Compare commits

..
Author SHA1 Message Date
jschoubben e56416fa8c The mesh's one resolver: its seat, a provider's address, zones, and a node's hosts file (hq ADR 0194, 0196, 0199)
- mesh-dns-resolver: a mesh seat delivering wildcard-resolution, so every node's resolver
  configuration resolves to its one holder; node-dns-resolver kept until nothing claims it.
- ${bound:<provision>:address}: the providing machine's private address, for the one consumer
  that cannot use a name — a machine's resolver configuration.
- zone: a module declares the zone it answers and the listen that answers it; the controller
  settles it per node, refuses duplicates and shadowing, and hands the resolver .Zones to forward.
- node-hosts-file: a node seat whose holder owns /etc/hosts, with entries/add/remove.
The resolver tests follow the catalogue: no runtime dns (containers copy the machine's resolvers),
live-restore held by resolv-conf, resolv.conf naming the resolver by address then a public one.
2026-10-04 00:38:48 +02:00
73 changed files with 627 additions and 4329 deletions
+2 -8
View File
@@ -1,11 +1,5 @@
# The Go it builds with, pinned here because genesis builds this file with no arguments (novox/hq ARG GO_BASE=golang:1.25-alpine
# issue 223) — the Makefile passes the same digest. A tag older than go.mod asks for is how # The control plane's image.
# `make image` broke once before (issue 146).
ARG GO_BASE=golang@sha256:8ac98ca534ac3f51e1f420a1dd2c15e74c75cfa0f23f3ad27eb5d7236c349a0c
# The control plane's image — for genesis and the lab only. The mesh runs the controller as a Go
# bundle the host starts as a process (module.json; novox/hq issue 213), and builds no image of it.
# Genesis builds this file and raises it as the container the process replaces on the first push
# (mesh-host internal/bootstrap, novox/hq issue 223).
# #
# novox/hq ADR 0006: this image is pinned by digest in the bundle the host carries, fetched on a # novox/hq ADR 0006: this image is pinned by digest in the bundle the host carries, fetched on a
# machine where no mesh exists yet, and run before there is anything to check it against. So it # machine where no mesh exists yet, and run before there is anything to check it against. So it
+4 -8
View File
@@ -27,21 +27,17 @@ build:
IMAGE ?= mesh-controller:$(VERSION) IMAGE ?= mesh-controller:$(VERSION)
DEV_TAG ?= mesh-controller:development DEV_TAG ?= mesh-controller:development
# The Go base the image is built on. # The base the module declares, read from the manifest rather than written here twice.
# #
# **`make image` was broken and stayed broken**, because the Dockerfile's fallback base was a Go # **`make image` was broken and stayed broken**, because the Dockerfile's fallback base was a Go
# older than go.mod asks for: every build died at `go mod download` with "go.mod requires go >= # older than go.mod asks for: every build died at `go mod download` with "go.mod requires go >=
# 1.26.0", and the pipeline never saw it because the pipeline passes the declared base in. Anybody # 1.26.0", and the pipeline never saw it because the pipeline passes the declared base in. Anybody
# building the image by hand hit it and had to find the digest themselves (novox/hq 04-ISSUES/146, # building the image by hand hit it and had to find the digest themselves (novox/hq 04-ISSUES/146,
# what it cost). # what it cost).
# GO_BASE ?= $(shell python3 -c "import json;print(next(o['image'] for o in json.load(open('module.json'))['build']['on'] if o['arg']=='GO_BASE'))" 2>/dev/null)
# **Pinned here since the manifest stopped building an image** (novox/hq issue 213): the mesh builds
# the controller as a Go bundle with its own toolchain, and only `make image` — genesis and the lab —
# still needs a Go base. The digest is the one the manifest declared until then.
GO_BASE ?= golang@sha256:8ac98ca534ac3f51e1f420a1dd2c15e74c75cfa0f23f3ad27eb5d7236c349a0c
image: image:
@test -n "$(GO_BASE)" || { echo "no GO_BASE; pass GO_BASE=<image>"; exit 1; } @test -n "$(GO_BASE)" || { echo "module.json declares no GO_BASE; pass GO_BASE=<image> or fix the manifest"; exit 1; }
docker build --build-arg GO_BASE=$(GO_BASE) --build-arg VERSION=$(VERSION) -t $(IMAGE) -t $(DEV_TAG) . docker build --build-arg GO_BASE=$(GO_BASE) --build-arg VERSION=$(VERSION) -t $(IMAGE) -t $(DEV_TAG) .
@echo @echo
@docker image inspect $(IMAGE) --format 'built {{.RepoTags}} {{.Size}} bytes' @docker image inspect $(IMAGE) --format 'built {{.RepoTags}} {{.Size}} bytes'
@@ -52,7 +48,7 @@ BUILDER_IMAGE ?= mesh-builder:$(VERSION)
BUILDER_DEV_TAG ?= mesh-builder:development BUILDER_DEV_TAG ?= mesh-builder:development
builder-image: builder-image:
@test -n "$(GO_BASE)" || { echo "no GO_BASE; pass GO_BASE=<image>"; exit 1; } @test -n "$(GO_BASE)" || { echo "module.json declares no GO_BASE; pass GO_BASE=<image> or fix the manifest"; exit 1; }
docker build --build-arg GO_BASE=$(GO_BASE) -f cmd/mesh-builder/Dockerfile -t $(BUILDER_IMAGE) -t $(BUILDER_DEV_TAG) . docker build --build-arg GO_BASE=$(GO_BASE) -f cmd/mesh-builder/Dockerfile -t $(BUILDER_IMAGE) -t $(BUILDER_DEV_TAG) .
@echo @echo
@docker image inspect $(BUILDER_IMAGE) --format 'built {{.RepoTags}} {{.Size}} bytes' @docker image inspect $(BUILDER_IMAGE) --format 'built {{.RepoTags}} {{.Size}} bytes'
-7
View File
@@ -193,13 +193,6 @@ passes every check that only looks at the message.
## The image ## The image
**The mesh no longer runs the controller from it** (novox/hq issue 213). The module declares a Go
bundle, `controller`, which the host on the controller's machine unpacks and runs as the process
`mesh-controller` under the account of the same name (ADR 0188 §1, §3). The image stays for what
still runs a container of the controller: genesis, which raises the first controller from it and
installs the module from its manifest (mesh-host `internal/bootstrap`), and the lab. Neither is the
mesh's own build any more — `make image` builds it.
`FROM scratch`, holding one statically linked binary and nothing else — no shell, no package `FROM scratch`, holding one statically linked binary and nothing else — no shell, no package
manager, no libc, no CA certificates. manager, no libc, no CA certificates.
+6 -6
View File
@@ -145,7 +145,7 @@ func TestTheRegistryTrustAndEveryImageFollowThePortTheNodeGaveTheStore(t *testin
// //
// Composed from the control plane's own manifest against a real inventory: the store's module is // Composed from the control plane's own manifest against a real inventory: the store's module is
// given 6852 on this node the way genesis or an operator gives it, and the control plane's // given 6852 on this node the way genesis or an operator gives it, and the control plane's
// process is told so beside the sealed connection genesis wrote. // container is told so beside the sealed connection genesis wrote.
func TestTheControlPlaneIsToldWhereTheNodePutTheStoreAndTheBroker(t *testing.T) { func TestTheControlPlaneIsToldWhereTheNodePutTheStoreAndTheBroker(t *testing.T) {
open := aMesh(t) open := aMesh(t)
ctx := t.Context() ctx := t.Context()
@@ -157,8 +157,8 @@ func TestTheControlPlaneIsToldWhereTheNodePutTheStoreAndTheBroker(t *testing.T)
if err != nil { if err != nil {
t.Fatal(err) t.Fatal(err)
} }
control, err := withSeatPorts(m).Resolve([]catalogue.Built{{Name: "controller", Kind: catalogue.ArtifactBundle, control, err := withSeatPorts(m).Resolve([]catalogue.Built{{Name: "server", Kind: catalogue.ArtifactImage,
Reference: "https://registry.example/mesh-controller/controller.tar.gz", Digest: aDigest}}) Reference: "registry.example/control@" + aDigest}})
if err != nil { if err != nil {
t.Fatal(err) t.Fatal(err)
} }
@@ -200,12 +200,12 @@ func TestTheControlPlaneIsToldWhereTheNodePutTheStoreAndTheBroker(t *testing.T)
var env map[string]any var env map[string]any
for _, r := range composed(t, open, "anchor").Resources { for _, r := range composed(t, open, "anchor").Resources {
if r["id"] == "mesh-controller.controller" { if r["id"] == "mesh-controller.server" {
env, _ = r["env"].(map[string]any) env, _ = r["env"].(map[string]any)
} }
} }
if env == nil { if env == nil {
t.Fatal("the control plane's process is not in its own node's declaration") t.Fatal("the control plane's container is not in its own node's declaration")
} }
for key, want := range map[string]string{ for key, want := range map[string]string{
"MESH_STORE_INVENTORY_PORT": "6852", "MESH_STORE_INVENTORY_PORT": "6852",
@@ -238,7 +238,7 @@ func withSeatPorts(m catalogue.Manifest) catalogue.Manifest {
out := m out := m
out.Resources = nil out.Resources = nil
for _, r := range m.Resources { for _, r := range m.Resources {
if r["type"] != "container" && r["type"] != "process" { if r["type"] != "container" {
out.Resources = append(out.Resources, r) out.Resources = append(out.Resources, r)
continue continue
} }
+2 -18
View File
@@ -148,11 +148,6 @@ func buildFrom(result link.BuildResult) inventory.Build {
// rebuild the graph rather than a list of names. // rebuild the graph rather than a list of names.
Path: result.Path, Path: result.Path,
} }
// When it was asked, which is what orders it against another build of the same module
// (novox/hq 04-ISSUES/219) — not when it was heard.
if asked, ok := link.BuildAskedAt(result.ID); ok {
kept.Asked = asked
}
for _, ref := range result.Against { for _, ref := range result.Against {
kept.Against = append(kept.Against, catalogue.Recorded(ref)) kept.Against = append(kept.Against, catalogue.Recorded(ref))
} }
@@ -414,7 +409,7 @@ func buildOne(ctx context.Context, source buildSource, path, ref string, wait ti
// Correlated by something the control plane makes, not by the module's name: two builds of one // Correlated by something the control plane makes, not by the module's name: two builds of one
// module can be in flight, and the second answer is not the first one's. // module can be in flight, and the second answer is not the first one's.
request := link.BuildRequest{ request := link.BuildRequest{
ID: link.NewBuildID(time.Now()), ID: fmt.Sprintf("%s-%d", "build", time.Now().UnixNano()),
Repository: repository, Repository: repository,
Path: path, Path: path,
Ref: ref, Ref: ref,
@@ -531,9 +526,6 @@ func takeIn(ctx context.Context, inv *inventory.Inventory, result link.BuildResu
BuiltFrom: result.Commit, Head: result.Commit, BuiltFrom: result.Commit, Head: result.Commit,
// What it stood on, so registration can judge a built manifest's base (to-be 38 WP2.4). // What it stood on, so registration can judge a built manifest's base (to-be 38 WP2.4).
Against: kept.Against, Against: kept.Against,
// When it was asked, so an older request heard later does not replace a newer one
// (novox/hq 04-ISSUES/219).
Asked: kept.Asked,
} }
if result.Source != nil && result.Source.Seat != "" { if result.Source != nil && result.Source.Seat != "" {
recorded.Repository, recorded.Seat = result.Source.Repository, result.Source.Seat recorded.Repository, recorded.Seat = result.Source.Repository, result.Source.Seat
@@ -552,16 +544,8 @@ func takeIn(ctx context.Context, inv *inventory.Inventory, result link.BuildResu
result.On, result.Repository, short(result.Commit), err) result.On, result.Repository, short(result.Commit), err)
} }
if err := inv.RegisterModule(ctx, manifest, recorded); err != nil { if err := inv.RegisterModule(ctx, manifest, recorded); err != nil {
if errors.Is(err, inventory.ErrSuperseded) {
return manifest, kept, fmt.Errorf("%s built %s (%s), recorded and not registered: %w",
result.On, manifest.Module, short(result.Commit), err)
}
return manifest, kept, err return manifest, kept, err
} }
// The keep set just moved, and new bytes just landed (novox/hq ADR 0189). Asked here rather
// than on a timer of its own: this is the only moment either is true. Never fatal — the build
// worked and the module is registered.
collect(ctx, inv)
return manifest, kept, nil return manifest, kept, nil
} }
@@ -589,7 +573,7 @@ func buildAndShow(ctx context.Context, source buildSource, path, ref string, wai
defer ask.Close() defer ask.Close()
result, err := ask.Submit(ctx, link.BuildRequest{ result, err := ask.Submit(ctx, link.BuildRequest{
ID: link.NewBuildID(time.Now()), ID: fmt.Sprintf("%s-%d", "build", time.Now().UnixNano()),
Repository: repository, Path: path, Ref: ref, Repository: repository, Path: path, Ref: ref,
Held: heldBy(ctx), Seats: seatBases(ctx), Held: heldBy(ctx), Seats: seatBases(ctx),
}, wait) }, wait)
-50
View File
@@ -2,12 +2,9 @@ package main
import ( import (
"encoding/json" "encoding/json"
"errors"
"strings" "strings"
"testing" "testing"
"time"
"github.com/novox/mesh-controller/internal/inventory"
"github.com/novox/mesh-controller/internal/link" "github.com/novox/mesh-controller/internal/link"
) )
@@ -103,50 +100,3 @@ func TestABuildAtACommitKeepsTheBranchTheModuleFollows(t *testing.T) {
t.Errorf("a module first built at a commit follows %q, want the default branch", src.Ref) t.Errorf("a module first built at a commit follows %q, want the default branch", src.Ref)
} }
} }
// novox/hq 04-ISSUES/219: an older request heard after a newer one is recorded and not registered,
// so a push sends what the newer request built.
func TestAnOlderBuildHeardLaterDoesNotReplaceTheNewer(t *testing.T) {
open := aMesh(t)
ctx := t.Context()
older := time.Date(2026, 10, 3, 21, 33, 45, 0, time.UTC)
newer := time.Date(2026, 10, 3, 21, 51, 57, 0, time.UTC)
result := func(asked time.Time, image string) link.BuildResult {
manifest, _ := json.Marshal(map[string]any{"module": "postgres", "version": image})
return link.BuildResult{ID: link.NewBuildID(asked), Repository: "http://forge.internal:20000/novox/mesh-catalog.git",
Path: "modules/postgres", Ref: "main", On: "anchor", Commit: "efff5415", Manifest: manifest,
Source: &link.SourceOnSeat{Seat: "git", Repository: "novox/mesh-catalog"}}
}
if _, _, err := takeIn(ctx, open.inventory, result(newer, "4bcd5f73")); err != nil {
t.Fatal(err)
}
_, _, err := takeIn(ctx, open.inventory, result(older, "0ab07fa9"))
if !errors.Is(err, inventory.ErrSuperseded) {
t.Fatalf("the older request's outcome was taken in as current: %v", err)
}
shelf, err := open.inventory.Catalogue(ctx)
if err != nil {
t.Fatal(err)
}
if got := shelf["postgres"].Version; got != "4bcd5f73" {
t.Errorf("postgres is %q; want the newer request's 4bcd5f73", got)
}
if builds, _ := open.inventory.Builds(ctx, "postgres", 5); len(builds) != 2 {
t.Errorf("the late build was not recorded: %v", builds)
}
}
func TestABuildIDSaysWhenItWasAsked(t *testing.T) {
at := time.Date(2026, 10, 3, 21, 51, 57, 392539762, time.UTC)
if got, ok := link.BuildAskedAt(link.NewBuildID(at)); !ok || !got.Equal(at) {
t.Errorf("read back %v %v; want %v", got, ok, at)
}
if got, ok := link.BuildAskedAt("build-1791064317392539762"); !ok || got.Format(time.TimeOnly) != "21:51:57" {
t.Errorf("the incident's id reads as %v %v", got, ok)
}
for _, id := range []string{"b-1", "build-2", "build-", "build-x", ""} {
if _, ok := link.BuildAskedAt(id); ok {
t.Errorf("%q read as a request time", id)
}
}
}
-12
View File
@@ -7,7 +7,6 @@ import (
"os" "os"
"path/filepath" "path/filepath"
"sort" "sort"
"strings"
"github.com/novox/mesh-controller/internal/catalogue" "github.com/novox/mesh-controller/internal/catalogue"
) )
@@ -91,17 +90,6 @@ func moduleCheck(paths []string, out io.Writer) error {
if len(m.Invokes) > 0 { if len(m.Invokes) > 0 {
fmt.Fprintf(out, ", invokes %s", joinInvokes(m.Invokes)) fmt.Fprintf(out, ", invokes %s", joinInvokes(m.Invokes))
} }
// The state it keeps and reads (novox/hq ADR 0201), so a reviewer sees what lands on the bus.
if len(m.State) > 0 {
kept := make([]string, 0, len(m.State))
for _, s := range m.State {
kept = append(kept, s.Name)
}
fmt.Fprintf(out, ", keeps state %s", strings.Join(kept, ", "))
}
if len(m.Reads) > 0 {
fmt.Fprintf(out, ", reads %s", strings.Join(m.Reads, ", "))
}
fmt.Fprintln(out) fmt.Fprintln(out)
} }
if failed > 0 { if failed > 0 {
-108
View File
@@ -1,108 +0,0 @@
package main
import (
"context"
"errors"
"fmt"
"os"
"time"
"github.com/novox/mesh-controller/internal/artifacts"
"github.com/novox/mesh-controller/internal/inventory"
)
// Letting the artifact store go of what the mesh no longer keeps (novox/hq ADR 0189, issue 108).
//
// **Run where the records change.** A build is the moment new bytes landed in the store and the
// moment the keep set moved, so it is the moment to say what may go — and it needs no timer of
// its own. Reclaiming the bytes is the store's own nightly step; this only decides.
//
// Never fatal to a build. The build succeeded, the module is registered, and a store that could
// not be reached is a thing to say rather than a reason to undo any of that. The next build asks
// again, and the references it could not collect are still uncollected, so nothing is lost by
// having failed.
// collect asks the store to let go of everything the mesh made and no longer keeps, and records
// what it let go of. Says what it did and what it could not; returns nothing, because nothing
// upstream should branch on it.
func collect(ctx context.Context, inv *inventory.Inventory) {
references, err := inv.ToCollect(ctx)
if err != nil {
fmt.Fprintf(os.Stderr, "could not work out what the artifact store may let go of: %v\n", err)
return
}
if len(references) == 0 {
return
}
shelf, err := inv.Catalogue(ctx)
if err != nil {
fmt.Fprintf(os.Stderr, "could not read the catalogue to find the artifact store: %v\n", err)
return
}
// As the mesh reaches it from the network. Empty means the store is not on the network — on a
// mesh being raised it is not yet, and there the store holds one build of anything and has
// nothing to collect.
address, err := artifactStoreAddress(ctx, inv, shelf, "")
if err != nil || address == "" {
if err != nil {
fmt.Fprintf(os.Stderr, "could not find the artifact store to collect from: %v\n", err)
}
return
}
// **Bounded, because this runs inside somebody's build.** The first sweep of a mesh that has
// never collected has the whole history to get through, and a person waiting on `build` should
// not pay for it. Two bounds, and what is left over is simply offered again next time —
// builds are frequent, and the point is that the store stops growing, not that it empties
// tonight.
within, stop := context.WithTimeout(ctx, sweepBudget)
defer stop()
store := artifacts.Store{Address: address}
var done []string
var left int
for i, reference := range references {
if i >= mostPerSweep || within.Err() != nil {
left = len(references) - i
break
}
err := store.LetGo(within, reference)
if err == nil || errors.Is(err, artifacts.Gone) {
// Gone is the outcome wanted, already true. Recorded so the next sweep does not ask
// again for ever.
done = append(done, reference)
continue
}
// **Stopped at the first refusal, not pushed through.** A store that refuses one refuses
// all of them — deletion disabled, the store down, the network gone — so going on would
// be a hundred identical failures and a hundred identical log lines in front of whoever
// was building something.
fmt.Fprintf(os.Stderr, "the artifact store kept %s, so nothing more was asked of it: %v\n",
reference, err)
left = len(references) - i
break
}
if len(done) > 0 {
// Recorded outside `within`: the deletions happened, and losing the record of them because
// the sweep ran out of budget would mean asking about them again for ever.
if err := inv.MarkCollected(ctx, done); err != nil {
fmt.Fprintf(os.Stderr, "the store let go of %d artifact(s) and the record of it did not keep: %v\n",
len(done), err)
return
}
fmt.Fprintf(os.Stderr, "the artifact store let go of %d artifact(s) the mesh no longer keeps\n",
len(done))
}
if left > 0 {
fmt.Fprintf(os.Stderr, "%d more to collect; the next build asks again\n", left)
}
}
// mostPerSweep is how many artifacts one sweep will ask about. Enough that a mesh building
// several times a day converges within days of this landing; small enough that no single build
// waits on the whole backlog.
const mostPerSweep = 200
// sweepBudget is the longest a sweep will keep a build waiting.
const sweepBudget = 60 * time.Second
+3 -13
View File
@@ -8,7 +8,6 @@ package main
import ( import (
"context" "context"
"errors"
"flag" "flag"
"fmt" "fmt"
"os" "os"
@@ -254,34 +253,25 @@ func parseAround(set *flag.FlagSet, args []string) ([]string, error) {
// became of a build nobody was watching. // became of a build nobody was watching.
func (b builds) Built(ctx context.Context, result link.BuildResult) error { func (b builds) Built(ctx context.Context, result link.BuildResult) error {
manifest, _, err := takeIn(ctx, b.inv, result) manifest, _, err := takeIn(ctx, b.inv, result)
// When it was asked, so a plan takes as its outcome only a build asked for it or after it
// (novox/hq 04-ISSUES/219). Zero when the id does not say.
asked, _ := link.BuildAskedAt(result.ID)
switch { switch {
case err != nil && result.Failed != "": case err != nil && result.Failed != "":
fmt.Printf("%s: %v\n", result.ID, err) fmt.Printf("%s: %v\n", result.ID, err)
if result.Module != "" { if result.Module != "" {
planBuilt(ctx, b.open, result.Module, result.Commit, result.Failed, asked) planBuilt(ctx, b.open, result.Module, result.Commit, result.Failed)
} else { } else {
planFailedBuild(ctx, b.open, result) planFailedBuild(ctx, b.open, result)
} }
return nil return nil
case errors.Is(err, inventory.ErrSuperseded):
// Not a failure: the module is already at what a later request built. A plan that asked
// before that later request is answered by it; one that asked after it ignores this.
fmt.Printf("%s: %v\n", result.ID, err)
planBuilt(ctx, b.open, manifest.Module, result.Commit, "", asked)
return nil
case err != nil: case err != nil:
fmt.Printf("%s: heard and recorded, and not registered: %v\n", result.ID, err) fmt.Printf("%s: heard and recorded, and not registered: %v\n", result.ID, err)
if manifest.Module != "" { if manifest.Module != "" {
planBuilt(ctx, b.open, manifest.Module, result.Commit, err.Error(), asked) planBuilt(ctx, b.open, manifest.Module, result.Commit, err.Error())
} }
return nil return nil
} }
fmt.Printf("%s: %s %s registered, built on %s from %s\n", fmt.Printf("%s: %s %s registered, built on %s from %s\n",
result.ID, manifest.Module, manifest.Version, result.On, short(result.Commit)) result.ID, manifest.Module, manifest.Version, result.On, short(result.Commit))
saysWhenThePolicyActs(ctx, b.inv, manifest.Module) saysWhenThePolicyActs(ctx, b.inv, manifest.Module)
planBuilt(ctx, b.open, manifest.Module, result.Commit, "", asked) planBuilt(ctx, b.open, manifest.Module, result.Commit, "")
return nil return nil
} }
+8 -8
View File
@@ -254,11 +254,10 @@ func theResolver(t *testing.T) catalogue.Manifest {
return m return m
} }
// The resolver is handed every machine on the private network as a wildcard, the same set and the // The resolver is handed every machine on the private network as a wildcard, and is handed it again
// same source as the hosts file, and is handed it again when a machine leaves — through the // when a machine leaves — through the module's own manifest asking for the fact, with no module of the
// module's own manifest asking for the fact, with no module of the mesh's own in between (hal // mesh's own in between (hal dnsmasq-app conversion, novox/hq 08-connectivity). It is the mesh's one
// dnsmasq-app conversion, novox/hq 08-connectivity). The runtime on that machine is pointed at the // resolver (ADR 0194), and the container runtime is given no resolver of its own (ADR 0196).
// machine's own address, where the resolver answers for its containers.
func TestTheResolverIsToldEveryMachineOnTheNetworkAndToldAgainWhenOneLeaves(t *testing.T) { func TestTheResolverIsToldEveryMachineOnTheNetworkAndToldAgainWhenOneLeaves(t *testing.T) {
open := aMesh(t) open := aMesh(t)
ctx := t.Context() ctx := t.Context()
@@ -293,11 +292,12 @@ func TestTheResolverIsToldEveryMachineOnTheNetworkAndToldAgainWhenOneLeaves(t *t
t.Errorf("the resolver's machines lack %q:\n%s", want, first) t.Errorf("the resolver's machines lack %q:\n%s", want, first)
} }
} }
// The container runtime is given no resolver of its own (novox/hq ADR 0196): it copies its
// machine's, which name the mesh's resolver first. A `dns` key would be a second account of where a
// container asks, read only when the runtime starts.
for _, r := range composed(t, open, "anchor").Resources { for _, r := range composed(t, open, "anchor").Resources {
if r["id"] == "dnsmasq.runtime-dns" { if r["id"] == "dnsmasq.runtime-dns" {
if !strings.Contains(r["content"].(string), `"10.77.0.1"`) || r["into"] != "json" { t.Errorf("the resolver still writes the runtime's own dns: %v", r)
t.Errorf("the runtime is not pointed at this machine's own address, written into its file: %v", r)
}
} }
} }
+74 -2
View File
@@ -657,6 +657,13 @@ func renderingFor(ctx context.Context, open *stores, node string,
machines[name] = at machines[name] = at
} }
// And every zone a module in the mesh answers itself (novox/hq ADR 0199), for the mesh's resolver
// to forward.
zones, err := zonesInTheMesh(ctx, open)
if err != nil {
return catalogue.Rendering{}, inventory.Node{}, err
}
// **The bus is never public** (novox/hq ADR 0169). It was a foundation port — widened from the // **The bus is never public** (novox/hq ADR 0169). It was a foundation port — widened from the
// broker's own `from: mesh` to from-anywhere on the broker's host, so a machine could enrol // broker's own `from: mesh` to from-anywhere on the broker's host, so a machine could enrol
// before it had an address on the private network. A machine joins through the tunnel now, and // before it had an address on the private network. A machine joins through the tunnel now, and
@@ -726,14 +733,79 @@ func renderingFor(ctx context.Context, open *stores, node string,
BusMembership: memberships[node], BusMembership: memberships[node],
Settings: settings, Generators: gens, Grants: grants, Needed: needed, Ports: ports, Settings: settings, Generators: gens, Grants: grants, Needed: needed, Ports: ports,
Certificate: certificate, Authority: authority, Mesh: private, Names: names, Certificate: certificate, Authority: authority, Mesh: private, Names: names,
Machines: machines, Machines: machines, Zones: zones,
Suffix: overlay.Suffix(), MeshRange: meshRange, TunnelInterface: overlay.Interface, Accounts: accounts, Foundation: foundation, Suffix: overlay.Suffix(), MeshRange: meshRange, TunnelInterface: overlay.Interface, Accounts: accounts, Foundation: foundation,
Kept: kept, Adopted: record.Adopted, OutwardLinks: outwardLinks, Kept: kept, Adopted: record.Adopted, OutwardLinks: outwardLinks,
Given: given, Taken: taken, Seats: seats, ArtifactStore: artifactStore, Built: built, Given: given, Taken: taken, Seats: seats, ArtifactStore: artifactStore, Built: built,
BusUsers: busUsers, BusUsers: busUsers,
}, record, nil }, record, nil
} }
// zonesInTheMesh is every zone a module in the mesh declares, where the mesh placed it (novox/hq ADR
// 0199): the zone settled from that node's settings, the node's private address, the port the
// answering listen is published on there.
//
// Read across every machine's resolution, as the roster once read routed names: a node whose set does
// not compose declares nothing and is passed over, so one broken machine does not cost the rest their
// zones; a store that cannot be read is raised, naming the machine, because returning the zones
// without it would withdraw them from the resolver as if the operator had (novox/hq 04-ISSUES/152).
// What the mesh refuses about the zones together — one declared twice, one shadowing the mesh's
// suffix or a node's public domain — is refused here, by name.
func zonesInTheMesh(ctx context.Context, open *stores) ([]catalogue.ZoneAt, error) {
inv := open.inventory
places, err := inv.Overlays(ctx)
if err != nil {
return nil, fmt.Errorf("where the machines are cannot be read: %w", err)
}
address := map[string]string{}
for _, p := range places {
if strings.TrimSpace(p.Address) != "" {
address[p.Name] = p.Address
}
}
nodes, err := inv.Nodes(ctx)
if err != nil {
return nil, fmt.Errorf("which machines the mesh has cannot be read: %w", err)
}
var zones []catalogue.ZoneAt
var public []string
for _, n := range nodes {
plan, _, err := planFor(ctx, open, n.Name)
switch {
case unresolvable(err):
continue
case err != nil:
return nil, fmt.Errorf("the zones %s answers cannot be read: %w", n.Name, err)
}
if plan.PublicDomain != "" {
public = append(public, plan.PublicDomain)
}
for _, m := range plan.Modules {
if m.Zone == nil {
continue
}
at := address[n.Name]
if at == "" {
// Not on the private network yet: nothing could reach its answerer.
continue
}
published, layers, err := portsGivenOn(ctx, inv, n.Name, m)
if err != nil {
return nil, fmt.Errorf("the zone %s declares on %s cannot be read: %w", m.Module, n.Name, err)
}
z, err := catalogue.ZoneOn(m, layers, published, n.Name, at)
if err != nil {
return nil, err
}
zones = append(zones, *z)
}
}
if problems := catalogue.ZonesProblems(zones, overlay.Suffix(), public); len(problems) > 0 {
return nil, fmt.Errorf("the mesh's zones cannot be forwarded:\n - %s", strings.Join(problems, "\n - "))
}
return zones, nil
}
// certificateFor is what the mesh certifies about one machine's internal name. // certificateFor is what the mesh certifies about one machine's internal name.
// //
// It reaches across two contexts and reads neither one's store from the other: `inventory` knows // It reaches across two contexts and reads neither one's store from the other: `inventory` knows
@@ -1,47 +0,0 @@
package main
import (
"testing"
"time"
"github.com/novox/mesh-controller/internal/inventory"
)
// novox/hq issue 213: for the moment a machine hands its controller over, the container and the
// process both run the plan timer on one store. Only the one holding the plans moves them; the other
// leaves them alone, and moves them once they are let go.
func TestAControllerLeavesThePlansToTheOneHoldingThem(t *testing.T) {
open := aMesh(t)
ctx := t.Context()
now := time.Now().UTC()
// Every tier done: the next step is the plan's last, and needs nothing but the store.
plan := inventory.Plan{ID: "plan-213", Repository: "r", Commit: "abc", Created: now, Updated: now,
State: inventory.PlanRolling, Tier: 1, Tiers: [][]string{{"app"}},
Modules: map[string]*inventory.PlanModule{"app": {State: "built"}}}
if err := open.inventory.SavePlan(ctx, plan); err != nil {
t.Fatal(err)
}
// The other controller: its own connections to the same store, holding the plans.
other, err := inventory.Open(ctx)
if err != nil {
t.Fatal(err)
}
t.Cleanup(other.Close)
release, err := other.HoldPlans(ctx, false)
if err != nil {
t.Fatal(err)
}
t.Cleanup(release) // before the close above: a pool waits for a connection still held
advancePlans(ctx, open)
if p, err := open.inventory.PlanByID(ctx, "plan-213"); err != nil || !p.Open() {
t.Fatalf("a controller moved a plan another held: %+v %v", p, err)
}
release()
advancePlans(ctx, open)
if p, err := open.inventory.PlanByID(ctx, "plan-213"); err != nil || p.State != inventory.PlanDone {
t.Fatalf("the plan did not move once it was let go: %+v %v", p, err)
}
}
+2 -17
View File
@@ -898,21 +898,6 @@ func raiseTheBus(ctx context.Context, inv *inventory.Inventory, address string)
if err := broker.RaiseSeats(js, inventory.MeshSeats(), holders); err != nil { if err := broker.RaiseSeats(js, inventory.MeshSeats(), holders); err != nil {
return err return err
} }
// Every module's state (novox/hq ADR 0201), from the catalogue: a bucket exists from
// registration, so a module reading one may watch it before its owner runs anywhere. One that
// nothing declares any more is said and kept — what it holds is data.
buckets, err := inv.DeclaredBuckets(ctx)
if err != nil {
return err
}
undeclared, err := broker.RaiseBuckets(js, buckets)
if err != nil {
return err
}
if len(undeclared) > 0 {
fmt.Printf("the bus holds state nothing declares any more, kept because it is data: %s — "+
"removing it is a person's act\n", strings.Join(undeclared, ", "))
}
// And how every module hears what it consumes. Derived from the same records the user list is // And how every module hears what it consumes. Derived from the same records the user list is
// composed from, so a module the mesh grants a consumer's subjects has that consumer waiting. // composed from, so a module the mesh grants a consumer's subjects has that consumer waiting.
// Done on every raise, not only when a credential is issued: every module moved onto this bus // Done on every raise, not only when a credential is issued: every module moved onto this bus
@@ -936,8 +921,8 @@ func raiseTheBus(ctx context.Context, inv *inventory.Inventory, address string)
} }
hearing++ hearing++
} }
fmt.Printf("the bus at %s has its streams, %d machine(s) can hear a declaration, %d module(s) "+ fmt.Printf("the bus at %s has its streams, %d machine(s) can hear a declaration, and %d module(s) "+
"can hear what they consume, and %d bucket(s) of state\n", broker.BareAddress(address), len(names), hearing, len(buckets)) "can hear what they consume\n", broker.BareAddress(address), len(names), hearing)
return nil return nil
} }
+3 -64
View File
@@ -2,7 +2,6 @@ package main
import ( import (
"context" "context"
"errors"
"flag" "flag"
"fmt" "fmt"
"sort" "sort"
@@ -289,23 +288,8 @@ func askTier(ctx context.Context, inv *inventory.Inventory, p *inventory.Plan) e
// planBuilt marks a module built (or failed) in every open plan whose current tier holds it, and // planBuilt marks a module built (or failed) in every open plan whose current tier holds it, and
// advances what that completes. Called from the daemon's take-in of every outcome. // advances what that completes. Called from the daemon's take-in of every outcome.
// func planBuilt(ctx context.Context, open *stores, module, commit, failed string) {
// **Only a build asked at or after the plan's ask is its outcome** (novox/hq 04-ISSUES/219). Two
// plans a few minutes apart both ask for a module; the earlier plan's build, finishing late, is not
// the later plan's answer — it stood on the bases from before the later plan's merge, and taking it
// would send machines, and the next tier, what the later merge replaced. asked is zero when the
// build's request time is not known, and such an outcome is taken as before.
func planBuilt(ctx context.Context, open *stores, module, commit, failed string, asked time.Time) {
inv := open.inventory inv := open.inventory
// One controller works the plans at a time (novox/hq issue 213); an outcome waits its turn rather
// than write over what the holder is about to save. Not taken, it is still in the build records,
// which the holder settles the plan from (issue 214).
release, err := inv.HoldPlans(ctx, true)
if err != nil {
fmt.Printf("plans: %s's outcome is left to the build records: %v\n", module, err)
return
}
defer release()
plans, err := inv.OpenPlans(ctx) plans, err := inv.OpenPlans(ctx)
if err != nil { if err != nil {
fmt.Printf("plans: cannot read them: %v\n", err) fmt.Printf("plans: cannot read them: %v\n", err)
@@ -331,9 +315,6 @@ func planBuilt(ctx context.Context, open *stores, module, commit, failed string,
state = &inventory.PlanModule{} state = &inventory.PlanModule{}
p.Modules[module] = state p.Modules[module] = state
} }
if askedBefore(asked, state.AskedAt) {
continue
}
if failed != "" { if failed != "" {
state.State = "failed" state.State = "failed"
state.Why = failed state.Why = failed
@@ -352,30 +333,13 @@ func planBuilt(ctx context.Context, open *stores, module, commit, failed string,
fmt.Printf("%s: %s; the tiers after it are not asked\n", p.ID, p.Note) fmt.Printf("%s: %s; the tiers after it are not asked\n", p.ID, p.Note)
} }
} }
advanceHeld(ctx, open) advancePlans(ctx, open)
} }
// advancePlans moves every open plan as far as the facts allow: a tier whose modules are all built // advancePlans moves every open plan as far as the facts allow: a tier whose modules are all built
// and whose gates are applied gives way to the next; the last tier done is the plan done. Called // and whose gates are applied gives way to the next; the last tier done is the plan done. Called
// after every outcome and on a timer, so a plan waiting on a machine's report moves when it comes. // after every outcome and on a timer, so a plan waiting on a machine's report moves when it comes.
