Merge fix/build-cpu-yields into the composer half
mesh/delivery merged: source.main moved to novox/mesh-sdk@960d6c34d25e
mesh/check checking 4ef49d039195 on 960d6c34d25e
mesh/delivery merged: source.main moved to novox/mesh-sdk@960d6c34d25e
mesh/check checking 4ef49d039195 on 960d6c34d25e
This commit is contained in:
@@ -34,6 +34,9 @@ type AskSteps struct {
|
||||
// the module's sweep.
|
||||
Release func(workspace string) error
|
||||
Logf func(format string, args ...any)
|
||||
// Has says whether this node has a need a package's tests declare (delivery.AskNeeds, issue 890); a package needing
|
||||
// what it lacks is not tested here but named in the level's Unmet, for the asker to place. Nil has nothing.
|
||||
Has func(need string) bool
|
||||
}
|
||||
|
||||
// RunAsk runs ask's job with steps and answers a delivery.BuildAnswer or a delivery.CheckAnswer.
|
||||
@@ -231,6 +234,9 @@ func (s AskSteps) level(ctx context.Context, job delivery.CheckJob, level string
|
||||
if !keepRunner {
|
||||
runner = "" // an installed module that ignores the runner judges the level as it judges any other (ADR 0535 §2)
|
||||
}
|
||||
if whole && len(job.Packages) > 0 {
|
||||
todo, whole = job.Packages, false // a placed ask tests its packages alone, whatever the digest said (ADR 0552 §4)
|
||||
}
|
||||
for _, priority := range []bool{true, false} {
|
||||
args := withRunner(map[string]any{"workspace": f.Workspace, "level": level})
|
||||
if job.Run != "" {
|
||||
@@ -307,9 +313,16 @@ func (s AskSteps) plan(ctx context.Context, job delivery.CheckJob, level string,
|
||||
return nil, true, runner != "" // a digest that names nothing or not the siblings keys no verdict: the level runs whole
|
||||
}
|
||||
la.Digest = &d
|
||||
only := map[string]bool{}
|
||||
for _, p := range job.Packages {
|
||||
only[p] = true
|
||||
}
|
||||
var todo []string
|
||||
for _, pd := range d.Packages {
|
||||
p := pd.Package
|
||||
if len(only) > 0 && !only[p] {
|
||||
continue // a placed ask's other packages were judged by the first ask (ADR 0552 §4)
|
||||
}
|
||||
if job.Kept && s.Kept != nil {
|
||||
tests, found, err := s.Kept(ctx, level, pd.Digest)
|
||||
if err != nil && s.Logf != nil {
|
||||
@@ -320,6 +333,15 @@ func (s AskSteps) plan(ctx context.Context, job delivery.CheckJob, level string,
|
||||
continue
|
||||
}
|
||||
}
|
||||
if needs := d.NeedsOf(p); len(delivery.Lacks(needs, s.Has)) > 0 {
|
||||
// Its tests would only skip here (issue 890): it is left for a node that has what they need.
|
||||
la.Unmet = append(la.Unmet, delivery.PackageNeeds{Package: p, Needs: needs})
|
||||
if s.Logf != nil {
|
||||
s.Logf("the %s level of %s is left to a node with %s: this node lacks %s", level, p,
|
||||
strings.Join(needs, ", "), strings.Join(delivery.Lacks(needs, s.Has), ", "))
|
||||
}
|
||||
continue
|
||||
}
|
||||
todo = append(todo, p)
|
||||
}
|
||||
return todo, false, false
|
||||
|
||||
@@ -20,6 +20,7 @@ type recorder struct {
|
||||
fetch map[string]any
|
||||
tests map[string]bool // package or module directory -> passed
|
||||
digests map[string]string
|
||||
needs []delivery.PackageNeeds
|
||||
}
|
||||
|
||||
func (r *recorder) steps() AskSteps {
|
||||
@@ -35,8 +36,10 @@ func (r *recorder) steps() AskSteps {
|
||||
Build: call("build", func(args map[string]any) any {
|
||||
return map[string]any{"digest": "sha256:" + args["artifact"].(string), "reference": "artifact-store://" + args["artifact"].(string)}
|
||||
}),
|
||||
Copy: call("copy", func(args map[string]any) any { return map[string]any{"digest": "sha256:copied"} }),
|
||||
Digest: call("digest", func(map[string]any) any { return map[string]any{"level": "unit", "packages": r.digests} }),
|
||||
Copy: call("copy", func(args map[string]any) any { return map[string]any{"digest": "sha256:copied"} }),
|
||||
Digest: call("digest", func(map[string]any) any {
|
||||
return map[string]any{"level": "unit", "packages": r.digests, "needs": r.needs}
|
||||
}),
|
||||
Test: call("test", func(args map[string]any) any {
|
||||
passed := true
|
||||
if pkgs, ok := args["packages"].([]string); ok {
|
||||
@@ -139,6 +142,43 @@ test {"level":"unit","packages":["x/pkg/a"],"workspace":"/w"}`
|
||||
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)
|
||||
}
|
||||
|
||||
// Issue 890/AC2: a package declaring node-build-node is not tested on a node that lacks it but named unmet, and is
|
||||
// tested on a node that has it.
|
||||
for _, has := range []bool{false, true} {
|
||||
r.calls, r.tests["x/pkg/b"] = nil, true
|
||||
r.needs = []delivery.PackageNeeds{{Package: "x/pkg/a", Needs: []string{delivery.NeedNodeBuildNode}}}
|
||||
steps := r.steps()
|
||||
if has {
|
||||
steps.Has = func(n string) bool { return n == delivery.NeedNodeBuildNode }
|
||||
}
|
||||
out, err := RunAsk(context.Background(), steps, ask(delivery.CheckJob{Levels: []string{delivery.LevelUnit}, Kept: true,
|
||||
Fetch: map[string]any{"repository": "novox/x", "commit": runCommit}}))
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
u := out.(delivery.CheckAnswer).Levels[0]
|
||||
tested := strings.Contains(strings.Join(r.calls, "\n"), `"x/pkg/a"`)
|
||||
if tested != has || (len(u.Unmet) == 0) == !has || (!has && (u.Unmet[0].Package != "x/pkg/a" || delivery.UnmetNeeds([]delivery.LevelAnswer{u})[0] != delivery.NeedNodeBuildNode)) {
|
||||
t.Fatalf("has %v: tested x/pkg/a %v, unmet %+v, calls %v", has, tested, u.Unmet, r.calls)
|
||||
}
|
||||
}
|
||||
// A placed ask naming its packages tests those alone and takes no other's kept verdict, also when the level would
|
||||
// run whole (ADR 0552 §4).
|
||||
for _, digests := range []map[string]string{r.digests, nil} {
|
||||
r.calls, r.digests = nil, digests
|
||||
steps := r.steps()
|
||||
steps.Has = func(string) bool { return true }
|
||||
out, err := RunAsk(context.Background(), steps, ask(delivery.CheckJob{Levels: []string{delivery.LevelUnit}, Kept: true, Packages: []string{"x/pkg/a"},
|
||||
Fetch: map[string]any{"repository": "novox/x", "commit": runCommit}}))
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
u := out.(delivery.CheckAnswer).Levels[0]
|
||||
if last := r.calls[len(r.calls)-1]; !strings.HasSuffix(last, `"packages":["x/pkg/a"],"workspace":"/w"}`) || len(u.Kept) != 0 || len(u.Tests) != 1 {
|
||||
t.Fatalf("digests %v: calls %v, kept %+v: want x/pkg/a alone tested, nothing taken kept", digests != nil, r.calls, u.Kept)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// ADR 0535 §2, §4: a merge that changes the build module's own code is judged by the candidate's runner: its digest says
|
||||
|
||||
@@ -6,6 +6,7 @@ import (
|
||||
"errors"
|
||||
"fmt"
|
||||
"sort"
|
||||
"strings"
|
||||
"sync"
|
||||
"time"
|
||||
|
||||
@@ -76,6 +77,11 @@ type Puller struct {
|
||||
// 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
|
||||
// Has says whether this node has a need an ask names (delivery.AskNeeds, issue 890). An ask needing what it lacks is
|
||||
// declined: its step ends refused as declined (delivery.StepDeclined), the message is dropped for its asker to put
|
||||
// again, and the worker it came from is not looked at again until the next pull's wait, so a node lacking the need
|
||||
// does not take the asker's next copy at once. Nil has nothing.
