx context.Context, inv *inventory.Inventory, f moveFacts, node string) ([]heldMove, error) {
|
||||
sent, known, err := inv.SentBuilds(ctx, node)
|
||||
if err != nil || !known {
|
||||
return nil, err
|
||||
}
|
||||
var out []string
|
||||
var out []heldMove
|
||||
for _, m := range sortedKeysOf(sent) {
|
||||
was := sent[m]
|
||||
now, held := f.current[m]
|
||||
@@ -197,12 +206,25 @@ func recordedWaiting(ctx context.Context, inv *inventory.Inventory, f moveFacts,
|
||||
continue
|
||||
}
|
||||
if v := f.recordedMove(m, was); !v.rolls {
|
||||
out = append(out, fmt.Sprintf("%s %s → %s %s", m, short(was), short(now.Commit), v.said))
|
||||
out = append(out, heldMove{Module: m, From: was, To: now.Commit, Why: v.said,
|
||||
Chosen: now.From == catalogue.FromPerson || now.From == catalogue.FromBus})
|
||||
}
|
||||
}
|
||||
return out, nil
|
||||
}
|
||||
|
||||
// recordedWaiting is, on one machine, every move of a recorded module that waits for a person, each said with why
|
||||
// (ADR 0377 §6): what `status` names the machine behind for, with `push <node>` as the remedy. A move under a
|
||||
// module's own `record` that recreates nothing and moves no data is not among them: it goes with its walk.
|
||||
func recordedWaiting(ctx context.Context, inv *inventory.Inventory, f moveFacts, node string) ([]string, error) {
|
||||
moves, err := heldMovesOn(ctx, inv, f, node)
|
||||
var out []string
|
||||
for _, h := range moves {
|
||||
out = append(out, fmt.Sprintf("%s %s → %s %s", h.Module, short(h.From), short(h.To), h.Why))
|
||||
}
|
||||
return out, err
|
||||
}
|
||||
|
||||
// stringsKeys is a map of lists as a map of its keys, for sortedKeysOf.
|
||||
func stringsKeys(m map[string][]string) map[string]string {
|
||||
out := map[string]string{}
|
||||
|
||||
@@ -1371,6 +1371,10 @@ func backlogObservation() []conditions.Observation {
|
||||
"them, `upgrade release-backlog --why …` releases them", n, strings.Join(machines, ", "), backlogNow.held)}
|
||||
w := releaseHeldWords(modules, machines)
|
||||
o.Headline, o.Explanation, o.Resolved, o.Needs = w.Headline, w.Explanation, w.Resolved, w.Needs
|
||||
// Asked of the operator, who releases them with an Approve (novox/hq issue 1732): the controller's own
|
||||
// `upgrade release-backlog`, which opens the release plan that walks them through the machines, each judged.
|
||||
o.Actions = []conditions.Action{{Label: "Release", Verb: "mesh-controller.upgrade", Level: conditions.LevelApprove,
|
||||
Arguments: map[string]string{"release-backlog": "true", "why": "", "cause": conditions.CauseOperatorAnswer}}}
|
||||
return []conditions.Observation{o}
|
||||
}
|
||||
|
||||
|
||||
@@ -2064,6 +2064,12 @@ func planLineSaid(p inventory.Plan, now time.Time, pause pauseView, bound time.D
|
||||
// refused ("a build waits there for its gate: <machine> (...)") is kept there. "building" with LATE
|
||||
// hid that reason from `plans`, `status` and the stalled condition (novox/hq issue 920).
|
||||
what = p.Note
|
||||
// And when the builds are held after a failed release, they wait for a person, not for a build, and the
|
||||
// operator is asked to release them (novox/hq issue 1732): said so, and not late.
|
||||
if strings.Contains(p.Note, errUngated.Error()) && backlogNow.held != "" {
|
||||
what += " — held after a failed delivery until a person releases it (the operator is asked)"
|
||||
late = ""
|
||||
}
|
||||
return fmt.Sprintf("%s · %s, held: %s, for %s%s", name, where, what, since, late)
|
||||
}
|
||||
return fmt.Sprintf("%s · %s, %s for %s%s", name, where, what, since, late)
|
||||
@@ -2271,7 +2277,7 @@ func plansCommand(ctx context.Context, args []string) error {
|
||||
bounds.of(p.Repository), func(module string) []string {
|
||||
on, _ := inv.Running(ctx, module)
|
||||
return on
|
||||
}, waitsOf(ctx, inv, []inventory.Plan{p})))
|
||||
}, waitsOf(ctx, inv, []inventory.Plan{p}))+heldSaid(p, heldNow(ctx, inv)))
|
||||
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, ", "),
|
||||
@@ -2466,11 +2472,12 @@ func plansCommand(ctx context.Context, args []string) error {
|
||||
return on
|
||||
}
|
||||
waits := waitsOf(ctx, inv, plans)
|
||||
held := heldNow(ctx, inv)
|
||||
for _, p := range plans {
|
||||
if p.Batch() {
|
||||
continue
|
||||
}
|
||||
fmt.Printf("%-28s %s\n", p.ID, planLineSaid(p, now, pause, bounds.of(p.Repository), running, waits))
|
||||
fmt.Printf("%-28s %s%s\n", p.ID, planLineSaid(p, now, pause, bounds.of(p.Repository), running, waits), heldSaid(p, held))
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
@@ -152,7 +152,7 @@ func answersRightly(q dnsmessage.Question) *dnsmessage.Message {
|
||||
func quickResolvers(t *testing.T, port string) {
|
||||
t.Helper()
|
||||
before, within, pause := resolverPort, resolverWithin, resolverPause
|
||||
resolverPort, resolverWithin, resolverPause = port, 150*time.Millisecond, 10*time.Millisecond
|
||||
resolverPort, resolverWithin, resolverPause = port, 60*time.Millisecond, 5*time.Millisecond
|
||||
t.Cleanup(func() { resolverPort, resolverWithin, resolverPause = before, within, pause })
|
||||
}
|
||||
|
||||
|
||||
@@ -244,6 +244,22 @@ var signalsTable = []signalRow{
|
||||
newest: func(f *signalFacts) time.Time {
|
||||
return newestOf(f.failed, func(p failedPlanFacts) time.Time { return p.since })
|
||||
}},
|
||||
{Row: "S24", Signal: "a move of a recorded module that waits for a person's push is asked of the operator",
|
||||
Emitter: "controller's plan", Trigger: "each machine with a move of a recorded module held for a person (novox/hq ADR 0377, issue 1732)",
|
||||
Bound: "none: raised on the first look that finds the machine holding such a move, naming the modules and the " +
|
||||
"machine, with Release (the machine's push) as the answer; ended when the machine no longer waits, whoever " +
|
||||
"pushed it. A hold a person chose (a module set to record with a why, the bus) is not asked.",
|
||||
Kind: kindMovesHeld, Severity: conditions.Warning, Phase: 3,
|
||||
needs: func(f *signalFacts) error { return f.heldErr }, watch: watchMovesHeld,
|
||||
newest: func(f *signalFacts) time.Time { return time.Time{} }},
|
||||
{Row: "S25", Signal: "a module left out of a send because the artifact store lacks an image it names",
|
||||
Emitter: "controller's send", Trigger: "each send whose declaration names an image of the store that the store does not hold (novox/hq issue 1742)",
|
||||
Bound: "none: raised on the first look at a registered build that names such an image, naming the module, each " +
|
||||
"machine that runs it and the image; every send leaves that module out; the store is asked again at each " +
|
||||
"look and the condition ends when it holds the image",
|
||||
Kind: kindImageMissing, Severity: conditions.Warning, Phase: 3,
|
||||
needs: func(f *signalFacts) error { return f.imagesErr }, watch: watchMissingImages,
|
||||
newest: func(f *signalFacts) time.Time { return time.Time{} }},
|
||||
{Row: "S20", Signal: "a send refused for the assignment generation it was composed from",
|
||||
Emitter: "node-engine", Trigger: "each refusal (novox/hq issue 234)",
|
||||
Bound: "none: raised at the first refusal, naming its sender, the generation it came from and the one the " +
|
||||
|
||||
@@ -171,6 +171,19 @@ var suppressions = map[string]suppression{
|
||||
since: f.now.Add(-time.Second)}}
|
||||
},
|
||||
},
|
||||
// A machine holding a move of a recorded module for a person is asked at its first look (novox/hq issue 1732).
|
||||
// Inside: nothing waits there.
|
||||
"S24": {
|
||||
inside: func(f *signalFacts) { f.held = nil },
|
||||
past: func(f *signalFacts) { f.held = []heldFacts{aHeldMailu()} },
|
||||
},
|
||||
// A registered build naming an image the artifact store lacks is raised at the first look (novox/hq issue 1742).
|
||||
"S25": {
|
||||
inside: func(f *signalFacts) { f.images = nil },
|
||||
past: func(f *signalFacts) {
|
||||
f.images = []imageFacts{{missingImage{Node: "anchor", Module: "automx", Image: automxImage}}}
|
||||
},
|
||||
},
|
||||
// A batch queued behind an open walk past that walk's bound, named.
|
||||
"S19": {
|
||||
inside: func(f *signalFacts) {
|
||||
|
||||
@@ -58,6 +58,12 @@ type signalFacts struct {
|
||||
// failed are the delivery plans that failed and are asked of the operator (S23, novox/hq ADR 0449).
|
||||
failed []failedPlanFacts
|
||||
failedErr error
|
||||
// held are the machines with moves of recorded modules waiting for a person's push (S24, novox/hq issue 1732).
|
||||
held []heldFacts
|
||||
heldErr error
|
||||
// images are the modules left out of a send because the artifact store lacks an image they name (S25, issue 1742).
|
||||
images []imageFacts
|
||||
imagesErr error
|
||||
// refusedSends are the sends a machine refused within the hour for the generation they were composed
|
||||
// from, each naming its sender (S20, novox/hq issue 234).
|
||||
refusedSends []inventory.Send
|
||||
@@ -357,6 +363,8 @@ func (w *watchdogs) gather(ctx context.Context) *signalFacts {
|
||||
f.batches, f.plansErr = gatherBatches(ctx, inv, now)
|
||||
}
|
||||
f.failed, f.failedErr = gatherFailedPlans(ctx, inv, now)
|
||||
f.held, f.heldErr = gatherHeldMoves(ctx, inv)
|
||||
f.images, f.imagesErr = gatherMissingImagesHere(ctx, inv)
|
||||
f.loop, f.loopErr = w.gatherLoop()
|
||||
f.asks, f.asksErr = w.gatherAsks(ctx, inv)
|
||||
if open, err := w.keeper.Open(ctx); err != nil {
|
||||
|
||||
@@ -3,7 +3,7 @@ module github.com/novox/mesh-controller
|
||||
go 1.26.0
|
||||
|
||||
require (
|
||||
git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261021153908-725590e06e75
|
||||
git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261022123624-5ea6c215a48b
|
||||
github.com/jackc/pgx/v5 v5.10.0
|
||||
github.com/nats-io/nats-server/v2 v2.11.17
|
||||
github.com/nats-io/nats.go v1.54.0
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
git.novox.be/novox/mesh-host v0.0.0-20261018171808-9d9e3a46c4f5 h1:E5stfIeCN6uYgA9TCv+4K8JgaURg3zQppvUgJLaDMP4=
|
||||
git.novox.be/novox/mesh-host v0.0.0-20261018171808-9d9e3a46c4f5/go.mod h1:4wyoCr6IIIIarEUuROThWDj7DAvJvIidqMjWcpSnOwE=
|
||||
git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261021153908-725590e06e75 h1:AcYfyJpYaUufhI93VG76+b001msXY4XX7kuRjnf33HY=
|
||||
git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261021153908-725590e06e75/go.mod h1:ouERNpZizzwZ0HLEtAypsY9FR20FyUgUYRni6J7kVCY=
|
||||
git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261022123624-5ea6c215a48b h1:5bYfSahHJbfPWV2D4h1ejmRyvUevJtrWSpbtiVCsaOQ=
|
||||
git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261022123624-5ea6c215a48b/go.mod h1:ouERNpZizzwZ0HLEtAypsY9FR20FyUgUYRni6J7kVCY=
|
||||
github.com/antithesishq/antithesis-sdk-go v0.7.0-default-no-op h1:Z/MZK75wC/NSrkgqeNIa7jexam9uWzhLmFTSCPI/kn0=
|
||||
github.com/antithesishq/antithesis-sdk-go v0.7.0-default-no-op/go.mod h1:FQyySiasQQM8735Ddel3MRojmy4dA1IqCeyJ5jmPMbI=
|
||||
github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
|
||||
|
||||
@@ -104,6 +104,9 @@ var (
|
||||
AssignmentsBucket = BucketName(ControllerSeat, MirrorAssignments)
|
||||
DeclaredConfigBucket = BucketName(ControllerSeat, MirrorDeclaredConfig)
|
||||
PredefinedBucket = BucketName(ControllerSeat, MirrorPredefined)
|
||||
// DeclaredPackagesBucket holds, keyed by the node, each package the modules assigned to it declare, present or absent,
|
||||
// with the declaring modules: what the pacman module's verbs read to say a package is declared (ADR 0507 §5).
|
||||
DeclaredPackagesBucket = BucketName(ControllerSeat, MirrorDeclaredPackages)
|
||||
)
|
||||
|
||||
// The mirrors' local names, as a reader names them in `reads` after `mesh-controller.`.
|
||||
@@ -111,6 +114,8 @@ const (
|
||||
MirrorAssignments = "assignments"
|
||||
MirrorDeclaredConfig = "declared-config"
|
||||
MirrorPredefined = "predefined"
|
||||
// MirrorDeclaredPackages is the local name of the packages each node's modules declare (ADR 0507 §5, issue 1840/S3).
|
||||
MirrorDeclaredPackages = "declared-packages"
|
||||
)
|
||||
|
||||
// The chain's buckets (novox/hq ADR 0408, issue 1089): builds, rollouts and assignments are one chain kept on the bus
|
||||
@@ -153,7 +158,7 @@ func ChainBuckets() []string { return []string{BuildsBucket, RolloutsBucket, Ass
|
||||
// ControllerMirrors are the local names of the controller's buckets a module may read: the record mirrors and the
|
||||
// chain's buckets.
|
||||
func ControllerMirrors() []string {
|
||||
return []string{MirrorAssignments, MirrorDeclaredConfig, MirrorPredefined, ChainBuilds, ChainRollouts, ChecksRunning}
|
||||
return []string{MirrorAssignments, MirrorDeclaredConfig, MirrorPredefined, ChainBuilds, ChainRollouts, ChecksRunning, PlansBuilding, MirrorDeclaredPackages}
|
||||
}
|
||||
|
||||
// MirrorsWrittenByAnother are the controller's mirrors whose writer is not the controller, each with its reason: the rule
|
||||
@@ -222,6 +227,7 @@ func IsControllerBucket(bucket string) bool {
|
||||
return bucket == CallsBucket || bucket == HandActsBucket || bucket == ConditionsBucket ||
|
||||
bucket == ConditionHistoryBucket || bucket == LeaseBucket || bucket == AskedBucket ||
|
||||
bucket == AssignmentsBucket || bucket == DeclaredConfigBucket || bucket == PredefinedBucket ||
|
||||
bucket == DeclaredPackagesBucket ||
|
||||
bucket == MergeWindowBucket || bucket == RolloutSilentBucket || bucket == CheckRunningBucket ||
|
||||
bucket == DeliveryMergesBucket || bucket == BuildsBucket || bucket == RolloutsBucket ||
|
||||
bucket == PlansBuildingBucket || bucket == delivery.HaveBucket
|
||||
@@ -230,7 +236,7 @@ func IsControllerBucket(bucket string) bool {
|
||||
// ControllerBuckets are the controller's own buckets, in the order they are asserted.
|
||||
func ControllerBuckets() []string {
|
||||
return []string{LeaseBucket, CallsBucket, HandActsBucket, ConditionsBucket, ConditionHistoryBucket, AskedBucket,
|
||||
AssignmentsBucket, DeclaredConfigBucket, PredefinedBucket, MergeWindowBucket, RolloutSilentBucket, CheckRunningBucket,
|
||||
AssignmentsBucket, DeclaredConfigBucket, PredefinedBucket, DeclaredPackagesBucket, MergeWindowBucket, RolloutSilentBucket, CheckRunningBucket,
|
||||
DeliveryMergesBucket, PlansBuildingBucket, BuildsBucket, RolloutsBucket, delivery.HaveBucket}
|
||||
}
|
||||
|
||||
@@ -446,6 +452,9 @@ func (j *JetStream) EnsureControllerBuckets() error {
|
||||
{PredefinedBucket, "the list of predefined keys the mesh published, the newest trunk build's of the " +
|
||||
"catalogue, one key `list` (novox/hq ADR 0348 §7, design 57 K3): written by the controller alone from " +
|
||||
"its store when a newer list is kept, read through `reads`"},
|
||||
{DeclaredPackagesBucket, "each package the modules assigned to a node declare, present or absent, with the " +
|
||||
"declaring modules, keyed by the node (novox/hq ADR 0507 §5): written by the controller alone when it " +
|
||||
"composes the node, only on a change, read through `reads`"},
|
||||
} {
|
||||
if _, err := js.CreateOrUpdateKeyValue(ctx, jetstream.KeyValueConfig{
|
||||
Bucket: m.bucket,
|
||||
|
||||
@@ -0,0 +1,41 @@
|
||||
package broker
|
||||
|
||||
import (
|
||||
"slices"
|
||||
"testing"
|
||||
)
|
||||
|
||||
// Issue 1840/S3 (ADR 0507 §5), 1840/AC5: a module whose manifest reads mesh-controller.declared-packages may name it in
|
||||
// `reads`, and reads the bucket and writes none; the controller writes it, so it is no mirror written by another, and it is
|
||||
// one of the controller's own buckets, asserted at its start.
|
||||
func TestAModuleReadingDeclaredPackagesReadsAndWritesNone(t *testing.T) {
|
||||
if !slices.Contains(ControllerMirrors(), "declared-packages") ||
|
||||
BucketName(ControllerSeat, MirrorDeclaredPackages) != DeclaredPackagesBucket {
|
||||
t.Fatalf("a module cannot name %s in `reads`: %v", DeclaredPackagesBucket, ControllerMirrors())
|
||||
}
|
||||
if _, other := MirrorsWrittenByAnother[MirrorDeclaredPackages]; other {
|
||||
t.Error("the controller writes the declared packages itself")
|
||||
}
|
||||
if !IsControllerBucket(DeclaredPackagesBucket) || !slices.Contains(ControllerBuckets(), DeclaredPackagesBucket) {
|
||||
t.Errorf("%s is not among the controller's buckets", DeclaredPackagesBucket)
|
||||
}
|
||||
perms, err := PermissionsFor(Principal{Kind: KindModule, Node: "one", Module: "pacman", PasswordHash: "x",
|
||||
Reads: []string{"mesh-controller.declared-packages"}})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
stream := "KV_" + DeclaredPackagesBucket
|
||||
has(t, perms.Publish, "$JS.API.STREAM.INFO."+stream)
|
||||
has(t, perms.Publish, "$JS.API.DIRECT.GET."+stream+".>")
|
||||
has(t, perms.Publish, "$JS.API.CONSUMER.CREATE."+stream+".>")
|
||||
for _, p := range perms.Publish {
|
||||
if SubjectsOverlap(p, "$KV."+DeclaredPackagesBucket+".one") {
|
||||
t.Errorf("the reading module may write %s through %q", DeclaredPackagesBucket, p)
|
||||
}
|
||||
}
|
||||
controller, err := PermissionsFor(Principal{Kind: KindController, PasswordHash: "x"})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
has(t, controller.Publish, "$KV."+DeclaredPackagesBucket+".>")
|
||||
}
|
||||
@@ -2,10 +2,7 @@ package broker
|
||||
|
||||
import (
|
||||
"context"
|
||||
"crypto/sha256"
|
||||
"crypto/tls"
|
||||
"crypto/x509"
|
||||
"encoding/hex"
|
||||
"errors"
|
||||
"fmt"
|
||||
"os"
|
||||
@@ -112,25 +109,6 @@ func DialPinned(url, fingerprint string, opts ...nats.Option) (*JetStream, error
|
||||
return Dial(url, opts...)
|
||||
}
|
||||
|
||||
// PinnedToFingerprint accepts exactly the certificate with this SHA-256 and no other.
|
||||
func PinnedToFingerprint(want string) *tls.Config {
|
||||
return &tls.Config{
|
||||
InsecureSkipVerify: true, //nolint:gosec // replaced by the pin below, which is stricter
|
||||
MinVersion: tls.VersionTLS12,
|
||||
VerifyPeerCertificate: func(rawCerts [][]byte, _ [][]*x509.Certificate) error {
|
||||
if len(rawCerts) == 0 {
|
||||
return errors.New("the bus presented no certificate")
|
||||
}
|
||||
sum := sha256.Sum256(rawCerts[0])
|
||||
got := "sha256:" + hex.EncodeToString(sum[:])
|
||||
if got != want {
|
||||
return fmt.Errorf("the bus presented a certificate this mesh does not know (%s…), expected %s…", got[:23], want[:23])
|
||||
}
|
||||
return nil
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
// Conn is the connection itself, for what the mesh keeps off JetStream on purpose — a heartbeat,
|
||||
// a tool call — where a lost message is answered by the next one or by a timeout the caller
|
||||
// already handles (design 25 §3).
