github/kubernetes
1
0
Fork 0
mirror of https://github.com/k3s-io/kubernetes.git synced 2025-12-07 18:06:21 +00:00
Code Issues Projects Releases Wiki Activity

Run test/instrumentation/update-*

Browse Source
This commit is contained in:
Tim Hockin
2023-12-09 17:54:43 -08:00
parent e5b64bdef7
commit 0c3e49e64c
2 changed files with 503 additions and 237 deletions
Download Patch File Download Diff File Expand all files Collapse all files

531
test/instrumentation/documentation/documentation-list.yaml
View File

@@ -271,6 +271,30 @@
labels:
- action
- error
- name: job_finished_indexes_total
subsystem: job_controller
help: "`The number of finished indexes. Possible values for the\n\t\t\tstatus label
are: \"succeeded\", \"failed\". Possible values for the\n\t\t\tbackoffLimit label
are: \"perIndex\" and \"global\"`"
type: Counter
stabilityLevel: ALPHA
labels:
- backoffLimit
- status
- name: job_pods_creation_total
subsystem: job_controller
help: |-
`The number of Pods created by the Job controller labelled with a reason for the Pod creation.
This metric also distinguishes between Pods created using different PodReplacementPolicy settings.
Possible values of the "reason" label are:
"new", "recreate_terminating_or_failed", "recreate_failed".
Possible values of the "status" label are:
"succeeded", "failed".`
type: Counter
stabilityLevel: ALPHA
labels:
- reason
- status
- name: pod_failures_handled_by_failure_policy_total
subsystem: job_controller
help: "`The number of failed Pods handled by failure policy with\n\t\t\trespect
@@ -381,47 +405,6 @@
stabilityLevel: ALPHA
labels:
- clusterCIDR
- name: multicidrset_allocation_tries_per_request
subsystem: node_ipam_controller
help: Histogram measuring CIDR allocation tries per request.
type: Histogram
stabilityLevel: ALPHA
labels:
- clusterCIDR
buckets:
- 1
- 5
- 25
- 125
- 625
- name: multicidrset_cidrs_allocations_total
subsystem: node_ipam_controller
help: Counter measuring total number of CIDR allocations.
type: Counter
stabilityLevel: ALPHA
labels:
- clusterCIDR
- name: multicidrset_cidrs_releases_total
subsystem: node_ipam_controller
help: Counter measuring total number of CIDR releases.
type: Counter
stabilityLevel: ALPHA
labels:
- clusterCIDR
- name: multicidrset_usage_cidrs
subsystem: node_ipam_controller
help: Gauge measuring percentage of allocated CIDRs.
type: Gauge
stabilityLevel: ALPHA
labels:
- clusterCIDR
- name: multicirdset_max_cidrs
subsystem: node_ipam_controller
help: Maximum number of CIDRs that can be allocated.
type: Gauge
stabilityLevel: ALPHA
labels:
- clusterCIDR
- name: force_delete_pod_errors_total
subsystem: pod_gc_collector
help: Number of errors encountered when forcefully deleting the pods since the Pod
@@ -443,8 +426,8 @@
- name: sorting_deletion_age_ratio
subsystem: replicaset_controller
help: The ratio of chosen deleted pod's ages to the current youngest pod's age (at
the time). Should be <2.The intent of this metric is to measure the rough efficacy
of the LogarithmicScaleDown feature gate's effect onthe sorting (and deletion)
the time). Should be <2. The intent of this metric is to measure the rough efficacy
of the LogarithmicScaleDown feature gate's effect on the sorting (and deletion)
of pods when a replicaset scales down. This only considers Ready pods when calculating
and reporting.
type: Histogram
@@ -466,26 +449,30 @@
help: Number of ResourceClaims creation request failures
type: Counter
stabilityLevel: ALPHA
- name: job_deletion_duration_seconds
subsystem: ttl_after_finished_controller
help: The time it took to delete the job since it became eligible for deletion
- name: pod_deletion_duration_seconds
subsystem: taint_eviction_controller
help: Latency, in seconds, between the time when a taint effect has been activated
for the Pod and its deletion via TaintEvictionController.
