Skip to content

fix(observer): emit every Prometheus series once #381

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
rldyourmnd merged 1 commit into from
Sep 2, 2026
Merged

fix(observer): emit every Prometheus series once #381

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 8 additions & 9 deletions internal/fleetobserve/metrics.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -169,15 +169,14 @@ func RenderPrometheus(snapshot Snapshot, now time.Time, maxStaleness time.Durati
labeledGaugeHeader(&output, "gha_fleet_queue_oldest_queued_wait_seconds_by_scale_set", "Longest wait since GitHub queued a still-queued intent, per configured scale set.")
for _, scaleSet := range scaleSets {
metric(&output, "gha_fleet_queue_oldest_queued_wait_seconds_by_scale_set", map[string]string{"scale_set": scaleSet}, float64(snapshot.Queue.OldestQueuedWaitSecondsByScaleSet[scaleSet]))

gauge(&output, "gha_fleet_queue_started_wait_samples", "Jobs whose runner started within the completed-wait window.", float64(snapshot.Queue.StartedWaitSamples))
gauge(&output, "gha_fleet_queue_started_wait_median_seconds", "Median wait, first queued to runner running, over jobs that started in the window.", float64(snapshot.Queue.StartedWaitMedianSeconds))
gauge(&output, "gha_fleet_queue_started_wait_p90_seconds", "Ninetieth-percentile wait, first queued to runner running, over jobs that started in the window.", float64(snapshot.Queue.StartedWaitP90Seconds))
gauge(&output, "gha_fleet_queue_started_wait_max_seconds", "Longest wait, first queued to runner running, over jobs that started in the window.", float64(snapshot.Queue.StartedWaitMaxSeconds))
labeledGaugeHeader(&output, "gha_fleet_queue_started_wait_p90_seconds_by_scale_set", "Ninetieth-percentile completed wait per scale set.")
for _, scaleSet := range scaleSets {
metric(&output, "gha_fleet_queue_started_wait_p90_seconds_by_scale_set", map[string]string{"scale_set": scaleSet}, float64(snapshot.Queue.StartedWaitP90ByScaleSet[scaleSet]))
}
}
gauge(&output, "gha_fleet_queue_started_wait_samples", "Jobs whose runner started within the completed-wait window.", float64(snapshot.Queue.StartedWaitSamples))
gauge(&output, "gha_fleet_queue_started_wait_median_seconds", "Median wait, first queued to runner running, over jobs that started in the window.", float64(snapshot.Queue.StartedWaitMedianSeconds))
gauge(&output, "gha_fleet_queue_started_wait_p90_seconds", "Ninetieth-percentile wait, first queued to runner running, over jobs that started in the window.", float64(snapshot.Queue.StartedWaitP90Seconds))
gauge(&output, "gha_fleet_queue_started_wait_max_seconds", "Longest wait, first queued to runner running, over jobs that started in the window.", float64(snapshot.Queue.StartedWaitMaxSeconds))
labeledGaugeHeader(&output, "gha_fleet_queue_started_wait_p90_seconds_by_scale_set", "Ninetieth-percentile completed wait per scale set.")
for _, scaleSet := range scaleSets {
metric(&output, "gha_fleet_queue_started_wait_p90_seconds_by_scale_set", map[string]string{"scale_set": scaleSet}, float64(snapshot.Queue.StartedWaitP90ByScaleSet[scaleSet]))
}
gauge(&output, "gha_fleet_incus_visible_instances", "Instances visible in the restricted Incus project.", float64(snapshot.Incus.VisibleInstances))
gauge(&output, "gha_fleet_incus_visible_maintenance_instances", "Visible exact image builder or smoke instances; observable maintenance capacity, never GitHub job runners.", float64(snapshot.Incus.VisibleMaintenanceInstances))
Expand Down
18 changes: 18 additions & 0 deletions internal/fleetobserve/metrics_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,6 +88,24 @@ func TestRenderPrometheusIsDeterministicAndBounded(t *testing.T) {
}
}

func TestRenderPrometheusEmitsEverySeriesOnce(t *testing.T) {
metrics := RenderPrometheus(healthyCollector(t).Collect(t.Context()), observationTime, 45*time.Second)
seen := map[string]bool{}
for line := range strings.Lines(metrics) {
if strings.HasPrefix(line, "#") || strings.TrimSpace(line) == "" {
continue
}
series, _, ok := strings.Cut(strings.TrimSpace(line), " ")
if !ok {
t.Fatalf("metric line has no value: %q", line)
}
if seen[series] {
t.Fatalf("Prometheus series emitted more than once: %s", series)
}
seen[series] = true
}
}

func TestRenderPrometheusExposesBoundedDiagnosticConvergence(t *testing.T) {
collector := healthyCollector(t)
collector.Diagnostics = func(time.Time) (workerdiagnostics.SpoolStats, error) {
Expand Down