novox/mesh-delivery
19
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Publish a merged candidate's image once; a retaken key builds only what is missing (review r1)

Browse Source
This commit is contained in:
jschoubben
2026-10-22 10:33:52 +02:00
parent bbc690539b
commit 12f61998c5
4 changed files with 191 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/mesh-delivery-builder/internal/build/claim.go
+20
View File
@@ -66,6 +66,23 @@ type ClaimOptions struct {
// ImageBuilder says whether a node runs a healthy image build module now: a key failed for NoImageBuilderPrefix is taken
// again only then. Nil means none does.
ImageBuilder func() bool
// Trunk is whether the trunk's record names this fingerprint. A done key whose image has no reference was built as a
// candidate's, which never pushes (ADR 0487 clause 12); on the trunk it is taken again to publish the image, when an image
// builder runs (ImageBuilder).
Trunk bool
}
// Unpublished is whether a done build holds an image built without a push: it has no reference.
func Unpublished(b delivery.BuilderBuild) bool {
if b.State != delivery.BuildDone {
return false
}
for _, a := range b.Artifacts {
if a.Kind == "image" && a.Reference == "" {
return true
}
}
return false
}
// Claim takes the build of module at fingerprint, or answers nil when it is not this builder's to build now:
@@ -101,6 +118,9 @@ func (c Claimer) Claim(ctx context.Context, module, fingerprint, manifest string
if modules := OneNodeModules(cur); len(modules) > 0 && opt.MoreNodes != nil && opt.MoreNodes(modules) {
return &Claim{Key: key, Rev: rev, Build: cur}, nil
}
if opt.Trunk && Unpublished(cur) && opt.ImageBuilder != nil && opt.ImageBuilder() {
return &Claim{Key: key, Rev: rev, Build: cur}, nil
}
return nil, nil
case cur.State == delivery.BuildFailed && (strings.HasPrefix(cur.Error, RefusedPrefix) || strings.HasPrefix(cur.Error, buildrun.DigestsDifferPrefix)):
return nil, nil
modules/mesh-delivery-builder/internal/build/run.go
+46 -3
View File
@@ -288,6 +288,7 @@ func (b *Builder) try(ctx context.Context, module string, m delivery.Module) {
}
key, _ := delivery.BuilderBuildKey(module, m.FP2)
b.mu.Lock()
trunk := b.trunkFP[key]
first := !b.tried[key]
b.tried[key] = true
epoch := b.epoch
@@ -297,7 +298,7 @@ func (b *Builder) try(ctx context.Context, module string, m delivery.Module) {
// A second build that failed is not tried again until the nodes change (issue 1664).
return (!failedBefore || epoch > failedAt) && b.moreNodes(modules)
}
cl, err := b.Claimer.Claim(ctx, module, m.FP2, m.Manifest, ClaimOptions{TakeOver: first, MoreNodes: moreNodes, ImageBuilder: b.imageBuilderRuns})
cl, err := b.Claimer.Claim(ctx, module, m.FP2, m.Manifest, ClaimOptions{TakeOver: first, MoreNodes: moreNodes, ImageBuilder: b.imageBuilderRuns, Trunk: trunk})
if err != nil {
b.logf("%s: %v", module, err)
return
@@ -305,7 +306,20 @@ func (b *Builder) try(ctx context.Context, module string, m delivery.Module) {
if cl == nil {
return
}
result := b.build(ctx, module, m, plan, planErr)
// A done key taken again builds only what is missing: the build modules that ran on one node, and the image when it was
// built as a candidate's; the other artifacts stay as the done key has them (ADR 0487 clauses 5 and 8).
var prior *delivery.BuilderBuild
var only map[string]bool
if cl.Build.State == delivery.BuildDone {
prior, only = &cl.Build, map[string]bool{}
for _, bm := range OneNodeModules(cl.Build) {
only[bm] = true
}
if trunk && Unpublished(cl.Build) {
only[ImageBuildModule] = true
}
}
result := b.build(ctx, module, m, plan, planErr, prior, only)
if ctx.Err() != nil {
return
}
@@ -365,7 +379,7 @@ type lane struct {
err error
}
func (b *Builder) build(ctx context.Context, module string, m delivery.Module, plan Plan, planErr error) delivery.BuilderBuild {
func (b *Builder) build(ctx context.Context, module string, m delivery.Module, plan Plan, planErr error, prior *delivery.BuilderBuild, only map[string]bool) delivery.BuilderBuild {
switch {
case planErr != nil:
return failed("%s", planErr)
@@ -388,7 +402,12 @@ func (b *Builder) build(ctx context.Context, module string, m delivery.Module, p
b.Places.Cancel(l.node)
}
}
var kept []string // build modules whose artifacts stay as the prior done key has them
for _, bm := range plan.Modules() {
if prior != nil && len(only) > 0 && !only[bm] {
kept = append(kept, bm)
continue
}
language := buildrun.LanguageOf[bm]
entries := b.Toolchains.Entries(language)
qualifies := func(node string) bool { return b.qualifies(node, bm) }
@@ -461,7 +480,23 @@ func (b *Builder) build(ctx context.Context, module string, m delivery.Module, p
return failed("%s", strings.Join(errs, "; "))
}
var artifacts []delivery.BuiltArtifact
keptModule := map[string]bool{}
for _, bm := range kept {
keptModule[bm] = true
}
for _, t := range plan.Tasks {
if keptModule[t.Module] {
found := false
for _, a := range prior.Artifacts {
if a.Name == t.Artifact {
artifacts, found = append(artifacts, a), true
}
}
if !found {
return failed("the done build holds no artifact %s to keep", t.Artifact)
}
continue
}
byNode := map[string]string{}
for _, l := range lanes {
if d, ok := l.digests[t.Artifact]; ok && l.module == t.Module {
@@ -480,6 +515,14 @@ func (b *Builder) build(ctx context.Context, module string, m delivery.Module, p
}
artifacts = append(artifacts, built)
}
for _, bm := range kept {
steps = append(steps, bm+" kept")
for lang, u := range prior.Toolchains {
if _, ok := used[lang]; !ok && buildrun.LanguageOf[bm] == lang {
used[lang] = u
}
}
}
step := "built " + strings.Join(steps, "; ")
if len(oneNode) > 0 {
// Marked so that Claim builds the key again once a second node qualifies (ADR 0478 clause 4).