|
||||
Has func(need string) bool
|
||||
|
||||
mu sync.Mutex
|
||||
inHand int
|
||||
@@ -86,6 +92,9 @@ type Puller struct {
|
||||
// watched is the capacity the config watch handed last, used in place of Capacity once hasWatched.
|
||||
watched int
|
||||
hasWatched bool
|
||||
// declined are the kinds whose worker handed an ask this node declined, left out of the pulls without a wait until
|
||||
// the next pull's wait ends.
|
||||
declined map[string]bool
|
||||
}
|
||||
|
||||
func (p *Puller) init() {
|
||||
@@ -283,17 +292,59 @@ func (p *Puller) Pull(ctx context.Context) error {
|
||||
|
||||
// next is one ask from the workers in their order: one already waiting on delivery, check or recheck, and when none
|
||||
// waits, a pull of the delivery worker that waits for one.
|
||||
//
|
||||
// A kind whose worker handed an ask this node declined is left out until that wait ended (issue 890): the pull's own
|
||||
// wait, no timer of its own.
|
||||
func (p *Puller) next(ctx context.Context, wait time.Duration) (*Pulled, error) {
|
||||
p.mu.Lock()
|
||||
declined := p.declined
|
||||
p.mu.Unlock()
|
||||
for _, kind := range delivery.AskKinds {
|
||||
if declined[kind] {
|
||||
continue
|
||||
}
|
||||
msg, err := p.Source.Next(ctx, kind, 0)
|
||||
if err != nil || msg != nil {
|
||||
return withKind(msg, kind), err
|
||||
}
|
||||
}
|
||||
msg, err := p.Source.Next(ctx, delivery.AskDelivery, wait)
|
||||
p.mu.Lock()
|
||||
p.declined = nil
|
||||
p.mu.Unlock()
|
||||
return withKind(msg, delivery.AskDelivery), err
|
||||
}
|
||||
|
||||
// decline ends the step of an ask this node lacks a need of, refused as declined with what it lacks, and drops the
|
||||
// message: the asker puts the ask again under a new id (issue 890). A message whose decline cannot be written is handed
|
||||
// back, as one whose start cannot be.
|
||||
func (p *Puller) decline(msg *Pulled, ask delivery.StepAsk, lacks []string) {
|
||||
step, key, err := begin(p.Put, p.Node, ask.Kind+" ask", ask.ID, AskWhat(ask))
|
||||
if err == nil {
|
||||
why := Refuse("the ask %s needs %s, and %s lacks %s: it is left to a node that has it", ask.ID,
|
||||
strings.Join(ask.Needs, ", "), p.Node, strings.Join(lacks, ", "))
|
||||
step.Ended = now().UTC()
|
||||
step.State, step.Reason = delivery.StepRefused, why.Error()
|
||||
step.Result, err = json.Marshal(delivery.StepDeclined{Declined: true, Needs: ask.Needs, Lacks: lacks})
|
||||
if err == nil {
|
||||
err = writeEnd(p.Put, key, step)
|
||||
}
|
||||
}
|
||||
if err != nil {
|
||||
p.logf("the ask %s cannot be declined on %s, so it is given back: %v", ask.ID, p.Node, err)
|
||||
_ = msg.Nak()
|
||||
return
|
||||
}
|
||||
p.logf("the ask %s is declined on %s: it needs %s, and this node lacks %s", ask.ID, p.Node, strings.Join(ask.Needs, ", "), strings.Join(lacks, ", "))
|
||||
_ = msg.Term()
|
||||
p.mu.Lock()
|
||||
if p.declined == nil {
|
||||
p.declined = map[string]bool{}
|
||||
}
|
||||
p.declined[msg.Kind] = true
|
||||
p.mu.Unlock()
|
||||
}
|
||||
|
||||
func withKind(msg *Pulled, kind string) *Pulled {
|
||||
if msg != nil {
|
||||
msg.Kind = kind
|
||||
@@ -314,6 +365,10 @@ func (p *Puller) take(ctx context.Context, msg *Pulled) {
|
||||
_ = msg.Term()
|
||||
return
|
||||
}
|
||||
if lacks := delivery.Lacks(ask.Needs, p.Has); len(lacks) > 0 {
|
||||
p.decline(msg, ask, lacks)
|
||||
return
|
||||
}
|
||||
step, key, err := begin(p.Put, p.Node, ask.Kind+" ask", ask.ID, AskWhat(ask))
|
||||
if err != nil {
|
||||
p.logf("the ask %s cannot start on %s: %v", ask.ID, p.Node, err)
|
||||
|
||||
@@ -137,23 +137,42 @@ func TestPullHoldsAtMostItsCapacity(t *testing.T) {
|
||||
waitFor(t, "all acked", func() bool { a, _, _ := src.Fates(); return len(a) == 3 })
|
||||
}
|
||||
|
||||
// An ask that is not one, or not this seat's, is dropped and runs nowhere.
|
||||
// An ask that is not one, or not this seat's, is dropped and runs nowhere. And issue 890/AC1: a check ask needing
|
||||
// node-build-node is declined on a node that lacks it (its step refused as declined, naming what it lacks, the message
|
||||
// dropped for the asker to put again), and runs on a node that has it.
|
||||
func TestPullDropsWhatIsNoAsk(t *testing.T) {
|
||||
src, st := NewFakeAsks(), newSteps()
|
||||
src.Publish(delivery.AskDelivery, []byte(`{"v":1}`))
|
||||
other := testAsk(delivery.AskDelivery)
|
||||
other.Language = delivery.AskNode
|
||||
_ = src.PublishAsk(other)
|
||||
placed := testAsk(delivery.AskCheck)
|
||||
placed.Needs = []string{delivery.NeedNodeBuildNode}
|
||||
if err := src.PublishAsk(placed); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
ran := false
|
||||
p := &Puller{Source: src, Language: delivery.AskGo, Node: "shanks", Put: st.put, Capacity: func() int { return 1 },
|
||||
p := &Puller{Source: src, Language: delivery.AskGo, Node: "ace", Put: st.put, Capacity: func() int { return 1 },
|
||||
PullWait: 10 * time.Millisecond, Run: func(ctx context.Context, a delivery.StepAsk) (any, error) { ran = true; return nil, nil }}
|
||||
ctx, cancel := context.WithCancel(context.Background())
|
||||
defer cancel()
|
||||
go p.Pull(ctx)
|
||||
waitFor(t, "two termed", func() bool { _, tm, _ := src.Fates(); return len(tm) == 2 })
|
||||
waitFor(t, "three termed", func() bool { _, tm, _ := src.Fates(); return len(tm) == 3 })
|
||||
if ran {
|
||||
t.Fatal("a wrong ask ran")
|
||||
t.Fatal("a wrong or a declined ask ran")
|
||||
}
|
||||
key, _ := delivery.AskStepKey("ace", placed.ID)
|
||||
s, _ := st.get(key)
|
||||
if d, ok := delivery.DeclinedOf(s); !ok || len(d.Lacks) != 1 || d.Lacks[0] != delivery.NeedNodeBuildNode || !strings.Contains(s.Reason, "lacks node-build-node") {
|
||||
t.Fatalf("the declined step = %+v", s)
|
||||
}
|
||||
has, hasSteps := NewFakeAsks(), newSteps()
|
||||
_ = has.PublishAsk(placed)
|
||||
q := &Puller{Source: has, Language: delivery.AskGo, Node: "g14", Put: hasSteps.put, Capacity: func() int { return 1 },
|
||||
PullWait: 10 * time.Millisecond, Has: func(n string) bool { return n == delivery.NeedNodeBuildNode },
|
||||
Run: func(ctx context.Context, a delivery.StepAsk) (any, error) { return nil, nil }}
|
||||
go q.Pull(ctx)
|
||||
waitFor(t, "the placed ask acked where its need is met", func() bool { a, _, _ := has.Fates(); return len(a) == 1 })
|
||||
}
|
||||
|
||||
// load reads the recorded steps state's raw values: the pause key is not a step, so it is kept apart.