//
// **One controller at a time** (novox/hq issue 213). A plan is read, changed and saved whole; two
// controllers — the old and the new while a machine hands its controller over — would each ask a
// tier the other had just asked. Taken without waiting: whoever holds the plans is moving them.
func advancePlans(ctx context.Context, open *stores) { func advancePlans(ctx context.Context, open *stores) {
release, err := open.inventory.HoldPlans(ctx, false)
if err != nil {
if !errors.Is(err, inventory.ErrPlansBusy) {
fmt.Printf("plans: cannot hold them: %v\n", err)
}
return
}
defer release()
advanceHeld(ctx, open)
}
// advanceHeld is advancePlans for a caller already holding the plans.
func advanceHeld(ctx context.Context, open *stores) {
inv := open.inventory inv := open.inventory
plans, err := inv.OpenPlans(ctx) plans, err := inv.OpenPlans(ctx)
if err != nil { if err != nil {
@@ -585,8 +549,7 @@ func planFailedBuild(ctx context.Context, open *stores, result link.BuildResult)
} }
for _, e := range entries { for _, e := range entries {
if repositoryMatches(e.Source.Repository, result.Repository) && e.Source.Path == result.Path { if repositoryMatches(e.Source.Repository, result.Repository) && e.Source.Path == result.Path {
asked, _ := link.BuildAskedAt(result.ID) planBuilt(ctx, open, e.Manifest.Module, result.Commit, result.Failed)
planBuilt(ctx, open, e.Manifest.Module, result.Commit, result.Failed, asked)
return return
} }
} }
@@ -703,19 +666,6 @@ func plansCommand(ctx context.Context, args []string) error {
} }
p.State = inventory.PlanFailed p.State = inventory.PlanFailed
p.Note = "stopped by hand at tier " + fmt.Sprint(p.Tier) p.Note = "stopped by hand at tier " + fmt.Sprint(p.Tier)
release, err := inv.HoldPlans(ctx, true)
if err != nil {
return err
}
defer release()
if p, err = inv.PlanByID(ctx, positionals[1]); err != nil {
return err
}
if !p.Open() {
return fmt.Errorf("%s is already %s", p.ID, p.State)
}
p.State = inventory.PlanFailed
p.Note = "stopped by hand at tier " + fmt.Sprint(p.Tier)
if err := inv.SavePlan(ctx, p); err != nil { if err := inv.SavePlan(ctx, p); err != nil {
return err return err
} }
@@ -841,11 +791,6 @@ func settleFromRecords(p *inventory.Plan, tier []string, recorded map[string][]i
if b.At.Before(*s.AskedAt) { if b.At.Before(*s.AskedAt) {
break break
} }
// Recorded after the ask and asked before it: an earlier ask's late outcome, not this
// one's (novox/hq 04-ISSUES/219).
if askedBefore(b.Asked, s.AskedAt) {
continue
}
outcome = &b outcome = &b
} }
if outcome == nil { if outcome == nil {
@@ -867,9 +812,3 @@ func settleFromRecords(p *inventory.Plan, tier []string, recorded map[string][]i
} }
return changed return changed
} }
// askedBefore is whether a build asked at asked was asked before a plan asked for its module — and
// so is not that plan's outcome (novox/hq 04-ISSUES/219). False when either time is not known.
func askedBefore(asked time.Time, planAsked *time.Time) bool {
return !asked.IsZero() && planAsked != nil && asked.Before(*planAsked)
}
-18
View File
@@ -155,24 +155,6 @@ func TestAPlanSettlesAnAskedBuildFromTheRecords(t *testing.T) {
t.Errorf("an ask with no record after it was settled: %+v", s) t.Errorf("an ask with no record after it was settled: %+v", s)
} }
// novox/hq 04-ISSUES/219: a build recorded after the ask but asked before it — an earlier
// plan's late outcome — is not this ask's, built or failed.
r := inventory.Plan{ID: "plan-3", Tiers: [][]string{{"postgres"}},
Modules: map[string]*inventory.PlanModule{"postgres": {State: "asked", AskedAt: &asked}}}
late := map[string][]inventory.Build{"postgres": {
{ID: "build-old", Commit: "efff5415", Asked: asked.Add(-18 * time.Minute), At: asked.Add(12 * time.Minute)},
}}
if settleFromRecords(&r, r.Tiers[0], late) || r.Modules["postgres"].State != "asked" {
t.Errorf("an earlier ask's late outcome settled this ask: %+v", r.Modules["postgres"])
}
// Newest heard first: the earlier ask's late outcome, then this ask's own, heard before it.
late["postgres"] = append(late["postgres"], inventory.Build{ID: "build-mine", Commit: "4bcd5f73",
Asked: asked.Add(time.Second), At: asked.Add(5 * time.Minute)})
if !settleFromRecords(&r, r.Tiers[0], late) || r.Modules["postgres"].State != "built" ||
r.Modules["postgres"].Commit != "4bcd5f73" {
t.Errorf("this ask's own outcome, heard before the earlier ask's, did not settle it: %+v", r.Modules["postgres"])
}
// A failure recorded after the ask fails the plan, as hearing it would have. // A failure recorded after the ask fails the plan, as hearing it would have.
q := inventory.Plan{ID: "plan-2", Tiers: [][]string{{"x"}}, q := inventory.Plan{ID: "plan-2", Tiers: [][]string{{"x"}},
Modules: map[string]*inventory.PlanModule{"x": {State: "asked", AskedAt: &asked}}} Modules: map[string]*inventory.PlanModule{"x": {State: "asked", AskedAt: &asked}}}
-7
View File
@@ -315,13 +315,6 @@ func (f following) SourceMoved(ctx context.Context, m link.SourceMoved) error {
for _, e := range moved { for _, e := range moved {
movedNames = append(movedNames, e.Manifest.Module) movedNames = append(movedNames, e.Manifest.Module)
} }
// Written and its first tier asked as one act on the plans (novox/hq issue 213): a timer on
// another controller reading it between the two would ask the tier again.
release, err := inv.HoldPlans(ctx, true)
if err != nil {
return notNow(err)
}
defer release()
plan := planOfMerge(m, movedNames, edges) plan := planOfMerge(m, movedNames, edges)
if hasCycle(plan.Tiers, edges) { if hasCycle(plan.Tiers, edges) {
fmt.Printf(" the last tier depends on itself: %s — built together, in no order\n", fmt.Printf(" the last tier depends on itself: %s — built together, in no order\n",
-99
View File
@@ -1,99 +0,0 @@
// Package artifacts speaks to the mesh's artifact store over its own door.
//
// Only what the mesh needs that nothing else does: letting go of something it put there
// (novox/hq ADR 0189, issue 108). Pushing is the builder's, through the container runtime; reading
// is every machine's, through its runtime. This is the one operation that belongs to the thing
// holding the records, because it is the only one that is a decision rather than a transfer.
package artifacts
import (
"context"
"fmt"
"net/http"
"strings"
"time"
"github.com/novox/mesh-controller/internal/catalogue"
)
// Store is the artifact store at an address, as this machine reaches it.
type Store struct {
// Address is `host:port` — the store as the caller reaches it now, composed and never
// recorded (novox/hq 04-ISSUES/102).
Address string
// HTTP is the client used; nil is a client with a modest timeout.
HTTP *http.Client
}
// Gone is the answer when the store does not hold it: the outcome wanted, already true.
var Gone = fmt.Errorf("the store does not hold it")
// LetGo asks the store to drop one artifact the mesh recorded making.
//
// Takes a reference as the mesh records it — `artifact-store://<module>/<artifact>@sha256:…` for
// an image, `…/blobs/sha256:…` for an archive — because that is the identity every record uses,
// and composes the address here at the moment of use.
//
// Returns Gone when the store answers that it does not have it. That is not a failure: the sweep
// wants the artifact absent, and it is. It is distinguished from success only so a caller can say
// which of the two happened.
func (s Store) LetGo(ctx context.Context, reference string) error {
path, kept := catalogue.InArtifactStore(reference)
if !kept {
// Nothing the mesh put in its own store. Refused rather than attempted: composing a
// delete for a reference of unknown shape is how a sweep reaches something that is not
// the mesh's.
return fmt.Errorf("%s is not a reference into the mesh's artifact store", reference)
}
if s.Address == "" {
return fmt.Errorf("this mesh has no artifact store on its network to ask about %s", reference)
}
repository, kind, digest, err := split(path)
if err != nil {
return err
}
url := "http://" + s.Address + "/v2/" + repository + "/" + kind + "/" + digest
request, err := http.NewRequestWithContext(ctx, http.MethodDelete, url, nil)
if err != nil {
return err
}
client := s.HTTP
if client == nil {
client = &http.Client{Timeout: 30 * time.Second}
}
response, err := client.Do(request)
if err != nil {
return err
}
defer response.Body.Close()
switch response.StatusCode {
case http.StatusAccepted, http.StatusOK, http.StatusNoContent:
return nil
case http.StatusNotFound:
return Gone
case http.StatusMethodNotAllowed:
// The registry was started without deletion enabled. Said plainly, because the remedy is
// a setting on the store's module and not anything about this artifact.
return fmt.Errorf(
"the artifact store refuses deletion: its server was started without it enabled "+
"(REGISTRY_STORAGE_DELETE_ENABLED), so nothing can be collected until the store "+
"module is applied again (novox/hq ADR 0189). Asking about %s", reference)
default:
return fmt.Errorf("the artifact store answered %s for %s", response.Status, reference)
}
}
// split reads a recorded path into the repository, which endpoint names the thing, and the digest.
//
// Two shapes, which are the two the mesh records: `<repository>@sha256:<hex>` is a manifest, and
// `<repository>/blobs/sha256:<hex>` is a blob.
func split(path string) (repository, kind, digest string, err error) {
if before, after, ok := strings.Cut(path, "@sha256:"); ok {
return before, "manifests", "sha256:" + after, nil
}
if before, after, ok := strings.Cut(path, "/blobs/sha256:"); ok {
return before, "blobs", "sha256:" + after, nil
}
return "", "", "", fmt.Errorf("%q names nothing the store holds by digest", path)
}
-94
View File
@@ -1,94 +0,0 @@
package artifacts
import (
"context"
"errors"
"net/http"
"net/http/httptest"
"strings"
"testing"
"github.com/novox/mesh-controller/internal/catalogue"
)
// Asking the store to let go of what the mesh no longer keeps (novox/hq ADR 0189, issue 108).
//
// A fake store records what it was asked to delete, so what is asserted is the mesh's decision
// and the shape of the request — not the registry's behaviour, which is the registry's to test.
func fakeStore(t *testing.T, answer int) (Store, *[]string) {
t.Helper()
var asked []string
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
if r.Method != http.MethodDelete {
t.Errorf("the store was asked %s %s; collecting is a delete", r.Method, r.URL.Path)
}
asked = append(asked, r.URL.Path)
w.WriteHeader(answer)
}))
t.Cleanup(server.Close)
return Store{Address: strings.TrimPrefix(server.URL, "http://")}, &asked
}
func TestAnImageAndAnArchiveAreAskedForAtTheirOwnEndpoints(t *testing.T) {
// The two shapes the mesh records: a manifest by digest, and a blob by digest. They are
// different endpoints, and asking at the wrong one answers 404 — which this would then
// record as collected, leaving the bytes on disk for ever while the record says otherwise.
store, asked := fakeStore(t, http.StatusAccepted)
ctx := context.Background()
image := catalogue.ArtifactStoreScheme + "web/app@sha256:abc123"
archive := catalogue.ArtifactStoreScheme + "web/config/blobs/sha256:def456"
if err := store.LetGo(ctx, image); err != nil {
t.Fatal(err)
}
if err := store.LetGo(ctx, archive); err != nil {
t.Fatal(err)
}
want := []string{"/v2/web/app/manifests/sha256:abc123", "/v2/web/config/blobs/sha256:def456"}
if len(*asked) != 2 || (*asked)[0] != want[0] || (*asked)[1] != want[1] {
t.Fatalf("the store was asked %v; want %v", *asked, want)
}
}
func TestAStoreThatDoesNotHaveItAnswersGone(t *testing.T) {
// The outcome wanted, already true. Told apart from success only so the sweep can say which
// happened; both are recorded, because retrying for ever is the thing to avoid.
store, _ := fakeStore(t, http.StatusNotFound)
err := store.LetGo(context.Background(), catalogue.ArtifactStoreScheme+"web/app@sha256:abc123")
if !errors.Is(err, Gone) {
t.Fatalf("a store that does not hold it answered %v, want Gone", err)
}
}
func TestAStoreWithDeletionOffSaysSoAndNamesTheRemedy(t *testing.T) {
// The registry answers 405 when it was started without deletion enabled. The remedy is a
// setting on the store's module, and saying "405" would send somebody to the wrong place.
store, _ := fakeStore(t, http.StatusMethodNotAllowed)
err := store.LetGo(context.Background(), catalogue.ArtifactStoreScheme+"web/app@sha256:abc123")
if err == nil {
t.Fatal("a store that refuses deletion was read as success")
}
if !strings.Contains(err.Error(), "REGISTRY_STORAGE_DELETE_ENABLED") {
t.Fatalf("the refusal does not name the remedy: %v", err)
}
}
func TestAReferenceThatIsNotTheMeshsOwnIsNeverAsked(t *testing.T) {
// The whole safety of the sweep is that it names only what the mesh recorded putting there.
// A reference of another shape — a vendor's image, a package version — is refused rather
// than composed into a delete somewhere that is not the mesh's store.
store, asked := fakeStore(t, http.StatusAccepted)
for _, reference := range []string{
"docker.io/library/registry@sha256:abc123",
"registry@sha256:abc123",
"1.4.2",
} {
if err := store.LetGo(context.Background(), reference); err == nil {
t.Errorf("%s was asked about; it is not a reference into the mesh's store", reference)
}
}
if len(*asked) != 0 {
t.Fatalf("the store was asked about %v", *asked)
}
}
-49
View File
@@ -1,7 +1,6 @@
package broker package broker
import ( import (
"context"
"crypto/sha256" "crypto/sha256"
"crypto/tls" "crypto/tls"
"crypto/x509" "crypto/x509"
@@ -13,7 +12,6 @@ import (
"time" "time"
"github.com/nats-io/nats.go" "github.com/nats-io/nats.go"
"github.com/nats-io/nats.go/jetstream"
) )
// The JetStream side of the controller: the one place the mesh's streams and consumers are // The JetStream side of the controller: the one place the mesh's streams and consumers are
@@ -318,50 +316,3 @@ func retentionOf(r Retention) nats.RetentionPolicy {
return nats.LimitsPolicy return nats.LimitsPolicy
} }
} }
// EnsureBucket creates a module's bucket if it is absent and brings its options to match if it is
// present (novox/hq ADR 0201).
//
// **An update, never a delete and recreate**, for the reason a stream is updated: recreating
// discards what the bucket holds, and what a module's state holds is data. The mesh's caps are
// asserted with the owner's options, so a bucket made by hand converges to them.
func (j *JetStream) EnsureBucket(b Bucket) error {
history := b.History
if history == 0 {
history = 1
}
js, err := jetstream.New(j.conn)
if err != nil {
return err
}
ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
defer cancel()
if _, err := js.CreateOrUpdateKeyValue(ctx, jetstream.KeyValueConfig{
Bucket: b.Bucket(),
Description: b.Why(),
History: uint8(history),
TTL: time.Duration(b.TTLSeconds) * time.Second,
MaxValueSize: StateMaxValueBytes,
MaxBytes: StateMaxBytes,
Storage: jetstream.FileStorage,
}); err != nil {
return fmt.Errorf("asserting bucket %s: %w", b.Bucket(), err)
}
return nil
}
// BucketNames is every key-value bucket on the server, the mesh's and anybody else's.
func (j *JetStream) BucketNames() ([]string, error) {
js, err := jetstream.New(j.conn)
if err != nil {
return nil, err
}
ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
defer cancel()
lister := js.KeyValueStoreNames(ctx)
var out []string
for name := range lister.Name() {
out = append(out, name)
}
return out, lister.Error()
}
-6
View File
@@ -45,11 +45,6 @@ type Membership struct {
// module that must tell the mesh from the world, the route proxy serving an internal name, reads // 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. // it here rather than keeping a definition of its own.
Mesh []string `json:"mesh,omitempty"` 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"`
} }
// Served is one address a tool is answered on. // Served is one address a tool is answered on.
@@ -108,7 +103,6 @@ func MembershipFor(node string, d Declared, where Placements) Membership {
m.Seats = append(m.Seats, SeatServed{Seat: s.Name, Verb: verb, Subject: seatToolSubject(s, verb, node)}) m.Seats = append(m.Seats, SeatServed{Seat: s.Name, Verb: verb, Subject: seatToolSubject(s, verb, node)})
} }
} }
m.State = stateIssuedFor(d)
if len(d.Invokes) > 0 { if len(d.Invokes) > 0 {
m.Reaches = map[string][]string{} m.Reaches = map[string][]string{}
for _, t := range d.Invokes { for _, t := range d.Invokes {
-17
View File
@@ -103,12 +103,6 @@ type Principal struct {
// permission and nothing beside it. // permission and nothing beside it.
Invokes []string Invokes []string
// State is the local names of the state this principal's module keeps, and Reads the state of
// others it reads as `<module>.<name>` (novox/hq ADR 0201): a bucket each, kept by the owner's
// instances and read by whoever declares it.
State []string
Reads []string
// PasswordHash is the bcrypt hash the mesh minted. The plaintext is sealed to the principal // PasswordHash is the bcrypt hash the mesh minted. The plaintext is sealed to the principal
// and never appears here: this file is written to a node's disk and read by a server, and a // and never appears here: this file is written to a node's disk and read by a server, and a
// secret that can be read from a configuration file is a secret with a wider blast radius // secret that can be read from a configuration file is a secret with a wider blast radius
@@ -427,10 +421,6 @@ func PermissionsFor(p Principal) (Permissions, error) {
} }
} }
// 5. Its state, and the state of others it reads (novox/hq ADR 0201): every one read and
// watched, its own written too.
pub = append(pub, stateGrants(p.Module, p.State, p.Reads)...)
case KindNodeTools: case KindNodeTools:
// **One process serves what every module on the machine would have served for itself** // **One process serves what every module on the machine would have served for itself**
// (novox/hq ADR 0175). Each carried module's whole tool namespace — the same grant that // (novox/hq ADR 0175). Each carried module's whole tool namespace — the same grant that
@@ -497,13 +487,6 @@ func PermissionsFor(p Principal) (Permissions, error) {
"$JS.API.CONSUMER.MSG.NEXT."+stream+"."+durable, "$JS.API.CONSUMER.MSG.NEXT."+stream+"."+durable,
"$JS.ACK."+stream+"."+durable+".>") "$JS.ACK."+stream+"."+durable+".>")
} }
// **And it keeps and reads state for the modules it carries** (novox/hq ADR 0201): the union
// of what each may do with a bucket — an owner's write, a reader's read. That one module's code
// does not write another's bucket through it is the runtime's to keep, from the membership
// each assignment is issued, as it keeps each module's events under that module's own name.
for _, d := range p.Carries {
pub = append(pub, stateGrants(d.Module, stateNames(d.State), d.Reads)...)
}
sub = unique(sub) sub = unique(sub)
pub = unique(pub) pub = unique(pub)
} }
-169
View File
@@ -1,169 +0,0 @@
package broker
import (
"fmt"
"sort"
"strings"
)
// A module's state on the bus (novox/hq ADR 0201, design 32 §4, design 25 §3).
//
// A module names the state it keeps (`state`) and the state of others it reads (`reads`), and each
// is a key-value bucket: the server's own last-per-subject stream with direct reads, delete markers
// and watches, which is the state relationship the mesh already uses for declarations, opened to
// modules. The controller creates every bucket from the catalogue — from registration, like a
// seat's stream, so a reader may watch before the owner runs anywhere — and no module can.
//
// Pure, like everything else in this package that decides what the bus holds; jetstream.go is the
// part that asks a server.
// The mesh's caps on a bucket, the same for every module: a value is a piece of state, not a file,
// and a bucket that grew without bound would be one module filling the bus's disk for everyone.
const (
StateMaxValueBytes = 256 * 1024
StateMaxBytes = 64 * 1024 * 1024
)
// A Bucket is one module's declared state as the bus holds it.
type Bucket struct {
Module string
Name string
// History is how many values a key keeps; zero is one.
History int
// TTLSeconds is how long a value lives; zero is until replaced or deleted.
TTLSeconds int
}
// BucketName is the bucket a module's state lives in: the module and the local name joined by an
// underscore, which neither may contain, so two modules can never derive one bucket.
func BucketName(module, name string) string { return module + "_" + name }
// Bucket is this bucket's name on the bus.
func (b Bucket) Bucket() string { return BucketName(b.Module, b.Name) }
// Why is carried into the server's description of the bucket, so somebody reading the server's
// own state finds whose it is and why it is kept.
func (b Bucket) Why() string {
return fmt.Sprintf("%s's state %q (novox/hq ADR 0201): its current value per key, written by %s, "+
"read by whatever declares it reads it; kept when %s is unassigned, because it is data",
b.Module, b.Name, b.Module, b.Module)
}
// bucketOfRead is the bucket a read names, `<module>.<name>`, or false when it names none.
func bucketOfRead(read string) (string, bool) {
at := strings.LastIndex(read, ".")
if at <= 0 || at == len(read)-1 {
return "", false
}
module, name := read[:at], read[at+1:]
if !safeSubject.MatchString(module) || !safeSubject.MatchString(name) {
return "", false
}
return BucketName(module, name), true
}
// stateGrants is what a principal publishes to reach the state its modules keep and read: for every
// bucket, binding to it, reading a key directly, and an ordered consumer for listing and watching,
// created and deleted on the bucket's own stream, with its flow control answered; for a bucket an
// owner keeps, writing under the bucket's own subjects too.
//
// **Measured against a running server, 2026-10-04** (novox/hq research 024), and each one is there
// because leaving it out failed: without STREAM.INFO nothing binds; without DIRECT.GET nothing is
// read; without CONSUMER.CREATE no key is listed and nothing is watched; without CONSUMER.DELETE a
// watch cannot be stopped and lingers on the server. A write outside these is refused by the server
// — and reaches the writer as a timeout, not a refusal, which is why the runtime refuses first.
func stateGrants(module string, keeps []string, reads []string) []string {
var out []string
read := func(bucket string) {
stream := "KV_" + bucket
out = append(out,
"$JS.API.STREAM.INFO."+stream,
"$JS.API.DIRECT.GET."+stream+".>",
"$JS.API.CONSUMER.CREATE."+stream+".>",
"$JS.API.CONSUMER.DELETE."+stream+".>",
"$JS.FC."+stream+".>")
}
for _, name := range keeps {
if !safeSubject.MatchString(name) {
continue
}
bucket := BucketName(module, name)
read(bucket)
out = append(out, "$KV."+bucket+".>")
}
for _, r := range reads {
if bucket, ok := bucketOfRead(r); ok {
read(bucket)
}
}
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).
type StateIssued struct {
Name string `json:"name"`
Bucket string `json:"bucket"`
Writes bool `json:"writes,omitempty"`
}
// stateIssuedFor is every bucket a module's code may reach, as its membership lists them.
func stateIssuedFor(d Declared) []StateIssued {
var out []StateIssued
for _, b := range d.State {
out = append(out, StateIssued{Name: b.Name, Bucket: BucketName(d.Module, b.Name), Writes: true})
}
for _, r := range d.Reads {
if bucket, ok := bucketOfRead(r); ok {
out = append(out, StateIssued{Name: r, Bucket: bucket})
}
}
return out
}
// stateNames is the local names of a module's own buckets.
func stateNames(buckets []Bucket) []string {
out := make([]string, 0, len(buckets))
for _, b := range buckets {
out = append(out, b.Name)
}
return out
}
// A BucketAsserter is the part of a JetStream connection bucket assertion needs.
type BucketAsserter interface {
// EnsureBucket creates the bucket if absent and brings its options to match if present, never
// discarding what it holds.
EnsureBucket(b Bucket) error
// BucketNames is every key-value bucket on the server.
BucketNames() ([]string, error)
}
// RaiseBuckets asserts every declared bucket and answers the buckets on the server that nothing
// declares any more.
//
// **Those are reported, never removed** (novox/hq ADR 0201, ADR 0030): what a module stored is
// data, and a manifest edited, a module renamed or a catalogue entry dropped is an ordinary day's
// work that must not take data with it. Removing one is a person's act.
func RaiseBuckets(a BucketAsserter, buckets []Bucket) (undeclared []string, err error) {
sorted := append([]Bucket(nil), buckets...)
sort.Slice(sorted, func(i, j int) bool { return sorted[i].Bucket() < sorted[j].Bucket() })
declared := map[string]bool{}
for _, b := range sorted {
if err := a.EnsureBucket(b); err != nil {
return nil, fmt.Errorf("asserting %s's state %q: %w", b.Module, b.Name, err)
}
declared[b.Bucket()] = true
}
names, err := a.BucketNames()
if err != nil {
return nil, fmt.Errorf("listing the bus's state: %w", err)
}
for _, n := range names {
if !declared[n] {
undeclared = append(undeclared, n)
}
}
sort.Strings(undeclared)
return undeclared, nil
}
-166
View File
@@ -1,166 +0,0 @@
package broker
import (
"slices"
"strings"
"testing"
"github.com/nats-io/nats.go"
)
// The grants measured against a running server (novox/hq research 024): an owner reads and writes
// its bucket, a reader only reads, and neither reaches any other bucket.
func TestAnOwnerWritesItsStateAndAReaderOnlyReads(t *testing.T) {
owner, err := PermissionsFor(Principal{Kind: KindModule, Node: "one", Module: "claude-code",
State: []string{"servers"}, PasswordHash: "x"})
if err != nil {
t.Fatal(err)
}
for _, s := range []string{
"$KV.claude-code_servers.>",
"$JS.API.STREAM.INFO.KV_claude-code_servers",
"$JS.API.DIRECT.GET.KV_claude-code_servers.>",
"$JS.API.CONSUMER.CREATE.KV_claude-code_servers.>",
"$JS.API.CONSUMER.DELETE.KV_claude-code_servers.>",
"$JS.FC.KV_claude-code_servers.>",
} {
has(t, owner.Publish, s)
}
hasNot(t, owner.Publish, "$KV.>")
hasNot(t, owner.Publish, "$JS.API.>")
reader, err := PermissionsFor(Principal{Kind: KindModule, Node: "one", Module: "console",
Reads: []string{"claude-code.servers"}, PasswordHash: "x"})
if err != nil {
t.Fatal(err)
}
has(t, reader.Publish, "$JS.API.DIRECT.GET.KV_claude-code_servers.>")
has(t, reader.Publish, "$JS.API.CONSUMER.CREATE.KV_claude-code_servers.>")
hasNot(t, reader.Publish, "$KV.claude-code_servers.>")
for _, s := range reader.Subscribe {
if s == "$KV.claude-code_servers.>" {
t.Fatalf("a reader subscribes the bucket's subjects directly: %v", reader.Subscribe)
}
}
}
// One runtime carries every module on its machine, so its grant is the union: the owner's write
// where an owner is carried, a read where only a reader is.
func TestTheRuntimeKeepsAndReadsStateForItsModules(t *testing.T) {
perms, err := PermissionsFor(Principal{Kind: KindNodeTools, Node: "one", Module: RuntimeModule,
Carries: []Declared{
{Module: "claude-code", State: []Bucket{{Module: "claude-code", Name: "servers"}},
Reads: []string{"licence-manager.bindings"}},
{Module: "audit"},
}, PasswordHash: "x"})
if err != nil {
t.Fatal(err)
}
has(t, perms.Publish, "$KV.claude-code_servers.>")
has(t, perms.Publish, "$JS.API.DIRECT.GET.KV_licence-manager_bindings.>")
hasNot(t, perms.Publish, "$KV.licence-manager_bindings.>")
}
// A module with no state is granted nothing of any bucket — the composition of every module that
// existed before this is unchanged.
func TestAModuleWithNoStateReachesNoBucket(t *testing.T) {
perms, err := PermissionsFor(Principal{Kind: KindModule, Node: "one", Module: "billing",
Emits: []string{"order.placed"}, PasswordHash: "x"})
if err != nil {
t.Fatal(err)
}
for _, s := range perms.Publish {
if strings.HasPrefix(s, "$KV.") || strings.HasPrefix(s, "$JS.FC.") || strings.Contains(s, ".KV_") {
t.Fatalf("granted %q without declaring state", s)
}
}
}
// A read that names no bucket grants nothing rather than something that happens to parse.
func TestAReadThatNamesNoBucketGrantsNothing(t *testing.T) {
if got := stateGrants("a", nil, []string{"nodot", "x.", ".y", "a.b>"}); len(got) != 0 {
t.Fatalf("granted %v for reads that name no bucket", got)
}
}
// The membership lists every bucket the module's code may reach, by the name the module uses for
// it, and whether it may write it — the list the runtime refuses from.
func TestAMembershipListsTheStateItsModuleMayReach(t *testing.T) {
m := MembershipFor("one", Declared{Module: "claude-code",
State: []Bucket{{Module: "claude-code", Name: "servers"}},
Reads: []string{"licence-manager.bindings"}}, Placements{})
want := []StateIssued{
{Name: "servers", Bucket: "claude-code_servers", Writes: true},
{Name: "licence-manager.bindings", Bucket: "licence-manager_bindings"},
}
if !slices.Equal(m.State, want) {
t.Fatalf("issued %+v, want %+v", m.State, want)
}
if none := MembershipFor("one", Declared{Module: "audit"}, Placements{}); none.State != nil {
t.Fatalf("a module with no state was issued %+v", none.State)
}
}
type buckets struct {
ensured []string
on []string
}
func (b *buckets) EnsureBucket(x Bucket) error {
b.ensured = append(b.ensured, x.Bucket())
return nil
}
func (b *buckets) BucketNames() ([]string, error) { return b.on, nil }
// Every declared bucket is asserted; one on the server that nothing declares is said, not removed.
func TestRaisingStateReportsWhatNothingDeclares(t *testing.T) {
b := &buckets{on: []string{"claude-code_servers", "gone_old", "ours_by_hand"}}
undeclared, err := RaiseBuckets(b, []Bucket{{Module: "claude-code", Name: "servers"}, {Module: "a", Name: "b"}})
if err != nil {
t.Fatal(err)
}
if !slices.Equal(b.ensured, []string{"a_b", "claude-code_servers"}) {
t.Fatalf("asserted %v", b.ensured)
}
if !slices.Equal(undeclared, []string{"gone_old", "ours_by_hand"}) {
t.Fatalf("reported %v", undeclared)
}
}
// Against a real server: a bucket is created with the owner's options and the mesh's caps,
// asserting it again changes nothing and keeps what it holds, and a changed option is brought to
// match in place.
func TestABucketIsAssertedInPlace(t *testing.T) {
js := aLiveBus(t)
b := Bucket{Module: "statetest", Name: "servers"}
if _, err := RaiseBuckets(js, []Bucket{b}); err != nil {
t.Fatalf("a real server refused a module's bucket: %v", err)
}
kv, err := js.Context().KeyValue(b.Bucket())
if err != nil {
t.Fatal(err)
}
if _, err := kv.Put("all.one", []byte(`{"kept":true}`)); err != nil {
t.Fatal(err)
}
b.History = 3
if _, err := RaiseBuckets(js, []Bucket{b}); err != nil {
t.Fatalf("asserting the bucket again failed, so a restart would: %v", err)
}
got, err := kv.Get("all.one")
if err != nil || string(got.Value()) != `{"kept":true}` {
t.Fatalf("asserting again lost what the bucket held: %v %v", got, err)
}
status, err := kv.Status()
if err != nil {
t.Fatal(err)
}
if status.History() != 3 {
t.Fatalf("history is %d, the owner declared 3", status.History())
}
if s, ok := status.(*nats.KeyValueBucketStatus); ok {
if c := s.StreamInfo().Config; c.MaxMsgSize != StateMaxValueBytes || c.MaxBytes != StateMaxBytes {
t.Fatalf("the mesh's caps are not on the bucket: value %d, bucket %d", c.MaxMsgSize, c.MaxBytes)
}
}
}
-5
View File
@@ -33,10 +33,6 @@ type Declared struct {
Watches []Seat Watches []Seat
// Invokes are the tools it calls, `<module>.<tool>` or `*` (novox/hq ADR 0152). // Invokes are the tools it calls, `<module>.<tool>` or `*` (novox/hq ADR 0152).
Invokes []string Invokes []string
// State is the state it keeps, each a bucket its instances write (novox/hq ADR 0201).
State []Bucket
// Reads are other modules' state it reads, each `<module>.<name>` (novox/hq ADR 0201).
Reads []string
} }
// Records is what composing a user list needs to know about the mesh, and nothing more. // Records is what composing a user list needs to know about the mesh, and nothing more.
@@ -85,7 +81,6 @@ func Users(r Records) ([]Principal, error) {
Kind: KindModule, Node: node, Module: d.Module, Kind: KindModule, Node: node, Module: d.Module,
Emits: d.Emits, Consumes: d.Consumes, Serves: d.Serves, Emits: d.Emits, Consumes: d.Consumes, Serves: d.Serves,
Holds: d.Holds, Uses: d.Uses, Watches: d.Watches, Invokes: d.Invokes, Holds: d.Holds, Uses: d.Uses, Watches: d.Watches, Invokes: d.Invokes,
State: stateNames(d.State), Reads: d.Reads,
}) })
} }
if runtimeHere { if runtimeHere {
+3 -106
View File
@@ -215,7 +215,7 @@ func Build(ctx context.Context, run Runner, publish Publisher,
sort.Slice(artifacts, func(i, j int) bool { return artifacts[i].Name < artifacts[j].Name }) sort.Slice(artifacts, func(i, j int) bool { return artifacts[i].Name < artifacts[j].Name })
for _, a := range artifacts { for _, a := range artifacts {
say("artifact", "%s (%s%s) — starting", a.Name, a.Kind, langSuffix(a)) say("artifact", "%s (%s%s) — starting", a.Name, a.Kind, langSuffix(a))
made, err := one(ctx, run, publish, manifest.Module, within, workspace, commit, credentials, a, args, held, npmrcPath, npmrc, seatBases, say) made, err := one(ctx, run, publish, manifest.Module, within, workspace, commit, credentials, a, args, held, npmrcPath, seatBases, say)
if err != nil { if err != nil {
say("artifact", "%s FAILED: %v", a.Name, err) say("artifact", "%s FAILED: %v", a.Name, err)
return Result{}, err return Result{}, err
@@ -443,7 +443,7 @@ func wantsPackages(manifest catalogue.Manifest, within string) bool {
func one(ctx context.Context, run Runner, publish Publisher, func one(ctx context.Context, run Runner, publish Publisher,
module, tree, workspace, commit, credentials string, a catalogue.Artifact, args []string, module, tree, workspace, commit, credentials string, a catalogue.Artifact, args []string,
held map[string]string, npmrc string, registry Npmrc, seats map[string]string, held map[string]string, npmrc string, seats map[string]string,
say func(step, format string, args ...any)) (catalogue.Built, error) { say func(step, format string, args ...any)) (catalogue.Built, error) {
switch a.Kind { switch a.Kind {
@@ -582,11 +582,6 @@ func one(ctx context.Context, run Runner, publish Publisher,
"holds no copy of it. Build %s first", "holds no copy of it. Build %s first",
module, a.Name, chain.Language, chain.Base, chain.Artifact, chain.Base) module, a.Name, chain.Language, chain.Base, chain.Artifact, chain.Base)
} }
// The module's own packages first, where the compiler and the bundler resolve them from
// (dependencies.go); nothing at all for a module whose package.json names only the SDK.
if err := installOwn(ctx, run, tree, chain, base, registry, say); err != nil {
return catalogue.Built{}, fmt.Errorf("%s: %s: %w", module, a.Name, err)
}
say("bundle", "compiling %s in %s's toolchain", a.Language, chain.Base) say("bundle", "compiling %s in %s's toolchain", a.Language, chain.Base)
compiled, err := compile(ctx, run, tree, chain, base, a) compiled, err := compile(ctx, run, tree, chain, base, a)
if err != nil { if err != nil {
@@ -598,12 +593,6 @@ func one(ctx context.Context, run Runner, publish Publisher,
if err != nil { if err != nil {
return catalogue.Built{}, fmt.Errorf("%s: writing %s's launchers failed: %w", module, a.Name, err) return catalogue.Built{}, fmt.Errorf("%s: writing %s's launchers failed: %w", module, a.Name, err)
} }
if chain.Bundler != "" {
say("bundle", "bundling each entrypoint into one file")
if compiled, err = bundled(ctx, run, tree, chain, base, a, launchers); err != nil {
return catalogue.Built{}, fmt.Errorf("%s: bundling %s failed: %w", module, a.Name, err)
}
}
say("bundle", "compiled, packing") say("bundle", "compiled, packing")
body, err := pack(compiled) body, err := pack(compiled)
if err != nil { if err != nil {
@@ -985,7 +974,7 @@ func compile(ctx context.Context, run Runner, tree string, chain Toolchain,
if _, err := run(ctx, tree, "docker", invocation...); err != nil { if _, err := run(ctx, tree, "docker", invocation...); err != nil {
return "", err return "", err
} }
if chain.Dependencies != "" && chain.Bundler == "" { if chain.Dependencies != "" {
// **What the bundle runs with, from the image it was compiled in** (Toolchain.Dependencies). // **What the bundle runs with, from the image it was compiled in** (Toolchain.Dependencies).
