Merge pull request #106266 from ahg-g/ahg-metrics

Move a number of scheduler metrics to STABLE

pkg/scheduler/internal/queue/scheduling_queue_test.go

@@ -46,7 +46,7 @@ import (
 )
 
 const queueMetricMetadata = `
-		# HELP scheduler_queue_incoming_pods_total [ALPHA] Number of pods added to scheduling queues by event and queue type.
+		# HELP scheduler_queue_incoming_pods_total [STABLE] Number of pods added to scheduling queues by event and queue type.
 		# TYPE scheduler_queue_incoming_pods_total counter
 	`
 

pkg/scheduler/metrics/metrics.go

@@ -111,7 +111,7 @@ var (
 			Help:      "E2e latency for a pod being scheduled which may include multiple scheduling attempts.",
 			// Start with 10ms with the last bucket being [~88m, Inf).
 			Buckets:        metrics.ExponentialBuckets(0.01, 2, 20),
-			StabilityLevel: metrics.ALPHA,
+			StabilityLevel: metrics.STABLE,
 		},
 		[]string{"attempts"})
 
@@ -121,7 +121,7 @@ var (
 			Name:           "pod_scheduling_attempts",
 			Help:           "Number of attempts to successfully schedule a pod.",
 			Buckets:        metrics.ExponentialBuckets(1, 2, 5),
-			StabilityLevel: metrics.ALPHA,
+			StabilityLevel: metrics.STABLE,
 		})
 
 	FrameworkExtensionPointDuration = metrics.NewHistogramVec(
@@ -131,7 +131,7 @@ var (
 			Help:      "Latency for running all plugins of a specific extension point.",
 			// Start with 0.1ms with the last bucket being [~200ms, Inf)
 			Buckets:        metrics.ExponentialBuckets(0.0001, 2, 12),
-			StabilityLevel: metrics.ALPHA,
+			StabilityLevel: metrics.STABLE,
 		},
 		[]string{"extension_point", "status", "profile"})
 
@@ -152,7 +152,7 @@ var (
 			Subsystem:      SchedulerSubsystem,
 			Name:           "queue_incoming_pods_total",
 			Help:           "Number of pods added to scheduling queues by event and queue type.",
-			StabilityLevel: metrics.ALPHA,
+			StabilityLevel: metrics.STABLE,
 		}, []string{"queue", "event"})
 
 	PermitWaitDuration = metrics.NewHistogramVec(

test/instrumentation/testdata/stable-metrics-list.yaml

@@ -1,3 +1,25 @@
+- name: framework_extension_point_duration_seconds
+  subsystem: scheduler
+  help: Latency for running all plugins of a specific extension point.
+  type: Histogram
+  stabilityLevel: STABLE
+  labels:
+  - extension_point
+  - profile
+  - status
+  buckets:
+  - 0.0001
+  - 0.0002
+  - 0.0004
+  - 0.0008
+  - 0.0016
+  - 0.0032
+  - 0.0064
+  - 0.0128
+  - 0.0256
+  - 0.0512
+  - 0.1024
+  - 0.2048
 - name: pending_pods
   subsystem: scheduler
   help: Number of pending pods, by the queue type. 'active' means number of pods in
@@ -7,6 +29,46 @@
   stabilityLevel: STABLE
   labels:
   - queue
+- name: pod_scheduling_attempts
+  subsystem: scheduler
+  help: Number of attempts to successfully schedule a pod.
+  type: Histogram
+  stabilityLevel: STABLE
+  buckets:
+  - 1
+  - 2
+  - 4
+  - 8
+  - 16
+- name: pod_scheduling_duration_seconds
+  subsystem: scheduler
+  help: E2e latency for a pod being scheduled which may include multiple scheduling
+    attempts.
+  type: Histogram
+  stabilityLevel: STABLE
+  labels:
+  - attempts
+  buckets:
+  - 0.01
+  - 0.02
+  - 0.04
+  - 0.08
+  - 0.16
+  - 0.32
+  - 0.64
+  - 1.28
+  - 2.56
+  - 5.12
+  - 10.24
+  - 20.48
+  - 40.96
+  - 81.92
+  - 163.84
+  - 327.68
+  - 655.36
+  - 1310.72
+  - 2621.44
+  - 5242.88
 - name: preemption_attempts_total
   subsystem: scheduler
   help: Total preemption attempts in the cluster till now
@@ -28,6 +90,14 @@
   - 40
   - 45
   - 50
+- name: queue_incoming_pods_total
+  subsystem: scheduler
+  help: Number of pods added to scheduling queues by event and queue type.
+  type: Counter
+  stabilityLevel: STABLE
+  labels:
+  - event
+  - queue
 - name: schedule_attempts_total
   subsystem: scheduler
   help: Number of attempts to schedule pods, by the result. 'unschedulable' means