type: Histogram
stabilityLevel: ALPHA
buckets:
- 0.005
- 0.025
- 0.1
- 0.2
- 0.4
- 0.8
- 1.6
- 3.2
- 6.4
- 12.8
- 25.6
- 51.2
- 102.4
- 204.8
- 409.6
- 819.2
- 0.5
- 1
- 2.5
- 10
- 30
- 60
- 120
- 180
- 240
- name: pod_deletions_total
subsystem: taint_eviction_controller
help: Total number of Pods deleted by TaintEvictionController since its start.
type: Counter
stabilityLevel: ALPHA
- name: job_pods_finished_total
subsystem: job_controller
help: The number of finished Pods that are fully tracked
@@ -504,8 +491,6 @@
- completion_mode
- result
buckets:
- 0.001
- 0.002
- 0.004
- 0.008
- 0.016
@@ -519,6 +504,8 @@
- 4.096
- 8.192
- 16.384
- 32.768
- 65.536
- name: job_syncs_total
subsystem: job_controller
help: The number of job syncs
@@ -678,6 +665,26 @@
labels:
- node
- volume_plugin
- name: job_deletion_duration_seconds
subsystem: ttl_after_finished_controller
help: The time it took to delete the job since it became eligible for deletion
type: Histogram
stabilityLevel: ALPHA
buckets:
- 0.1
- 0.2
- 0.4
- 0.8
- 1.6
- 3.2
- 6.4
- 12.8
- 25.6
- 51.2
- 102.4
- 204.8
- 409.6
- 819.2
- name: volume_operation_total_errors
help: Total volume operation errors
type: Counter
@@ -852,6 +859,12 @@
help: Last graceful shutdown start time since unix epoch in seconds
type: Gauge
stabilityLevel: ALPHA
- name: image_garbage_collected_total
subsystem: kubelet
help: Total number of images garbage collected by the kubelet, whether through disk
usage or image age.
type: Counter
stabilityLevel: ALPHA
- name: lifecycle_handler_http_fallbacks_total
subsystem: kubelet
help: The number of times lifecycle handlers successfully fell back to http from
@@ -876,6 +889,31 @@
stabilityLevel: ALPHA
labels:
- node
- name: node_startup_duration_seconds
subsystem: kubelet
help: Duration in seconds of node startup in total.
type: Gauge
stabilityLevel: ALPHA
- name: node_startup_post_registration_duration_seconds
subsystem: kubelet
help: Duration in seconds of node startup after registration.
type: Gauge
stabilityLevel: ALPHA
- name: node_startup_pre_kubelet_duration_seconds
subsystem: kubelet
help: Duration in seconds of node startup before kubelet starts.
type: Gauge
stabilityLevel: ALPHA
- name: node_startup_pre_registration_duration_seconds
subsystem: kubelet
help: Duration in seconds of node startup before registration.
type: Gauge
stabilityLevel: ALPHA
- name: node_startup_registration_duration_seconds
subsystem: kubelet
help: Duration in seconds of node startup during registration.
