Compare commits

..
Author SHA1 Message Date
jschoubben a073aeae5e Merge remote-tracking branch 'origin/main' into feat/try-speed 2026-10-25 03:17:34 +01:00
jschoubben 99407c37df Merge remote-tracking branch 'origin/main' into feat/try-speed 2026-10-25 01:29:22 +02:00
jschoubben 9b408db24a buildstep: run a check's levels side by side and answer them in level order, so the integration level no longer waits for the unit level and the first failing level is still named first (issue 1921, try speed S10) 2026-10-25 01:22:50 +02:00
jschoubben 571ac521f0 delivery: keep a merged member in its group's candidate, marked merged, so the heads an Approve covers hold until every member merged (issue 1921, issue 1791, try speed S9) 2026-10-25 01:17:16 +02:00
jschoubben 4a12ccb78d buildstep: deepen a merge preview's history from the mirror when it holds the trunk commit, so the preview fetches no history from the forge (issue 1921, try speed S6) 2026-10-25 01:08:39 +02:00
jschoubben cb548a6a58 buildstep: keep what one command of an ask writes into the caches for its later commands, so vet, unit tests and the integration compile build each package once; the shared cache stays unchanged (issue 1921, try speed S2) 2026-10-25 00:58:46 +02:00
jschoubben bc16740feb Run every test step of a check's level after a failure, and let a verdict name every failed test (issue 1921)
A check ask stopped its level at the first test step that did not pass,
so the packages after the changed ones never ran and a check found one
fault per round. Every step now runs; the level still fails, and no
later level runs (ADR 0484 clause 13). The verdict gains Failures, every
failed test with its first line, at most MaxFailures and a count.
2026-10-24 23:41:54 +02:00
29 changed files with 639 additions and 671 deletions
+39 -19
View File
@@ -8,6 +8,7 @@ import (
"slices"
"sort"
"strings"
"sync"
"git.novox.be/novox/mesh-sdk/go/delivery"
)
@@ -170,16 +171,36 @@ func (s AskSteps) check(ctx context.Context, job delivery.CheckJob) (any, error)
if job.Runner != "" && (job.RunnerWhen == "" || changesUnder(f.Changed, job.RunnerWhen)) {
runner = job.Runner
}
for _, level := range job.Levels {
la := delivery.LevelAnswer{Level: level}
passed, err := s.level(ctx, job, level, f, runner, &la)
answer.Levels = append(answer.Levels, la)
if err != nil {
return nil, err
}
if !passed {
return answer, nil // the first level that did not pass ends the check (ADR 0484 clause 13)
// The levels run side by side (issue 1921, try speed S10; the operator's yes to D1, ADR 0541): the integration level
// does not wait for the unit level. They are answered in their order, so the first level that did not pass is still
// the first failure the asker reads (ADR 0484 clause 13); the levels after it are kept in the answer for the log.
type ran struct {
la delivery.LevelAnswer
passed bool
err error
}
runs := make([]ran, len(job.Levels))
var wg sync.WaitGroup
for i, level := range job.Levels {
wg.Add(1)
go func() {
defer wg.Done()
runs[i].la = delivery.LevelAnswer{Level: level}
runs[i].passed, runs[i].err = s.level(ctx, job, level, f, runner, &runs[i].la)
}()
}
wg.Wait()
failed := false
for _, r := range runs {
if r.err != nil {
if failed {
continue // a level after the first failure that could not run: the failure is the answer
}
answer.Levels = append(answer.Levels, r.la)
return nil, r.err
}
answer.Levels = append(answer.Levels, r.la)
failed = failed || !r.passed
}
return answer, nil
}
@@ -208,6 +229,9 @@ func (s AskSteps) level(ctx context.Context, job delivery.CheckJob, level string
_ = json.Unmarshal(r, &t)
return t.Passed, nil
}
// Every test step of the level runs, also after one that did not pass, so one check names every failing test of the
// level and not only the first (issue 1921); the level as a whole passes only when each of its steps did.
all := true
if s.Digest == nil {
// A module with no digest (Node) tests each module directory of the tree, those whose tests changed first.
for _, priority := range []bool{true, false} {
@@ -219,14 +243,12 @@ func (s AskSteps) level(ctx context.Context, job delivery.CheckJob, level string
if err != nil {
return false, fmt.Errorf("the %s level of %s: %w", level, dir, err)
}
if !passed {
return false, nil
}
all = all && passed
}
}
return true, nil
return all, nil
}
todo, all, keepRunner := s.plan(ctx, job, level, f, runner, withRunner, la)
todo, whole, keepRunner := s.plan(ctx, job, level, f, runner, withRunner, la)
if !keepRunner {
runner = "" // an installed module that ignores the runner judges the level as it judges any other (ADR 0535 §2)
}
@@ -235,7 +257,7 @@ func (s AskSteps) level(ctx context.Context, job delivery.CheckJob, level string
if job.Run != "" {
args["run"] = job.Run
}
if all {
if whole {
if priority {
continue // nothing to put first: the level runs whole after
}
@@ -255,11 +277,9 @@ func (s AskSteps) level(ctx context.Context, job delivery.CheckJob, level string
if err != nil {
return false, fmt.Errorf("the %s level: %w", level, err)
}
if !passed {
return false, nil
}
all = all && passed // the packages left still run (issue 1921)
}
return true, nil
return all, nil
}
// release removes an ask's workspace, saying a failure: the module's sweep removes it later.
+60
View File
@@ -0,0 +1,60 @@
package buildstep
import (
"context"
"encoding/json"
"sync"
"testing"
"time"
"git.novox.be/novox/mesh-sdk/go/delivery"
)
// 1921/S10 (the operator's yes to D1, ADR 0541): a check's levels run side by side: the integration level has started
// before the unit level ends. The answer holds the levels in their order, so with the unit level failing it still names
// the unit level first; the integration level's answer is kept after it for the log.
func TestACheckRunsItsLevelsSideBySideAndAnswersThemInOrder(t *testing.T) {
integrationStarted := make(chan struct{})
var once sync.Once
var mu sync.Mutex
unitWaited := false
steps := AskSteps{
Fetch: func(context.Context, map[string]any) (any, error) {
return map[string]any{"workspace": "/w", "modules": []string{"."}}, nil
},
Test: func(ctx context.Context, args map[string]any) (any, error) {
switch args["level"] {
case delivery.LevelUnit:
select {
case <-integrationStarted:
mu.Lock()
unitWaited = true
mu.Unlock()
case <-time.After(2 * time.Second):
}
return map[string]any{"passed": false, "level": "unit"}, nil
default:
once.Do(func() { close(integrationStarted) })
return map[string]any{"passed": true, "level": "integration"}, nil
}
},
}
out, err := RunAsk(context.Background(), steps, ask(delivery.CheckJob{Levels: []string{delivery.LevelUnit, delivery.LevelIntegration},
Fetch: map[string]any{"repository": "novox/x", "commit": runCommit}}))
if err != nil {
t.Fatal(err)
}
mu.Lock()
defer mu.Unlock()
if !unitWaited {
t.Error("the integration level did not start while the unit level ran")
}
a := out.(delivery.CheckAnswer)
if len(a.Levels) != 2 || a.Levels[0].Level != delivery.LevelUnit || a.Levels[1].Level != delivery.LevelIntegration {
t.Fatalf("levels %+v, want unit then integration", a.Levels)
}
var first struct{ Passed bool }
if err := json.Unmarshal(a.Levels[0].Tests[0], &first); err != nil || first.Passed {
t.Errorf("the first level's result %s, want the unit level's failure", a.Levels[0].Tests[0])
}
}
+58 -8
View File
@@ -6,6 +6,7 @@ import (
"errors"
"fmt"
"strings"
"sync"
"testing"
"time"
@@ -16,6 +17,7 @@ const runCommit = "0123456789abcdef0123456789abcdef01234567"
// recorder is a build module's step tools that record each call.
type recorder struct {
mu sync.Mutex // a check's levels run side by side (issue 1921, S10)
calls []string
fetch map[string]any
tests map[string]bool // package or module directory -> passed
@@ -26,7 +28,9 @@ func (r *recorder) steps() AskSteps {
call := func(name string, answer func(args map[string]any) any) StepFunc {
return func(ctx context.Context, args map[string]any) (any, error) {
b, _ := json.Marshal(args)
r.mu.Lock()
r.calls = append(r.calls, name+" "+string(b))
r.mu.Unlock()
return answer(args), nil
}
}
@@ -109,9 +113,9 @@ func TestRunAskRefusesAnotherToolchain(t *testing.T) {
}
}
// 1887/A3, A5a, issue 1887 design limit 1: a check ask runs the levels of one check after one fetch: it digests the unit
// level, takes the kept verdicts, tests the packages whose tests changed first, and stops at the first failure, running
// no later level.
