fix(cag): resolve data races, add queue observability, fix test coverage

Cycle 2 fixes from reviewer-sre + reviewer-quality:

- scheduler.go: remove delete() under RLock (data race); expired entries
  skipped on read, cleaned lazily by next MarkFailed write
- proxy.go: pre-populate transports for scheduler backends at startup to
  prevent concurrent map writes from ServeHTTP goroutines
- proxy.go: log + IncrQueueFull() on queue-full 503 path (was silent)
- proxy.go: remove stub total_tokens/hit_rate from cache-hit log event
- serviceadapter/router.go: Warnf when Auth.Required but jwtValidator nil
- observability: add queue_full_requests_total counter + Prometheus export
- scheduler_test.go: TestBackendAcquireCancelledContext (ctx cancel branch)
- proxy_test.go: implement TestWarmupHeaderHandling (remove t.Skip)
- router_test.go: TestAuthenticate_MethodCapabilityOverrideDirect (auth coverage)
This commit is contained in:
Admin Bot
2026-09-27 18:39:45 +08:00
parent fc5c0e967d
commit a731185588
8 changed files with 184 additions and 27 deletions
+51
View File
@@ -100,6 +100,57 @@ func TestSchedulerSelectNoKeyRoundRobin(t *testing.T) {
}
}
// TestBackendAcquireCancelledContext verifies that Acquire returns ctx.Err() when the
// context is cancelled while the caller is blocked waiting for a concurrency slot,
// and that the queue depth returns to 0 after cancellation.
func TestBackendAcquireCancelledContext(t *testing.T) {
b := newBackend("host:1", 1, 1)
// G1: acquire and hold the only slot indefinitely.
if err := b.Acquire(context.Background()); err != nil {
t.Fatalf("G1 Acquire: unexpected error: %v", err)
}
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
g2Done := make(chan error, 1)
go func() {
g2Done <- b.Acquire(ctx)
}()
// Give G2 time to enter the queue and block waiting for a slot.
time.Sleep(20 * time.Millisecond)
// Verify G2 is queued (queue channel has one item).
if qd := len(b.queue); qd != 1 {
t.Errorf("expected queue depth 1 while G2 blocked, got %d", qd)
}
// Cancel ctx while G2 is waiting for the slot.
cancel()
select {
case err := <-g2Done:
if err == nil {
t.Fatal("G2 Acquire: expected ctx.Err(), got nil")
}
if !errors.Is(err, context.Canceled) {
t.Fatalf("G2 Acquire: expected context.Canceled, got %v", err)
}
case <-time.After(time.Second):
t.Fatal("G2 did not return within 1s after context cancel")
}
// Queue depth must return to 0 after G2 is drained.
if qd := len(b.queue); qd != 0 {
t.Errorf("expected queue depth 0 after cancellation, got %d", qd)
}
// Cleanup: release G1's slot.
b.Release()
}
// TestSchedulerMarkFailedExcludesBackend verifies that a failed backend is not
// selected within the fail window (30 s default).
func TestSchedulerMarkFailedExcludesBackend(t *testing.T) {