diff --git a/test/instrumentation/documentation/documentation-list.yaml b/test/instrumentation/documentation/documentation-list.yaml index 557baca0f9c..b94b377b3a3 100644 --- a/test/instrumentation/documentation/documentation-list.yaml +++ b/test/instrumentation/documentation/documentation-list.yaml @@ -12,6 +12,36 @@ certificate is invalid or unused, the value will be +INF. type: Gauge stabilityLevel: ALPHA +- name: sync_duration_seconds + subsystem: clustertrustbundle_publisher + help: The time it took to sync a cluster trust bundle. + type: Histogram + stabilityLevel: ALPHA + labels: + - code + 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: sync_total + subsystem: clustertrustbundle_publisher + help: Number of syncs that occurred in cluster trust bundle publisher. + type: Counter + stabilityLevel: ALPHA + labels: + - code - name: sync_duration_seconds subsystem: root_ca_cert_publisher help: Number of namespace syncs happened in root ca cert publisher. @@ -446,6 +476,11 @@ - 2 - 4 - 8 +- name: allocated_resource_claims + subsystem: resourceclaim_controller + help: Number of allocated ResourceClaims + type: Gauge + stabilityLevel: ALPHA - name: create_attempts_total subsystem: resourceclaim_controller help: Number of ResourceClaims creation requests @@ -456,6 +491,11 @@ help: Number of ResourceClaims creation request failures type: Counter stabilityLevel: ALPHA +- name: resource_claims + subsystem: resourceclaim_controller + help: Number of ResourceClaims + type: Gauge + stabilityLevel: ALPHA - name: job_pods_finished_total subsystem: job_controller help: The number of finished Pods that are fully tracked @@ -531,44 +571,14 @@ - state - name: create_failures_total subsystem: ephemeral_volume_controller - help: Number of PersistenVolumeClaims creation requests + help: Number of PersistentVolumeClaim creation requests type: Counter stabilityLevel: ALPHA - name: create_total subsystem: ephemeral_volume_controller - help: Number of PersistenVolumeClaims creation requests + help: Number of PersistentVolumeClaim creation requests type: Counter stabilityLevel: ALPHA -- name: client_expiration_renew_errors - subsystem: certificate_manager - namespace: kubelet - help: Counter of certificate renewal errors. - type: Counter - stabilityLevel: ALPHA -- name: certificate_manager_server_rotation_seconds - subsystem: kubelet - help: Histogram of the number of seconds the previous certificate lived before being - rotated. - type: Histogram - stabilityLevel: ALPHA - buckets: - - 60 - - 3600 - - 14400 - - 86400 - - 604800 - - 2.592e+06 - - 7.776e+06 - - 1.5552e+07 - - 3.1104e+07 - - 1.24416e+08 -- name: certificate_manager_server_ttl_seconds - subsystem: kubelet - help: Gauge of the shortest TTL (time-to-live) of the Kubelet's serving certificate. - The value is in seconds until certificate expiry (negative if already expired). - If serving certificate is invalid or unused, the value will be +INF. - type: Gauge - stabilityLevel: ALPHA - name: credential_provider_plugin_duration subsystem: kubelet help: Duration of execution in seconds for credential provider plugin @@ -595,11 +605,6 @@ stabilityLevel: ALPHA labels: - plugin_name -- name: server_expiration_renew_errors - subsystem: kubelet - help: Counter of certificate renewal errors. - type: Counter - stabilityLevel: ALPHA - name: pv_collector_bound_pv_count help: Gauge measuring number of persistent volume currently bound type: Custom @@ -612,6 +617,8 @@ stabilityLevel: ALPHA labels: - namespace + - storage_class + - volume_attributes_class - name: pv_collector_total_pv_count help: Gauge measuring total number of persistent volumes type: Custom @@ -631,6 +638,8 @@ stabilityLevel: ALPHA labels: - namespace + - storage_class + - volume_attributes_class - name: retroactive_storageclass_errors_total help: Total number of failed retroactive StorageClass assignments to persistent volume claim @@ -641,6 +650,18 @@ claim type: Counter stabilityLevel: ALPHA +- name: selinux_warning_controller_selinux_volume_conflict + help: Conflict between two Pods using the same volume + type: Custom + stabilityLevel: ALPHA + labels: + - property + - pod1_namespace + - pod1_name + - pod1_value + - pod2_namespace + - pod2_name + - pod2_value - name: storage_count_attachable_volumes_in_use help: Measure number of volumes in use type: Custom @@ -699,6 +720,41 @@ labels: - operation_name - plugin_name +- name: client_expiration_renew_errors + subsystem: certificate_manager + namespace: kubelet + help: Counter of certificate renewal errors. + type: Counter + stabilityLevel: ALPHA +- name: certificate_manager_server_rotation_seconds + subsystem: kubelet + help: Histogram of the number of seconds the previous certificate lived before being + rotated. + type: Histogram + stabilityLevel: ALPHA + buckets: + - 60 + - 3600 + - 14400 + - 86400 + - 604800 + - 2.592e+06 + - 7.776e+06 + - 1.5552e+07 + - 3.1104e+07 + - 1.24416e+08 +- name: certificate_manager_server_ttl_seconds + subsystem: kubelet + help: Gauge of the shortest TTL (time-to-live) of the Kubelet's serving certificate. + The value is in seconds until certificate expiry (negative if already expired). + If serving certificate is invalid or unused, the value will be +INF. + type: Gauge + stabilityLevel: ALPHA +- name: server_expiration_renew_errors + subsystem: kubelet + help: Counter of certificate renewal errors. + type: Counter + stabilityLevel: ALPHA - name: container_swap_usage_bytes help: Current amount of the container swap usage in bytes. Reported only on non-windows systems @@ -708,6 +764,59 @@ - container - pod - namespace +- name: grpc_operations_duration_seconds + subsystem: dra + help: Duration in seconds of the DRA gRPC operations + type: Histogram + stabilityLevel: ALPHA + labels: + - driver_name + - grpc_status_code + - method_name + buckets: + - 0.1 + - 0.1534127404634391 + - 0.23535468936502524 + - 0.36106407876409946 + - 0.5539182980610752 + - 0.849781240983936 + - 1.303672689737678 + - 1.9999999999999993 + - 3.0682548092687805 + - 4.7070937873005025 + - 7.221281575281985 + - 11.078365961221499 + - 16.995624819678714 + - 26.07345379475354 + - 39.99999999999997 +- name: operations_duration_seconds + subsystem: dra + help: Latency histogram in seconds for the duration of handling all ResourceClaims + referenced by a pod when the pod starts or stops. Identified by the name of the + operation (PrepareResources or UnprepareResources) and separated by the success + of the operation. The number of failed operations is provided through the histogram's + overall count. + type: Histogram + stabilityLevel: ALPHA + labels: + - is_error + - operation_name + buckets: + - 0.1 + - 0.1534127404634391 + - 0.23535468936502524 + - 0.36106407876409946 + - 0.5539182980610752 + - 0.849781240983936 + - 1.303672689737678 + - 1.9999999999999993 + - 3.0682548092687805 + - 4.7070937873005025 + - 7.221281575281985 + - 11.078365961221499 + - 16.995624819678714 + - 26.07345379475354 + - 39.99999999999997 - name: force_cleaned_failed_volume_operation_errors_total help: The number of volumes that failed force cleanup after their reconstruction failed during kubelet startup. @@ -726,6 +835,13 @@ stabilityLevel: ALPHA labels: - static +- name: admission_rejections_total + subsystem: kubelet + help: Cumulative number pod admission rejections by the Kubelet. + type: Counter + stabilityLevel: ALPHA + labels: + - reason - name: cgroup_manager_duration_seconds subsystem: kubelet help: Duration in seconds for cgroup manager operations. Broken down by method. @@ -745,6 +861,20 @@ - 2.5 - 5 - 10 +- name: cgroup_version + subsystem: kubelet + help: cgroup version on the hosts. + type: Gauge + stabilityLevel: ALPHA +- name: container_aligned_compute_resources_count + subsystem: kubelet + help: Cumulative number of aligned compute resources allocated to containers by + alignment type. + type: Counter + stabilityLevel: ALPHA + labels: + - boundary + - scope - name: kubelet_container_log_filesystem_used_bytes help: Bytes used by the container's logs on the filesystem. type: Custom @@ -765,6 +895,12 @@ - 4 - 8 - 16 +- name: cpu_manager_exclusive_cpu_allocation_count + subsystem: kubelet + help: The total number of CPUs exclusively allocated to containers running on this + node + type: Gauge + stabilityLevel: ALPHA - name: cpu_manager_pinning_errors_total subsystem: kubelet help: The number of cpu core allocations which