// 1887/A3, A5a: a check ask runs the levels of one check after one fetch: it digests the unit level, takes the kept
// verdicts, tests the packages whose tests changed first, then the rest also after a failure (issue 1921); the levels run
// side by side and are answered in order, the first that did not pass first (ADR 0484 clause 13; issue 1921 S10).
func TestRunAskChecksTheLevelsOfOneCheck(t *testing.T) {
r := &recorder{
fetch: map[string]any{"workspace": "/w", "changed": []string{"pkg/b/b_test.go"}},
@@ -123,19 +127,26 @@ func TestRunAskChecksTheLevelsOfOneCheck(t *testing.T) {
if err != nil {
t.Fatal(err)
}
got := strings.Join(r.calls, "\n")
var unit []string
for _, c := range r.calls {
if !strings.Contains(c, `"level":"integration"`) {
unit = append(unit, c)
}
}
got := strings.Join(unit, "\n")
want := `fetch {"base":"` + runCommit + `","commit":"` + runCommit + `","repository":"novox/x"}
digest {"level":"unit","workspace":"/w"}
test {"level":"unit","packages":["x/pkg/b"],"workspace":"/w"}`
test {"level":"unit","packages":["x/pkg/b"],"workspace":"/w"}
test {"level":"unit","packages":["x/pkg/a"],"workspace":"/w"}`
if got != want {
t.Fatalf("calls:\n%s\nwant:\n%s", got, want)
}
a := out.(delivery.CheckAnswer)
if len(a.Levels) != 1 {
t.Fatalf("levels %+v, want the unit level alone", a.Levels)
if len(a.Levels) != 2 || a.Levels[1].Level != delivery.LevelIntegration {
t.Fatalf("levels %+v, want the unit level first, the integration level after it", a.Levels)
}
u := a.Levels[0]
if u.Level != delivery.LevelUnit || len(u.Kept) != 1 || u.Kept[0].Package != "x/pkg/k" || u.Kept[0].Tests != 7 || len(u.Tests) != 1 || u.Digest == nil {
if u.Level != delivery.LevelUnit || len(u.Kept) != 1 || u.Kept[0].Package != "x/pkg/k" || u.Kept[0].Tests != 7 || len(u.Tests) != 2 || u.Digest == nil {
t.Fatalf("the unit level %+v", u)
}
}
@@ -203,3 +214,42 @@ func TestRunAskChecksNodeModulesAndConflicts(t *testing.T) {
t.Fatalf("a conflict: %v %v", err, r.calls)
}
}
// Issue 1921: a failure in the packages whose tests changed does not stop the level: the other packages still run, so two
// failing packages, one changed and one not, are two test results of the one level, and the level does not pass. A Node
// check runs every module directory after one fails too.
func TestRunAskRunsEveryPackageAfterAFailure(t *testing.T) {
r := &recorder{
fetch: map[string]any{"workspace": "/w", "changed": []string{"pkg/b/b_test.go"}},
digests: map[string]string{"x/pkg/a": "d-a", "x/pkg/b": "d-b"},
tests: map[string]bool{"x/pkg/a": false, "x/pkg/b": false},
}
out, err := RunAsk(context.Background(), r.steps(), ask(delivery.CheckJob{Levels: []string{delivery.LevelIntegration, delivery.LevelUnit},
Fetch: map[string]any{"repository": "novox/x", "commit": runCommit}}))
if err != nil {
t.Fatal(err)
}
a := out.(delivery.CheckAnswer)
if len(a.Levels) != 2 || len(a.Levels[0].Tests) != 2 || a.Levels[0].Level != delivery.LevelIntegration {
t.Fatalf("levels %+v, want the first level with both packages' results, in the order asked", a.Levels)
}
for i, raw := range a.Levels[0].Tests {
var res struct{ Passed bool }
if err := json.Unmarshal(raw, &res); err != nil || res.Passed {
t.Errorf("result %d %s, want a failure", i, raw)
}
}
r = &recorder{fetch: map[string]any{"workspace": "/w", "modules": []string{"a", "b"}, "changed": []string{"b/test/x.test.ts"}},
tests: map[string]bool{"a": true, "b": false}}
s := r.steps()
s.Digest = nil
out, err = RunAsk(context.Background(), s, ask(delivery.CheckJob{Levels: []string{delivery.LevelUnit, delivery.LevelIntegration},
Fetch: map[string]any{"repository": "novox/x", "commit": runCommit}}))
if err != nil {
t.Fatal(err)
}
if a := out.(delivery.CheckAnswer); len(r.calls) != 5 || len(a.Levels) != 2 || len(a.Levels[0].Tests) != 2 || a.Levels[0].Level != delivery.LevelUnit {
t.Fatalf("calls %v, levels %+v: want both directories of each level, the unit level first", r.calls, a.Levels)
}
}
+3 -12
View File
@@ -42,20 +42,11 @@ func NodeCapacity(path, fallback, node string, logf func(string, ...any)) func()
}
setting, _ = s[CapacitySetting].(string)
}
n, err := capacityOf(setting, node)
caps, err := buildrun.ParseCapacity(setting)
if err != nil {
say("%v, so %s pulls nothing", err, node)
say("%v, so %s pulls nothing", fmt.Errorf("the build capacity: %w", err), node)
return 0
}
return n
return (&buildrun.Places{Capacity: caps}).CapacityOf(node)
}
}
// capacityOf is node's capacity in a setting's `<node>=<asks>` pairs: DefaultCapacity for a node it does not name.
func capacityOf(setting, node string) (int, error) {
caps, err := buildrun.ParseCapacity(setting)
if err != nil {
return 0, fmt.Errorf("the build capacity: %w", err)
}
return (&buildrun.Places{Capacity: caps}).CapacityOf(node), nil
}
+114 -10
View File
@@ -3,10 +3,13 @@ package buildstep
import (
"context"
"fmt"
"io/fs"
"os"
"path"
"path/filepath"
"strconv"
"strings"
"sync"
"git.novox.be/novox/mesh-sdk/go/forgekey"
)
@@ -29,16 +32,25 @@ const Bubblewrap = "bwrap"
// - the Workspace and Writable directories read-write, the ReadOnly ones (the toolchain, the modules the fetch step
// downloaded) read-only;
// - the shared warm Caches read-only under a throwaway writable layer (S18), or read-write for a trunk build alone
// (WriteCaches), so a candidate's code never changes what a later build reads.
// (WriteCaches), so a candidate's code never changes what a later build reads;
// - with a CacheLayer, what one command writes into the caches kept for the later commands of the same ask (issue 1921,
// the try speed-up): the vet, the unit tests and the integration compile of one ask compile each package once.
type Isolation struct {
Workspace string
Writable []string
ReadOnly []string
Caches []string
WriteCaches bool
Env []string
// CacheLayer is a directory of the ask's own, in its workspace and gone with it: each command writes the caches into
// a layer of its own beneath it (overlayfs refuses an upper layer two mounts share, and an ask's commands run side by
// side), which Isolated moves into the ask's kept layer when the command ends; every later command reads the kept
// layer above the shared cache. The shared cache stays unchanged. Empty: what a command writes is thrown away.
CacheLayer string
Env []string
// Hosts is the file bound as /etc/hosts; Isolated writes one naming only the loopback.
Hosts string
// run is the directory of this command's own writable layers under CacheLayer; Isolated makes one per command.
run string
}
// etcNeeded is what of /etc a program in the step may read: who the users are, where the libraries are, the
@@ -91,7 +103,7 @@ func (iso Isolation) command(env []string, name string, args ...string) ([]strin
for _, group := range []struct {
what string
dirs []string
}{{"writable directory", iso.Writable}, {"read-only directory", iso.ReadOnly}, {"cache", iso.Caches}} {
}{{"writable directory", iso.Writable}, {"read-only directory", iso.ReadOnly}, {"cache", iso.Caches}, {"cache layer", layerDirs(iso.CacheLayer)}} {
for _, d := range group.dirs {
if err := checkDir(group.what, d); err != nil {
return nil, err
@@ -113,7 +125,7 @@ func (iso Isolation) command(env []string, name string, args ...string) ([]strin
for _, d := range iso.ReadOnly {
argv = append(argv, "--ro-bind", d, d)
}
argv = append(argv, cacheArgs(iso.Caches, iso.WriteCaches)...)
argv = append(argv, iso.cacheArgs()...)
argv = append(argv, "--bind", iso.Workspace, iso.Workspace)
for _, d := range iso.Writable {
argv = append(argv, "--bind", d, d)
@@ -134,19 +146,107 @@ func (iso Isolation) command(env []string, name string, args ...string) ([]strin
// cacheArgs binds the shared warm caches (S18): for a trunk build read-write, so the next build is warm; for any other
// read-only beneath an overlay whose writes go to a tmpfs of the step's own, so the step writes as a build does and
// nothing it wrote outlives it (bubblewrap's --tmp-overlay, an overlay mount in the step's user namespace).
func cacheArgs(caches []string, write bool) []string {
// nothing it wrote outlives it (bubblewrap's --tmp-overlay, an overlay mount in the step's user namespace). With a
// CacheLayer the ask's kept layer lies above the shared cache and the command's writes go to its own layer on disk
// (--overlay), which Isolated keeps for the ask when the command ends.
func (iso Isolation) cacheArgs() []string {
var argv []string
for _, c := range caches {
if write {
for i, c := range iso.Caches {
switch {
case iso.WriteCaches:
argv = append(argv, "--bind", c, c)
continue
case iso.CacheLayer != "":
upper, work := iso.runLayer(i)
argv = append(argv, "--overlay-src", c, "--overlay-src", keptLayer(iso.CacheLayer, i), "--overlay", upper, work, c)
default:
argv = append(argv, "--overlay-src", c, "--tmp-overlay", c)
}
argv = append(argv, "--overlay-src", c, "--tmp-overlay", c)
}
return argv
}
func layerDirs(layer string) []string {
if layer == "" {
return nil
}
return []string{layer}
}
// keptLayer is where the ask keeps what its commands wrote into the cache i.
func keptLayer(layer string, i int) string { return filepath.Join(layer, "kept", strconv.Itoa(i)) }
// runLayer is the upper and work directory of this command's writes into the cache i. Command, which makes no
// directory, names the layer "run"; Isolated gives each command one of its own.
func (iso Isolation) runLayer(i int) (upper, work string) {
run := iso.run
if run == "" {
run = filepath.Join(iso.CacheLayer, "run")
}
return filepath.Join(run, strconv.Itoa(i), "upper"), filepath.Join(run, strconv.Itoa(i), "work")
}
// layerLocks hold one mutex per cache layer, so two commands ending at once keep their writes one after the other.
var layerLocks sync.Map
// prepareLayer makes the kept layers and a run directory of the command's own under the cache layer.
func (iso *Isolation) prepareLayer() error {
if iso.CacheLayer == "" || iso.WriteCaches || len(iso.Caches) == 0 {
return nil
}
if err := os.MkdirAll(filepath.Join(iso.CacheLayer, "runs"), 0o700); err != nil {
return err
}
run, err := os.MkdirTemp(filepath.Join(iso.CacheLayer, "runs"), "run-")
if err != nil {
return err
}
iso.run = run
for i := range iso.Caches {
upper, work := iso.runLayer(i)
for _, d := range []string{keptLayer(iso.CacheLayer, i), upper, work} {
if err := os.MkdirAll(d, 0o700); err != nil {
return err
}
}
}
return nil
}
// keepLayer moves what the command wrote into the caches into the ask's kept layers, and removes its run directory.
