Files
mesh-sdk/go/buildstep/pull_test.go
T
jochen 981a35b598 End a step left by a previous process at once: every step names its owner (issue 1890)
A delivery that replaced mesh-build-go left a check ask's key running, and
the new process's start sweep spared it as an ask younger than the step
bound, so it held a build slot until a hand end (issue 1890, note 21).
Each step now records its owner (boot id, pid, process start); the sweep
ends a running step of another owner at once and says its owner, while a
key with no owner keeps the earlier rule. The conformance kit gains the
left-running case every build module runs through its own start sweep.
2026-10-27 01:19:29 +01:00

439 lines
18 KiB
Go

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"
)
// steps records a steps state's puts: the last value of each key.
type steps struct {
mu sync.Mutex
keys map[string]delivery.Step
}
func newSteps() *steps { return &steps{keys: map[string]delivery.Step{}} }
func (s *steps) put(key string, value any) (uint64, error) {
raw, _ := value.(json.RawMessage)
st, err := delivery.DecodeStep(raw)
if err != nil {
return 0, err
}
s.mu.Lock()
s.keys[key] = st
s.mu.Unlock()
return 1, nil
}
func (s *steps) get(key string) (delivery.Step, bool) {
s.mu.Lock()
defer s.mu.Unlock()
st, ok := s.keys[key]
return st, ok
}
func testAsk(kind string) delivery.StepAsk {
id := NewID()
a := delivery.StepAsk{ID: id, Kind: kind, Language: delivery.AskGo, Asker: "mesh-delivery-builder", At: time.Now()}
fetch := map[string]any{"repository": "novox/x", "commit": "0123456789abcdef0123456789abcdef01234567"}
if kind == delivery.AskDelivery {
b := buildJobFixture
b.Fetch = fetch
a.Build = &b
} else {
a.Check = &delivery.CheckJob{Fetch: fetch, Levels: []string{delivery.LevelUnit}}
}
return a
}
var buildJobFixture = delivery.BuildJob{Module: "m", Path: ".", Artifacts: []delivery.AskArtifact{{Artifact: "bundle"}}}
func waitFor(t *testing.T, what string, cond func() bool) {
t.Helper()
deadline := time.Now().Add(2 * time.Second)
for !cond() {
if time.Now().After(deadline) {
t.Fatalf("waited 2 s for %s", what)
}
time.Sleep(time.Millisecond)
}
}
// 1887/A2a: given a check ask published before a delivery ask and one slot, the delivery ask runs first.
func TestPullTakesDeliveryBeforeCheck(t *testing.T) {
src, st := NewFakeAsks(), newSteps()
check, recheck, deliver := testAsk(delivery.AskCheck), testAsk(delivery.AskRecheck), testAsk(delivery.AskDelivery)
for _, a := range []delivery.StepAsk{recheck, check, deliver} {
if err := src.PublishAsk(a); err != nil {
t.Fatal(err)
}
}
var mu sync.Mutex
var order []string
p := &Puller{Source: src, Language: delivery.AskGo, Node: "shanks", Put: st.put, Capacity: func() int { return 1 },
PullWait: 10 * time.Millisecond, Run: func(ctx context.Context, a delivery.StepAsk) (any, error) {
mu.Lock()
order = append(order, a.Kind)
mu.Unlock()
return map[string]string{"ran": a.ID}, nil
}}
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
go p.Pull(ctx)
waitFor(t, "three asks acked", func() bool { a, _, _ := src.Fates(); return len(a) == 3 })
mu.Lock()
defer mu.Unlock()
if want := []string{delivery.AskDelivery, delivery.AskCheck, delivery.AskRecheck}; len(order) != 3 || order[0] != want[0] || order[1] != want[1] || order[2] != want[2] {
t.Fatalf("order = %v, want %v", order, want)
}
key, _ := delivery.AskStepKey("shanks", deliver.ID)
s, ok := st.get(key)
if !ok || s.State != delivery.StepPassed || string(s.Result) != `{"ran":"`+deliver.ID+`"}` {
t.Fatalf("the step %s = %+v (%v)", key, s, ok)
}
}
// 1887/A2a, 1887/AC-pull: given capacity 2 and three asks waiting, two run and the third waits, and it starts when
// one ends, with no timer. Issue 1806's follow-up: the 2 is the CPU's, a configured 3 bounded by a 12-core slice at 6
// cores a step, said once in capacity.<node>; and issue 1890: a run's phase is written to its step key and logged with
// its ask id, and its end keeps the last phase.