|
||||
|
||||
@@ -98,17 +98,6 @@ func (l Log) Config() jetstream.StreamConfig {
|
||||
}
|
||||
}
|
||||
|
||||
// LogIssued is one log an assignment may reach, by the name its module uses for it (novox/hq ADR
|
||||
// 0297): its stream, the subject its entries go under, and whether it may append. Only the owner's
|
||||
// instances are issued a log, so Writes is always true today; it is said so the runtime need not
|
||||
// assume it.
|
||||
type LogIssued struct {
|
||||
Name string `json:"name"`
|
||||
Stream string `json:"stream"`
|
||||
Subject string `json:"subject"`
|
||||
Writes bool `json:"writes"`
|
||||
}
|
||||
|
||||
// logsIssuedFor is every log a module's code may reach, as its membership lists them: its own.
|
||||
func logsIssuedFor(d Declared) []LogIssued {
|
||||
var out []LogIssued
|
||||
|
||||
@@ -1,7 +1,6 @@
|
||||
package broker
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"slices"
|
||||
"sort"
|
||||
"strings"
|
||||
@@ -16,81 +15,6 @@ import (
|
||||
// grant is the same composition read the other way. The shape issued today is the shape the mesh
|
||||
// already had, so nothing moves when a membership first arrives; only who decides it moves.
|
||||
|
||||
// Membership is one assignment's subjects: what this instance of a module on this machine serves,
|
||||
// and what it may reach.
|
||||
type Membership struct {
|
||||
Node string `json:"node"`
|
||||
Module string `json:"module"`
|
||||
// Serves is every address a tool of this instance answers on. `{tool}` stands for the tool's
|
||||
// own name, which the module knows and the mesh does not need to: the mesh issues the address,
|
||||
// the runtime fills the name. An address with a queue is shared with the module's other
|
||||
// instances, and the bus hands each call to one of them; an address without is this instance's.
|
||||
Serves []Served `json:"serves"`
|
||||
// Seats is every verb of a seat this instance holds, at the subject the seat's callers use.
|
||||
Seats []SeatServed `json:"seats,omitempty"`
|
||||
// Emits is where an event of this module lands; `{event}` stands for the event's name.
|
||||
Emits string `json:"emits"`
|
||||
// Reaches is each tool this module may call, `<module>.<tool>`, to the subjects that reach it:
|
||||
// the first is whichever instance answers, when the mesh issued one; the rest name a machine.
|
||||
Reaches map[string][]string `json:"reaches,omitempty"`
|
||||
// Tools is where this instance answers what it serves — the runtime's one verb of its own.
|
||||
Tools string `json:"tools"`
|
||||
// Receives is what this assignment is given for each requirement it receives, by requirement:
|
||||
// the contributions of every module that asked for it, as the catalogue composed them (novox/hq
|
||||
// ADR 0167). The same list its received file is written from, so the two cannot disagree; a
|
||||
// requirement nobody contributed to is an empty list, never absent. Kept as JSON because the
|
||||
// catalogue owns the shape of a contribution and the bus only carries it.
|
||||
Receives map[string]json.RawMessage `json:"receives,omitempty"`
|
||||
// Mesh is every machine's address on the private network — what a rule saying "from the mesh"
|
||||
// resolves to in the packet filter, issued here from the same list (novox/hq ADR 0167). A
|
||||
// module that must tell the mesh from the world, the route proxy serving an internal name, reads
|
||||
// it here rather than keeping a definition of its own.
|
||||
Mesh []string `json:"mesh,omitempty"`
|
||||
// State is every bucket this module's code may reach, by the name it uses for each, and whether
|
||||
// it may write it (novox/hq ADR 0201): the runtime answers a bundle's state verbs from this list
|
||||
// and refuses, with the reason, what is not on it — the bus enforces only the union over every
|
||||
// module on the machine.
|
||||
State []StateIssued `json:"state,omitempty"`
|
||||
// Logs is every log this module's code may reach, by the name it uses for each (novox/hq ADR 0297):
|
||||
// its own and no other's, since a log is its owner's alone. The runtime answers a bundle's log verbs
|
||||
// from this list and refuses, with the reason, a log not on it.
|
||||
Logs []LogIssued `json:"logs,omitempty"`
|
||||
// SeatTraffic is what this module's code may submit, say, hear, take, ask, answer and read on seats
|
||||
// that name their caller or their kind (novox/hq ADR 0259 §3). The runtime carrying the module
|
||||
// publishes, takes and answers for it only what is listed here: the bus enforces only the union
|
||||
// over every module on the machine, so one module's code reaching another's name or kind through
|
||||
// the runtime is the runtime's to refuse.
|
||||
SeatTraffic *SeatTraffic `json:"seat-traffic,omitempty"`
|
||||
// Streams are this module's own streams (novox/hq ADR 0363 §2): an event one of them carries is published
|
||||
// on that stream's subject, never on Emits. Hears are the module streams it hears, each through a durable
|
||||
// consumer on that stream the runtime binds beside the one on EVENTS (§8).
|
||||
Streams []StreamIssued `json:"streams,omitempty"`
|
||||
Hears []HeardIssued `json:"hears,omitempty"`
|
||||
// Waits are the event families a session may wait on through the mesh MCP server, the tool runner's
|
||||
// alone (novox/hq ADR 0367 §2): the subjects its account is granted, under the names a session asks for.
|
||||
// The tool runner refuses any family not listed here.
|
||||
Waits []WaitIssued `json:"waits,omitempty"`
|
||||
}
|
||||
|
||||
// Served is one address a tool is answered on.
|
||||
type Served struct {
|
||||
Subject string `json:"subject"`
|
||||
Queue string `json:"queue,omitempty"`
|
||||
}
|
||||
|
||||
// SeatServed is one verb of a held seat, where its callers ask.
|
||||
type SeatServed struct {
|
||||
Seat string `json:"seat"`
|
||||
Verb string `json:"verb"`
|
||||
Subject string `json:"subject"`
|
||||
}
|
||||
|
||||
// MembershipSubject is the one address a runtime derives for itself: where its own membership is
|
||||
// published, from the two names its credential carries. Everything else is in the membership.
|
||||
func MembershipSubject(node, module string) string {
|
||||
return "mesh.assignment." + node + "." + module
|
||||
}
|
||||
|
||||
// Placements is where every module runs, for deciding which instance answers for the module.
|
||||
type Placements struct {
|
||||
// Nodes is each module's machines.
|
||||
|
||||
@@ -260,21 +260,6 @@ func ownStreamGrants(module string, streams []ModuleStream) []string {
|
||||
return out
|
||||
}
|
||||
|
||||
// StreamIssued is one of a module's own streams as its membership names it (ADR 0363 §2): the events it
|
||||
// carries, as the bus spells them, and the subject an event of them is published on, `{event}` the event.
|
||||
type StreamIssued struct {
|
||||
Stream string `json:"stream"`
|
||||
Events []string `json:"events"`
|
||||
Subject string `json:"subject"`
|
||||
}
|
||||
|
||||
// HeardIssued is one module stream an assignment hears, as its membership names it (ADR 0363 §8): the
|
||||
// stream and the durable consumer on it the runtime binds.
|
||||
type HeardIssued struct {
|
||||
Stream string `json:"stream"`
|
||||
Consumer string `json:"consumer"`
|
||||
}
|
||||
|
||||
// streamsIssuedFor is every stream of its own a module's membership names.
|
||||
func streamsIssuedFor(d Declared) []StreamIssued {
|
||||
var out []StreamIssued
|
||||
|
||||
+22
-5
@@ -361,9 +361,11 @@ var VaultNodeKey = SeatVerb{Seat: "mesh-vault", Verb: "node-key"}
|
||||
|
||||
// VerbsTheControllerActsOnAWarrant are the other seat verbs the controller calls when the operator's warrant
|
||||
// chooses them (novox/hq ADR 0259): a machine's service restarted, and a walk started or stopped through the
|
||||
// controller's own `plans`. Named one by one; a node seat's on any machine, a mesh seat's flat.
|
||||
// controller's own `plans`, a machine's held builds sent by its own `push` and the builds held after a failed release
|
||||
// sent by its own `upgrade release-backlog` (novox/hq issue 1732). Named one by one; a node seat's on any machine, a
|
||||
// mesh seat's flat.
|
||||
var VerbsTheControllerActsOnAWarrant = []SeatVerb{{Seat: "node-service-manager", Verb: "restart"},
|
||||
{Seat: ControllerSeat, Verb: "plans"}}
|
||||
{Seat: ControllerSeat, Verb: "plans"}, {Seat: ControllerSeat, Verb: "push"}, {Seat: ControllerSeat, Verb: "upgrade"}}
|
||||
|
||||
// VerbsTheControllerAsksTheOperatorChannel are the operator channel's verbs the controller calls (novox/hq
|
||||
// ADR 0380): `tell`, one plain message with no condition behind it — a module's own secret given, named,
|
||||
@@ -387,6 +389,16 @@ type DegradableGrant struct {
|
||||
// works. Every other grant stays required — missing one of those is a controller that comes up and is
|
||||
// refused on the first thing it tries, with no fallback that covers it.
|
||||
var DegradableGrants = []DegradableGrant{
|
||||
{
|
||||
Subject: "mesh.seat." + ControllerSeat + ".tool.push",
|
||||
Reason: "refused: the ask of a held move (Release) is answered, and the refusal told, while the operator's own " +
|
||||
"push at the terminal still sends the machine (issue 1732; ADR 0259)",
|
||||
},
|
||||
{
|
||||
Subject: "mesh.seat." + ControllerSeat + ".tool.upgrade",
|
||||
Reason: "refused: the ask of the builds held after a failed release is answered, and the refusal told, while the " +
|
||||
"operator's own `upgrade release-backlog` at the terminal still releases them (issue 1732; ADR 0259)",
|
||||
},
|
||||
{
|
||||
Subject: "mesh.seat." + VerbsTheControllerAsksTheOperatorChannel[0].Seat + ".tool." + VerbsTheControllerAsksTheOperatorChannel[0].Verb,
|
||||
Reason: "refused: the controller raises the secret-given condition as before (ADR 0380 §9)",
|
||||
@@ -417,6 +429,11 @@ var DegradableGrants = []DegradableGrant{
|
||||
Reason: "refused: the controller then says no plan builds, and no check is held while a delivery builds — a check run " +
|
||||
"wrongly costs a delivery a place, a check held wrongly costs a pull request its turn (ADR 0483 clause 2, issue 1687)",
|
||||
},
|
||||
{
|
||||
Subject: "$KV." + DeclaredPackagesBucket + ".>",
|
||||
Reason: "carried only at genesis: the controller composes its own permissions and pushes them to the bus at its " +
|
||||
"first push, and keeps the packages each node declares only after that, holding the lease (ADR 0507 §5, issue 1840)",
|
||||
},
|
||||
{
|
||||
Subject: "mesh.seat." + ControllerSeat + ".event.sent",
|
||||
Reason: "refused: the controller says a tier sent to a machine only for outsiders, and a send that could not " +
|
||||
@@ -702,7 +719,7 @@ func PermissionsFor(p Principal) (Permissions, error) {
|
||||
// And asking the operator (novox/hq ADR 0259): an ask and its cancel under its own name, its warrants
|
||||
// heard under its own name, the record of its asks read under its own name — as any user of the seat,
|
||||
// derived the same way, from the seat its holder declares.
|
||||
tp, ts := SeatTrafficOf(ControllerSeat, nil, p.Uses, nil).grants()
|
||||
tp, ts := seatTrafficGrants(SeatTrafficOf(ControllerSeat, nil, p.Uses, nil))
|
||||
pub = append(pub, tp...)
|
||||
sub = append(sub, ts...)
|
||||
// And asks who answers (novox/hq to-be 45 §4, D3): the self-check finds every seat's holder by
|
||||
@@ -1035,7 +1052,7 @@ func PermissionsFor(p Principal) (Permissions, error) {
|
||||
|
||||
// 6. Its traffic on seats that name their caller or their kind, ask proofs or keep records
|
||||
// (novox/hq ADR 0259 §3).
|
||||
tp, ts := SeatTrafficOf(p.Module, p.Holds, p.Uses, p.Watches).grants()
|
||||
tp, ts := seatTrafficGrants(SeatTrafficOf(p.Module, p.Holds, p.Uses, p.Watches))
|
||||
pub = append(pub, tp...)
|
||||
sub = append(sub, ts...)
|
||||
|
||||
@@ -1159,7 +1176,7 @@ func PermissionsFor(p Principal) (Permissions, error) {
|
||||
// not publish under another's name or kind through it is the runtime's to keep, from the seat
|
||||
// traffic each module's membership lists.
|
||||
for _, d := range p.Carries {
|
||||
tp, ts := SeatTrafficOf(d.Module, d.Holds, d.Uses, d.Watches).grants()
|
||||
tp, ts := seatTrafficGrants(SeatTrafficOf(d.Module, d.Holds, d.Uses, d.Watches))
|
||||
pub = append(pub, tp...)
|
||||
sub = append(sub, ts...)
|
||||
}
|
||||
|
||||
@@ -35,39 +35,6 @@ func OnNATS() (address string, on bool, err error) {
|
||||
return address, true, nil
|
||||
}
|
||||
|
||||
// CredentialIn reads the user and password out of a bus address, and the address without them.
|
||||
//
|
||||
// The controller's own credential arrives in its address, the way the old bus's does. Split out so the
|
||||
// controller can record a hash of what it is actually using: its user is created by the installer at a
|
||||
// bootstrap password, before the controller exists to mint one, and a composition that left itself out
|
||||
// would produce a bus the writer cannot connect to.
|
||||
func CredentialIn(address string) (user, password, bare string) {
|
||||
at := strings.LastIndex(address, "@")
|
||||
if at < 0 {
|
||||
return "", "", address
|
||||
}
|
||||
scheme := ""
|
||||
rest := address[:at]
|
||||
if i := strings.Index(rest, "://"); i >= 0 {
|
||||
scheme, rest = rest[:i+3], rest[i+3:]
|
||||
}
|
||||
user, password, _ = strings.Cut(rest, ":")
|
||||
return user, password, scheme + address[at+1:]
|
||||
}
|
||||
|
||||
// BareAddress is a bus address with any credential stripped, for something that only needs to know
|
||||
// whether a server is answering there.
|
||||
func BareAddress(address string) string {
|
||||
_, _, bare := CredentialIn(address)
|
||||
if bare == "" {
|
||||
return address
|
||||
}
|
||||
if strings.Contains(bare, "://") {
|
||||
return bare
|
||||
}
|
||||
return "nats://" + bare
|
||||
}
|
||||
|
||||
// BusAddress is where the mesh's bus is, with this process's credential, and refuses to be empty:
|
||||
// there is one bus, and a control plane without it can hold records and answer nothing (novox/hq
|
||||
// ADR 0131, design 28 task 5.5).
|
||||
|
||||
@@ -1,28 +0,0 @@
|
||||
package broker
|
||||
|
||||
import (
|
||||
"testing"
|
||||
)
|
||||
|
||||
// Which bus the mesh is on is one fact, and being told about both is refused.
|
||||
//
|
||||
|
||||
// The controller's own credential arrives in its address, and has to be readable out of it — its user
|
||||
// is created by the installer at a bootstrap password, before the controller exists to mint one.
|
||||
func TestACredentialIsReadOutOfABusAddress(t *testing.T) {
|
||||
for _, c := range []struct{ in, user, password, bare string }{
|
||||
{"nats://controller:secret@127.0.0.1:4222", "controller", "secret", "nats://127.0.0.1:4222"},
|
||||
{"controller:secret@127.0.0.1:4222", "controller", "secret", "127.0.0.1:4222"},
|
||||
{"nats://127.0.0.1:4222", "", "", "nats://127.0.0.1:4222"},
|
||||
{"127.0.0.1:4222", "", "", "127.0.0.1:4222"},
|
||||
// A password containing an at-sign: split on the last one, or the address becomes part of the
|
||||
// credential and the connection goes somewhere nobody named.
|
||||
{"nats://controller:a@b@127.0.0.1:4222", "controller", "a@b", "nats://127.0.0.1:4222"},
|
||||
} {
|
||||
user, password, bare := CredentialIn(c.in)
|
||||
if user != c.user || password != c.password || bare != c.bare {
|
||||
t.Errorf("%q read as %q/%q at %q; wanted %q/%q at %q",
|
||||
c.in, user, password, bare, c.user, c.password, c.bare)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,30 @@
|
||||
package broker
|
||||
|
||||
import (
|
||||
"slices"
|
||||
"testing"
|
||||
)
|
||||
|
||||
// Issue 1687 (ADR 0483 clause 2): a module whose manifest reads mesh-controller.plans-building may name it in `reads`, and
|
||||
// reads the bucket and writes none; the controller writes it, so it is no mirror written by another.
|
||||
func TestAModuleReadingPlansBuildingReadsAndWritesNone(t *testing.T) {
|
||||
if !slices.Contains(ControllerMirrors(), "plans-building") || BucketName(ControllerSeat, PlansBuilding) != PlansBuildingBucket {
|
||||
t.Fatalf("a module cannot name %s in `reads`: %v", PlansBuildingBucket, ControllerMirrors())
|
||||
}
|
||||
if _, other := MirrorsWrittenByAnother[PlansBuilding]; other {
|
||||
t.Error("the controller writes the plans building itself")
|
||||
}
|
||||
perms, err := PermissionsFor(Principal{Kind: KindModule, Node: "one", Module: "mesh-delivery-checker", PasswordHash: "x",
|
||||
Reads: []string{"mesh-controller.plans-building"}})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
stream := "KV_" + PlansBuildingBucket
|
||||
has(t, perms.Publish, "$JS.API.STREAM.INFO."+stream)
|
||||
has(t, perms.Publish, "$JS.API.DIRECT.GET."+stream+".>")
|
||||
for _, p := range perms.Publish {
|
||||
if SubjectsOverlap(p, "$KV."+PlansBuildingBucket+".plan-1") {
|
||||
t.Errorf("the reading module may write %s through %q", PlansBuildingBucket, p)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,41 @@
|
||||
package broker
|
||||
|
||||
import "testing"
|
||||
|
||||
// 1840/AC9: a process account declaring the state `x` may watch and list the keys of its module's own bucket (a consumer
|
||||
// created and deleted on KV_<module>_x), read and write it, and has no grant on another module's bucket or on a mirror of the
|
||||
// controller's, whatever it is named after.
|
||||
func TestAProcessMayWatchItsOwnStateAndNoOthers(t *testing.T) {
|
||||
p := Principal{Kind: KindProcess, Node: "novox", Module: "mesh-mail", Process: "send", State: []string{"x"}}
|
||||
got := perms(t, p)
|
||||
for _, s := range []string{
|
||||
"$JS.API.CONSUMER.CREATE.KV_mesh-mail_x",
|
||||
"$JS.API.CONSUMER.CREATE.KV_mesh-mail_x.watcher",
|
||||
"$JS.API.CONSUMER.CREATE.KV_mesh-mail_x.watcher.$KV.mesh-mail_x.>",
|
||||
"$JS.API.CONSUMER.DELETE.KV_mesh-mail_x.watcher",
|
||||
"$JS.API.DIRECT.GET.KV_mesh-mail_x.$KV.mesh-mail_x.key",
|
||||
"$JS.API.STREAM.INFO.KV_mesh-mail_x",
|
||||
"$JS.FC.KV_mesh-mail_x.watcher",
|
||||
"$KV.mesh-mail_x.key",
|
||||
} {
|
||||
if !allowed(got.Publish, s) {
|
||||
t.Errorf("the process may not publish %s, so it cannot watch or list its own state", s)
|
||||
}
|
||||
}
|
||||
for _, other := range []string{"mesh-other_x", "mesh-mail_y", DeclaredPackagesBucket, AssignmentsBucket} {
|
||||
for _, s := range []string{
|
||||
"$JS.API.CONSUMER.CREATE.KV_" + other,
|
||||
"$JS.API.CONSUMER.CREATE.KV_" + other + ".watcher",
|
||||
"$JS.API.CONSUMER.CREATE.KV_" + other + ".watcher.$KV." + other + ".>",
|
||||
"$JS.API.CONSUMER.DELETE.KV_" + other + ".watcher",
|
||||
"$JS.API.DIRECT.GET.KV_" + other + ".$KV." + other + ".key",
|
||||
"$JS.API.STREAM.INFO.KV_" + other,
|
||||
"$JS.FC.KV_" + other + ".watcher",
|
||||
"$KV." + other + ".key",
|
||||
} {
|
||||
if allowed(got.Publish, s) {
|
||||
t.Errorf("the process may publish %s, on a bucket that is not its own state", s)
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,38 @@
|
||||
package broker
|
||||
|
||||
import (
|
||||
"git.novox.be/novox/mesh-sdk/go/membership"
|
||||
"git.novox.be/novox/mesh-sdk/go/process"
|
||||
)
|
||||
|
||||
// The membership the mesh issues an assignment (novox/hq ADR 0160), its subject, its stream, the bare address and the
|
||||
// pin are mesh-sdk's, public so that a module's program outside this Go module, the route proxy, reads them too
|
||||
// (novox/hq ADR 0480 clause 4, issue 1633). This package keeps no second copy: what follows only names them where the
|
||||
// controller already did.
