diff --git a/test/instrumentation/testdata/documentation-list.yaml b/test/instrumentation/documentation/documentation-list.yaml similarity index 96% rename from test/instrumentation/testdata/documentation-list.yaml rename to test/instrumentation/documentation/documentation-list.yaml index 4b884cb9521..5585e648855 100644 --- a/test/instrumentation/testdata/documentation-list.yaml +++ b/test/instrumentation/documentation/documentation-list.yaml @@ -281,6 +281,7 @@ stabilityLevel: ALPHA labels: - completion_mode + - reason - result - name: job_pods_finished_total subsystem: job_controller @@ -324,6 +325,16 @@ - action - completion_mode - result +- 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 + to the failure policy action applied based on the matched\n\t\t\trule. Possible + values of the action label correspond to the\n\t\t\tpossible values for the failure + policy rule action, which are:\n\t\t\t\"FailJob\", \"Ignore\" and \"Count\".`" + type: Counter + stabilityLevel: ALPHA + labels: + - action - name: terminated_pods_tracking_finalizer_total subsystem: job_controller help: |- @@ -547,6 +558,16 @@ help: Counter of certificate renewal errors. type: Counter stabilityLevel: ALPHA +- name: retroactive_storageclass_errors_total + help: Total number of failed retroactive StorageClass assignments to persistent + volume claim + type: Counter + stabilityLevel: ALPHA +- name: retroactive_storageclass_total + help: Total number of retroactive StorageClass assignments to persistent volume + claim + type: Counter + stabilityLevel: ALPHA - name: volume_operation_total_errors help: Total volume operation errors type: Counter @@ -584,6 +605,16 @@ - 4 - 8 - 16 +- name: cpu_manager_pinning_errors_total + subsystem: kubelet + help: The number of cpu core allocations which required pinning failed. + type: Counter + stabilityLevel: ALPHA +- name: cpu_manager_pinning_requests_total + subsystem: kubelet + help: The number of cpu core allocations which required pinning. + type: Counter + stabilityLevel: ALPHA - name: device_plugin_alloc_duration_seconds subsystem: kubelet help: Duration in seconds to serve a device plugin Allocation request. Broken down @@ -1727,6 +1758,52 @@ - 4.096 - 8.192 - 16.384 +- name: check_duration_seconds + subsystem: validating_admission_policy + namespace: apiserver + help: Validation admission latency for individual validation expressions in seconds, + labeled by policy and param resource, further including binding, state and enforcement + action taken. + type: Histogram + stabilityLevel: ALPHA + labels: + - enforcement_action + - params + - policy + - policy_binding + - state + - validation_expression + buckets: + - 5e-07 + - 0.001 + - 0.01 + - 0.1 + - 1 +- name: check_total + subsystem: validating_admission_policy + namespace: apiserver + help: Validation admission policy check total, labeled by policy and param resource, + and further identified by binding, validation expression, enforcement action taken, + and state. + type: Counter + stabilityLevel: ALPHA + labels: + - enforcement_action + - params + - policy + - policy_binding + - state + - validation_expression +- name: definition_total + subsystem: validating_admission_policy + namespace: apiserver + help: Validation admission policy count total, labeled by state and enforcement + action. + type: Counter + stabilityLevel: ALPHA + labels: + - enforcement_action + - state - name: step_admission_duration_seconds_summary subsystem: admission namespace: apiserver @@ -2736,6 +2813,13 @@ help: Total number of failed data encryption key(DEK) generation operations. type: Counter stabilityLevel: ALPHA +- name: storage_db_total_size_in_bytes + subsystem: apiserver + help: Total size of the storage database file physically allocated in bytes. + type: Gauge + stabilityLevel: ALPHA + labels: + - endpoint - name: envelope_transformation_cache_misses_total subsystem: storage namespace: apiserver @@ -2855,12 +2939,6 @@ stabilityLevel: ALPHA labels: - resource -- name: etcd_db_total_size_in_bytes - help: Total size of the etcd database file physically allocated in bytes. - type: Gauge - stabilityLevel: ALPHA - labels: - - endpoint - name: etcd_lease_object_counts help: Number of objects attached to a single etcd lease. type: Histogram diff --git a/test/instrumentation/testdata/documentation.md b/test/instrumentation/documentation/documentation.md similarity index 96% rename from test/instrumentation/testdata/documentation.md rename to test/instrumentation/documentation/documentation.md index 6a75ad66c48..1337a5949ef 100644 --- a/test/instrumentation/testdata/documentation.md +++ b/test/instrumentation/documentation/documentation.md @@ -6,10 +6,10 @@ description: >- --- -## Metrics (auto-generated 2022 Oct 27) +## Metrics (auto-generated 2022 Oct 31) This page details the metrics that different Kubernetes components export. You can query the metrics endpoint for these -components using an HTTP scrape, and fetch the metrics in Prometheus format. +components using an HTTP scrape, and fetch the current metrics data in Prometheus format. ### List of Stable Kubernetes Metrics @@ -554,6 +554,12 @@ components using an HTTP scrape, and fetch the metrics in Prometheus format. Total number of failed data encryption key(DEK) generation operations. None None +apiserver_storage_db_total_size_in_bytes +ALPHA +Gauge +Total size of the storage database file physically allocated in bytes. +
endpoint
+None apiserver_storage_envelope_transformation_cache_misses_total ALPHA Counter @@ -608,6 +614,24 @@ components using an HTTP scrape, and fetch the metrics in Prometheus format. Number of requests dropped with 'TLS handshake error from' error None None +apiserver_validating_admission_policy_check_duration_seconds +ALPHA +Histogram +Validation admission latency for individual validation expressions in seconds, labeled by policy and param resource, further including binding, state and enforcement action taken. +
enforcement_action
params
policy
policy_binding
state
validation_expression
+None +apiserver_validating_admission_policy_check_total +ALPHA +Counter +Validation admission policy check total, labeled by policy and param resource, and further identified by binding, validation expression, enforcement action taken, and state. +
enforcement_action
params
policy
policy_binding
state
validation_expression
+None +apiserver_validating_admission_policy_definition_total +ALPHA +Counter +Validation admission policy count total, labeled by state and enforcement action. +
enforcement_action
state
+None apiserver_watch_cache_events_dispatched_total ALPHA Counter @@ -914,12 +938,6 @@ components using an HTTP scrape, and fetch the metrics in Prometheus format. Number of etcd bookmarks (progress notify events) split by kind.