func TestPullHoldsAtMostItsCapacity(t *testing.T) {
src, st := NewFakeAsks(), newSteps()
asks := []delivery.StepAsk{}
for i := 0; i < 3; i++ {
a := testAsk(delivery.AskDelivery)
asks = append(asks, a)
_ = src.PublishAsk(a)
}
release := make(chan struct{})
var mu sync.Mutex
started := 0
var said []string
capacities := map[string][]byte{}
quota := 1200
p := &Puller{Source: src, Language: delivery.AskGo, Node: "shanks", Put: st.put, Capacity: func() int { return 3 },
CoresPerStep: func() float64 { return 6 },
Quota: func() (int, string) { mu.Lock(); defer mu.Unlock(); return quota, "a test's slice" },
PausePut: func(key string, v any) (uint64, error) {
mu.Lock()
capacities[key] = v.(json.RawMessage)
mu.Unlock()
return 1, nil
},
Logf: func(f string, a ...any) { mu.Lock(); said = append(said, fmt.Sprintf(f, a...)); mu.Unlock() },
PullWait: 10 * time.Millisecond, Run: func(ctx context.Context, a delivery.StepAsk) (any, error) {
mu.Lock()
started++
mu.Unlock()
Phase(ctx, "unit: tests of 3 packages")
<-release
return nil, nil
}}
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
go p.Pull(ctx)
waitFor(t, "two in hand", func() bool { return p.InHand() == 2 })
time.Sleep(30 * time.Millisecond) // three pull waits: the third must still wait
if p.InHand() != 2 || src.Waiting(delivery.AskDelivery) != 1 {
t.Fatalf("in hand %d, waiting %d; want 2 and 1", p.InHand(), src.Waiting(delivery.AskDelivery))
}
c := p.CapacityDetail()
if c.Effective != 2 || c.Configured != 3 || c.ByCPU != 2 || c.QuotaCores != 12 || !strings.Contains(c.Why, "bounded by the CPU") {
t.Fatalf("the capacity judged by = %+v, want 2 of a configured 3 bounded by 12 cores / 6", c)
}
mu.Lock()
raw := capacities["capacity.shanks"]
capLines := 0
for _, l := range said {
if strings.Contains(l, "build capacity of shanks is 2, bounded by the CPU") {
capLines++
}
}
mu.Unlock()
if got, err := delivery.DecodeCapacity(raw); err != nil || got.Effective != 2 || capLines != 1 {
t.Fatalf("capacity.shanks = %s (%v), said %d times; want effective 2, said once", raw, err, capLines)
}
waitFor(t, "a phase on the step key", func() bool {
key, _ := delivery.AskStepKey("shanks", p.Running()[0].ID)
s, _ := st.get(key)
return s.State == delivery.StepRunning && s.Phase == "unit: tests of 3 packages" && !s.PhaseAt.IsZero() && s.Owner == Owner // 1890/AC5
})
release <- struct{}{}
waitFor(t, "the third taken", func() bool { return src.Waiting(delivery.AskDelivery) == 0 })
// Taken from the source comes a moment before its run starts: wait for the start, not only the take.
waitFor(t, "the third started", func() bool { mu.Lock(); defer mu.Unlock(); return started == 3 })
close(release)
waitFor(t, "all acked", func() bool { a, _, _ := src.Fates(); return len(a) == 3 })
for _, a := range asks {
key, _ := delivery.AskStepKey("shanks", a.ID)
if s, _ := st.get(key); s.State != delivery.StepPassed || s.Phase != "unit: tests of 3 packages" || s.Owner != Owner {
t.Errorf("the end of %s = %+v, want passed in its last phase", a.ID, s)
}
}
mu.Lock()
logged := strings.Join(said, "\n")
quota = 600 // the cap lowered: one step at 6 cores, followed at the next judgement
mu.Unlock()
if !strings.Contains(logged, "the delivery ask "+asks[0].ID+" on shanks: unit: tests of 3 packages") {
t.Errorf("no journal line names the ask's phase: %s", logged)
}
if c := p.CapacityDetail(); c.Effective != 1 {
t.Errorf("after the quota fell to 6 cores, capacity %+v, want 1", c)
}
}
// 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: "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, "three termed", func() bool { _, tm, _ := src.Fates(); return len(tm) == 3 })
if 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.