// A second run in the same image rather than a shell wrapped around the compiler: the // A second run in the same image rather than a shell wrapped around the compiler: the
// compile line stays a plain command a reader can run by hand, and the copy is one more // compile line stays a plain command a reader can run by hand, and the copy is one more
@@ -1235,95 +1224,3 @@ func writeLaunchers(root string, chain Toolchain, a catalogue.Artifact) (map[str
} }
return out, nil return out, nil
} }
// bundledSuffix is where a bundle's one-file output is written, beside what the compiler wrote.
const bundledSuffix = ".bundled"
// bundled makes every entrypoint and every launcher of a compiled bundle ONE file, in the toolchain
// image's bundler, and answers the directory to pack (novox/hq ADR 0193).
//
// **What a launched bundle runs is what it imports, and nothing else.** Every served bundle is its
// own process, so it carries its own copy of the SDK and its own dependencies inlined — the
// toolchain's whole node_modules no longer travels in every bundle. An entrypoint a process runs by
// name (`node daemon/index.js`) is bundled in place under its own name; a launcher keeps its name
// and its first line, and stays executable. A package the bundler cannot inline is named by the
// artifact (`external`), kept as an import, and only then is the toolchain's runtime directory
// copied beside the files. CommonJS inlined into an ES module still finds `require`.
func bundled(ctx context.Context, run Runner, tree string, chain Toolchain, base string,
a catalogue.Artifact, launchers map[string]string) (string, error) {
const within = "/app/modules/module"
out, final := Out(a.Name), Out(a.Name)+bundledSuffix
if err := os.RemoveAll(filepath.Join(tree, final)); err != nil {
return "", err
}
if err := os.MkdirAll(filepath.Join(tree, final), 0o755); err != nil {
return "", err
}
common := []string{"--bundle", "--platform=node", "--format=esm", "--target=node22",
"--outbase=" + out, "--outdir=" + final, "--log-level=warning",
"--banner:js=import { createRequire as __meshRequire } from 'node:module'; const require = __meshRequire(import.meta.url);"}
for _, x := range a.External {
common = append(common, "--external:"+x)
}
var plain []string
for _, e := range a.Entrypoints {
if strings.HasSuffix(e, ".js") {
plain = append(plain, out+"/"+e)
}
}
var launch []string
for _, l := range sortedValues(launchers) {
launch = append(launch, out+"/"+l)
}
// Refused by name in an image that predates the bundler, as the dependencies copy is: a bundle
// packed without it would carry nothing it imports. Run as itself: npm installs esbuild's native
// binary in place of its script, which `node` cannot run.
guard := `test -x "$0" || { echo "the toolchain image carries no bundler at $0: it predates one-file bundles, rebuild mesh-tools first" >&2; exit 1; }; exec "$0" "$@"`
step := func(entries []string, extra ...string) error {
if len(entries) == 0 {
return nil
}
invocation := []string{"run", "--rm", "--volume", tree + ":" + within, "--workdir", within, base,
"sh", "-c", guard, chain.Bundler}
invocation = append(invocation, entries...)
invocation = append(invocation, common...)
invocation = append(invocation, extra...)
_, err := run(ctx, tree, "docker", invocation...)
return err
}
if err := step(plain); err != nil {
return "", err
}
if err := step(launch, "--out-extension:.js=.mjs"); err != nil {
return "", err
}
// Plain `.js` output is an ES module; said once, as the runtime directory used to say it.
if err := os.WriteFile(filepath.Join(tree, final, "package.json"), []byte(`{"type":"module","private":true}`+"\n"), 0o644); err != nil {
return "", err
}
for _, l := range launchers {
path := filepath.Join(tree, final, filepath.FromSlash(l))
if _, err := os.Stat(path); err == nil {
if err := os.Chmod(path, 0o755); err != nil {
return "", err
}
}
}
if len(a.External) > 0 && chain.Dependencies != "" {
copying := []string{"run", "--rm", "--volume", tree + ":" + within, "--workdir", within, base,
"sh", "-c", `cp -a "$0/node_modules" "$1/"`, chain.Dependencies, final}
if _, err := run(ctx, tree, "docker", copying...); err != nil {
return "", fmt.Errorf("copying the packages %s keeps external: %w", a.Name, err)
}
}
return filepath.Join(tree, final), nil
}
func sortedValues(m map[string]string) []string {
out := make([]string, 0, len(m))
for _, v := range m {
out = append(out, v)
}
sort.Strings(out)
return out
}
+14 -38
View File
@@ -83,49 +83,25 @@ func TestABundleIsCompiledAndPackedWithNoDockerfile(t *testing.T) {
t.Fatalf("the bundle was not pinned: %v", got.Manifest.Resources[0]) t.Fatalf("the bundle was not pinned: %v", got.Manifest.Resources[0])
} }
// **One file per entrypoint and launcher, in the toolchain's bundler** (novox/hq ADR 0193). A // **And what it runs with, from the image it was compiled in** (novox/hq to-be 38 WP3). A
// second run in the same toolchain image bundles each into the artifact's bundled output, the SDK // second run in the same toolchain image copies the toolchain's runtime directory — the
// inlined, refusing by name in an image that predates the bundler; and the toolchain's // `"type": "module"` package.json and the pruned node_modules — into the output's root, and
// node_modules is no longer copied into a bundle that keeps nothing external. // refuses by name when the image carries none rather than packing a bundle that starts nowhere.
var bundling []string var copied string
for _, line := range r.ran { for _, line := range r.ran {
if strings.HasPrefix(line, "docker run") && strings.Contains(line, "esbuild") { if strings.HasPrefix(line, "docker run") && strings.Contains(line, "/app/runtime") {
bundling = append(bundling, line) copied = line
} }
} }
if len(bundling) != 2 { if copied == "" {
t.Fatalf("want one bundling run for the entrypoints and one for the launchers:\n%s", strings.Join(r.ran, "\n")) t.Fatalf("the bundle's dependencies were not copied in after the compile:\n%s", strings.Join(r.ran, "\n"))
} }
for _, want := range []string{"mesh-tools/build@sha256:", "predates one-file bundles", "--bundle", "--format=esm", if !strings.Contains(copied, "mesh-tools/build@sha256:") || !strings.Contains(copied, "predates") ||
"--platform=node", "--outdir=" + Out("code") + ".bundled", Out("code") + "/index.js"} { !strings.Contains(copied, Out("code")) {
if !strings.Contains(bundling[0], want) { t.Fatalf("the copy does not run in the same toolchain, refuse an older image by name, or land in the artifact's output: %s", copied)
t.Errorf("the entrypoints' bundling lacks %q: %s", want, bundling[0])
}
} }
if !strings.Contains(bundling[1], Out("code")+"/index.serve.mjs") || !strings.Contains(bundling[1], "--out-extension:.js=.mjs") { if strings.Index(strings.Join(r.ran, "\n"), "--outDir") > strings.Index(strings.Join(r.ran, "\n"), "/app/runtime") {
t.Errorf("the launcher is not bundled under its own name: %s", bundling[1]) t.Fatal("the dependencies were copied before the compile wrote its output")
}
if strings.Contains(strings.Join(r.ran, "\n"), "/app/runtime") {
t.Errorf("the toolchain's node_modules was copied into a bundle that keeps nothing external:\n%s", strings.Join(r.ran, "\n"))
}
if strings.Index(strings.Join(r.ran, "\n"), "--outDir") > strings.Index(strings.Join(r.ran, "\n"), "esbuild") {
t.Fatal("the bundler ran before the compile wrote its output")
}
}
// A bundle naming packages it keeps external is bundled with them as imports, and carries the
// toolchain's node_modules for them — the one case it still does.
func TestABundleKeepingAPackageExternalCarriesTheToolchainsModules(t *testing.T) {
manifest := strings.Replace(aBundle, `"entrypoints":["index.js"]`, `"entrypoints":["index.js"],"external":["sharp"]`, 1)
r, workspace := aRepository(t, manifest, map[string]string{"index.ts": "console.log(1)"})
held := map[string]string{"mesh-tools/build": "registry.invalid/mesh-tools/build@sha256:" + strings.Repeat("b", 64)}
if _, err := Build(context.Background(), compiling{r}.run, r,
"https://forge.invalid/greeter.git", "", "", workspace, held, Npmrc{}, GitCredential{}, nil); err != nil {
t.Fatal(err)
}
all := strings.Join(r.ran, "\n")
if !strings.Contains(all, "--external:sharp") || !strings.Contains(all, "/app/runtime") {
t.Errorf("an external package was not kept as an import with the toolchain's modules beside it:\n%s", all)
} }
} }
-147
View File
@@ -1,147 +0,0 @@
package builder
import (
"context"
"encoding/json"
"errors"
"fmt"
"os"
"path/filepath"
"sort"
"strings"
)
// A module's own packages, installed before its bundle is compiled, so the bundler inlines them.
//
// **A bundle could only import what the toolchain happened to carry.** The compiler and the bundler
// resolve an import by walking up from the module's source: the module's own directory first, then
// the toolchain image's node_modules. Nothing ever put anything in the first, so a module needing a
// database driver (`pg`, `mongodb`, `mssql`) could not be a bundle at all, and kept a container whose
// recipe installed it by hand (novox/hq ADR 0198 §4: "the backend's own driver inside the bundle").
// Now the module's `package.json` says what it depends on, as any Node package does, and the build
// installs exactly that into the module's own directory before compiling.
//
// **The SDK the toolchain carries is the one a bundle is built with, whatever the module says**
// (novox/hq issue 212: the toolchain is rebuilt on every SDK release and every bundle after it). A
// module's `package.json` names `@novox/mesh-sdk` with a range — it has to, to type-check on a
// workstation — and installing that range would shadow the toolchain's copy for this module alone:
// one module compiled against an older SDK than its neighbours, chosen by a caret nobody re-reads.
// So the SDK is taken out of what is installed (and never fetched), and any copy something else
// pulls in is removed afterwards; every import of it resolves past the module's node_modules to the
// toolchain's. A module therefore cannot pin a different SDK, by design: the toolchain is the pin.
//
// **Correctness before speed.** Every build installs afresh into a fresh clone, from the lockfile
// when the module has one (`npm ci`, exact) and from its ranges otherwise; nothing installed is kept
// between builds. What is shared is npm's own download cache, a named volume, which is
// content-addressed and verified by integrity on every read — it saves the network, never the
// install. Install scripts do not run: the build node runs nobody's postinstall, and what a script
// would build natively could not be inlined into one file anyway.
// sdkPackage is the package a TypeScript bundle's launcher serves through, and the one package a
// module's own dependencies never supply (above).
const sdkPackage = "@novox/mesh-sdk"
// npmCache is the named volume npm's download cache lives in across builds on one build node.
const npmCache = "mesh-builder-npm-cache"
// ownDependencies is what a module's package.json depends on beyond the SDK, sorted; nothing when
// the module has no package.json or depends on nothing else — which builds exactly as before.
func ownDependencies(tree string) ([]string, error) {
raw, err := os.ReadFile(filepath.Join(tree, "package.json"))
if errors.Is(err, os.ErrNotExist) {
return nil, nil
}
if err != nil {
return nil, err
}
var p struct {
Dependencies map[string]string `json:"dependencies"`
}
if err := json.Unmarshal(raw, &p); err != nil {
return nil, fmt.Errorf("the module's package.json is not JSON: %w", err)
}
var names []string
for name := range p.Dependencies {
if name != sdkPackage {
names = append(names, name)
}
}
sort.Strings(names)
return names, nil
}
// installSteps is the script run inside the toolchain image, from the module's own directory ($0).
// It works in a scratch copy so the module's package.json and lockfile are never rewritten, takes
// the SDK out of what is installed, installs production dependencies only, removes any copy of the
// SDK something pulled in, and puts the result at the module's node_modules.
const installSteps = `set -e
work="$(mktemp -d)"
cp "$0/package.json" "$work/"
if [ -f "$0/package-lock.json" ]; then cp "$0/package-lock.json" "$work/"; fi
cd "$work"
node -e '
const fs = require("fs"), sdk = process.argv[1];
const p = JSON.parse(fs.readFileSync("package.json", "utf8"));
for (const k of ["dependencies", "peerDependencies", "optionalDependencies"]) if (p[k]) delete p[k][sdk];
delete p.devDependencies; delete p.scripts;
fs.writeFileSync("package.json", JSON.stringify(p));
' "$1"
shift
if [ -f package-lock.json ]; then
npm ci --omit=dev --omit=peer --ignore-scripts --no-audit --no-fund "$@"
else
npm install --omit=dev --omit=peer --ignore-scripts --no-audit --no-fund --no-package-lock "$@"
fi
find node_modules -depth -type d -path "*/node_modules/@novox/mesh-sdk" -exec rm -rf {} +
rm -rf "$0/node_modules"
cp -a node_modules "$0/node_modules"
`
// installOwn installs a TypeScript module's own production dependencies into its directory, in the
// toolchain image, before the compile — or does nothing at all for a module that has none.
func installOwn(ctx context.Context, run Runner, tree string, chain Toolchain, base string,
registry Npmrc, say func(step, format string, args ...any)) error {
if chain.Language != "typescript" {
return nil
}
deps, err := ownDependencies(tree)
if err != nil || len(deps) == 0 {
return err
}
scoped := strings.TrimSpace(registry.Scope)
if !registry.Enabled() {
// **No registry, no scoped package.** Without the mesh's registry a scoped name resolves on
// the public one, where anybody may have published it: a dependency that installs is not
// the dependency the module meant.
for _, d := range deps {
if strings.HasPrefix(d, "@novox/") {
return fmt.Errorf("the module depends on %s, and this build knows no package registry "+
"for its scope; it would resolve from the public registry, which is not where the "+
"mesh publishes it", d)
}
}
}
const within = "/app/modules/module"
invocation := []string{"run", "--rm",
"--volume", tree + ":" + within,
"--volume", npmCache + ":/root/.npm",
"--workdir", within}
var flags []string
if registry.Enabled() {
// The registry is reached where the binding says it is, which may be this machine's own
// loopback — the reason an image build that resolves packages runs on the host network too.
invocation = append(invocation, "--network", "host")
reg := strings.TrimSpace(registry.Registry)
if !strings.HasSuffix(reg, "/") {
reg += "/"
}
flags = append(flags, "--"+scoped+":registry="+reg)
}
invocation = append(invocation, base, "sh", "-c", installSteps, within, sdkPackage)
invocation = append(invocation, flags...)
say("bundle", "installing the module's own packages: %s", strings.Join(deps, ", "))
if _, err := run(ctx, tree, "docker", invocation...); err != nil {
return fmt.Errorf("installing the module's own packages (%s): %w", strings.Join(deps, ", "), err)
}
return nil
}
-131
View File
@@ -1,131 +0,0 @@
package builder
import (
"context"
"strings"
"testing"
)
// A module's own packages (dependencies.go): installed into its own directory, in the toolchain,
// before the compile, so the bundler inlines them — the SDK always the toolchain's.
func buildWithPackageJSON(t *testing.T, pkg string, extra map[string]string, registry Npmrc) (*recorded, error) {
t.Helper()
files := map[string]string{"index.ts": "console.log(1)"}
if pkg != "" {
files["package.json"] = pkg
}
for k, v := range extra {
files[k] = v
}
r, workspace := aRepository(t, aBundle, files)
held := map[string]string{"mesh-tools/build": "registry.invalid/mesh-tools/build@sha256:" + strings.Repeat("b", 64)}
_, err := Build(context.Background(), compiling{r}.run, r,
"https://forge.invalid/greeter.git", "", "", workspace, held, registry, GitCredential{}, nil)
return r, err
}
func installs(r *recorded) []string {
var out []string
for _, line := range r.ran {
if strings.HasPrefix(line, "docker run") && strings.Contains(line, "npm ci") {
out = append(out, line)
}
}
return out
}
func compileIndex(r *recorded) int {
for i, line := range r.ran {
if strings.Contains(line, "--outDir") {
return i
}
}
return -1
}
func TestAModulesOwnPackagesAreInstalledInTheToolchainBeforeTheCompile(t *testing.T) {
r, err := buildWithPackageJSON(t, `{"type":"module","dependencies":{"@novox/mesh-sdk":"^0.1.0","pg":"^8"},"devDependencies":{"typescript":"^5"}}`,
nil, Npmrc{Scope: "@novox", Registry: "https://forge.invalid/api/packages/novox/npm"})
if err != nil {
t.Fatal(err)
}
got := installs(r)
if len(got) != 1 {
t.Fatalf("want one install of the module's own packages:\n%s", strings.Join(r.ran, "\n"))
}
line := got[0]
for _, want := range []string{
"mesh-tools/build@sha256:", // in the toolchain image
":/app/modules/module", // into the module's own directory
"--workdir /app/modules/module", //
npmCache + ":/root/.npm", // npm's verified download cache, and only that
"--omit=dev", "--ignore-scripts", // production packages, no build-node scripts
"npm ci", "npm install", "--no-package-lock", // the lockfile when there is one, else the ranges
"--@novox:registry=https://forge.invalid/api/packages/novox/npm/", // the scope from the mesh's registry
"--network host",
"@novox/mesh-sdk", // named, to be taken out of what is installed
} {
if !strings.Contains(line, want) {
t.Errorf("the install lacks %q:\n%s", want, line)
}
}
// The SDK is the toolchain's: never installed from the module's range, and any copy removed.
if !strings.Contains(line, `delete p[k][sdk]`) || !strings.Contains(line, `-path "*/node_modules/@novox/mesh-sdk" -exec rm -rf`) {
t.Errorf("the module's own SDK range could shadow the toolchain's SDK:\n%s", line)
}
if i, c := strings.Index(strings.Join(r.ran, "\n"), "npm ci"), compileIndex(r); c < 0 ||
i > strings.Index(strings.Join(r.ran, "\n"), "--outDir") {
t.Fatalf("the install did not run before the compile:\n%s", strings.Join(r.ran, "\n"))
}
}
// **A module with nothing beyond the SDK builds exactly as before**: the same commands, no install.
func TestAModuleDependingOnlyOnTheSDKBuildsExactlyAsBefore(t *testing.T) {
without, err := buildWithPackageJSON(t, "", nil, Npmrc{})
if err != nil {
t.Fatal(err)
}
for _, pkg := range []string{
`{"type":"module","dependencies":{"@novox/mesh-sdk":"^0.1.0"},"devDependencies":{"typescript":"^5"}}`,
`{"type":"module"}`,
} {
with, err := buildWithPackageJSON(t, pkg, map[string]string{"package-lock.json": "{}"}, Npmrc{Scope: "@novox", Registry: "https://forge.invalid/npm/"})
if err != nil {
t.Fatal(err)
}
if strings.Contains(strings.Join(with.ran, "\n"), "npm ") {
t.Fatalf("a module depending on nothing but the SDK ran npm:\n%s", strings.Join(with.ran, "\n"))
}
if len(with.ran) != len(without.ran) {
t.Fatalf("a module depending only on the SDK built differently from one with no package.json:\n%s\n---\n%s",
strings.Join(with.ran, "\n"), strings.Join(without.ran, "\n"))
}
}
}
// Without the mesh's registry a scoped package would resolve on the public one: refused by name.
func TestAScopedPackageWithNoRegistryIsRefused(t *testing.T) {
r, err := buildWithPackageJSON(t, `{"dependencies":{"@novox/mesh-sdk":"^0.1.0","@novox/other":"^1"}}`, nil, Npmrc{})
if err == nil || !strings.Contains(err.Error(), "@novox/other") {
t.Fatalf("a scoped package was installed with no registry for its scope: %v", err)
}
if strings.Contains(strings.Join(r.ran, "\n"), "--outDir") {
t.Fatal("the compile ran after the refusal")
}
// A public package installs without one, from the public registry and nothing else.
r, err = buildWithPackageJSON(t, `{"dependencies":{"mssql":"^11"}}`, nil, Npmrc{})
if err != nil {
t.Fatal(err)
}
if got := installs(r); len(got) != 1 || strings.Contains(got[0], ":registry=") || strings.Contains(got[0], "--network host") {
t.Fatalf("a public package's install: %v", got)
}
}
func TestAnUnreadablePackageJSONIsRefusedByName(t *testing.T) {
_, err := buildWithPackageJSON(t, `{"dependencies":`, nil, Npmrc{})
if err == nil || !strings.Contains(err.Error(), "package.json") {
t.Fatalf("a broken package.json was not refused by name: %v", err)
}
}
-20
View File
@@ -200,23 +200,3 @@ func TestWhatABuildReadIsTheRepositoriesItsRecipesName(t *testing.T) {
t.Fatal("a module whose recipes name no other repository read one") t.Fatal("a module whose recipes name no other repository read one")
} }
} }
// novox/hq 04-ISSUES/212: a toolchain stands on the SDK's published package, and is built with the
// exact version the mesh published — an argument that changes when the SDK does, so a rebuild after
// a release never reuses an install of the version before it.
func TestAPackageTheMeshPublishedIsPassedByItsExactVersion(t *testing.T) {
manifest := catalogue.Manifest{
Module: "mesh-tools",
Build: &catalogue.Build{
On: []catalogue.BuildsOn{{Arg: "MESH_SDK", Module: "mesh-sdk", Artifact: "lib"}},
},
}
held := map[string]string{"mesh-sdk/lib": "@novox/mesh-sdk@0.1.6"}
args, resolved, err := standingOn(context.Background(), manifest, held, noMirror)
if err != nil {
t.Fatal(err)
}
if fmt.Sprint(args) != "[--build-arg MESH_SDK=@novox/mesh-sdk@0.1.6]" || fmt.Sprint(resolved) != "[@novox/mesh-sdk@0.1.6]" {
t.Errorf("the package was passed as %v, recorded as %v", args, resolved)
}
}
+2 -13
View File
@@ -67,23 +67,13 @@ type Toolchain struct {
// `package.json` saying `"type": "module"` — Node reads a bare `.js` as CommonJS otherwise, so a // `package.json` saying `"type": "module"` — Node reads a bare `.js` as CommonJS otherwise, so a
// bundle with its dependencies and without that line still fails to start — and the pruned, // bundle with its dependencies and without that line still fails to start — and the pruned,
// production-only node_modules the runtime itself ships with: the SDK's and the runtime's // production-only node_modules the runtime itself ships with: the SDK's and the runtime's
// dependencies, and nothing module-specific (a module's own npm dependencies are installed into // dependencies, and nothing module-specific yet (novox/hq ADR 0188 §5: a skeleton; a module's
// its own directory before the compile and inlined by the bundler: dependencies.go). Empty for a // own npm dependencies are a later step). Empty for a language whose bundle carries its own —
// language whose bundle carries its own —
// a Go binary is static, a Python bundle is installed with its dependencies. // a Go binary is static, a Python bundle is installed with its dependencies.
// //
// A toolchain image without the directory fails the build by name rather than packing a bundle // A toolchain image without the directory fails the build by name rather than packing a bundle
// that starts nowhere: the image predates this and must be rebuilt first. // that starts nowhere: the image predates this and must be rebuilt first.
//
// *Since the bundler (below):* copied only for a bundle that names packages it keeps external,
// which cannot be inlined; a bundle with none carries no node_modules at all.
Dependencies string Dependencies string
// Bundler is the bundler inside the toolchain image that makes each compiled entrypoint and each
// launcher ONE self-contained file (novox/hq ADR 0193): every served bundle is its own process
// now, so each carries its own copy of what it imports — the SDK included — and nothing else.
// A bundle shrinks from the toolchain's whole node_modules to the code it runs. Empty for a
// language whose build is already one file.
Bundler string
// SystemStamp is the variable this language's linker fills with the artifact's declared system, // SystemStamp is the variable this language's linker fills with the artifact's declared system,
// for a language whose binaries are pinned to one at link time (novox/hq ADR 0005). // for a language whose binaries are pinned to one at link time (novox/hq ADR 0005).
// //
@@ -149,7 +139,6 @@ var toolchains = []Toolchain{
Unit: UnitSources, Unit: UnitSources,
SourceExt: ".ts", SourceExt: ".ts",
Dependencies: "/app/runtime", Dependencies: "/app/runtime",
Bundler: "/app/node_modules/esbuild/bin/esbuild",
}, },
{ {
Language: "go", Language: "go",
@@ -1,166 +0,0 @@
package catalogue
import (
"encoding/json"
"strings"
"testing"
)
// novox/hq issue 213 (ADR 0188 §1, §3): a module's own Go service is a bundle the host runs as a
// process, not an image. Each test holds one thing that had to change in the composer for the
// controller to be declared that way.
const aServiceDigest = "sha256:dddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddd"
// aServiceModule is the controller's shape in miniature: it answers tools of its own, its code is a
// Go bundle a process runs as an account it declares, its secrets belong to that account, it
// prepares its state, and its process replaces the container it used to run as.
func aServiceModule(t *testing.T) Manifest {
t.Helper()
raw := `{
"module": "svc", "version": "1", "tools": ["status"], "prepares": true,
"own-secrets": {"store": "${dir:state}/store"},
"secrets-owner": "svc",
"resources": [
{"id": "state", "type": "directory", "mode": "0700", "place": "mesh", "owner": "svc"},
{"id": "service", "type": "process", "name": "svc", "artifact": "code",
"run": ["./svc", "serve"], "user": "svc", "replaces": ["server"],
"env": {"SVC_STORE_FILE": "${dir:state}/store", "SVC_STORE_PORT": "${seat:mesh-store:5432}"}},
{"id": "account", "type": "user", "name": "svc", "shell": "/usr/bin/nologin", "home": "/var/lib/svc"}
],
"build": {"artifacts": [{"name": "code", "kind": "bundle", "language": "go", "system": "arch",
"from": "cmd/svc", "binary": "svc"}]}
}`
m, err := ParseManifest([]byte(raw))
if err != nil {
t.Fatalf("the service's manifest is refused: %v", err)
}
resolved, err := m.Resolve([]Built{{Name: "code", Kind: ArtifactBundle,
Reference: ArtifactStoreScheme + "svc/code@" + aServiceDigest, Digest: aServiceDigest}})
if err != nil {
t.Fatal(err)
}
return resolved
}
func composeTheService(t *testing.T, with Rendering) []map[string]any {
t.Helper()
with.Needed = map[string]map[string]string{"svc": {"store": "sealed-store"}}
with.ArtifactStore = "anchor.internal:5100"
out, err := Resolution{Node: "anchor", Modules: []Manifest{aServiceModule(t)}}.Declaration(with)
if err != nil {
t.Fatalf("the service does not compose: %v", err)
}
return out
}
func indexOf(out []map[string]any, id string) int {
for i, r := range out {
if r["id"] == id {
return i
}
}
return -1
}
// A module that declares tools has every bundle served by the node's runtime unless it says
// otherwise — and the controller declares the verbs it answers as tools. Its service bundle is run
// by its own process; launched a second time by the runtime it would be a second controller
// pretending to be an MCP server.
func TestABundleItsOwnProcessRunsIsNotServedByTheRuntime(t *testing.T) {
m := aServiceModule(t)
if len(m.Bundles) != 1 {
t.Fatalf("the service's bundle was not kept: %+v", m.Bundles)
}
if loads := m.Bundles[0].Loads; len(loads) != 0 {
t.Fatalf("the runtime would launch the service's own bundle as tools: %v", loads)
}
// And a bundle no resource runs still is served, as a module declaring tools always had it.
tools := Manifest{Module: "t", Version: "1", Tools: []string{"x"},
Build: &Build{Artifacts: []Artifact{{Name: "tools", Kind: ArtifactBundle, Language: "go",
System: "arch", From: "cmd/t"}}}}
resolved, err := tools.Resolve([]Built{{Name: "tools", Kind: ArtifactBundle,
Reference: ArtifactStoreScheme + "t/tools@" + aServiceDigest, Digest: aServiceDigest}})
if err != nil {
t.Fatal(err)
}
if loads := resolved.Bundles[0].Loads; len(loads) != 1 || loads[0] != "t" {
t.Fatalf("a tools bundle nothing runs is no longer served: %v", loads)
}
}
// The account is created before anything is given to it. Its secrets are mesh-computed and so
// placed before the module's own resources; given to a user the machine did not have yet, they were
// refused on the first apply and the process started without them.
func TestAModulesAccountComesBeforeWhatBelongsToIt(t *testing.T) {
out := composeTheService(t, Rendering{})
account, secret := indexOf(out, "svc.account"), indexOf(out, "svc."+NeedID("store"))
if account < 0 || secret < 0 {
t.Fatalf("the account or the secret is missing: %v", out)
}
if account > secret {
t.Fatalf("the secret owned by svc is written before svc exists: account at %d, secret at %d",
account, secret)
}
if owner := out[secret]["owner"]; owner != "svc" {
t.Errorf("the secret belongs to %v, not the account its process runs as", owner)
}
}
// The process is the module's program; its preparation is the same program asked to prepare, as a
// step before it — with the same account and environment, and handing nothing over.
func TestAProcessIsPreparedByItsOwnProgram(t *testing.T) {
out := composeTheService(t, Rendering{})
step, process := indexOf(out, "svc.service-prepare"), indexOf(out, "svc.service")
if step < 0 || process < 0 || step > process {
t.Fatalf("the preparation is not a step before the process (%d, %d): %v", step, process, out)
}
s := out[step]
if s["type"] != "process" || s["run-once"] != true || s["name"] != "svc-prepare" {
t.Errorf("the preparation is not a run-once process: %v", s)
}
if run, _ := json.Marshal(s["run"]); string(run) != `["./svc","prepare"]` {
t.Errorf("the preparation runs %s", run)
}
if s["user"] != "svc" || s["source"] != out[process]["source"] {
t.Errorf("the preparation does not run the same bundle as the same account: %v", s)
}
if env, _ := s["env"].(map[string]any); env["SVC_STORE_FILE"] == nil {
t.Errorf("the preparation is not given the process's environment: %v", s["env"])
}
if _, has := s["replaces"]; has {
t.Errorf("the preparation would hand over what the process replaces: %v", s)
}
if _, has := s["args"]; has {
t.Errorf("the preparation carries a container's args: %v", s)
}
}
// What the process replaces is named as the host recorded it, `<module>.<id>`; unprefixed, the host
// matches nothing and removes the container first, as before.
func TestWhatAProcessReplacesIsNamedAsTheHostRecordedIt(t *testing.T) {
out := composeTheService(t, Rendering{})
p := out[indexOf(out, "svc.service")]
if got, _ := json.Marshal(p["replaces"]); string(got) != `["svc.server"]` {
t.Fatalf("the process replaces %s", got)
}
}
func TestWhatReplacesMayNameIsRefusedNearItsAuthor(t *testing.T) {
for what, resource := range map[string]string{
"a container": `{"id":"c","type":"container","name":"c","image":"x@` + aServiceDigest + `","replaces":["old"]}`,
"a step": `{"id":"p","type":"process","name":"p","run":["./p"],"run-once":true,"replaces":["old"]}`,
"something declared": `{"id":"p","type":"process","name":"p","run":["./p"],"replaces":["p"]}`,
"another module's": `{"id":"p","type":"process","name":"p","run":["./p"],"replaces":["other.old"]}`,
"not a list": `{"id":"p","type":"process","name":"p","run":["./p"],"replaces":"old"}`,
} {
raw := `{"module":"m","version":"1","resources":[` + resource + `]}`
if _, err := ParseManifest([]byte(raw)); err == nil || !strings.Contains(err.Error(), "replace") {
t.Errorf("replaces on %s was accepted: %v", what, err)
}
}
ok := `{"module":"m","version":"1","resources":[{"id":"p","type":"process","name":"p","run":["./p"],"replaces":["old"]}]}`
if _, err := ParseManifest([]byte(ok)); err != nil {
t.Errorf("a process replacing what its module no longer declares was refused: %v", err)
}
}
+7 -14
View File
@@ -21,8 +21,9 @@ import (
// formats and gains no fields. // formats and gains no fields.
// //
// **It stays name-agnostic** ([ADR 0027]). The mesh does not learn what a `postgres-database` is: // **It stays name-agnostic** ([ADR 0027]). The mesh does not learn what a `postgres-database` is:
// `at`, `as` and `from` are facts about any provision at all, and everything else comes from what // `at`, `as`, `from` and `address` (the providing machine's private address, novox/hq ADR 0194) are
// the provider said it serves — whose keys are agreed by the requirement's name, not by this file. // facts about any provision at all, and everything else comes from what the provider said it
// serves — whose keys are agreed by the requirement's name, not by this file.
// bound is where a module says a value from one of its bindings belongs: // bound is where a module says a value from one of its bindings belongs:
// ${bound:<provision>.<key>}. // ${bound:<provision>.<key>}.
@@ -46,7 +47,7 @@ func boundUsed(content string) [][2]string {
// Three facts the mesh states about any provision, plus whatever the provider said it serves. A // Three facts the mesh states about any provision, plus whatever the provider said it serves. A
// module may not reach a binding it does not have — the same boundary as a secret, for the same // module may not reach a binding it does not have — the same boundary as a secret, for the same
// reason. // reason.
func knownFor(m Manifest, needs []Needed, node string) (map[string]map[string]string, error) { func knownFor(m Manifest, needs []Needed, node string) map[string]map[string]string {
out := map[string]map[string]string{} out := map[string]map[string]string{}
for _, want := range m.Wants() { for _, want := range m.Wants() {
for i := range needs { for i := range needs {
@@ -54,20 +55,12 @@ func knownFor(m Manifest, needs []Needed, node string) (map[string]map[string]st
if n.Name != want || n.For != m.Module { if n.Name != want || n.For != m.Module {
continue continue
} }
as := ConsumerIdentity(node, IdentitySource(m.Slug, m.Module))
values := map[string]string{ values := map[string]string{
"at": n.At, "at": n.At,
"from": n.From, "from": n.From,
"as": as, "as": ConsumerIdentity(node, IdentitySource(m.Slug, m.Module)),
} }
// What the provider derives for this consumer rather than for all of them for key, value := range n.Serves {
// (novox/hq ADR 0202). Filled here, the one place a provision and the module
// requiring it are both in hand.
served, err := ServedTo(n.Serves, as)
if err != nil {
return nil, fmt.Errorf("%s requires %s: %w", m.Module, want, err)
}
for key, value := range served {
// The provider's own vocabulary. Rendered plainly: a port is 5432, not 5432.000000, // The provider's own vocabulary. Rendered plainly: a port is 5432, not 5432.000000,
// which is what a float would write and what a connection string would refuse. // which is what a float would write and what a connection string would refuse.
values[key] = plainly(value) values[key] = plainly(value)
@@ -75,7 +68,7 @@ func knownFor(m Manifest, needs []Needed, node string) (map[string]map[string]st
out[want] = values out[want] = values
} }
} }
return out, nil return out
} }
// withOwnNames adds a module's own composed names to what it may name from one binding: // withOwnNames adds a module's own composed names to what it may name from one binding:
@@ -232,3 +232,34 @@ func TestTwoModulesOnOneNodeAreTwoIdentities(t *testing.T) {
t.Fatal("one module on two machines shares an identity") t.Fatal("one module on two machines shares an identity")
} }
} }
// A machine's resolver configuration must name its resolver by address — it cannot resolve the name
// of the thing it resolves names with (novox/hq ADR 0194). So a binding offers the providing
// machine's private address beside its name, and only when the machine has one.
func TestABindingOffersTheProvidersAddress(t *testing.T) {
consumer := func() Resolution {
return Resolution{
Node: "workstation",
Modules: []Manifest{{
Module: "resolv-conf",
Requires: []string{"wildcard-resolution"},
Resources: []map[string]any{{
"id": "resolv", "type": "file", "path": "/etc/resolv.conf", "mode": "0644",
"content": "nameserver ${bound:wildcard-resolution:address}\n",
}},
}},
Needs: []Needed{{Name: "wildcard-resolution", From: "anchor", At: "anchor.internal", For: "resolv-conf"}},
}
}
out, err := consumer().Declaration(Rendering{Machines: map[string]string{"anchor.internal": "10.77.0.1"}})
if err != nil {
t.Fatal(err)
}
if got := fileNamed(out, "resolv-conf.resolv")["content"]; got != "nameserver 10.77.0.1\n" {
t.Fatalf("the resolver is not named by its address: %q", got)
}
// A machine with no address yet: refused, never written with a blank where the address belongs.
if _, err := consumer().Declaration(Rendering{}); err == nil {
t.Fatal("a file naming an address the mesh does not have was composed")
}
}
+7 -25
View File
@@ -77,7 +77,6 @@ func (m Manifest) Resolve(built []Built) (Manifest, error) {
// build compare equal. // build compare equal.
out.Bundles = nil out.Bundles = nil
if m.Build != nil { if m.Build != nil {
run := runByAResource(m)
for _, a := range m.Build.Artifacts { for _, a := range m.Build.Artifacts {
if a.Kind != ArtifactBundle { if a.Kind != ArtifactBundle {
continue continue
@@ -85,13 +84,8 @@ func (m Manifest) Resolve(built []Built) (Manifest, error) {
made := by[a.Name] made := by[a.Name]
// What the runtime loads: what the artifact said, else every entrypoint of a module // What the runtime loads: what the artifact said, else every entrypoint of a module
// that declares tools, else nothing (the field's own rule; see Artifact.Loads). // that declares tools, else nothing (the field's own rule; see Artifact.Loads).