|
||||
type (
|
||||
Membership = membership.Membership
|
||||
Served = membership.Served
|
||||
SeatServed = membership.SeatServed
|
||||
StateIssued = membership.StateIssued
|
||||
LogIssued = membership.LogIssued
|
||||
Worker = membership.Worker
|
||||
SeatTraffic = membership.SeatTraffic
|
||||
KindHeld = membership.KindHeld
|
||||
StreamIssued = membership.StreamIssued
|
||||
HeardIssued = membership.HeardIssued
|
||||
WaitIssued = membership.WaitIssued
|
||||
)
|
||||
|
||||
// AssignmentsStream holds every assignment's membership, the newest per subject.
|
||||
const AssignmentsStream = membership.AssignmentsStream
|
||||
|
||||
var (
|
||||
// MembershipSubject is where an assignment's own membership is published.
|
||||
MembershipSubject = membership.Subject
|
||||
// CredentialIn reads the user and password out of a bus address, and the address without them.
|
||||
CredentialIn = membership.CredentialIn
|
||||
// BareAddress is a bus address with any credential stripped.
|
||||
BareAddress = membership.BareAddress
|
||||
// PinnedToFingerprint accepts exactly the certificate with this SHA-256 and no other.
|
||||
PinnedToFingerprint = process.PinnedToFingerprint
|
||||
)
|
||||
@@ -24,44 +24,6 @@ import "sort"
|
||||
// And one read: **a holder's records**, a bucket the seat names, read by each user under its own name only
|
||||
// (`$KV.<bucket>.<module>.>`), so an asker reads the state of its own asks and no other asker's.
|
||||
|
||||
// Worker is one durable consumer a holder pulls a seat's work from.
|
||||
type Worker struct {
|
||||
Stream string
|
||||
Consumer string
|
||||
Filter string
|
||||
}
|
||||
|
||||
// SeatTraffic is one module's seat traffic beyond tools. Publish and Subscribe are subject patterns, in the
|
||||
// server's wildcards; the runtime that carries the module checks a bundle's request against them, since
|
||||
// the runtime's own principal holds the union of every module it carries.
|
||||
type SeatTraffic struct {
|
||||
// Publish is what it submits (accepts of seats it uses), says (events of seats it holds) and asks
|
||||
// (proofs of seats it holds a kind of).
|
||||
Publish []string `json:"publish,omitempty"`
|
||||
// Subscribe is what it hears: events of seats it uses that are named by caller, events of seats it
|
||||
// watches, and accepts of seats it holds.
|
||||
Subscribe []string `json:"subscribe,omitempty"`
|
||||
// Answers is the proof subjects it answers, as a watcher of a kinded seat.
|
||||
Answers []string `json:"answers,omitempty"`
|
||||
// Workers are the work queues it takes from, as a holder.
|
||||
Workers []Worker `json:"workers,omitempty"`
|
||||
// Records is the direct-get subjects of the records it reads under its own name.
|
||||
Records []string `json:"records,omitempty"`
|
||||
// Kinds are the holders of every kinded bench it uses or watches, with what each promises: the one
|
||||
// account of which channel is which, and what it can carry, that the router judges an answer by. The
|
||||
// controller's, from the claims, never a channel's word (novox/hq ADR 0259 §5).
|
||||
Kinds []KindHeld `json:"kinds,omitempty"`
|
||||
}
|
||||
|
||||
// KindHeld is one kind of a kinded bench and who holds it.
|
||||
type KindHeld struct {
|
||||
Seat string `json:"seat"`
|
||||
Kind string `json:"kind"`
|
||||
Module string `json:"module"`
|
||||
Node string `json:"node"`
|
||||
Capabilities []string `json:"capabilities,omitempty"`
|
||||
}
|
||||
|
||||
// KindedBenches are the seats that may be kinded (ADR 0234 §2): making another is a decision, recorded.
|
||||
var KindedBenches = map[string]bool{"channel": true, "intake": true}
|
||||
|
||||
@@ -175,9 +137,9 @@ func SeatTrafficOf(module string, holds, uses, watches []Seat) SeatTraffic {
|
||||
return t
|
||||
}
|
||||
|
||||
// grants is the bus permissions seat traffic needs: the subjects themselves, and the JetStream API a
|
||||
// seatTrafficGrants is the bus permissions seat traffic needs: the subjects themselves, and the JetStream API a
|
||||
// worker is pulled and acknowledged through and a record is read through.
|
||||
func (t SeatTraffic) grants() (pub, sub []string) {
|
||||
func seatTrafficGrants(t SeatTraffic) (pub, sub []string) {
|
||||
pub = append(pub, t.Publish...)
|
||||
sub = append(sub, t.Subscribe...)
|
||||
sub = append(sub, t.Answers...)
|
||||
|
||||
@@ -186,16 +186,6 @@ func perMachineNames(buckets []Bucket) []string {
|
||||
return out
|
||||
}
|
||||
|
||||
// StateIssued is one bucket an assignment may reach, by the name its module uses for it: its own
|
||||
// state by the local name, another's as `<module>.<name>` (novox/hq ADR 0201). Key, when set, is the
|
||||
// one key it may reach (novox/hq ADR 0260): this machine's.
|
||||
type StateIssued struct {
|
||||
Name string `json:"name"`
|
||||
Bucket string `json:"bucket"`
|
||||
Writes bool `json:"writes,omitempty"`
|
||||
Key string `json:"key,omitempty"`
|
||||
}
|
||||
|
||||
// stateIssuedFor is every bucket a module's code may reach on a machine, as its membership lists them.
|
||||
func stateIssuedFor(d Declared, node string) []StateIssued {
|
||||
var out []StateIssued
|
||||
|
||||
@@ -80,9 +80,6 @@ const RestrictedMetadata = "mesh-restricted"
|
||||
// it under: never set by a mesh-internal work-queue stream (a seat's, a check's), only by Stream.WorkQueue.
|
||||
const WorkQueueMetadata = "mesh-work-queue"
|
||||
|
||||
// AssignmentsStream holds every assignment's membership, the newest per subject.
|
||||
const AssignmentsStream = "ASSIGNMENTS"
|
||||
|
||||
// What a durable consumer gave up on is kept (novox/hq issue 330, design 25 §3).
|
||||
//
|
||||
// **The server says it and keeps it; the controller copies it.** A consumer that handed a message over
|
||||
|
||||
+1
-1
@@ -29,7 +29,7 @@ accounts {
|
||||
]
|
||||
users = [
|
||||
{ user: "controller", password: "$2a$11$cccccccccccccccccccccc", permissions: {
|
||||
publish: { allow: ["$JS.ACK.CONTROL.controller.>", "$JS.ACK.DEAD_LETTER_NOTICES.controller.>", "$JS.ACK.EVENTS.controller-merges.>", "$JS.ACK.EVENTS.controller.>", "$JS.API.>", "$KV.SEAT_MESH_BUILD_MACHINE_cancelled.>", "$KV.SEAT_NODE_BUILD_AGENT_cancelled.>", "$KV.mesh-controller_asked.>", "$KV.mesh-controller_assignments.>", "$KV.mesh-controller_builds.>", "$KV.mesh-controller_calls.>", "$KV.mesh-controller_checks-running.>", "$KV.mesh-controller_condition-history.>", "$KV.mesh-controller_conditions.>", "$KV.mesh-controller_declared-config.>", "$KV.mesh-controller_delivery-merges.>", "$KV.mesh-controller_hand-acts.>", "$KV.mesh-controller_lease.>", "$KV.mesh-controller_merge-window.>", "$KV.mesh-controller_plans-building.>", "$KV.mesh-controller_predefined.>", "$KV.mesh-controller_rollout-silent.>", "$KV.mesh-controller_rollouts.>", "$SRV.INFO", "_INBOX.enrol.>", "mesh.again.>", "mesh.assignment.>", "mesh.events.dead.>", "mesh.mod.*.tool.>", "mesh.node.>", "mesh.seat.mesh-build-machine.accept.>", "mesh.seat.mesh-build-machine.tool.>", "mesh.seat.mesh-controller.event.applied", "mesh.seat.mesh-controller.event.assignment-changed", "mesh.seat.mesh-controller.event.built-before", "mesh.seat.mesh-controller.event.checked", "mesh.seat.mesh-controller.event.condition-changed", "mesh.seat.mesh-controller.event.condition-cleared", "mesh.seat.mesh-controller.event.condition-raised", "mesh.seat.mesh-controller.event.declared-config-changed", "mesh.seat.mesh-controller.event.doctor-heartbeat", "mesh.seat.mesh-controller.event.healer-acted", "mesh.seat.mesh-controller.event.plan-moved", "mesh.seat.mesh-controller.event.predefined-changed", "mesh.seat.mesh-controller.event.refused", "mesh.seat.mesh-controller.event.rolled-back", "mesh.seat.mesh-controller.event.secret-replaced", "mesh.seat.mesh-controller.event.sent", "mesh.seat.mesh-controller.tool.plans", "mesh.seat.mesh-delivery.tool.close", "mesh.seat.mesh-delivery.tool.groups", "mesh.seat.mesh-delivery.tool.release", "mesh.seat.mesh-delivery.tool.stalled", "mesh.seat.mesh-delivery.tool.stop", "mesh.seat.mesh-delivery.tool.times", "mesh.seat.node-backup.tool.backed-up.*", "mesh.seat.node-backup.tool.now.*", "mesh.seat.node-build-agent.accept.>", "mesh.seat.node-build-agent.check.>", "mesh.seat.node-build-agent.tool.>", "mesh.seat.node-intrusion-prevention.tool.banned.*", "mesh.seat.node-launcher.tool.secret.*", "mesh.seat.node-service-manager.tool.restart.*", "mesh.seat.operator-channel.tool.tell"] }
|
||||
publish: { allow: ["$JS.ACK.CONTROL.controller.>", "$JS.ACK.DEAD_LETTER_NOTICES.controller.>", "$JS.ACK.EVENTS.controller-merges.>", "$JS.ACK.EVENTS.controller.>", "$JS.API.>", "$KV.SEAT_MESH_BUILD_MACHINE_cancelled.>", "$KV.SEAT_NODE_BUILD_AGENT_cancelled.>", "$KV.mesh-controller_asked.>", "$KV.mesh-controller_assignments.>", "$KV.mesh-controller_builds.>", "$KV.mesh-controller_calls.>", "$KV.mesh-controller_checks-running.>", "$KV.mesh-controller_condition-history.>", "$KV.mesh-controller_conditions.>", "$KV.mesh-controller_declared-config.>", "$KV.mesh-controller_declared-packages.>", "$KV.mesh-controller_delivery-merges.>", "$KV.mesh-controller_hand-acts.>", "$KV.mesh-controller_lease.>", "$KV.mesh-controller_merge-window.>", "$KV.mesh-controller_plans-building.>", "$KV.mesh-controller_predefined.>", "$KV.mesh-controller_rollout-silent.>", "$KV.mesh-controller_rollouts.>", "$SRV.INFO", "_INBOX.enrol.>", "mesh.again.>", "mesh.assignment.>", "mesh.events.dead.>", "mesh.mod.*.tool.>", "mesh.node.>", "mesh.seat.mesh-build-machine.accept.>", "mesh.seat.mesh-build-machine.tool.>", "mesh.seat.mesh-controller.event.applied", "mesh.seat.mesh-controller.event.assignment-changed", "mesh.seat.mesh-controller.event.built-before", "mesh.seat.mesh-controller.event.checked", "mesh.seat.mesh-controller.event.condition-changed", "mesh.seat.mesh-controller.event.condition-cleared", "mesh.seat.mesh-controller.event.condition-raised", "mesh.seat.mesh-controller.event.declared-config-changed", "mesh.seat.mesh-controller.event.doctor-heartbeat", "mesh.seat.mesh-controller.event.healer-acted", "mesh.seat.mesh-controller.event.plan-moved", "mesh.seat.mesh-controller.event.predefined-changed", "mesh.seat.mesh-controller.event.refused", "mesh.seat.mesh-controller.event.rolled-back", "mesh.seat.mesh-controller.event.secret-replaced", "mesh.seat.mesh-controller.event.sent", "mesh.seat.mesh-controller.tool.plans", "mesh.seat.mesh-controller.tool.push", "mesh.seat.mesh-controller.tool.upgrade", "mesh.seat.mesh-delivery.tool.close", "mesh.seat.mesh-delivery.tool.groups", "mesh.seat.mesh-delivery.tool.release", "mesh.seat.mesh-delivery.tool.stalled", "mesh.seat.mesh-delivery.tool.stop", "mesh.seat.mesh-delivery.tool.times", "mesh.seat.node-backup.tool.backed-up.*", "mesh.seat.node-backup.tool.now.*", "mesh.seat.node-build-agent.accept.>", "mesh.seat.node-build-agent.check.>", "mesh.seat.node-build-agent.tool.>", "mesh.seat.node-intrusion-prevention.tool.banned.*", "mesh.seat.node-launcher.tool.secret.*", "mesh.seat.node-service-manager.tool.restart.*", "mesh.seat.operator-channel.tool.tell"] }
|
||||
subscribe: { allow: ["$JS.API.>", "$JS.EVENT.ADVISORY.CONSUMER.DELETED.>", "$JS.EVENT.ADVISORY.CONSUMER.MAX_DELIVERIES.>", "$SRV.INFO", "$SRV.INFO.mesh-controller", "$SRV.INFO.mesh-controller.>", "$SRV.PING", "$SRV.PING.mesh-controller", "$SRV.PING.mesh-controller.>", "$SRV.STATS", "$SRV.STATS.mesh-controller", "$SRV.STATS.mesh-controller.>", "_DELIVER.controller", "_DELIVER.controller.>", "_INBOX.controller.>", "mesh.control.>", "mesh.mod.*.event.provisioner.failing", "mesh.mod.*.event.provisioner.recovered", "mesh.mod.*.event.provisioner.retirement", "mesh.mod.gitea.event.pull.merged", "mesh.mod.gitea.event.pull.updated", "mesh.mod.mesh-catalog.event.catching-up", "mesh.mod.mesh-catalog.event.upgraded", "mesh.seat.mesh-build-machine.event.built", "mesh.seat.mesh-controller.tool.>", "mesh.seat.node-build-agent.event.built", "mesh.seat.operator-channel.event.decided.mesh-controller"] }
|
||||
allow_responses: { max: 1, ttl: "1m" }
|
||||
} }
|
||||
|
||||
@@ -31,12 +31,6 @@ type Wait struct {
|
||||
Last string
|
||||
}
|
||||
|
||||
// WaitIssued is one family as a membership issues it: the name a session asks for, and its subject.
|
||||
type WaitIssued struct {
|
||||
Event string `json:"event"`
|
||||
Subject string `json:"subject"`
|
||||
}
|
||||
|
||||
// WaitSubject is where a family's events land. Each token is checked before it becomes a subject: a
|
||||
// wildcard, a dot inside a name or an empty token would widen the grant.
|
||||
func WaitSubject(w Wait) (string, error) {
|
||||
|
||||
@@ -177,7 +177,7 @@ var WritersTable = []WriterRow{
|
||||
KeptIn: "key-value " + CheckRunningBucket + ", aged out when not renewed", Others: "the build seat's holders read it to drop a duplicate request",
|
||||
Subjects: kvOf(CheckRunningBucket), Writes: holdsTheBuildSeat,
|
||||
Shared: "every machine holding the build seat puts the key of the check it runs and deletes it when the check ends"},
|
||||
{State: "a delivery plan in its build phase", Writer: "controller (lease holder), at the first build's ask and at each refresh",
|
||||
{State: "the plans-building mirror", Writer: "controller (lease holder), at the first build's ask and at each refresh",
|
||||
KeptIn: "key-value " + PlansBuildingBucket + ", aged out when not refreshed",
|
||||
Others: "the build seat's holders read it and take no new check while a key is there (ADR 0483)",
|
||||
Subjects: kvOf(PlansBuildingBucket), Writes: isController},
|
||||
@@ -236,6 +236,9 @@ var WritersTable = []WriterRow{
|
||||
{State: "the predefined-keys mirror", Writer: "controller (lease holder), from its store, only on a change",
|
||||
KeptIn: "key-value " + PredefinedBucket, Others: "read through `reads` as mesh-controller." + MirrorPredefined,
|
||||
Subjects: kvOf(PredefinedBucket), Writes: isController},
|
||||
{State: "the declared-packages mirror", Writer: "controller (lease holder), from the composition of each node, only on a change",
|
||||
KeptIn: "key-value " + DeclaredPackagesBucket, Others: "read through `reads` as mesh-controller." + MirrorDeclaredPackages,
|
||||
Subjects: kvOf(DeclaredPackagesBucket), Writes: isController},
|
||||
// What a machine's provisioner client placed of a module's files (novox/hq ADR 0349 §4, design 57 P6): its own
|
||||
// machine's word alone, which a walk's end and a gate wait for (ADR 0362, ADR 0349 §15). Kept newest per module
|
||||
// in the stream ProvAppliedStream, and by the client in the provisioner server's `applied` bucket.
|
||||
|
||||
@@ -30,7 +30,7 @@ var designRows = []string{
|
||||
"a pull request's check asked",
|
||||
"a pull request's check running",
|
||||
// The plans in their build phase, a bucket the build seat's holders read (ADR 0483 clause 2, issue 1687).
|
||||
"a delivery plan in its build phase",
|
||||
"the plans-building mirror",
|
||||
"a merge announced",
|
||||
"a pull request's head announced",
|
||||
"a pull request's merge check",
|
||||
@@ -49,6 +49,7 @@ var designRows = []string{
|
||||
"a declaration's large files",
|
||||
"the declared-config mirror",
|
||||
"the predefined-keys mirror",
|
||||
"the declared-packages mirror",
|
||||
// The provisioner client's word on what it placed (novox/hq ADR 0349 §4, design 57 P6).
|
||||
"a module's files placed on a machine",
|
||||
}
|
||||
|
||||
@@ -86,11 +86,14 @@ func TestAnImageCompilingGoIsHandedItsBuildSourceAndSaysIt(t *testing.T) {
|
||||
}
|
||||
for file, want := range map[string]bool{"proxy/main.go": true, "internal/shared/s.go": true, "go.mod": true,
|
||||
"cmd/ctl/main.go": false, "internal/only/o.go": false, "README.md": false} {
|
||||
_, err := os.Stat(filepath.Join(workspace, "narrow-server", filepath.FromSlash(file)))
|
||||
if (err == nil) != want {
|
||||
t.Errorf("%s handed to the recipe: %v, wanted %v", file, err == nil, want)
|
||||
held := slices.Contains(r.builtFrom, file)
|
||||
if held != want {
|
||||
t.Errorf("%s handed to the recipe: %v, wanted %v", file, held, want)
|
||||
}
|
||||
}
|
||||
if _, err := os.Stat(filepath.Join(workspace, "narrow-server")); err == nil {
|
||||
t.Error("the narrowed build source was left in the workspace")
|
||||
}
|
||||
|
||||
// Said per repository: its own, the manifest and the recipe; the context's, the closure.
|
||||
if len(got.Sources) != 2 {
|
||||
|
||||
@@ -219,6 +219,11 @@ func build(ctx context.Context, run Runner, publish Publisher,
|
||||
if err := os.MkdirAll(workspace, 0o755); err != nil {
|
||||
return Result{}, err
|
||||
}
|
||||
// **A node with no room takes no build** (novox/hq issue 1834).
|
||||
if err := RoomToWork("/", workspace); err != nil {
|
||||
say("clone", "refused: %v", err)
|
||||
return Result{}, err
|
||||
}
|
||||
// The credential is a file git reads, never an argument: a URL carrying a password in argv
|
||||
// would be readable by anything that can list processes for as long as a clone runs.
|
||||
credentials, forget, err := storeCredential(workspace, forge)
|
||||
@@ -738,11 +743,41 @@ func logging(log Log) func(step, format string, args ...any) {
|
||||
}
|
||||
}
|
||||
|
||||
// keepsImageLocally says the publisher leaves the image in the machine's runtime as the artifact itself.
|
||||
func keepsImageLocally(publish Publisher) bool {
|
||||
switch publish.(type) {
|
||||
case Local, *Local:
|
||||
return true
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// PushedNames is implemented by a publisher that tags the image under other names to push it: the names it leaves in the
|
||||
// machine's runtime for a repository, which go with the build's own tag (novox/hq issue 1834).