type: Gauge
stabilityLevel: ALPHA
- name: orphan_pod_cleaned_volumes
subsystem: kubelet
help: The total number of orphaned Pods whose volumes were cleaned in the last periodic
@@ -1003,17 +1041,31 @@
type: Histogram
stabilityLevel: ALPHA
buckets:
- 0.005
- 0.01
- 0.025
- 0.05
- 0.1
- 0.25
- 0.5
- 1
- 2.5
- 2
- 3
- 4
- 5
- 6
- 8
- 10
- 20
- 30
- 45
- 60
- 120
- 180
- 240
- 300
- 360
- 480
- 600
- 900
- 1200
- 1800
- 2700
- 3600
- name: pod_start_sli_duration_seconds
subsystem: kubelet
help: Duration in seconds to start a pod, excluding time to pull images and run
@@ -1047,6 +1099,39 @@
- 1800
- 2700
- 3600
- name: pod_start_total_duration_seconds
subsystem: kubelet
help: Duration in seconds to start a pod since creation, including time to pull
images and run init containers, measured from pod creation timestamp to when all
its containers are reported as started and observed via watch
type: Histogram
stabilityLevel: ALPHA
buckets:
- 0.5
- 1
- 2
- 3
- 4
- 5
- 6
- 8
- 10
- 20
- 30
- 45
- 60
- 120
- 180
- 240
- 300
- 360
- 480
- 600
- 900
- 1200
- 1800
- 2700
- 3600
- name: pod_status_sync_duration_seconds
subsystem: kubelet
help: Duration in seconds to sync a pod status update. Measures time from detection
@@ -1761,6 +1846,8 @@
Pods.
type: Gauge
stabilityLevel: ALPHA
labels:
- volume_plugin
- name: volume_manager_selinux_volume_context_mismatch_warnings_total
help: Number of errors when a Pod uses a volume that is already mounted with a different
SELinux context than the Pod needs. They are not errors yet, but they will become
@@ -1768,11 +1855,15 @@
access modes.
type: Gauge
stabilityLevel: ALPHA
labels:
- volume_plugin
- name: volume_manager_selinux_volumes_admitted_total
help: Number of volumes whose SELinux context was fine and will be mounted with
mount -o context option.
type: Gauge
stabilityLevel: ALPHA
labels:
- volume_plugin
- name: volume_manager_total_volumes
help: Number of volumes in Volume Manager
type: Custom
@@ -1798,6 +1889,30 @@
stabilityLevel: ALPHA
labels:
- signerName
- name: ip_errors_total
subsystem: clusterip_repair
namespace: apiserver
help: 'Number of errors detected on clusterips by the repair loop broken down by
type of error: leak, repair, full, outOfRange, duplicate, unknown, invalid'
type: Counter
stabilityLevel: ALPHA
labels:
- type
- name: reconcile_errors_total
subsystem: clusterip_repair
namespace: apiserver
help: Number of reconciliation failures on the clusterip repair reconcile loop
type: Counter
stabilityLevel: ALPHA
- name: port_errors_total
subsystem: nodeport_repair
namespace: apiserver
help: 'Number of errors detected on ports by the repair loop broken down by type
of error: leak, repair, full, outOfRange, duplicate, unknown'
type: Counter
stabilityLevel: ALPHA
labels:
- type
- name: allocated_ips
subsystem: clusterip_allocator
namespace: kube_apiserver
@@ -2000,6 +2115,11 @@
stabilityLevel: ALPHA
labels:
- operation
- name: invalid_legacy_auto_token_uses_total
subsystem: serviceaccount
help: Cumulative invalid auto-generated legacy tokens used
type: Counter
stabilityLevel: ALPHA
- name: legacy_auto_token_uses_total
subsystem: serviceaccount
help: Cumulative auto-generated legacy tokens used
@@ -2304,6 +2424,24 @@
- 0.0512
- 0.1024
- 0.2048
- name: ratcheting_seconds
subsystem: validation
namespace: apiextensions_apiserver
help: Time for comparison of old to new for the purposes of CRDValidationRatcheting
during an UPDATE in seconds.
type: Histogram
stabilityLevel: ALPHA
buckets:
- 1e-05
- 4e-05
- 0.00016
- 0.00064
- 0.00256
- 0.01024
- 0.04096
- 0.16384
- 0.65536
- 2.62144
- name: conversion_webhook_duration_seconds
namespace: apiserver
help: Conversion webhook request latency
@@ -2833,9 +2971,9 @@
- subresource
- verb
- version
- name: request_body_sizes
- name: request_body_size_bytes
subsystem: apiserver
help: Apiserver request body sizes broken out by size.