//
// **Never, unasked, a bundle one of the module's own resources runs** (novox/hq issue 213).
// A process the host runs is the module's service, not its tools: the controller declares
// the verbs it answers as `tools` and serves them itself, and its bundle would otherwise
// have been launched a second time by the node's runtime, as an MCP child it is not.
loads := append([]string(nil), a.Loads...) loads := append([]string(nil), a.Loads...)
if a.Loads == nil && len(m.Tools) > 0 && !run[a.Name] { if a.Loads == nil && len(m.Tools) > 0 {
loads = append([]string(nil), a.Entrypoints...) loads = append([]string(nil), a.Entrypoints...)
// A bundle compiled to a binary has no entrypoints: the binary is what it is, and what // A bundle compiled to a binary has no entrypoints: the binary is what it is, and what
// the runtime starts to serve it (novox/hq ADR 0193). So a Go tools bundle is served // the runtime starts to serve it (novox/hq ADR 0193). So a Go tools bundle is served
@@ -220,11 +214,6 @@ func (b *Build) problems(module string) []string {
// A bundle's source is the module's own directory by definition, and what it needs to say // A bundle's source is the module's own directory by definition, and what it needs to say
// is which compiler — because the mesh chooses that, and cannot choose for a module that // is which compiler — because the mesh chooses that, and cannot choose for a module that
// has not said. // has not said.
if len(a.External) > 0 && (a.Kind != ArtifactBundle || a.Language != "typescript") {
problems = append(problems, fmt.Sprintf(
"%s: %q names packages it keeps external, and only a TypeScript bundle is bundled into "+
"one file with some kept out (novox/hq ADR 0193)", module, a.Name))
}
if len(a.Env) > 0 && a.Kind != ArtifactBundle { if len(a.Env) > 0 && a.Kind != ArtifactBundle {
problems = append(problems, fmt.Sprintf( problems = append(problems, fmt.Sprintf(
"%s: %q is a %q and says what it is given (env). Only a bundle the node's runtime "+ "%s: %q is a %q and says what it is given (env). Only a bundle the node's runtime "+
@@ -459,18 +448,6 @@ func BinaryOf(a Artifact) string {
return a.Name return a.Name
} }
// runByAResource is the artifacts one of a module's own resources names — a process that runs it,
// a step, an archive that unpacks it — by name.
func runByAResource(m Manifest) map[string]bool {
named := map[string]bool{}
for _, r := range m.Resources {
if a, ok := r["artifact"].(string); ok && a != "" {
named[a] = true
}
}
return named
}
// undeliveredBundles says which of a module's bundles nothing would ever put on a machine (novox/hq // undeliveredBundles says which of a module's bundles nothing would ever put on a machine (novox/hq
// 04-ISSUES/216). A bundle reaches a machine three ways: the node's runtime serves it (it says // 04-ISSUES/216). A bundle reaches a machine three ways: the node's runtime serves it (it says
// `loads`, or its module declares `tools`), a resource names it (a process, a step, an archive), or // `loads`, or its module declares `tools`), a resource names it (a process, a step, an archive), or
@@ -481,7 +458,12 @@ func undeliveredBundles(m Manifest) []string {
if m.Build == nil || m.Module == RuntimeModule { if m.Build == nil || m.Module == RuntimeModule {
return nil return nil
} }
named := runByAResource(m) named := map[string]bool{}
for _, r := range m.Resources {
if a, ok := r["artifact"].(string); ok && a != "" {
named[a] = true
}
}
var problems []string var problems []string
for _, a := range m.Build.Artifacts { for _, a := range m.Build.Artifacts {
if a.Kind != ArtifactBundle || named[a.Name] || len(a.Loads) > 0 || len(m.Tools) > 0 { if a.Kind != ArtifactBundle || named[a.Name] || len(a.Loads) > 0 || len(m.Tools) > 0 {
-311
View File
@@ -1,311 +0,0 @@
package catalogue
import (
"fmt"
"regexp"
"sort"
"strings"
)
// What a provider derives for one consumer, said once in the provider's definition and delivered
// to both ends (novox/hq ADR 0202, issue 124).
//
// A `serves` block is otherwise literal: the same values for every consumer. Where the provider
// *names the resource* — a bucket, a database, a vhost — the name is derived from who is asking,
// and before this the mesh had no channel for it. The provider recomputed it in its own code and
// every consumer transcribed it into its own definition by hand, which is a copy of somebody
// else's rule kept in agreement by nobody. One of three transcriptions was wrong for months.
//
// **The mesh learns no protocol here; it spells its own name in an alphabet it already knows.**
// The only fact a served value may name is the identity the mesh itself minted for the consumer,
// in one of two alphabets: as it was minted, and as a DNS label. Everything a provider wants
// around it — a prefix, a suffix, a separator — it writes around the placeholder, because a
// served value is a string.
// consumerFact is `${consumer:<fact>}` or `${consumer:<fact>:<alphabet>}`.
var consumerFact = regexp.MustCompile(`\$\{consumer:([a-z][a-z0-9-]*)(?::([a-z][a-z0-9-]*))?\}`)
// consumerFacts are what a served value may name about the consumer it is being derived for.
// One entry, deliberately: the identity is the one thing about a consumer the mesh itself chose,
// so it is the one thing the mesh can hand to a provider without either end guessing.
var consumerFacts = []string{"as"}
// consumerAlphabets are the ways the mesh will write that identity. `dns` is the mesh's own
// identifier with its separator written `-` instead of `_` — the whole of the difference between
// the alphabet the mesh mints in and the one buckets, vhosts and hostnames accept.
var consumerAlphabets = []string{"dns"}
// ServedTo fills a provider's served values for one consumer.
//
// `as` is the identity the mesh minted for that consumer — the same string it is told to present
// as a login. Values with no placeholder are returned exactly as they were, and a block with no
// placeholder at all is returned unchanged, so this costs nothing for the providers that derive
// nothing.
//
// Only strings carry placeholders. A number, a boolean or a nested object is a value the provider
// stated outright, and is left alone.
func ServedTo(serves map[string]any, as string) (map[string]any, error) {
if len(serves) == 0 {
return serves, nil
}
var out map[string]any
for _, key := range sortedAnyKeys(serves) {
text, ok := serves[key].(string)
if !ok || !strings.Contains(text, "${consumer:") {
continue
}
filled, err := consumerInto(text, as)
if err != nil {
return nil, fmt.Errorf("the value served as %q: %w", key, err)
}
if out == nil {
// Copied only once something actually changes: the caller's map is the manifest's,
// and a provider that derives nothing must not have it rewritten underneath it.
out = make(map[string]any, len(serves))
for k, v := range serves {
out[k] = v
}
}
out[key] = filled
}
if out == nil {
return serves, nil
}
return out, nil
}
// consumerInto replaces every `${consumer:…}` in one value.
//
// **A fact or an alphabet the mesh does not have is refused, not left standing.** Written through,
// the literal `${consumer:as}` would reach a configuration file and be read as a bucket name,
// failing somewhere that names neither the module nor the mesh — the same reasoning `${bound:…}`
// is refused by (boundInto).
func consumerInto(value, as string) (string, error) {
var failed error
out := consumerFact.ReplaceAllStringFunc(value, func(match string) string {
parts := consumerFact.FindStringSubmatch(match)
fact, alphabet := parts[1], parts[2]
if fact != "as" {
if failed == nil {
failed = fmt.Errorf(
"says %s, and the mesh states %s about a consumer", match, orNothing(consumerFacts))
}
return match
}
switch alphabet {
case "":
return as
case "dns":
return asDNSLabel(as)
default:
if failed == nil {
failed = fmt.Errorf(
"says %s, and the mesh writes an identity as %s", match, orNothing(consumerAlphabets))
}
return match
}
})
if failed != nil {
return "", failed
}
return out, nil
}
// asDNSLabel writes a minted identity as a DNS label.
//
// The mesh's identities are already lower-case letters, digits and `_` (ConsumerIdentity), and
// already short enough for the tightest backend they reach (CheckIdentity, twenty characters). So
// this is the separator and nothing else — no lower-casing of what is already lower case, no
// truncation to a limit the identity is already inside, no padding of a name that is already long
// enough. Each of those would be the mesh guessing at a rule it has not been given.
func asDNSLabel(as string) string {
return strings.ReplaceAll(as, "_", "-")
}
// CheckServes refuses a `serves` block that names a consumer fact or an alphabet the mesh does not
// have, when the definition is parsed rather than when a consumer is resolved.
//
// A provision nobody consumes yet still has its rule read: a definition that would be refused the
// first time somebody required it is a definition that is wrong now.
func CheckServes(m Manifest) []string {
var problems []string
for _, provision := range sortedServes(m.Serves) {
for _, key := range sortedAnyKeys(m.Serves[provision]) {
text, ok := m.Serves[provision][key].(string)
if !ok {
continue
}
// A probe identity, because what is checked is the shape of the statement and not
// what any consumer is called.
if _, err := consumerInto(text, "mesh_node_module"); err != nil {
problems = append(problems, fmt.Sprintf(
"%s serves %s, and the value it serves as %q %s", m.Module, provision, key, err))
}
}
}
return problems
}
func sortedServes(serves map[string]map[string]any) []string {
out := make([]string, 0, len(serves))
for k := range serves {
out = append(out, k)
}
sort.Strings(out)
return out
}
func sortedAnyKeys(values map[string]any) []string {
out := make([]string, 0, len(values))
for k := range values {
out = append(out, k)
}
sort.Strings(out)
return out
}
// derivedFor is what the provider on this machine derives for one consumer of one provision
// (novox/hq ADR 0202).
//
// Settled first, then derived: an operator may set a prefix on what the provider serves and the
// mesh still fills the consumer's half of it ([ADR 0174]). Only the keys that actually name the
// consumer are returned — the rest of a `serves` block is the same for every consumer and is
// already in the provider's own definition, so repeating it here would be a second copy to go
// stale.
//
// The first module in the resolved order that says it serves the provision answers, which is the
// choice servedOnThisMachine makes for the consumer's half. Nothing serving it on this machine is
// not an error: a contribution can reach a machine whose provider is a record or an adapter, and
// then there is nothing derived to tell.
func (r Resolution) derivedFor(provision, as, consumer, local string, settings SettingsBy) (map[string]any, error) {
for _, m := range r.Modules {
serves, said := m.Serves[provision]
if !said {
continue
}
var names map[string]any
for key, value := range serves {
if text, ok := value.(string); ok && strings.Contains(text, "${consumer:") {
if names == nil {
names = map[string]any{}
}
names[key] = value
}
}
if names == nil {
return nil, nil
}
// **A consumer that keeps several holders of this provision is refused** — this is issue
// 124's own failure one case to the side, and it would be just as quiet.
//
// Each holder gets its own login, `…_<local>` (ADR 0094), and a provider derives from the
// login, so it would make one resource per holder. The consumer's side has no such
// dimension: one binding file per provision, one `${bound:<provision>:<key>}`, both
// derived from the un-suffixed identity. So the provider would create the holder's
// resource and the consumer would be configured against a name nothing made — it would
// authenticate successfully and be refused on every object, which reads like a credential
// fault and is not one.
//
// Lifting this means giving the consumer's side a local dimension. That is a decision,
// not an omission, and until it is taken the mesh says so rather than guessing.
if local != "" {
return nil, fmt.Errorf(
"%s keeps several holders of %s (this one is %q), and %s derives %s for each "+
"consumer from the login the mesh minted. Each holder has its own login, and a "+
"consumer is told one value per requirement — so the two ends would name "+
"different things and nothing would compare them (novox/hq ADR 0202)",
consumer, local, provision, m.Module, orNothing(sortedAnyKeys(names)))
}
settled, err := Settle(names, settings[m.Module])
if err != nil {
return nil, fmt.Errorf("%s serving %s: %w", m.Module, provision, err)
}
derived, err := ServedTo(settled, as)
if err != nil {
return nil, fmt.Errorf("%s serving %s to %s: %w", m.Module, provision, as, err)
}
return derived, nil
}
return nil, nil
}
// notTranscribed refuses a consumer's file that writes out the value its provider derives for it,
// instead of asking for it (novox/hq ADR 0202, issue 124).
//
// **What would have caught the one wrong instance.** The object store's three consumers each wrote
// their bucket into their own configuration by hand. One of them named a predecessor's bucket, and
// nothing compared it to what the provider would actually create: the module would have
// authenticated successfully and been refused on every object, which reads like a credential fault
// and is not one. It looked authoritative for months.
//
// The test is exact and costs one string search: a definition whose file already contains the
// value the mesh is about to derive for it has written down somebody else's rule. It cannot be a
// coincidence — a derived value carries the identity the mesh minted for this very consumer on
// this very machine, which nothing else would spell out — and it cannot be checked afterwards,
// because after substitution every consumer's file contains it legitimately.
//
// Only values that actually name the consumer are judged. A provider that serves a constant under
// the same key serves the same constant to everyone, and a consumer repeating it is redundant
// rather than wrong.
func notTranscribed(resource map[string]any, known map[string]map[string]string, module string) error {
if fmt.Sprint(resource["type"]) != "file" {
return nil
}
content, ok := resource["content"].(string)
if !ok || content == "" {
return nil
}
for _, provision := range sortedKnown(known) {
values := known[provision]
identity := values["as"]
if identity == "" {
continue
}
for _, key := range sortedStringKeys(values) {
if key == "as" {
// The login is not derived from itself, and a consumer that must present it in a
// connection string legitimately has it from `${bound:…}` — which is what it will
// be after substitution, so this would judge the substitution, not the module.
continue
}
value := values[key]
if value == "" || !namesTheConsumer(value, identity) {
continue
}
if !strings.Contains(content, value) {
continue
}
return fmt.Errorf(
"%s writes %q into %v, and that is exactly what %s derives for it — a definition "+
"keeping its own copy of somebody else's naming rule is one that can disagree "+
"with it, silently. Say ${bound:%s:%s} and be told",
module, value, resource["id"], provision, provision, key)
}
}
return nil
}
// namesTheConsumer is whether a derived value was built from this consumer's identity — in the
// alphabet it was minted in, or as a DNS label. A value that does not contain it was not derived
// from it, whatever else it may be.
func namesTheConsumer(value, identity string) bool {
return strings.Contains(value, identity) || strings.Contains(value, asDNSLabel(identity))
}
func sortedKnown(known map[string]map[string]string) []string {
out := make([]string, 0, len(known))
for k := range known {
out = append(out, k)
}
sort.Strings(out)
return out
}
func sortedStringKeys(values map[string]string) []string {
out := make([]string, 0, len(values))
for k := range values {
out = append(out, k)
}
sort.Strings(out)
return out
}
@@ -1,131 +0,0 @@
package catalogue
import (
"encoding/json"
"fmt"
"os"
"strings"
"testing"
)
// novox/hq issue 213: the controller is a Go program and was the one piece of the mesh's own Go
// code still shipped as an image (ADR 0188 §1). Its own manifest, composed for the machine that runs
// it, is a Go bundle run by the host as a process — and no container.
func TestTheControllerIsAProcessAndNoContainer(t *testing.T) {
raw, err := os.ReadFile("../../module.json")
if err != nil {
t.Fatal(err)
}
m, err := ParseManifest(raw)
if err != nil {
t.Fatalf("the controller's own manifest does not parse:\n%v", err)
}
if m.Build == nil || len(m.Build.Artifacts) != 1 {
t.Fatalf("the controller builds %+v; it is one bundle", m.Build)
}
a := m.Build.Artifacts[0]
if a.Kind != ArtifactBundle || a.Language != "go" || a.System == "" || BinaryOf(a) != "mesh-controller" {
t.Fatalf("the controller's artifact is %+v, not a Go bundle naming its system and binary", a)
}
for _, c := range m.Capabilities {
if c == "container-runtime" {
t.Error("the controller still requires a container runtime on its machine")
}
}
digest := "sha256:" + strings.Repeat("c", 64)
control, err := m.Resolve([]Built{{Name: a.Name, Kind: ArtifactBundle,
Reference: ArtifactStoreScheme + "mesh-controller/" + a.Name + "@" + digest, Digest: digest}})
if err != nil {
t.Fatal(err)
}
// The node's runtime does not launch it: it serves its seat's verbs itself.
if loads := control.Bundles[0].Loads; len(loads) != 0 {
t.Errorf("the node's runtime would launch the controller as a tools bundle: %v", loads)
}
needed := map[string]map[string]string{"mesh-controller": {}}
for name := range m.OwnSecrets {
needed["mesh-controller"][name] = "sealed-" + name
}
out, err := Resolution{Node: "anchor", Modules: []Manifest{control}}.Declaration(Rendering{
Needed: needed, ArtifactStore: "anchor.internal:5100",
Seats: map[string]map[int]int{"mesh-store": {5432: 6852}},
})
if err != nil {
t.Fatalf("the controller does not compose: %v", err)
}
var process, step map[string]any
account, firstSecret := -1, -1
for i, r := range out {
switch {
case r["type"] == "container":
t.Errorf("the controller's declaration still runs a container: %v", r)
case r["id"] == "mesh-controller.controller":
process = r
case r["id"] == "mesh-controller.controller-prepare":
step = r
if process != nil {
t.Error("the controller's preparation is placed after the process it prepares for")
}
case r["type"] == "user" && r["name"] == "mesh-controller":
account = i
case strings.HasPrefix(fmt.Sprint(r["id"]), "mesh-controller.needs-") && firstSecret < 0:
firstSecret = i
}
}
if process == nil {
t.Fatalf("the controller's process is not in its declaration: %v", out)
}
if run, _ := json.Marshal(process["run"]); string(run) != `["./mesh-controller","serve"]` {
t.Errorf("the controller is run as %s, not its own bundle's binary", run)
}
if process["source"] != "anchor.internal:5100/mesh-controller/"+a.Name+"@"+digest || process["digest"] != digest {
t.Errorf("the controller's bundle is fetched from %v (%v)", process["source"], process["digest"])
}
// The user: an account the host declares, which owns what the process reads.
if process["user"] != "mesh-controller" || account < 0 {
t.Errorf("the controller runs as %v, and the account declared is at %d", process["user"], account)
}
if firstSecret >= 0 && account > firstSecret {
t.Error("the controller's secrets are written before the account they belong to exists")
}
for _, r := range out {
if strings.HasPrefix(fmt.Sprint(r["id"]), "mesh-controller.needs-") && r["owner"] != "mesh-controller" {
t.Errorf("%v belongs to %v, which the controller's process cannot read", r["id"], r["owner"])
}
}
if dir := fileNamed(out, "mesh-controller.mesh-state"); dir == nil || dir["owner"] != "mesh-controller" {
t.Errorf("the controller's state directory is not its account's to enter: %v", dir)
}
// Each mount became a path the process reads: nothing it is told is a path inside a container.
state := fmt.Sprint(fileNamed(out, "mesh-controller.mesh-state")["path"])
env, _ := process["env"].(map[string]any)
for key, value := range env {
v := fmt.Sprint(value)
if strings.HasPrefix(v, "/run/secrets") || strings.HasPrefix(v, "/broker-tls") {
t.Errorf("%s=%s is a path inside the container the controller no longer runs in", key, v)
}
if strings.HasSuffix(key, "_FILE") && !strings.HasPrefix(v, state+"/") {
t.Errorf("%s=%s is not one of the files the mesh places for it", key, v)
}
}
if env["MESH_BROKER_CERTIFICATE"] != "/var/lib/mesh-broker-tls/tls.crt" {
t.Errorf("the controller reads the broker's certificate from %v", env["MESH_BROKER_CERTIFICATE"])
}
if env["MESH_STORE_INVENTORY_PORT"] != "6852" {
t.Errorf("the controller is told the store is on %v; the node put it on 6852", env["MESH_STORE_INVENTORY_PORT"])
}
// The handover: the container it ran as goes only once this is running.
if got, _ := json.Marshal(process["replaces"]); string(got) != `["mesh-controller.server"]` {
t.Errorf("the controller's process replaces %s, not the container it ran as", got)
}
// And its state is prepared first, by the same program as the same account.
if step == nil || step["run-once"] != true || step["user"] != "mesh-controller" {
t.Fatalf("the controller's preparation is %v", step)
}
if run, _ := json.Marshal(step["run"]); string(run) != `["./mesh-controller","prepare"]` {
t.Errorf("the controller's preparation runs %s", run)
}
}
+24 -112
View File
@@ -155,6 +155,10 @@ type Rendering struct {
// standing beside the machines and looking as real as they do. // standing beside the machines and looking as real as they do.
Machines map[string]string Machines map[string]string
// Zones is every zone a module in the mesh answers itself, where it is answered (novox/hq ADR
// 0199): the mesh's resolver forwards each one there.
Zones []ZoneAt
Settings SettingsBy Settings SettingsBy
Generators map[string]Generator Generators map[string]Generator
// Grants are the credentials this node must create, for the provisions it offers. Passed in // Grants are the credentials this node must create, for the provisions it offers. Passed in
@@ -645,16 +649,7 @@ func (r Resolution) compose(with Rendering, owner map[string]string,
if err != nil { if err != nil {
return nil, err return nil, err
} }
as := ConsumerIdentity(r.Node, IdentitySource(m.Slug, m.Module)) file, err := boundFile(*found, m.Binds[to], ConsumerIdentity(r.Node, IdentitySource(m.Slug, m.Module)), own)
// What the provider derives for THIS consumer, filled here where the consumer is
// known (novox/hq ADR 0202). The same fill knownFor does below, so the binding file
// and the module's `${bound:…}` substitutions cannot say different things.
told := *found
told.Serves, err = ServedTo(told.Serves, as)
if err != nil {
return nil, fmt.Errorf("%s is told about %s: %w", m.Module, to, err)
}
file, err := boundFile(told, m.Binds[to], as, own)
if err != nil { if err != nil {
return nil, err return nil, err
} }
@@ -702,15 +697,7 @@ func (r Resolution) compose(with Rendering, owner map[string]string,
// Now, and not before: a module whose resources are computed replaces them wholesale, and // Now, and not before: a module whose resources are computed replaces them wholesale, and
// merging earlier would throw away the files it still needs. // merging earlier would throw away the files it still needs.
// resources = append(append([]map[string]any{}, first...), resources...)
// **Except the module's own accounts, which go before even those** (novox/hq issue 213). What
// the mesh computes may belong to one: a module whose code runs as an account it declares has
// its secrets written owned by that account, and a file given to a user the machine does not
// have yet fails — so on the first apply the secrets were refused, the process started without
// them, and the second apply healed it, which is the fault the paragraph above describes.
// An account depends on nothing the mesh computes.
accounts, rest := accountsFirst(resources)
resources = append(append(accounts, first...), rest...)
// No container is given the mesh's names (novox/hq ADR 0148). It used to be: every // No container is given the mesh's names (novox/hq ADR 0148). It used to be: every
// container got the whole roster as `--add-host` entries at creation, and a name that // container got the whole roster as `--add-host` entries at creation, and a name that
@@ -728,10 +715,7 @@ func (r Resolution) compose(with Rendering, owner map[string]string,
return nil, err return nil, err
} }
// And what its bindings say, for the half of a connection that is not secret. // And what its bindings say, for the half of a connection that is not secret.
known, err := knownFor(m, r.Needs, r.Node) known := knownFor(m, r.Needs, r.Node)
if err != nil {
return nil, err
}
// A requirement answered on this same machine is not in r.Needs — its binding file is // A requirement answered on this same machine is not in r.Needs — its binding file is
// written from `here` (above) — and so `${bound:…}` could not name it, though the file // written from `here` (above) — and so `${bound:…}` could not name it, though the file
// beside it said the same facts. Filled from the same answer, so the two cannot disagree. // beside it said the same facts. Filled from the same answer, so the two cannot disagree.
@@ -748,14 +732,20 @@ func (r Resolution) compose(with Rendering, owner map[string]string,
} }
local := *answered local := *answered
local.For = m.Module local.For = m.Module
here, err := knownFor(m, []Needed{local}, r.Node) for provision, values := range knownFor(m, []Needed{local}, r.Node) {
if err != nil {
return nil, err
}
for provision, values := range here {
known[provision] = values known[provision] = values
} }
} }
// And the providing machine's private address, beside its name (novox/hq ADR 0194). A name is
// what nearly every consumer wants; the one that cannot use it is a machine's resolver
// configuration, which must reach the resolver before it can resolve anything — the resolver's
// own name included. Absent when the machine has no address yet, so a file naming it is refused
// rather than written with a blank where an address belongs.
for _, values := range known {
if address := with.Machines[values["at"]]; address != "" {
values["address"] = address
}
}
// And what the module is called through each requirement it contributes to (novox/hq // And what the module is called through each requirement it contributes to (novox/hq
// 04-ISSUES/122) — the same composition its binding file carries. // 04-ISSUES/122) — the same composition its binding file carries.
for provision, values := range known { for provision, values := range known {
@@ -777,17 +767,6 @@ func (r Resolution) compose(with Rendering, owner map[string]string,
// And the machine underneath, which no binding of its own can tell it. // And the machine underneath, which no binding of its own can tell it.
thisMachine := machineFacts(r, with.Names, with.MeshRange) thisMachine := machineFacts(r, with.Names, with.MeshRange)
// **A definition that already holds the answer transcribed it** (novox/hq ADR 0202).
// Judged over what the module itself declares, and before anything is substituted: the
// mesh's own generated files — the binding, the contributions — legitimately carry the
// derived value, and after substitution so does every consumer's file, so this is the one
// moment the two can be told apart.
for _, own := range m.Resources {
if err := notTranscribed(own, known, m.Module); err != nil {
return nil, err
}
}
// Which of this module's files carry a secret, for the rule that a container may not read // Which of this module's files carry a secret, for the rule that a container may not read
// one of them as its environment without saying so (ADR 0086, issue 041). // one of them as its environment without saying so (ADR 0086, issue 041).
secretFiles := secretFilesOf(resources) secretFiles := secretFilesOf(resources)
@@ -907,21 +886,6 @@ func (r Resolution) compose(with Rendering, owner map[string]string,
if renamed := reflectsRenamed(m.Module, resource["reload-on"]); renamed != nil { if renamed := reflectsRenamed(m.Module, resource["reload-on"]); renamed != nil {
copied["reload-on"] = renamed copied["reload-on"] = renamed
} }
// And which of its module's containers a scheduled step holds still (novox/hq ADR 0189).
// **The loudest of the three when it is missed.** An unprefixed `restart-on` matches
// nothing and a service quietly never restarts; an unprefixed `while-stopped` names a
// container the declaration does not contain, and the host refuses the whole
// declaration — so the machine takes nothing at all, for every push, until this is
// right. That is what it did on the control node (2026-10-04).
if renamed := reflectsRenamed(m.Module, resource[WhileStopped]); renamed != nil {
copied[WhileStopped] = renamed
}
// And what a process replaces (novox/hq issue 213): a resource of this module's that it
// no longer declares, named as the host recorded it, or the host hands nothing over and
// removes it first.
if renamed := reflectsRenamed(m.Module, resource["replaces"]); renamed != nil {
copied["replaces"] = renamed
}
// **What reads one of this module's own secrets is restarted when it changes** (novox/hq // **What reads one of this module's own secrets is restarted when it changes** (novox/hq
// issue 203, issue 206). A credential is re-issued by the mesh, and a container that // issue 203, issue 206). A credential is re-issued by the mesh, and a container that
// mounted the old file keeps the old one open: the build machine ran for an hour on a // mounted the old file keeps the old one open: the build machine ran for an hour on a
@@ -951,7 +915,7 @@ func (r Resolution) compose(with Rendering, owner map[string]string,
// plane's; making a name resolve is the module's software. Emitted as ordinary files under // plane's; making a name resolve is the module's software. Emitted as ordinary files under
// this module's name, so they are applied, reported and removed exactly as anything else // this module's name, so they are applied, reported and removed exactly as anything else
// it declares. // it declares.
given, err := FactsInto(m, r, with.Names, with.Machines, with.Accounts, with.Suffix) given, err := FactsWithZonesInto(m, r, with.Names, with.Machines, with.Accounts, with.Suffix, with.Zones)
if err != nil { if err != nil {
return nil, err return nil, err
} }
@@ -1211,19 +1175,6 @@ type Contribution struct {
// requirement's name — everything providing `reverse-proxy` understands the same shape, which // requirement's name — everything providing `reverse-proxy` understands the same shape, which
// is what makes swapping one for another cost nothing. // is what makes swapping one for another cost nothing.
Values map[string]any `json:"values"` Values map[string]any `json:"values"`
// Derived is what this provider's own definition said it derives for this consumer, already
// derived (novox/hq ADR 0202).
//
// **The provider is told, rather than recomputing it.** A served value may name the consumer's
// identity — a bucket named for who is asking, a database prefixed with it — and before this
// the rule lived twice: once in the provisioner's code, once transcribed into every consumer's
// definition. The mesh fills the provider's own statement here and delivers the same filled
// value to the consumer, so the two cannot disagree: there is no second computation to
// disagree with.
//
// Only the keys that are per-consumer. The rest of what the provider serves is the same for
// everyone and is in its own definition, where it already is.
Derived map[string]any `json:"derived,omitempty"`
} }
// grantPath is where one consumer's sealed credential lands on the providing machine. // grantPath is where one consumer's sealed credential lands on the providing machine.
@@ -1315,17 +1266,12 @@ func (r Resolution) contributions(settings SettingsBy, grants []Grant,
// told about it and withdraws the login on its next pass. // told about it and withdraws the login on its next pass.
continue continue
} }
as := holderAs(ConsumerIdentity(g.Consumer, IdentitySource(g.Slug, g.From)), g.Local)
derived, err := r.derivedFor(g.Provision, as, g.From, g.Local, settings)
if err != nil {
return nil, err
}
out[g.Provision] = append(out[g.Provision], Contribution{ out[g.Provision] = append(out[g.Provision], Contribution{
From: g.From, Node: g.Consumer, At: g.At, Values: g.Values, Derived: derived, From: g.From, Node: g.Consumer, At: g.At, Values: g.Values,
// One holder per local name: the identity the consumer is known by, and the local name // One holder per local name: the identity the consumer is known by, and the local name
// after it where the module keeps several (ADR 0094). Not a login any backend checks — // after it where the module keeps several (ADR 0094). Not a login any backend checks —
// a secret is not a login — so the identity limit does not apply to the suffix. // a secret is not a login — so the identity limit does not apply to the suffix.
As: as, As: holderAs(ConsumerIdentity(g.Consumer, IdentitySource(g.Slug, g.From)), g.Local),
Secret: grantPath(directories[g.Provision], g.Consumer, holderAs(g.From, g.Local)), Secret: grantPath(directories[g.Provision], g.Consumer, holderAs(g.From, g.Local)),
}) })
if granted[g.Provision] == nil { if granted[g.Provision] == nil {
@@ -2078,18 +2024,12 @@ func preparationTarget(m Manifest) string {
return "" return ""
} }
for _, r := range m.Resources { for _, r := range m.Resources {
// A container, or a process the host runs from a bundle the module built (novox/hq issue if fmt.Sprint(r["type"]) != "container" || !ownArtifact(r, m.Module) {
// 213): the same program in the same context, hosted as a unit rather than a container.
kind := fmt.Sprint(r["type"])
if (kind != "container" && kind != "process") || !ownArtifact(r, m.Module) {
continue continue
} }
if once, _ := r["run-once"].(bool); once { if once, _ := r["run-once"].(bool); once {
continue continue
} }
if r["schedule"] != nil {
continue
}
return fmt.Sprint(r["id"]) return fmt.Sprint(r["id"])
} }
return "" return ""
@@ -2103,10 +2043,7 @@ func ownArtifact(resource map[string]any, module string) bool {
return true return true
} }
image, _ := resource["image"].(string) image, _ := resource["image"].(string)
// A process or an archive carries what was built as its source (novox/hq issue 213). return strings.HasPrefix(image, ArtifactStoreScheme+module+"/")
source, _ := resource["source"].(string)
return strings.HasPrefix(image, ArtifactStoreScheme+module+"/") ||
strings.HasPrefix(source, ArtifactStoreScheme+module+"/")
} }
// prepared is the module's own resource as the step that prepares its state: the same image, the same // prepared is the module's own resource as the step that prepares its state: the same image, the same
@@ -2128,19 +2065,7 @@ func prepared(from map[string]any) map[string]any {
step["id"] = fmt.Sprint(from["id"]) + "-prepare" step["id"] = fmt.Sprint(from["id"]) + "-prepare"
step["name"] = fmt.Sprint(from["name"]) + "-prepare" step["name"] = fmt.Sprint(from["name"]) + "-prepare"
step["run-once"] = true step["run-once"] = true
if fmt.Sprint(from["type"]) == "process" { step["args"] = []any{PreparationArgument}
// A process says its whole command: the program, then its arguments. The step is the same
// program asked to prepare (novox/hq issue 213). It replaces nothing — what the process
// replaces is handed over to the process, never to the step that runs before it — and a
// step is not restarted, it runs again when what it reads changed, which `restart-on` says.
run := stringsIn(from["run"])
if len(run) > 0 {
step["run"] = []any{run[0], PreparationArgument}
}
delete(step, "replaces")
} else {
step["args"] = []any{PreparationArgument}
}
delete(step, "ports") delete(step, "ports")
delete(step, "ip") delete(step, "ip")
delete(step, "schedule") delete(step, "schedule")
@@ -2285,16 +2210,3 @@ func withRestartOn(have any, add []string) []any {
} }
return out return out
} }
// accountsFirst splits a module's resources into its accounts and everything else, each in the order
// written.
func accountsFirst(resources []map[string]any) (accounts, rest []map[string]any) {
for _, r := range resources {
if fmt.Sprint(r["type"]) == "user" {
accounts = append(accounts, r)
continue
}
rest = append(rest, r)
}
return accounts, rest
}
@@ -1,343 +0,0 @@
package catalogue
import (
"encoding/json"
"strings"
"testing"
)
// What a provider derives for each consumer, said once and delivered to both ends
// (novox/hq ADR 0202, issue 124).
//
// The failure these are written against: the object store's provisioner derived each consumer's
// bucket from the login the mesh minted, in its own code, and the mesh had no channel to tell the
// consumer which bucket that was — so all three consumers wrote the answer into their own
// definitions by hand. Two were right. One named a predecessor's bucket and would have
// authenticated successfully and been refused on every object. Each of them also named the
// machine the module happens to run on, which a definition may not do.