|
||||
type PushedNames interface {
|
||||
PushedNames(repository string) []string
|
||||
}
|
||||
|
||||
// releaseImage removes the names an image was given on the node, in one command: its layers go only with the last. It runs
|
||||
// with a context of its own, the build's may be cancelled. A name never made (the build failed before it) is no fault;
|
||||
// one that cannot be removed is said, and removal is said only when the image is gone.
|
||||
func releaseImage(ctx context.Context, run Runner, names []string, say func(step, format string, args ...any)) {
|
||||
removing, done := context.WithTimeout(context.WithoutCancel(ctx), time.Minute)
|
||||
defer done()
|
||||
if _, err := run(removing, "", "docker", append([]string{"rmi"}, names...)...); err != nil {
|
||||
if !strings.Contains(err.Error(), "No such image") {
|
||||
say("image", "the local image %s could not be removed, and goes with the week's sweep: %v", strings.Join(names, ", "), err)
|
||||
}
|
||||
return
|
||||
}
|
||||
say("image", "the local image %s is removed: the registry holds it", strings.Join(names, ", "))
|
||||
}
|
||||
|
||||
// contextFrom clones an image artifact's own build context, when it names one apart from this
|
||||
// module's own repository — a fresh tree, the same way the module's own is, keyed by artifact
|
||||
// name so two artifacts of one module naming different contexts do not collide.
|
||||
func contextFrom(ctx context.Context, run Runner, workspace, artifact, credentials string,
|
||||
from catalogue.ArtifactContext, seats map[string]string, say func(step, format string, args ...any)) (string, error) {
|
||||
from catalogue.ArtifactContext, seats map[string]string, say func(step, format string, args ...any)) (_ string, err error) {
|
||||
url, err := contextURL(from, seats)
|
||||
if err != nil {
|
||||
return "", err
|
||||
@@ -752,6 +787,12 @@ func contextFrom(ctx context.Context, run Runner, workspace, artifact, credentia
|
||||
if err := os.RemoveAll(dir); err != nil {
|
||||
return "", err
|
||||
}
|
||||
// A clone that failed half-way is no context to leave behind (novox/hq issue 1834).
|
||||
defer func() {
|
||||
if err != nil {
|
||||
os.RemoveAll(dir)
|
||||
}
|
||||
}()
|
||||
if _, err := run(ctx, workspace, "git", cloneWith(credentials, "clone", "--quiet", url, dir)...); err != nil {
|
||||
return "", fmt.Errorf("cannot clone %s: %w", url, err)
|
||||
}
|
||||
@@ -1143,6 +1184,8 @@ func one(ctx context.Context, run Runner, publish Publisher,
|
||||
src.contexts[a.Name] = t
|
||||
}
|
||||
buildDir = cloned
|
||||
// Let go of when the image is built, whatever became of it (novox/hq issue 1834).
|
||||
defer os.RemoveAll(cloned)
|
||||
if t, _ := trunkOf(ctx, run, cloned, "HEAD"); t == "" || !atTrunkHead(ctx, run, cloned, "HEAD", t) {
|
||||
src.contextOffHead()
|
||||
}
|
||||
@@ -1180,6 +1223,7 @@ func one(ctx context.Context, run Runner, publish Publisher,
|
||||
src.ownHas(paths...)
|
||||
}
|
||||
buildDir = narrowed
|
||||
defer os.RemoveAll(narrowed)
|
||||
} else if a.Context != nil {
|
||||
src.readWhole(*a.Context)
|
||||
}
|
||||
@@ -1205,6 +1249,16 @@ func one(ctx context.Context, run Runner, publish Publisher,
|
||||
}
|
||||
invocation = append(invocation, ".")
|
||||
say("image", "docker build -f %s", recipePath)
|
||||
// **The local tag goes with the build** (novox/hq issue 1834): an image published to a registry is held there, and
|
||||
// a tag per module and commit left on the node was the 96 GB of a full disk. Only a node publishing nowhere (a
|
||||
// mesh being raised) keeps it, since the local image is then the artifact.
|
||||
if !keepsImageLocally(publish) {
|
||||
names := []string{local}
|
||||
if p, ok := publish.(PushedNames); ok {
|
||||
names = append(names, p.PushedNames(module+"/"+a.Name)...)
|
||||
}
|
||||
defer releaseImage(ctx, run, names, say)
|
||||
}
|
||||
if _, err := run(ctx, buildDir, "docker", invocation...); err != nil {
|
||||
return catalogue.Built{}, fmt.Errorf("%s: building %s failed: %w", module, a.Name, err)
|
||||
}
|
||||
|
||||
@@ -38,6 +38,9 @@ type recorded struct {
|
||||
stamped time.Time
|
||||
// tree is what git names as the tree of the module's directory; empty answers as for a commit.
|
||||
tree string
|
||||
// builtFrom is the files (slash-separated, relative) of the folder the last `docker build` ran in, read as it ran:
|
||||
// the build removes that folder when it ends (novox/hq issue 1834).
|
||||
builtFrom []string
|
||||
}
|
||||
|
||||
func (r *recorded) run(_ context.Context, dir, name string, args ...string) (string, error) {
|
||||
@@ -53,6 +56,16 @@ func (r *recorded) run(_ context.Context, dir, name string, args ...string) (str
|
||||
break
|
||||
}
|
||||
}
|
||||
if name == "docker" && len(args) > 0 && args[0] == "build" {
|
||||
r.builtFrom = nil
|
||||
_ = filepath.WalkDir(dir, func(p string, d os.DirEntry, err error) error {
|
||||
if err == nil && !d.IsDir() {
|
||||
rel, _ := filepath.Rel(dir, p)
|
||||
r.builtFrom = append(r.builtFrom, filepath.ToSlash(rel))
|
||||
}
|
||||
return nil
|
||||
})
|
||||
}
|
||||
switch {
|
||||
case name == "git" && isClone:
|
||||
repository := args[len(args)-2]
|
||||
|
||||
@@ -123,8 +123,41 @@ type CheckSpec struct {
|
||||
// controller could not learn them, and the verdict says so.
|
||||
Siblings []Sibling
|
||||
SiblingsUnknown string
|
||||
// Held are the approved held values of the check's pull requests (novox/hq ADR 0502 clause 4): written to a file and
|
||||
// handed to the gate, which lays them over the change's composition only. None: no flag, no file.
|
||||
Held []HeldValue
|
||||
}
|
||||
|
||||
// HeldValue is one approved config value held for a key an open pull request introduces: the value of Key for Module on
|
||||
// Node (a machine's real name; the gate finds it in the snapshot by its pseudonym). The gate reads this document.
|
||||
type HeldValue struct {
|
||||
Pull string `json:"pull"`
|
||||
Head string `json:"head,omitempty"`
|
||||
Node string `json:"node"`
|
||||
Module string `json:"module"`
|
||||
Key string `json:"key"`
|
||||
Value json.RawMessage `json:"value"`
|
||||
Approved string `json:"approved,omitempty"`
|
||||
By string `json:"by,omitempty"`
|
||||
At string `json:"at,omitempty"`
|
||||
}
|
||||
|
||||
// writeHeld writes the held values to held.json under root and answers its path; empty, and nothing written, for none.
|
||||
func writeHeld(root string, held []HeldValue) (string, error) {
|
||||
if len(held) == 0 {
|
||||
return "", nil
|
||||
}
|
||||
raw, err := json.Marshal(held)
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
file := filepath.Join(root, "held.json")
|
||||
return file, os.WriteFile(file, raw, 0o644)
|
||||
}
|
||||
|
||||
// heldFlag is how the gate is given the held values: only when there are some, so a judge from before --held still runs.
|
||||
const heldFlag = `${MESH_CHECK_HELD:+--held "$MESH_CHECK_HELD"}`
|
||||
|
||||
// Sibling is one other open pull request of a delivery group (novox/hq ADR 0382): the repository it is in as
|
||||
// owner/repo, its number, its whole head, the branch it merges into, and Dir, the directory the check finds that
|
||||
// repository under beside it (an entry of Beside).
|
||||
@@ -272,6 +305,8 @@ const (
|
||||
// EnvGroup is a delivery group's other heads, as JSON, for the gate (novox/hq ADR 0239); empty for a
|
||||
// pull request checked alone.
|
||||
EnvGroup = "MESH_CHECK_GROUP"
|
||||
// EnvHeld is the file of the approved held values of the check's pull requests (novox/hq ADR 0502); empty for none.
|
||||
EnvHeld = "MESH_CHECK_HELD"
|
||||
// EnvTests is a `go test -run` pattern and EnvStoreOnly is 1 when a branch tried before its pull request
|
||||
// asks for only those tests, or only the store tests (novox/hq issue 686). Never set for a pull request's
|
||||
// check. A script that reads neither runs whole.
|
||||
@@ -357,6 +392,12 @@ func Check(ctx context.Context, run Runner, spec CheckSpec, workspace, registry
|
||||
ctx, stop := context.WithTimeout(ctx, CheckTimeout)
|
||||
defer stop()
|
||||
|
||||
// **A node with no room takes no check** (novox/hq issue 1834): said as the check's verdict, never a throwaway store
|
||||
// that dies at once on a full disk.
|
||||
if err := RoomToWork("/", workspace); err != nil {
|
||||
say("check", "refused: %v", err)
|
||||
return CheckVerdict{}, err
|
||||
}
|
||||
root := filepath.Join(workspace, "check")
|
||||
if err := os.RemoveAll(root); err != nil {
|
||||
return CheckVerdict{}, err
|
||||
@@ -572,6 +613,15 @@ func Check(ctx context.Context, run Runner, spec CheckSpec, workspace, registry
|
||||
}
|
||||
}
|
||||
|
||||
// The approved held values of the check's pull requests, for the gate (novox/hq ADR 0502 clause 4).
|
||||
heldFile, err := writeHeld(root, spec.Held)
|
||||
if err != nil {
|
||||
return CheckVerdict{}, err
|
||||
}
|
||||
if heldFile != "" {
|
||||
say("check", "with %d config value(s) held for its pull request(s)", len(spec.Held))
|
||||
}
|
||||
|
||||
// Every clone is made: the credential is gone before anything of the check runs (novox/hq issue 462).
|
||||
forget()
|
||||
|
||||
@@ -733,7 +783,7 @@ func Check(ctx context.Context, run Runner, spec CheckSpec, workspace, registry
|
||||
EnvTestStore + "=" + storeURL, EnvTestBus + "=nats://" + bus, EnvRepository + "=" + spec.Owner + "/" + spec.Repo,
|
||||
EnvBeside + "=" + root,
|
||||
EnvModules + "=" + strings.Join(append(append([]string{}, spec.Modules...), spec.New...), ","),
|
||||
EnvGroup + "=" + groupFile,
|
||||
EnvGroup + "=" + groupFile, EnvHeld + "=" + heldFile,
|
||||
"GOCACHE=" + filepath.Join(workspace, "go-cache"), "GOMODCACHE=" + filepath.Join(workspace, "go-modules")}
|
||||
env = append(env, changedEnv...)
|
||||
env = append(env, selection(spec)...)
|
||||
@@ -1100,7 +1150,7 @@ func gateLayer(ctx context.Context, spec CheckSpec, tree, root, gate, verdictFil
|
||||
if err := running(inToolchain(tree, append(env, EnvVerdict+"="+verdictFile), "sh", "-c",
|
||||
`"$MESH_GATE" merge-gate --facts "$MESH_FACTS" --store "$MESH_GATE_POSTGRES" `+
|
||||
`--repository "$MESH_CHECK_REPOSITORY" --tree . `+gateChangedFlag(env)+` `+
|
||||
`${MESH_CHECK_GROUP:+--group "$MESH_CHECK_GROUP"} --json > "$MESH_CHECK_VERDICT"`)); err != nil {
|
||||
`${MESH_CHECK_GROUP:+--group "$MESH_CHECK_GROUP"} `+heldFlag+` --json > "$MESH_CHECK_VERDICT"`)); err != nil {
|
||||
if ctx.Err() != nil {
|
||||
return "error", "the check was ended during the merge gate"
|
||||
}
|
||||
@@ -1587,7 +1637,9 @@ func BusImage(version string) string {
|
||||
|
||||
// throwaway starts a container publishing one port on loopback, and answers where it is reached.
|
||||
func throwaway(ctx context.Context, run, plain Runner, name, image string, port int, opts, args []string) (string, error) {
|
||||
invocation := []string{"run", "-d", "--rm", "--name", name, "-p", fmt.Sprintf("127.0.0.1::%d", port)}
|
||||
// Never with --rm (novox/hq issue 1834): a store that dies at once took its log with it. The check removes what it
|
||||
// raised, with its volumes, after it has read why one stopped (RemoveContainersOf).
|
||||
invocation := []string{"run", "-d", "--name", name, "-p", fmt.Sprintf("127.0.0.1::%d", port)}
|
||||
invocation = append(invocation, opts...)
|
||||
invocation = append(invocation, image)
|
||||
invocation = append(invocation, args...)
|
||||
@@ -1608,17 +1660,45 @@ func throwaway(ctx context.Context, run, plain Runner, name, image string, port
|
||||
|
||||
// waitFor runs a readiness command in a container until it answers, for a minute.
|
||||
func waitFor(ctx context.Context, run Runner, name string, ready []string) error {
|
||||
for i := 0; i < 60; i++ {
|
||||
return waitReady(ctx, run, name, ready, 60)
|
||||
}
|
||||
|
||||
// waitReady is waitFor for a number of tries, a second apart. A container that never answers is not left a mystery
|
||||
// (novox/hq issue 1834): its state and exit code and the last 20 lines of its log are in the error, read before the
|
||||
// check removes it.
|
||||
func waitReady(ctx context.Context, run Runner, name string, ready []string, attempts int) error {
|
||||
for i := 0; i < attempts; i++ {
|
||||
if _, err := run(ctx, "", "docker", append([]string{"exec", name}, ready...)...); err == nil {
|
||||
return nil
|
||||
}
|
||||
if i == attempts-1 {
|
||||
break
|
||||
}
|
||||
select {
|
||||
case <-ctx.Done():
|
||||
return ctx.Err()
|
||||
case <-time.After(time.Second):
|
||||
}
|
||||
}
|
||||
return fmt.Errorf("%s never became ready", name)
|
||||
return fmt.Errorf("%s never became ready%s", name, whyItStopped(ctx, run, name))
|
||||
}
|
||||
|
||||
// whyItStopped is ": <state>, exit code N; its last log lines: …" for a container, or "" when docker says nothing.
|
||||
func whyItStopped(ctx context.Context, run Runner, name string) string {
|
||||
reading, done := context.WithTimeout(context.WithoutCancel(ctx), 30*time.Second)
|
||||
defer done()
|
||||
var said []string
|
||||
if out, err := run(reading, "", "docker", "inspect", "--format",
|
||||
"{{.State.Status}}, exit code {{.State.ExitCode}}", name); err == nil && strings.TrimSpace(out) != "" {
|
||||
said = append(said, strings.TrimSpace(out))
|
||||
}
|
||||
if out, err := run(reading, "", "docker", "logs", "--tail", "20", name); err == nil && strings.TrimSpace(out) != "" {
|
||||
said = append(said, "its last log lines: "+strings.TrimSpace(out))
|
||||
}
|
||||
if len(said) == 0 {
|
||||
return ""
|
||||
}
|
||||
return ": " + strings.Join(said, "; ")
|
||||
}
|
||||
|
||||
// dialable waits for an address to take a connection, for a minute.
|
||||
|
||||
@@ -0,0 +1,33 @@
|
||||
package builder
|
||||
|
||||
import (
|
||||
"os"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
"testing"
|
||||
)
|
||||
|
||||
// 1826/AC2: the held values are written whole to held.json, and the gate is given the flag only when there are some.
|
||||
func TestHeldValuesAreWrittenForTheGateAndNoneWriteNothing(t *testing.T) {
|
||||
root := t.TempDir()
|
||||
if file, err := writeHeld(root, nil); err != nil || file != "" {
|
||||
t.Fatalf("none wrote %q %v", file, err)
|
||||
}
|
||||
if _, err := os.Stat(filepath.Join(root, "held.json")); err == nil {
|
||||
t.Fatal("none wrote a file")
|
||||
}
|
||||
file, err := writeHeld(root, []HeldValue{{Pull: "novox/mesh-catalog#434", Node: "ace", Module: "n8n", Key: "media-gid",
|
||||
Value: []byte("2000"), Approved: "the operator"}})
|
||||
if err != nil || file != filepath.Join(root, "held.json") {
|
||||
t.Fatalf("wrote %q %v", file, err)
|
||||
}
|
||||
raw, _ := os.ReadFile(file)
|
||||
for _, want := range []string{`"node":"ace"`, `"module":"n8n"`, `"key":"media-gid"`, `"value":2000`} {
|
||||
if !strings.Contains(string(raw), want) {
|
||||
t.Fatalf("%s lacks %s", raw, want)
|
||||
}
|
||||
}
|
||||
if !strings.Contains(heldFlag, `--held "$MESH_CHECK_HELD"`) || !strings.HasPrefix(heldFlag, "${MESH_CHECK_HELD:+") {
|
||||
t.Fatalf("the flag is %s", heldFlag)
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,216 @@
|
||||
package builder
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
"testing"
|
||||
)
|
||||
|
||||
// Issue 1834: a build node's root disk filled and every check there ended "the store never became ready". A node
|
||||
// frees what each build and check leaves, refuses to take work under a floor of free space, and a store that does
|
||||
// not come up says why.
|
||||
|
||||
func init() {
|
||||
// The disk the tests run on is none of their business; the tests of the floor say their own.
|
||||
FreeBytes = func(string) (uint64, error) { return 500 << 30, nil }
|
||||
}
|
||||
|
||||
func withFree(t *testing.T, bytes uint64) {
|
||||
t.Helper()
|
||||
was := FreeBytes
|
||||
FreeBytes = func(string) (uint64, error) { return bytes, nil }
|
||||
t.Cleanup(func() { FreeBytes = was })
|
||||
}
|
||||
|
||||
// 1834/AC2: given 3 GiB free, when a check or a build is asked, then it refuses at once, saying so, running nothing.
|
||||
func TestACheckUnderTheFloorOfFreeSpaceRefusesSayingSo(t *testing.T) {
|
||||
withFree(t, 3<<30)
|
||||
var ran []string
|
||||
run := func(_ context.Context, _ string, name string, args ...string) (string, error) {
|
||||
ran = append(ran, name+" "+strings.Join(args, " "))
|
||||
return "", nil
|
||||
}
|
||||
_, err := Check(context.Background(), run, CheckSpec{ID: "build-1"}, t.TempDir(), "registry.invalid", GitCredential{}, nil)
|
||||
if err == nil || !strings.Contains(err.Error(), "the build node has 3 GiB free on /, under the floor of 20 GiB") {
|
||||
t.Fatalf("a check on a full disk said %v", err)
|
||||
}
|
||||
if len(ran) != 0 {
|
||||
t.Errorf("a refused check ran %v", ran)
|
||||
}
|
||||
}
|
||||
|
||||
func TestABuildUnderTheFloorOfFreeSpaceRefusesSayingSo(t *testing.T) {
|
||||
withFree(t, 3<<30)
|
||||
r := &recorded{}
|
||||
_, err := Build(context.Background(), r.run, r, "https://forge.invalid/x.git", "", "", t.TempDir(), nil, Npmrc{}, GitCredential{}, nil)
|
||||
if err == nil || !strings.Contains(err.Error(), "under the floor of 20 GiB") {
|
||||
t.Fatalf("a build on a full disk said %v", err)
|
||||
}
|
||||
if len(r.ran) != 0 {
|
||||
t.Errorf("a refused build ran %v", r.ran)
|
||||
}
|
||||
}
|
||||
|
||||
// The workspace's filesystem is read too, and a workspace not made yet is read at its nearest folder.
|
||||
func TestTheWorkspacesFilesystemIsReadToo(t *testing.T) {
|
||||
was := FreeBytes
|
||||
t.Cleanup(func() { FreeBytes = was })
|
||||
missing := filepath.Join(t.TempDir(), "not", "yet")
|
||||
FreeBytes = func(p string) (uint64, error) {
|
||||
if p == "/" {
|
||||
return 100 << 30, nil
|
||||
}
|
||||
if _, err := os.Stat(p); err != nil {
|
||||
t.Errorf("read the free space of %s, which is not there", p)
|
||||
}
|
||||
return 1 << 30, nil
|
||||
}
|
||||
err := RoomToWork("/", missing)
|
||||
if err == nil || !strings.Contains(err.Error(), "1 GiB free on "+missing) {
|
||||
t.Errorf("the workspace's disk, under the floor, said %v", err)
|
||||
}
|
||||
FreeBytes = func(string) (uint64, error) { return 0, errors.New("no") }
|
||||
if RoomToWork("/") == nil {
|
||||
t.Error("a disk that cannot be read was taken as having room")
|
||||
}
|
||||
}
|
||||
|
||||
// 1834/AC3: given a store that stops at once, when the check waits for it, then its exit code and last log lines are
|
||||
// in the error and the container is removed afterwards, not by --rm before anyone could read it.