resource
None -etcd_db_total_size_in_bytes -ALPHA -Gauge -Total size of the etcd database file physically allocated in bytes. -
endpoint
-None etcd_lease_object_counts ALPHA Histogram @@ -966,7 +984,7 @@ components using an HTTP scrape, and fetch the metrics in Prometheus format. ALPHA Counter The number of finished job -
completion_mode
result
+
completion_mode
reason
result
None job_controller_job_pods_finished_total ALPHA @@ -986,6 +1004,12 @@ components using an HTTP scrape, and fetch the metrics in Prometheus format. The number of job syncs
action
completion_mode
result
None +job_controller_pod_failures_handled_by_failure_policy_total +ALPHA +Counter +`The number of failed Pods handled by failure policy with, respect to the failure policy action applied based on the matched, rule. Possible values of the action label correspond to the, possible values for the failure policy rule action, which are:, "FailJob", "Ignore" and "Count".` +
action
+None job_controller_terminated_pods_tracking_finalizer_total ALPHA Counter @@ -1064,6 +1088,18 @@ components using an HTTP scrape, and fetch the metrics in Prometheus format. The number of containers per pod. None None +kubelet_cpu_manager_pinning_errors_total +ALPHA +Counter +The number of cpu core allocations which required pinning failed. +None +None +kubelet_cpu_manager_pinning_requests_total +ALPHA +Counter +The number of cpu core allocations which required pinning. +None +None kubelet_device_plugin_alloc_duration_seconds ALPHA Histogram @@ -1586,6 +1622,18 @@ components using an HTTP scrape, and fetch the metrics in Prometheus format. Response size in bytes. Broken down by verb and host.
host
verb
None +retroactive_storageclass_errors_total +ALPHA +Counter +Total number of failed retroactive StorageClass assignments to persistent volume claim +None +None +retroactive_storageclass_total +ALPHA +Counter +Total number of retroactive StorageClass assignments to persistent volume claim +None +None root_ca_cert_publisher_sync_duration_seconds ALPHA Histogram diff --git a/test/instrumentation/documentation/main.go b/test/instrumentation/documentation/main.go index e423ded75b6..4abd3ffb760 100755 --- a/test/instrumentation/documentation/main.go +++ b/test/instrumentation/documentation/main.go @@ -110,7 +110,7 @@ type templateData struct { } func main() { - dat, err := os.ReadFile("test/instrumentation/testdata/documentation-list.yaml") + dat, err := os.ReadFile("test/instrumentation/documentation/documentation-list.yaml") if err == nil { var parsedMetrics []metric err = yaml.Unmarshal(dat, &parsedMetrics) diff --git a/test/instrumentation/stability-utils.sh b/test/instrumentation/stability-utils.sh index 749d68e37cc..f00a18aff20 100755 --- a/test/instrumentation/stability-utils.sh +++ b/test/instrumentation/stability-utils.sh @@ -114,7 +114,7 @@ kube::update::documentation::list() { echo "${red}!!! updating golden list of metrics has failed! ${reset}" >&2 exit 1 fi - mv -f "$temp_file" "${KUBE_ROOT}/test/instrumentation/testdata/documentation-list.yaml" + mv -f "$temp_file" "${KUBE_ROOT}/test/instrumentation/documentation/documentation-list.yaml" echo "${green}Updated list of metrics for documentation ${reset}" } @@ -126,7 +126,7 @@ kube::update::documentation() { echo "${red}!!! updating documentation has failed! ${reset}" >&2 exit 1 fi - mv -f "$temp_file" "${KUBE_ROOT}/test/instrumentation/testdata/documentation.md" + mv -f "$temp_file" "${KUBE_ROOT}/test/instrumentation/documentation/documentation.md" echo "${green}Updated documentation of metrics.${reset}" }