type kv struct {
mu sync.Mutex
vals map[string][]byte
}
func (k *kv) put(key string, value any) (uint64, error) {
raw, _ := value.(json.RawMessage)
k.mu.Lock()
defer k.mu.Unlock()
if k.vals == nil {
k.vals = map[string][]byte{}
}
k.vals[key] = append([]byte(nil), raw...)
return 1, nil
}
func (k *kv) load(key string) ([]byte, error) {
k.mu.Lock()
defer k.mu.Unlock()
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.
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)
}
})
}
}
// 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{}
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}
if err := p.Pause("the operator"); err != nil {
t.Fatal(err)
}
key, _ := delivery.PauseKey("shanks")
raw, _ := st.load(key)
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}
_ = src.PublishAsk(testAsk(delivery.AskDelivery))
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
go again.Pull(ctx)
time.Sleep(50 * time.Millisecond)
if !again.Paused() || src.Waiting(delivery.AskDelivery) != 1 {
t.Fatalf("restarted: paused %v, waiting %d; want paused and 1", again.Paused(), src.Waiting(delivery.AskDelivery))
}
if err := again.Resume("the operator"); err != nil {
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
// acknowledges its ask, so the stream gives it to another node.
func TestPullHeartbeatAndStop(t *testing.T) {
src, st := NewFakeAsks(), newSteps()
a := testAsk(delivery.AskDelivery)
_ = src.PublishAsk(a)
running := make(chan struct{})
p := &Puller{Source: src, Language: delivery.AskGo, Node: "shanks", Put: st.put, Capacity: func() int { return 1 },
PullWait: 10 * time.Millisecond, Heartbeat: 5 * time.Millisecond,
Run: func(ctx context.Context, a delivery.StepAsk) (any, error) {
close(running)
<-ctx.Done()
return nil, ctx.Err()
}}
ctx, cancel := context.WithCancel(context.Background())
stopped := make(chan struct{})
go func() { p.Pull(ctx); close(stopped) }()
<-running
waitFor(t, "two heartbeats", func() bool { src.mu.Lock(); defer src.mu.Unlock(); return src.InProgress >= 2 })
cancel()
<-stopped
waitFor(t, "the step's goroutine gone", func() bool { return p.InHand() == 0 })
acked, termed, naked := src.Fates()
if len(acked)+len(termed)+len(naked) != 0 {
t.Fatalf("a stopped holder gave its ask a fate: acked %v termed %v naked %v", acked, termed, naked)
}
key, _ := delivery.AskStepKey("shanks", a.ID)
if s, ok := st.get(key); !ok || s.State != delivery.StepRunning {
t.Fatalf("the step %s = %+v, want left running", key, s)
}
}
// 1907: an ask taken past AskRuns (each run took its node down) is run no more: its step ends failed saying why, so the
// asker's key fails, and it is ended on the stream, not offered to another node.
func TestAPoisonedAskIsSaidAndRunNoMore(t *testing.T) {
src, st := NewFakeAsks(), newSteps()
src.Delivered = delivery.AskRuns + 1
a := testAsk(delivery.AskDelivery)
_ = src.PublishAsk(a)
ran := false
p := &Puller{Source: src, Language: delivery.AskGo, Node: "shanks", 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, "the ask termed", func() bool { _, tm, _ := src.Fates(); return len(tm) == 1 })
key, _ := delivery.AskStepKey("shanks", a.ID)
s, ok := st.get(key)
if ran || !ok || s.State != delivery.StepFailed || !strings.Contains(s.Reason, "taken 3 times") || !strings.Contains(s.Reason, "poison") {
t.Fatalf("ran %v, step %+v", ran, s)
}
if acked, _, naked := src.Fates(); len(acked)+len(naked) != 0 {
t.Errorf("acked %v naked %v, want it termed alone", acked, naked)
}
}