// store is an object store in the shape minio has: it serves a region and a port to everyone, and
// a bucket named for whoever is asking.
func store() Manifest {
return Manifest{
Module: "store", Version: "1",
Provides: FromAnywhere("s3-bucket"),
Listens: []Listening{{Port: 9000, Protocol: "tcp", From: FromMesh}},
Serves: map[string]map[string]any{"s3-bucket": {
"region": "eu-west",
"bucket": "${consumer:as:dns}",
}},
Receives: map[string]string{"s3-bucket": "/var/lib/store/grants/mesh.json"},
Grants: map[string]string{"s3-bucket": "/var/lib/store/grants"},
Resources: []map[string]any{{
"id": "server", "type": "container", "name": "store", "ports": []any{"9000"},
}},
}
}
// files is a consumer that writes the bucket into its own configuration — which is the thing it
// could not do before, and had to transcribe.
func files() Manifest {
return Manifest{
Module: "files", Version: "1", Slug: "files",
Requires: []string{"s3-bucket"},
Binds: map[string]string{"s3-bucket": "/var/lib/files/store.json"},
Secrets: map[string]string{"s3-bucket": "/var/lib/files/store.secret"},
Resources: []map[string]any{{
"id": "env", "type": "file", "path": "/var/lib/files/env", "mode": "0600",
"content": "BUCKET=${bound:s3-bucket:bucket}\nREGION=${bound:s3-bucket:region}\n",
}},
}
}
// pics is a second consumer of the same provider on the same machine: two derivations, neither
// the other's.
func pics() Manifest {
return Manifest{
Module: "pics", Version: "1", Slug: "pics",
Requires: []string{"s3-bucket"},
Binds: map[string]string{"s3-bucket": "/var/lib/pics/store.json"},
Secrets: map[string]string{"s3-bucket": "/var/lib/pics/store.secret"},
Resources: []map[string]any{{
"id": "env", "type": "file", "path": "/var/lib/pics/env", "mode": "0600",
"content": "BUCKET=${bound:s3-bucket:bucket}\n",
}},
}
}
// The three places the derived value lands must agree, because agreeing is the whole point: the
// consumer's own file, the binding it reads as JSON, and the provider's contributions entry.
func TestADerivedValueReachesBothEndsAndAgrees(t *testing.T) {
r, err := Resolve(shelf(store(), files()), []string{"store", "files"}, reachable(), World{})
if err != nil {
t.Fatal(err)
}
out, err := r.Declaration(Rendering{Grants: []Grant{{
Provision: "s3-bucket", Consumer: "workstation", From: "files", Slug: "files",
Values: map[string]any{}, Sealed: "c2VhbGVk",
}}})
if err != nil {
t.Fatal(err)
}
// The mesh minted this identity for the consumer; the bucket is that identity as a DNS label.
// Derived here with the mesh's own function, so the test cannot agree with a wrong rule.
as := ConsumerIdentity("workstation", IdentitySource("files", "files"))
want := strings.ReplaceAll(as, "_", "-")
if want == as || !strings.Contains(as, "_") {
t.Fatalf("the mesh's identity %q has no separator to rewrite; this test proves nothing", as)
}
env := fileNamed(out, "files.env")
if env == nil {
t.Fatalf("the consumer was given no file: %v", out)
}
if got := env["content"].(string); !strings.Contains(got, "BUCKET="+want+"\n") {
t.Errorf("the consumer's own file was not told the bucket:\n%s\nwant BUCKET=%s", got, want)
}
binding := fileNamed(out, "files.bound-s3-bucket")
if binding == nil {
t.Fatalf("the consumer was given no binding: %v", out)
}
var said struct {
Serves map[string]any `json:"serves"`
}
if err := json.Unmarshal([]byte(binding["content"].(string)), &said); err != nil {
t.Fatal(err)
}
if said.Serves["bucket"] != want {
t.Errorf("the binding says the bucket is %q, want %q", said.Serves["bucket"], want)
}
// And what is the same for everybody is still the same for everybody.
if said.Serves["region"] != "eu-west" {
t.Errorf("the binding lost what the provider serves to all: %v", said.Serves)
}
given := storeGrants(t, out)
if len(given) != 1 {
t.Fatalf("the provider was told about %d consumer(s): %v", len(given), given)
}
if given[0].Derived["bucket"] != want {
t.Errorf("the provider was told the bucket is %v, and the consumer was told %q — "+
"the two ends disagree, which is the whole failure", given[0].Derived["bucket"], want)
}
// Only the per-consumer half. The region is the same for everyone and is already in the
// provider's own definition; repeating it here would be a copy to go stale.
if _, carried := given[0].Derived["region"]; carried {
t.Errorf("the provider was handed back what it already says for everyone: %v", given[0].Derived)
}
}
// Two consumers of one provider on one machine get two buckets, and neither gets the other's.
func TestTwoConsumersOfOneProviderGetTheirOwnDerivation(t *testing.T) {
r, err := Resolve(shelf(store(), files(), pics()),
[]string{"store", "files", "pics"}, reachable(), World{})
if err != nil {
t.Fatal(err)
}
out, err := r.Declaration(Rendering{Grants: []Grant{
{Provision: "s3-bucket", Consumer: "workstation", From: "files", Slug: "files",
Values: map[string]any{}, Sealed: "c2VhbGVk"},
{Provision: "s3-bucket", Consumer: "workstation", From: "pics", Slug: "pics",
Values: map[string]any{}, Sealed: "c2VhbGVk"},
}})
if err != nil {
t.Fatal(err)
}
forFiles := strings.ReplaceAll(ConsumerIdentity("workstation", IdentitySource("files", "files")), "_", "-")
forPics := strings.ReplaceAll(ConsumerIdentity("workstation", IdentitySource("pics", "pics")), "_", "-")
if forFiles == forPics {
t.Fatal("the two consumers were given the same identity; this test proves nothing")
}
if got := fileNamed(out, "files.env")["content"].(string); !strings.Contains(got, "BUCKET="+forFiles+"\n") {
t.Errorf("files was not given its own bucket:\n%s", got)
}
if got := fileNamed(out, "pics.env")["content"].(string); !strings.Contains(got, "BUCKET="+forPics+"\n") {
t.Errorf("pics was not given its own bucket:\n%s", got)
}
var buckets []any
for _, g := range storeGrants(t, out) {
buckets = append(buckets, g.Derived["bucket"])
}
if len(buckets) != 2 || buckets[0] == buckets[1] {
t.Errorf("the provider was told %v; it must be told one bucket per consumer", buckets)
}
}
// An operator may still set what the provider serves, and the mesh still derives the rest: the
// setting is laid on first, then the consumer's half is filled.
func TestASettingComposesWithADerivedValue(t *testing.T) {
r, err := Resolve(shelf(store(), files()), []string{"store", "files"}, reachable(), World{})
if err != nil {
t.Fatal(err)
}
out, err := r.Declaration(Rendering{
Settings: SettingsBy{"store": {{From: "the operator",
Values: map[string]any{"bucket": "team-${consumer:as:dns}"}}}},
Grants: []Grant{{Provision: "s3-bucket", Consumer: "workstation", From: "files", Slug: "files",
Values: map[string]any{}, Sealed: "c2VhbGVk"}},
})
if err != nil {
t.Fatal(err)
}
want := "team-" + strings.ReplaceAll(ConsumerIdentity("workstation", IdentitySource("files", "files")), "_", "-")
if got := fileNamed(out, "files.env")["content"].(string); !strings.Contains(got, "BUCKET="+want+"\n") {
t.Errorf("the operator's prefix did not survive the derivation:\n%s\nwant BUCKET=%s", got, want)
}
if given := storeGrants(t, out); given[0].Derived["bucket"] != want {
t.Errorf("the provider was told %v, the consumer %q", given[0].Derived["bucket"], want)
}
}
// A fact or an alphabet the mesh does not have is refused where the definition is, not where a
// consumer happens to be resolved — and the refusal says what may be said instead.
func TestAServedValueNamingSomethingTheMeshDoesNotHaveIsRefused(t *testing.T) {
for _, c := range []struct{ value, says string }{
{"${consumer:node}", "as"},
{"${consumer:as:punycode}", "dns"},
} {
m := store()
m.Serves["s3-bucket"]["bucket"] = c.value
raw, err := json.Marshal(m)
if err != nil {
t.Fatal(err)
}
_, err = ParseManifest(raw)
if err == nil {
t.Fatalf("%s was accepted", c.value)
}
if !strings.Contains(err.Error(), c.value) {
t.Errorf("the refusal of %s does not quote it: %v", c.value, err)
}
if !strings.Contains(err.Error(), c.says) {
t.Errorf("the refusal of %s does not say what may be said (%q): %v", c.value, c.says, err)
}
}
}
// `dns` is checked against an identity the mesh actually mints, not an invented string.
func TestTheDNSAlphabetIsTheMintedIdentityWithItsSeparatorRewritten(t *testing.T) {
as := ConsumerIdentity("anchor", IdentitySource("ncloud", "nextcloud"))
if err := CheckIdentity("anchor", IdentitySource("ncloud", "nextcloud")); err != nil {
t.Fatalf("the mesh would not mint this identity at all: %v", err)
}
label := asDNSLabel(as)
if strings.Contains(label, "_") {
t.Errorf("%q is not a DNS label", label)
}
if strings.ReplaceAll(label, "-", "_") != as {
t.Errorf("%q is not %q with its separator rewritten", label, as)
}
}
// The check that would have caught the one wrong instance: a consumer that writes the derived
// value into its own definition instead of asking for it is refused, whether it transcribed the
// right answer or a predecessor's.
func TestAConsumerThatTranscribesWhatItsProviderDerivesIsRefused(t *testing.T) {
as := ConsumerIdentity("workstation", IdentitySource("files", "files"))
transcribed := strings.ReplaceAll(as, "_", "-")
m := files()
m.Resources = []map[string]any{{
"id": "env", "type": "file", "path": "/var/lib/files/env", "mode": "0600",
// Exactly what the provider will create — correct today, and a copy of a rule that is
// not this module's.
"content": "BUCKET=" + transcribed + "\n",
}}
r, err := Resolve(shelf(store(), m), []string{"store", "files"}, reachable(), World{})
if err != nil {
t.Fatal(err)
}
_, err = r.Declaration(Rendering{Grants: []Grant{{
Provision: "s3-bucket", Consumer: "workstation", From: "files", Slug: "files",
Values: map[string]any{}, Sealed: "c2VhbGVk",
}}})
if err == nil {
t.Fatal("a definition holding its own copy of the provider's naming rule was accepted")
}
if !strings.Contains(err.Error(), "${bound:s3-bucket:bucket}") {
t.Errorf("the refusal does not say what to write instead: %v", err)
}
// And a constant the provider serves to everyone is not a transcription: repeating it is
// redundant, not wrong, and refusing it would be the mesh policing style.
m.Resources = []map[string]any{{
"id": "env", "type": "file", "path": "/var/lib/files/env", "mode": "0600",
"content": "REGION=eu-west\n",
}}
r, err = Resolve(shelf(store(), m), []string{"store", "files"}, reachable(), World{})
if err != nil {
t.Fatal(err)
}
if _, err := r.Declaration(Rendering{Grants: []Grant{{
Provision: "s3-bucket", Consumer: "workstation", From: "files", Slug: "files",
Values: map[string]any{}, Sealed: "c2VhbGVk",
}}}); err != nil {
t.Errorf("a value the provider serves to everyone was judged a transcription: %v", err)
}
}
func storeGrants(t *testing.T, out []map[string]any) []Contribution {
t.Helper()
for _, r := range out {
if r["path"] != "/var/lib/store/grants/mesh.json" {
continue
}
var parsed struct {
Given []Contribution `json:"given"`
}
if err := json.Unmarshal([]byte(r["content"].(string)), &parsed); err != nil {
t.Fatal(err)
}
return parsed.Given
}
t.Fatalf("the provider was given no contributions file: %v", out)
return nil
}
// A consumer that keeps SEVERAL holders of one provision is refused, rather than told one thing
// while its provider is told another.
//
// **This is issue 124's own failure, one case to the side.** The mesh gives each holder its own
// login — `mesh_node_mod_<local>` (ADR 0094) — and the provider derives from the login, so it
// would make one resource per holder. The consumer's side has no such dimension: there is one
// binding file per provision and one `${bound:<provision>:<key>}`, both derived from the
// un-suffixed identity. So the provider would create `…-mod-cold` and the consumer would be
// configured against `…-mod`: it would authenticate successfully and be refused on every object,
// which is exactly the fault this whole record exists to end.
//
// Refused, loudly, at the one place that can see both halves. Lifting it means giving the
// consumer's side a local dimension, which is a decision and not an omission.
func TestAConsumerWithSeveralHoldersOfADerivingProviderIsRefused(t *testing.T) {
m := files()
// Two holders of the one provision, the shape ADR 0094 gives a module that keeps several.
m.Secrets = nil
m.SecretsMany = map[string]map[string]string{"s3-bucket": {
"hot": "/var/lib/files/hot.secret",
"cold": "/var/lib/files/cold.secret",
}}
m.Resources = []map[string]any{{
"id": "env", "type": "file", "path": "/var/lib/files/env", "mode": "0600",
"content": "BUCKET=${bound:s3-bucket:bucket}\n",
}}
r, err := Resolve(shelf(store(), m), []string{"store", "files"}, reachable(), World{})
if err != nil {
t.Fatal(err)
}
_, err = r.Declaration(Rendering{Grants: []Grant{
{Provision: "s3-bucket", Consumer: "workstation", From: "files", Slug: "files",
Local: "hot", Values: map[string]any{}, Sealed: "c2VhbGVk"},
{Provision: "s3-bucket", Consumer: "workstation", From: "files", Slug: "files",
Local: "cold", Values: map[string]any{}, Sealed: "c2VhbGVk"},
}})
if err == nil {
t.Fatal("a consumer with several holders of a deriving provider was accepted; " +
"its two ends would have disagreed in silence")
}
for _, want := range []string{"files", "s3-bucket", "bucket"} {
if !strings.Contains(err.Error(), want) {
t.Errorf("the refusal does not name %q: %v", want, err)
}
}
}
+17 -23
View File
@@ -1,7 +1,6 @@
package catalogue package catalogue
import ( import (
"encoding/json"
"fmt" "fmt"
"os" "os"
"reflect" "reflect"
@@ -171,7 +170,7 @@ func TestTheForgeHoldsTheNpmAndGitSeats(t *testing.T) {
// **And the forge's own address follows it**, composed from the manifest in the catalogue beside // **And the forge's own address follows it**, composed from the manifest in the catalogue beside
// this checkout (novox/hq 04-ISSUES/088). // this checkout (novox/hq 04-ISSUES/088).
// //
// The forge is reached a third way that neither test above covers: by its own code, over the // The forge is reached a third way that neither test above covers: by its own sidecar, over the
// machine's loopback, told where to go in its environment. The `2999:3000` mapping that lets the // machine's loopback, told where to go in its environment. The `2999:3000` mapping that lets the
// forge go on binding 3000 does nothing for a caller dialling the machine — so a literal there is // forge go on binding 3000 does nothing for a caller dialling the machine — so a literal there is
// wrong on every node whose assignment differs, and wrong for a second reason on a node given the // wrong on every node whose assignment differs, and wrong for a second reason on a node given the
@@ -179,13 +178,13 @@ func TestTheForgeHoldsTheNpmAndGitSeats(t *testing.T) {
// in an `env` at all is a declaration, not a manifest. // in an `env` at all is a declaration, not a manifest.
func TestTheForgesOwnAddressFollowsThePortTheNodeGaveIt(t *testing.T) { func TestTheForgesOwnAddressFollowsThePortTheNodeGaveIt(t *testing.T) {
forge, err := catalogueManifest(t, "gitea").Resolve([]Built{{ forge, err := catalogueManifest(t, "gitea").Resolve([]Built{{
Name: "code", Kind: ArtifactBundle, Name: "runtime", Kind: ArtifactImage,
Reference: ArtifactStoreScheme + "gitea/code/blobs/" + bundleDigest, Digest: bundleDigest, Reference: "registry.example/gitea-runtime@sha256:" + strings.Repeat("a", 64),
}}) }})
if err != nil { if err != nil {
t.Fatalf("the forge's manifest does not resolve against its own build: %v", err) t.Fatalf("the forge's manifest does not resolve against its own build: %v", err)
} }
r := Resolution{Node: "anchor", Modules: []Manifest{forge, theRuntime(t)}, Needs: []Needed{ r := Resolution{Node: "anchor", Modules: []Manifest{forge}, Needs: []Needed{
{Name: "postgres-database", For: "gitea", From: "anchor", At: "127.0.0.1", {Name: "postgres-database", For: "gitea", From: "anchor", At: "127.0.0.1",
Serves: map[string]any{"port": float64(5432)}, Sealed: "sealed-db"}, Serves: map[string]any{"port": float64(5432)}, Sealed: "sealed-db"},
{Name: "route", For: "gitea", From: "anchor"}, {Name: "route", For: "gitea", From: "anchor"},
@@ -195,8 +194,8 @@ func TestTheForgesOwnAddressFollowsThePortTheNodeGaveIt(t *testing.T) {
// The number this node was given for the forge — the one the machine it is about to run on // The number this node was given for the forge — the one the machine it is about to run on
// already publishes. // already publishes.
out, err := r.Declaration(Rendering{ArtifactStore: "anchor.internal:5101", out, err := r.Declaration(Rendering{
Needed: map[string]map[string]string{RuntimeModule: {"broker": "sealed-broker"}}, Needed: map[string]map[string]string{"gitea": {"broker": "sealed-broker"}},
Given: map[string]map[int]int{"gitea": {3000: 2999}}, Given: map[string]map[int]int{"gitea": {3000: 2999}},
}) })
if err != nil { if err != nil {
@@ -211,19 +210,14 @@ func TestTheForgesOwnAddressFollowsThePortTheNodeGaveIt(t *testing.T) {
if published := fmt.Sprint(server["ports"]); !strings.Contains(published, "2999:3000") { if published := fmt.Sprint(server["ports"]); !strings.Contains(published, "2999:3000") {
t.Fatalf("the forge is not published on the port this node gave it: %v", server["ports"]) t.Fatalf("the forge is not published on the port this node gave it: %v", server["ports"])
} }
// The forge's own code runs in the node's runtime (novox/hq ADR 0198), given its words there. runtime := fileNamed(out, "gitea.runtime")
runtime := fileNamed(out, RuntimeModule+"."+RuntimeProcessID())
if runtime == nil { if runtime == nil {
t.Fatalf("the node's runtime is not in the declaration: %v", ids(out)) t.Fatalf("the forge's sidecar is not in the declaration: %v", out)
} }
env, _ := runtime["env"].(map[string]string) env, _ := runtime["env"].(map[string]any)
var given map[string]map[string]string if env["MESH_GITEA_URL"] != "http://127.0.0.1:2999" {
if err := json.Unmarshal([]byte(env[RuntimeToolEnv]), &given); err != nil { t.Fatalf("the forge's sidecar dials %v while the machine publishes the forge on 2999 — "+
t.Fatalf("the runtime's %s is not JSON: %q", RuntimeToolEnv, env[RuntimeToolEnv]) "whatever reads it dials a dead port", env["MESH_GITEA_URL"])
}
if given["gitea"]["MESH_GITEA_URL"] != "http://127.0.0.1:2999" {
t.Fatalf("the forge's code dials %v while the machine publishes the forge on 2999 — "+
"whatever reads it dials a dead port", given["gitea"]["MESH_GITEA_URL"])
} }
} }
@@ -235,13 +229,13 @@ func declaredGiteaSsh(t *testing.T, given map[int]int) map[string]any {
t.Helper() t.Helper()
forge := catalogueManifest(t, "gitea") forge := catalogueManifest(t, "gitea")
resolved, err := forge.Resolve([]Built{{ resolved, err := forge.Resolve([]Built{{
Name: "code", Kind: ArtifactBundle, Name: "runtime", Kind: ArtifactImage,
Reference: ArtifactStoreScheme + "gitea/code/blobs/" + bundleDigest, Digest: bundleDigest, Reference: "registry.example/gitea-runtime@sha256:" + strings.Repeat("a", 64),
}}) }})
if err != nil { if err != nil {
t.Fatalf("the forge's manifest does not resolve against its own build: %v", err) t.Fatalf("the forge's manifest does not resolve against its own build: %v", err)
} }
r := Resolution{Node: "anchor", Modules: []Manifest{resolved, theRuntime(t)}, Needs: []Needed{ r := Resolution{Node: "anchor", Modules: []Manifest{resolved}, Needs: []Needed{
{Name: "postgres-database", For: "gitea", From: "anchor", At: "127.0.0.1", {Name: "postgres-database", For: "gitea", From: "anchor", At: "127.0.0.1",
Serves: map[string]any{"port": float64(5432)}, Sealed: "sealed-db"}, Serves: map[string]any{"port": float64(5432)}, Sealed: "sealed-db"},
{Name: "route", For: "gitea", From: "anchor"}, {Name: "route", For: "gitea", From: "anchor"},
@@ -252,8 +246,8 @@ func declaredGiteaSsh(t *testing.T, given map[int]int) map[string]any {
for k, v := range given { for k, v := range given {
givenPorts[k] = v givenPorts[k] = v
} }
out, err := r.Declaration(Rendering{ArtifactStore: "anchor.internal:5101", out, err := r.Declaration(Rendering{
Needed: map[string]map[string]string{RuntimeModule: {"broker": "sealed-broker"}}, Needed: map[string]map[string]string{"gitea": {"broker": "sealed-broker"}},
Ports: map[string]map[int]int{"gitea": givenPorts}, Ports: map[string]map[int]int{"gitea": givenPorts},
Given: map[string]map[int]int{"gitea": given}, Given: map[string]map[int]int{"gitea": given},
}) })
-29
View File
@@ -1,29 +0,0 @@
package catalogue
import (
"os"
"regexp"
"testing"
)
// novox/hq issue 223: genesis raises the controller as a container built from this repository's own
// Dockerfile, with no build arguments — the manifest no longer builds an image, so nothing passes a
// base in. The Dockerfile's own default must therefore be a Go that builds this module, pinned by
// digest, and the replacement the manifest's process names must be the container genesis raises.
func TestGenesisCanBuildTheControllersImageAsItStands(t *testing.T) {
raw, err := os.ReadFile("../../Dockerfile")
if err != nil {
t.Fatal(err)
}
if !regexp.MustCompile(`(?m)^ARG GO_BASE=golang@sha256:[0-9a-f]{64}$`).Match(raw) {
t.Fatal("the Dockerfile's default Go base is not pinned by digest; genesis builds it with no arguments")
}
makefile, err := os.ReadFile("../../Makefile")
if err != nil {
t.Fatal(err)
}
pin := regexp.MustCompile(`golang@sha256:[0-9a-f]{64}`)
if string(pin.Find(raw)) != string(pin.Find(makefile)) {
t.Errorf("the Dockerfile and the Makefile build on different Go: %s, %s", pin.Find(raw), pin.Find(makefile))
}
}
+6 -143
View File
@@ -325,15 +325,6 @@ type Manifest struct {
// person's account (design 25 §7) already had the same shape. // person's account (design 25 §7) already had the same shape.
Invokes []string `json:"invokes,omitempty"` Invokes []string `json:"invokes,omitempty"`
// State is the current state this module keeps on the bus, by local name: each a key-value
// bucket the controller creates, which every instance of the module writes and reads
// (novox/hq ADR 0201). Not history — that is an event — and never a secret, sealed or not.
State []StateDeclaration `json:"state,omitempty"`
// Reads are other modules' state this module reads and watches, each `<module>.<name>`
// (novox/hq ADR 0201). Read-only: only the owner's instances write.
Reads []string `json:"reads,omitempty"`
// Capabilities the machine must have. A different field from Requires because the remedy // Capabilities the machine must have. A different field from Requires because the remedy
// differs: a missing module can be assigned, and a missing capability means the wrong // differs: a missing module can be assigned, and a missing capability means the wrong
// machine. // machine.
@@ -549,6 +540,10 @@ type Manifest struct {
// `restart-on` names to restart when the roster changes. // `restart-on` names to restart when the roster changes.
Facts map[string]RosterFile `json:"facts,omitempty"` Facts map[string]RosterFile `json:"facts,omitempty"`
// Zone is the zone of names this module answers itself, and the listen that answers it (novox/hq
// ADR 0199). The mesh's resolver forwards the zone to it; nothing here names an address.
Zone *Zone `json:"zone,omitempty"`
// Certificate is where this module wants a certificate for its machine's name inside the // Certificate is where this module wants a certificate for its machine's name inside the
// mesh, and where the key that goes with it can be found. // mesh, and where the key that goes with it can be found.
// //
@@ -766,11 +761,6 @@ type Artifact struct {
// list twice. A module declaring no tools has nothing the runtime loads, whatever it compiles. // list twice. A module declaring no tools has nothing the runtime loads, whatever it compiles.
Loads []string `json:"loads,omitempty"` Loads []string `json:"loads,omitempty"`
// External are packages a TypeScript bundle keeps as imports rather than inlining — a native
// addon, a package that reads its own files — and so carries the toolchain's node_modules for
// (novox/hq ADR 0193). Absent for nearly every bundle, which is then one file per entrypoint.
External []string `json:"external,omitempty"`
// Env is what a tools bundle is given on a machine (novox/hq ADR 0192): words and their values, // Env is what a tools bundle is given on a machine (novox/hq ADR 0192): words and their values,
// paths and constants composed with ${dir:…} and ${port:…} exactly as a container's environment // paths and constants composed with ${dir:…} and ${port:…} exactly as a container's environment
// is, never a secret's content. The node's runtime hands it to this bundle and to no other. // is, never a secret's content. The node's runtime hands it to this bundle and to no other.
@@ -1325,8 +1315,6 @@ func ParseManifest(raw []byte) (Manifest, error) {
// module whose event names are wrong installs, starts, connects and reacts to nothing, with // module whose event names are wrong installs, starts, connects and reacts to nothing, with
// every log line saying it is fine (novox/hq 04-ISSUES/127). // every log line saying it is fine (novox/hq 04-ISSUES/127).
problems = append(problems, EventProblems(m)...) problems = append(problems, EventProblems(m)...)
// And what it may call its state, and whose it may read (state.go, novox/hq ADR 0201).
problems = append(problems, StateProblems(m)...)
wellFormed := true wellFormed := true
for _, c := range m.Claims { for _, c := range m.Claims {
if !name.MatchString(c.Name) { if !name.MatchString(c.Name) {
@@ -1439,10 +1427,6 @@ func ParseManifest(raw []byte) (Manifest, error) {
"%s serves %q to whoever requires it, and does not provide it", m.Module, to)) "%s serves %q to whoever requires it, and does not provide it", m.Module, to))
} }
} }
// A served value may be derived for the consumer it is served to (novox/hq ADR 0202). Read
// here, where the definition is, rather than when somebody first requires it: a rule that
// would be refused at the first consumer is wrong from the moment it is written.
problems = append(problems, CheckServes(m)...)
for to, where := range m.Binds { for to, where := range m.Binds {
if !placedOrAbsolute(where) { if !placedOrAbsolute(where) {
problems = append(problems, fmt.Sprintf( problems = append(problems, fmt.Sprintf(
@@ -1530,53 +1514,6 @@ func ParseManifest(raw []byte) (Manifest, error) {
"program that reads what the mesh delivered and reconciles", "program that reads what the mesh delivered and reconciles",
m.Module, r["id"])) m.Module, r["id"]))
} }
// **What a process replaces is something the module no longer declares** (novox/hq issue 213).
// The host keeps it running until the process is, then removes it: so it is named by the id the
// module used to give it, it is never a resource the module still declares — that would be
// applied and removed by one declaration — and only a process that stays up has anything to
// hand over to. Said here, near the author, as the host would refuse it far away.
ids := map[string]bool{}
for _, r := range m.Resources {
ids[fmt.Sprint(r["id"])] = true
}
for _, r := range m.Resources {
raw, present := r["replaces"]
if !present {
continue
}
if fmt.Sprint(r["type"]) != "process" {
problems = append(problems, fmt.Sprintf(
"%s: %v says what it replaces, and only a process does", m.Module, r["id"]))
continue
}
if once, _ := r["run-once"].(bool); once || r["schedule"] != nil {
problems = append(problems, fmt.Sprintf(
"%s: %v replaces something and runs once or on a schedule — only a process that stays "+
"up is there a moment later to hand over to", m.Module, r["id"]))
}
list, ok := raw.([]any)
if !ok {
problems = append(problems, fmt.Sprintf(
"%s: %v replaces %v; replaces is a list of the ids this module no longer declares",
m.Module, r["id"], raw))
continue
}
for _, item := range list {
id, ok := item.(string)
switch {
case !ok || strings.TrimSpace(id) == "":
problems = append(problems, fmt.Sprintf(
"%s: %v replaces %v, which is not an id", m.Module, r["id"], item))
case strings.Contains(id, "."):
problems = append(problems, fmt.Sprintf(
"%s: %v replaces %q; a process replaces only a resource of its own module, named "+
"by its own id", m.Module, r["id"], id))
case ids[id]:
problems = append(problems, fmt.Sprintf(
"%s: %v replaces %q, which this module still declares", m.Module, r["id"], id))
}
}
}
// **A module that prepares its state must have code the mesh can run** (novox/hq ADR 0135). The // **A module that prepares its state must have code the mesh can run** (novox/hq ADR 0135). The
// preparation is the module's own program in its preparation mode, so it is derived from the // preparation is the module's own program in its preparation mode, so it is derived from the
// resource that runs that program — and a module declaring none has asked for something the mesh // resource that runs that program — and a module declaring none has asked for something the mesh
@@ -1584,7 +1521,7 @@ func ParseManifest(raw []byte) (Manifest, error) {
// quietly prepares nothing. // quietly prepares nothing.
if m.Prepares && preparationTarget(m) == "" { if m.Prepares && preparationTarget(m) == "" {
problems = append(problems, fmt.Sprintf( problems = append(problems, fmt.Sprintf(
"%s says it prepares its state, and declares no container or process running an artifact it built — "+ "%s says it prepares its state, and declares no container running an artifact it built — "+
"the preparation is this module's own program, so there has to be one for the mesh to "+ "the preparation is this module's own program, so there has to be one for the mesh to "+
"run it in", m.Module)) "run it in", m.Module))
} }
@@ -1637,13 +1574,6 @@ func ParseManifest(raw []byte) (Manifest, error) {
} }
} }
} }
// **A scheduled step may hold this module's own containers still while it runs**
// (novox/hq ADR 0189). What the host judges is the declaration it receives — whether each
// id is a container placed on that machine; what belongs here is what only the definition
// shows: that the ids are this module's, that they are containers, and that the step is
// scheduled. A module naming a neighbour's container would be a module that can stop the
// mesh, and the manifest is where that is visible.
problems = append(problems, whileStoppedProblems(m, r, hasSchedule(r))...)
} }
for name, own := range m.OwnSecrets { for name, own := range m.OwnSecrets {
if !placedOrAbsolute(own.Path) { if !placedOrAbsolute(own.Path) {
@@ -1816,6 +1746,7 @@ func ParseManifest(raw []byte) (Manifest, error) {
} }
} }
problems = append(problems, zoneProblems(m)...)
if len(problems) > 0 { if len(problems) > 0 {
sort.Strings(problems) sort.Strings(problems)
return Manifest{}, fmt.Errorf("this manifest cannot be used:\n - %s", return Manifest{}, fmt.Errorf("this manifest cannot be used:\n - %s",
@@ -2175,71 +2106,3 @@ func (o OwnSecrets) Paths() map[string]string {
// InstancesInterchangeable is the one value of a definition's `instances`: the module is the same // InstancesInterchangeable is the one value of a definition's `instances`: the module is the same
// on every machine, so any instance may answer for the module. // on every machine, so any instance may answer for the module.
const InstancesInterchangeable = "interchangeable" const InstancesInterchangeable = "interchangeable"
// WhileStopped is the resource key naming the containers a scheduled step holds still while it
// runs (novox/hq ADR 0189). Carried to the host unchanged, like `schedule`.
const WhileStopped = "while-stopped"
// hasSchedule is whether a resource declares a cadence, as a string.
func hasSchedule(r map[string]any) bool {
s, _ := r["schedule"].(string)
return s != ""
}
// whileStoppedProblems judges one container's maintenance window against its own definition
// (novox/hq ADR 0189).
//
// Three things the manifest is the only place to see: that the step is scheduled (a one-time
// offline job says *before* rather than *instead of* — at apply the host already has a window,
// because the declaration is applied in order and a run-once step gates what follows); that every
// id it names is **this module's own** container; and that it does not name itself.
//
// The host checks the fourth — that the container is actually placed on that machine — because
// that is a fact about the declaration and not about the definition.
func whileStoppedProblems(m Manifest, r map[string]any, scheduled bool) []string {
raw, present := r[WhileStopped]
if !present {
return nil
}
ids, ok := raw.([]any)
if !ok {
return []string{fmt.Sprintf(
"%s declares %s on %v as a %T; it is a list of this module's container ids",
m.Module, WhileStopped, r["id"], raw)}
}
var problems []string
if len(ids) > 0 && !scheduled {
problems = append(problems, fmt.Sprintf(
"%s declares %s on %v, which has no schedule. A maintenance window is for a recurring "+
"step: at apply the mesh already has one, because a run-once step gates what is "+
"declared after it (novox/hq ADR 0189)", m.Module, WhileStopped, r["id"]))
}
containers := map[string]bool{}
for _, own := range m.Resources {
if fmt.Sprint(own["type"]) == "container" {
containers[fmt.Sprint(own["id"])] = true
}
}
for _, each := range ids {
id, ok := each.(string)
if !ok {
problems = append(problems, fmt.Sprintf(
"%s declares %s on %v naming a %T; each entry is a container's id",
m.Module, WhileStopped, r["id"], each))
continue
}
if id == fmt.Sprint(r["id"]) {
problems = append(problems, fmt.Sprintf(
"%s declares %s on %v naming itself", m.Module, WhileStopped, r["id"]))
continue
}
if !containers[id] {
problems = append(problems, fmt.Sprintf(
"%s declares %s on %v naming %q, which is not a container this module declares. "+
"A step may hold still its own module's containers and nobody else's — one "+
"that could quiesce a neighbour could stop the mesh",
m.Module, WhileStopped, r["id"], id))
}
}
return problems
}
+5 -10
View File
@@ -31,7 +31,7 @@ import (
// //
// So a module asks. `${port:8080}` is "the machine-side port you gave me for the 8080 I said I // So a module asks. `${port:8080}` is "the machine-side port you gave me for the 8080 I said I
// listen on", and the module writes that where it would otherwise have written a literal — in a // listen on", and the module writes that where it would otherwise have written a literal — in a
// file's content, or in a value of a container's or a process's `env`. // file's content, or in a value of a container's `env`.
// //
// **The environment is filled by the control plane, exactly as a bound value is.** A port is not // **The environment is filled by the control plane, exactly as a bound value is.** A port is not
// secret — the mesh holds it in the clear — so there is nothing for the host to be the only // secret — the mesh holds it in the clear — so there is nothing for the host to be the only
@@ -64,12 +64,7 @@ func portsUsed(content string) []int {
} }
// portInto replaces a resource's ${port:…} placeholders with what this machine assigned — in a // portInto replaces a resource's ${port:…} placeholders with what this machine assigned — in a
// file's content, and in a value of a container's or a process's environment. // file's content, and in a value of a container's environment.
//
// **A process's environment is a container's** (novox/hq to-be 38 WP4c). A module's code moving out
// of its container becomes a process on the machine and still has to be told what the container
// was told; filled for one kind and not the other, the literal reached the process and was read as
// a port, and the modules that moved first wrote their run-once steps a 0600 env file instead.
// //
// A port the module did not say it listens on is refused, for the same reason a binding's unknown // A port the module did not say it listens on is refused, for the same reason a binding's unknown
// key is: the module is asking about something it never declared, and the answer would be a guess. // key is: the module is asking about something it never declared, and the answer would be a guess.
@@ -89,7 +84,7 @@ func portInto(resource map[string]any, module string, listens []Listening, with
} }
resource["content"] = filled resource["content"] = filled
case "container", "process": case "container":
env, ok := resource["env"].(map[string]any) env, ok := resource["env"].(map[string]any)
if !ok { if !ok {
return nil return nil
@@ -111,8 +106,8 @@ func portInto(resource map[string]any, module string, listens []Listening, with
continue continue
} }
value, err := portsFilledInto(written, value, err := portsFilledInto(written,
fmt.Sprintf("%s's %s %s sets %s to something that", fmt.Sprintf("%s's container %s sets %s to something that",
module, resource["type"], resource["name"], key), module, listens, with) module, resource["name"], key), module, listens, with)
if err != nil { if err != nil {
return err return err
} }
-80
View File
@@ -1,80 +0,0 @@
package catalogue
import (
"strings"
"testing"
)
// **A process's environment is composed as a container's is** (novox/hq to-be 38 WP4c).