// A file the command wrote replaces the kept one (a cache's newest write wins); a whiteout (a file the command
// deleted) is not kept, since a cache entry deleted by one command is no fault of a later one. A write that cannot be
// kept only means a later command builds it again.
func (iso Isolation) keepLayer() {
if iso.run == "" {
return
}
defer os.RemoveAll(iso.run)
mu, _ := layerLocks.LoadOrStore(iso.CacheLayer, &sync.Mutex{})
mu.(*sync.Mutex).Lock()
defer mu.(*sync.Mutex).Unlock()
for i := range iso.Caches {
upper, _ := iso.runLayer(i)
kept := keptLayer(iso.CacheLayer, i)
filepath.WalkDir(upper, func(p string, d fs.DirEntry, err error) error {
if err != nil || p == upper {
return nil
}
rel, _ := filepath.Rel(upper, p)
to := filepath.Join(kept, rel)
switch {
case d.IsDir():
if fi, err := os.Lstat(to); err == nil && !fi.IsDir() {
os.Remove(to)
}
os.MkdirAll(to, 0o700)
case d.Type().IsRegular():
os.Rename(p, to)
}
return nil
})
}
}
// loopbackHosts is the hosts file of a step: the loopback and nothing else.
const loopbackHosts = "127.0.0.1 localhost\n::1 localhost\n"
@@ -166,6 +266,10 @@ func Isolated(run forgekey.Runner, iso Isolation) forgekey.Runner {
}
iso := iso
iso.Hosts = hosts
if err := iso.prepareLayer(); err != nil {
return forgekey.Ran{Status: 1, Err: "the step's cache layer: " + err.Error()}
}
defer iso.keepLayer()
argv, err := iso.command(env, name, args...)
if err != nil {
return forgekey.Ran{Status: 1, Err: err.Error()}
+36
View File
@@ -64,3 +64,39 @@ func TestARunStepReachesNothingAndLeavesTheCachesUnchanged(t *testing.T) {
t.Fatalf("the step's write to its workspace did not stay (status %d, %s%s): %q %v", r.Status, r.Stderr, r.Err, b, err)
}
}
// 1921/S2: in one ask (one cache layer), a second go build of the same package does not compile it again, and the
// shared cache is unchanged afterwards.
func TestASecondBuildOfTheAskFindsTheFirstsCompiledAndTheSharedCacheIsUnchanged(t *testing.T) {
if _, err := exec.LookPath(Bubblewrap); err != nil {
t.Fatalf("bubblewrap is not installed here (issue 1309): %v", err)
}
goBin, err := exec.LookPath("go")
if err != nil {
t.Fatal(err)
}
root := t.TempDir()
shared := filepath.Join(root, "gobuild")
if err := os.MkdirAll(shared, 0o700); err != nil {
t.Fatal(err)
}
workspace := filepath.Join(root, "ws")
tree := filepath.Join(workspace, "tree")
writeFile(t, tree, "go.mod", "module probe\n\ngo 1.22\n")
writeFile(t, tree, "probe.go", "package probe\n\nfunc Probe() int { return 42 }\n")
run := Isolated(forgekey.ExecRunnerFor(0), Isolation{Workspace: workspace, Caches: []string{shared},
CacheLayer: filepath.Join(workspace, "cachelayer"), ReadOnly: []string{filepath.Dir(filepath.Dir(goBin))}})
env := []string{"PATH=" + filepath.Dir(goBin) + ":/usr/bin:/bin", "GOCACHE=" + shared, "GOTOOLCHAIN=local", "GOFLAGS=-mod=mod"}
for i, want := range []bool{true, false} {
r := run(context.Background(), env, "go", "-C", tree, "build", "-x", "./...")
if r.Status != 0 || r.Err != "" {
t.Fatalf("build %d: status %d %s\n%s", i+1, r.Status, r.Err, r.Stderr)
}
if compiled := strings.Contains(r.Stderr, "/compile "); compiled != want {
t.Errorf("build %d compiled the package: %v, want %v\n%s", i+1, compiled, want, r.Stderr)
}
}
if entries, _ := os.ReadDir(shared); len(entries) != 0 {
t.Errorf("the shared cache was written: %d entries", len(entries))
}
}
+110
View File
@@ -0,0 +1,110 @@
package buildstep
import (
"context"
"os"
"path/filepath"
"sync"
"testing"
"git.novox.be/novox/mesh-sdk/go/forgekey"
)
// overlayOf answers the upper directory a command line gives the cache c, "" when it gives none.
func overlayOf(argv []string, c string) string {
for i := 0; i+3 < len(argv); i++ {
if argv[i] == "--overlay" && argv[i+3] == c {
return argv[i+1]
}
}
return ""
}
// 1921/S2: with a cache layer, a command reads the ask's kept layer above the shared cache and writes into a layer on
// disk of its own, never into the shared cache and never into a throwaway tmpfs.
func TestACommandWithACacheLayerReadsTheKeptLayerAndWritesItsOwn(t *testing.T) {
fixedSystem(t)
iso := Isolation{Workspace: "/w", Caches: []string{"/cache/gomod", "/cache/gobuild"}, CacheLayer: "/w/cachelayer"}
argv, err := iso.Command("go", "vet")
if err != nil {
t.Fatal(err)
}
for i, c := range iso.Caches {
if !holds(argv, "--overlay-src", c, "--overlay-src", keptLayer(iso.CacheLayer, i), "--overlay") {
t.Errorf("the cache %s is not read beneath the ask's kept layer: %v", c, argv)
}
if up := overlayOf(argv, c); up == "" || filepath.Dir(filepath.Dir(filepath.Dir(up))) != "/w/cachelayer" {
t.Errorf("the cache %s is written into %q, not a layer of the ask's own: %v", c, up, argv)
}
if holds(argv, "--tmp-overlay", c) || holds(argv, "--bind", c, c) {
t.Errorf("the cache %s is thrown away or written: %v", c, argv)
}
}
if _, err := (Isolation{Workspace: "/w", CacheLayer: "cachelayer"}).Command("go"); err == nil {
t.Error("a relative cache layer was taken")
}
}
// 1921/S2: what one command wrote into the caches is kept for the ask's later commands, the shared cache stays
// unchanged, two commands at once write into layers of their own (overlayfs refuses an upper layer two mounts share),
// and a command's own layer is gone when it ends.
func TestWhatOneCommandCompiledIsReadByTheNextOfTheSameAsk(t *testing.T) {
fixedSystem(t)
root := t.TempDir()
shared := filepath.Join(root, "gobuild")
if err := os.MkdirAll(shared, 0o700); err != nil {
t.Fatal(err)
}
layer := filepath.Join(root, "ws", "cachelayer")
var mu sync.Mutex
uppers := map[string]bool{}
gate := make(chan struct{})
var started sync.WaitGroup
started.Add(2)
inner := func(ctx context.Context, env []string, name string, args ...string) forgekey.Ran {
up := overlayOf(args, shared)
mu.Lock()
uppers[up] = true
mu.Unlock()
if holds(args, "--", "go", "build") {
started.Done()
<-gate // both commands are running before either ends
os.MkdirAll(filepath.Join(up, "ab"), 0o700)
os.WriteFile(filepath.Join(up, "ab", args[len(args)-1]+"-d"), []byte("compiled"), 0o600)
}
return forgekey.Ran{}
}
run := Isolated(inner, Isolation{Workspace: filepath.Join(root, "ws"), Caches: []string{shared}, CacheLayer: layer})
var wg sync.WaitGroup
for _, pkg := range []string{"one", "two"} {
wg.Add(1)
go func() { defer wg.Done(); run(context.Background(), nil, "go", "build", pkg) }()
}
started.Wait()
close(gate)
wg.Wait()
if len(uppers) != 2 {
t.Fatalf("two commands at once wrote into %d layers, want 2 of their own: %v", len(uppers), uppers)
}
for _, pkg := range []string{"one", "two"} {
if b, err := os.ReadFile(filepath.Join(keptLayer(layer, 0), "ab", pkg+"-d")); err != nil || string(b) != "compiled" {
t.Errorf("what the build of %s compiled is not kept for the ask: %q %v", pkg, b, err)
}
}
for up := range uppers {
if _, err := os.Stat(up); !os.IsNotExist(err) {
t.Errorf("the command's own layer %s outlived it: %v", up, err)
}
}
var next []string
Isolated(func(ctx context.Context, env []string, name string, args ...string) forgekey.Ran {
next = args
return forgekey.Ran{}
}, Isolation{Workspace: filepath.Join(root, "ws"), Caches: []string{shared}, CacheLayer: layer})(context.Background(), nil, "go", "test")
if !holds(next, "--overlay-src", shared, "--overlay-src", keptLayer(layer, 0)) {
t.Errorf("the next command does not read the kept layer: %v", next)
}
if entries, _ := os.ReadDir(shared); len(entries) != 0 {
t.Errorf("the shared cache was written: %v", entries)
}
}
+15 -6
View File
@@ -24,7 +24,8 @@ type MergeResult struct {
// signature, no hook, nothing of the machine's git configuration that changes a merge. Nothing is pushed.