|
||||
|
||||
@@ -69,6 +69,37 @@ func TestTheCopiedComposerComposesAsTheControllers(t *testing.T) {
|
||||
}
|
||||
})
|
||||
}
|
||||
// An asker on a seat pulled by kind hears what that seat's workers gave up on, and no other stream's dead letters
|
||||
// (novox/hq issue 734: a check ask given up during a bus reload left its try running for ever).
|
||||
t.Run("an asker reads its seat's dead letters", func(t *testing.T) {
|
||||
build := Seat{Name: "node-build-go", Scope: "node", Accepts: []string{"delivery", "check", "recheck"}, PulledByKind: true}
|
||||
perms, err := PermissionsFor(Principal{Kind: KindModule, Node: "one", Module: "mesh-delivery-checker", Uses: []Seat{build}})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
for subject, want := range map[string]bool{
|
||||
"$JS.API.CONSUMER.CREATE.DEAD_LETTERS.x1.mesh.events.dead.SEAT_NODE_BUILD_GO.>": true,
|
||||
"$JS.API.CONSUMER.CREATE.DEAD_LETTERS.x1.mesh.events.dead.SEAT_NODE_BUILD_GO.w.next": true,
|
||||
"$JS.API.CONSUMER.DELETE.DEAD_LETTERS.x1": true,
|
||||
"$JS.API.CONSUMER.MSG.NEXT.DEAD_LETTERS.x1": true,
|
||||
"$JS.API.CONSUMER.CREATE.DEAD_LETTERS.x1.mesh.events.dead.EVENTS.>": false,
|
||||
"$JS.API.CONSUMER.CREATE.DEAD_LETTERS.x1": false,
|
||||
"$JS.API.STREAM.PURGE.DEAD_LETTERS": false,
|
||||
"$JS.FC.DEAD_LETTERS.x1": false,
|
||||
} {
|
||||
if got := MayPublish(perms, subject); got != want {
|
||||
t.Errorf("may publish %s: %v, want %v", subject, got, want)
|
||||
}
|
||||
}
|
||||
plain, err := PermissionsFor(Principal{Kind: KindModule, Node: "one", Module: "shop",
|
||||
Uses: []Seat{{Name: "telegram-sender", Accepts: []string{"send"}}}})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if MayPublish(plain, "$JS.API.CONSUMER.DELETE.DEAD_LETTERS.x1") {
|
||||
t.Error("a user of a seat not pulled by kind reads DEAD_LETTERS")
|
||||
}
|
||||
})
|
||||
t.Run("the controller's golden server configuration", func(t *testing.T) {
|
||||
seat := Seat{Name: "telegram-sender", Accepts: []string{"send"}, Emits: []string{"delivered", "failed"}}
|
||||
got, err := Compose(
|
||||
|
||||
@@ -24,8 +24,9 @@ import (
|
||||
// subjects cover it, so what travels there — a code typed by the operator — is never persisted. A kinded
|
||||
// holder asks with its own kind; the modules that watch the seat answer.
|
||||
//
|
||||
// And one read: **a holder's records**, a bucket the seat names, read by each user under its own name only
|
||||
// (`$KV.<bucket>.<module>.>`), so an asker reads the state of its own asks and no other asker's.
|
||||
// And two reads: **a holder's records**, a bucket the seat names, read by each user under its own name only
|
||||
// (`$KV.<bucket>.<module>.>`), so an asker reads the state of its own asks and no other asker's; and on a seat pulled by
|
||||
// kind, **what its workers gave up on**, the copies DEAD_LETTERS keeps of the seat's stream (DeadLetterReads, issue 734).
|
||||
|
||||
// BuildAskMaxDeliver bounds the deliveries of a build seat's ask (issue 1907): mesh-sdk delivery.AskMaxDeliver, written
|
||||
// here as the broker mirrors the catalogue rather than importing it.
|
||||
@@ -129,6 +130,9 @@ func SeatTrafficOf(module string, holds, uses, watches []Seat) SeatTraffic {
|
||||
}
|
||||
t.Records = append(t.Records, "$JS.API.DIRECT.GET.KV_"+b+".$KV."+b+"."+module+".>")
|
||||
}
|
||||
if s.PulledByKind && len(s.Accepts) > 0 && safeSubject.MatchString(s.Name) {
|
||||
t.Records = append(t.Records, DeadLetterReads(seatStreamName(s.Name))...)
|
||||
}
|
||||
}
|
||||
for _, w := range watches {
|
||||
if w.Kinded {
|
||||
@@ -151,6 +155,20 @@ func SeatTrafficOf(module string, holds, uses, watches []Seat) SeatTraffic {
|
||||
return t
|
||||
}
|
||||
|
||||
// DeadLetterReads is what a user of a seat pulled by kind is granted to hear which of the asks it put the seat's workers
|
||||
// gave up on (novox/hq issue 734): an ordered consumer on DEAD_LETTERS filtered to the copies the controller keeps of that
|
||||
// seat's stream (DeadLetterSubject(stream, *)), pulled, and its deletion. A copy carries the ask's own message id
|
||||
// (Mesh-Dead-Msg-Id), so the asker ends the step it waits for instead of waiting for ever; it reads the seat's dead
|
||||
// letters and no other stream's, and changes none.
|
||||
func DeadLetterReads(stream string) []string {
|
||||
return []string{
|
||||
"$JS.API.STREAM.INFO." + DeadLettersStream,
|
||||
"$JS.API.CONSUMER.CREATE." + DeadLettersStream + ".*." + DeadLetterSubject(stream, ">"),
|
||||
"$JS.API.CONSUMER.MSG.NEXT." + DeadLettersStream + ".*",
|
||||
"$JS.API.CONSUMER.DELETE." + DeadLettersStream + ".*",
|
||||
}
|
||||
}
|
||||
|
||||
// seatTrafficGrants is the bus permissions seat traffic needs: the subjects themselves, and the JetStream API a
|
||||
// worker is pulled and acknowledged through and a record is read through.
|
||||
func seatTrafficGrants(t SeatTraffic) (pub, sub []string) {
|
||||
|
||||
@@ -2,11 +2,15 @@ package buildrun
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"strings"
|
||||
"sync"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"git.novox.be/novox/mesh-sdk/go/delivery"
|
||||
"git.novox.be/novox/mesh-sdk/go/health"
|
||||
)
|
||||
|
||||
func goAsk(id string) delivery.StepAsk {
|
||||
@@ -48,6 +52,74 @@ func TestAnAskerPutsOnceAndReadsTheStep(t *testing.T) {
|
||||
if len(g.Asks()) != 0 {
|
||||
t.Fatal("a wait put an ask")
|
||||
}
|
||||
// Issue 734: an ask the build seat gave up on (DEAD_LETTERS keeps its copy with the ask's id) ends its wait as failed
|
||||
// with the words, though a node had taken it; under NotTakenBound one no node takes ends at the bound; a step written
|
||||
// first is answered as the node wrote it.