//
// A module's code moving out of its container becomes a process on the machine, and what its
// container's environment asked for — the port this machine gave the module, the place it put the
// module's directory — it still has to be told. Filled for a container and not for a process, the
// literal `${port:8080}` reached the process as its environment and was read as a port; the modules
// that moved first wrote their run-once steps an env file instead.
func processModule(env map[string]any) Manifest {
return Manifest{
Module: "showcase",
Listens: []Listening{{Port: 8080, From: FromMesh}},
Resources: []map[string]any{
{"id": "data", "type": "directory", "mode": "0700"},
{"id": "setup", "type": "process", "name": "showcase-setup", "run-once": true,
"run": []any{"/usr/bin/showcase", "setup"}, "env": env},
},
}
}
func TestAProcessIsToldItsPortAndItsPlaceInItsEnvironment(t *testing.T) {
env := map[string]any{
"SHOWCASE_URL": "http://127.0.0.1:${port:8080}",
"SHOWCASE_DATA": "${dir:data}/objects",
"SHOWCASE_DB": "127.0.0.1:${seat:mesh-store:5432}",
"GREETING": "hello",
}
out, err := Resolution{Node: "anchor", Modules: []Manifest{processModule(env)}}.Declaration(Rendering{
Ports: map[string]map[int]int{"showcase": {8080: 21000}},
Seats: map[string]map[int]int{"mesh-store": {5432: 6852}},
})
if err != nil {
t.Fatalf("a process asking for its port and its place does not compose: %v", err)
}
setup := fileNamed(out, "showcase.setup")
if setup == nil {
t.Fatalf("the process is not in the declaration: %v", out)
}
got, _ := setup["env"].(map[string]any)
for key, want := range map[string]string{
"SHOWCASE_URL": "http://127.0.0.1:21000",
"SHOWCASE_DATA": "/var/lib/showcase/data/objects",
"SHOWCASE_DB": "127.0.0.1:6852",
"GREETING": "hello",
} {
if got[key] != want {
t.Errorf("the process is told %s=%v, want %q", key, got[key], want)
}
}
if env["SHOWCASE_URL"] != "http://127.0.0.1:${port:8080}" {
t.Fatalf("composing for one machine edited the module's own manifest: %v", env)
}
}
// An unknown reference in a process's environment is refused as a container's is, naming the
// process and the variable — left alone, it would reach the machine as a literal.
func TestAProcessAskingAboutAnUndeclaredPortIsRefused(t *testing.T) {
env := map[string]any{"SHOWCASE_URL": "http://127.0.0.1:${port:9999}"}
_, err := Resolution{Node: "anchor", Modules: []Manifest{processModule(env)}}.Declaration(Rendering{})
if err == nil {
t.Fatal("a process was told a port its module never said it listens on")
}
for _, said := range []string{"showcase-setup", "SHOWCASE_URL", "${port:9999}", "8080"} {
if !strings.Contains(err.Error(), said) {
t.Errorf("the refusal does not say %q: %v", said, err)
}
}
env = map[string]any{"SHOWCASE_DATA": "${dir:date}/objects"}
if _, err := (Resolution{Node: "anchor", Modules: []Manifest{processModule(env)}}).Declaration(Rendering{}); err == nil ||
!strings.Contains(err.Error(), "${dir:date}") {
t.Fatalf("a process naming no directory of its module was not refused: %v", err)
}
}
+44 -23
View File
@@ -48,9 +48,12 @@ func TestTheResolverForwardsToFixedUpstreamsAndNeverReadsResolvConf(t *testing.T
} }
for _, want := range []string{ for _, want := range []string{
"\nno-resolv\n", "\nserver=1.1.1.1\n", "\nserver=8.8.8.8\n", "\nno-resolv\n", "\nserver=1.1.1.1\n", "\nserver=8.8.8.8\n",
// Loopback is the mesh-wide setting's default; a machine answering its own LAN adds its // The private address and loopback, never a LAN's (novox/hq ADR 0194): a device that is not a
// address there (novox/hq issue 198). // member cannot reach what the mesh's names point at.
"\nlisten-address=${setting:listen-addresses}\n", "\nlisten-address=${machine:address}\n", "\nbind-dynamic\n", "\nlisten-address=127.0.0.1\n", "\nlisten-address=${machine:address}\n", "\nbind-dynamic\n",
// No hosts file and no operator's files: the mesh's resolver answers every node (ADR 0199).
"\nno-hosts\n",
"\nconf-file=" + m.Facts["zones"].Path + "\n",
"\ndomain-needed\n", "\nbogus-priv\n", "\ndomain-needed\n", "\nbogus-priv\n",
"\nconf-file=" + m.Facts["node-zones"].Path + "\n", "\nconf-file=" + m.Facts["node-zones"].Path + "\n",
} { } {
@@ -73,7 +76,15 @@ func TestTheResolverForwardsToFixedUpstreamsAndNeverReadsResolvConf(t *testing.T
t.Errorf("the resolver listens on %s", taken) t.Errorf("the resolver listens on %s", taken)
} }
} }
// And the file that decides what the machine asks names it there, alone. // Never a directory or a file the operator keeps: a line written for one machine's programs would
// become an answer for every node (ADR 0199).
for _, never := range []string{"conf-dir=", "addn-hosts=", "listen-address=${setting:"} {
if strings.Contains(config, never) {
t.Errorf("the mesh's resolver still reads or listens on %q", never)
}
}
// And the file that decides what the machine asks names the mesh's resolver first, by address,
// and a public one second, asked only when the first is silent (ADR 0196).
var resolv string var resolv string
for _, r := range catalogueManifest(t, "resolv-conf").Resources { for _, r := range catalogueManifest(t, "resolv-conf").Resources {
if r["path"] == "/etc/resolv.conf" { if r["path"] == "/etc/resolv.conf" {
@@ -86,13 +97,16 @@ func TestTheResolverForwardsToFixedUpstreamsAndNeverReadsResolvConf(t *testing.T
nameservers = append(nameservers, strings.TrimPrefix(line, "nameserver ")) nameservers = append(nameservers, strings.TrimPrefix(line, "nameserver "))
} }
} }
if len(nameservers) != 1 || nameservers[0] != "127.0.0.1" { if len(nameservers) != 2 || nameservers[0] != "${bound:wildcard-resolution:address}" || nameservers[1] != "1.1.1.1" {
t.Errorf("resolv.conf names %v; the predecessor's names the mesh's resolver alone at 127.0.0.1", nameservers) t.Errorf("resolv.conf names %v; the mesh's resolver by address first, a public one second", nameservers)
} }
// The split-DNS alternative points at the same address, or a machine that keeps if !strings.Contains(resolv, "\noptions timeout:1 attempts:1") {
t.Errorf("the fallback is not reached after one short attempt:\n%s", resolv)
}
// The split-DNS alternative points at the same resolver, or a machine that keeps
// systemd-resolved in charge would route the mesh's suffix to nothing. // systemd-resolved in charge would route the mesh's suffix to nothing.
for _, r := range catalogueManifest(t, "resolved-split-dns").Resources { for _, r := range catalogueManifest(t, "resolved-split-dns").Resources {
if content, _ := r["content"].(string); content != "" && !strings.Contains(content, "DNS=127.0.0.1\n") { if content, _ := r["content"].(string); content != "" && !strings.Contains(content, "DNS=${bound:wildcard-resolution:address}\n") {
t.Errorf("resolved-split-dns does not point at the resolver's address:\n%s", content) t.Errorf("resolved-split-dns does not point at the resolver's address:\n%s", content)
} }
} }
@@ -100,7 +114,8 @@ func TestTheResolverForwardsToFixedUpstreamsAndNeverReadsResolvConf(t *testing.T
// The resolver and what points the machine at it compose on one machine, and what arrives is the // The resolver and what points the machine at it compose on one machine, and what arrives is the
// mesh's account of every machine as a wildcard, the suffix kept local, the daemon restarting on // mesh's account of every machine as a wildcard, the suffix kept local, the daemon restarting on
// that file, and the runtime pointed at this machine's own address. // that file, the machine pointed at the resolver by address, and the runtime given no resolver of
// its own but kept running across a restart (ADR 0196).
func TestTheResolverAndWhatAsksItComposeOnOneMachine(t *testing.T) { func TestTheResolverAndWhatAsksItComposeOnOneMachine(t *testing.T) {
got, err := Resolve(resolverShelf(t), []string{"dnsmasq", "resolv-conf"}, got, err := Resolve(resolverShelf(t), []string{"dnsmasq", "resolv-conf"},
Node{Name: "anchor", At: "anchor.internal"}, World{}) Node{Name: "anchor", At: "anchor.internal"}, World{})
@@ -115,6 +130,7 @@ func TestTheResolverAndWhatAsksItComposeOnOneMachine(t *testing.T) {
// issue 111) — the resolver's zones read only the second, and in this scenario the two // issue 111) — the resolver's zones read only the second, and in this scenario the two
// happen to be the same map, since nothing routed is part of it. // happen to be the same map, since nothing routed is part of it.
Names: twoMachines, Machines: twoMachines, Suffix: "internal", Names: twoMachines, Machines: twoMachines, Suffix: "internal",
Zones: []ZoneAt{{Zone: "incus", Address: "10.42.0.2", Port: 5353}},
Needed: map[string]map[string]string{"dnsmasq": {"broker": "sealed"}}, Needed: map[string]map[string]string{"dnsmasq": {"broker": "sealed"}},
Settings: SettingsBy{"dnsmasq": {{From: "the mesh", Values: map[string]any{"listen-addresses": "127.0.0.1"}}}}, Settings: SettingsBy{"dnsmasq": {{From: "the mesh", Values: map[string]any{"listen-addresses": "127.0.0.1"}}}},
}) })
@@ -144,24 +160,29 @@ func TestTheResolverAndWhatAsksItComposeOnOneMachine(t *testing.T) {
for _, id := range service["restart-on"].([]any) { for _, id := range service["restart-on"].([]any) {
reflects[id.(string)] = true reflects[id.(string)] = true
} }
if !reflects["dnsmasq.config"] || !reflects["dnsmasq.fact-node-zones"] { if !reflects["dnsmasq.config"] || !reflects["dnsmasq.fact-node-zones"] || !reflects["dnsmasq.fact-zones"] {
t.Errorf("the daemon does not restart on its configuration and the machines file both: %v", service["restart-on"]) t.Errorf("the daemon does not restart on its configuration, the machines and the zones: %v", service["restart-on"])
}
if z, _ := ids["dnsmasq.fact-zones"]["content"].(string); !strings.Contains(z, "server=/incus/10.42.0.2#5353\n") {
t.Errorf("the resolver was not told to forward the zone to its answerer:\n%s", z)
} }
// The runtime's own file, written into (novox/hq ADR 0102) with the keys this module states: // The runtime's own file, written into (novox/hq ADR 0102) with one key, by what decides how the
// where containers resolve, and that a restart keeps them running — because the runtime reads // machine resolves: a restart keeps every container running. No `dns` — a container copies its
// `dns` only when it starts, and the one restart that needs is the operator's (issue 110). // machine's resolvers (ADR 0196), and the mesh's resolver is not written into the runtime twice.
runtime := ids["dnsmasq.runtime-dns"] if ids["dnsmasq.runtime-dns"] != nil {
t.Errorf("the resolver still writes the runtime's dns: %v", ids["dnsmasq.runtime-dns"])
}
runtime := ids["resolv-conf.runtime-config"]
if runtime == nil || runtime["path"] != "/etc/docker/daemon.json" || runtime["into"] != "json" { if runtime == nil || runtime["path"] != "/etc/docker/daemon.json" || runtime["into"] != "json" {
t.Fatalf("the runtime's dns is not written into its file: %v", runtime) t.Fatalf("live-restore is not written into the runtime's file: %v", runtime)
} }
var keys map[string]any var keys map[string]any
if err := json.Unmarshal([]byte(runtime["content"].(string)), &keys); err != nil { if err := json.Unmarshal([]byte(runtime["content"].(string)), &keys); err != nil {
t.Fatalf("the runtime's keys are not JSON: %v", err) t.Fatalf("the runtime's keys are not JSON: %v", err)
} }
dns, _ := keys["dns"].([]any) if len(keys) != 1 || keys["live-restore"] != true {
if len(keys) != 2 || len(dns) != 1 || dns[0] != "10.42.0.1" || keys["live-restore"] != true { t.Errorf("the runtime is given %v; live-restore and nothing else", keys)
t.Errorf("the runtime is given %v; containers resolve at this machine's own private-network address, a restart keeps them, and nothing else is written", keys)
} }
// The runtime is reloaded when that file changes, and never restarted: a restart stops every // The runtime is reloaded when that file changes, and never restarted: a restart stops every
// container on the machine (ADR 0102), and a reload is what turns live-restore on. // container on the machine (ADR 0102), and a reload is what turns live-restore on.
@@ -171,10 +192,10 @@ func TestTheResolverAndWhatAsksItComposeOnOneMachine(t *testing.T) {
continue continue
} }
if _, restarts := r["restart-on"]; restarts { if _, restarts := r["restart-on"]; restarts {
t.Errorf("the resolver orders the runtime restarted, which stops every container (ADR 0102): %v", r) t.Errorf("the runtime is ordered restarted, which stops every container (ADR 0102): %v", r)
} }
for _, on := range asStrings(r["reload-on"]) { for _, on := range asStrings(r["reload-on"]) {
if on == "dnsmasq.runtime-dns" { if on == "resolv-conf.runtime-config" {
reloaded = true reloaded = true
} }
} }
@@ -184,8 +205,8 @@ func TestTheResolverAndWhatAsksItComposeOnOneMachine(t *testing.T) {
} }
resolv := ids["resolv-conf.resolv"] resolv := ids["resolv-conf.resolv"]
if resolv == nil || !strings.Contains(resolv["content"].(string), "\nnameserver 127.0.0.1\n") { if resolv == nil || !strings.Contains(resolv["content"].(string), "\nnameserver 10.42.0.1\nnameserver 1.1.1.1\n") {
t.Fatalf("the machine is not pointed at the resolver: %v", resolv) t.Fatalf("the machine is not pointed at the resolver by address, with the public fallback: %v", resolv)
} }
} }
+27
View File
@@ -61,6 +61,16 @@ type rosterView struct {
Suffix string Suffix string
Names []rosterEntry Names []rosterEntry
Machines []rosterEntry Machines []rosterEntry
// Zones is every zone a module in the mesh answers itself, with where its answerer is (novox/hq
// ADR 0199) — what the mesh's resolver forwards. Ordered by zone.
Zones []rosterZone
}
// rosterZone is one zone as a template sees it: the zone, and the address and port answering it.
type rosterZone struct {
Zone string
Address string
Port int
} }
// rosterEntry is one machine as a template sees it: its bare name, its full mesh name, its address, // rosterEntry is one machine as a template sees it: its bare name, its full mesh name, its address,
@@ -80,6 +90,12 @@ type rosterEntry struct {
// `machines` is only the machines — the two must not be confused (novox/hq 04-ISSUES/111), so both // `machines` is only the machines — the two must not be confused (novox/hq 04-ISSUES/111), so both
// are given and the template chooses. // are given and the template chooses.
func FactsInto(m Manifest, r Resolution, every, machines, accounts map[string]string, suffix string) ([]map[string]any, error) { func FactsInto(m Manifest, r Resolution, every, machines, accounts map[string]string, suffix string) ([]map[string]any, error) {
return FactsWithZonesInto(m, r, every, machines, accounts, suffix, nil)
}
// FactsWithZonesInto is FactsInto with the mesh's zones in the view, for a template that ranges them.
func FactsWithZonesInto(m Manifest, r Resolution, every, machines, accounts map[string]string, suffix string,
zones []ZoneAt) ([]map[string]any, error) {
if len(m.Facts) == 0 { if len(m.Facts) == 0 {
return nil, nil return nil, nil
} }
@@ -94,6 +110,7 @@ func FactsInto(m Manifest, r Resolution, every, machines, accounts map[string]st
Suffix: strings.TrimPrefix(suffixOr(suffix), "."), Suffix: strings.TrimPrefix(suffixOr(suffix), "."),
Names: entriesFrom(every, accounts, suffix), Names: entriesFrom(every, accounts, suffix),
Machines: entriesFrom(machines, accounts, suffix), Machines: entriesFrom(machines, accounts, suffix),
Zones: zonesFrom(zones),
} }
out := make([]map[string]any, 0, len(names)) out := make([]map[string]any, 0, len(names))
@@ -223,3 +240,13 @@ func sortedNames(addresses map[string]string) []string {
sort.Strings(out) sort.Strings(out)
return out return out
} }
// zonesFrom is the zones a template ranges, ordered by zone so two renderings of one mesh are one file.
func zonesFrom(zones []ZoneAt) []rosterZone {
out := make([]rosterZone, 0, len(zones))
for _, z := range zones {
out = append(out, rosterZone{Zone: z.Zone, Address: z.Address, Port: z.Port})
}
sort.Slice(out, func(i, j int) bool { return out[i].Zone < out[j].Zone })
return out
}
+5 -5
View File
@@ -43,8 +43,8 @@ import (
var ofSeat = regexp.MustCompile(`\$\{seat:([a-z0-9][a-z0-9-]*):([0-9]+)\}`) var ofSeat = regexp.MustCompile(`\$\{seat:([a-z0-9][a-z0-9-]*):([0-9]+)\}`)
// seatInto replaces a resource's ${seat:…} placeholders with where this machine put each seat's // seatInto replaces a resource's ${seat:…} placeholders with where this machine put each seat's
// holder — in a file's content, and in a value of a container's or a process's environment. The // holder — in a file's content, and in a value of a container's environment. The same two places
// same places portInto fills, for the same reason: they are where a program reads a number from. // portInto fills, for the same reason: they are where a process reads a number from.
func seatInto(resource map[string]any, module string, with Rendering) error { func seatInto(resource map[string]any, module string, with Rendering) error {
switch fmt.Sprint(resource["type"]) { switch fmt.Sprint(resource["type"]) {
case "file": case "file":
@@ -58,7 +58,7 @@ func seatInto(resource map[string]any, module string, with Rendering) error {
} }
resource["content"] = filled resource["content"] = filled
case "container", "process": case "container":
env, ok := resource["env"].(map[string]any) env, ok := resource["env"].(map[string]any)
if !ok { if !ok {
return nil return nil
@@ -78,8 +78,8 @@ func seatInto(resource map[string]any, module string, with Rendering) error {
continue continue
} }
value, err := seatsFilledInto(written, value, err := seatsFilledInto(written,
fmt.Sprintf("%s's %s %s sets %s to something that", fmt.Sprintf("%s's container %s sets %s to something that",
module, resource["type"], resource["name"], key), with) module, resource["name"], key), with)
if err != nil { if err != nil {
return err return err
} }
+9 -10
View File
@@ -101,7 +101,7 @@ func TestTheControlPlanesOwnAddressesFollowTheNodesPorts(t *testing.T) {
} }
// The manifest itself names them now; withSeatPorts is a no-op on it, and this holds it so. // The manifest itself names them now; withSeatPorts is a no-op on it, and this holds it so.
for _, r := range m.Resources { for _, r := range m.Resources {
if r["type"] != "process" { if r["type"] != "container" {
continue continue
} }
env, _ := r["env"].(map[string]any) env, _ := r["env"].(map[string]any)
@@ -113,9 +113,8 @@ func TestTheControlPlanesOwnAddressesFollowTheNodesPorts(t *testing.T) {
} }
m = withSeatPorts(m) m = withSeatPorts(m)
control, err := m.Resolve([]Built{{ control, err := m.Resolve([]Built{{
Name: "controller", Kind: ArtifactBundle, Name: "server", Kind: ArtifactImage,
Reference: ArtifactStoreScheme + "mesh-controller/controller@sha256:" + strings.Repeat("c", 64), Reference: ArtifactStoreScheme + "mesh-controller/server@sha256:" + strings.Repeat("c", 64),
Digest: "sha256:" + strings.Repeat("c", 64),
}}) }})
if err != nil { if err != nil {
t.Fatal(err) t.Fatal(err)
@@ -136,9 +135,9 @@ func TestTheControlPlanesOwnAddressesFollowTheNodesPorts(t *testing.T) {
if err != nil { if err != nil {
t.Fatalf("the control plane does not compose: %v", err) t.Fatalf("the control plane does not compose: %v", err)
} }
server := fileNamed(out, "mesh-controller.controller") server := fileNamed(out, "mesh-controller.server")
if server == nil { if server == nil {
t.Fatalf("the control plane's process is not in the declaration: %v", out) t.Fatalf("the control plane's container is not in the declaration: %v", out)
} }
env, _ := server["env"].(map[string]any) env, _ := server["env"].(map[string]any)
for key, want := range map[string]string{ for key, want := range map[string]string{
@@ -152,8 +151,8 @@ func TestTheControlPlanesOwnAddressesFollowTheNodesPorts(t *testing.T) {
t.Errorf("the control plane is told %s=%v; the node put it on %s", key, env[key], want) t.Errorf("the control plane is told %s=%v; the node put it on %s", key, env[key], want)
} }
} }
if got := server["source"]; got != "anchor.internal:5100/mesh-controller/controller@sha256:"+strings.Repeat("c", 64) { if got := server["image"]; got != "anchor.internal:5100/mesh-controller/server@sha256:"+strings.Repeat("c", 64) {
t.Errorf("the control plane's own bundle is fetched from %v, not routed through the store", got) t.Errorf("the control plane's own image is %v, not routed through the store", got)
} }
// And on a mesh where the foundation is where genesis raised it, nothing is added. // And on a mesh where the foundation is where genesis raised it, nothing is added.
@@ -161,7 +160,7 @@ func TestTheControlPlanesOwnAddressesFollowTheNodesPorts(t *testing.T) {
if err != nil { if err != nil {
t.Fatal(err) t.Fatal(err)
} }
env, _ = fileNamed(out, "mesh-controller.controller")["env"].(map[string]any) env, _ = fileNamed(out, "mesh-controller.server")["env"].(map[string]any)
if env["MESH_STORE_INVENTORY_PORT"] != "" { if env["MESH_STORE_INVENTORY_PORT"] != "" {
t.Errorf("with no settings, the control plane is told %v", env) t.Errorf("with no settings, the control plane is told %v", env)
} }
@@ -187,7 +186,7 @@ func withSeatPorts(m Manifest) Manifest {
out := m out := m
out.Resources = nil out.Resources = nil
for _, r := range m.Resources { for _, r := range m.Resources {
if r["type"] != "container" && r["type"] != "process" { if r["type"] != "container" {
out.Resources = append(out.Resources, r) out.Resources = append(out.Resources, r)
continue continue
} }
+24
View File
@@ -107,7 +107,31 @@ var defaultSeats = []Seat{
// that machine unresolvable in the meantime. Deleted once no registered manifest claims it. // that machine unresolvable in the meantime. Deleted once no registered manifest claims it.
{Name: "mesh-build-machine", Scope: ScopeMesh, {Name: "mesh-build-machine", Scope: ScopeMesh,
Accepts: []string{"build"}, Emits: []string{"started", "built", "log.*"}, Decision: "novox/hq ADR 0190"}, Accepts: []string{"build"}, Emits: []string{"started", "built", "log.*"}, Decision: "novox/hq ADR 0190"},
// **The mesh's one resolver** (novox/hq ADR 0194, 0196): every node's internal domain, held in one
// place, and every node and container asks it first. Delivers what a machine's resolver
// configuration requires, so that requirement resolves to the holder wherever it is placed.
{Name: "mesh-dns-resolver", Scope: ScopeMesh, Delivers: "wildcard-resolution", Decision: "novox/hq ADR 0194"},
// **Retired by ADR 0194, kept while a manifest still claims it** — the same reason as
// mesh-build-machine above: a machine still holds it until the mesh's resolver replaces it, and
// removing the row first would make that machine unresolvable. Deleted once nothing claims it.
{Name: "node-dns-resolver", Scope: ScopeNode, Decision: "novox/hq ADR 0121"}, {Name: "node-dns-resolver", Scope: ScopeNode, Decision: "novox/hq ADR 0121"},
// **A machine's /etc/hosts is one module's** (novox/hq ADR 0199): its holder writes the machine's
// own lines and keeps every other line as the operator's, changed through these three verbs on that
// machine alone. The controller holds none of it.
{Name: "node-hosts-file", Scope: ScopeNode, Decision: "novox/hq ADR 0199",
Serves: []Verb{
{Name: "entries", Description: "Every line of this machine's /etc/hosts, each marked whose it is: " +
"the operator's, or the block of the module or tool that writes it.",
Input: schema(map[string]string{}, nil)},
{Name: "add", Description: "Add one address and its names to the operator's lines of this machine's " +
"/etc/hosts — a name for this machine's own programs, not the mesh's.",
Input: schema(map[string]string{"address": "the IPv4 or IPv6 address",
"names": "the names for it, separated by spaces"}, []string{"address", "names"})},
{Name: "remove", Description: "Remove one name, or every line of one address, from the operator's " +
"lines of this machine's /etc/hosts. A line a module writes is refused, naming the module.",
Input: schema(map[string]string{"name": "a host name, or an address to remove every line of"},
[]string{"name"})},
}},
// The intrusion prevention's verbs (novox/hq ADR 0179): what a person asks a machine's ban list // The intrusion prevention's verbs (novox/hq ADR 0179): what a person asks a machine's ban list
// whatever keeps it — who is banned and why, ban one address, let one go. Every holder serves all // whatever keeps it — who is banned and why, ban one address, let one go. Every holder serves all
// four; the jails themselves are composed from the modules the machine runs (to-be 31). // four; the jails themselves are composed from the modules the machine runs (to-be 31).
-7
View File
@@ -215,13 +215,6 @@ func CatalogueProblems(shelf Shelf) []string {
} }
} }
} }
// A read of a module's state that module does not keep (novox/hq ADR 0201) — said only where the
// owner is on the shelf, as a consumer may be installed before its emitter.
var manifests []Manifest
for _, module := range shelfOrder(shelf) {
manifests = append(manifests, shelf[module])
}
problems = append(problems, StateReadsNothingDeclares(manifests)...)
sort.Strings(problems) sort.Strings(problems)
return problems return problems
} }
+4 -4
View File
@@ -44,10 +44,10 @@ func TestTheSeatsAreAClosedSetAndEachNamesItsDecision(t *testing.T) {
delivered[s.Delivers] = s.Name delivered[s.Delivers] = s.Name
} }
} }
// Seventeen since node-build-agent (novox/hq ADR 0190) — sixteen once the retired // Nineteen since mesh-dns-resolver (novox/hq ADR 0194) and node-hosts-file (ADR 0199) — two fewer
// mesh-build-machine row goes, when no registered manifest claims it any more. // once the retired mesh-build-machine and node-dns-resolver rows go, when no manifest claims either.
if len(Seats()) != 17 { if len(Seats()) != 19 {
t.Errorf("the mesh defines %d seats rather than 17; the set is closed, so a change here is "+ t.Errorf("the mesh defines %d seats rather than 19; the set is closed, so a change here is "+
"a decision (novox/hq ADR 0110): %s", len(Seats()), seatNames()) "a decision (novox/hq ADR 0110): %s", len(Seats()), seatNames())
} }
} }
-150
View File
@@ -1,150 +0,0 @@
package catalogue
import (
"bytes"
"encoding/json"
"fmt"
"regexp"
"strings"
)
// What a module may call its state, and whose state it may ask to read (novox/hq ADR 0201).
//
// A module names its state **locally** — `servers`, never a bucket or a subject — and another
// module's as `<module>.<name>`, the way a consumed event names its emitter (design 32 §1). The
// mesh derives the bucket from the two names, so the module and the local name must each be one
// token: the bucket joins them with an underscore, which neither may contain, so two modules can
// never derive one bucket.
// stateName is one local name of a module's state: lower-case, no dot, no underscore.
var stateName = regexp.MustCompile(`^[a-z0-9][a-z0-9-]*$`)
// The mesh's caps on what a module may ask of a bucket's history.
const (
// StateMostHistory is the most past values a key may keep. The server's own limit.
StateMostHistory = 64
)
// StateDeclaration is one bucket a module owns: its local name, and the options that are the
// owner's to choose, as a seat chooses how long its backlog survives (design 32 §3).
type StateDeclaration struct {
Name string `json:"name"`
// History is how many values a key keeps, the current one included; zero is one.
History int `json:"history,omitempty"`
// TTLSeconds is how long a value lives once written; zero is until it is replaced or deleted.
TTLSeconds int `json:"ttl-seconds,omitempty"`
}
// UnmarshalJSON reads a bucket as its bare name, or as {name, history, ttl-seconds}.
func (s *StateDeclaration) UnmarshalJSON(raw []byte) error {
trimmed := bytes.TrimSpace(raw)
if len(trimmed) > 0 && trimmed[0] == '"' {
return json.Unmarshal(trimmed, &s.Name)
}
type plain StateDeclaration
var full plain
dec := json.NewDecoder(bytes.NewReader(trimmed))
dec.DisallowUnknownFields()
if err := dec.Decode(&full); err != nil {
return fmt.Errorf("a state is either a name or {name, history, ttl-seconds}: %w", err)
}
*s = StateDeclaration(full)
return nil
}
// MarshalJSON writes back the short form when there is nothing else to say.
func (s StateDeclaration) MarshalJSON() ([]byte, error) {
if s.History == 0 && s.TTLSeconds == 0 {
return json.Marshal(s.Name)
}
type plain StateDeclaration
return json.Marshal(plain(s))
}
// ReadState splits a read into the owning module and the local name, or says why it is not one.
func ReadState(read string) (module, local string, err error) {
at := strings.LastIndex(read, ".")
if at <= 0 || at == len(read)-1 {
return "", "", fmt.Errorf("%q does not name a module and its state: a read is <module>.<name>", read)
}
module, local = read[:at], read[at+1:]
if !stateName.MatchString(module) {
return "", "", fmt.Errorf("%q cannot own state: a module whose state is read is one plain name", module)
}
if !stateName.MatchString(local) {
return "", "", fmt.Errorf("%q is not a state name: lower-case letters, digits and hyphens", local)
}
return module, local, nil
}
// StateProblems is what is wrong with a manifest's state and reads.
//
// Refused at registration, because a bucket name the bus cannot hold is a module that installs,
// starts, and is refused on its first write with a reason about a bucket nobody named.
func StateProblems(m Manifest) []string {
var problems []string
if len(m.State) > 0 && !stateName.MatchString(m.Module) {
problems = append(problems, fmt.Sprintf(
"%s keeps state, and a module's name is part of its buckets' names, which take one plain "+
"name — no dot (novox/hq ADR 0201)", m.Module))
}
seen := map[string]bool{}
for _, s := range m.State {
switch {
case !stateName.MatchString(s.Name):
problems = append(problems, fmt.Sprintf(
"%s keeps state %q: a state is named locally — lower-case letters, digits and hyphens, "+
"no dot and no underscore; the mesh derives the bucket (novox/hq ADR 0201)", m.Module, s.Name))
case seen[s.Name]:
problems = append(problems, fmt.Sprintf("%s keeps state %q twice", m.Module, s.Name))
}
seen[s.Name] = true
if s.History < 0 || s.History > StateMostHistory {
problems = append(problems, fmt.Sprintf(
"%s keeps %d values of %q; a key keeps between 1 and %d", m.Module, s.History, s.Name, StateMostHistory))
}
if s.TTLSeconds < 0 {
problems = append(problems, fmt.Sprintf("%s gives %q a negative lifetime", m.Module, s.Name))
}
}
for _, r := range m.Reads {
module, _, err := ReadState(r)
if err != nil {
problems = append(problems, fmt.Sprintf("%s reads %v", m.Module, err))
continue
}
if module == m.Module {
problems = append(problems, fmt.Sprintf(
"%s reads %q, which is its own state: a module reads and writes what it keeps already", m.Module, r))
}
}
return problems
}
// StateReadsNothingDeclares is every read across a catalogue whose owner is present and declares no
// such state. An absent owner says nothing — a module may be installed long before the one whose
// state it reads, as a consumer may before its emitter (design 32 §1).
func StateReadsNothingDeclares(manifests []Manifest) []string {
declared := map[string]map[string]bool{}
for _, m := range manifests {
own := map[string]bool{}
for _, s := range m.State {
own[s.Name] = true
}
declared[m.Module] = own
}
var problems []string
for _, m := range manifests {
for _, r := range m.Reads {
module, local, err := ReadState(r)
if err != nil {
continue
}
if own, present := declared[module]; present && !own[local] {
problems = append(problems, fmt.Sprintf(
"%s reads %q, and %s keeps no state called %q", m.Module, r, module, local))
}
}
}
return problems
}
-94
View File
@@ -1,94 +0,0 @@
package catalogue
import (
"encoding/json"
"strings"
"testing"
)
// A module declares the state it keeps and the state it reads (novox/hq ADR 0201), a bucket by its
// bare name or with the owner's options.
func TestAManifestMaySayWhatStateItKeepsAndReads(t *testing.T) {
m, err := ParseManifest([]byte(`{"module":"claude-code","version":"1",` +
`"state":["servers",{"name":"seen","history":5,"ttl-seconds":3600}],` +
`"reads":["licence-manager.bindings"]}`))
if err != nil {
t.Fatal(err)
}
if len(m.State) != 2 || m.State[0].Name != "servers" || m.State[1].History != 5 || m.State[1].TTLSeconds != 3600 {
t.Fatalf("state not read: %+v", m.State)
}
if len(m.Reads) != 1 || m.Reads[0] != "licence-manager.bindings" {
t.Fatalf("reads not read: %v", m.Reads)
}
// Written back as it came in: the short form where nothing else is said.
out, _ := json.Marshal(m.State)
if string(out) != `["servers",{"name":"seen","history":5,"ttl-seconds":3600}]` {
t.Fatalf("written back as %s", out)
}
}
// A name the bus could not hold, or that would let two modules derive one bucket, is refused at
// registration in the manifest's words.
func TestAStateNameIsLocalAndOneToken(t *testing.T) {
for _, c := range []struct{ manifest, says string }{
{`{"module":"a","version":"1","state":["mesh.servers"]}`, `keeps state "mesh.servers": a state is named locally`},
{`{"module":"a","version":"1","state":["my_servers"]}`, `keeps state "my_servers"`},
{`{"module":"a","version":"1","state":["s","s"]}`, `keeps state "s" twice`},
{`{"module":"a","version":"1","state":[{"name":"s","history":65}]}`, `a key keeps between 1 and 64`},
{`{"module":"a.b","version":"1","state":["s"]}`, `no dot`},
{`{"module":"a","version":"1","reads":["bindings"]}`, `a read is <module>.<name>`},
{`{"module":"a","version":"1","reads":["a.s"]}`, `which is its own state`},
{`{"module":"a","version":"1","state":[{"name":"s","shared":true}]}`, `{name, history, ttl-seconds}`},
} {
_, err := ParseManifest([]byte(c.manifest))
if err == nil {
t.Errorf("%s was accepted", c.manifest)
continue
}
if !strings.Contains(err.Error(), c.says) {
t.Errorf("%s refused for the wrong reason: %v", c.manifest, err)
}
}
}
// A read whose owner is present must name a state that owner keeps; an absent owner says nothing,
// because a module may be installed before the one whose state it reads.
func TestAReadNamesStateItsOwnerKeeps(t *testing.T) {
owner := Manifest{Module: "licence-manager", State: []StateDeclaration{{Name: "bindings"}}}
good := Manifest{Module: "claude-code", Reads: []string{"licence-manager.bindings", "absent.anything"}}
bad := Manifest{Module: "other", Reads: []string{"licence-manager.tokens"}}
if p := StateReadsNothingDeclares([]Manifest{owner, good}); len(p) != 0 {
t.Fatalf("a read of declared state was refused: %v", p)
}
p := StateReadsNothingDeclares([]Manifest{owner, bad})
if len(p) != 1 || !strings.Contains(p[0], `licence-manager keeps no state called "tokens"`) {
t.Fatalf("a read of state nobody keeps was not named: %v", p)
}
}
// **Across the whole catalogue**: every state name is local, and every read whose owner is present
// names state that owner keeps.
func TestEveryManifestsStateIsLocalAndEveryReadIsKept(t *testing.T) {
manifests := theCatalogue(t)
var problems []string
for _, m := range manifests {
problems = append(problems, StateProblems(m)...)
}
problems = append(problems, StateReadsNothingDeclares(manifests)...)
if len(problems) > 0 {
t.Fatalf("the catalogue's state is not what ADR 0201 says:\n %s", strings.Join(problems, "\n "))
}
}
// `module check` says it too: the cross-catalogue pass names a read nothing on the shelf keeps.
func TestTheCataloguePassNamesAReadItsOwnerDoesNotKeep(t *testing.T) {
shelf := Shelf{
"licence-manager": {Module: "licence-manager", State: []StateDeclaration{{Name: "bindings"}}},
"claude-code": {Module: "claude-code", Reads: []string{"licence-manager.tokens"}},
}
problems := CatalogueProblems(shelf)
if len(problems) != 1 || !strings.Contains(problems[0], `keeps no state called "tokens"`) {
t.Fatalf("the catalogue pass said %v", problems)
}
}
-145
View File
@@ -1,145 +0,0 @@
package catalogue
import (
"encoding/json"
"fmt"
"strings"
"testing"
)
// A scheduled step may hold its module's own containers still while it runs (novox/hq ADR 0189).