//
// A merge needs both histories, so it makes the fetch whole (the shallow clone FetchCommit made is deepened) and
// fetches base by its sha. A head that does not merge cleanly is an answer, not an error: the files in conflict, the
// fetches base by its sha: from the mirror WithMirror names, when it holds base (UpdateMirror to base first), else
// from remote. A head that does not merge cleanly is an answer, not an error: the files in conflict, the
// merge undone and the workspace left at base. A head already in base answers a Merge equal to Base and no changed
// paths. An error is that the merge could not be tried: a base or commit that is not a full sha, no base, a workspace
// not at commit, or a fetch or git command that failed. remote and the options are those of FetchCommit; the runner's
@@ -67,12 +68,20 @@ func MergeInto(ctx context.Context, run forgekey.Runner, dir, remote, base, comm
if err != nil {
return res, err
}
fetch := []string{"fetch", "--no-tags", "origin", base}
if strings.TrimSpace(shallow) == "true" {
fetch = []string{"fetch", "--no-tags", "--unshallow", "origin", base}
fetchFrom := func(source string) error {
fetch := []string{"fetch", "--no-tags", source, base}
if strings.TrimSpace(shallow) == "true" {
fetch = []string{"fetch", "--no-tags", "--unshallow", source, base}
}
_, err := git(fetch...)
return err
}
if _, err := git(fetch...); err != nil {
return res, fmt.Errorf("the trunk commit %s: %w", base, err)
// With a mirror brought to the trunk commit, the history is deepened from it, a local fetch (issue 1921, try speed
// S6); a mirror that cannot answer leaves it to the forge, as before.
if o.mirror == "" || fetchFrom(o.mirror) != nil {
if err := fetchFrom("origin"); err != nil {
return res, fmt.Errorf("the trunk commit %s: %w", base, err)
}
}
if _, err := git("checkout", "-q", "--detach", base); err != nil {
return res, fmt.Errorf("the trunk commit %s cannot be checked out: %w", base, err)
+30
View File
@@ -170,3 +170,33 @@ func TestMergeIntoAHeadAlreadyInTheTrunkChangesNothing(t *testing.T) {
t.Errorf("result = %+v, %v", res, err)
}
}
// 1921/S6: with a mirror brought to the head and to the trunk commit, the merge asks the forge for nothing: it succeeds
// with the forge gone.
func TestMergeIntoWithAMirrorAtTheTrunkNeedsNoForge(t *testing.T) {
r := newMergeRig(t)
head := r.head(map[string]string{"b.txt": "head\n"})
base := r.advance(map[string]string{"a.txt": "one\ntwo\nthree\nfour\n"})
mirror := filepath.Join(t.TempDir(), "mirror.git")
if err := os.MkdirAll(mirror, 0o755); err != nil {
t.Fatal(err)
}
for _, c := range []string{head, base} {
if err := UpdateMirror(context.Background(), forgekey.ExecRunner, mirror, r.remote, c, "", AllowFileRemote()); err != nil {
t.Fatal(err)
}
}
if err := FetchCommit(context.Background(), forgekey.ExecRunner, r.ws, r.remote, head, "", AllowFileRemote(), WithMirror(mirror)); err != nil {
t.Fatal(err)
}
if err := os.RemoveAll(r.bare); err != nil { // the forge is gone
t.Fatal(err)
}
res, err := MergeInto(context.Background(), forgekey.ExecRunner, r.ws, r.remote, base, head, AllowFileRemote(), WithMirror(mirror))
if err != nil {
t.Fatalf("the merge asked the forge: %v", err)
}
if len(res.Merge) != 40 || !reflect.DeepEqual(res.Changed, []string{"b.txt"}) {
t.Errorf("result = %+v", res)
}
}
+36
View File
@@ -72,3 +72,39 @@ func TestMergeIntoRunsTheCheckMergesCommands(t *testing.T) {
}
}
}
// 1921/S6: with a mirror that holds the trunk commit, the merge deepens the workspace from the mirror, a local fetch,
// and asks the forge nothing; a mirror that cannot answer falls back to the forge.
func TestMergeIntoWithAMirrorFetchesTheTrunkFromTheMirror(t *testing.T) {
base := strings.Repeat("b", 40)
mirror := t.TempDir()
answer := func(failMirror bool) *fakeGit {
return &fakeGit{rule: func(l string) forgekey.Ran {
switch {
case strings.HasSuffix(l, "rev-parse HEAD"):
return forgekey.Ran{Stdout: sha + "\n"}
case strings.Contains(l, "--is-shallow-repository"):
return forgekey.Ran{Stdout: "true\n"}
case failMirror && strings.Contains(l, " fetch ") && strings.Contains(l, mirror):
return forgekey.Ran{Status: 128, Stderr: "fatal: not our ref"}
}
return forgekey.Ran{}
}}
}
f := answer(false)
dir := t.TempDir()
if _, err := MergeInto(context.Background(), f.run, dir, "ssh://mesh-forge/o/r.git", base, sha, WithMirror(mirror)); err != nil {
t.Fatal(err)
}
all := strings.Join(f.calls, "\n")
if !strings.Contains(all, "fetch --no-tags --unshallow "+mirror+" "+base) || strings.Contains(all, "--unshallow origin") {
t.Errorf("the trunk was not fetched from the mirror alone:\n%s", all)
}
g := answer(true)
if _, err := MergeInto(context.Background(), g.run, t.TempDir(), "ssh://mesh-forge/o/r.git", base, sha, WithMirror(mirror)); err != nil {
t.Fatal(err)
}
if all := strings.Join(g.calls, "\n"); !strings.Contains(all, "fetch --no-tags --unshallow origin "+base) {
t.Errorf("a mirror that could not answer did not fall back to the forge:\n%s", all)
}
}
+9 -104
View File
@@ -9,7 +9,6 @@ import (
"sync"
"time"
stdio "git.novox.be/novox/mesh-sdk/go"
"git.novox.be/novox/mesh-sdk/go/delivery"
)
@@ -65,17 +64,10 @@ type Puller struct {
PullWait time.Duration
Heartbeat time.Duration
Logf func(format string, args ...any)
// Load reads one key of the state the node's pause is kept in (nil and no error when it is absent). When set, Pull
// reads the node's pause key (delivery.PauseKey) before it pulls, and Pause and Resume write it with PausePut, so a
// pause outlives a restart.
// Load reads one key of the module's steps state (nil and no error when it is absent). When set, Pull reads the
// node's pause key (delivery.PauseKey) before it pulls, and Pause and Resume write it with Put, so a pause outlives
// a restart.
Load func(key string) ([]byte, error)
// PausePut writes the node's pause key: the module's pauses state (delivery.PausesState), which has no age, so a
// pause never ends by itself while the steps state drops its old keys. Put when nil.
PausePut Put
// WatchConfig, when set, follows the module's config value `capacity` (CapacitySetting) as mesh-config resolves it
// for this node, and wakes the puller on each change (watchCapacity): WatchConfigServed in a module, a test's own
// double. Until it hands a value the puller judges by Capacity.
WatchConfig func(key string, handle func(stdio.ProvisionChange) error) error
mu sync.Mutex
inHand int
@@ -83,9 +75,6 @@ type Puller struct {
paused bool
wake chan struct{}
once sync.Once
// watched is the capacity the config watch handed last, used in place of Capacity once hasWatched.
watched int
hasWatched bool
}
func (p *Puller) init() {
@@ -124,11 +113,7 @@ func (p *Puller) setPaused(paused bool, by string) error {
if err != nil {
return err
}
put := p.PausePut
if put == nil {
put = p.Put
}
if _, err := put(key, json.RawMessage(raw)); err != nil {
if _, err := p.Put(key, json.RawMessage(raw)); err != nil {
return fmt.Errorf("buildstep: writing the pause of %s: %w", p.Node, err)
}
}
@@ -201,29 +186,13 @@ func (p *Puller) Running() []RunningAsk {
// room says whether the puller may take one more ask now.
func (p *Puller) room() bool {
ok, _, _ := p.roomNow()
return ok
}
// roomNow is room, with the capacity and the asks in hand it was judged on.
func (p *Puller) roomNow() (ok bool, capacity, inHand int) {
p.mu.Lock()
watched, has := p.watched, p.hasWatched
p.mu.Unlock()
if has {
capacity = watched
} else if p.Capacity != nil {
capacity := 0
if p.Capacity != nil {
capacity = p.Capacity()
}
p.mu.Lock()
defer p.mu.Unlock()
return !p.paused && p.inHand < capacity, capacity, p.inHand
}
// CapacityNow is the capacity the puller judges by: the config watch's last value, else Capacity.
func (p *Puller) CapacityNow() int {
_, capacity, _ := p.roomNow()
return capacity
return !p.paused && p.inHand < capacity
}
// Pull takes and runs asks until ctx ends. An ask still running then is neither ended nor acknowledged: the stream
@@ -234,11 +203,8 @@ func (p *Puller) Pull(ctx context.Context) error {
return errors.New("buildstep: a puller needs its source, its steps' put and its run")
}
if err := p.restore(); err != nil {
// An unreadable pause degrades to not paused, said once: a puller that stops silently is the worse failure, and a
// node kept from building is held by its capacity (0), not by a pause.
p.logf("the pause of %s cannot be read: %v; pulling as not paused", p.Node, err)
return err // pulling on a pause that cannot be read could build on a node paused on purpose
}
go p.watchCapacity() // WatchConfigServed waits for Serve, which a module starts after its pull
wait := p.PullWait
if wait <= 0 {
wait = DefaultPullWait
@@ -247,17 +213,12 @@ func (p *Puller) Pull(ctx context.Context) error {
if err := ctx.Err(); err != nil {
return err
}
if ok, capacity, inHand := p.roomNow(); !ok {
// Parked until something wakes it: a capacity change (the config watch), a resume, or a step's end. Every
// park logs once, so a puller that sits idle says why (issue 1887).
p.logf("the %s puller on %s parks: %d of capacity %d in hand, paused %v", p.Language, p.Node, inHand, capacity, p.Paused())
if !p.room() {
select {
case <-ctx.Done():
return ctx.Err()
case <-p.wake:
}
_, capacity, inHand = p.roomNow()
p.logf("the %s puller on %s wakes: %d of capacity %d in hand, paused %v", p.Language, p.Node, inHand, capacity, p.Paused())
continue
}
msg, err := p.next(ctx, wait)
@@ -387,59 +348,3 @@ func (p *Puller) run(ctx context.Context, msg *Pulled, ask delivery.StepAsk, key
p.logf("the ask %s ended on %s and its acknowledgement failed: %v", ask.ID, p.Node, aerr)
}
}
// watchCapacity follows the module's config value `capacity` when WatchConfig is set (issue 1887, 2026-10-25: g14's
// puller started at capacity 0 sat parked with capacity 2 set, because nothing woke it to read its settings file
// again). The value comes as mesh-config resolved it for this node, the event of the change itself: the runtime hands
// the value now and then each change its machine's provisioner client says moved, so nothing polls, and the puller does
// not wait for the node-engine to fill its settings file again. Each value handed is kept, used in place of Capacity,
// and wakes the puller. A watch that cannot start leaves the puller on Capacity, said once.