|
||||
func TestAStoreThatDiesSaysWhyItDied(t *testing.T) {
|
||||
var ran []string
|
||||
run := func(_ context.Context, _ string, name string, args ...string) (string, error) {
|
||||
line := name + " " + strings.Join(args, " ")
|
||||
ran = append(ran, line)
|
||||
switch {
|
||||
case args[0] == "exec":
|
||||
return "", errors.New("Error response from daemon: container is not running")
|
||||
case args[0] == "inspect":
|
||||
return "exited exit code 1\n", nil
|
||||
case args[0] == "logs":
|
||||
return "initdb: error: could not create directory: No space left on device\n", nil
|
||||
}
|
||||
return "", nil
|
||||
}
|
||||
err := waitReady(context.Background(), run, "build-1-store", []string{"pg_isready"}, 1)
|
||||
for _, want := range []string{"build-1-store never became ready", "exit code 1", "No space left on device"} {
|
||||
if err == nil || !strings.Contains(err.Error(), want) {
|
||||
t.Errorf("the verdict %q lacks %q", err, want)
|
||||
}
|
||||
}
|
||||
logs := ""
|
||||
for _, l := range ran {
|
||||
if strings.HasPrefix(l, "docker logs") {
|
||||
logs = l
|
||||
}
|
||||
}
|
||||
if logs != "docker logs --tail 20 build-1-store" {
|
||||
t.Errorf("the log was read as %q", logs)
|
||||
}
|
||||
}
|
||||
|
||||
func TestTheThrowawayStoreIsNotStartedWithRm(t *testing.T) {
|
||||
var started []string
|
||||
run := func(_ context.Context, _ string, name string, args ...string) (string, error) {
|
||||
if args[0] == "run" {
|
||||
started = args
|
||||
}
|
||||
return "127.0.0.1:40000\n", nil
|
||||
}
|
||||
if _, err := throwaway(context.Background(), run, run, "build-1-store", "postgres:17-alpine", 5432, nil, nil); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
for _, a := range started {
|
||||
if a == "--rm" {
|
||||
t.Errorf("started with --rm, which erases why it died: %v", started)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// 1834/AC1: given an image built for a check or a walk and published to the registry, when the build ends, then the
|
||||
// local image tag, the narrowed source and the context clone it left are gone; an image published nowhere (a mesh
|
||||
// being raised) is kept, since it is the artifact.
|
||||
// pushedNamed is a publisher that tags the image as <registry>/<repository> to push it, as the registry one does.
|
||||
type pushedNamed struct{ *recorded }
|
||||
|
||||
func (pushedNamed) PushedNames(repository string) []string {
|
||||
return []string{"registry.invalid/" + repository}
|
||||
}
|
||||
|
||||
func TestABuildRemovesWhatItLeftOnTheNode(t *testing.T) {
|
||||
r := &recorded{
|
||||
contents: map[string]string{"modules/m/" + ManifestName: anImageWithAContext, "modules/m/Dockerfile": "FROM scratch\n"},
|
||||
secondary: map[string]map[string]string{"https://forge.invalid/ctl.git": {"go.mod": "module x\n"}},
|
||||
}
|
||||
workspace := t.TempDir()
|
||||
if _, err := Build(context.Background(), r.run, pushedNamed{r}, "https://forge.invalid/c.git", "modules/m", "", workspace, nil, Npmrc{},
|
||||
GitCredential{}, nil); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
// Both names go in one rmi: the layers stay while either is left (the push tagged the image with the registry's).
|
||||
if !strings.Contains(strings.Join(r.ran, "\n"), "docker rmi m-server:c0ffeec0 registry.invalid/m/server") {
|
||||
t.Errorf("the image built for it and its pushed name were not removed: %v", r.ran)
|
||||
}
|
||||
left, _ := filepath.Glob(filepath.Join(workspace, "*"))
|
||||
if len(left) != 0 {
|
||||
t.Errorf("the build left %v in its workspace", left)
|
||||
}
|
||||
}
|
||||
|
||||
const anImageWithAContext = `{"module":"m","version":"1",
|
||||
"build":{"artifacts":[{"name":"server","kind":"image","from":"Dockerfile",
|
||||
"context":{"repository":"https://forge.invalid/ctl.git","ref":"main"}}]}}`
|
||||
|
||||
func TestAnImageKeptLocallyIsNotRemoved(t *testing.T) {
|
||||
r := &recorded{contents: map[string]string{"modules/m/" + ManifestName: anImageWithAContext, "modules/m/Dockerfile": "FROM scratch\n"}}
|
||||
local := Local{Run: func(ctx context.Context, dir, name string, args ...string) (string, error) {
|
||||
if args[0] == "image" {
|
||||
return "sha256:" + strings.Repeat("a", 64) + "\n", nil
|
||||
}
|
||||
return r.run(ctx, dir, name, args...)
|
||||
}}
|
||||
if _, err := Build(context.Background(), local.Run, local, "https://forge.invalid/c.git", "modules/m", "", t.TempDir(), nil, Npmrc{},
|
||||
GitCredential{}, nil); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if strings.Contains(strings.Join(r.ran, "\n"), "docker rmi") {
|
||||
t.Errorf("the artifact of a mesh being raised was removed: %v", r.ran)
|
||||
}
|
||||
}
|
||||
|
||||
// The held image the comparison pulls to read is let go of once read.
|
||||
func TestTheHeldImageAComparisonPullsIsRemovedAfterReading(t *testing.T) {
|
||||
var ran []string
|
||||
run := func(_ context.Context, _ string, name string, args ...string) (string, error) {
|
||||
ran = append(ran, name+" "+strings.Join(args, " "))
|
||||
if args[0] == "create" {
|
||||
return "abcdef0123456789\n", nil
|
||||
}
|
||||
if args[0] == "image" {
|
||||
return "", errors.New("stop here")
|
||||
}
|
||||
return "", nil
|
||||
}
|
||||
_, _ = imageContent(context.Background(), run, t.TempDir(), "reg.invalid/m/server@sha256:"+strings.Repeat("a", 64))
|
||||
if got := ran[len(ran)-1]; !strings.HasPrefix(got, "docker rmi reg.invalid/m/server@sha256:") {
|
||||
t.Errorf("the last command was %q, not the removal of the pulled image: %v", got, ran)
|
||||
}
|
||||
}
|
||||
|
||||
func TestAnImageThatCannotBeRemovedIsNotSaidRemoved(t *testing.T) {
|
||||
var said []string
|
||||
run := func(context.Context, string, string, ...string) (string, error) {
|
||||
return "", errors.New("image is being used")
|
||||
}
|
||||
releaseImage(context.Background(), run, []string{"a:1"}, func(step, format string, args ...any) {
|
||||
said = append(said, format)
|
||||
})
|
||||
for _, s := range said {
|
||||
if strings.Contains(s, "is removed") {
|
||||
t.Errorf("said removed: %q", s)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,46 @@
|
||||
package builder
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"syscall"
|
||||
)
|
||||
|
||||
// FreeSpaceFloor is the free space a build node must have, on / and on its workspace's filesystem, before it takes
|
||||
// a build or a check (novox/hq issue 1834): under it, a throwaway store cannot initialise its data directory and
|
||||
// dies at once, and the check ended "never became ready" instead of saying the disk was full.
|
||||
const FreeSpaceFloor = 20 << 30
|
||||
|
||||
// FreeBytes reads the bytes an unprivileged writer can still use on the filesystem holding path. A variable so a
|
||||
// test answers for a disk it does not have.
|
||||
var FreeBytes = func(path string) (uint64, error) {
|
||||
var s syscall.Statfs_t
|
||||
if err := syscall.Statfs(path, &s); err != nil {
|
||||
return 0, err
|
||||
}
|
||||
return s.Bavail * uint64(s.Bsize), nil
|
||||
}
|
||||
|
||||
// RoomToWork refuses, saying how much is free, when any of the paths' filesystems is under FreeSpaceFloor. A path
|
||||
// that does not exist yet (a workspace not made) is read at its nearest folder that does.
|
||||
func RoomToWork(paths ...string) error {
|
||||
for _, p := range paths {
|
||||
at := p
|
||||
for {
|
||||
if _, err := os.Stat(at); err == nil || filepath.Dir(at) == at {
|
||||
break
|
||||
}
|
||||
at = filepath.Dir(at)
|
||||
}
|
||||
free, err := FreeBytes(at)
|
||||
if err != nil {
|
||||
return fmt.Errorf("the free space on %s cannot be read: %w", p, err)
|
||||
}
|
||||
if free < FreeSpaceFloor {
|
||||
return fmt.Errorf("the build node has %d GiB free on %s, under the floor of %d GiB",
|
||||
free>>30, p, FreeSpaceFloor>>30)
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
@@ -172,11 +172,11 @@ func TestANarrowedTreeHoldsTheBuildSourceAndNothingElse(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// This repository's own programs: the route proxy's build source is not the controller's, and neither
|
||||
// holds the other's command.
|
||||
// This repository's own programs: the route proxy lives in its module's own Go module, so its build source is
|
||||
// not the controller's, and neither holds the other's command.
|
||||
func TestThisRepositorysProgramsHaveBuildSourcesOfTheirOwn(t *testing.T) {
|
||||
root := filepath.Join("..", "..")
|
||||
proxy, err := GoBuildSource(root, "examples/route-proxy")
|
||||
proxy, err := GoBuildSource(filepath.Join(root, "modules", "route-proxy"), "cmd/route-proxy")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
@@ -194,15 +194,15 @@ func TestThisRepositorysProgramsHaveBuildSourcesOfTheirOwn(t *testing.T) {
|
||||
file string
|
||||
held bool
|
||||
}{
|
||||
{proxy, "the route proxy", "examples/route-proxy/main.go", true},
|
||||
{proxy, "the route proxy", "internal/broker/broker.go", true},
|
||||
{proxy, "the route proxy", "cmd/mesh-controller/main.go", false},
|
||||
{proxy, "the route proxy", "internal/conditions/condition.go", false},
|
||||
{proxy, "the route proxy", "cmd/route-proxy/main.go", true},
|
||||
{proxy, "the route proxy", "cmd/route-proxy/bus.go", true},
|
||||
{proxy, "the route proxy", "go.mod", true},
|
||||
{proxy, "the route proxy", "cmd/route-provider/main.go", false},
|
||||
{proxy, "the route proxy", "README.md", false},
|
||||
{controller, "the controller", "cmd/mesh-controller/main.go", true},
|
||||
{controller, "the controller", "internal/conditions/condition.go", true},
|
||||
{controller, "the controller", "internal/inventory/migrations/0001-nodes.sql", true},
|
||||
{controller, "the controller", "examples/route-proxy/main.go", false},
|
||||
{controller, "the controller", "modules/route-proxy/cmd/route-proxy/main.go", false},
|
||||
{controller, "the controller", "cmd/mesh-builder/main.go", false},
|
||||
{controller, "the controller", "README.md", false},
|
||||
{builder, "the build seat's program", "cmd/mesh-builder/main.go", true},
|
||||
|
||||
@@ -3,6 +3,7 @@ package builder
|
||||
import (
|
||||
"context"
|
||||
"os/exec"
|
||||
"regexp"
|
||||
"strings"
|
||||
"syscall"
|
||||
"time"
|
||||
@@ -41,6 +42,11 @@ func inItsOwnGroup(cmd *exec.Cmd) {
|
||||
cmd.WaitDelay = KillWait
|
||||
}
|
||||
|
||||
// CgroupParent is the slice every container a build or check starts joins (novox/hq issue 1798), so the node's own
|
||||
// weights and cap bind it: the build-agent module declares the slice with the machine's CPU weight, IO weight and
|
||||
// memory limits, and names it in MESH_BUILD_CGROUP_PARENT. Empty, a container joins the runtime's default.
|
||||
var CgroupParent string
|
||||
|
||||
// Labelled is a Runner that marks every container a build starts with the build's id, so a kill
|
||||
// finds what outlived the docker client (novox/hq ADR 0219). Applied at the one place every command
|
||||
// passes rather than at each `docker run` the builder composes: a run added later is labelled too.
|
||||
@@ -55,8 +61,11 @@ func LabelledArgs(name string, args []string, id string) []string {
|
||||
if name != "docker" || len(args) == 0 || args[0] != "run" || id == "" {
|
||||
return args
|
||||
}
|
||||
out := make([]string, 0, len(args)+2)
|
||||
out := make([]string, 0, len(args)+4)
|
||||
out = append(out, "run", "--label", BuildLabel+"="+id)
|
||||
if CgroupParent != "" {
|
||||
out = append(out, "--cgroup-parent", CgroupParent)
|
||||
}
|
||||
return append(out, args[1:]...)
|
||||
}
|
||||
|
||||
@@ -71,12 +80,45 @@ func RemoveContainersOf(ctx context.Context, run Runner, id string) (int, error)
|
||||
if len(ids) == 0 {
|
||||
return 0, nil
|
||||
}
|
||||
if _, err := run(ctx, "", "docker", append([]string{"rm", "-f"}, ids...)...); err != nil {
|
||||
if err := removeWithVolumes(ctx, run, ids); err != nil {
|
||||
return 0, err
|
||||
}
|
||||
return len(ids), nil
|
||||
}
|
||||
|
||||
// MountedVolumes is the template `docker inspect --format` reads the names of a container's volumes with.
|
||||
const MountedVolumes = `{{range .Mounts}}{{if eq .Type "volume"}}{{println .Name}}{{end}}{{end}}`
|
||||
|
||||
// anonymousVolume is the name docker gives a volume it makes for an image's VOLUME line: 64 hex digits.
|
||||
var anonymousVolume = regexp.MustCompile(`^[0-9a-f]{64}$`)
|
||||
|
||||
// removeWithVolumes removes containers together with their anonymous volumes (novox/hq issue 1772). A throwaway
|
||||
// store declares its data directory a VOLUME, docker makes an anonymous volume for it, and `docker rm -f`
|
||||
// without -v leaves that volume for ever: 1,629 of them, 107 GB, on one build node. So the volumes the
|
||||
// containers mount are read first, the containers are removed with -v, and an anonymous volume still there
|
||||
// afterwards is removed by name. Only a volume one of these containers mounted, and only one with an anonymous
|
||||
// volume's name, is touched: a named volume — an operator's own data — never is. A volume already gone is
|
||||
// no failure.
|
||||
func removeWithVolumes(ctx context.Context, run Runner, ids []string) error {
|
||||
var volumes []string
|
||||
if out, err := run(ctx, "", "docker", append([]string{"inspect", "--format", MountedVolumes}, ids...)...); err == nil {
|
||||
seen := map[string]bool{}
|
||||
for _, name := range strings.Fields(out) {
|
||||
if anonymousVolume.MatchString(name) && !seen[name] {
|
||||
seen[name] = true
|
||||
volumes = append(volumes, name)
|
||||
}
|
||||
}
|
||||
}
|
||||
if _, err := run(ctx, "", "docker", append([]string{"rm", "-f", "-v"}, ids...)...); err != nil {
|
||||
return err
|
||||
}
|
||||
if len(volumes) > 0 {
|
||||
_, _ = run(ctx, "", "docker", append([]string{"volume", "rm"}, volumes...)...)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// A holder that stops mid-build leaves its containers running (novox/hq issue 306).
|
||||
//
|
||||
// A build's containers are removed by the build itself, by a kill, or by the next delivery of the same
|
||||
@@ -106,7 +148,7 @@ func RemoveLeftBehind(ctx context.Context, run Runner) (int, error) {
|
||||
if len(ids) == 0 {
|
||||
return 0, nil
|
||||
}
|
||||
if _, err := run(ctx, "", "docker", append([]string{"rm", "-f"}, ids...)...); err != nil {
|
||||
if err := removeWithVolumes(ctx, run, ids); err != nil {
|
||||
return 0, err
|
||||
}
|
||||
return len(ids), nil
|
||||
|
||||
@@ -2,6 +2,7 @@ package builder
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"reflect"
|
||||
"strings"
|
||||
"testing"
|
||||
@@ -49,7 +50,8 @@ func TestAKillRemovesTheContainersLabelledWithTheBuild(t *testing.T) {
|
||||
if err != nil || n != 2 {
|
||||
t.Fatalf("%d %v", n, err)
|
||||
}
|
||||
if want := []string{"docker ps -aq --filter label=mesh.build=build-3", "docker rm -f c1 c2"}; !reflect.DeepEqual(ran, want) {
|
||||
if want := []string{"docker ps -aq --filter label=mesh.build=build-3", "docker inspect --format " + MountedVolumes + " c1 c2",
|
||||
"docker rm -f -v c1 c2"}; !reflect.DeepEqual(ran, want) {
|
||||
t.Errorf("ran %v", ran)
|
||||
}
|
||||
}
|
||||
@@ -73,7 +75,7 @@ func TestAStartingHolderRemovesWhatEarlierHoldersLeftAndNothingElse(t *testing.T
|
||||
if n != 3 {
|
||||
t.Errorf("removed %d", n)
|
||||
}
|
||||
if len(ran) != 2 || !reflect.DeepEqual(ran[1], []string{"docker", "rm", "-f", "c1", "c2", "c7"}) {
|
||||
if len(ran) != 3 || !reflect.DeepEqual(ran[2], []string{"docker", "rm", "-f", "-v", "c1", "c2", "c7"}) {
|
||||
t.Fatalf("ran %v", ran)
|
||||
}
|
||||
if !strings.Contains(strings.Join(ran[0], " "), "--filter label=mesh.build") {
|
||||
@@ -90,3 +92,75 @@ func TestAStartingHolderRemovesWhatEarlierHoldersLeftAndNothingElse(t *testing.T
|
||||
t.Errorf("with nothing of the seat's: %d %v %v", n, err, ran)
|
||||
}
|
||||
}
|
||||
|
||||
// **Issue 1772**: a throwaway store declares its data directory a VOLUME, so docker makes an anonymous volume for
|
||||
// it, and `docker rm -f` without -v leaves that volume behind (1,629 of them, 107 GB, on one build node). Every
|
||||
// container a build or check removes is removed with its anonymous volumes (-v), and any volume the container
|
||||
// mounted that is still there afterwards is removed by name — those, and only those, never a named volume.
|
||||
func TestARemovedContainerTakesItsAnonymousVolumesWithIt(t *testing.T) {
|
||||
anon := strings.Repeat("a", 64)
|
||||
other := strings.Repeat("b", 64)
|
||||
var ran []string
|
||||
run := func(_ context.Context, _ string, name string, args ...string) (string, error) {
|
||||
ran = append(ran, name+" "+strings.Join(args, " "))
|
||||
switch args[0] {
|
||||
case "ps":
|
||||
return "c1\n", nil
|
||||
case "inspect":
|
||||
return anon + "\n" + "compose_data\n" + other + "\n", nil
|
||||
}
|
||||
return "", nil
|
||||
}
|
||||
if n, err := RemoveContainersOf(context.Background(), run, "build-4"); err != nil || n != 1 {
|
||||
t.Fatalf("%d %v", n, err)
|
||||
}
|
||||
last := ran[len(ran)-1]
|
||||
if want := "docker volume rm " + anon + " " + other; last != want {
|
||||
t.Errorf("last command %q, want %q", last, want)
|
||||
}
|
||||
if !strings.Contains(strings.Join(ran, "\n"), "docker rm -f -v c1") {
|
||||
t.Errorf("ran %v", ran)
|
||||
}
|
||||
if strings.Contains(last, "compose_data") {
|
||||
t.Errorf("a named volume was removed: %q", last)
|
||||
}
|
||||
}
|
||||
|
||||
// A volume already gone when the sweep looks (rm -v took it) is no failure.
|
||||
func TestAVolumeAlreadyGoneIsNoFailure(t *testing.T) {
|
||||
run := func(_ context.Context, _ string, name string, args ...string) (string, error) {
|
||||
switch args[0] {
|
||||
case "ps":
|
||||
return "c1\n", nil
|
||||
case "inspect":
|
||||
return strings.Repeat("c", 64) + "\n", nil
|
||||
case "volume":
|
||||
return "", errors.New("no such volume")
|
||||
}
|
||||
return "", nil
|
||||
}
|
||||
if n, err := RemoveContainersOf(context.Background(), run, "build-5"); err != nil || n != 1 {
|
||||
t.Fatalf("%d %v", n, err)
|
||||
}
|
||||
}
|
||||
|
||||
// A node's build slice limits everything a build or check starts (novox/hq issue 1798): with a parent
|
||||
// set, every `docker run` joins it, so the node's CPU and IO weights and memory cap bind the container;
|
||||
// with none set the arguments are as they always were.