help: Apiserver request body size in bytes broken out by resource and verb.
type: Histogram
stabilityLevel: ALPHA
labels:
@@ -3135,6 +3273,35 @@
- group
- kind
- version
- name: watch_list_duration_seconds
subsystem: apiserver
help: Response latency distribution in seconds for watch list requests broken by
group, version, resource and scope.
type: Histogram
stabilityLevel: ALPHA
labels:
- group
- resource
- scope
- version
buckets:
- 0.05
- 0.1
- 0.2
- 0.4
- 0.6
- 0.8
- 1
- 2
- 4
- 6
- 8
- 10
- 15
- 20
- 30
- 45
- 60
- name: authenticated_user_requests
help: Counter of authenticated requests broken out by username.
type: Counter
@@ -3422,7 +3589,8 @@
- 1e+08
- 1e+09
- name: apiserver_storage_objects
help: Number of stored objects at the time of last check split by kind.
help: Number of stored objects at the time of last check split by kind. In case
of a fetching error, the value will be -1.
type: Gauge
stabilityLevel: STABLE
labels:
@@ -4165,6 +4333,84 @@
- 4096
- 8192
- 16384
- name: changes
subsystem: endpoint_slice_controller
help: Number of EndpointSlice changes
type: Counter
stabilityLevel: ALPHA
labels:
- operation
- name: desired_endpoint_slices
subsystem: endpoint_slice_controller
help: Number of EndpointSlices that would exist with perfect endpoint allocation
type: Gauge
stabilityLevel: ALPHA
- name: endpoints_added_per_sync
subsystem: endpoint_slice_controller
help: Number of endpoints added on each Service sync
type: Histogram
stabilityLevel: ALPHA
buckets:
- 2
- 4
- 8
- 16
- 32
- 64
- 128
- 256
- 512
- 1024
- 2048
- 4096
- 8192
- 16384
- 32768
- name: endpoints_desired
subsystem: endpoint_slice_controller
help: Number of endpoints desired
type: Gauge
stabilityLevel: ALPHA
- name: endpoints_removed_per_sync
subsystem: endpoint_slice_controller
help: Number of endpoints removed on each Service sync
type: Histogram
stabilityLevel: ALPHA
buckets:
- 2
- 4
- 8
- 16
- 32
- 64
- 128
- 256
- 512
- 1024
- 2048
- 4096
- 8192
- 16384
- 32768
- name: endpointslices_changed_per_sync
subsystem: endpoint_slice_controller
help: Number of EndpointSlices changed on each Service sync
type: Histogram
stabilityLevel: ALPHA
labels:
- topology
- name: num_endpoint_slices
subsystem: endpoint_slice_controller
help: Number of EndpointSlices
type: Gauge
stabilityLevel: ALPHA
- name: syncs
subsystem: endpoint_slice_controller
help: Number of EndpointSlice syncs
type: Counter
stabilityLevel: ALPHA
labels:
- result
- name: kubernetes_build_info
help: A metric with a constant '1' value labeled by major, minor, git version, git
commit, git tree state, build date, Go version, and compiler from which Kubernetes
@@ -4189,6 +4435,13 @@
stabilityLevel: ALPHA
labels:
- name
- name: leader_election_slowpath_total
help: Total number of slow path exercised in renewing leader leases. 'name' is the
string used to identify the lease. Please make sure to group by name.
type: Counter
stabilityLevel: ALPHA
labels:
- name
- name: rest_client_dns_resolution_duration_seconds
help: DNS resolver latency in seconds. Broken down by host.
type: Histogram
@@ -4444,23 +4697,6 @@
labels:
- name
- stage
- name: healthcheck
namespace: kubernetes
help: This metric records the result of a single healthcheck.
type: Gauge
stabilityLevel: BETA
labels:
- name
- type
- name: healthchecks_total
namespace: kubernetes
help: This metric records the results of all healthcheck.
type: Counter
stabilityLevel: BETA
labels:
- name
- status
- type
- name: registered_metrics_total
help: The count of registered metrics broken by stability level and deprecation
version.