func (p *Puller) watchCapacity() {
if p.WatchConfig == nil {
return
}
err := p.WatchConfig(CapacitySetting, func(c stdio.ProvisionChange) error {
n, why := p.capacityFrom(c)
p.mu.Lock()
before, had := p.watched, p.hasWatched
p.watched, p.hasWatched = n, true
p.mu.Unlock()
switch {
case why != "":
p.logf("the %s puller on %s pulls nothing: %s", p.Language, p.Node, why)
case !had || before != n:
p.logf("the %s build capacity of %s is %d, as mesh-config resolved it", p.Language, p.Node, n)
}
p.Wake()
return nil
})
if err != nil {
p.logf("the %s build capacity of %s cannot be followed on the bus, so it is read from the settings file when the "+
"puller wakes: %v", p.Language, p.Node, err)
}
}
// WatchConfigServed is stdio.WatchConfig once Serve has the runtime's channel (stdio.Served): a build module starts its
// pull before it serves, and a watch asked before that would be refused.
func WatchConfigServed(key string, handle func(stdio.ProvisionChange) error) error {
<-stdio.Served()
return stdio.WatchConfig(key, handle)
}
// capacityFrom is the node's capacity in one value the watch handed, and why it is 0 when it cannot be read.
func (p *Puller) capacityFrom(c stdio.ProvisionChange) (int, string) {
if c.Refused != "" {
return 0, "its capacity is no longer answered: " + c.Refused
}
setting := ""
if len(c.Value) > 0 && string(c.Value) != "null" {
if err := json.Unmarshal(c.Value, &setting); err != nil {
return 0, fmt.Sprintf("its capacity %s is not a string", c.Value)
}
}
n, err := capacityOf(setting, p.Node)
if err != nil {
return 0, err.Error()
}
return n, ""
}
-39
View File
@@ -1,39 +0,0 @@
package buildstep
import (
"encoding/json"
"sync"
"testing"
stdio "git.novox.be/novox/mesh-sdk/go"
)
// configWatch is a double of stdio.WatchConfig: it hands the value now at the start, as the runtime does, and a test
// hands each change after with set.
type configWatch struct {
mu sync.Mutex
value string
handle func(stdio.ProvisionChange) error
asked string
}
func (w *configWatch) watch(key string, handle func(stdio.ProvisionChange) error) error {
w.mu.Lock()
w.asked, w.handle = key, handle
value := w.value
w.mu.Unlock()
return handle(stdio.ProvisionChange{Kind: "config", Key: key, Value: json.RawMessage(`"` + value + `"`)})
}
func (w *configWatch) set(t *testing.T, value string) {
t.Helper()
w.mu.Lock()
handle, key := w.handle, w.asked
w.mu.Unlock()
if handle == nil {
t.Fatal("the puller watches no config value")
}
if err := handle(stdio.ProvisionChange{Kind: "config", Key: key, Value: json.RawMessage(`"` + value + `"`)}); err != nil {
t.Fatal(err)
}
}
+24 -101
View File
@@ -3,15 +3,11 @@ package buildstep
import (
"context"
"encoding/json"
"errors"
"fmt"
"strings"
"sync"
"sync/atomic"
"testing"
"time"
stdio "git.novox.be/novox/mesh-sdk/go"
"git.novox.be/novox/mesh-sdk/go/delivery"
)
@@ -179,85 +175,36 @@ func (k *kv) load(key string) ([]byte, error) {
return k.vals[key], nil
}
// 1887/A2b, 1887/AC-zero, 1887/AC-wake: at capacity 0 the puller takes nothing; a capacity raised takes effect at the
// next pull, or, with the config watch (g14 idle at capacity 2, 2026-10-25), at once when the value moves, with no
// pause, resume or step end to wake it; a refused value pulls nothing, and a watch that cannot start leaves the
// settings file's capacity.
// 1887/A2b, 1887/AC-zero: at capacity 0 the puller takes nothing; a capacity raised takes effect at the next pull.
func TestPullAtCapacityZeroTakesNothing(t *testing.T) {
t.Run("settings file", func(t *testing.T) {
src, st := NewFakeAsks(), &kv{}
_ = src.PublishAsk(testAsk(delivery.AskDelivery))
var mu sync.Mutex
capacity := 0
p := &Puller{Source: src, Language: delivery.AskGo, Node: "novox", Put: st.put, PullWait: 10 * time.Millisecond,
Capacity: func() int { mu.Lock(); defer mu.Unlock(); return capacity },
Run: func(ctx context.Context, a delivery.StepAsk) (any, error) { return nil, nil }}
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
go p.Pull(ctx)
time.Sleep(50 * time.Millisecond)
if src.Waiting(delivery.AskDelivery) != 1 {
t.Fatal("a node at capacity 0 took an ask")
}
mu.Lock()
capacity = 1
mu.Unlock()
p.Wake()
waitFor(t, "the ask taken at capacity 1", func() bool { a, _, _ := src.Fates(); return len(a) == 1 })
})
t.Run("config watch wakes", func(t *testing.T) {
src, st := NewFakeAsks(), newSteps()
_ = src.PublishAsk(testAsk(delivery.AskDelivery))
w := &configWatch{value: "shanks=3,g14=0"}
p := &Puller{Source: src, Language: delivery.AskGo, Node: "g14", Put: st.put, PullWait: 10 * time.Millisecond,
Capacity: func() int { return 0 }, // the settings file, not refilled yet
WatchConfig: w.watch,
Run: func(ctx context.Context, a delivery.StepAsk) (any, error) { return nil, nil }}
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
go p.Pull(ctx)
waitFor(t, "the watch of the capacity", func() bool { w.mu.Lock(); defer w.mu.Unlock(); return w.handle != nil })
time.Sleep(30 * time.Millisecond)
if src.Waiting(delivery.AskDelivery) != 1 {
t.Fatal("a node at capacity 0 took an ask")
}
if w.asked != CapacitySetting {
t.Fatalf("the puller watches %q, want %q", w.asked, CapacitySetting)
}
w.set(t, "shanks=3,g14=2")
waitFor(t, "the ask taken once the capacity moved to 2", func() bool { a, _, _ := src.Fates(); return len(a) == 1 })
})
for _, c := range []struct {
name string
watch func(string, func(stdio.ProvisionChange) error) error
room bool
}{
{"refused value leaves no room", func(key string, handle func(stdio.ProvisionChange) error) error {
return handle(stdio.ProvisionChange{Kind: "config", Key: key, Refused: "the module is no longer on g14"})
}, false},
{"watch that cannot start keeps the settings file", func(string, func(stdio.ProvisionChange) error) error {
return errors.New("no runtime")
}, true},
} {
t.Run(c.name, func(t *testing.T) {
p := &Puller{Source: NewFakeAsks(), Language: delivery.AskGo, Node: "g14", Put: newSteps().put,
Capacity: func() int { return 1 }, WatchConfig: c.watch,
Run: func(ctx context.Context, a delivery.StepAsk) (any, error) { return nil, nil }}
p.watchCapacity()
if p.room() != c.room {
t.Fatalf("room = %v, want %v", p.room(), c.room)
}
})
src, st := NewFakeAsks(), &kv{}
_ = src.PublishAsk(testAsk(delivery.AskDelivery))
var mu sync.Mutex
capacity := 0
p := &Puller{Source: src, Language: delivery.AskGo, Node: "novox", Put: st.put, PullWait: 10 * time.Millisecond,
Capacity: func() int { mu.Lock(); defer mu.Unlock(); return capacity },
Run: func(ctx context.Context, a delivery.StepAsk) (any, error) { return nil, nil }}
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
go p.Pull(ctx)
time.Sleep(50 * time.Millisecond)
if src.Waiting(delivery.AskDelivery) != 1 {
t.Fatal("a node at capacity 0 took an ask")
}
mu.Lock()
capacity = 1
mu.Unlock()
p.Wake()
waitFor(t, "the ask taken at capacity 1", func() bool { a, _, _ := src.Fates(); return len(a) == 1 })
}
// 1887/A2b: a paused puller takes nothing, its pause is kept on the pause key, and a puller started again on that state
// stays paused until resumed.
func TestPullPauseOutlivesARestart(t *testing.T) {
src, st, steps := NewFakeAsks(), &kv{}, &kv{}
src, st := NewFakeAsks(), &kv{}
run := func(ctx context.Context, a delivery.StepAsk) (any, error) { return nil, nil }
p := &Puller{Source: src, Language: delivery.AskGo, Node: "shanks", Put: steps.put, PausePut: st.put, Load: st.load,
PullWait: 10 * time.Millisecond, Capacity: func() int { return 2 }, Run: run}
p := &Puller{Source: src, Language: delivery.AskGo, Node: "shanks", Put: st.put, Load: st.load, PullWait: 10 * time.Millisecond,
Capacity: func() int { return 2 }, Run: run}
if err := p.Pause("the operator"); err != nil {
t.Fatal(err)
}
@@ -266,12 +213,9 @@ func TestPullPauseOutlivesARestart(t *testing.T) {
if v, err := delivery.DecodePause(raw); err != nil || !v.Paused || v.By != "the operator" {
t.Fatalf("the pause key holds %s (%v)", raw, err)
}
if raw, _ := steps.load(key); raw != nil {
t.Fatalf("the pause was written in the steps state, whose keys age out: %s", raw)
}
// The restart: a new puller on the same state.