|
||||
dead := &DeadLetters{}
|
||||
lw := LostAskWaiter{Inner: g, Dead: dead}
|
||||
k = Asker{Publisher: g, Waiter: lw, Bound: time.Minute}
|
||||
g.Write(delivery.Step{ID: "mvl0frv18d1970", Node: "ace", State: delivery.StepRunning, Started: time.Now()})
|
||||
given, ok := GivenUpOf(map[string][]string{"Mesh-Dead-Msg-Id": {"mvl0frv18d1970"}, "Mesh-Dead-Deliveries": {"5"},
|
||||
"Mesh-Dead-Stream": {"SEAT_NODE_BUILD_GO"}, "Mesh-Dead-Gave-Up": {"2026-10-26T12:26:40Z"}})
|
||||
if !ok {
|
||||
t.Fatal("a dead letter's headers were not read")
|
||||
}
|
||||
go dead.Heard(given)
|
||||
step, err = k.Wait(context.Background(), goAsk("mvl0frv18d1970"))
|
||||
if err != nil || step.State != delivery.StepFailed || !IsLost(step) ||
|
||||
!strings.Contains(step.Reason, LostWords+" after 5 deliveries at 2026-10-26T12:26:40Z") {
|
||||
t.Fatalf("a given-up ask: %+v, %v", step, err)
|
||||
}
|
||||
if _, err := k.Passed(step, nil); err == nil || !strings.Contains(err.Error(), "on "+LostNode+" failed: "+LostWords) {
|
||||
t.Fatalf("a given-up ask's error: %v", err)
|
||||
}
|
||||
step, err = k.Wait(NotTakenBound(context.Background(), 20*time.Millisecond), goAsk("mvl0frv18d1971"))
|
||||
if err != nil || !IsNotTaken(step) || IsLost(step) {
|
||||
t.Fatalf("an ask no node took: %+v, %v", step, err)
|
||||
}
|
||||
g.Write(delivery.Step{ID: "mvl0frv18d1972", Node: "g14", State: delivery.StepPassed})
|
||||
if step, err = k.Wait(NotTakenBound(context.Background(), time.Minute), goAsk("mvl0frv18d1972")); err != nil || step.Node != "g14" {
|
||||
t.Fatalf("a step written: %+v, %v", step, err)
|
||||
}
|
||||
// Review round 1 of issue 734: a hearing the bus refuses at start is deaf and says so, never holds the start up, and
|
||||
// tries again on the next ask waited for; heard, it says so and hands the given-up asks on.
|
||||
fol := &refusingFollower{refuse: 1}
|
||||
var mu sync.Mutex
|
||||
var told []Hearing
|
||||
hearing := NewDeadLetterHearing(context.Background(), fol, []string{delivery.AskGo}, dead, nil,
|
||||
func(h Hearing) { mu.Lock(); told = append(told, h); mu.Unlock() })
|
||||
hearing.Wait()
|
||||
if why := hearing.Deaf(); !strings.Contains(why, "SEAT_NODE_BUILD_GO: permissions violation") {
|
||||
t.Fatalf("a refused hearing says %q", why)
|
||||
}
|
||||
k = Asker{Publisher: g, Waiter: LostAskWaiter{Inner: g, Dead: dead, Hearing: hearing}, Bound: time.Minute}
|
||||
g.Write(delivery.Step{ID: "mvl0frv18d1973", Node: "g14", State: delivery.StepPassed})
|
||||
if _, err := k.Wait(context.Background(), goAsk("mvl0frv18d1973")); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
hearing.Wait()
|
||||
mu.Lock()
|
||||
if hearing.Deaf() != "" || len(told) != 2 || told[0].Heard || !told[1].Heard || fol.calls() != 2 {
|
||||
t.Fatalf("after an ask: deaf %q, told %+v, followed %d times", hearing.Deaf(), told, fol.calls())
|
||||
}
|
||||
mu.Unlock()
|
||||
fol.heard(GivenUp{AskID: "mvl0frv18d1974", Deliveries: 5})
|
||||
step, err = k.Wait(context.Background(), goAsk("mvl0frv18d1974"))
|
||||
if err != nil || !IsLost(step) {
|
||||
t.Fatalf("an ask heard given up after the hearing came back: %+v, %v", step, err)
|
||||
}
|
||||
for _, row := range []struct {
|
||||
h *Hearing
|
||||
want string
|
||||
}{{nil, health.StateUnhealthy}, {&told[0], health.StateUnhealthy}, {&told[1], health.StateHealthy}} {
|
||||
var raw []byte
|
||||
if row.h != nil {
|
||||
raw, _ = json.Marshal(row.h)
|
||||
}
|
||||
if a := HearingHealth(raw); a.State != row.want || a.Why == "" {
|
||||
t.Errorf("health of %+v = %+v, want %s", row.h, a, row.want)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Review (issue 734 path): an ask taken again by the same node (its build module replaced mid-run) is bounded from the
|
||||
@@ -69,3 +141,26 @@ func TestARedeliveryToTheSameNodeRestartsTheBound(t *testing.T) {
|
||||
t.Fatalf("step %+v, %v, want the redelivered run's pass", step, err)
|
||||
}
|
||||
}
|
||||
|
||||
// refusingFollower refuses the first `refuse` follows, as the bus does before the asker's grant is composed.
|
||||
type refusingFollower struct {
|
||||
mu sync.Mutex
|
||||
refuse int
|
||||
n int
|
||||
hand func(GivenUp)
|
||||
}
|
||||
|
||||
func (f *refusingFollower) Follow(_ context.Context, _ string, _ time.Time, heard func(GivenUp)) (func(), error) {
|
||||
f.mu.Lock()
|
||||
defer f.mu.Unlock()
|
||||
f.n++
|
||||
if f.n <= f.refuse {
|
||||
return nil, errors.New("permissions violation")
|
||||
}
|
||||
f.hand = heard
|
||||
return func() {}, nil
|
||||
}
|
||||
|
||||
func (f *refusingFollower) calls() int { f.mu.Lock(); defer f.mu.Unlock(); return f.n }
|
||||
|
||||
func (f *refusingFollower) heard(g GivenUp) { f.mu.Lock(); h := f.hand; f.mu.Unlock(); h(g) }
|
||||
|
||||
@@ -0,0 +1,495 @@
|
||||
package buildrun
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"strconv"
|
||||
"strings"
|
||||
"sync"
|
||||
"time"
|
||||
|
||||
"github.com/nats-io/nats.go/jetstream"
|
||||
|
||||
"git.novox.be/novox/mesh-sdk/go/delivery"
|
||||
"git.novox.be/novox/mesh-sdk/go/health"
|
||||
)
|
||||
|
||||
// **An ask the build seat gave up on ends its step** (novox/hq issue 734). A build seat's worker offers an ask
|
||||
// delivery.AskMaxDeliver times; one handed out that often without an answer (a bus reload that drops every hand-out, a node
|
||||
// that dies taking it each time) is given up by the server, and the controller keeps a copy of it in DEAD_LETTERS under
|
||||
// mesh.events.dead.<seat stream>.<worker>, with the ask's message id (its ask id), how often it was handed out and when it
|
||||
// was given up. No build node writes a step for it, so an asker that waits for the step waits for ever: a try stays
|
||||
// running and holds a try place, a check's verdict stays running and its pull request waits.
|
||||
//
|
||||
// An asker of the build seats (the checker, the builder) hears those copies (DeadLetterHearing: an ordered consumer on
|
||||
// DEAD_LETTERS filtered to the build seats' streams, granted to a user of a seat pulled by kind, buscompose
|
||||
// DeadLetterReads) into DeadLetters, and LostAskWaiter ends the waiting step at once as failed on the node LostNode, its
|
||||
// reason saying LostWords; the asker decides what follows (the checker ends a try as error and asks a check again, the
|
||||
// builder asks its part of a build again).
|
||||
//
|
||||
// Belt and braces, where the asker says so in the context (NotTakenBound; the checker's tries): an ask no build node took
|
||||
// within a bound ends the same way, saying NotTakenWords. An ask waits in the stream as long as the backlog is otherwise
|
||||
// (ADR 0525 §9): a backlog is no fault.
|
||||
|
||||
// LostNode is the node a step ended for a lost ask names: no build node wrote it.
|
||||
const LostNode = "bus"
|
||||
|
||||
// The words of a step ended for its ask.
|
||||
const (
|
||||
LostWords = "its ask was given up by the build seat"
|
||||
NotTakenWords = "no build node took its ask"
|
||||
)
|
||||
|
||||
// The headers the controller keeps a given-up message's copy with in DEAD_LETTERS (mesh-controller internal/link
|
||||
// deadletters.go): the original message id (an ask's is its ask id), how often it was handed out, when it was given up.