|
||||
func TestEveryContainerJoinsTheNodesBuildSlice(t *testing.T) {
|
||||
was := CgroupParent
|
||||
defer func() { CgroupParent = was }()
|
||||
CgroupParent = "meshbuild.slice"
|
||||
got := LabelledArgs("docker", []string{"run", "--rm", "img", "sh"}, "build-1")
|
||||
want := []string{"run", "--label", "mesh.build=build-1", "--cgroup-parent", "meshbuild.slice", "--rm", "img", "sh"}
|
||||
if !reflect.DeepEqual(got, want) {
|
||||
t.Errorf("1798/AC1: docker run became %v", got)
|
||||
}
|
||||
if got := LabelledArgs("docker", []string{"build", "."}, "build-1"); !reflect.DeepEqual(got, []string{"build", "."}) {
|
||||
t.Errorf("a docker build became %v", got)
|
||||
}
|
||||
CgroupParent = ""
|
||||
if got := LabelledArgs("docker", []string{"run", "img"}, "build-1"); !reflect.DeepEqual(got, []string{"run", "--label", "mesh.build=build-1", "img"}) {
|
||||
t.Errorf("1798/AC1: with no slice, docker run became %v", got)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -43,6 +43,11 @@ type Registry struct {
|
||||
HTTP *http.Client
|
||||
}
|
||||
|
||||
// PushedNames are the names PublishImage leaves the image under on the node.
|
||||
func (r Registry) PushedNames(repository string) []string {
|
||||
return []string{r.Address + "/" + repository}
|
||||
}
|
||||
|
||||
// PublishImage pushes a locally built image and returns a reference pinned by digest.
|
||||
//
|
||||
// The digest is read back from the registry's own answer rather than computed here. What matters
|
||||
@@ -59,15 +64,35 @@ func (r Registry) PublishImage(ctx context.Context, localTag, repository string)
|
||||
}); err != nil {
|
||||
return "", err
|
||||
}
|
||||
out, err := r.Run(ctx, "", "docker", "inspect", "--format", "{{index .RepoDigests 0}}", remote)
|
||||
// Every digest the daemon lists for the image, one per line: the image may have been pushed under other names before
|
||||
// (a check's scratch copy, another registry), and the first of them is not the one this push made (novox/hq issue
|
||||
// 1742: a build recorded a digest the store never held).
|
||||
out, err := r.Run(ctx, "", "docker", "inspect", "--format", "{{range .RepoDigests}}{{println .}}{{end}}", remote)
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("pushed %s and cannot read back what it was pinned as: %w", remote, err)
|
||||
}
|
||||
pinned := strings.TrimSpace(out)
|
||||
if !strings.Contains(pinned, "@sha256:") {
|
||||
first, pinned := "", ""
|
||||
for _, line := range strings.Split(out, "\n") {
|
||||
line = strings.TrimSpace(line)
|
||||
if line == "" {
|
||||
continue
|
||||
}
|
||||
if first == "" {
|
||||
first = line
|
||||
}
|
||||
if strings.HasPrefix(line, remote+"@sha256:") {
|
||||
pinned = line
|
||||
break
|
||||
}
|
||||
}
|
||||
if pinned == "" {
|
||||
if strings.Contains(first, "@sha256:") {
|
||||
return "", fmt.Errorf("pushed %s, but the daemon lists no digest for that name (only %q): the digest of another "+
|
||||
"repository is not what this registry serves", remote, first)
|
||||
}
|
||||
// A tag is not a pin. It can be made to point at something else, and this file is applied
|
||||
// on machines with no mesh to ask about anything (novox/hq ADR 0006).
|
||||
return "", fmt.Errorf("%s came back as %q, which is not pinned by digest", remote, pinned)
|
||||
return "", fmt.Errorf("%s came back as %q, which is not pinned by digest", remote, first)
|
||||
}
|
||||
return pinned, nil
|
||||
}
|
||||
|
||||
@@ -252,3 +252,32 @@ func TestAPushedImageComesBackPinned(t *testing.T) {
|
||||
t.Fatalf("it did not tag and then push: %v", ran)
|
||||
}
|
||||
}
|
||||
|
||||
// 1742: an image pushed under other names before lists their digests too, and the digest recorded is the one of the name
|
||||
// this push made — never the first listed, which may be another repository's.
|
||||
func TestThePinnedDigestIsTheOneOfTheNamePushed(t *testing.T) {
|
||||
want := "registry.invalid/shell/server@sha256:" + strings.Repeat("b", 64)
|
||||
earlier := "registry.invalid/scratch/shell/server@sha256:" + strings.Repeat("a", 64)
|
||||
r := Registry{Address: "registry.invalid", Run: func(
|
||||
_ context.Context, _, name string, args ...string) (string, error) {
|
||||
if name == "docker" && len(args) > 0 && args[0] == "inspect" {
|
||||
return earlier + "\n" + want + "\n", nil
|
||||
}
|
||||
return "", nil
|
||||
}}
|
||||
got, err := r.PublishImage(context.Background(), "local", "shell/server")
|
||||
if err != nil || got != want {
|
||||
t.Fatalf("pinned %q (%v); want %q", got, err, want)
|
||||
}
|
||||
// Only another repository's digest is listed: the push is not taken for pinned.
|
||||
r.Run = func(_ context.Context, _, name string, args ...string) (string, error) {
|
||||
if name == "docker" && len(args) > 0 && args[0] == "inspect" {
|
||||
return earlier + "\n", nil
|
||||
}
|
||||
return "", nil
|
||||
}
|
||||
if _, err := r.PublishImage(context.Background(), "local", "shell/server"); err == nil ||
|
||||
!strings.Contains(err.Error(), "no digest for that name") {
|
||||
t.Fatalf("a digest of another repository was taken for the push's own: %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -253,6 +253,13 @@ func (s scratchPublisher) PublishImage(ctx context.Context, localTag, repository
|
||||
return s.to.PublishImage(ctx, localTag, ScratchPrefix+repository)
|
||||
}
|
||||
|
||||
func (s scratchPublisher) PushedNames(repository string) []string {
|
||||
if p, ok := s.to.(PushedNames); ok {
|
||||
return p.PushedNames(ScratchPrefix + repository)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func (s scratchPublisher) PublishArchive(ctx context.Context, repository string, body []byte, digest string) (string, error) {
|
||||
return s.to.PublishArchive(ctx, ScratchPrefix+repository, body, digest)
|
||||
}
|
||||
|
||||
@@ -88,6 +88,9 @@ func imageContent(ctx context.Context, run Runner, dir, ref string) (string, err
|
||||
if _, err := run(ctx, dir, "docker", "pull", "--quiet", ref); err != nil {
|
||||
return "", fmt.Errorf("pulling %s: %w", ref, err)
|
||||
}
|
||||
// The image is on the node only for the reading (novox/hq issue 1834); one a container still runs is refused by
|
||||
// docker and stays.
|
||||
defer func() { _, _ = run(context.WithoutCancel(ctx), dir, "docker", "rmi", ref) }()
|
||||
config, err := run(ctx, dir, "docker", "image", "inspect", "--format",
|
||||
"{{.Os}}/{{.Architecture}}/{{.Variant}} {{json .Config}}", ref)
|
||||
if err != nil {
|
||||
@@ -105,7 +108,7 @@ func imageContent(ctx context.Context, run Runner, dir, ref string) (string, err
|
||||
if id == "" {
|
||||
return "", errors.New("the container engine named no container for " + ref)
|
||||
}
|
||||
defer func() { _, _ = run(context.WithoutCancel(ctx), dir, "docker", "rm", "--force", id) }()
|
||||
defer func() { _, _ = run(context.WithoutCancel(ctx), dir, "docker", "rm", "--force", "--volumes", id) }()
|
||||
if err := os.MkdirAll(dir, 0o700); err != nil {
|
||||
return "", err
|
||||
}
|
||||
|
||||
@@ -185,7 +185,7 @@ func TestABuildsBuildSourceComesBackOverWhatItRead(t *testing.T) {
|
||||
said.Read = []ReadRepository{{Repository: "novox/mesh-controller", Ref: "main"}, {Repository: "novox/other"}}
|
||||
said.Sources = []BuildSource{
|
||||
{Paths: []string{"modules/route-proxy/Dockerfile", "modules/route-proxy/module.json"}},
|
||||
{Repository: "novox/mesh-controller", Ref: "main", Paths: []string{"examples/route-proxy/", "go.mod"}},
|
||||
{Repository: "novox/mesh-controller", Ref: "main", Paths: []string{"modules/route-proxy/cmd/route-proxy/", "go.mod"}},
|
||||
{Repository: "novox/unread", Paths: []string{"x"}},
|
||||
}
|
||||
unsaid := aBuild("unsaid", "build-agent", "")
|
||||
@@ -200,7 +200,7 @@ func TestABuildsBuildSourceComesBackOverWhatItRead(t *testing.T) {
|
||||
t.Fatal(err)
|
||||
}
|
||||
want := []ReadRepository{
|
||||
{Repository: "novox/mesh-controller", Ref: "main", Paths: []string{"examples/route-proxy/", "go.mod"}},
|
||||
{Repository: "novox/mesh-controller", Ref: "main", Paths: []string{"modules/route-proxy/cmd/route-proxy/", "go.mod"}},
|
||||
{Repository: "novox/other"},
|
||||
{Paths: []string{"modules/route-proxy/Dockerfile", "modules/route-proxy/module.json"}, Own: true},
|
||||
}
|
||||
@@ -238,7 +238,7 @@ func TestAFailedNewerBuildLeavesTheBuildSourceStale(t *testing.T) {
|
||||
worked.Asked = time.Now().Add(-time.Hour)
|
||||
worked.Read = []ReadRepository{{Repository: "novox/mesh-controller", Ref: "main"}}
|
||||
worked.Sources = []BuildSource{{Paths: []string{"modules/route-proxy/module.json"}},
|
||||
{Repository: "novox/mesh-controller", Ref: "main", Paths: []string{"examples/route-proxy/"}}}
|
||||
{Repository: "novox/mesh-controller", Ref: "main", Paths: []string{"modules/route-proxy/cmd/route-proxy/"}}}
|
||||
failed := aBuild("failed", "route-proxy", "compile error")
|
||||
failed.Asked = time.Now()
|
||||
for _, b := range []Build{worked, failed} {
|
||||
|
||||
@@ -0,0 +1,83 @@
|
||||
package inventory
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"reflect"
|
||||
"slices"
|
||||
"testing"
|
||||
)
|
||||
|
||||
// aNodesPackages is the resources of a node whose modules declare packages: one package two modules declare present, one
|
||||
// declared absent, and a resource that is no package.
|
||||
func aNodesPackages() ([]map[string]any, map[string]string) {
|
||||
return []map[string]any{
|
||||
{"id": "web.pkg-curl", "type": "package", "package": "curl"},
|
||||
{"id": "backup.pkg-curl", "type": "package", "package": "curl"},
|
||||
{"id": "web.pkg-nano", "type": "package", "package": "nano", "absent": true},
|
||||
{"id": "web.conf", "type": "file", "path": "/etc/web.conf"},
|
||||
},
|
||||
map[string]string{"web.pkg-curl": "web", "backup.pkg-curl": "backup", "web.pkg-nano": "web", "web.conf": "web"}
|
||||
}
|
||||
|
||||
// 1840/AC5: the declared-packages mirror's value for a node names each package with the modules that declare it and whether
|
||||
// they declare it absent, and the same declaration is the same bytes however its resources are ordered, so a pass over an
|
||||
// unchanged node writes nothing.
|
||||
func TestTheDeclaredPackagesValueNamesEachPackageWithItsModules(t *testing.T) {
|
||||
resources, owner := aNodesPackages()
|
||||
got, err := DeclaredPackagesValue("one", resources, owner)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
want := `{"node":"one","packages":[{"package":"curl","modules":["backup","web"],"absent":false},` +
|
||||
`{"package":"nano","modules":["web"],"absent":true}]}`
|
||||
if string(got) != want {
|
||||
t.Errorf("the value is\n%s\nwant\n%s", got, want)
|
||||
}
|
||||
reversed := slices.Clone(resources)
|
||||
slices.Reverse(reversed)
|
||||
again, err := DeclaredPackagesValue("one", reversed, owner)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if !bytes.Equal(got, again) {
|
||||
t.Errorf("the same declaration in another order is other bytes:\n%s\n%s", got, again)
|
||||
}
|
||||
if got := jsonFields(reflect.TypeOf(DeclaredPackagesMirrored{})); !slices.Equal(got, []string{"node", "packages"}) {
|
||||
t.Errorf("the value carries %v", got)
|
||||
}
|
||||
}
|
||||
|
||||
// A node declaring no package has a value that says so, an empty list and not null.
|
||||
func TestANodeDeclaringNoPackageHasAnEmptyList(t *testing.T) {
|
||||
got, err := DeclaredPackagesValue("one", nil, nil)
|
||||
if err != nil || string(got) != `{"node":"one","packages":[]}` {
|
||||
t.Errorf("the value is %s (%v)", got, err)
|
||||
}
|
||||
}
|
||||
|
||||
// 1840/S3: a node's value stays under the 64 KiB a mirror's key holds at far more packages than a node declares: 600
|
||||
// packages, each declared by four modules, is a few times what the largest node declares today.
|
||||
func TestTheDeclaredPackagesValueOfABigNodeFitsAKey(t *testing.T) {
|
||||
var resources []map[string]any
|
||||
owner := map[string]string{}
|
||||
for p := 0; p < 600; p++ {
|
||||
for m := 0; m < 4; m++ {
|
||||
id := fmt.Sprintf("module-%d.pkg-%d", m, p)
|
||||
resources = append(resources, map[string]any{"id": id, "type": "package", "package": fmt.Sprintf("package-%d", p)})
|
||||
owner[id] = fmt.Sprintf("module-%d", m)
|
||||
}
|
||||
}
|
||||
got, err := DeclaredPackagesValue("one", resources, owner)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
var v DeclaredPackagesMirrored
|
||||
if err := json.Unmarshal(got, &v); err != nil || len(v.Packages) != 600 {
|
||||
t.Fatalf("the value holds %d packages (%v)", len(v.Packages), err)
|
||||
}
|
||||
if len(got) >= 64<<10 {
|
||||
t.Errorf("the value is %d bytes, over the 64 KiB a key holds", len(got))
|
||||
}
|
||||
}
|
||||
@@ -5,7 +5,10 @@ import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"sort"
|
||||
"time"
|
||||
|
||||
"git.novox.be/novox/mesh-sdk/go/catalogue"
|
||||
)
|
||||
|
||||
// The values of the controller's record mirrors, built from the store (novox/hq ADR 0289, design 54 §1,
|
||||
@@ -179,3 +182,75 @@ func (i *Inventory) PredefinedMirror(ctx context.Context) (map[string][]byte, er
|
||||
}
|
||||
return map[string][]byte{PredefinedMirrorKey: value}, nil
|
||||
}
|
||||
|
||||
// DeclaredOf is a manifest's config declarations as the mirror holds them (DeclaredMirrored), so a pull request's
|
||||
// declarations are told to mesh-config in the one shape it reads the trunk's in (novox/hq ADR 0502 clause 2).
|
||||
func DeclaredOf(settings map[string]catalogue.SettingDeclaration) (map[string]DeclaredMirrored, error) {
|
||||
raw, err := json.Marshal(settings)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return declaredMirrored(raw)
|
||||
}
|
||||
|
||||
// PackageDeclared is one package a node's modules declare, as the declared-packages mirror holds it (ADR 0507 §5): its
|
||||
// name, the modules that declare it that way, sorted, and whether they declare it absent. A package some modules declare
|
||||
// present and others absent is two entries; the composition refuses that pair, so it is seen only while it is refused.
|
||||
type PackageDeclared struct {
|
||||
Package string `json:"package"`
|
||||
Modules []string `json:"modules"`
|
||||
Absent bool `json:"absent"`
|
||||
}
|
||||
|
||||
// DeclaredPackagesMirrored is one node's value of the declared-packages mirror, keyed by the node: its packages sorted by
|
||||
// name (absent after present). Fixed fields and no time, so the same declaration is the same bytes (ADR 0289 §1).
|
||||
type DeclaredPackagesMirrored struct {
|
||||
Node string `json:"node"`
|
||||
Packages []PackageDeclared `json:"packages"`
|
||||
}
|
||||
|
||||
// DeclaredPackagesValue is the mirror's value for one node, from the resources its composition declares and the module that
|
||||
// owns each (Composed.Owner, by resource id). A resource that is no package, or names none, is left out.
|
||||
func DeclaredPackagesValue(node string, resources []map[string]any, owner map[string]string) ([]byte, error) {
|
||||
type key struct {
|
||||
name string
|
||||
absent bool
|
||||
}
|
||||
by := map[key]map[string]bool{}
|
||||
for _, r := range resources {
|
||||
if fmt.Sprint(r["type"]) != "package" {
|
||||
continue
|
||||
}
|
||||
name, _ := r["package"].(string)
|
||||
if name == "" {
|
||||
continue
|
||||
}
|
||||
k := key{name, r["absent"] == true}
|
||||
if by[k] == nil {
|
||||
by[k] = map[string]bool{}
|
||||
}
|
||||
if module := owner[fmt.Sprint(r["id"])]; module != "" {
|
||||
by[k][module] = true
|
||||
}
|
||||
}
|
||||
keys := make([]key, 0, len(by))
|
||||
for k := range by {
|
||||
keys = append(keys, k)
|
||||
}
|
||||
sort.Slice(keys, func(i, j int) bool {
|
||||
if keys[i].name != keys[j].name {
|
||||
return keys[i].name < keys[j].name
|
||||
}
|
||||
return !keys[i].absent && keys[j].absent
|
||||
})
|
||||
v := DeclaredPackagesMirrored{Node: node, Packages: []PackageDeclared{}}
|
||||
for _, k := range keys {
|
||||
modules := make([]string, 0, len(by[k]))
|
||||
for m := range by[k] {
|
||||
modules = append(modules, m)
|
||||
}
|
||||
sort.Strings(modules)
|
||||
v.Packages = append(v.Packages, PackageDeclared{Package: k.name, Modules: modules, Absent: k.absent})
|
||||
}
|
||||
return json.Marshal(v)
|
||||
}
|
||||
|
||||
@@ -0,0 +1,28 @@
|
||||
package link
|
||||
|
||||
import (
|
||||
"context"
|
||||
"testing"
|
||||
|
||||
"github.com/nats-io/nats.go"
|
||||
)
|
||||
|
||||
// 1768/AC1: a request dropped as a duplicate of one another builder runs marks nothing in hand: the claim is not made,
|
||||
// so no mark is left behind to fail every later claim.
|
||||
func TestADuplicateDropIsJudgedBeforeTheClaimSoLeavesNoMark(t *testing.T) {
|
||||
claims := 0
|
||||
m := &natsMachine{
|
||||
opts: MachineOptions{Claim: func() bool { claims++; return true }},
|
||||
duplicate: func(context.Context, BuildRequest) string { return "ace is running it" },
|
||||
}
|
||||
if m.admit(context.Background(), &nats.Msg{}, BuildRequest{ID: "build-1"}) {
|
||||
t.Fatal("a duplicate was admitted")
|
||||
}
|
||||
if claims != 0 {
|
||||
t.Fatalf("a dropped duplicate was claimed %d times, which leaves the in-hand mark behind", claims)
|
||||
}
|
||||
m.duplicate = func(context.Context, BuildRequest) string { return "" }
|
||||
if !m.admit(context.Background(), &nats.Msg{}, BuildRequest{ID: "build-2"}) || claims != 1 {
|
||||
t.Fatalf("a request that is no duplicate was not claimed once: claims=%d", claims)
|
||||
}
|
||||
}
|
||||
@@ -218,6 +218,25 @@ type CheckRequest struct {
|
||||
Try bool `json:"try,omitempty"`
|
||||
Tests string `json:"tests,omitempty"`
|
||||
StoreOnly bool `json:"store-only,omitempty"`
|
||||
// HeldConfig are the approved held values of the pull requests this check is of (novox/hq ADR 0502 clause 4): each
|
||||
// a config value the operator approved for a key an open pull request introduces. The merge gate lays them over
|
||||
// their module's values on their node in the composition with the change only, never in the mesh as it is. Empty
|
||||
// from a controller from before it, or when mesh-config held none or did not answer.
|
||||
HeldConfig []HeldConfig `json:"held_config,omitempty"`
|
||||
}
|
||||
|
||||
// HeldConfig is one approved held value (novox/hq ADR 0502), as mesh-config's `held` action answers it.
|
||||
type HeldConfig struct {
|
||||
Pull string `json:"pull"`
|
||||
Head string `json:"head,omitempty"`
|
||||
Node string `json:"node"`
|
||||
Module string `json:"module"`
|
||||
Key string `json:"key"`
|
||||
Value json.RawMessage `json:"value"`
|
||||
// Approved says who approved it, in words, as mesh-config states it; By and At are who held it and when.
|
||||
Approved string `json:"approved,omitempty"`
|
||||
By string `json:"by,omitempty"`
|
||||
At string `json:"at,omitempty"`
|
||||
}
|
||||
|
||||
// StepTried is the step a build seat says a try's outcome under, in the build's log: one line, a Tried as JSON
|
||||
@@ -292,6 +311,10 @@ type GroupMember struct {
|
||||
// Base is the branch it merges into: the build seat merges the head into that trunk's head before the
|
||||
// group is composed (novox/hq ADR 0323 §6). A build seat from before it composes the head alone.