//
// The host judges what it receives — whether each id is a container on that machine. What the
// definition is the only place to see is judged here, near whoever wrote it.
func aStoreManifest(step map[string]any) []byte {
m := map[string]any{
"module": "distribution", "version": "1",
"resources": []any{
map[string]any{"id": "store", "type": "container", "name": "mesh-registry",
"image": "registry@sha256:" + strings.Repeat("a", 64)},
step,
},
}
raw, _ := json.Marshal(m)
return raw
}
func TestAMaintenanceWindowOnItsOwnModulesContainerIsAccepted(t *testing.T) {
raw := aStoreManifest(map[string]any{
"id": "collect", "type": "container", "name": "mesh-registry-collect",
"image": "registry@sha256:" + strings.Repeat("a", 64),
"schedule": "30 3 * * *", "while-stopped": []any{"store"},
})
if _, err := ParseManifest(raw); err != nil {
t.Fatalf("a step holding its own module's container still was refused: %v", err)
}
}
func TestAMaintenanceWindowIsRefusedWhereTheDefinitionShowsItCannotMean(t *testing.T) {
for _, c := range []struct {
name string
step map[string]any
says string
}{
{
"on a step with no schedule",
map[string]any{"id": "collect", "type": "container", "name": "c",
"image": "registry@sha256:" + strings.Repeat("a", 64),
"while-stopped": []any{"store"}},
"gates what is declared after it",
},
{
"on a run-once step, which already has order",
map[string]any{"id": "collect", "type": "container", "name": "c",
"image": "registry@sha256:" + strings.Repeat("a", 64),
"run-once": true, "while-stopped": []any{"store"}},
"A maintenance window is for a recurring step",
},
{
"naming a container this module does not declare",
map[string]any{"id": "collect", "type": "container", "name": "c",
"image": "registry@sha256:" + strings.Repeat("a", 64),
"schedule": "30 3 * * *", "while-stopped": []any{"the-broker"}},
"could quiesce a neighbour could stop the mesh",
},
{
"naming itself",
map[string]any{"id": "collect", "type": "container", "name": "c",
"image": "registry@sha256:" + strings.Repeat("a", 64),
"schedule": "30 3 * * *", "while-stopped": []any{"collect"}},
"naming itself",
},
{
"written as something that is not a list",
map[string]any{"id": "collect", "type": "container", "name": "c",
"image": "registry@sha256:" + strings.Repeat("a", 64),
"schedule": "30 3 * * *", "while-stopped": "store"},
"a list of this module's container ids",
},
} {
_, err := ParseManifest(aStoreManifest(c.step))
if err == nil {
t.Errorf("%s was accepted", c.name)
continue
}
if !strings.Contains(err.Error(), c.says) {
t.Errorf("%s: the refusal does not say %q:\n%v", c.name, c.says, err)
}
}
}
// A composed declaration names the step's held containers the way the machine knows them.
//
// **The gap that let a bug through to the control node.** The manifest says `while-stopped:
// ["store"]`, because a module names its own resources locally; the declaration a machine
// receives calls that container `distribution.store`, because every resource is composed under
// its module. `restart-on` and `reload-on` are rewritten for exactly this reason, and
// `while-stopped` was not — so the host found no container by that id and refused the whole
// declaration, every push, until it was fixed.
//
// It passed every test on both sides: the controller's tests read manifests, the host's read
// hand-written declarations with bare ids. Only composing one and judging the result catches it.
func TestAComposedWindowNamesTheContainerAsTheMachineKnowsIt(t *testing.T) {
store := Manifest{
Module: "distribution", Version: "1",
Provides: FromAnywhere("artifact-store"),
Listens: []Listening{{Port: 5000, Protocol: "tcp", From: FromMesh}},
Serves: map[string]map[string]any{"artifact-store": {"port": 5000}},
Resources: []map[string]any{
{"id": "store", "type": "container", "name": "mesh-registry",
"image": "registry@sha256:" + strings.Repeat("a", 64), "ports": []any{"5000"}},
{"id": "collect", "type": "container", "name": "mesh-registry-collect",
"image": "registry@sha256:" + strings.Repeat("a", 64),
"schedule": "30 3 * * *", WhileStopped: []any{"store"}},
},
}
r, err := Resolve(shelf(store), []string{"distribution"}, reachable(), World{})
if err != nil {
t.Fatal(err)
}
out, err := r.Declaration(Rendering{})
if err != nil {
t.Fatal(err)
}
collect := fileNamed(out, "distribution.collect")
if collect == nil {
for _, res := range out {
if res["id"] == "distribution.collect" {
collect = res
}
}
}
if collect == nil {
t.Fatalf("the step was not composed at all: %v", out)
}
held, _ := collect[WhileStopped].([]any)
if len(held) != 1 {
t.Fatalf("the composed step holds %v still; want one container", collect[WhileStopped])
}
if got := fmt.Sprint(held[0]); got != "distribution.store" {
t.Fatalf("the composed step says it holds %q still, and the machine's container is "+
"called %q — the host refuses a declaration naming a container it does not have, "+
"whole, so the machine would take nothing at all", got, "distribution.store")
}
}
+117
View File
@@ -0,0 +1,117 @@
package catalogue
import (
"fmt"
"sort"
"strings"
)
// Zones: names a module answers itself (novox/hq ADR 0199).
//
// The mesh's resolver holds each node's internal domain and nothing else (ADR 0191, 0194). A module
// whose names are its own — the lab's scenario machines, known only while a scenario runs — declares
// the zone it answers and the listen that answers it; the controller hands the resolver's holder every
// zone with the declaring node's private address and the port that listen is published on, and the
// holder forwards the zone there. **A definition names no address** (ADR 0112): the zone is a setting,
// the listen is the module's own, and where they are is the mesh's fact.
// Zone is the manifest's declaration that a module answers the names in one zone.
type Zone struct {
// Name is the zone: a label or a dotted name, normally `${setting:<key>}`, so the operator chooses
// it and the definition does not.
Name string `json:"name"`
// Listen names one of the module's listens: the DNS answerer for the zone.
Listen string `json:"listen"`
}
// ZoneAt is a declared zone where the mesh placed it: what the resolver's holder forwards, and where.
type ZoneAt struct {
Zone string
Node string
Module string
Address string
Port int
}
// zoneProblems is what is wrong with a module's zone declaration on its own, before any node.
func zoneProblems(m Manifest) []string {
if m.Zone == nil {
return nil
}
var problems []string
if strings.TrimSpace(m.Zone.Name) == "" {
problems = append(problems, fmt.Sprintf("%s declares a zone with no name", m.Module))
}
if !m.hasListen(m.Zone.Listen) {
problems = append(problems, fmt.Sprintf(
"%s declares zone %q answered by listen %q, and has no listen of that name",
m.Module, m.Zone.Name, m.Zone.Listen))
}
return problems
}
func (m Manifest) hasListen(name string) bool {
if name == "" {
return false
}
for _, l := range m.Listens {
if l.Name == name {
return true
}
}
return false
}
// ZoneOn is one module's zone as one node places it: the name settled from the node's settings, the
// port its answering listen is published on there. Nothing when the module declares no zone.
func ZoneOn(m Manifest, layers []Layer, published map[int]int, node, address string) (*ZoneAt, error) {
if m.Zone == nil {
return nil, nil
}
settled, err := Settle(map[string]any{"zone": m.Zone.Name}, layers)
if err != nil {
return nil, fmt.Errorf("%s's zone on %s: %w", m.Module, node, err)
}
zone := strings.Trim(strings.ToLower(fmt.Sprint(settled["zone"])), ".")
var port int
for _, l := range m.Listens {
if l.Name == m.Zone.Listen {
port = l.Port
if at, given := published[l.Port]; given {
port = at
}
}
}
return &ZoneAt{Zone: zone, Node: node, Module: m.Module, Address: address, Port: port}, nil
}
// ZonesProblems is what the mesh refuses about its zones together: one zone declared twice, a zone
// that is the mesh's suffix or under it, a zone that is a node's public domain or under one. A module
// may not shadow names the mesh's resolver or the public DNS answers.
func ZonesProblems(zones []ZoneAt, suffix string, publicDomains []string) []string {
var problems []string
under := func(zone, domain string) bool {
domain = strings.Trim(strings.ToLower(domain), ".")
return domain != "" && (zone == domain || strings.HasSuffix(zone, "."+domain))
}
seen := map[string]ZoneAt{}
for _, z := range zones {
if other, twice := seen[z.Zone]; twice && (other.Node != z.Node || other.Module != z.Module) {
problems = append(problems, fmt.Sprintf("zone %q is declared by %s on %s and by %s on %s; one module answers a zone",
z.Zone, other.Module, other.Node, z.Module, z.Node))
}
seen[z.Zone] = z
if under(z.Zone, suffix) {
problems = append(problems, fmt.Sprintf("%s on %s declares zone %q, which is the mesh's own suffix or under it",
z.Module, z.Node, z.Zone))
}
for _, d := range publicDomains {
if under(z.Zone, d) {
problems = append(problems, fmt.Sprintf("%s on %s declares zone %q, which is the public domain %q or under it",
z.Module, z.Node, z.Zone, d))
}
}
}
sort.Strings(problems)
return problems
}
+78
View File
@@ -0,0 +1,78 @@
package catalogue
import (
"strings"
"testing"
)
// A zone names the listen that answers it, or there is nothing to forward to (novox/hq ADR 0199).
func TestAZoneMustNameOneOfTheModulesListens(t *testing.T) {
_, err := ParseManifest([]byte(`{"module":"lab","version":"1",
"listens":[{"name":"dns","port":5353,"protocol":"udp","from":"mesh","why":"the lab's names"}],
"zone":{"name":"${setting:zone}","listen":"web"}}`))
if err == nil || !strings.Contains(err.Error(), `has no listen of that name`) {
t.Fatalf("a zone answered by a listen the module does not have was accepted: %v", err)
}
if _, err := ParseManifest([]byte(`{"module":"lab","version":"1",
"listens":[{"name":"dns","port":5353,"protocol":"udp","from":"mesh","why":"the lab's names"}],
"zone":{"name":"${setting:zone}","listen":"dns"}}`)); err != nil {
t.Fatalf("a well-formed zone was refused: %v", err)
}
}
// The zone is the operator's (a setting) and the port is where this machine publishes the listen —
// neither is the definition's to state.
func TestAZoneIsPlacedFromTheNodesSettingAndPublishedPort(t *testing.T) {
m := Manifest{Module: "lab", Zone: &Zone{Name: "${setting:zone}", Listen: "dns"},
Listens: []Listening{{Name: "dns", Port: 5353, From: FromMesh}}}
z, err := ZoneOn(m, []Layer{{From: "node", Values: map[string]any{"zone": "Incus."}}},
map[int]int{5353: 15353}, "workstation", "10.77.0.3")
if err != nil {
t.Fatal(err)
}
if z.Zone != "incus" || z.Address != "10.77.0.3" || z.Port != 15353 || z.Node != "workstation" {
t.Fatalf("the zone was placed as %+v", *z)
}
if _, err := ZoneOn(m, nil, nil, "workstation", "10.77.0.3"); err == nil {
t.Fatal("a zone nobody named was placed")
}
}
// One module answers a zone, and none may shadow the mesh's names or a public domain.
func TestTheMeshRefusesAZoneTwiceOrOneThatShadows(t *testing.T) {
one := ZoneAt{Zone: "incus", Node: "workstation", Module: "lab", Address: "10.77.0.3", Port: 53}
if p := ZonesProblems([]ZoneAt{one}, "internal", []string{"example.tld"}); len(p) != 0 {
t.Fatalf("one ordinary zone was refused: %v", p)
}
twice := one
twice.Node, twice.Module = "laptop", "other"
cases := map[string][]ZoneAt{
"declared by": {one, twice},
"mesh's own suffix": {{Zone: "lab.internal", Node: "a", Module: "m"}},
"public domain": {{Zone: "dev.example.tld", Node: "a", Module: "m"}},
}
for want, zones := range cases {
p := strings.Join(ZonesProblems(zones, "internal", []string{"example.tld"}), "\n")
if !strings.Contains(p, want) {
t.Errorf("not refused for %q: %q", want, p)
}
}
}
// The resolver's template sees every zone with where it is answered, in zone order.
func TestTheResolversTemplateRangesTheZones(t *testing.T) {
m := Manifest{Module: "dnsmasq", Facts: map[string]RosterFile{"zones": {
Path: "/etc/mesh-resolver/zones.conf",
Template: "{{range .Zones}}server=/{{.Zone}}/{{.Address}}#{{.Port}}\n{{end}}",
}}}
out, err := FactsWithZonesInto(m, Resolution{Node: "anchor"}, nil, nil, nil, "", []ZoneAt{
{Zone: "zeta", Address: "10.77.0.2", Port: 53},
{Zone: "incus", Address: "10.77.0.3", Port: 15353},
})
if err != nil {
t.Fatal(err)
}
if got := out[0]["content"]; got != "server=/incus/10.77.0.3#15353\nserver=/zeta/10.77.0.2#53\n" {
t.Fatalf("the resolver was told %q", got)
}
}
+14 -43
View File
@@ -42,29 +42,9 @@ type Build struct {
// Failed is the builder's own words, empty when it worked. // Failed is the builder's own words, empty when it worked.
Failed string Failed string
Made []Artifact Made []Artifact
// Asked is when the build was requested, zero when that is not known (an id of another shape, At time.Time
// or a build recorded before the mesh kept it). **What orders one build of a module against
// another** (novox/hq 04-ISSUES/219): builds in flight together finish in any order, and the
// one asked last stood on the newest bases.
Asked time.Time
// At is when the outcome was recorded — when it finished, not when it was asked.
At time.Time
} }
// AskedOrAt is when the build was asked, or when it was recorded when that is not known — the
// order the mesh had before it kept the request time.
func (b Build) AskedOrAt() time.Time {
if !b.Asked.IsZero() {
return b.Asked
}
return b.At
}
// newestRequestFirst is the ordering every "what a module currently is" question uses: the newest
// request wins, whenever it finished (novox/hq 04-ISSUES/219). A build whose request time is not
// known is placed at the moment it was recorded, which is the rule that held before.
const newestRequestFirst = `coalesce(asked, at) desc, at desc`
// ReadRepository is a repository a build read source from besides the module's own. // ReadRepository is a repository a build read source from besides the module's own.
type ReadRepository struct { type ReadRepository struct {
Repository string `json:"repository"` Repository string `json:"repository"`
@@ -103,17 +83,13 @@ func (i *Inventory) RecordBuild(ctx context.Context, b Build) error {
if b.Module != "" { if b.Module != "" {
module = &b.Module module = &b.Module
} }
var asked *time.Time
if !b.Asked.IsZero() {
asked = &b.Asked
}
_, err = i.store.Pool().Exec(ctx, _, err = i.store.Pool().Exec(ctx,
`insert into build (id, repository, ref, module, commit_hash, built_on, failed, made, `insert into build (id, repository, ref, module, commit_hash, built_on, failed, made,
source_path, manifest, built_against, built_contexts, asked) source_path, manifest, built_against, built_contexts)
values ($1, $2, $3, $4, $5, $6, $7, $8, $9, $10, $11, $12, $13) values ($1, $2, $3, $4, $5, $6, $7, $8, $9, $10, $11, $12)
on conflict (id) do nothing`, on conflict (id) do nothing`,
b.ID, b.Repository, b.Ref, module, b.Commit, b.On, b.Failed, made, b.ID, b.Repository, b.Ref, module, b.Commit, b.On, b.Failed, made,
b.Path, manifestOrNil(b.Manifest), against, read, asked) b.Path, manifestOrNil(b.Manifest), against, read)
return err return err
} }
@@ -126,11 +102,11 @@ func (i *Inventory) Builds(ctx context.Context, module string, limit int) ([]Bui
if limit <= 0 { if limit <= 0 {
limit = 20 limit = 20
} }
query := `select id, repository, ref, coalesce(module,''), commit_hash, built_on, failed, made, asked, at query := `select id, repository, ref, coalesce(module,''), commit_hash, built_on, failed, made, at
from build order by at desc limit $1` from build order by at desc limit $1`
args := []any{limit} args := []any{limit}
if module != "" { if module != "" {
query = `select id, repository, ref, coalesce(module,''), commit_hash, built_on, failed, made, asked, at query = `select id, repository, ref, coalesce(module,''), commit_hash, built_on, failed, made, at
from build where module = $2 order by at desc limit $1` from build where module = $2 order by at desc limit $1`
args = append(args, module) args = append(args, module)
} }
@@ -145,14 +121,10 @@ func (i *Inventory) Builds(ctx context.Context, module string, limit int) ([]Bui
for rows.Next() { for rows.Next() {
var b Build var b Build
var made []byte var made []byte
var asked *time.Time
if err := rows.Scan(&b.ID, &b.Repository, &b.Ref, &b.Module, &b.Commit, if err := rows.Scan(&b.ID, &b.Repository, &b.Ref, &b.Module, &b.Commit,
&b.On, &b.Failed, &made, &asked, &b.At); err != nil { &b.On, &b.Failed, &made, &b.At); err != nil {
return nil, err return nil, err
} }
if asked != nil {
b.Asked = *asked
}
if err := json.Unmarshal(made, &b.Made); err != nil { if err := json.Unmarshal(made, &b.Made); err != nil {
return nil, err return nil, err
} }
@@ -163,9 +135,8 @@ func (i *Inventory) Builds(ctx context.Context, module string, limit int) ([]Bui
// Held is every artifact this mesh has built, keyed "<module>/<artifact>". // Held is every artifact this mesh has built, keyed "<module>/<artifact>".
// //
// **The successful build of each module asked last wins**, which is the same rule the rest of the // **The newest successful build of each module wins**, which is the same rule the rest of the mesh
// mesh uses for what a module currently is — asked last, not finished last (novox/hq // uses for what a module currently is. A module rebuilt to something broken and then rebuilt again
// 04-ISSUES/219): an older request that finishes later stood on older bases. A module rebuilt to something broken and then rebuilt again
// is at the second one; a module whose last build failed is at the last one that worked, because a // is at the second one; a module whose last build failed is at the last one that worked, because a
// failure published nothing and the thing it published before is still what exists. // failure published nothing and the thing it published before is still what exists.
// //
@@ -176,7 +147,7 @@ func (i *Inventory) Held(ctx context.Context) (map[string]string, error) {
`select distinct on (module) module, made `select distinct on (module) module, made
from build from build
where module is not null and module <> '' and failed = '' where module is not null and module <> '' and failed = ''
order by module, `+newestRequestFirst) order by module, at desc`)
if err != nil { if err != nil {
return nil, err return nil, err
} }
@@ -214,7 +185,7 @@ func (i *Inventory) BuiltAgainst(ctx context.Context) (map[string][]string, erro
`select distinct on (module) module, built_against `select distinct on (module) module, built_against
from build from build
where module is not null and module <> '' and failed = '' where module is not null and module <> '' and failed = ''
order by module, `+newestRequestFirst) order by module, at desc`)
if err != nil { if err != nil {
return nil, err return nil, err
} }
@@ -252,7 +223,7 @@ func (i *Inventory) ReadRepositories(ctx context.Context) (map[string][]ReadRepo
`select distinct on (module) module, built_contexts `select distinct on (module) module, built_contexts
from build from build
where module is not null and module <> '' and failed = '' where module is not null and module <> '' and failed = ''
order by module, `+newestRequestFirst) order by module, at desc`)
if err != nil { if err != nil {
return nil, err return nil, err
} }
@@ -303,7 +274,7 @@ func manifestOrNil(raw []byte) any {
// follows when it decides whether to announce at all. // follows when it decides whether to announce at all.
// //
// One row per module and commit: a module built twice at the same commit is one fact, and the // One row per module and commit: a module built twice at the same commit is one fact, and the
// row asked last is the one whose artifacts are current (novox/hq 04-ISSUES/219). // latest row is the one whose artifacts are current.
func (i *Inventory) Announceable(ctx context.Context) ([]Build, error) { func (i *Inventory) Announceable(ctx context.Context) ([]Build, error) {
rows, err := i.store.Pool().Query(ctx, rows, err := i.store.Pool().Query(ctx,
`select distinct on (module, commit_hash) `select distinct on (module, commit_hash)
@@ -311,7 +282,7 @@ func (i *Inventory) Announceable(ctx context.Context) ([]Build, error) {
source_path, manifest, built_against, at source_path, manifest, built_against, at
from build from build
where failed = '' and module is not null and module <> '' and commit_hash <> '' where failed = '' and module is not null and module <> '' and commit_hash <> ''
order by module, commit_hash, `+newestRequestFirst) order by module, commit_hash, at desc`)
if err != nil { if err != nil {
return nil, err return nil, err
} }
+1 -66
View File
@@ -49,12 +49,6 @@ func (i *Inventory) BusRecords(ctx context.Context) (broker.Records, error) {
} }
} }
// Who holds each seat held once for the mesh, where the mesh recorded it (novox/hq issue 218).
holdings, err := i.Holdings(ctx)
if err != nil {
return broker.Records{}, fmt.Errorf("cannot read who holds the mesh's seats: %w", err)
}
out := broker.Records{Assigned: map[string][]broker.Declared{}, People: map[string][]string{}, out := broker.Records{Assigned: map[string][]broker.Declared{}, People: map[string][]string{},
Interchangeable: map[string]bool{}} Interchangeable: map[string]bool{}}
for _, n := range nodes { for _, n := range nodes {
@@ -78,9 +72,7 @@ func (i *Inventory) BusRecords(ctx context.Context) (broker.Records, error) {
"%s is assigned to %s and is not in the catalogue, so what it may say cannot "+ "%s is assigned to %s and is not in the catalogue, so what it may say cannot "+
"be derived", module, n.Name) "be derived", module, n.Name)
} }
d := declaredFor(m, seats) out.Assigned[n.Name] = append(out.Assigned[n.Name], declaredFor(m, seats))
d.Holds = heldHere(d.Holds, holdings, n.Name, module)
out.Assigned[n.Name] = append(out.Assigned[n.Name], d)
if m.Instances == catalogue.InstancesInterchangeable { if m.Instances == catalogue.InstancesInterchangeable {
out.Interchangeable[m.Module] = true out.Interchangeable[m.Module] = true
} }
@@ -132,9 +124,6 @@ func declaredFor(m catalogue.Manifest, seats map[string]catalogue.SeatDeclaratio
Serves: m.Tools, Serves: m.Tools,
// And what it calls (novox/hq ADR 0152) — the console's `*`, nothing else's. // And what it calls (novox/hq ADR 0152) — the console's `*`, nothing else's.
Invokes: m.Invokes, Invokes: m.Invokes,
// And the state it keeps and reads (novox/hq ADR 0201).
State: bucketsOf(m),
Reads: m.Reads,
} }
for _, c := range m.Claims { for _, c := range m.Claims {
// Every seat with a protocol, the mesh's own included. One that says only who does a job is // Every seat with a protocol, the mesh's own included. One that says only who does a job is
@@ -151,30 +140,6 @@ func declaredFor(m catalogue.Manifest, seats map[string]catalogue.SeatDeclaratio
return d return d
} }
// bucketsOf is the state a module keeps, as the bus holds it.
func bucketsOf(m catalogue.Manifest) []broker.Bucket {
var out []broker.Bucket
for _, s := range m.State {
out = append(out, broker.Bucket{Module: m.Module, Name: s.Name, History: s.History, TTLSeconds: s.TTLSeconds})
}
return out
}
// DeclaredBuckets is every bucket the catalogue declares, registered modules assigned or not: a
// bucket exists from registration, like a seat's stream, so a module reading it may watch before its
// owner runs anywhere (novox/hq ADR 0201).
func (i *Inventory) DeclaredBuckets(ctx context.Context) ([]broker.Bucket, error) {
declared, err := i.Catalogue(ctx)
if err != nil {
return nil, fmt.Errorf("cannot read the catalogue: %w", err)
}
var out []broker.Bucket
for _, m := range declared {
out = append(out, bucketsOf(m)...)
}
return out, nil
}
func asSeat(s catalogue.SeatDeclaration) broker.Seat { func asSeat(s catalogue.SeatDeclaration) broker.Seat {
return broker.Seat{Name: s.Name, Scope: s.Scope, Accepts: s.Accepts, Emits: s.Emits, return broker.Seat{Name: s.Name, Scope: s.Scope, Accepts: s.Accepts, Emits: s.Emits,
Serves: catalogue.VerbNames(s.Serves)} Serves: catalogue.VerbNames(s.Serves)}
@@ -218,33 +183,3 @@ func (i *Inventory) NodesWithALiveToken(ctx context.Context) ([]string, error) {
} }
return out, rows.Err() return out, rows.Err()
} }
// heldHere keeps of what a module claims only the seats it holds on this machine (novox/hq issue 218).
// A seat held once per machine is held by every assignment that claims it. A seat held once for the
// mesh is held by one assignment: where the mesh recorded who holds it, a claim on any other machine
// grants nothing and issues nothing — or the module would serve the role's verbs from a machine that
// is not the role's, and a question to the mesh's store would be answered from the wrong database. A
// mesh seat with no holder on record is left as it was derived.
func heldHere(claimed []broker.Seat, holdings []catalogue.Held, node, module string) []broker.Seat {
recorded := map[string][]catalogue.Held{}
for _, h := range holdings {
if h.Scope == catalogue.ScopeMesh {
recorded[h.Claim] = append(recorded[h.Claim], h)
}
}
var out []broker.Seat
for _, s := range claimed {
holders, onRecord := recorded[s.Name]
if s.Scope != catalogue.ScopeMesh || !onRecord {
out = append(out, s)
continue
}
for _, h := range holders {
if h.Node == node && h.Module == module {
out = append(out, s)
break
}
}
}
return out
}
+35 -42
View File
@@ -17,10 +17,6 @@ import (
// ErrNoSuchModule is what the mesh says about a module it has never been told about. // ErrNoSuchModule is what the mesh says about a module it has never been told about.
var ErrNoSuchModule = errors.New("no module of that name") var ErrNoSuchModule = errors.New("no module of that name")
// ErrSuperseded is a registration from a build asked before the one the module is already at
// (novox/hq 04-ISSUES/219). The build is recorded; what the module is does not change.
var ErrSuperseded = errors.New("a build asked later is already what the module is")
// ErrStillAssigned is why a module cannot be forgotten. // ErrStillAssigned is why a module cannot be forgotten.
// //
// Its own error because it is not a fault: it means a machine is running that module now, and // Its own error because it is not a fault: it means a machine is running that module now, and
@@ -51,10 +47,6 @@ type Source struct {
// itself no longer carries its build (novox/hq to-be 38 WP2.4). Empty for a manifest handed over // itself no longer carries its build (novox/hq to-be 38 WP2.4). Empty for a manifest handed over
// by hand, which carries its `build.on` itself. // by hand, which carries its `build.on` itself.
Against []string Against []string
// Asked is when the build this manifest came from was requested (novox/hq 04-ISSUES/219). Zero
// is a manifest handed over by hand, or a build whose request time is not known: either is
// taken as asked at the moment it is registered.
Asked time.Time
} }
// Current reports whether what the mesh holds is what the source last had. // Current reports whether what the mesh holds is what the source last had.
@@ -78,12 +70,11 @@ func (i *Inventory) RegisterModule(ctx context.Context, m catalogue.Manifest, fr
// (novox/hq ADR 0175, to-be 38 WP2.4): a module serving its tools from a container built on the // (novox/hq ADR 0175, to-be 38 WP2.4): a module serving its tools from a container built on the
// runtime's image. Refused at registration, by name, for a module that is new to the catalogue // runtime's image. Refused at registration, by name, for a module that is new to the catalogue
// or that was registered in another shape — the mechanism that keeps the old pattern from // or that was registered in another shape — the mechanism that keeps the old pattern from
// returning by habit. Before the runtime exists the pattern is accepted as it always was. // returning by habit. **Not refused for a module already registered in that shape**: the
// // catalogue holds some thirty of them the day the runtime arrives, each moves to a bundle in
// *Since 2026-10-04 (to-be 38 WP4b's last step):* refused for **every** module. While some // its own change (to-be 38 WP4 onward), and a gate that refused every rebuild of every unmoved
// thirty modules still stood in that shape, one already registered so was rebuilt without // module in the meantime would stop the whole pipeline to make a point the record already makes.
// complaint, so the pipeline kept running while each moved; every module has moved since, and // Before the runtime exists the pattern is accepted as it always was.
// the exception would only let one move back.
if m.Module != catalogue.RuntimeModule { if m.Module != catalogue.RuntimeModule {
if why := catalogue.ToolContainerOnTheRuntime(m, from.Against); why != "" { if why := catalogue.ToolContainerOnTheRuntime(m, from.Against); why != "" {
runtime, err := i.hasModule(ctx, catalogue.RuntimeModule) runtime, err := i.hasModule(ctx, catalogue.RuntimeModule)
@@ -91,7 +82,13 @@ func (i *Inventory) RegisterModule(ctx context.Context, m catalogue.Manifest, fr
return err return err
} }
if runtime { if runtime {
return fmt.Errorf("%s is not registered: %s", m.Module, why) already, err := i.registeredInThatShape(ctx, m.Module)
if err != nil {
return err
}
if !already {
return fmt.Errorf("%s is not registered: %s", m.Module, why)
}
} }
} }
} }
@@ -100,23 +97,13 @@ func (i *Inventory) RegisterModule(ctx context.Context, m catalogue.Manifest, fr
return err return err
} }
asked := from.Asked
if asked.IsZero() {
asked = time.Now()
}
// A module registered without provenance keeps whatever it had. Handing over a manifest by // A module registered without provenance keeps whatever it had. Handing over a manifest by
// hand is a legitimate way to fix something in a hurry, and it should not silently erase the // hand is a legitimate way to fix something in a hurry, and it should not silently erase the
// record of where the module normally comes from — which is the only thing that would say, // record of where the module normally comes from — which is the only thing that would say,
// afterwards, that the machine is running something nobody can rebuild. // afterwards, that the machine is running something nobody can rebuild.
// _, err = i.store.Pool().Exec(ctx,
// **An older request never replaces a newer one** (novox/hq 04-ISSUES/219). Builds of one `insert into module (name, manifest, version, source, source_path, source_seat, ref, built_from, source_head)
// module in flight together finish in any order, and each stood on the bases the mesh held when values ($1, $2, nullif($3,''), nullif($4,''), $7, $8, nullif($5,''), nullif($6,''), nullif($6,''))
// it was asked; the one asked later is what the module is, whichever is heard last. An outcome
// of an earlier request is kept in the build records and changes nothing here.
tag, err := i.store.Pool().Exec(ctx,
`insert into module (name, manifest, version, source, source_path, source_seat, ref, built_from, source_head, built_asked)
values ($1, $2, nullif($3,''), nullif($4,''), $7, $8, nullif($5,''), nullif($6,''), nullif($6,''), $9)
on conflict (name) do update set on conflict (name) do update set
manifest = excluded.manifest, manifest = excluded.manifest,
version = excluded.version, version = excluded.version,
@@ -128,23 +115,29 @@ func (i *Inventory) RegisterModule(ctx context.Context, m catalogue.Manifest, fr
else excluded.source_seat end, else excluded.source_seat end,
ref = coalesce(excluded.ref, module.ref), ref = coalesce(excluded.ref, module.ref),
built_from = coalesce(excluded.built_from, module.built_from), built_from = coalesce(excluded.built_from, module.built_from),
source_head = coalesce(excluded.built_from, module.source_head), source_head = coalesce(excluded.built_from, module.source_head)`,
built_asked = excluded.built_asked m.Module, raw, m.Version, from.Repository, from.Ref, from.BuiltFrom, from.Path, from.Seat)
where module.built_asked is null or module.built_asked <= excluded.built_asked`, return err
m.Module, raw, m.Version, from.Repository, from.Ref, from.BuiltFrom, from.Path, from.Seat, asked) }
// registeredInThatShape is whether the catalogue already holds this module as a tools container on
// the runtime's image — judged from the manifest it holds and what that module's newest build stood
// on, the same two things the gate judges a new registration by. False for a module the catalogue
// does not hold.
func (i *Inventory) registeredInThatShape(ctx context.Context, name string) (bool, error) {
held, err := i.Catalogue(ctx)
if err != nil { if err != nil {
return err return false, err
} }
if tag.RowsAffected() == 0 { stored, has := held[name]
var current time.Time if !has {
if err := i.store.Pool().QueryRow(ctx, return false, nil
`select built_asked from module where name = $1`, m.Module).Scan(&current); err != nil {
return err
}
return fmt.Errorf("%w: %s is at a build asked %s, and this one was asked %s",
ErrSuperseded, m.Module, current.UTC().Format(time.RFC3339), asked.UTC().Format(time.RFC3339))
} }
return nil against, err := i.BuiltAgainst(ctx)
if err != nil {
return false, err
}
return catalogue.ToolContainerOnTheRuntime(stored, against[name]) != "", nil
} }
// hasModule is whether the catalogue holds a module of that name. // hasModule is whether the catalogue holds a module of that name.
+8 -8
View File
@@ -688,9 +688,9 @@ func TestRegisteringWithoutProvenanceKeepsTheSeat(t *testing.T) {
// Once the node's tool runtime is in the catalogue, a module serving its tools from a container // Once the node's tool runtime is in the catalogue, a module serving its tools from a container
// built on the runtime's image is refused at registration, naming the record (novox/hq ADR 0175, // built on the runtime's image is refused at registration, naming the record (novox/hq ADR 0175,
// to-be 38 WP2.4) — for every module, since every module has moved (WP4b's last step; WP3's // to-be 38 WP2.4) — for a module new to the catalogue or one that had moved away from it; a module
// amendment let one already standing in that shape be rebuilt while each moved). Before the // already standing in that shape is rebuilt as before, so the catalogue's pipeline keeps running
// runtime, it is accepted as it always was — so a // while each moves (WP3's amendment). Before the runtime, it is accepted as it always was — so a
// mesh converts in the order the design says and nothing is refused before there is anything to // mesh converts in the order the design says and nothing is refused before there is anything to
// move to. // move to.
func TestAToolContainerIsRefusedOnceTheRuntimeIsRegistered(t *testing.T) { func TestAToolContainerIsRefusedOnceTheRuntimeIsRegistered(t *testing.T) {
@@ -715,11 +715,11 @@ func TestAToolContainerIsRefusedOnceTheRuntimeIsRegistered(t *testing.T) {
t.Fatal(err) t.Fatal(err)
} }
// **A module already registered in that shape is refused too** (WP4b's last step): every module // **A module already registered in that shape is rebuilt without complaint** (to-be 38 WP2.4 as
// has moved, and a rebuild in the old shape is one moving back. // amended by WP3): some thirty of them stand the day the runtime arrives, and each moves in its
if err := inv.RegisterModule(ctx, filter, Source{Repository: "/r", Against: stoodOn}); err == nil || // own change. The gate is against the pattern spreading, not against the pipeline running.
!strings.Contains(err.Error(), "ADR 0175") { if err := inv.RegisterModule(ctx, filter, Source{Repository: "/r", Against: stoodOn}); err != nil {
t.Fatalf("a rebuild of a module in the old pattern was registered beside the runtime: %v", err) t.Fatalf("a rebuild of a module that already had the pattern was refused: %v", err)
} }
// A module new to the catalogue in that shape is refused, naming the record. // A module new to the catalogue in that shape is refused, naming the record.
newcomer := filter newcomer := filter
-242
View File
@@ -1,242 +0,0 @@
package inventory
import (
"context"
"encoding/json"
"strings"
)
// What the artifact store keeps, and what it may let go (novox/hq ADR 0189, issue 108).
//
// The store has never collected anything: every build pushes another layer set and nothing has
// ever removed one. The registry's own answer — collect what no tag names — is wrong here, because
// the mesh pushes each artifact under one moving tag and pins machines by digest, so every build
// but the newest is untagged and some machine may still be running it.
//
// **So the mesh decides, from its own records, and it never has to look in the store to do it.**
// It has never put anything there it did not record, which means every digest it could remove is
// already in a build row. A digest the mesh did not record making is therefore never named here —
// not as a safety margin but as the rule restated, and it is what keeps the sweep away from the
// images genesis pushed before any record existed (04-ISSUES/102, F4).
// KeptBuilds is how many successful builds of each module keep their artifacts, counting the
// newest. The newest is what the mesh hands a machine now; the four behind it are how far back a
// release that turns out wrong can be taken.
const KeptBuilds = 5
// ToCollect is every artifact the mesh made, no longer keeps, and has not already collected.
//
// Three reasons an artifact stays, and nothing else is a reason:
//
// - **a definition names it** — the reference appears in a module's recorded manifest, which is
// what the mesh would hand a machine now. No age limit: this is the floor;
// - **the mesh can still go back to it** — it is an artifact of one of the KeptBuilds most
// recent successful builds of its module;
// - it was already collected, in which case there is nothing left to do.
//
// Returned in a stated order so two runs over the same records ask for the same things in the
// same sequence, which is what makes a failed sweep safe to simply run again.
func (i *Inventory) ToCollect(ctx context.Context) ([]string, error) {
keep, err := i.keptReferences(ctx)
if err != nil {
return nil, err
}
rows, err := i.store.Pool().Query(ctx,
// Every artifact of every successful build, oldest first, minus what has already been
// collected. A failed build published nothing, so it names nothing to remove.