modules/mesh-delivery-builder/internal/build/run_test.go
+76
View File
@@ -530,3 +530,79 @@ func TestANodeThatIsNotOnlineIsNotChosenAndComingBackWakesTheBuild(t *testing.T)
t.Errorf("build = %+v, want done once a node is online", v)
}
}
func TestACandidatesImageIsPublishedOnceWhenTheTrunkNamesItsFingerprint(t *testing.T) { // review r1, mesh-delivery 1; ADR 0487 clause 5
r := newRig(t, imageArt)
r.b.Health = imageHave(t, "ace")
trunkModule(t, r) // the trunk carries another fingerprint; fp1 is the candidate's
r.b.Candidate(context.Background(), "feat%2Fx", candidateValue(t, "feat/x", 7, headX))
r.b.Wait()
v := valueOf(t, r.st, r.key)
if v.State != delivery.BuildDone || v.Artifacts[0].Reference != "" {
t.Fatalf("candidate build = %+v, want done with no reference", v)
}
if n := len(r.bm.callsOf("build_image_build")); n != 1 {
t.Fatalf("%d image builds after the candidate, want 1", n)
}
// The pull request is merged: the trunk's record names the candidate's fingerprint.
r.b.Module(context.Background(), "m", moduleValue(t, "modules/m"))
r.b.Wait()
v = valueOf(t, r.st, r.key)
if v.State != delivery.BuildDone || len(v.Artifacts) != 1 || v.Artifacts[0].Reference == "" {
t.Fatalf("trunk build = %+v, want done with a reference", v)
}
calls := r.bm.callsOf("build_image_build")
published := 0
for _, c := range calls {
if c.body.(map[string]any)["publish"] == true {
published++
}
}
if len(calls) != 2 || published != 1 {
t.Errorf("%d image builds, %d with publish, want 2 and exactly 1", len(calls), published)
}
// Written once more only: looking again builds nothing.
rev := r.st.revs[r.key]
r.b.Module(context.Background(), "m", moduleValue(t, "modules/m"))
r.b.Wait()
if r.st.revs[r.key] != rev || len(r.bm.callsOf("build_image_build")) != 2 {
t.Error("a published key was built again")
}
}
func TestASecondGoNodeDoesNotBuildOrPushTheImageAgain(t *testing.T) { // review r1, mesh-delivery 2; ADR 0487 clause 8
r := newRig(t, goBundle, imageArt)
r.b.Health = imageHave(t, "ace", "novox")
r.pres.Put("ace", presenceValue(t, false), false) // only novox qualifies for Go (and the image)
v := r.consider(t, "modules/m")
if v.State != delivery.BuildDone || len(OneNodeModules(v)) != 1 {
t.Fatalf("build = %+v, want done with the Go bundle on one node", v)
}
var image delivery.BuiltArtifact
for _, a := range v.Artifacts {
if a.Kind == "image" {
image = a
}
}
if image.Reference == "" {
t.Fatalf("artifacts = %+v, want a published image", v.Artifacts)
}
r.pres.Put("ace", presenceValue(t, true), false)
r.b.Reconsider(context.Background())
r.b.Wait()
v = valueOf(t, r.st, r.key)
if len(OneNodeModules(v)) != 0 || len(v.Artifacts) != 2 {
t.Fatalf("build = %+v, want done on two Go nodes", v)
}
if n := len(r.bm.callsOf("build_image_build")); n != 1 {
t.Errorf("%d image builds, want the one of the first build only", n)
}
for _, a := range v.Artifacts {
if a.Kind == "image" && a != image {
t.Errorf("image = %+v, was %+v: the done key was rewritten with another image", a, image)
}
}
if n := len(r.bm.callsOf("build_go_build")); n != 3 { // one, then two
t.Errorf("%d go builds, want 3", n)
}
}