@@ -4469,100 +4705,23 @@
labels:
- deprecated_version
- stability_level
- name: x509_insecure_sha1_total
subsystem: kube_aggregator
namespace: apiserver
help: Counts the number of requests to servers with insecure SHA1 signatures in
their serving certificate OR the number of connection failures due to the insecure
SHA1 signatures (either/or, based on the runtime environment)
type: Counter
stabilityLevel: ALPHA
- name: x509_missing_san_total
subsystem: kube_aggregator
namespace: apiserver
help: Counts the number of requests to servers missing SAN extension in their serving
certificate OR the number of connection failures due to the lack of x509 certificate
SAN extension missing (either/or, based on the runtime environment)
type: Counter
stabilityLevel: ALPHA
- name: changes
subsystem: endpoint_slice_controller
help: Number of EndpointSlice changes
type: Counter
stabilityLevel: ALPHA
labels:
- operation
- name: desired_endpoint_slices
subsystem: endpoint_slice_controller
help: Number of EndpointSlices that would exist with perfect endpoint allocation
- name: healthcheck
namespace: kubernetes
help: This metric records the result of a single healthcheck.
type: Gauge
stabilityLevel: ALPHA
- name: endpoints_added_per_sync
subsystem: endpoint_slice_controller
help: Number of endpoints added on each Service sync
type: Histogram
stabilityLevel: ALPHA
buckets:
- 2
- 4
- 8
- 16
- 32
- 64
- 128
- 256
- 512
- 1024
- 2048
- 4096
- 8192
- 16384
- 32768
- name: endpoints_desired
subsystem: endpoint_slice_controller
help: Number of endpoints desired
type: Gauge
stabilityLevel: ALPHA
- name: endpoints_removed_per_sync
subsystem: endpoint_slice_controller
help: Number of endpoints removed on each Service sync
type: Histogram
stabilityLevel: ALPHA
buckets:
- 2
- 4
- 8
- 16
- 32
- 64
- 128
- 256
- 512
- 1024
- 2048
- 4096
- 8192
- 16384
- 32768
- name: endpointslices_changed_per_sync
subsystem: endpoint_slice_controller
help: Number of EndpointSlices changed on each Service sync
type: Histogram
stabilityLevel: ALPHA
stabilityLevel: STABLE
labels:
- topology
- name: num_endpoint_slices
subsystem: endpoint_slice_controller
help: Number of EndpointSlices
type: Gauge
stabilityLevel: ALPHA
- name: syncs
subsystem: endpoint_slice_controller
help: Number of EndpointSlice syncs
- name
- type
- name: healthchecks_total
namespace: kubernetes
help: This metric records the results of all healthcheck.
type: Counter
stabilityLevel: ALPHA
stabilityLevel: STABLE
labels:
- result
- name
- status
- type
- name: aggregator_openapi_v2_regeneration_count
help: Counter of OpenAPI v2 spec regeneration count broken down by causing APIService
name and reason.
@@ -4592,6 +4751,22 @@
labels:
- name
- reason
- name: x509_insecure_sha1_total
subsystem: kube_aggregator
namespace: apiserver
help: Counts the number of requests to servers with insecure SHA1 signatures in
their serving certificate OR the number of connection failures due to the insecure
SHA1 signatures (either/or, based on the runtime environment)
type: Counter
stabilityLevel: ALPHA
- name: x509_missing_san_total
subsystem: kube_aggregator
namespace: apiserver
help: Counts the number of requests to servers missing SAN extension in their serving
certificate OR the number of connection failures due to the lack of x509 certificate
SAN extension missing (either/or, based on the runtime environment)
type: Counter
stabilityLevel: ALPHA
- name: api_request_duration_seconds
namespace: cloudprovider_azure
help: Latency of an Azure API call