again := &Puller{Source: src, Language: delivery.AskGo, Node: "shanks", Put: steps.put, PausePut: st.put, Load: st.load,
PullWait: 10 * time.Millisecond, Capacity: func() int { return 2 }, Run: run}
again := &Puller{Source: src, Language: delivery.AskGo, Node: "shanks", Put: st.put, Load: st.load, PullWait: 10 * time.Millisecond,
Capacity: func() int { return 2 }, Run: run}
_ = src.PublishAsk(testAsk(delivery.AskDelivery))
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
@@ -284,27 +228,6 @@ func TestPullPauseOutlivesARestart(t *testing.T) {
t.Fatal(err)
}
waitFor(t, "the ask taken after the resume", func() bool { a, _, _ := src.Fates(); return len(a) == 1 })
t.Run("a pause that cannot be read is said and pulled as not paused", func(t *testing.T) {
src := NewFakeAsks()
var said atomic.Value
p := &Puller{Source: src, Language: delivery.AskGo, Node: "shanks", Put: steps.put, PausePut: st.put,
Load: func(string) ([]byte, error) { return nil, errors.New("no runtime yet") },
PullWait: 10 * time.Millisecond, Capacity: func() int { return 2 }, Run: run,
Logf: func(f string, a ...any) {
if m := fmt.Sprintf(f, a...); strings.Contains(m, "cannot be read") {
said.Store(m)
}
}}
_ = src.PublishAsk(testAsk(delivery.AskDelivery))
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
go p.Pull(ctx)
waitFor(t, "the ask taken", func() bool { a, _, _ := src.Fates(); return len(a) == 1 })
if m, _ := said.Load().(string); !strings.Contains(m, "pulling as not paused") {
t.Fatalf("the unreadable pause was not said: %q", m)
}
})
}
// 1887/A2c: a long step tells the bus it is still being worked; a holder that stops mid-step neither ends nor
+5 -1
View File
@@ -14,7 +14,11 @@ func SeatTools(seat, what string, p *Puller) []stdio.Tool {
Run: func(map[string]any) (any, error) { return run() }}
}
current := func() (any, error) {
return map[string]any{"node": p.Node, "capacity": p.CapacityNow(), "running": p.Running(), "paused": p.Paused()}, nil
capacity := 0
if p.Capacity != nil {
capacity = p.Capacity()
}
return map[string]any{"node": p.Node, "capacity": capacity, "running": p.Running(), "paused": p.Paused()}, nil
}
return []stdio.Tool{
verb("current", "The "+what+" asks this node runs now (each one's id, kind and when it started), its build capacity, "+
+2 -12
View File
@@ -181,25 +181,15 @@ type Want struct {
Rule int `json:"rule,omitempty"`
Backup string `json:"backup,omitempty"`
Words string `json:"words,omitempty"`
// Put says the want was written by a put (ADR 0546), and Hold that the put holds it: the rules pass over it until it
// is released. A put's want names no newest fingerprint or rule.
Put bool `json:"put,omitempty"`
Hold bool `json:"hold,omitempty"`
}
func (w Want) check() error {
if w.Removed {
if w.FP != "" || w.Composed != "" || w.Newest != "" || w.Rule != 0 || w.Backup != "" || w.Put || w.Hold {
return fmt.Errorf("delivery: a removed want names no fingerprint, composition, rule, backup answer or put")
if w.FP != "" || w.Composed != "" || w.Newest != "" || w.Rule != 0 || w.Backup != "" {
return fmt.Errorf("delivery: a removed want names no fingerprint, composition, rule or backup answer")
}
return nil
}
if w.Hold && !w.Put {
return fmt.Errorf("delivery: only a put holds a want")
}
if w.Put && (w.Newest != "" || w.Rule != 0) {
return fmt.Errorf("delivery: a put's want is held back by no rule")
}
if err := checkFingerprint(w.FP, "a want's fingerprint"); err != nil {
return err
}
-52
View File
@@ -4,7 +4,6 @@ import (
"errors"
"strings"
"testing"
"time"
)
// 1297/B1a: a want key round-trips through its parser; a held key, a have key and a node's own key are refused,
@@ -78,7 +77,6 @@ func TestAssignerValuesRoundTrip(t *testing.T) {
{FP: fp2of('a'), Composed: hashOf('1')},
{FP: fp2of('a'), Composed: hashOf('1'), Newest: fp2of('b'), Rule: RuleCanary, Words: "the canary ace does not run it healthy yet"},
{Removed: true, Words: "the module left g14"},
{FP: fp2of('a'), Composed: hashOf('1'), Put: true, Hold: true, Words: "put by the operator: the bus's user list"},
}
for _, w := range wants {
data, err := EncodeWant(w)
@@ -91,24 +89,6 @@ func TestAssignerValuesRoundTrip(t *testing.T) {
t.Errorf("want %+v came back %+v, %v", w, got, err)
}
}
at := time.Date(2026, 10, 25, 21, 0, 0, 0, time.UTC)
p := Put{FP: fp2of('a'), Hold: true, Why: "the bus's user list", By: "shanks.node-tools", At: at}.Said(at, PutAsked, "put asked")
p = p.Said(at, PutAsked, "put asked").Said(at.Add(time.Second), PutWanted, "want written")
p.Composed = hashOf('1')
if len(p.Steps) != 2 || p.Step != PutWanted || PutEnded(p.Step) || !PutEnded(PutReleased) {
t.Errorf("a put's steps are %+v at %s", p.Steps, p.Step)
}
pkey, _ := PutKey("novox", "nats")
if n, m, err := ParsePutKey(pkey); err != nil || n != "novox" || m != "nats" {
t.Errorf("the put key %s reads %s %s, %v", pkey, n, m, err)
}
pdata, err := EncodePut(p)
if err != nil {
t.Fatal(err)
}
if gotP, err := DecodePut(pdata); err != nil || gotP.FP != p.FP || gotP.Step != PutWanted || len(gotP.Steps) != 2 || !gotP.Hold {
t.Errorf("the put came back %+v, %v", gotP, err)
}
h := Held{Node: "ace", Words: "its health check failed: connection refused"}
data, err := EncodeHeld(h)
if err != nil {
@@ -148,9 +128,6 @@ func TestAssignerValuesRefused(t *testing.T) {
{FP: fp2of('a'), Newest: fp2of('b')},
{FP: fp2of('a'), Newest: fp2of('a'), Rule: 3},
{FP: fp2of('a'), Composed: hashOf('1'), Newest: fp2of('b'), Rule: 8},
{FP: fp2of('a'), Composed: hashOf('1'), Hold: true},
{FP: fp2of('a'), Composed: hashOf('1'), Put: true, Newest: fp2of('b'), Rule: 3},
{Removed: true, Put: true},
} {
if _, err := EncodeWant(w); err == nil {
t.Errorf("EncodeWant(%+v) accepted", w)
@@ -171,19 +148,6 @@ func TestAssignerValuesRefused(t *testing.T) {
t.Errorf("EncodeDifference(%+v) accepted", d)
}
}
for _, p := range []Put{
{FP: fp2of('a'), Why: "w", Step: "walking"},
{FP: fp2of('a'), Step: PutAsked},
{FP: "src2:abc", Why: "w", Step: PutAsked},
{FP: fp2of('a'), Why: "w", Step: PutWanted, Composed: "sha256:x"},
} {
if _, err := EncodePut(p); err == nil {
t.Errorf("EncodePut(%+v) accepted", p)
}
}
if _, _, err := ParsePutKey("ace.node"); err == nil {
t.Errorf("a node's own key was read as a put")
}
if _, err := DecodeWant([]byte(`{"v":2,"fp":"` + fp2of('a') + `"}`)); !errors.Is(err, ErrUnknownVersion) {
t.Errorf("a want of version 2 was read: %v", err)
}
@@ -298,20 +262,4 @@ func TestControllerGrant(t *testing.T) {
if _, err := EncodeControllerGrant(ControllerGrant{Accounts: []string{""}}); err == nil {
t.Errorf("a grant naming an empty account was accepted")
}
g := ControllerGrant{Accounts: []string{"ace.mesh-build-go", "shanks.mesh-mail.reader"}}
for _, c := range []struct {
g ControllerGrant
node, module string
names bool
}{
{g, "ace", "mesh-build-go", true},
{g, "shanks", "mesh-mail", true},
{g, "g14", "mesh-build-go", false},
{g, "ace", "mesh-build", false},
{ControllerGrant{}, "novox", "nats", true},
} {
if got := c.g.NamesNode(c.node, c.module); got != c.names {
t.Errorf("%v names %s.%s: %v, want %v", c.g.Accounts, c.node, c.module, got, c.names)
}
}
}
+27
View File
@@ -0,0 +1,27 @@
package delivery
import (
"strings"
"testing"
)
// 1791/1921 S9: a member of a group that merged stays in the candidate, marked merged, with its head, so the heads hash
// the Approve covers holds until every member merged; a candidate whose every member merged is refused.
func TestACandidateKeepsAMergedMemberAndRefusesOneWhoseEveryMemberMerged(t *testing.T) {
a := Head{Repository: "novox/a", Number: 1, Head: strings.Repeat("1", 40)}
b := Head{Repository: "novox/b", Number: 2, Head: strings.Repeat("2", 40)}
hash, _ := HeadsHash([]Head{a, b})
c := Candidate{Group: "feat/x", HeadsHash: hash, Pulls: []CandidatePull{{Head: a, Modules: []string{}, Merged: true}, {Head: b, Modules: []string{}}}}
raw, err := EncodeCandidate(c)
if err != nil {
t.Fatal(err)
}
back, err := DecodeCandidate(raw)
if err != nil || !back.Pulls[0].Merged || back.Pulls[1].Merged || back.HeadsHash != hash {
t.Fatalf("read back %+v, %v", back, err)
}
c.Pulls[1].Merged = true
if _, err := EncodeCandidate(c); err == nil {
t.Error("a candidate whose every member merged was written")
}
}
+21 -6
View File
@@ -139,16 +139,25 @@ type FailedFirst struct {
Words string `json:"words,omitempty"`
}
// MaxFailures is the most entries a verdict's Failures holds (issue 1921): fifty tests named one by one, and an entry
// after them saying how many more failed.
const MaxFailures = 50
// Verdict is the value of a verdict key: the group and its heads hash, the trunk head of each repository it was judged
// against (repository to full sha), the State (running, pass or fail), what failed first, the tests run and kept per
// level, each part's time, the machines composed and the mesh-sdk version the composition ran with (ADR 0446 clause 5).
type Verdict struct {
V int `json:"v"`
Group string `json:"group"`
Heads string `json:"heads"`
Trunk map[string]string `json:"trunk,omitempty"`
State string `json:"state"`
Failed FailedFirst `json:"failed,omitzero"`
V int `json:"v"`
Group string `json:"group"`
Heads string `json:"heads"`
Trunk map[string]string `json:"trunk,omitempty"`
State string `json:"state"`
Failed FailedFirst `json:"failed,omitzero"`
// Failures names every test that failed, in the order judged, each with the first line of its words (issue 1921):
// Failed keeps the first one's words whole, and a check that ran every test says all it found here. At most
// MaxFailures entries, the last of a longer list saying how many more failed. Absent in a value written before it,
// and from a verdict whose failure is no test.
