Files
mesh-controller/cmd/mesh-controller/status_summary_test.go
T
jochen e74c32ed50 Keep calls and hand acts on the bus, answer status at once, record durations (hq to-be 45 Phase 0)
A controller restart lost every call's outcome, `status` composed the mesh
while its caller waited (18.6s live on 2026-10-06, past the 10s window), a
repair by hand left no trace, and the core's bounds had nothing measured to
be set from.

- calls: kept in the controller's bucket mesh-controller_calls (last 1000 or
  14 days, answers bounded to 64 KiB), read by id across a restart; a
  controller starting marks a stopped one's running calls abandoned; each
  call names its caller from the inbox its answer goes to.
- status: the serving controller composes it at start, after news from a
  machine, a build or an acting verb, and every minute; the verb answers the
  last composition at once with when and how long it took. Composing resolves
  each machine once instead of twice.
- hand-act log in mesh-controller_hand-acts: push (required through the seat),
  plans stop/close, broker consumer-reset and the new hand-act record take
  --why/--cause/--condition; `hand-acts` lists them and repeated causes;
  status counts the week's.
- durations (migration 0066): apply (send to first report), heartbeat gap,
  plan tier and build, recorded as heard; `durations` summarises them.
- the controller's seat row takes this binary's definition of its own verbs,
  so the console no longer judges calls against an older build's schema.
- the controller is granted its two buckets' subjects.
2026-10-06 02:59:36 +02:00

153 lines
4.5 KiB
Go

package main
import (
"context"
"encoding/json"
"errors"
"strings"
"sync/atomic"
"testing"
"time"
"github.com/novox/mesh-controller/internal/link"
)
// quickly shortens the summary's clocks for one test.
func quickly(t *testing.T) {
t.Helper()
every, settle := statusEvery, statusSettle
statusEvery, statusSettle = time.Hour, 10*time.Millisecond
t.Cleanup(func() { statusEvery, statusSettle = every, settle })
}
// **`status` answers in full within ten seconds, five times in a row** (novox/hq to-be 45 Phase 0,
// D9) — however long composing it takes. On 2026-10-06 composing took eighteen seconds and the
// verb answered "still running"; from the summary it answers at once, in full, saying when.
func TestStatusAnswersAtOnceHoweverLongComposingTakes(t *testing.T) {
quickly(t)
var composed atomic.Int32
slow := make(chan struct{})
s := newStatusSummary(func(ctx context.Context) ([]byte, error) {
if composed.Add(1) > 1 {
<-slow // every composition after the first outlasts any caller
}
return []byte(`{"wrong":[],"machines":4}`), nil
})
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
defer close(slow)
go s.keep(ctx)
for i := 0; i < 5; i++ {
s.nudge() // a composition is under way and does not finish
start := time.Now()
got, err := s.answer(ctx)
if err != nil {
t.Fatal(err)
}
if took := time.Since(start); took > time.Second {
t.Fatalf("answer %d took %s", i+1, took)
}
m := got.(map[string]any)
if m["answer"].(map[string]any)["machines"] != float64(4) || m["composed"] == "" || m["ok"] != true {
t.Fatalf("answer %d was not in full: %v", i+1, m)
}
}
}
// The first composition is waited for, never past the caller's window; a controller with none yet
// says so rather than answering an empty mesh as a well one.
func TestStatusBeforeItsFirstCompositionSaysSo(t *testing.T) {
quickly(t)
was := link.AnswerWithin
link.AnswerWithin = 1100 * time.Millisecond
t.Cleanup(func() { link.AnswerWithin = was })
never := make(chan struct{})
defer close(never)
s := newStatusSummary(func(context.Context) ([]byte, error) { <-never; return nil, nil })
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
go s.keep(ctx)
start := time.Now()
_, err := s.answer(ctx)
if err == nil || !strings.Contains(err.Error(), "has no status to answer yet") {
t.Fatalf("answered %v", err)
}
if took := time.Since(start); took > link.AnswerWithin {
t.Fatalf("waited %s, past the caller's window", took)
}
}
// A nudge composes it again, once for several close together; a failed composition leaves the last
// summary standing and says it is the last that could be composed.
func TestANudgeComposesAgainAndAFailureKeepsTheLastSummary(t *testing.T) {
quickly(t)
var composed atomic.Int32
fail := atomic.Bool{}
s := newStatusSummary(func(context.Context) ([]byte, error) {
n := composed.Add(1)
if fail.Load() {
return nil, errors.New("the store did not answer")
}
body, _ := json.Marshal(map[string]any{"n": n})
return body, nil
})
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
go s.keep(ctx)
if _, err := s.answer(ctx); err != nil {
t.Fatal(err)
}
s.nudge()
s.nudge()
s.nudge()
waitFor(t, func() bool { return composed.Load() == 2 })
time.Sleep(50 * time.Millisecond)
if n := composed.Load(); n != 2 {
t.Fatalf("three nudges together composed %d times after the first", n-1)
}
fail.Store(true)
s.nudge()
waitFor(t, func() bool { return composed.Load() == 3 })
waitFor(t, func() bool {
got, err := s.answer(ctx)
if err != nil {
t.Fatal(err)
}
m := got.(map[string]any)
return m["lastAttemptFailed"] != nil && m["answer"].(map[string]any)["n"] == float64(2)
})
}
// The seat's `status` answers from the summary when this process keeps one.
func TestTheStatusVerbAnswersFromTheSummary(t *testing.T) {
quickly(t)
s := newStatusSummary(func(context.Context) ([]byte, error) { return []byte(`{"from":"summary"}`), nil })
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
go s.keep(ctx)
statusFrom = s
t.Cleanup(func() { statusFrom = nil })
handlers, _, err := seatToolHandlers()
if err != nil {
t.Fatal(err)
}
got, err := handlers["status"](ctx, json.RawMessage(`{}`))
if err != nil {
t.Fatal(err)
}
if got.(map[string]any)["answer"].(map[string]any)["from"] != "summary" {
t.Fatalf("answered %v", got)
}
}
func waitFor(t *testing.T, ok func() bool) {
t.Helper()
deadline := time.Now().Add(3 * time.Second)
for !ok() {
if time.Now().After(deadline) {
t.Fatal("never happened")
}
time.Sleep(5 * time.Millisecond)
}
}