|
||||
const (
|
||||
DeadHeaderMsgID = "Mesh-Dead-Msg-Id"
|
||||
DeadHeaderDeliveries = "Mesh-Dead-Deliveries"
|
||||
DeadHeaderGaveUp = "Mesh-Dead-Gave-Up"
|
||||
DeadHeaderStream = "Mesh-Dead-Stream"
|
||||
)
|
||||
|
||||
// DeadLettersStream is the stream the controller keeps given-up messages in, and DeadLetterFilter the subjects of one seat
|
||||
// stream's copies there (buscompose DeadLetterSubject).
|
||||
const DeadLettersStream = "DEAD_LETTERS"
|
||||
|
||||
// DeadLetterFilter is the subjects DEAD_LETTERS keeps a seat stream's given-up messages under.
|
||||
func DeadLetterFilter(stream string) string { return "mesh.events.dead." + stream + ".>" }
|
||||
|
||||
// SeatStream is the stream of a build seat's language (buscompose seatStreamName of node-build-<language>).
|
||||
func SeatStream(language string) string { return "SEAT_NODE_BUILD_" + strings.ToUpper(language) }
|
||||
|
||||
// GivenUp is one ask a build seat gave up on, as DEAD_LETTERS keeps it.
|
||||
type GivenUp struct {
|
||||
AskID string
|
||||
Stream string
|
||||
Deliveries int
|
||||
At time.Time
|
||||
}
|
||||
|
||||
// GivenUpOf reads a DEAD_LETTERS copy's headers; false when it names no message id.
|
||||
func GivenUpOf(header map[string][]string) (GivenUp, bool) {
|
||||
get := func(k string) string {
|
||||
if v := header[k]; len(v) > 0 {
|
||||
return strings.TrimSpace(v[0])
|
||||
}
|
||||
return ""
|
||||
}
|
||||
g := GivenUp{AskID: get(DeadHeaderMsgID), Stream: get(DeadHeaderStream)}
|
||||
if g.AskID == "" {
|
||||
return GivenUp{}, false
|
||||
}
|
||||
g.Deliveries, _ = strconv.Atoi(get(DeadHeaderDeliveries))
|
||||
g.At, _ = time.Parse(time.RFC3339Nano, get(DeadHeaderGaveUp))
|
||||
return g, true
|
||||
}
|
||||
|
||||
// Words are what a step ended for the given-up ask says.
|
||||
func (g GivenUp) Words() string {
|
||||
at := "at an unknown time"
|
||||
if !g.At.IsZero() {
|
||||
at = "at " + g.At.UTC().Format(time.RFC3339)
|
||||
}
|
||||
return fmt.Sprintf("%s after %d deliveries %s (kept in %s); ask again", LostWords, g.Deliveries, at, DeadLettersStream)
|
||||
}
|
||||
|
||||
// keptGivenUp is how many given-up asks DeadLetters remembers for a waiter that starts after the copy was heard.
|
||||
const keptGivenUp = 1024
|
||||
|
||||
// DeadLetters holds the given-up asks heard, and hands each to the waiter of its ask. Safe for concurrent use.
|
||||
type DeadLetters struct {
|
||||
mu sync.Mutex
|
||||
heard map[string]GivenUp
|
||||
order []string
|
||||
watchers map[string][]chan GivenUp
|
||||
}
|
||||
|
||||
// Heard takes one given-up ask in.
|
||||
func (d *DeadLetters) Heard(g GivenUp) {
|
||||
d.mu.Lock()
|
||||
if d.heard == nil {
|
||||
d.heard, d.watchers = map[string]GivenUp{}, map[string][]chan GivenUp{}
|
||||
}
|
||||
if _, ok := d.heard[g.AskID]; !ok {
|
||||
d.order = append(d.order, g.AskID)
|
||||
if len(d.order) > keptGivenUp {
|
||||
delete(d.heard, d.order[0])
|
||||
d.order = d.order[1:]
|
||||
}
|
||||
}
|
||||
d.heard[g.AskID] = g
|
||||
ws := d.watchers[g.AskID]
|
||||
delete(d.watchers, g.AskID)
|
||||
d.mu.Unlock()
|
||||
for _, w := range ws {
|
||||
w <- g // buffered, one each
|
||||
}
|
||||
}
|
||||
|
||||
// watch answers a channel that gets the ask's given-up copy once (at once when it was heard already), and its cancel.
|
||||
func (d *DeadLetters) watch(askID string) (<-chan GivenUp, func()) {
|
||||
ch := make(chan GivenUp, 1)
|
||||
d.mu.Lock()
|
||||
defer d.mu.Unlock()
|
||||
if d.heard == nil {
|
||||
d.heard, d.watchers = map[string]GivenUp{}, map[string][]chan GivenUp{}
|
||||
}
|
||||
if g, ok := d.heard[askID]; ok {
|
||||
ch <- g
|
||||
return ch, func() {}
|
||||
}
|
||||
d.watchers[askID] = append(d.watchers[askID], ch)
|
||||
return ch, func() {
|
||||
d.mu.Lock()
|
||||
defer d.mu.Unlock()
|
||||
ws := d.watchers[askID]
|
||||
for i, w := range ws {
|
||||
if w == ch {
|
||||
d.watchers[askID] = append(ws[:i], ws[i+1:]...)
|
||||
break
|
||||
}
|
||||
}
|
||||
if len(d.watchers[askID]) == 0 {
|
||||
delete(d.watchers, askID)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
type notTakenKey struct{}
|
||||
|
||||
// NotTakenBound says, in ctx, that an ask no build node took within bound ends its step (a try's, never a check's).
|
||||
func NotTakenBound(ctx context.Context, bound time.Duration) context.Context {
|
||||
return context.WithValue(ctx, notTakenKey{}, bound)
|
||||
}
|
||||
|
||||
func notTakenBoundOf(ctx context.Context) time.Duration {
|
||||
d, _ := ctx.Value(notTakenKey{}).(time.Duration)
|
||||
return d
|
||||
}
|
||||
|
||||
// LostAskWaiter is an AskWaiter that ends an ask's step when the build seat gave the ask up (DeadLetters), or, under
|
||||
// NotTakenBound, when no build node took it within the bound: it hands the asker a failed step whose reason says why, on
|
||||
// the node "bus". Every step the build module writes is handed on as it is.
|
||||
type LostAskWaiter struct {
|
||||
Inner AskWaiter
|
||||
Dead *DeadLetters
|
||||
// Hearing, when set, is asked to hear DEAD_LETTERS again each time an ask is waited for while it cannot: an ask put is
|
||||
// the event that makes hearing matter.
|
||||
Hearing interface {
|
||||
Deaf() string
|
||||
Again()
|
||||
}
|
||||
Now func() time.Time
|
||||
}
|
||||
|
||||
func (w LostAskWaiter) now() time.Time {
|
||||
if w.Now != nil {
|
||||
return w.Now()
|
||||
}
|
||||
return time.Now()
|
||||
}
|
||||
|
||||
// WatchAsk is AskWaiter's.
|
||||
func (w LostAskWaiter) WatchAsk(ctx context.Context, module, askID string) (<-chan delivery.Step, error) {
|
||||
if w.Hearing != nil && w.Hearing.Deaf() != "" {
|
||||
w.Hearing.Again()
|
||||
}
|
||||
inner, err := w.Inner.WatchAsk(ctx, module, askID)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
var dead <-chan GivenUp
|
||||
cancel := func() {}
|
||||
if w.Dead != nil {
|
||||
dead, cancel = w.Dead.watch(askID)
|
||||
}
|
||||
// The not-taken bound is a context's (ADR 0437 §8: no timer), ended when a node takes the ask.