`select b.made
from build b
where b.failed = '' and b.module is not null and b.module <> ''
order by b.at asc, b.id asc`)
if err != nil {
return nil, err
}
defer rows.Close()
collected, err := i.alreadyCollected(ctx)
if err != nil {
return nil, err
}
seen := map[string]bool{}
var out []string
for rows.Next() {
var raw []byte
if err := rows.Scan(&raw); err != nil {
return nil, err
}
var made []Artifact
if err := json.Unmarshal(raw, &made); err != nil {
// One unreadable record must not stop the rest being collected — and an artifact this
// row named is simply not offered, which errs toward keeping.
continue
}
for _, a := range made {
if a.Reference == "" || keep[a.Reference] || collected[a.Reference] || seen[a.Reference] {
continue
}
seen[a.Reference] = true
out = append(out, a.Reference)
}
}
return out, rows.Err()
}
// keptReferences is every artifact reference the mesh still keeps, for either of the two reasons.
func (i *Inventory) keptReferences(ctx context.Context) (map[string]bool, error) {
keep := map[string]bool{}
// **Whatever a definition the mesh holds names.** Read as text rather than by walking the
// resource shapes: a reference may be a container's image, a bundle's source, or a field some
// later kind of resource grows, and what matters is only whether the mesh could hand this
// string to a machine. A manifest that mentions it is a manifest that might.
manifests, err := i.store.Pool().Query(ctx, `select manifest::text from module where manifest is not null`)
if err != nil {
return nil, err
}
defer manifests.Close()
var named []string
for manifests.Next() {
var text string
if err := manifests.Scan(&text); err != nil {
return nil, err
}
named = append(named, text)
}
if err := manifests.Err(); err != nil {
return nil, err
}
// The KeptBuilds most recent successful builds of each module, whole.
recent, err := i.store.Pool().Query(ctx,
`select made from (
select made, row_number() over (partition by module order by at desc, id desc) as back
from build
where failed = '' and module is not null and module <> ''
) ranked where back <= $1`, KeptBuilds)
if err != nil {
return nil, err
}
defer recent.Close()
for recent.Next() {
var raw []byte
if err := recent.Scan(&raw); err != nil {
return nil, err
}
var made []Artifact
if err := json.Unmarshal(raw, &made); err != nil {
continue
}
for _, a := range made {
if a.Reference != "" {
keep[a.Reference] = true
}
}
}
if err := recent.Err(); err != nil {
return nil, err
}
// And anything a manifest mentions. Done after the recent set so the scan runs over the
// candidates rather than over every reference ever recorded: a manifest holds a reference
// composed with the store's address or kept bare, so the search is for the digest within it.
if len(named) > 0 {
all, err := i.everyReferenceMade(ctx)
if err != nil {
return nil, err
}
for _, reference := range all {
if keep[reference] {
continue
}
digest := digestIn(reference)
if digest == "" {
// Not something the store holds by digest; nothing here can speak for it, so it
// is kept rather than guessed about.
keep[reference] = true
continue
}
for _, text := range named {
if strings.Contains(text, digest) {
keep[reference] = true
break
}
}
}
}
return keep, nil
}
// everyReferenceMade is every artifact reference any successful build recorded.
func (i *Inventory) everyReferenceMade(ctx context.Context) ([]string, error) {
rows, err := i.store.Pool().Query(ctx,
`select made from build where failed = '' and module is not null and module <> ''`)
if err != nil {
return nil, err
}
defer rows.Close()
seen := map[string]bool{}
var out []string
for rows.Next() {
var raw []byte
if err := rows.Scan(&raw); err != nil {
return nil, err
}
var made []Artifact
if err := json.Unmarshal(raw, &made); err != nil {
continue
}
for _, a := range made {
if a.Reference == "" || seen[a.Reference] {
continue
}
seen[a.Reference] = true
out = append(out, a.Reference)
}
}
return out, rows.Err()
}
// digestIn is the `sha256:<hex>` a reference names, empty when it names none.
func digestIn(reference string) string {
for _, marker := range []string{"@sha256:", "/sha256:"} {
if _, after, ok := strings.Cut(reference, marker); ok {
return "sha256:" + after
}
}
return ""
}
// alreadyCollected is what the store has already been asked to let go.
func (i *Inventory) alreadyCollected(ctx context.Context) (map[string]bool, error) {
rows, err := i.store.Pool().Query(ctx, `select reference from artifact_collected`)
if err != nil {
return nil, err
}
defer rows.Close()
out := map[string]bool{}
for rows.Next() {
var reference string
if err := rows.Scan(&reference); err != nil {
return nil, err
}
out[reference] = true
}
return out, rows.Err()
}
// MarkCollected records that the store no longer holds these.
//
// **A store that answered "not found" is recorded too.** The outcome wanted is that the artifact
// is gone, and it is; retrying it every sweep for ever is the failure this table exists to
// prevent. Only a store that could not be reached, or refused, leaves a reference unmarked — and
// then the next sweep asks again, which is what should happen.
func (i *Inventory) MarkCollected(ctx context.Context, references []string) error {
for _, reference := range references {
if _, err := i.store.Pool().Exec(ctx,
`insert into artifact_collected (reference) values ($1) on conflict (reference) do nothing`,
reference); err != nil {
return err
}
}
return nil
}
-147
View File
@@ -1,147 +0,0 @@
package inventory
import (
"context"
"fmt"
"testing"
"github.com/novox/mesh-controller/internal/catalogue"
)
// What the store keeps, and what it may let go (novox/hq ADR 0189, issue 108).
//
// The store has collected nothing since it was raised, and the registry's own answer — collect
// what no tag names — would delete images machines are running, because the mesh pushes under one
// moving tag and pins by digest. So the rule is the mesh's, read from its own records, and these
// are the three reasons an artifact stays and the one reason it goes.
// ref is an artifact reference as the mesh records one.
func ref(module, artifact string, n int) string {
return fmt.Sprintf("%s%s/%s@sha256:%064x", catalogue.ArtifactStoreScheme, module, artifact, n)
}
// built records one successful build of a module publishing one image.
func built(t *testing.T, inv *Inventory, id, module string, n int) string {
t.Helper()
reference := ref(module, "app", n)
b := aBuild(id, module, "")
b.Made = []Artifact{{Name: "app", Kind: "image", Reference: reference}}
if err := inv.RecordBuild(context.Background(), b); err != nil {
t.Fatal(err)
}
return reference
}
func TestTheStoreKeepsTheRecentBuildsAndLetsGoOfTheRest(t *testing.T) {
inv := fresh(t)
ctx := context.Background()
// Eight builds of one module, oldest first. Five are kept — the newest, and the four a
// release that turns out wrong can be taken back to.
var made []string
for i := 1; i <= 8; i++ {
made = append(made, built(t, inv, fmt.Sprintf("b%02d", i), "web", i))
}
go_, err := inv.ToCollect(ctx)
if err != nil {
t.Fatal(err)
}
want := made[:3] // the three oldest
if len(go_) != len(want) {
t.Fatalf("offered %v to collect; want the %d oldest of %d", go_, len(want), len(made))
}
for i := range want {
if go_[i] != want[i] {
t.Fatalf("offered %v; want %v — and in that order, so a failed sweep is safe to run again",
go_, want)
}
}
}
func TestADefinitionNamingAnArtifactKeepsItHoweverOldItIs(t *testing.T) {
// The floor: no age limit. A module recorded at an older commit still names what the mesh
// would hand a machine now, and that is what must not be collected out from under it.
inv := fresh(t)
ctx := context.Background()
var made []string
for i := 1; i <= 8; i++ {
made = append(made, built(t, inv, fmt.Sprintf("b%02d", i), "web", i))
}
oldest := made[0]
// A definition the mesh holds, whose container runs that oldest image.
m := catalogue.Manifest{Module: "web", Version: "1", Resources: []map[string]any{{
"id": "app", "type": "container", "name": "web", "image": oldest,
}}}
if err := inv.RegisterModule(ctx, m, Source{Repository: "https://forge.invalid/web.git"}); err != nil {
t.Fatal(err)
}
go_, err := inv.ToCollect(ctx)
if err != nil {
t.Fatal(err)
}
for _, reference := range go_ {
if reference == oldest {
t.Fatalf("the mesh offered to collect %s, which a definition it holds names", oldest)
}
}
if len(go_) != 2 {
t.Fatalf("offered %v; want the two oldest that nothing names", go_)
}
}
func TestWhatHasBeenCollectedIsNotOfferedAgain(t *testing.T) {
// Without this the sweep reissues a delete for every artifact it has ever collected, every
// time it runs, for ever — a number of requests that grows with the mesh's whole history.
inv := fresh(t)
ctx := context.Background()
for i := 1; i <= 7; i++ {
built(t, inv, fmt.Sprintf("b%02d", i), "web", i)
}
first, err := inv.ToCollect(ctx)
if err != nil {
t.Fatal(err)
}
if len(first) != 2 {
t.Fatalf("offered %v, want two", first)
}
if err := inv.MarkCollected(ctx, first); err != nil {
t.Fatal(err)
}
again, err := inv.ToCollect(ctx)
if err != nil {
t.Fatal(err)
}
if len(again) != 0 {
t.Fatalf("offered %v again after collecting it", again)
}
}
func TestAFailedBuildNamesNothingToCollectAndEachModuleIsCountedOnItsOwn(t *testing.T) {
inv := fresh(t)
ctx := context.Background()
// A failed build published nothing, so it is neither kept nor collected — and it must not
// count against the module's five.
for i := 1; i <= 6; i++ {
built(t, inv, fmt.Sprintf("w%02d", i), "web", i)
}
if err := inv.RecordBuild(ctx, aBuild("w99", "web", "the recipe would not build")); err != nil {
t.Fatal(err)
}
// And a second module with three builds keeps all three: five each, not five between them.
for i := 1; i <= 3; i++ {
built(t, inv, fmt.Sprintf("d%02d", i), "db", 100+i)
}
go_, err := inv.ToCollect(ctx)
if err != nil {
t.Fatal(err)
}
if len(go_) != 1 || go_[0] != ref("web", "app", 1) {
t.Fatalf("offered %v; want only web's oldest — db's three are all within its five", go_)
}
}
-20
View File
@@ -100,23 +100,3 @@ func TestABundleStandsOnTheToolchainItIsCompiledIn(t *testing.T) {
} }
} }
} }
// novox/hq 04-ISSUES/212: a toolchain standing on the SDK's package is planned after the SDK, so a
// release of the SDK rebuilds the toolchain, and every bundle compiled in it after that.
func TestAToolchainStandingOnTheSDKFollowsIt(t *testing.T) {
entries := []Entry{
{Manifest: catalogue.Manifest{Module: "mesh-sdk"}},
{Manifest: catalogue.Manifest{Module: "mesh-tools", Build: &catalogue.Build{
On: []catalogue.BuildsOn{{Arg: "MESH_SDK", Module: "mesh-sdk", Artifact: "lib"}}}}},
}
edges := dependenciesOf(entries, nil, nil)
found := false
for _, e := range edges {
if e.From == "mesh-tools" && e.To == "mesh-sdk" {
found = true
}
}
if !found {
t.Errorf("no edge from the toolchain to the SDK: %v", edges)
}
}
-32
View File
@@ -1,32 +0,0 @@
package inventory
import (
"testing"
"github.com/novox/mesh-controller/internal/broker"
"github.com/novox/mesh-controller/internal/catalogue"
)
// novox/hq issue 218: a seat held once for the mesh is granted and issued only to the holder on record;
// a node seat to every machine's claimant; a mesh seat with no holder on record as derived.
func TestOnlyTheRecordedHolderHoldsAMeshSeat(t *testing.T) {
claimed := []broker.Seat{
{Name: "mesh-store", Scope: catalogue.ScopeMesh},
{Name: "node-packet-filter", Scope: catalogue.ScopeNode},
{Name: "unrecorded", Scope: catalogue.ScopeMesh},
}
holdings := []catalogue.Held{{Claim: "mesh-store", Scope: catalogue.ScopeMesh, Node: "control", Module: "postgres"}}
names := func(ss []broker.Seat) (out []string) {
for _, s := range ss {
out = append(out, s.Name)
}
return
}
if got := names(heldHere(claimed, holdings, "control", "postgres")); len(got) != 3 {
t.Errorf("the holder lost a seat: %v", got)
}
got := names(heldHere(claimed, holdings, "other", "postgres"))
if len(got) != 2 || got[0] != "node-packet-filter" || got[1] != "unrecorded" {
t.Errorf("a claimant on another machine holds %v; want the node seat and the unrecorded one, not the store", got)
}
}
-59
View File
@@ -87,62 +87,3 @@ func (i *Inventory) tryHold(ctx context.Context, sorted []string) (func(), strin
} }
return release, "", nil return release, "", nil
} }
// ErrPlansBusy is the plans held by another act — on a machine replacing its controller, the other
// controller — for longer than a caller waits, or at all for one that does not wait.
var ErrPlansBusy = errors.New("another controller is working the plans")
// HoldPlans makes working the plans one act at a time, across every controller on the store
// (novox/hq issue 213). A plan is read, changed and written whole; two controllers doing that at
// once — the old and the new for the moment a machine hands its controller over, or a controller
// and a person's `plans stop` — each act on what the other has not saved yet: a tier asked twice,
// an outcome written over. A session-level advisory lock on one connection, released by the
// returned function and by the session ending, so a controller that dies holding it holds nothing.
//
// wait false gives ErrPlansBusy at once when another holds them — the timer's way: the holder is
// moving the plans already. wait true looks again every HoldPoll for up to HoldWaitFor — an
// outcome's or a merge's way, which must be written.
func (i *Inventory) HoldPlans(ctx context.Context, wait bool) (func(), error) {
deadline := time.Now().Add(HoldWaitFor)
for {
release, took, err := i.tryLock(ctx, "mesh-plans")
if err != nil || took {
return release, err
}
if !wait || time.Now().After(deadline) {
return nil, ErrPlansBusy
}
select {
case <-ctx.Done():
return nil, ctx.Err()
case <-time.After(HoldPoll):
}
}
}
// tryLock takes one named advisory lock on a connection of its own, or gives the connection back.
func (i *Inventory) tryLock(ctx context.Context, key string) (func(), bool, error) {
conn, err := i.store.Pool().Acquire(ctx)
if err != nil {
return nil, false, err
}
var once sync.Once
release := func() {
once.Do(func() {
if _, err := conn.Exec(context.WithoutCancel(ctx), `select pg_advisory_unlock_all()`); err != nil {
_ = conn.Conn().Close(context.WithoutCancel(ctx))
}
conn.Release()
})
}
var took bool
if err := conn.QueryRow(ctx, `select pg_try_advisory_lock(hashtext($1)::bigint)`, key).Scan(&took); err != nil {
release()
return nil, false, err
}
if !took {
release()
return nil, false, nil
}
return release, true, nil
}
-38
View File
@@ -1,38 +0,0 @@
package inventory
import (
"errors"
"testing"
"time"
)
// novox/hq issue 213: while a machine hands its controller over from the container to the process,
// two controllers run on one store for a moment. Working the plans is one act at a time across them.
func TestThePlansAreWorkedByOneControllerAtATime(t *testing.T) {
first := ForTest(t)
// A second controller: its own connections to the same store.
second, err := Open(t.Context())
if err != nil {
t.Fatal(err)
}
t.Cleanup(second.Close)
release, err := first.HoldPlans(t.Context(), false)
if err != nil {
t.Fatalf("the plans could not be held when nobody held them: %v", err)
}
t.Cleanup(release) // a pool closing waits for a connection still held; release is idempotent
if _, err := second.HoldPlans(t.Context(), false); !errors.Is(err, ErrPlansBusy) {
t.Fatalf("a second controller held the plans while the first did: %v", err)
}
// A waiter gets them once they are let go.
was := HoldPoll
HoldPoll = 10 * time.Millisecond
defer func() { HoldPoll = was }()
go func() { time.Sleep(50 * time.Millisecond); release() }()
again, err := second.HoldPlans(t.Context(), true)
if err != nil {
t.Fatalf("a waiting controller never got the plans once they were let go: %v", err)
}
again()
}
@@ -1,23 +0,0 @@
-- A build is ordered by when it was asked, not when it finished (novox/hq 04-ISSUES/219).
--
-- Two builds of one module can be in flight together — two merge plans a few minutes apart, each
-- asking for everything standing on what it changed — and they finish in any order. Each build
-- stands on the bases the mesh held when it was *asked*, so the one asked later is the newer one.
-- The mesh ordered builds by `at`, which is when the outcome was recorded, and registered whatever
-- it heard last: an older request that took longer replaced a newer one as what the module is, and
-- the next push sent machines an image built on a base the mesh had already replaced.
--
-- `build.asked` is when the build was requested, read from the correlation id the controller wrote
-- (`build-<unix nanoseconds>`). Nullable: an id of any other shape says no request time, and such a
-- build is placed where it was recorded, which is the order the mesh had before this.
alter table build add column asked timestamptz;
update build
set asked = to_timestamp((substring(id from '^build-([0-9]{19})$'))::numeric / 1000000000)
where id ~ '^build-[0-9]{19}$';
-- `module.built_asked` is when the build the module's registered manifest came from was asked, so
-- a later-heard outcome of an earlier request is recorded and not registered. A manifest handed over
-- by hand is a request made when it is handed over. Null for a module registered before this was
-- kept: its next registration, whichever it is, sets it.
alter table module add column built_asked timestamptz;
@@ -1,23 +0,0 @@
-- What the artifact store no longer keeps (novox/hq ADR 0189, issue 108).
--
-- The mesh removes from its store only what it put there and can account for: every digest it
-- could remove is already in a build record, so the sweep reads its own records rather than
-- enumerating the store. What it does not get from those records is whether it has already
-- removed something -- `build.made` says what that build published, for ever, which is history
-- and not an index of what is on disk.
--
-- Without this the sweep would reissue a delete for every artifact it has ever collected, every
-- time it runs, and each one would answer 404 -- a number of requests that grows with the mesh's
-- whole history and never shrinks.
--
-- Keyed by the reference as the mesh records it (`artifact-store://<module>/<artifact>@sha256:…`),
-- because that is the identity the record uses everywhere else. Not a foreign key to build: two
-- builds can publish the same digest (the same source built twice produces the same bytes), and
-- what is collected is the artifact, not the attempt that made it.
create table artifact_collected (
reference text primary key,
-- When the store answered. Kept so a reader of an old build record can tell "this artifact is
-- gone" from "this artifact was never there", which are different kinds of surprise.
at timestamptz not null default now()
);
-124
View File
@@ -1,124 +0,0 @@
package inventory
import (
"context"
"errors"
"testing"
"time"
"github.com/novox/mesh-controller/internal/catalogue"
)
// novox/hq 04-ISSUES/219: two builds of one module in flight together, the one asked first heard
// last. The newer request stood on the newer base; the older one's late outcome is recorded and is
// not what the module is.
func postgresBuild(id string, asked time.Time, image string) Build {
b := aBuild(id, "postgres", "")
b.Asked = asked
b.Against = []string{"mesh-tools/runtime@sha256:" + id}
b.Made = []Artifact{{Name: "server", Kind: "image", Reference: "postgres@sha256:" + image}}
return b
}
func TestAnOlderRequestFinishingLaterIsNotWhatTheModuleHolds(t *testing.T) {
inv := fresh(t)
ctx := context.Background()
older := time.Date(2026, 10, 3, 21, 33, 45, 0, time.UTC)
newer := time.Date(2026, 10, 3, 21, 51, 57, 0, time.UTC)
// The newer request finishes first, the older one last — recorded in that order.
if err := inv.RecordBuild(ctx, postgresBuild("newer", newer, "4bcd5f73")); err != nil {
t.Fatal(err)
}
if err := inv.RecordBuild(ctx, postgresBuild("older", older, "0ab07fa9")); err != nil {
t.Fatal(err)
}
held, err := inv.Held(ctx)
if err != nil {
t.Fatal(err)
}
if got := held["postgres/server"]; got != "postgres@sha256:4bcd5f73" {
t.Errorf("postgres holds %q; want the newer request's image 4bcd5f73", got)
}
against, err := inv.BuiltAgainst(ctx)
if err != nil {
t.Fatal(err)
}
if got := against["postgres"]; len(got) != 1 || got[0] != "mesh-tools/runtime@sha256:newer" {
t.Errorf("postgres stands on %v; want what the newer request stood on", got)
}
// Both are still recorded, the late one first as what happened lately.
builds, err := inv.Builds(ctx, "postgres", 5)
if err != nil {
t.Fatal(err)
}
if len(builds) != 2 || builds[0].ID != "older" || !builds[0].Asked.Equal(older) {
t.Fatalf("both builds, newest heard first, with when they were asked: %+v", builds)
}
}
func TestABuildWithNoKnownRequestTimeIsOrderedByWhenItWasRecorded(t *testing.T) {
// What the mesh did before it kept the request time, so a row from before still answers.
inv := fresh(t)
ctx := context.Background()
for _, id := range []string{"first", "second"} {
b := aBuild(id, "shell", "")
b.Made = []Artifact{{Name: "config", Kind: "archive", Reference: "…/" + id}}
if err := inv.RecordBuild(ctx, b); err != nil {
t.Fatal(err)
}
}
held, err := inv.Held(ctx)
if err != nil {
t.Fatal(err)
}
if got := held["shell/config"]; got != "…/second" {
t.Errorf("shell holds %q; want the one recorded last", got)
}
}
func TestARegistrationFromAnOlderRequestDoesNotReplaceANewerOne(t *testing.T) {
inv := fresh(t)
ctx := context.Background()
older := time.Date(2026, 10, 3, 21, 33, 45, 0, time.UTC)
newer := time.Date(2026, 10, 3, 21, 51, 57, 0, time.UTC)
from := func(asked time.Time) Source {
return Source{Repository: "novox/mesh-catalog", Seat: "git", Path: "modules/postgres",
BuiltFrom: "efff5415", Asked: asked}
}
if err := inv.RegisterModule(ctx, catalogue.Manifest{Module: "postgres", Version: "fixed"}, from(newer)); err != nil {
t.Fatal(err)
}
err := inv.RegisterModule(ctx, catalogue.Manifest{Module: "postgres", Version: "stale"}, from(older))
if !errors.Is(err, ErrSuperseded) {
t.Fatalf("an older request's registration was not refused as superseded: %v", err)
}
shelf, err := inv.Catalogue(ctx)
if err != nil {
t.Fatal(err)
}
if got := shelf["postgres"].Version; got != "fixed" {
t.Fatalf("postgres is %q; want the newer request's manifest", got)
}
// A later request, and a manifest handed over by hand — asked when it is handed over — both
// replace it as before.
if err := inv.RegisterModule(ctx, catalogue.Manifest{Module: "postgres", Version: "later"},
from(newer.Add(time.Minute))); err != nil {
t.Fatal(err)
}
if err := inv.RegisterModule(ctx, catalogue.Manifest{Module: "postgres", Version: "by-hand"}, Source{}); err != nil {
t.Fatal(err)
}
if shelf, _ := inv.Catalogue(ctx); shelf["postgres"].Version != "by-hand" {
t.Fatalf("postgres is %q; want the manifest handed over by hand", shelf["postgres"].Version)
}
src, err := inv.SourceOf(ctx, "postgres")
if err != nil || src.Repository != "novox/mesh-catalog" {
t.Fatalf("a hand registration erased the provenance: %+v %v", src, err)
}
}
-29
View File
@@ -2,9 +2,6 @@ package link
import ( import (
"encoding/json" "encoding/json"
"strconv"
"strings"
"time"
) )
// Asking a machine to build a module, and hearing what came out. // Asking a machine to build a module, and hearing what came out.
@@ -20,32 +17,6 @@ import (
// holds no opinion about what they contain, and a host that also built things would be a host // holds no opinion about what they contain, and a host that also built things would be a host
// with a container runtime requirement and a git dependency (novox/hq ADR 0005). // with a container runtime requirement and a git dependency (novox/hq ADR 0005).
// NewBuildID is the correlation for a build asked at that moment: `build-<unix nanoseconds>`.
//
// **The id carries when the build was asked, and that is read back** (novox/hq 04-ISSUES/219). Builds
// of one module can be in flight together and finish in any order; what a module currently is must
// be the newest *request's* outcome, not the last one heard, and the id is the one thing every
// outcome echoes whichever builder answered it. One place writes the shape and one reads it.
func NewBuildID(asked time.Time) string {
return "build-" + strconv.FormatInt(asked.UnixNano(), 10)
}
// BuildAskedAt is when the build with this id was asked, as NewBuildID wrote it. False for an id
// of any other shape — one written before this was read, or by hand — whose request time the mesh
// does not know.
func BuildAskedAt(id string) (time.Time, bool) {
digits, ok := strings.CutPrefix(id, "build-")
if !ok || digits == "" {
return time.Time{}, false
}
nanos, err := strconv.ParseInt(digits, 10, 64)
// A number too small to be a moment this mesh could have asked at is a name, not a time.
if err != nil || nanos < time.Date(2020, 1, 1, 0, 0, 0, 0, time.UTC).UnixNano() {
return time.Time{}, false
}
return time.Unix(0, nanos).UTC(), true
}
// BuildRequest is one module to build. // BuildRequest is one module to build.
type BuildRequest struct { type BuildRequest struct {
// ID correlates the answer with the asking. Not the module name: two builds of one module can // ID correlates the answer with the asking. Not the module name: two builds of one module can
+2 -54
View File
@@ -5,7 +5,6 @@ import (
"encoding/json" "encoding/json"
"errors" "errors"
"fmt" "fmt"
"log"
"strings" "strings"
"time" "time"
@@ -79,15 +78,10 @@ func (n *natsInbound) Receive(ctx context.Context, act func(context.Context, Con
// than creating one here: the consumer is an object with a configuration — ack policy, ack // than creating one here: the consumer is an object with a configuration — ack policy, ack
// wait, redelivery — and a client that creates its own would be a second opinion about it. // wait, redelivery — and a client that creates its own would be a second opinion about it.
control := make(chan *nats.Msg, Prefetch) control := make(chan *nats.Msg, Prefetch)
said, err := standingBy(ctx, log.Default(), "CONTROL", func() (*nats.Subscription, error) { said, err := js.ChanSubscribe("", control, nats.Bind("CONTROL", broker.ControllerName))
return js.ChanSubscribe("", control, nats.Bind("CONTROL", broker.ControllerName))
})
if err != nil { if err != nil {
return fmt.Errorf("subscribing to what nodes say: %w", err) return fmt.Errorf("subscribing to what nodes say: %w", err)
} }
if said == nil {
return nil // stopped while standing by
}
defer func() { _ = said.Unsubscribe() }() defer func() { _ = said.Unsubscribe() }()
// Heartbeats, on core NATS and off any stream (design 25 §3). Their own subscription because // Heartbeats, on core NATS and off any stream (design 25 §3). Their own subscription because
@@ -103,15 +97,10 @@ func (n *natsInbound) Receive(ctx context.Context, act func(context.Context, Con
var events chan *nats.Msg var events chan *nats.Msg
if len(n.follows) > 0 { if len(n.follows) > 0 {
events = make(chan *nats.Msg, Prefetch) events = make(chan *nats.Msg, Prefetch)
followed, err := standingBy(ctx, log.Default(), "EVENTS", func() (*nats.Subscription, error) { followed, err := js.ChanSubscribe("", events, nats.Bind("EVENTS", broker.ControllerName))
return js.ChanSubscribe("", events, nats.Bind("EVENTS", broker.ControllerName))
})
if err != nil { if err != nil {
return fmt.Errorf("subscribing to what the catalogue says: %w", err) return fmt.Errorf("subscribing to what the catalogue says: %w", err)
} }
if followed == nil {
return nil
}
defer func() { _ = followed.Unsubscribe() }() defer func() { _ = followed.Unsubscribe() }()
} }
@@ -335,44 +324,3 @@ func (m *natsControl) forget() {
type replyAddressed struct { type replyAddressed struct {
ReplyTo string `json:"reply_to,omitempty"` ReplyTo string `json:"reply_to,omitempty"`
} }
// StandbyPoll is how often a controller standing by looks again for its consumers. A variable so a
// test need not wait.
var StandbyPoll = 2 * time.Second
// standingBy binds one of the controller's consumers, waiting while another controller holds it.
//
// **Two controllers, one consumer** (novox/hq issue 213). The controller's consumers are push
// consumers with no delivery group, so the server lets one subscription bind each — on purpose:
// two would each act on every message (issue 146). When a machine hands its controller over from
// the container to the process, the host starts the process first and removes the container only
// once the process is up; the process then finds the consumers bound. Exiting on that would never
// be up, so the container would never go. It stands by instead — the seat's verbs are already
// served from a queue group, and the plans wait on their lock — and binds as soon as the other lets
// go. Nil and no error is ctx ending while it waited.
func standingBy(ctx context.Context, logger interface{ Printf(string, ...any) }, stream string,
bind func() (*nats.Subscription, error)) (*nats.Subscription, error) {
said := false
for {
sub, err := bind()
if err == nil {
if said {
logger.Printf("took the controller's consumer on %s: the controller that held it let go", stream)
}
return sub, nil
}
if !strings.Contains(err.Error(), "already bound") {
return nil, err
}
if !said {
logger.Printf("another controller holds the controller's consumer on %s; standing by "+
"until it lets go", stream)
said = true
}
select {
case <-ctx.Done():
return nil, nil
case <-time.After(StandbyPoll):
}
}
}
-69
View File
@@ -1,69 +0,0 @@
package link
import (
"context"
"encoding/json"
"os"
"testing"
"time"
"github.com/novox/mesh-controller/internal/broker"
)
// novox/hq issue 213: while a machine hands its controller over, the new controller (the process)
// is started while the old one (the container) still holds the controller's consumers. It must not
// exit — the host would read that as a replacement that did not come up and never remove the
// container — and must not act on what the old one is handed. It stands by, and takes the consumers
// when the old one lets go.
func TestNatsASecondControllerStandsByAndTakesOverWhenTheFirstLetsGo(t *testing.T) {
js := aBus(t)
was := StandbyPoll
StandbyPoll = 50 * time.Millisecond
defer func() { StandbyPoll = was }()
old := &counted{}
_, stopOld := servingOn(t, js, old)
eventually(t, "the first controller binding its consumer", func() bool {
info, err := js.Context().ConsumerInfo("CONTROL", broker.ControllerName)
return err == nil && info.PushBound
})
// The new one, on a connection of its own as the process would have.
second, err := broker.Dial(os.Getenv("MESH_TEST_NATS"))
if err != nil {
t.Fatal(err)
}
t.Cleanup(second.Close)
fresh := &counted{}
s := &Server{inbound: Nats(second), bus: OverNATS{Conn: second.Conn(), JS: second.Context()},
listener: fresh, log: quiet()}
ctx, stopNew := context.WithCancel(context.Background())
defer stopNew()
ended := make(chan error, 1)
go func() { ended <- s.Serve(ctx) }()
select {
case err := <-ended:
t.Fatalf("the second controller stopped instead of standing by: %v", err)
case <-time.After(500 * time.Millisecond):
}
report := func(declared string) {
body, _ := json.Marshal(Report{Node: "anchor", Declared: declared, Applied: []string{"store"}})
if _, err := js.Context().Publish(ReportSubject("anchor"), body); err != nil {
t.Fatal(err)
}
}
report("d1")
eventually(t, "the holding controller hearing the report", func() bool { return old.count() == 1 })
if fresh.count() != 0 {
t.Fatal("the controller standing by acted on a report the holder was handed")
}
stopOld()
report("d2")
eventually(t, "the second controller taking over once the first let go", func() bool { return fresh.count() == 1 })
if old.count() != 1 {
t.Errorf("the first controller heard %d reports", old.count())
}
}
+1 -1
View File
@@ -30,7 +30,7 @@ func TestTheManifestsOwnPlaceholderUnfilledLeavesTheStoreWhereTheFileSays(t *tes
} }
var written string var written string
for _, r := range m.Resources { for _, r := range m.Resources {
if r.Type == "process" { if r.Type == "container" {
written = r.Env["MESH_STORE_INVENTORY_PORT"] written = r.Env["MESH_STORE_INVENTORY_PORT"]
} }
} }
+38 -31
View File
@@ -2,6 +2,9 @@
"module": "mesh-controller", "module": "mesh-controller",
"version": "1", "version": "1",
"slug": "control", "slug": "control",
"capabilities": [
"container-runtime"
],
"claims": [ "claims": [
{ {
"name": "mesh-controller", "name": "mesh-controller",
@@ -23,7 +26,7 @@
"broker-address": "${dir:mesh-state}/broker-address", "broker-address": "${dir:mesh-state}/broker-address",
"bus": "${dir:mesh-state}/bus" "bus": "${dir:mesh-state}/bus"
}, },
"secrets-owner": "mesh-controller", "secrets-owner": "65534:65534",
"prepares": true, "prepares": true,
"tools": [ "tools": [
"tools", "tools",
@@ -40,58 +43,62 @@
"build" "build"
], ],
"resources": [ "resources": [
{
"id": "account",
"type": "user",
"name": "mesh-controller",
"shell": "/usr/bin/nologin",
"home": "/var/lib/mesh-controller"
},
{ {
"id": "mesh-state", "id": "mesh-state",
"type": "directory", "type": "directory",
"mode": "0700", "mode": "0700",
"place": "mesh", "place": "mesh"
"owner": "mesh-controller"
}, },
{ {
"id": "controller", "id": "server",
"type": "process", "type": "container",
"name": "mesh-controller", "name": "mesh-controller",
"artifact": "controller", "network": "host",
"run": [ "args": [
"./mesh-controller",
"serve" "serve"
], ],
"user": "mesh-controller",
"env": { "env": {
"MESH_BROKER_CERTIFICATE": "/var/lib/mesh-broker-tls/tls.crt", "MESH_BROKER_CERTIFICATE": "/broker-tls/tls.crt",
"MESH_STORE_INVENTORY_FILE": "${dir:mesh-state}/inventory", "MESH_STORE_INVENTORY_FILE": "/run/secrets/inventory",
"MESH_STORE_IDENTITY_FILE": "${dir:mesh-state}/identity", "MESH_STORE_IDENTITY_FILE": "/run/secrets/identity",
"MESH_STORE_LICENCES_FILE": "${dir:mesh-state}/licences", "MESH_STORE_LICENCES_FILE": "/run/secrets/licences",
"MESH_BROKER_MANAGEMENT_FILE": "${dir:mesh-state}/broker-management", "MESH_BROKER_MANAGEMENT_FILE": "/run/secrets/broker-management",
"MESH_BROKER_ADDRESS_FILE": "${dir:mesh-state}/broker-address", "MESH_BROKER_ADDRESS_FILE": "/run/secrets/broker-address",
"MESH_STORE_INVENTORY_PORT": "${seat:mesh-store:5432}", "MESH_STORE_INVENTORY_PORT": "${seat:mesh-store:5432}",
"MESH_STORE_IDENTITY_PORT": "${seat:mesh-store:5432}", "MESH_STORE_IDENTITY_PORT": "${seat:mesh-store:5432}",
"MESH_STORE_LICENCES_PORT": "${seat:mesh-store:5432}", "MESH_STORE_LICENCES_PORT": "${seat:mesh-store:5432}",
"MESH_BROKER_MANAGEMENT_PORT": "${seat:mesh-broker:15672}", "MESH_BROKER_MANAGEMENT_PORT": "${seat:mesh-broker:15672}",
"MESH_BROKER_ADDRESS_PORT": "${seat:mesh-broker:5671}", "MESH_BROKER_ADDRESS_PORT": "${seat:mesh-broker:5671}",
"MESH_BUS_NATS_FILE": "${dir:mesh-state}/bus" "MESH_BUS_NATS_FILE": "/run/secrets/bus"
}, },
"replaces": [ "volumes": [
"server" "/var/lib/mesh-broker-tls:/broker-tls:ro",
"${dir:mesh-state}/inventory:/run/secrets/inventory:ro",
"${dir:mesh-state}/identity:/run/secrets/identity:ro",
"${dir:mesh-state}/licences:/run/secrets/licences:ro",
"${dir:mesh-state}/broker:/run/secrets/broker:ro",
"${dir:mesh-state}/bus:/run/secrets/bus:ro",
"${dir:mesh-state}/broker-management:/run/secrets/broker-management:ro",
"${dir:mesh-state}/broker-address:/run/secrets/broker-address:ro"
],
"artifact": "server",
"restart-on": [
"control-env"
] ]
} }
], ],
"build": { "build": {
"artifacts": [ "artifacts": [
{ {
"name": "controller", "name": "server",
"kind": "bundle", "kind": "image",
"language": "go", "from": "Dockerfile"
"system": "arch", }
"from": "cmd/mesh-controller", ],
"binary": "mesh-controller" "on": [
{
"arg": "GO_BASE",
"image": "golang@sha256:8ac98ca534ac3f51e1f420a1dd2c15e74c75cfa0f23f3ad27eb5d7236c349a0c"
} }
] ]
} }