Failures []FailedFirst `json:"failures,omitempty"`
Levels map[string]LevelResult `json:"levels,omitempty"`
Took Took `json:"took,omitzero"`
Machines []string `json:"machines,omitempty"`
@@ -222,6 +231,12 @@ func (v Verdict) check() error {
}
}
named := v.Failed.Test != "" || v.Failed.Machine != ""
if len(v.Failures) > 0 && v.State != VerdictFail {
return fmt.Errorf("delivery: a %s verdict names no failures", v.State)
}
if len(v.Failures) > MaxFailures+1 {
return fmt.Errorf("delivery: the verdict names %d failures, more than %d and the count of the rest", len(v.Failures), MaxFailures)
}
switch v.State {
case VerdictRunning:
if v.Failed != (FailedFirst{}) {
+36
View File
@@ -3,6 +3,7 @@ package delivery
import (
"encoding/json"
"errors"
"strconv"
"strings"
"testing"
"time"
@@ -600,3 +601,38 @@ func TestPreviewOfAHeadInConflict(t *testing.T) {
t.Errorf("the old reader: %+v %v", old, err)
}
}
// Issue 1921: a failed verdict names every failed test in Failures and reads back the same; an older reader's value
// without it reads too; Failures on a verdict that is no fail, and more than MaxFailures and the count of the rest, are
// refused.
func TestVerdictNamesEveryFailure(t *testing.T) {
v := passVerdict()
v.State = VerdictFail
v.Failed = FailedFirst{Test: "integration: x/a.TestA", Words: "a_test.go:9: want 1, got 2\nmore"}
v.Failures = []FailedFirst{{Test: "integration: x/a.TestA", Words: "a_test.go:9: want 1, got 2"}, {Test: "integration: x/b.TestB", Words: "b_test.go:3: boom"}}
data, err := EncodeVerdict(v)
if err != nil {
t.Fatal(err)
}
got, err := DecodeVerdict(data)
v.V = Version
if err != nil || !SameVerdict(got, v) || !strings.Contains(string(data), `"failures":[{"test":"integration: x/a.TestA"`) {
t.Fatalf("%s: %+v %v", data, got, err)
}
old := strings.Replace(string(data), string(data[strings.Index(string(data), `,"failures":`):strings.Index(string(data), `,"levels":`)]), "", 1)
if got, err := DecodeVerdict([]byte(old)); err != nil || len(got.Failures) != 0 || got.Failed != v.Failed {
t.Fatalf("a value without failures: %+v %v (%s)", got, err, old)
}
p := passVerdict()
p.Failures = v.Failures
if _, err := EncodeVerdict(p); err == nil {
t.Error("a pass with failures was written")
}
v.Failures = make([]FailedFirst, MaxFailures+2)
for i := range v.Failures {
v.Failures[i] = FailedFirst{Test: "unit: x.T" + strconv.Itoa(i)}
}
if _, err := EncodeVerdict(v); err == nil {
t.Error("a verdict naming more than MaxFailures and the rest was written")
}
}
-17
View File
@@ -73,20 +73,3 @@ func DecodeControllerGrant(data []byte) (ControllerGrant, error) {
// SameControllerGrant says whether two grants are the same value.
func SameControllerGrant(a, b ControllerGrant) bool { return reflect.DeepEqual(a, b) }
// NamesNode says whether the grant names module's accounts on node: its own `<node>.<module>` or a process's
// `<node>.<module>.<process>`. A grant that names no account (a module that does not speak on the bus) names every
// node. The assigner wants a node only once the grant names its account (issue 1945), and a put waits for it (ADR
// 0546 clause 4).
func (g ControllerGrant) NamesNode(node, module string) bool {
if len(g.Accounts) == 0 {
return true
}
own := node + "." + module
for _, a := range g.Accounts {
if a == own || strings.HasPrefix(a, own+".") {
return true
}
}
return false
}
-148
View File
@@ -1,148 +0,0 @@
package delivery
import (
"encoding/json"
"fmt"
"time"
)
// A put (novox/hq ADR 0546): one version of a module put on one node by the assigner's tool `assigner_put`. Each put is the
// key `<node>.<module>` of the assigner's state puts, which holds the version asked, the hold, why, and each step the
// assigner took or waits on, so a reader watches the key to follow it. The want the put writes carries Put (and Hold),
// so the assigner's rules pass over that key while the put holds it.
// AssignerPutsBucket is the assigner's bucket of puts, `<owner module>_puts`.
const AssignerPutsBucket = AssignerModule + "_puts"
// AssignerPutsHistory is the revisions the puts bucket keeps per key: each step of a put is one.
const AssignerPutsHistory = 20
// A put's steps, in the order they are taken (ADR 0546 clauses 3 to 9). A put stands at the last step written.
const (
// PutAsked is a put written by the tool, not taken up by a pass yet.
PutAsked = "asked"
// PutBuild waits for the builder's build at the fingerprint.
PutBuild = "build"
// PutCompose waits for the controller's composition (and grant) at the fingerprint.
PutCompose = "compose"
// PutPerson waits for the operator's answer to the ask about the move.
PutPerson = "person"
// PutSnapshot waits for the bus's streams to be snapshotted after the operator's yes.
PutSnapshot = "snapshot"
// PutWanted is the want written: the node's have has not reached it yet.
PutWanted = "wanted"
// PutHolding is a held put whose have runs it healthy: the want stays until released.
PutHolding = "holding"
// PutDone is a put without hold whose have ran it healthy: the rules write the want again.
PutDone = "done"
// PutReleased is a put released by the tool `assigner_release`.
PutReleased = "released"
// PutRefused is a put that cannot go on: a build that failed, an answer no, a snapshot not taken. Its words say why.
PutRefused = "refused"
)
// PutEnded says a put at this step is over: nothing more is done for it and the rules own the want.
func PutEnded(step string) bool {
return step == PutDone || step == PutReleased || step == PutRefused
}
// PutStep is one step a put took: when, which, and what was done or waits, in a sentence.
type PutStep struct {
At time.Time `json:"at"`
Step string `json:"step"`
Words string `json:"words"`
}
// PutStepsKept is how many steps a put keeps, newest last.
const PutStepsKept = 16
// Put is the value of a key of AssignerPutsBucket.
type Put struct {
V int `json:"v"`
// FP is the fingerprint put, of the new form.
FP string `json:"fp"`
// Hold keeps the want at FP until released.
Hold bool `json:"hold,omitempty"`
Why string `json:"why"`
// By is who asked, as the bus named the caller; "unproven" when it named none.
By string `json:"by,omitempty"`
At time.Time `json:"at"`
// Step is where the put stands now, one of the Put* steps; Words say it in a sentence.
Step string `json:"step"`
Words string `json:"words,omitempty"`
// Composed is the digest of the composition the want names, once known.
Composed string `json:"composed,omitempty"`
// Ask is the key, in AssignerAsksBucket, of the ask about the move, once asked.
Ask string `json:"ask,omitempty"`
// Snapshot says where the bus's streams were snapshotted, once they were.
Snapshot string `json:"snapshot,omitempty"`
// Steps are the steps taken, oldest first, at most PutStepsKept.
Steps []PutStep `json:"steps,omitempty"`
}
// Said is p at step with words, the step added to its steps when it differs from the last one.
func (p Put) Said(at time.Time, step, words string) Put {
if p.Step == step && p.Words == words {
return p
}
p.Step, p.Words = step, words
p.Steps = append(append([]PutStep(nil), p.Steps...), PutStep{At: at.UTC(), Step: step, Words: words})
if len(p.Steps) > PutStepsKept {
p.Steps = p.Steps[len(p.Steps)-PutStepsKept:]
}
return p
}
func (p Put) check() error {
if err := checkFingerprint(p.FP, "a put's fingerprint"); err != nil {
return err
}
if p.Why == "" {
return fmt.Errorf("delivery: a put says why")
}
switch p.Step {
case PutAsked, PutBuild, PutCompose, PutPerson, PutSnapshot, PutWanted, PutHolding, PutDone, PutReleased, PutRefused:
default:
return fmt.Errorf("delivery: %q is not a step of a put", p.Step)
}
if p.Composed != "" {
return checkDigest(p.Composed, "a put's composition digest")
}
return nil
}
// PutKey is the key, in AssignerPutsBucket, of the put of module on node: `<node>.<module>`.
func PutKey(node, module string) (string, error) {
return HaveKey(node, module)
}
// ParsePutKey reads a PutKey.
func ParsePutKey(key string) (node, module string, err error) {
node, module, isNode, err := ParseHaveKey(key)
if err == nil && isNode {
err = fmt.Errorf("delivery: %q is a node's own key, and no put", key)
}
return node, module, err
}
// EncodePut is p as JSON at Version; it refuses a fingerprint not of the new form, a put that says no why and an
// unknown step.
func EncodePut(p Put) ([]byte, error) {
if err := p.check(); err != nil {
return nil, err
}
p.V = Version
return json.Marshal(p)
}
// DecodePut reads a put; it refuses an unknown version (ErrUnknownVersion) and what EncodePut refuses.
func DecodePut(data []byte) (Put, error) {
var p Put
if err := decode(data, &p); err != nil {
return Put{}, err
}
if err := p.check(); err != nil {
return Put{}, err
}
return p, nil
}
+11
View File
@@ -269,6 +269,10 @@ type CandidatePull struct {
Head
Modules []string `json:"modules"`
Fps map[string]CandidateModule `json:"fps,omitempty"`
// Merged says the pull request merged while another member of its group is still open: it stays in the candidate
// with the head it merged at, so the heads hash an Approve covers holds until every member merged, and the checker
// judges the members still open by the verdict the group had (issue 1791). A reader of the older shape ignores it.