|
||||
var notTaken <-chan struct{}
|
||||
bound := notTakenBoundOf(ctx)
|
||||
stopBound := func() {}
|
||||
if bound > 0 {
|
||||
var nt context.Context
|
||||
nt, stopBound = context.WithTimeout(context.Background(), bound)
|
||||
notTaken = nt.Done()
|
||||
}
|
||||
out := make(chan delivery.Step)
|
||||
go func() {
|
||||
defer close(out)
|
||||
defer cancel()
|
||||
defer func() { stopBound() }()
|
||||
send := func(s delivery.Step) bool {
|
||||
select {
|
||||
case out <- s:
|
||||
return true
|
||||
case <-ctx.Done():
|
||||
return false
|
||||
}
|
||||
}
|
||||
ended := func(reason string) delivery.Step {
|
||||
at := w.now().UTC()
|
||||
return delivery.Step{ID: askID, Node: LostNode, State: delivery.StepFailed, Reason: reason, Ended: at}
|
||||
}
|
||||
for {
|
||||
select {
|
||||
case <-ctx.Done():
|
||||
return
|
||||
case s, ok := <-inner:
|
||||
if !ok {
|
||||
return
|
||||
}
|
||||
if notTaken != nil {
|
||||
stopBound() // a node took it: its step is bounded by the asker from its start
|
||||
notTaken = nil
|
||||
}
|
||||
if !send(s) {
|
||||
return
|
||||
}
|
||||
case g := <-dead:
|
||||
dead = nil
|
||||
send(ended(g.Words()))
|
||||
return
|
||||
case <-notTaken:
|
||||
send(ended(fmt.Sprintf("%s within %s of its put; it was lost or waits behind a backlog; ask again", NotTakenWords, bound)))
|
||||
return
|
||||
}
|
||||
}
|
||||
}()
|
||||
return out, nil
|
||||
}
|
||||
|
||||
// IsLost says whether a step was ended by LostAskWaiter because the build seat gave its ask up (LostWords).
|
||||
func IsLost(s delivery.Step) bool { return s.Node == LostNode && strings.Contains(s.Reason, LostWords) }
|
||||
|
||||
// IsNotTaken says whether a step was ended by LostAskWaiter because no build node took its ask within the bound.
|
||||
func IsNotTaken(s delivery.Step) bool {
|
||||
return s.Node == LostNode && strings.Contains(s.Reason, NotTakenWords)
|
||||
}
|
||||
|
||||
// **The asker hears DEAD_LETTERS, tries again when it cannot, and says whether it hears** (issue 734). The read is
|
||||
// granted with the asker's seat traffic (buscompose DeadLetterReads); an asker started before its grant was composed is
|
||||
// refused, and an asker that only tried once would stay deaf until it starts again, silently. DeadLetterHearing tries in
|
||||
// the background, never holding the start up, and again on an event (Again): the asker's reconnect to the bus, and every
|
||||
// ask waited for while it is deaf (LostAskWaiter.Hearing); no timer. Each change of whether it hears is said (Said), so
|
||||
// the module's health tool says it: a deaf asker is not healthy.
|
||||
|
||||
// Hearing is what a DeadLetterHearing says: whether it hears every build seat stream it follows, and why not.
|
||||
type Hearing struct {
|
||||
Heard bool `json:"heard"`
|
||||
Streams []string `json:"streams"`
|
||||
Why string `json:"why,omitempty"`
|
||||
At time.Time `json:"at"`
|
||||
}
|
||||
|
||||
// HearingKey is the key a module keeps its Hearing under, in its own state (the checker's and the builder's hearing).
|
||||
const HearingKey = "dead-letters"
|
||||
|
||||
// DeadLetterFollower starts following one seat stream's copies in DEAD_LETTERS from since, handing each given-up ask to
|
||||
// heard; it answers the stop, or why it cannot.
|
||||
type DeadLetterFollower interface {
|
||||
Follow(ctx context.Context, stream string, since time.Time, heard func(GivenUp)) (func(), error)
|
||||
}
|
||||
|
||||
// JetStreamDeadLetters is the bus side of a DeadLetterFollower: an ordered consumer on DEAD_LETTERS filtered to the
|
||||
// stream's copies, which resumes where it was after a reconnect and, reset before it heard any, starts at since again.
|
||||
type JetStreamDeadLetters struct{ JS jetstream.JetStream }
|
||||
|
||||
// Follow is DeadLetterFollower's.
|
||||
func (j JetStreamDeadLetters) Follow(ctx context.Context, stream string, since time.Time, heard func(GivenUp)) (func(), error) {
|
||||
cons, err := j.JS.OrderedConsumer(ctx, DeadLettersStream, jetstream.OrderedConsumerConfig{
|
||||
FilterSubjects: []string{DeadLetterFilter(stream)}, DeliverPolicy: jetstream.DeliverByStartTimePolicy, OptStartTime: &since})
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
cc, err := cons.Consume(func(m jetstream.Msg) {
|
||||
if g, ok := GivenUpOf(m.Headers()); ok {
|
||||
heard(g)
|
||||
}
|
||||
})
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return cc.Stop, nil
|
||||
}
|
||||
|
||||
// DeadLetterHearing follows the build seats' given-up asks into Dead. Make it with NewDeadLetterHearing.
|
||||
type DeadLetterHearing struct {
|
||||
follower DeadLetterFollower
|
||||
streams []string
|
||||
dead *DeadLetters
|
||||
logf func(string, ...any)
|
||||
said func(Hearing)
|
||||
ctx context.Context
|
||||
since time.Time
|
||||
|
||||
mu sync.Mutex
|
||||
stops map[string]func()
|
||||
why map[string]string
|
||||
trying bool
|
||||
again bool
|
||||
told *Hearing
|
||||
wg sync.WaitGroup
|
||||
}
|
||||
|
||||
// NewDeadLetterHearing starts hearing the given-up asks of each language's build seat stream, in the background. said
|
||||
// is told each change of whether it hears (nil tells nothing); ctx ends it.
|
||||
func NewDeadLetterHearing(ctx context.Context, follower DeadLetterFollower, languages []string, dead *DeadLetters,
|
||||
logf func(string, ...any), said func(Hearing)) *DeadLetterHearing {
|
||||
h := &DeadLetterHearing{follower: follower, dead: dead, logf: logf, said: said, ctx: ctx, since: time.Now(),
|
||||
stops: map[string]func(){}, why: map[string]string{}}
|
||||
for _, l := range languages {
|
||||
s := SeatStream(l)
|
||||
h.streams = append(h.streams, s)
|
||||
h.why[s] = "not tried yet"
|
||||
}
|
||||
if h.logf == nil {
|
||||
h.logf = func(string, ...any) {}
|
||||
}
|
||||
h.Again()
|
||||
return h
|
||||
}
|
||||
|
||||
// Deaf says why a stream is not heard, or "" when every one is.
|
||||
func (h *DeadLetterHearing) Deaf() string {
|
||||
h.mu.Lock()
|
||||
defer h.mu.Unlock()
|
||||
return h.deafLocked()
|
||||
}
|
||||
|
||||
func (h *DeadLetterHearing) deafLocked() string {
|
||||
var out []string
|
||||
for _, s := range h.streams {
|
||||
if why, deaf := h.why[s]; deaf {
|
||||
out = append(out, s+": "+why)
|
||||
}
|
||||
}
|
||||
if len(out) == 0 {
|
||||
return ""
|
||||
}
|
||||
return DeadLettersStream + " is not heard, so an ask a build seat gives up on is waited for until its bound: " +
|
||||
strings.Join(out, "; ")
|
||||
}
|
||||
|
||||
// Again tries, in the background, every stream not heard yet; a call while it tries makes it try once more after.
|
||||
func (h *DeadLetterHearing) Again() {
|
||||
h.mu.Lock()
|
||||
if h.trying {
|
||||
h.again = true
|
||||
h.mu.Unlock()
|
||||
return
|
||||
}
|
||||
h.trying = true
|
||||
h.mu.Unlock()
|
||||
h.wg.Add(1)
|
||||
go func() {
|
||||
defer h.wg.Done()
|
||||
for {
|
||||
h.try()
|
||||
h.mu.Lock()
|
||||
if !h.again || h.ctx.Err() != nil {
|
||||
h.trying = false
|
||||
h.mu.Unlock()
|
||||
return
|
||||
}
|
||||
h.again = false
|
||||
h.mu.Unlock()
|
||||
}
|
||||
}()
|
||||
}
|
||||
|
||||
// Wait returns when no try runs.
|
||||
func (h *DeadLetterHearing) Wait() { h.wg.Wait() }
|
||||
|
||||
// Stop ends every stream's following.
