An older build request never replaces a newer one's artifact

Builds of one module in flight together finish in any order, and the mesh
took whatever it heard last as what the module is: RegisterModule overwrote
the module's manifest unconditionally, and Held/BuiltAgainst/ReadRepositories
ordered builds by when they were recorded. A postgres build asked before the
mesh-tools runtime fix finished after the one asked after it, and the next
push deployed the stale image (novox/hq issue 219).

A build is now ordered by when it was asked, read from the build-<nanos> id
the controller writes: build.asked and module.built_asked (migration 0055).
A registration from an earlier request than the module's current one is
recorded and refused as superseded. A plan takes as its outcome only a build
asked at or after its own ask, so an earlier plan's leftover build cannot
settle a later plan. Ids of any other shape keep the old order.
This commit is contained in:
jochen
2026-10-04 00:22:11 +02:00
parent c0c3c3fed4
commit 9745c1ab31
10 changed files with 375 additions and 27 deletions
+14 -2
View File
@@ -148,6 +148,11 @@ func buildFrom(result link.BuildResult) inventory.Build {
// rebuild the graph rather than a list of names.
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 {
kept.Against = append(kept.Against, catalogue.Recorded(ref))
}
@@ -409,7 +414,7 @@ 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
// module can be in flight, and the second answer is not the first one's.
request := link.BuildRequest{
ID: fmt.Sprintf("%s-%d", "build", time.Now().UnixNano()),
ID: link.NewBuildID(time.Now()),
Repository: repository,
Path: path,
Ref: ref,
@@ -526,6 +531,9 @@ func takeIn(ctx context.Context, inv *inventory.Inventory, result link.BuildResu
BuiltFrom: result.Commit, Head: result.Commit,
// What it stood on, so registration can judge a built manifest's base (to-be 38 WP2.4).
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 != "" {
recorded.Repository, recorded.Seat = result.Source.Repository, result.Source.Seat
@@ -544,6 +552,10 @@ func takeIn(ctx context.Context, inv *inventory.Inventory, result link.BuildResu
result.On, result.Repository, short(result.Commit), err)
}
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, nil
@@ -573,7 +585,7 @@ func buildAndShow(ctx context.Context, source buildSource, path, ref string, wai
defer ask.Close()
result, err := ask.Submit(ctx, link.BuildRequest{
ID: fmt.Sprintf("%s-%d", "build", time.Now().UnixNano()),
ID: link.NewBuildID(time.Now()),
Repository: repository, Path: path, Ref: ref,
Held: heldBy(ctx), Seats: seatBases(ctx),
}, wait)
+50
View File
@@ -2,9 +2,12 @@ package main
import (
"encoding/json"
"errors"
"strings"
"testing"
"time"
"github.com/novox/mesh-controller/internal/inventory"
"github.com/novox/mesh-controller/internal/link"
)
@@ -100,3 +103,50 @@ func TestABuildAtACommitKeepsTheBranchTheModuleFollows(t *testing.T) {
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)
}
}
}
+13 -3
View File
@@ -8,6 +8,7 @@ package main
import (
"context"
"errors"
"flag"
"fmt"
"os"
@@ -253,25 +254,34 @@ func parseAround(set *flag.FlagSet, args []string) ([]string, error) {
// became of a build nobody was watching.
func (b builds) Built(ctx context.Context, result link.BuildResult) error {
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 {
case err != nil && result.Failed != "":
fmt.Printf("%s: %v\n", result.ID, err)
if result.Module != "" {
planBuilt(ctx, b.open, result.Module, result.Commit, result.Failed)
planBuilt(ctx, b.open, result.Module, result.Commit, result.Failed, asked)
} else {
planFailedBuild(ctx, b.open, result)
}
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:
fmt.Printf("%s: heard and recorded, and not registered: %v\n", result.ID, err)
if manifest.Module != "" {
planBuilt(ctx, b.open, manifest.Module, result.Commit, err.Error())
planBuilt(ctx, b.open, manifest.Module, result.Commit, err.Error(), asked)
}
return nil
}
fmt.Printf("%s: %s %s registered, built on %s from %s\n",
result.ID, manifest.Module, manifest.Version, result.On, short(result.Commit))
saysWhenThePolicyActs(ctx, b.inv, manifest.Module)
planBuilt(ctx, b.open, manifest.Module, result.Commit, "")
planBuilt(ctx, b.open, manifest.Module, result.Commit, "", asked)
return nil
}
+23 -2
View File
@@ -288,7 +288,13 @@ 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
// 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
plans, err := inv.OpenPlans(ctx)
if err != nil {
@@ -315,6 +321,9 @@ func planBuilt(ctx context.Context, open *stores, module, commit, failed string)
state = &inventory.PlanModule{}
p.Modules[module] = state
}
if askedBefore(asked, state.AskedAt) {
continue
}
if failed != "" {
state.State = "failed"
state.Why = failed
@@ -549,7 +558,8 @@ func planFailedBuild(ctx context.Context, open *stores, result link.BuildResult)
}
for _, e := range entries {
if repositoryMatches(e.Source.Repository, result.Repository) && e.Source.Path == result.Path {
planBuilt(ctx, open, e.Manifest.Module, result.Commit, result.Failed)
asked, _ := link.BuildAskedAt(result.ID)
planBuilt(ctx, open, e.Manifest.Module, result.Commit, result.Failed, asked)
return
}
}
@@ -791,6 +801,11 @@ func settleFromRecords(p *inventory.Plan, tier []string, recorded map[string][]i
if b.At.Before(*s.AskedAt) {
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
}
if outcome == nil {
@@ -812,3 +827,9 @@ func settleFromRecords(p *inventory.Plan, tier []string, recorded map[string][]i
}
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
@@ -155,6 +155,24 @@ func TestAPlanSettlesAnAskedBuildFromTheRecords(t *testing.T) {
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.
q := inventory.Plan{ID: "plan-2", Tiers: [][]string{{"x"}},
Modules: map[string]*inventory.PlanModule{"x": {State: "asked", AskedAt: &asked}}}