Merged bool `json:"merged,omitempty"`
}
// CandidateNoneNoModule is the None2 of a candidate's module whose directory the merge preview names no manifest for:
@@ -346,6 +350,13 @@ func (c Candidate) check() error {
if len(c.Pulls) == 0 {
return fmt.Errorf("delivery: a candidate names no pull request")
}
open := false
for _, p := range c.Pulls {
open = open || !p.Merged
}
if !open {
return fmt.Errorf("delivery: every pull request of the candidate merged: the group is no candidate any more")
}
heads := make([]Head, len(c.Pulls))
for i, p := range c.Pulls {
heads[i] = p.Head
+2 -6
View File
@@ -535,13 +535,9 @@ func ParseAskStepKey(key string) (node, askID string, err error) {
return node, askID, nil
}
// PausesState is the state a build module keeps its nodes' pause keys in. It has no age, unlike StepsState, whose keys
// are per step and dropped after their age: a pause kept among the steps would end by itself.
const PausesState = "pauses"
// PauseKey is the key, in a build module's PausesState, that keeps whether the module on node takes asks:
// PauseKey is the key, in a build module's StepsBucket, that keeps whether the module on node takes asks:
// `paused.<node>` (issue 1887's design limit 2: every holder pulls from one shared worker, so a node's pause is its holder
// not fetching, kept so a restart keeps it). A pause key is never an ask's step key: its second part is a node.
// not fetching, kept here so a restart keeps it). A pause key is never an ask's step key: its second part is a node.
func PauseKey(node string) (string, error) {
if err := checkName("node", node); err != nil {
return "", err
+1 -7
View File
@@ -283,15 +283,9 @@ func ViewAnswerFits(a ViewAnswer, ask AssignerAsk) error {
if a.Asking != ask.Ask.ID {
return fmt.Errorf("delivery: the view's answer is to the asking %s, and the ask stands at the asking %s", a.Asking, ask.Ask.ID)
}
o, ok := ask.Ask.Option(a.Option)
if !ok {
if _, ok := ask.Ask.Option(a.Option); !ok {
return fmt.Errorf("delivery: the view's answer chose %q, which the asking %s does not offer", a.Option, ask.Ask.ID)
}
if o.Level != "" && o.Level != asks.Acknowledge {
// An option that authorises is answered on a channel that proves who answered (ADR 0259 §5, ADR 0546 clause 8),
// never in the view, which proves nobody.
return fmt.Errorf("delivery: the view's answer chose %q, an option of level %s, which only a channel that proves who answered takes", a.Option, o.Level)
}
return nil
}
-7
View File
@@ -158,11 +158,4 @@ func TestViewAnswerFits(t *testing.T) {
if err := ViewAnswerFits(ViewAnswer{Asking: first.Ask.ID, Option: "restore"}, first); err == nil {
t.Errorf("an option the ask does not offer fits")
}
// An option that authorises is never answered in the view (ADR 0546 clause 8).
approving := first
approving.Ask.Options = append([]asks.Option(nil), first.Ask.Options...)
approving.Ask.Options[0].Level = asks.Approve
if err := ViewAnswerFits(answer, approving); err == nil || !strings.Contains(err.Error(), "approve") {
t.Errorf("the view answered an option of level approve: %v", err)
}
}
-32
View File
@@ -1,16 +1,11 @@
package process
import (
"context"
"encoding/json"
"errors"
"fmt"
"os"
"path/filepath"
"strings"
"testing"
"github.com/nats-io/nats.go/jetstream"
)
// 1171/AC2: given an account file broker-<process id> in the controller's form {url, fingerprint, node,
@@ -51,28 +46,6 @@ func TestReadAccountToleratesNoClaimsAtAll(t *testing.T) {
// 1171/AC2: a file missing url, user or password is refused, naming the field; the password never appears
// in the error even when it is the field present and another is missing.
func TestReadAccountRefusesAFileMissingAField(t *testing.T) {
t.Run("1945: a refused bucket stops a start only when the part cannot work without it", func(t *testing.T) {
refusal := errors.New("nats: permissions violation for publish to $JS.API.STREAM.INFO.KV_mesh-delivery-gate_source")
for _, c := range []struct {
name string
err error
}{{"refused", refusal}, {"not answered", context.DeadlineExceeded}} {
var said []string
logf := func(f string, a ...any) { said = append(said, fmt.Sprintf(f, a...)) }
if kv := OptionalBucket(context.Background(), refusingBus{c.err}, "b", "b is not heard", logf); kv != nil {
t.Errorf("%s: an optional bucket answered %v", c.name, kv)
}
NotWatched(logf, "b", c.err, "b is not heard")
if len(said) != 2 || !strings.Contains(said[0], c.err.Error()) || !strings.Contains(said[1], "cannot be watched") {
t.Errorf("%s: said %q", c.name, said)
}
if _, err := EssentialBucket(context.Background(), refusingBus{c.err}, "builder", "b", "build"); err == nil ||
!strings.Contains(err.Error(), "grant of b") || !strings.Contains(err.Error(), "the builder cannot build") {
t.Errorf("%s: an essential bucket: %v", c.name, err)
}
}
})
for _, tc := range []struct {
field string
values map[string]any
@@ -109,8 +82,3 @@ func writeAccount(t *testing.T, fields map[string]any) string {
}
return path
}
// refusingBus refuses every bucket with err.
type refusingBus struct{ err error }
func (r refusingBus) KeyValue(context.Context, string) (jetstream.KeyValue, error) { return nil, r.err }
-55
View File
@@ -1,55 +0,0 @@
package process
import (
"context"
"fmt"
"github.com/nats-io/nats.go/jetstream"
)
// **A part does not stop for a bucket it can work without** (novox/hq issue 1945, met twice on 2026-10-25: the delivery
// builder exited on a refused read of the gate's source and crash-looped). A grant reaches the bus with a delivery, so a
// bucket, a watch or a consumer the bus refuses, or times out on, at start is often only not granted yet: exiting for it
// stops the part until a person's hand. A part opens what it cannot do its job at all without with EssentialBucket, which
// stops its start with an error naming the bucket and its grant, and everything else with OptionalBucket, which says what
// is not heard and goes on; a watch the bus refuses on an optional bucket is said with NotWatched. Here, beside State,
// because this is where a process opens what it keeps and reads on the bus; the parts that open buckets with their own
// JetStream (the delivery parts) take the same three.
// BucketOpener is the part of the bus a start opens buckets with: a jetstream.JetStream, or a test's fake.
type BucketOpener interface {
KeyValue(ctx context.Context, bucket string) (jetstream.KeyValue, error)
}
// EssentialBucket opens a bucket part cannot work without (it cannot `does` without it); its error is EssentialErr's.
func EssentialBucket(ctx context.Context, js BucketOpener, part, name, does string) (jetstream.KeyValue, error) {
kv, err := js.KeyValue(ctx, name)
if err != nil {
return nil, EssentialErr(part, name, does, err)
}
return kv, nil
}
// EssentialErr is the error of a bucket, consumer or stream named name that part cannot work without: it says what part
// cannot do, that it stops, and the grant to look at.
func EssentialErr(part, name, does string, err error) error {
return fmt.Errorf("%s cannot be read (%v): the %s cannot %s without it, so it stops; where the bus refused it or did not "+
"answer, this module's grant of %s (its manifest's reads, state or consumes, issued with its credential) has not "+
"reached the bus yet", name, err, part, does, name)
}
// OptionalBucket opens a bucket the part works without: any error is said with what is not heard (without), and nil
// answered.
func OptionalBucket(ctx context.Context, js BucketOpener, name, without string, logf func(string, ...any)) jetstream.KeyValue {
kv, err := js.KeyValue(ctx, name)
if err != nil {
logf("the bucket %s cannot be read (%v): %s", name, err, without)
return nil
}
return kv
}
// NotWatched says that an optional bucket opened but its watch was refused or not answered: what is not heard.
func NotWatched(logf func(string, ...any), name string, err error, without string) {
logf("the bucket %s cannot be watched (%v): %s", name, err, without)
}
-8
View File
@@ -154,15 +154,8 @@ const CodeChanged = -32010
var (
current *channel
currentMu sync.Mutex
// served is closed once Serve has the runtime's channel (Served).
served = make(chan struct{})
servedOnce sync.Once
)
// Served is closed once Serve has the runtime's channel, so code started before Serve can wait for it instead of
// asking again until the runtime takes it: a watch of a config value, a subscribe.
func Served() <-chan struct{} { return served }
// Serve answers the runtime on stdin and stdout until stdin closes. An empty name serves as the
// module the runtime named in MESH_SERVED_MODULE.
func Serve(name string, tools []Tool) error {
@@ -187,7 +180,6 @@ func ServeOn(name string, tools []Tool, in io.Reader, out io.Writer) error {
currentMu.Lock()
current = c
currentMu.Unlock()
servedOnce.Do(func() { close(served) })
// What the bundle said it keeps is announced once it serves: the runtime answers the publish on this channel, so
// it is asked from beside the loop that reads the answer.
go func() { _ = announce1() }()
-21
View File
@@ -16,22 +16,6 @@ func TestABundleEmitsThroughTheRuntimeAndServesAsItsModule(t *testing.T) {
t.Setenv(ServedAs, "chime")
t.Setenv("MESH_MODULE", "chime")
t.Setenv("MESH_NODE", "anchor")
// 1887/AC-wake: Served closes once Serve has the runtime's channel, not before; the globals are put back after.
oldServed := served
served, servedOnce = make(chan struct{}), sync.Once{}
t.Cleanup(func() {
served, servedOnce = oldServed, sync.Once{}
select {
case <-oldServed: // it was closed: its Once is spent too
servedOnce.Do(func() {})
default:
}
})
select {
case <-Served():
t.Fatal("Served closed before Serve")
default:
}
inR, inW := io.Pipe()
outR, outW := io.Pipe()
go func() {
@@ -66,11 +50,6 @@ func TestABundleEmitsThroughTheRuntimeAndServesAsItsModule(t *testing.T) {
if got := next()["result"].(map[string]any)["serverInfo"].(map[string]any)["name"]; got != "chime" {
t.Fatalf("served as %v, want the module the runtime named", got)
}
select {
case <-Served():
case <-time.After(2 * time.Second):
t.Fatal("Served did not close once serving")
}
send(map[string]any{"jsonrpc": "2.0", "id": 2, "method": "tools/call", "params": map[string]any{"name": "ring", "arguments": map[string]any{}}})
asked := next()
if asked["method"] != "mesh/publish" {