|
||||
func (h *DeadLetterHearing) Stop() {
|
||||
h.mu.Lock()
|
||||
defer h.mu.Unlock()
|
||||
for s, stop := range h.stops {
|
||||
stop()
|
||||
delete(h.stops, s)
|
||||
}
|
||||
}
|
||||
|
||||
func (h *DeadLetterHearing) try() {
|
||||
for _, s := range h.streams {
|
||||
h.mu.Lock()
|
||||
_, deaf := h.why[s]
|
||||
h.mu.Unlock()
|
||||
if !deaf || h.ctx.Err() != nil {
|
||||
continue
|
||||
}
|
||||
stream := s
|
||||
stop, err := h.follower.Follow(h.ctx, stream, h.since, func(g GivenUp) {
|
||||
h.logf("the ask %s on %s was given up after %d deliveries at %s: the wait for its step ends", g.AskID, g.Stream,
|
||||
g.Deliveries, g.At.Format(time.RFC3339))
|
||||
h.dead.Heard(g)
|
||||
})
|
||||
h.mu.Lock()
|
||||
if err != nil {
|
||||
h.why[stream] = err.Error()
|
||||
h.logf("the asks %s gives up on are not heard (%s of %s); tried again at the next reconnect or ask: %v",
|
||||
stream, DeadLetterFilter(stream), DeadLettersStream, err)
|
||||
} else {
|
||||
delete(h.why, stream)
|
||||
h.stops[stream] = stop
|
||||
h.logf("the asks %s gives up on are heard from %s", stream, DeadLettersStream)
|
||||
}
|
||||
h.mu.Unlock()
|
||||
}
|
||||
h.tell()
|
||||
}
|
||||
|
||||
// tell says the hearing when it changed.
|
||||
func (h *DeadLetterHearing) tell() {
|
||||
h.mu.Lock()
|
||||
why := h.deafLocked()
|
||||
now := Hearing{Heard: why == "", Streams: append([]string(nil), h.streams...), Why: why, At: time.Now().UTC()}
|
||||
same := h.told != nil && h.told.Heard == now.Heard && h.told.Why == now.Why
|
||||
if !same {
|
||||
h.told = &now
|
||||
}
|
||||
h.mu.Unlock()
|
||||
if !same && h.said != nil {
|
||||
h.said(now)
|
||||
}
|
||||
}
|
||||
|
||||
// HearingState is the name of the state an asker keeps its Hearing in (`<module>_hearing`, key HearingKey), which its
|
||||
// health tool reads.
|
||||
const HearingState = "hearing"
|
||||
|
||||
// SayHearing is a DeadLetterHearing's said that keeps each Hearing in kv under HearingKey; nil kv keeps nothing and
|
||||
// says so once.
|
||||
func SayHearing(ctx context.Context, kv jetstream.KeyValue, logf func(string, ...any)) func(Hearing) {
|
||||
if kv == nil {
|
||||
if logf != nil {
|
||||
logf("whether %s is heard is not kept: the state %s is not there, so the health tool cannot say it", DeadLettersStream, HearingState)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
return func(h Hearing) {
|
||||
data, err := json.Marshal(h)
|
||||
if err == nil {
|
||||
_, err = kv.Put(ctx, HearingKey, data)
|
||||
}
|
||||
if err != nil && logf != nil {
|
||||
logf("whether %s is heard could not be kept: %v", DeadLettersStream, err)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// HearingHealth is the health answer of an asker's kept Hearing (raw, empty when none is kept): healthy while it hears
|
||||
// DEAD_LETTERS, unhealthy saying why while it does not or has not said.
|
||||
func HearingHealth(raw []byte) health.Answer {
|
||||
if len(raw) == 0 {
|
||||
return health.Unhealthy("it has not said whether it hears " + DeadLettersStream + " (issue 734): it is starting, or its state " + HearingState + " is not there")
|
||||
}
|
||||
var h Hearing
|
||||
if err := json.Unmarshal(raw, &h); err != nil {
|
||||
return health.Unhealthy("what it keeps of hearing " + DeadLettersStream + " is not a hearing: " + err.Error())
|
||||
}
|
||||
if !h.Heard {
|
||||
return health.Unhealthy(h.Why + " (since " + h.At.Format(time.RFC3339) + "; tried again at its next reconnect or ask)")
|
||||
}
|
||||
return health.Healthy("it hears " + DeadLettersStream + " for " + strings.Join(h.Streams, ", "))
|
||||
}
|
||||
+117
-1
@@ -45,6 +45,86 @@ const (
|
||||
// AskLanguages are the build seats' languages.
|
||||
var AskLanguages = []string{AskGo, AskNode, AskImage}
|
||||
|
||||
// **An ask may name what its node needs** (issue 890, novox/hq ADR 0525 §1 as the placement record amends it). The seat's
|
||||
// workers are shared, so the asker still chooses no node; a check ask whose packages' tests need something only some
|
||||
// nodes have names it in Needs, and a holder whose node lacks one of them takes no part of the ask: it ends the ask's step
|
||||
// refused as declined (StepDeclined) and drops the message, and the asker puts the ask again under a new id, so a node
|
||||
// that has the need takes it. A need is a node seat whose holder installs what the tests read on its node; a package
|
||||
// declares it beside its tests, and the build module's digest reports it (LevelDigest.Needs).
|
||||
|
||||
// NeedNodeBuildNode is the need of a package whose integration tests read the Node build module's installed toolchain
|
||||
// (ADR 0533 §1): the node holds the seat node-build-node, so its toolchain is installed where the Go build module's
|
||||
// integration level is given it.
|
||||
const NeedNodeBuildNode = "node-build-node"
|
||||
|
||||
// AskNeeds are the needs an ask may name.
|
||||
var AskNeeds = []string{NeedNodeBuildNode}
|
||||
|
||||
// CheckNeed refuses a need that is not one of AskNeeds.
|
||||
func CheckNeed(need string) error {
|
||||
for _, n := range AskNeeds {
|
||||
if need == n {
|
||||
return nil
|
||||
}
|
||||
}
|
||||
return fmt.Errorf("delivery: %q is not a need an ask may name (%s)", need, strings.Join(AskNeeds, ", "))
|
||||
}
|
||||
|
||||
// Lacks is what of needs has does not say the node has, in the order of needs; a nil has has nothing.
|
||||
func Lacks(needs []string, has func(need string) bool) []string {
|
||||
var out []string
|
||||
for _, n := range needs {
|
||||
if has == nil || !has(n) {
|
||||
out = append(out, n)
|
||||
}
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// PackageNeeds is one package and what its tests need of the node at a level.
|
||||
type PackageNeeds struct {
|
||||
Package string `json:"package"`
|
||||
Needs []string `json:"needs"`
|
||||
}
|
||||
|
||||
// StepDeclined is the result of the step of an ask a holder declined: the ask's needs, and those the holder's node lacks.
|
||||
// The step's state is refused; the asker puts the ask again under a new id (DeclinedOf).
|
||||
type StepDeclined struct {
|
||||
Declined bool `json:"declined"`
|
||||
Needs []string `json:"needs"`
|
||||
Lacks []string `json:"lacks"`
|
||||
}
|
||||
|
||||
// DeclinedOf says whether step is a declined ask's, and what its node lacked.
|
||||
func DeclinedOf(step Step) (StepDeclined, bool) {
|
||||
if step.State != StepRefused || len(step.Result) == 0 {
|
||||
return StepDeclined{}, false
|
||||
}
|
||||
var d StepDeclined
|
||||
if err := json.Unmarshal(step.Result, &d); err != nil || !d.Declined {
|
||||
return StepDeclined{}, false
|
||||
}
|
||||
return d, true
|
||||
}
|
||||
|
||||
// UnmetNeeds are the needs of the packages the levels left untested (LevelAnswer.Unmet), each once, sorted.