|
||||
Base string `json:"base,omitempty"`
|
||||
// Trunk is the base branch's head the forge announced with the head (novox/hq issue 1106): the trunk commit the
|
||||
// composed verdict names for this member when the build seat named none, so a member whose trunk did not move is
|
||||
// never merged-refused for a verdict that names no trunk.
|
||||
Trunk string `json:"trunk,omitempty"`
|
||||
}
|
||||
|
||||
// Who judges a merge check's gate.
|
||||
|
||||
@@ -163,6 +163,8 @@ type natsMachine struct {
|
||||
// build waits, then the checks of pull requests marked ready, then every other check (novox/hq ADR 0406 §3).
|
||||
subs []*takeQueue
|
||||
opts MachineOptions
|
||||
// duplicate stands in for runningElsewhere in tests; nil is the real one.
|
||||
duplicate func(context.Context, BuildRequest) string
|
||||
// gate is what the loop asks of the bus to hold checks while a delivery builds; nil is the bus's (a test sets a fake).
|
||||
gate checkGate
|
||||
// said is the faults of the hold already said, letKey whether this holder created the let-through key for the check it
|
||||
@@ -405,18 +407,7 @@ func (m *natsMachine) handOver(ctx context.Context, msg *nats.Msg, q *takeQueue,
|
||||
return
|
||||
}
|
||||
}
|
||||
// **Drained in the moment it was fetched** (novox/hq ADR 0335): handed back at once, as a pause
|
||||
// landing then is.
|
||||
if m.opts.Claim != nil && !m.opts.Claim() {
|
||||
_ = msg.Nak()
|
||||
return
|
||||
}
|
||||
// **A duplicate of a check another builder is running is dropped** (issue 1649): an ask redelivered to this machine
|
||||
// because its first holder did not say, in time, that it had it. The running key names that builder and this same
|
||||
// ask; running it a second time would spend a second place on one check.
|
||||
if why := m.runningElsewhere(ctx, request); why != "" {
|
||||
fmt.Fprintf(os.Stderr, "%s is handed out again while another builder runs it and is dropped: %s\n", request.ID, why)
|
||||
_ = msg.Ack()
|
||||
if !m.admit(ctx, msg, request) {
|
||||
return
|
||||
}
|
||||
// A build outlives the acknowledgement window many times over; said while it runs,
|
||||
@@ -460,6 +451,33 @@ func (m *natsMachine) quiesce(keep *takeQueue) {
|
||||
}
|
||||
}
|
||||
|
||||
// admit decides whether a fetched request is run here, and answers the message when it is not.
|
||||
//
|
||||
// **The duplicate is judged before the request is claimed** (issue 1768): a claim marks the build in hand, and a request
|
||||
// dropped after it left the mark behind, so every later claim failed and every ask was handed back at once until all
|
||||
// had spent their deliveries. A request dropped here has marked nothing.
|
||||
//
|
||||
// **Drained in the moment it was fetched** (novox/hq ADR 0335): handed back at once, as a pause landing then is.
|
||||
func (m *natsMachine) admit(ctx context.Context, msg *nats.Msg, request BuildRequest) bool {
|
||||
// **A duplicate of a check another builder is running is dropped** (issue 1649): an ask redelivered to this machine
|
||||
// because its first holder did not say, in time, that it had it. The running key names that builder and this same
|
||||
// ask; running it a second time would spend a second place on one check.
|
||||
elsewhere := m.runningElsewhere
|
||||
if m.duplicate != nil {
|
||||
elsewhere = m.duplicate
|
||||
}
|
||||
if why := elsewhere(ctx, request); why != "" {
|
||||
fmt.Fprintf(os.Stderr, "%s is handed out again while another builder runs it and is dropped: %s\n", request.ID, why)
|
||||
_ = msg.Ack()
|
||||
return false
|
||||
}
|
||||
if m.opts.Claim != nil && !m.opts.Claim() {
|
||||
_ = msg.Nak()
|
||||
return false
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
// runningElsewhere says why an ask need not run here, or nothing: the bucket of the checks running says another builder
|
||||
// runs this very ask (its id, its head and its trunk commit). A key that cannot be read runs the check.
|
||||
func (m *natsMachine) runningElsewhere(ctx context.Context, r BuildRequest) string {
|
||||
|
||||
@@ -0,0 +1,92 @@
|
||||
package ownmanifest
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
"testing"
|
||||
)
|
||||
|
||||
// imagesOutOfPlace lists the image artifacts among manifests (module name to its manifest's text) whose Dockerfile
|
||||
// is not a file inside that module's own directory, root/<module> (novox/hq ADR 0487 clause 13, which replaced the
|
||||
// refusal of the image kind of ADR 0480 clause 11). The image builder builds a module from its directory alone.
|
||||
// It reads the manifest as plain JSON, since the catalogue parser refuses some of these itself. It mirrors mesh-catalog's checks/imageplace: an empty from, an absolute one, one leaving the directory with ..,
|
||||
// or a name that is no file there, is refused.
|
||||
func imagesOutOfPlace(t *testing.T, root string, manifests map[string][]byte) []string {
|
||||
t.Helper()
|
||||
var out []string
|
||||
for module, raw := range manifests {
|
||||
var m struct {
|
||||
Build struct {
|
||||
Artifacts []struct{ Name, Kind, From string } `json:"artifacts"`
|
||||
} `json:"build"`
|
||||
}
|
||||
if err := json.Unmarshal(raw, &m); err != nil {
|
||||
t.Fatalf("%s does not parse: %v", module, err)
|
||||
}
|
||||
for _, a := range m.Build.Artifacts {
|
||||
if a.Kind != "image" {
|
||||
continue
|
||||
}
|
||||
clean := filepath.Clean(a.From)
|
||||
bad := a.From == "" || filepath.IsAbs(clean) || clean == ".." || strings.HasPrefix(clean, ".."+string(filepath.Separator))
|
||||
if !bad {
|
||||
info, err := os.Stat(filepath.Join(root, module, clean))
|
||||
bad = err != nil || info.IsDir()
|
||||
}
|
||||
if bad {
|
||||
out = append(out, module+" ("+a.Name+" from "+a.From+")")
|
||||
}
|
||||
}
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// Every image a module of this repository declares is built from a Dockerfile in the module's own directory
|
||||
// (novox/hq ADR 0487 clause 13). The catalogue's own modules are held to the same by checks/imageplace in mesh-catalog.
|
||||
func TestEveryImageArtifactBuildsFromADockerfileInItsOwnModuleDirectory(t *testing.T) {
|
||||
root := filepath.Join("..", "..", "modules")
|
||||
paths, err := filepath.Glob(filepath.Join(root, "*", "module.json"))
|
||||
if err != nil || len(paths) == 0 {
|
||||
t.Fatalf("no module manifests found in this repository's modules: %v", err)
|
||||
}
|
||||
manifests := map[string][]byte{}
|
||||
for _, p := range paths {
|
||||
raw, err := os.ReadFile(p)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
manifests[filepath.Base(filepath.Dir(p))] = raw
|
||||
}
|
||||
if got := imagesOutOfPlace(t, root, manifests); len(got) != 0 {
|
||||
t.Errorf("these image artifacts do not build from a Dockerfile in their own module's directory "+
|
||||
"(ADR 0487 clause 13): %v", got)
|
||||
}
|
||||
}
|
||||
|
||||
// The check fails on each bad case and passes on a good one, so it holds something.
|
||||
func TestAnImageWhoseDockerfileIsOutOfPlaceIsFoundAndOneInPlaceIsNot(t *testing.T) {
|
||||
root := t.TempDir()
|
||||
if err := os.MkdirAll(filepath.Join(root, "x", "sub"), 0o755); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
for _, f := range []string{"x/Dockerfile", "x/sub/Dockerfile", "outside"} {
|
||||
if err := os.WriteFile(filepath.Join(root, f), nil, 0o644); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
}
|
||||
manifest := func(from string) map[string][]byte {
|
||||
return map[string][]byte{"x": []byte(`{"module":"x","version":"1","build":{"artifacts":[{"name":"server","kind":"image","from":"` + from + `"}]}}`)}
|
||||
}
|
||||
for _, from := range []string{"Dockerfile", "sub/Dockerfile", "./Dockerfile"} {
|
||||
if got := imagesOutOfPlace(t, root, manifest(from)); len(got) != 0 {
|
||||
t.Errorf("from %q: found %v, want none", from, got)
|
||||
}
|
||||
}
|
||||
for _, from := range []string{"", "/etc/Dockerfile", "../outside", "..", "sub/../../outside", "Missing", "sub"} {
|
||||
if got := imagesOutOfPlace(t, root, manifest(from)); len(got) != 1 {
|
||||
t.Errorf("from %q: found %v, want it refused", from, got)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -11,7 +11,7 @@ import (
|
||||
//
|
||||
// route-proxy keeps each ACME authority's account and certificates in a directory named after a
|
||||
// digest of the directory URL and of the root bundle its `trust` container copies in
|
||||
// (examples/route-proxy, forThisAuthority). Until ADR 0226 the URL was rendered from a binding to
|
||||
// (modules/route-proxy/cmd/route-proxy, forThisAuthority). Until ADR 0226 the URL was rendered from a binding to
|
||||
// `public-acme`'s `acme-ca`, spelled with the port. A URL spelled any other way — even the same
|
||||
// authority without `:443` — or a root bundle from another image is a new authority to the proxy:
|
||||
// a new account, and every routed name ordered again, on two machines at once, against Let's
|
||||
@@ -36,8 +36,11 @@ func TestRouteProxyKeepsItsPublicAccountDirectory(t *testing.T) {
|
||||
}
|
||||
|
||||
// As a build would leave it: each artifact a container names resolved to an image. Which image
|
||||
// does not matter to the file checked here.
|
||||
// does not matter to the file checked here. An archive resource carries no image: it unpacks a bundle.
|
||||
for _, res := range m.Resources {
|
||||
if res["type"] == "archive" {
|
||||
continue
|
||||
}
|
||||
if artifact, ok := res["artifact"].(string); ok {
|
||||
delete(res, "artifact")
|
||||
res["image"] = "registry.invalid/route-proxy/" + artifact +
|
||||
@@ -86,3 +89,57 @@ func TestRouteProxyKeepsItsPublicAccountDirectory(t *testing.T) {
|
||||
"plan for the account (ADR 0226)", trust, trustImage)
|
||||
}
|
||||
}
|
||||
|
||||
// The proxy's program is mounted into the pinned trust image, not baked into an image (novox/hq ADR 0480 clauses 1,
|
||||
// 2 and 4): a Go bundle of the module's own Go module stamped for alpine, unpacked by an archive resource, mounted
|
||||
// read-only at /opt/mesh, called through args, and named under restart-on so a new program never leaves the old
|
||||
// one running. The container's name, network and logging are what the jail and the routes rely on.
|
||||
func TestRouteProxyRunsItsMountedProgramOnTheTrustImage(t *testing.T) {
|
||||
m := catalogueManifest(t, "route-proxy")
|
||||
var bundle *Artifact
|
||||
for i, a := range m.Build.Artifacts {
|
||||
if a.Name == "server" {
|
||||
bundle = &m.Build.Artifacts[i]
|
||||
}
|
||||
if a.Kind == "image" {
|
||||
t.Errorf("artifact %s is an image built from a Dockerfile (ADR 0452 §1)", a.Name)
|
||||
}
|
||||
}
|
||||
if bundle == nil || bundle.Kind != "bundle" || bundle.Language != "go" || bundle.System != "alpine" ||
|
||||
bundle.From != "cmd/route-proxy" || bundle.Binary != "route-proxy" {
|
||||
t.Fatalf("the server artifact is not a Go bundle of cmd/route-proxy stamped for alpine: %+v", bundle)
|
||||
}
|
||||
var archive, server map[string]any
|
||||
for _, r := range m.Resources {
|
||||
switch {
|
||||
case r["type"] == "archive" && r["artifact"] == "server":
|
||||
archive = r
|
||||
case r["id"] == "server":
|
||||
server = r
|
||||
}
|
||||
}
|
||||
if archive == nil || server == nil {
|
||||
t.Fatalf("archive %v or server container %v is missing", archive, server)
|
||||
}
|
||||
if server["artifact"] != "trust" || server["name"] != "route-proxy" || server["network"] != "host" || server["logging"] != "journald" {
|
||||
t.Errorf("the server container moved: %v", server)
|
||||
}
|
||||
mount := archive["path"].(string) + ":/opt/mesh:ro"
|
||||
mounted := false
|
||||
for _, v := range server["volumes"].([]any) {
|
||||
mounted = mounted || v == mount
|
||||
}
|
||||
if !mounted {
|
||||
t.Errorf("the archive is not mounted read-only at /opt/mesh (%s): %v", mount, server["volumes"])
|
||||
}
|
||||
if args, _ := server["args"].([]any); len(args) != 1 || args[0] != "/opt/mesh/route-proxy" {
|
||||
t.Errorf("args are %v, want the mounted program", server["args"])
|
||||
}
|
||||
restarts := false
|
||||
for _, v := range server["restart-on"].([]any) {
|
||||
restarts = restarts || v == archive["id"]
|
||||
}
|
||||
if !restarts {
|
||||
t.Errorf("restart-on %v does not name the archive %v", server["restart-on"], archive["id"])
|
||||
}
|
||||
}
|
||||
|
||||
@@ -57,10 +57,13 @@ var (
|
||||
// mesh-config publishes as its own (design 57 K3).
|
||||
Predefined = Mirror{Name: broker.MirrorPredefined, Bucket: broker.PredefinedBucket,
|
||||
Event: link.KeyPredefinedChanged}
|
||||
// DeclaredPackages is each node's packages its modules declare, keyed by the node (ADR 0507 §5). It raises no event:
|
||||
// the seat's emits, which the SDK states, do not name one, and a reader reads the bucket when it is asked.
|
||||
DeclaredPackages = Mirror{Name: broker.MirrorDeclaredPackages, Bucket: broker.DeclaredPackagesBucket}
|
||||
)
|
||||
|
||||
// Mirrors is every mirror this package writes, in the order they are written.
|
||||
func Mirrors() []Mirror { return []Mirror{DeclaredConfig, Predefined} }
|
||||
func Mirrors() []Mirror { return []Mirror{DeclaredConfig, Predefined, DeclaredPackages} }
|
||||
|
||||
// The changes an event says.
|
||||
const (
|
||||
@@ -251,7 +254,7 @@ func (w *Writer) put(ctx context.Context, key string, value []byte, before kept,
|
||||
|
||||
// say raises one write's event, tried once more when refused and then counted as lost.
|
||||
func (w *Writer) say(ctx context.Context, key, change string, fields []string, revision uint64) {
|
||||
if w.Announce == nil {
|
||||
if w.Announce == nil || w.Mirror.Event == "" {
|
||||
return
|
||||
}
|
||||
e := Event{Mirror: w.Mirror.Name, Key: key, Change: change, Fields: fields, Revision: revision, At: w.now().UTC()}
|
||||
|
||||
@@ -9,6 +9,7 @@ import (
|
||||
|
||||
"github.com/nats-io/nats.go/jetstream"
|
||||
"github.com/novox/mesh-controller/internal/broker"
|
||||
"github.com/novox/mesh-controller/internal/inventory"
|
||||
"github.com/novox/mesh-controller/internal/testbus"
|
||||
)
|
||||
|
||||
@@ -246,3 +247,49 @@ func TestNatsARemovalWithoutTheLeaseRemovesNothing(t *testing.T) {
|
||||
t.Errorf("the key was removed without the lease: %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
// 1840/AC5 (ADR 0507 §5, ADR 0289 §1): the declared-packages mirror, keyed by the node, writes a node's value once; a second
|
||||
// pass over the same declaration writes nothing (the bucket takes no message); a package newly declared changes the one key;
|
||||
// a node gone removes its key. It raises no event: the seat's emits name none for it.
|
||||
func TestNatsTheDeclaredPackagesMirrorWritesOnlyOnAChange(t *testing.T) {
|
||||
js, api := aMirrorBus(t)
|
||||
events := listen(t, js.Conn(), "mesh.seat."+broker.ControllerSeat+".event.>")
|
||||
w := aWriter(t, js, api, DeclaredPackages)
|
||||
ctx := t.Context()
|
||||
value := func(node string, resources ...map[string]any) []byte {
|
||||
t.Helper()
|
||||
owner := map[string]string{}
|
||||
for _, r := range resources {
|
||||
owner[r["id"].(string)] = "web"
|
||||
}
|
||||
v, err := inventory.DeclaredPackagesValue(node, resources, owner)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
return v
|
||||
}
|
||||
curl := map[string]any{"id": "web.curl", "type": "package", "package": "curl"}
|
||||
nano := map[string]any{"id": "web.nano", "type": "package", "package": "nano", "absent": true}
|
||||
|
||||
if r, err := w.Sync(ctx, map[string][]byte{"one": value("one", curl), "two": value("two")}); err != nil ||
|
||||
r != (Result{Written: 2}) {
|
||||
t.Fatalf("the first pass wrote %+v (%v)", r, err)
|
||||
}
|
||||
before := writes(t, api, DeclaredPackages.Bucket)
|
||||
if r, err := w.Sync(ctx, map[string][]byte{"one": value("one", curl), "two": value("two")}); err != nil || r != (Result{}) {
|
||||
t.Errorf("a pass over the same declarations wrote %+v (%v)", r, err)
|
||||
}
|
||||
if got := writes(t, api, DeclaredPackages.Bucket) - before; got != 0 {
|
||||
t.Errorf("a pass over the same declarations put %d messages in the bucket", got)
|
||||
}
|
||||
if r, err := w.Sync(ctx, map[string][]byte{"one": value("one", curl, nano), "two": value("two")}); err != nil ||
|
||||
r != (Result{Written: 1}) {
|
||||
t.Errorf("a package newly declared wrote %+v (%v)", r, err)
|
||||
}
|
||||
if r, err := w.Sync(ctx, map[string][]byte{"one": value("one", curl, nano)}); err != nil || r != (Result{Removed: 1}) {
|
||||
t.Errorf("a node gone wrote %+v (%v)", r, err)
|
||||
}
|
||||
if said := settle(events, 1); len(said) != 0 {
|
||||
t.Errorf("the declared-packages mirror raised %+v", said)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -19,18 +19,10 @@ import (
|
||||
// bus upgrade moves the catalogue's pin; this then fails in the merge check until the tests' pin moves
|
||||
// with it, so the controller is never tested against a bus the mesh no longer runs, or not yet.
|
||||
func TestTheBusTheTestsRunIsTheBusTheMeshRuns(t *testing.T) {
|
||||
dockerfile := filepath.Join(beside.Catalogue(t), "nats", "Dockerfile")
|
||||
raw, err := os.ReadFile(dockerfile)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
pinned := regexp.MustCompile(`upstream: nats ([0-9.]+)-alpine`).FindSubmatch(raw)
|
||||
if pinned == nil {
|
||||
t.Fatalf("%s says no release its digest is", dockerfile)
|
||||
}
|
||||
if string(pinned[1]) != Version {
|
||||
t.Errorf("the tests run bus %s and the catalogue's bus image is %s: move go.mod's nats-server pin "+
|
||||
"(and `go mod vendor`) with the image", Version, pinned[1])
|
||||
release, from := catalogueBusRelease(t, filepath.Join(beside.Catalogue(t), "nats"))
|
||||
if release != Version {
|
||||
t.Errorf("the tests run bus %s and the catalogue's bus image is %s (%s): move go.mod's nats-server pin "+
|
||||
"(and `go mod vendor`) with the image", Version, release, from)
|
||||
}
|
||||
path := os.Getenv("MESH_FACTS")
|
||||
if path == "" {
|
||||
@@ -57,3 +49,51 @@ func TestTheBusTheTestsRunIsTheBusTheMeshRuns(t *testing.T) {
|
||||
}
|
||||
|
||||
// A test's bus is its own: what one test makes, the next never sees.
|
||||
|
||||
// catalogueBusRelease is the server release the catalogue's nats module runs, and where it was read. Since
|
||||
// ADR 0497 the server is an upstream artifact in the module's manifest (`nats:<release>-alpine@sha256:…`);
|
||||
// before it, an image built from the module's Dockerfile, whose `upstream: nats <release>-alpine` line said
|
||||
// the release its digest is. The manifest is read first; the Dockerfile only where the manifest names no
|
||||
// upstream nats image (a catalogue from before that move, such as the captured copy). Neither is a failure.
