kubernetes/test/instrumentation/testdata/stable-metrics-list.yaml
2022-11-04 13:55:32 +01:00

329 lines
6.5 KiB
YAML

- name: job_creation_skew_duration_seconds
subsystem: cronjob_controller
help: Time between when a cronjob is scheduled to be run, and when the corresponding
job is created
type: Histogram
stabilityLevel: STABLE
buckets:
- 1
- 2
- 4
- 8
- 16
- 32
- 64
- 128
- 256
- 512
- name: evictions_total
subsystem: node_collector
help: Number of Node evictions that happened since current instance of NodeController
started.
type: Counter
stabilityLevel: STABLE
labels:
- zone
- 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
activeQ; 'backoff' means number of pods in backoffQ; 'unschedulable' means number
of pods in unschedulablePods.
type: Gauge
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
type: Counter
stabilityLevel: STABLE
- name: preemption_victims
subsystem: scheduler
help: Number of selected preemption victims
type: Histogram
stabilityLevel: STABLE
buckets:
- 1
- 2
- 4
- 8
- 16
- 32
- 64
- 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
a pod could not be scheduled, while 'error' means an internal scheduler problem.
type: Counter
stabilityLevel: STABLE
labels:
- profile
- result
- name: scheduling_attempt_duration_seconds
subsystem: scheduler
help: Scheduling attempt latency in seconds (scheduling algorithm + binding)
type: Histogram
stabilityLevel: STABLE
labels:
- profile
- result
buckets:
- 0.001
- 0.002
- 0.004
- 0.008
- 0.016
- 0.032
- 0.064
- 0.128
- 0.256
- 0.512
- 1.024
- 2.048
- 4.096
- 8.192
- 16.384
- name: controller_admission_duration_seconds
subsystem: admission
namespace: apiserver
help: Admission controller latency histogram in seconds, identified by name and
broken out for each operation and API resource and type (validate or admit).
type: Histogram
stabilityLevel: STABLE
labels:
- name
- operation
- rejected
- type
buckets:
- 0.005
- 0.025
- 0.1
- 0.5
- 1
- 2.5
- name: step_admission_duration_seconds
subsystem: admission
namespace: apiserver
help: Admission sub-step latency histogram in seconds, broken out for each operation
and API resource and step type (validate or admit).
type: Histogram
stabilityLevel: STABLE
labels:
- operation
- rejected
- type
buckets:
- 0.005
- 0.025
- 0.1
- 0.5
- 1
- 2.5
- name: webhook_admission_duration_seconds
subsystem: admission
namespace: apiserver
help: Admission webhook latency histogram in seconds, identified by name and broken
out for each operation and API resource and type (validate or admit).
type: Histogram
stabilityLevel: STABLE
labels:
- name
- operation
- rejected
- type
buckets:
- 0.005
- 0.025
- 0.1
- 0.5
- 1
- 2.5
- name: current_inflight_requests
subsystem: apiserver
help: Maximal number of currently used inflight request limit of this apiserver
per request kind in last second.
type: Gauge
stabilityLevel: STABLE
labels:
- request_kind
- name: longrunning_requests
subsystem: apiserver
help: Gauge of all active long-running apiserver requests broken out by verb, group,
version, resource, scope and component. Not all requests are tracked this way.
type: Gauge
stabilityLevel: STABLE
labels:
- component
- group
- resource
- scope
- subresource
- verb
- version
- name: request_duration_seconds
subsystem: apiserver
help: Response latency distribution in seconds for each verb, dry run value, group,
version, resource, subresource, scope and component.
type: Histogram
stabilityLevel: STABLE
labels:
- component
- dry_run
- group
- resource
- scope
- subresource
- verb
- version
buckets:
- 0.005
- 0.025
- 0.05
- 0.1
- 0.2
- 0.4
- 0.6
- 0.8
- 1
- 1.25
- 1.5
- 2
- 3
- 4
- 5
- 6
- 8
- 10
- 15
- 20
- 30
- 45
- 60
- name: request_total
subsystem: apiserver
help: Counter of apiserver requests broken out for each verb, dry run value, group,
version, resource, scope, component, and HTTP response code.
type: Counter
stabilityLevel: STABLE
labels:
- code
- component
- dry_run
- group
- resource
- scope
- subresource
- verb
- version
- name: requested_deprecated_apis
subsystem: apiserver
help: Gauge of deprecated APIs that have been requested, broken out by API group,
version, resource, subresource, and removed_release.
type: Gauge
stabilityLevel: STABLE
labels:
- group
- removed_release
- resource
- subresource
- version
- name: response_sizes
subsystem: apiserver
help: Response size distribution in bytes for each group, version, verb, resource,
subresource, scope and component.
type: Histogram
stabilityLevel: STABLE
labels:
- component
- group
- resource
- scope
- subresource
- verb
- version
buckets:
- 1000
- 10000
- 100000
- 1e+06
- 1e+07
- 1e+08
- 1e+09
- name: apiserver_storage_objects
help: Number of stored objects at the time of last check split by kind.
type: Gauge
stabilityLevel: STABLE
labels:
- resource