|
||||
func UnmetNeeds(levels []LevelAnswer) []string {
|
||||
seen := map[string]bool{}
|
||||
var out []string
|
||||
for _, l := range levels {
|
||||
for _, u := range l.Unmet {
|
||||
for _, n := range u.Needs {
|
||||
if !seen[n] {
|
||||
seen[n] = true
|
||||
out = append(out, n)
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
sort.Strings(out)
|
||||
return out
|
||||
}
|
||||
|
||||
// AskRuns is how many times an ask is run before it is taken for poison (issue 1907): an ask whose run never ends (it
|
||||
// takes its node down, or its process dies with it) is delivered again by its stream to the next free node (ADR 0525
|
||||
// §6); the holder that takes it past AskRuns runs it no more, writes its step failed saying so, and ends it, so the
|
||||
@@ -171,6 +251,8 @@ type StepAsk struct {
|
||||
Build *BuildJob `json:"build,omitempty"`
|
||||
Check *CheckJob `json:"check,omitempty"`
|
||||
Compose *ComposeJob `json:"compose,omitempty"`
|
||||
// Needs are what the node that runs the ask must have (AskNeeds); a check ask's alone. Empty: any node.
|
||||
Needs []string `json:"needs,omitempty"`
|
||||
}
|
||||
|
||||
// ComposeJob is a compose ask's job (novox/hq ADR 0482 clause 4, issue 1622): fetch the commit, build the composer
|
||||
@@ -255,6 +337,9 @@ type CheckJob struct {
|
||||
RunnerWhen string `json:"runner_when,omitempty"`
|
||||
// Run is a try's test pattern (go test -run): each level runs it alone, digesting nothing.
|
||||
Run string `json:"run,omitempty"`
|
||||
// Packages, when set, are the only packages each level tests (issue 890, ADR 0552 §4): a placed ask names the
|
||||
// packages the first ask left unmet, and the others are neither tested nor taken kept, so nothing is judged twice.
|
||||
Packages []string `json:"packages,omitempty"`
|
||||
}
|
||||
|
||||
func (a StepAsk) check() error {
|
||||
@@ -290,6 +375,13 @@ func (a StepAsk) check() error {
|
||||
return fmt.Errorf("delivery: the ask %s is a check on the delivery stream, which carries trunk builds alone", a.ID)
|
||||
case a.Check != nil && a.Language == AskImage:
|
||||
return fmt.Errorf("delivery: the ask %s is a check of an image, which has no tests", a.ID)
|
||||
case len(a.Needs) > 0 && a.Check == nil:
|
||||
return fmt.Errorf("delivery: the ask %s names needs and is no check, whose tests alone need a node", a.ID)
|
||||
}
|
||||
for _, n := range a.Needs {
|
||||
if err := CheckNeed(n); err != nil {
|
||||
return fmt.Errorf("the ask %s: %w", a.ID, err)
|
||||
}
|
||||
}
|
||||
if a.Build != nil {
|
||||
return a.Build.check(a.ID)
|
||||
@@ -350,6 +442,11 @@ func (c CheckJob) check(id string) error {
|
||||
return err
|
||||
}
|
||||
}
|
||||
for _, p := range c.Packages {
|
||||
if p == "" || strings.ContainsAny(p, " \t\n") {
|
||||
return fmt.Errorf("delivery: the check ask %s names a package %q that is no import path", id, p)
|
||||
}
|
||||
}
|
||||
return checkFetchArgs(id, c.Fetch)
|
||||
}
|
||||
|
||||
@@ -433,6 +530,9 @@ type LevelAnswer struct {
|
||||
Digest *LevelDigest `json:"digest,omitempty"`
|
||||
Kept []KeptTaken `json:"kept,omitempty"`
|
||||
Tests []json.RawMessage `json:"tests,omitempty"`
|
||||
// Unmet are the packages the level did not test on this node, because their tests need what it lacks (issue 890): the
|
||||
// asker keeps what passed and asks them again of a node that has it (StepAsk.Needs).
|
||||
Unmet []PackageNeeds `json:"unmet,omitempty"`
|
||||
}
|
||||
|
||||
// LevelDigest is the digest's answer as a level keeps it in the ask's step result: its packages a list of
|
||||
@@ -446,6 +546,8 @@ type LevelDigest struct {
|
||||
Beside []string `json:"beside,omitempty"`
|
||||
WithoutTests []string `json:"without_tests,omitempty"`
|
||||
JudgedBy string `json:"judged_by,omitempty"`
|
||||
// Needs are the packages whose tests at this level need something of the node (issue 890), as they declare it.
|
||||
Needs []PackageNeeds `json:"needs,omitempty"`
|
||||
}
|
||||
|
||||
// PackageDigest is one package's digest at a level.
|
||||
@@ -463,6 +565,7 @@ func (d *LevelDigest) UnmarshalJSON(raw []byte) error {
|
||||
Beside []string `json:"beside"`
|
||||
WithoutTests []string `json:"without_tests"`
|
||||
JudgedBy string `json:"judged_by"`
|
||||
Needs []PackageNeeds `json:"needs"`
|
||||
}
|
||||
if err := json.Unmarshal(raw, &v); err != nil {
|
||||
return err
|
||||
@@ -482,7 +585,20 @@ func (d *LevelDigest) UnmarshalJSON(raw []byte) error {
|
||||
}
|
||||
}
|
||||
sort.Slice(pkgs, func(i, j int) bool { return pkgs[i].Package < pkgs[j].Package })
|
||||
*d = LevelDigest{Level: v.Level, Packages: pkgs, Beside: v.Beside, WithoutTests: v.WithoutTests, JudgedBy: v.JudgedBy}
|
||||
*d = LevelDigest{Level: v.Level, Packages: pkgs, Beside: v.Beside, WithoutTests: v.WithoutTests, JudgedBy: v.JudgedBy, Needs: v.Needs}
|
||||
return nil
|
||||
}
|
||||
|
||||
// NeedsOf is what the package's tests need of the node at the digest's level; nil when it declares nothing.
|
||||
func (d *LevelDigest) NeedsOf(pkg string) []string {
|
||||
if d == nil {
|
||||
return nil
|
||||
}
|
||||
for _, n := range d.Needs {
|
||||
if n.Package == pkg {
|
||||
return n.Needs
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
|
||||
@@ -56,6 +56,7 @@ func TestAskRefusesUnknownKindAndLanguage(t *testing.T) {
|
||||
"recheck": func(a *StepAsk) { a.Kind = AskRecheck },
|
||||
"commit": func(a *StepAsk) { a.Build.Fetch = map[string]any{"repository": "novox/x", "commit": "main"} },
|
||||
"path": func(a *StepAsk) { a.Build.Path = "" },
|
||||
"needs": func(a *StepAsk) { a.Needs = []string{NeedNodeBuildNode} }, // issue 890: a build needs no node
|
||||
}
|
||||
for name, change := range cases {
|
||||
a := buildAsk()
|
||||
@@ -80,6 +81,23 @@ func TestAskRefusesUnknownKindAndLanguage(t *testing.T) {
|
||||
if _, err := EncodeStepAsk(c); err == nil {
|
||||
t.Error("a check of an image encoded")
|
||||
}
|
||||
// Issue 890: a check names a known need and round-trips it; an unknown need is refused.
|
||||
c = checkAsk()
|
||||
c.Check.Packages = []string{"a b"}
|
||||
if _, err := EncodeStepAsk(c); err == nil {
|
||||
t.Error("a package that is no import path encoded")
|
||||
}
|
||||
c.Check.Packages = []string{"x/pkg/a"}
|
||||
c.Needs = []string{"gpu"}
|
||||
if _, err := EncodeStepAsk(c); err == nil {
|
||||
t.Error("an unknown need encoded")
|
||||
}
|
||||
c.Needs = []string{NeedNodeBuildNode}
|
||||
if raw, err := EncodeStepAsk(c); err != nil {
|
||||
t.Errorf("a check needing %s: %v", NeedNodeBuildNode, err)
|
||||
} else if back, err := DecodeStepAsk(raw); err != nil || len(back.Needs) != 1 || back.Needs[0] != NeedNodeBuildNode {
|
||||
t.Errorf("the need did not round-trip: %+v %v", back.Needs, err)
|
||||
}
|
||||
raw, _ := EncodeStepAsk(buildAsk())
|
||||
for _, bad := range []string{
|
||||
strings.Replace(string(raw), `"kind":"delivery"`, `"kind":"queue"`, 1),
|
||||
|
||||
Reference in New Issue
Block a user