|
||||
func catalogueBusRelease(t *testing.T, module string) (release, from string) {
|
||||
t.Helper()
|
||||
manifest := filepath.Join(module, "module.json")
|
||||
raw, err := os.ReadFile(manifest)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
var m struct {
|
||||
Build struct {
|
||||
Artifacts []struct {
|
||||
Name string `json:"name"`
|
||||
Kind string `json:"kind"`
|
||||
From string `json:"from"`
|
||||
} `json:"artifacts"`
|
||||
} `json:"build"`
|
||||
}
|
||||
if err := json.Unmarshal(raw, &m); err != nil {
|
||||
t.Fatalf("%s: %v", manifest, err)
|
||||
}
|
||||
upstream := regexp.MustCompile(`^(?:[^/]+/)*nats:([0-9]+\.[0-9]+\.[0-9]+)-alpine(?:@sha256:[0-9a-f]{64})?$`)
|
||||
for _, a := range m.Build.Artifacts {
|
||||
if a.Kind != "upstream" || !strings.HasPrefix(a.From[strings.LastIndex(a.From, "/")+1:], "nats:") {
|
||||
continue
|
||||
}
|
||||
pinned := upstream.FindStringSubmatch(a.From)
|
||||
if pinned == nil {
|
||||
t.Fatalf("%s: the upstream artifact %q is %q, which says no release in the form nats:<x.y.z>-alpine",
|
||||
manifest, a.Name, a.From)
|
||||
}
|
||||
return pinned[1], manifest
|
||||
}
|
||||
dockerfile := filepath.Join(module, "Dockerfile")
|
||||
raw, err = os.ReadFile(dockerfile)
|
||||
if err != nil {
|
||||
t.Fatalf("%s names no upstream nats image, and the image built before it is not there either: %v", manifest, err)
|
||||
}
|
||||
pinned := regexp.MustCompile(`upstream: nats ([0-9.]+)-alpine`).FindSubmatch(raw)
|
||||
if pinned == nil {
|
||||
t.Fatalf("%s says no release its digest is", dockerfile)
|
||||
}
|
||||
return string(pinned[1]), dockerfile
|
||||
}
|
||||
|
||||
@@ -6,3 +6,4 @@ MESH_NPM_TOKEN_FILE=/run/mesh/package-registry.secret
|
||||
MESH_GENESIS_PACKAGE_REGISTRY=/run/mesh/genesis-package-registry.json
|
||||
MESH_WORKSPACE=${dir:workspace}
|
||||
MESH_JUDGE_CACHE=${dir:judge-cache}
|
||||
MESH_BUILD_CGROUP_PARENT=meshbuild.slice
|
||||
|
||||
@@ -0,0 +1,10 @@
|
||||
# Managed by the mesh (module build-agent). Replaced on every push; edit the module's settings instead.
|
||||
#
|
||||
# Everything a build or check starts on this machine runs in this slice (novox/hq issue 1798): the build
|
||||
# agent starts every container with --cgroup-parent=meshbuild.slice. The weights only bind while the machine
|
||||
# is busy, so an idle machine still builds at full speed; the memory limits are the part that always binds.
|
||||
[Slice]
|
||||
CPUWeight=${setting:cpu-weight}
|
||||
IOWeight=${setting:io-weight}
|
||||
MemoryHigh=${setting:memory-high}
|
||||
MemoryMax=${setting:memory-max}
|
||||
@@ -187,3 +187,61 @@ func TestTheAgentReadsTheGatesPullKeysAndTodaysBoth(t *testing.T) {
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Builds and checks run below the machine's own work (novox/hq issue 1798): the module declares the slice
|
||||
// every build container joins with its limits as settings that have defaults, and tells the agent its name.
|
||||
func TestTheBuildSliceCarriesTheMachinesLimits(t *testing.T) {
|
||||
raw, err := os.ReadFile("module.json")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
var m struct {
|
||||
Config map[string]struct {
|
||||
Default any `json:"default"`
|
||||
} `json:"config"`
|
||||
}
|
||||
if err := json.Unmarshal(raw, &m); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
slice, err := os.ReadFile("files/meshbuild.slice")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
for key, property := range map[string]string{"cpu-weight": "CPUWeight", "io-weight": "IOWeight", "memory-high": "MemoryHigh", "memory-max": "MemoryMax"} {
|
||||
if c, ok := m.Config[key]; !ok || c.Default == nil {
|
||||
t.Errorf("1798/AC2: setting %s is missing or has no default", key)
|
||||
}
|
||||
if !strings.Contains(string(slice), property+"=${setting:"+key+"}") {
|
||||
t.Errorf("1798/AC2: the slice does not set %s from %s", property, key)
|
||||
}
|
||||
}
|
||||
var placed, running bool
|
||||
for _, r := range read(t).Resources {
|
||||
placed = placed || (r["type"] == "file" && r["path"] == "/etc/systemd/system/meshbuild.slice")
|
||||
running = running || (r["type"] == "service" && r["unit"] == "meshbuild.slice" && r["state"] == "running")
|
||||
}
|
||||
if !placed || !running {
|
||||
t.Errorf("1798/AC2: the slice must be placed (%v) and running (%v)", placed, running)
|
||||
}
|
||||
// 1798/AC3: a dash in a slice's name nests it in the slice named before the dash, and cgroup v2 weights only
|
||||
// compare siblings, so the name has none and the slice sits at the top level beside user.slice.
|
||||
for _, r := range read(t).Resources {
|
||||
if r["type"] == "service" && r["unit"] == "meshbuild.slice" {
|
||||
if strings.Contains(strings.TrimSuffix(r["unit"].(string), ".slice"), "-") {
|
||||
t.Errorf("1798/AC3: slice name %v nests", r["unit"])
|
||||
}
|
||||
// 1798/AC4: a changed limit reaches systemd only if the unit restarts when its file changes.
|
||||
restart, _ := r["restart-on"].([]any)
|
||||
if len(restart) != 1 || restart[0] != "build-slice" {
|
||||
t.Errorf("1798/AC4: the slice unit does not restart on its file: %v", restart)
|
||||
}
|
||||
}
|
||||
}
|
||||
env, err := os.ReadFile("files/build-agent.env")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if !strings.Contains(string(env), "MESH_BUILD_CGROUP_PARENT=meshbuild.slice") {
|
||||
t.Error("1798/AC1: the agent is not told the slice's name")
|
||||
}
|
||||
}
|
||||
|
||||
@@ -2,6 +2,34 @@
|
||||
"module": "build-agent",
|
||||
"version": "1",
|
||||
"slug": "agent",
|
||||
"config": {
|
||||
"cpu-weight": {
|
||||
"type": "number",
|
||||
"description": "The CPU weight of everything a build or check starts on this machine, from 1 to 10000 against 100 for an ordinary service or a login session: under load the builds get their share of that, on an idle machine they take what is free (novox/hq issue 1798). The default 20 is about a sixth of the CPU against one competing workload; a desktop may take 10. Changing it restarts the build slice, which stops every build and check running on that machine at that moment; they fail and must be retried.",
|
||||
"minimum": 1,
|
||||
"maximum": 10000,
|
||||
"default": 20
|
||||
},
|
||||
"io-weight": {
|
||||
"type": "number",
|
||||
"description": "The disk IO weight of everything a build or check starts, from 1 to 10000 against 100 for an ordinary service: the default 10 lets the machine's own work go first (novox/hq issue 1798). Changing it restarts the build slice, which stops every build and check running on that machine at that moment; they fail and must be retried.",
|
||||
"minimum": 1,
|
||||
"maximum": 10000,
|
||||
"default": 10
|
||||
},
|
||||
"memory-high": {
|
||||
"type": "string",
|
||||
"description": "The memory above which builds and checks are slowed and made to give memory back, a percentage of the machine's memory or a size (systemd's MemoryHigh): the default 50% leaves half the machine to what it runs (novox/hq issue 1798). Changing it restarts the build slice, which stops every build and check running on that machine at that moment; they fail and must be retried.",
|
||||
"pattern": "([1-9][0-9]?|100)%|[1-9][0-9]*[KMGT]",
|
||||
"default": "50%"
|
||||
},
|
||||
"memory-max": {
|
||||
"type": "string",
|
||||
"description": "The memory builds and checks together may never exceed, a percentage or a size (systemd's MemoryMax); a build past it is killed by the kernel and fails, so keep it above memory-high: the default 70% (novox/hq issue 1798). Changing it restarts the build slice, which stops every build and check running on that machine at that moment; they fail and must be retried.",
|
||||
"pattern": "([1-9][0-9]?|100)%|[1-9][0-9]*[KMGT]",
|
||||
"default": "70%"
|
||||
}
|
||||
},
|
||||
"capabilities": [
|
||||
"container-runtime"
|
||||
],
|
||||
@@ -9,7 +37,12 @@
|
||||
{
|
||||
"name": "node-build-agent",
|
||||
"scope": "node",
|
||||
"serves": ["current", "kill", "pause", "resume"]
|
||||
"serves": [
|
||||
"current",
|
||||
"kill",
|
||||
"pause",
|
||||
"resume"
|
||||
]
|
||||
}
|
||||
],
|
||||
"reads": [
|
||||
@@ -48,7 +81,7 @@
|
||||
"id": "judge-cache",
|
||||
"path": "${dir:judge-cache}",
|
||||
"class": "cache",
|
||||
"why": "the Go cache every merge check's judge is built with and the group judges kept per head; mounted into judge builds only, never into a check's containers (novox/hq ADR 0358 §6)"
|
||||
"why": "the Go cache every merge check's judge is built with and the group judges kept per head; mounted into judge builds only, never into a check's containers (novox/hq ADR 0358 \u00a76)"
|
||||
}
|
||||
]
|
||||
},
|
||||
@@ -69,6 +102,23 @@
|
||||
"type": "directory",
|
||||
"mode": "0700"
|
||||
},
|
||||
{
|
||||
"id": "build-slice",
|
||||
"type": "file",
|
||||
"path": "/etc/systemd/system/meshbuild.slice",
|
||||
"mode": "0644",
|
||||
"trusted": false,
|
||||
"template": "files/meshbuild.slice"
|
||||
},
|
||||
{
|
||||
"id": "build-slice-unit",
|
||||
"type": "service",
|
||||
"unit": "meshbuild.slice",
|
||||
"state": "running",
|
||||
"restart-on": [
|
||||
"build-slice"
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "agent-env",
|
||||
"type": "file",
|
||||
|
||||
@@ -1,29 +0,0 @@
|
||||
ARG ALPINE_BASE=alpine:3.20
|
||||
ARG GO_BASE=golang:1.25
|
||||
# The route-proxy module's runtime image: the reference reverse proxy compiled into a container.
|
||||
#
|
||||
# **The proxy source sits beside this module.** The canonical proxy, the contract written as something
|
||||
# that runs, lives in this same repository, mesh-controller, at examples/route-proxy (novox/hq 08-connectivity
|
||||
# §3), and the repository is the build context (a module lives whole in one repository, novox/hq ADR 0420),
|
||||
# so this Dockerfile compiles ./examples/route-proxy from the repository root. The build seat hands it only
|
||||
# that program's build source, its import closure, go.mod, go.sum and the vendored packages it uses
|
||||
# (novox/hq ADR 0267, the artifact's `compiles`), so a merge elsewhere in the repository does not
|
||||
# move this image, and a COPY of anything outside it fails by name.
|
||||
#
|
||||
# docker build -f modules/route-proxy/Dockerfile -t mesh-route-proxy:development .
|
||||
#
|
||||
# The mesh pins the digest of what this produces; the committed module.json carries the placeholder
|
||||
# digest every mesh-built image does, replaced at publish.
|
||||
FROM ${GO_BASE} AS build
|
||||
WORKDIR /src
|
||||
COPY go.mod go.sum ./
|
||||
RUN go mod download
|
||||
COPY . .
|
||||
RUN CGO_ENABLED=0 GOOS=linux go build -trimpath -buildvcs=false -ldflags=-buildid= -o /mesh-route-proxy ./examples/route-proxy
|
||||
|
||||
# A small runtime with the public CA roots the ACME client needs to reach a real authority, and run
|
||||
# as root so it can bind :80 and :443 — the two privileged ports a public front door listens on.
|
||||
FROM ${ALPINE_BASE}
|
||||
RUN apk add --no-cache ca-certificates
|
||||
COPY --from=build /mesh-route-proxy /usr/local/bin/mesh-route-proxy
|
||||
ENTRYPOINT ["/usr/local/bin/mesh-route-proxy"]
|
||||
@@ -45,15 +45,15 @@ pinned image is not moved without a decision; mesh-controller's
|
||||
|
||||
## How it ships the Go proxy
|
||||
|
||||
The proxy is a Go program, unlike the TypeScript tool-runtime modules. Its source sits in this same
|
||||
repository, mesh-controller, at `examples/route-proxy`, the contract written as something that runs. This
|
||||
module ships the packaging: a multi-stage [`Dockerfile`](Dockerfile) whose build context is the repository
|
||||
root and which compiles `./examples/route-proxy` into `mesh-route-proxy`. The committed `module.json` carries the
|
||||
placeholder digest every mesh-built image does (`@sha256:0000…`); the mesh pins the real digest at
|
||||
publish.
|
||||
The proxy is a Go program, unlike the TypeScript tool-runtime modules. Its source sits in this module, at
|
||||
`cmd/route-proxy`, in the module's own Go module (`go.mod`, with a `vendor/` directory), the contract written as
|
||||
something that runs. No image is built for it (novox/hq ADR 0480): the `server` artifact is a Go bundle compiled
|
||||
for alpine, an `archive` resource unpacks it onto the machine, and the `route-proxy` container runs the pinned
|
||||
`trust` image (the same alpine digest whose system roots the public account directory is named after) with the
|
||||
archive mounted read-only at `/opt/mesh` and `/opt/mesh/route-proxy` as its program. A new build of the program
|
||||
restarts the container, because the archive is in its `restart-on`.
|
||||
|
||||
In the lab, `mesh-lab/scripts/build-route-proxy-image.sh` builds this into the local daemon as
|
||||
`mesh-route-proxy:development`, and a scenario stocks it and serves it by digest.
|
||||
In the lab, a scenario stocks the same alpine image and serves it by digest.
|
||||
|
||||
## Certificates, and the endpoint (resolves 04-ISSUES/004)
|
||||
|
||||
|
||||
@@ -77,7 +77,8 @@ func TestAConsumerOfARouteIsToldItsNamesFromItsPlanEntry(t *testing.T) {
|
||||
// route-proxy's own files and resources stay as they were (issue 792): the module answers its route through the
|
||||
// helper but is not marked moved, so its acme.env, its broker secret and its containers are composed as today and
|
||||
// the public ingress does not change. Everything of the manifest but its build, what it provides and the state it
|
||||
// keeps is pinned by this digest; changing the ingress means changing it here, on purpose.
|
||||
// keeps is pinned by this digest; changing the ingress means changing it here, on purpose. Re-pinned in R4d (novox/hq
|
||||
// ADR 0480): the program is an archive mounted into the trust image, the container and its files are otherwise as before.
|
||||
func TestRouteProxyIsNotMovedAndKeepsItsOwnFiles(t *testing.T) {
|
||||
raw, err := os.ReadFile("../../module.json")
|
||||
if err != nil {
|
||||
@@ -102,7 +103,7 @@ func TestRouteProxyIsNotMovedAndKeepsItsOwnFiles(t *testing.T) {
|
||||
t.Fatal(err)
|
||||
}
|
||||
sum := sha256.Sum256(pinned)
|
||||
if got := hex.EncodeToString(sum[:]); got != "57a39de0943d8b33b9db6cb998ce97f8793602cca6cdfa5849c1c392390454a3" {
|
||||
if got := hex.EncodeToString(sum[:]); got != "85cb955e5a4b2d8826f50aa76433064a576e8b15b71537032eb93c7388c0ee28" {
|
||||
t.Fatalf("route-proxy's own manifest changed: digest %s", got)
|
||||
}
|
||||
// The two acme templates are pinned the same way (issue 849): they are what the proxy's certificates are asked
|
||||
|
||||
@@ -4,14 +4,14 @@ import (
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"log"
|
||||
"os"
|
||||
"strings"
|
||||
"sync/atomic"
|
||||
"time"
|
||||
|
||||
"github.com/nats-io/nats.go"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/broker"
|
||||
"git.novox.be/novox/mesh-sdk/go/membership"
|
||||
"git.novox.be/novox/mesh-sdk/go/process"
|
||||
)
|
||||
|
||||
// What the mesh issued this proxy, read on the bus (novox/hq ADR 0160, ADR 0167).
|
||||
@@ -21,16 +21,6 @@ import (
|
||||
// network, which is who may be served an internal name. Read once at connect and followed, so a
|
||||
// route added or a machine joining reaches a running proxy without a restart.
|
||||
|
||||
// credential is the bus account the mesh delivered as this module's own secret named broker.
|
||||
type credential struct {
|
||||
URL string `json:"url"`
|
||||
Fingerprint string `json:"fingerprint"`
|
||||
Node string `json:"node"`
|
||||
Module string `json:"module"`
|
||||
User string `json:"user"`
|
||||
Password string `json:"password"`
|
||||
}
|
||||
|
||||
// followMembership connects with the credential in path and applies every membership the mesh
|
||||
// issues this proxy. It retries the first connection for as long as it takes: a proxy that started
|
||||
// before the bus keeps serving the file, and takes the bus when it answers.
|
||||
@@ -46,60 +36,23 @@ func followMembership(path string, held *table, fromBus *atomic.Bool) {
|
||||
}
|
||||
|
||||
func followOnce(path string, held *table, fromBus *atomic.Bool) error {
|
||||
raw, err := os.ReadFile(path)
|
||||
account, err := process.ReadAccount(path)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
var cred credential
|
||||
if err := json.Unmarshal(raw, &cred); err != nil {
|
||||
return fmt.Errorf("the broker credential is not one: %w", err)
|
||||
}
|
||||
if cred.Node == "" || cred.Module == "" {
|
||||
return fmt.Errorf("the broker credential names no node or module, so it has no membership")
|
||||
}
|
||||
|
||||
opts := []nats.Option{
|
||||
nats.Name(cred.Node + "." + cred.Module),
|
||||
nats.UserInfo(cred.User, cred.Password),
|
||||
// Its own inbox, and nothing wider: every principal is granted `_INBOX.<its user>.>` alone.
|
||||
nats.CustomInboxPrefix("_INBOX." + cred.User),
|
||||
// The bus being restarted is an upgrade, not a reason to stop following.
|
||||
nats.MaxReconnects(-1),
|
||||
}
|
||||
if strings.TrimSpace(cred.Fingerprint) != "" {
|
||||
opts = append(opts, nats.Secure(broker.PinnedToFingerprint(cred.Fingerprint)))
|
||||
}
|
||||
conn, err := nats.Connect(cred.URL, opts...)
|
||||
conn, err := process.Connect(account, nats.Name(account.Node+"."+account.Module))
|
||||
if err != nil {
|
||||
return fmt.Errorf("connecting to the bus at %s: %w", broker.BareAddress(cred.URL), err)
|
||||
return fmt.Errorf("connecting to the bus at %s: %w", membership.BareAddress(account.URL), err)
|
||||
}
|
||||
|
||||
subject := broker.MembershipSubject(cred.Node, cred.Module)
|
||||
apply := func(body []byte) {
|
||||
var issued broker.Membership
|
||||
if err := json.Unmarshal(body, &issued); err != nil {
|
||||
log.Printf("a membership arrived that is not one: %v", err)
|
||||
return
|
||||
}
|
||||
subject := membership.Subject(account.Node, account.Module)
|
||||
err = conn.FollowMembership(func(issued membership.Membership) {
|
||||
if took := applyMembership(issued, held); took && !fromBus.Swap(true) {
|
||||
log.Printf("routes now come from this proxy's membership on %s", subject)
|
||||
}
|
||||
}
|
||||
|
||||
// Followed first, read second: an issue landing between the two is applied, not missed.
|
||||
if _, err := conn.Subscribe(subject, func(m *nats.Msg) { apply(m.Data) }); err != nil {
|
||||
}, func(err error) { log.Print(err) })
|
||||
if err != nil {
|
||||
conn.Close()
|
||||
return fmt.Errorf("cannot follow %s: %w", subject, err)
|
||||
}
|
||||
// The subject-addressed direct get: the one request this account may make of the stream.
|
||||
got, err := conn.Request("$JS.API.DIRECT.GET."+broker.AssignmentsStream+"."+subject, nil, 5*time.Second)
|
||||
switch {
|
||||
case err != nil:
|
||||
log.Printf("cannot read the membership issued on %s yet (%v); following it", subject, err)
|
||||
case got.Header.Get("Status") != "" || len(got.Data) == 0:
|
||||
log.Printf("no membership issued on %s yet; serving the file until one is", subject)
|
||||
default:
|
||||
apply(got.Data)
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
@@ -108,7 +61,7 @@ func followOnce(path string, held *table, fromBus *atomic.Bool) error {
|
||||
//
|
||||
// A membership with no routes in it is one from a controller older than ADR 0167, and the file stays
|
||||
// the source rather than every route being withdrawn because a field was absent.
|
||||
func applyMembership(issued broker.Membership, held *table) bool {
|
||||
func applyMembership(issued membership.Membership, held *table) bool {
|
||||
raw, carries := issued.Receives["route"]
|
||||
if !carries {
|
||||
return false
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user