required pinning failed. @@ -775,6 +911,11 @@ help: The number of cpu core allocations which required pinning. type: Counter stabilityLevel: ALPHA +- name: cpu_manager_shared_pool_size_millicores + subsystem: kubelet + help: The size of the shared CPU pool for non-guaranteed QoS pods, in millicores. + type: Gauge + stabilityLevel: ALPHA - name: desired_pods subsystem: kubelet help: The number of pods the kubelet is being instructed to run. static is true @@ -868,7 +1009,7 @@ - eviction_signal - name: graceful_shutdown_end_time_seconds subsystem: kubelet - help: Last graceful shutdown start time since unix epoch in seconds + help: Last graceful shutdown end time since unix epoch in seconds type: Gauge stabilityLevel: ALPHA - name: graceful_shutdown_start_time_seconds @@ -1726,132 +1867,6 @@ 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: reconcile_errors_total - subsystem: nodeport_repair - namespace: apiserver - help: Number of reconciliation failures on the nodeport repair reconcile loop - type: Counter - stabilityLevel: ALPHA -- name: allocated_ips - subsystem: clusterip_allocator - namespace: kube_apiserver - help: Gauge measuring the number of allocated IPs for Services - type: Gauge - stabilityLevel: ALPHA - labels: - - cidr -- name: allocation_errors_total - subsystem: clusterip_allocator - namespace: kube_apiserver - help: Number of errors trying to allocate Cluster IPs - type: Counter - stabilityLevel: ALPHA - labels: - - cidr - - scope -- name: allocation_total - subsystem: clusterip_allocator - namespace: kube_apiserver - help: Number of Cluster IPs allocations - type: Counter - stabilityLevel: ALPHA - labels: - - cidr - - scope -- name: available_ips - subsystem: clusterip_allocator - namespace: kube_apiserver - help: Gauge measuring the number of available IPs for Services - type: Gauge - stabilityLevel: ALPHA - labels: - - cidr -- name: allocated_ports - subsystem: nodeport_allocator - namespace: kube_apiserver - help: Gauge measuring the number of allocated NodePorts for Services - type: Gauge - stabilityLevel: ALPHA -- name: allocation_errors_total - subsystem: nodeport_allocator - namespace: kube_apiserver - help: Number of errors trying to allocate NodePort - type: Counter - stabilityLevel: ALPHA - labels: - - scope -- name: allocation_total - subsystem: nodeport_allocator - namespace: kube_apiserver - help: Number of NodePort allocations - type: Counter - stabilityLevel: ALPHA - labels: - - scope -- name: available_ports - subsystem: nodeport_allocator - namespace: kube_apiserver - help: Gauge measuring the number of available NodePorts for Services - type: Gauge - stabilityLevel: ALPHA -- name: backend_tls_failure_total - subsystem: pod_logs - namespace: kube_apiserver - help: Total number of requests for pods/logs that failed due to kubelet server TLS - verification - type: Counter - stabilityLevel: ALPHA -- name: insecure_backend_total - subsystem: pod_logs - namespace: kube_apiserver - help: 'Total number of requests for pods/logs sliced by usage type: enforce_tls, - skip_tls_allowed, skip_tls_denied' - type: Counter - stabilityLevel: ALPHA - labels: - - usage -- name: pods_logs_backend_tls_failure_total - subsystem: pod_logs - namespace: kube_apiserver - help: Total number of requests for pods/logs that failed due to kubelet server TLS - verification - type: Counter - deprecatedVersion: 1.27.0 - stabilityLevel: ALPHA -- name: pods_logs_insecure_backend_total - subsystem: pod_logs - namespace: kube_apiserver - help: 'Total number of requests for pods/logs sliced by usage type: enforce_tls, - skip_tls_allowed, skip_tls_denied' - type: Counter - deprecatedVersion: 1.27.0 - stabilityLevel: ALPHA - labels: - - usage - name: kubeproxy_iptables_ct_state_invalid_dropped_packets_total help: packets dropped by iptables to work around conntrack problems type: Custom @@ -2094,32 +2109,57 @@ help: Cumulative proxy rules Service changes type: Counter stabilityLevel: ALPHA -- name: binder_cache_requests_total - subsystem: scheduler_volume - help: Total number for request volume binding cache +- 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: - - operation -- name: scheduling_stage_error_total - subsystem: scheduler_volume - help: Volume scheduling stage error count + - 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: - - operation -- name: operations_seconds - subsystem: csi - help: Container Storage Interface operation duration with gRPC error code status - total + - type +- name: reconcile_errors_total + subsystem: nodeport_repair + namespace: apiserver + help: Number of reconciliation failures on the nodeport repair reconcile loop + type: Counter + stabilityLevel: ALPHA +- name: allocated_ips + subsystem: clusterip_allocator + namespace: kube_apiserver + help: Gauge measuring the number of allocated IPs for Services + type: Gauge + stabilityLevel: ALPHA + labels: + - cidr +- name: allocation_duration_seconds + subsystem: clusterip_allocator + namespace: kube_apiserver + help: Duration in seconds to allocate a Cluster IP by ServiceCIDR type: Histogram stabilityLevel: ALPHA labels: - - driver_name - - grpc_status_code - - method_name - - migrated + - cidr buckets: + - 0.005 + - 0.01 + - 0.025 + - 0.05 - 0.1 - 0.25 - 0.5 @@ -2127,12 +2167,167 @@ - 2.5 - 5 - 10 - - 15 - - 25 - - 50 - - 120 - - 300 - - 600 +- name: allocation_errors_total + subsystem: clusterip_allocator + namespace: kube_apiserver + help: Number of errors trying to allocate Cluster IPs + type: Counter + stabilityLevel: ALPHA + labels: + - cidr + - scope +- name: allocation_total + subsystem: clusterip_allocator + namespace: kube_apiserver + help: Number of Cluster IPs allocations + type: Counter + stabilityLevel: ALPHA + labels: + - cidr + - scope +- name: available_ips + subsystem: clusterip_allocator + namespace: kube_apiserver + help: Gauge measuring the number of available IPs for Services + type: Gauge + stabilityLevel: ALPHA + labels: + - cidr +- name: allocated_ports + subsystem: nodeport_allocator + namespace: kube_apiserver + help: Gauge measuring the number of allocated NodePorts for Services + type: Gauge + stabilityLevel: ALPHA +- name: allocation_errors_total + subsystem: nodeport_allocator + namespace: kube_apiserver + help: Number of errors trying to allocate NodePort + type: Counter + stabilityLevel: ALPHA + labels: + - scope +- name: allocation_total + subsystem: nodeport_allocator + namespace: kube_apiserver + help: Number of NodePort allocations + type: Counter + stabilityLevel: ALPHA + labels: + - scope +- name: available_ports + subsystem: nodeport_allocator + namespace: kube_apiserver + help: Gauge measuring the number of available NodePorts for Services + type: Gauge + stabilityLevel: ALPHA +- name: backend_tls_failure_total + subsystem: pod_logs + namespace: kube_apiserver + help: Total number of requests for pods/logs that failed due to kubelet server TLS + verification + type: Counter + stabilityLevel: ALPHA +- name: insecure_backend_total + subsystem: pod_logs + namespace: kube_apiserver + help: 'Total number of requests for pods/logs sliced by usage type: enforce_tls, + skip_tls_allowed, skip_tls_denied' + type: Counter + stabilityLevel: ALPHA + labels: + - usage +- name: pods_logs_backend_tls_failure_total + subsystem: pod_logs + namespace: kube_apiserver + help: Total number of requests for pods/logs that failed due to kubelet server TLS + verification + type: Counter + deprecatedVersion: 1.27.0 + stabilityLevel: ALPHA +- name: pods_logs_insecure_backend_total + subsystem: pod_logs + namespace: kube_apiserver + help: 'Total number of requests for pods/logs sliced by usage type: enforce_tls, + skip_tls_allowed, skip_tls_denied' + type: Counter + deprecatedVersion: 1.27.0 + stabilityLevel: ALPHA + labels: + - usage +- name: fetch_keys_data_timestamp + subsystem: externaljwt + namespace: apiserver + help: Unix Timestamp in seconds of the last successful FetchKeys data_timestamp + value returned by the external signer + type: Gauge + stabilityLevel: ALPHA +- name: fetch_keys_request_total + subsystem: externaljwt + namespace: apiserver + help: Total attempts at syncing supported JWKs + type: Counter + stabilityLevel: ALPHA + labels: + - code +- name: fetch_keys_success_timestamp + subsystem: externaljwt + namespace: apiserver + help: Unix Timestamp in seconds of the last successful FetchKeys request + type: Gauge + stabilityLevel: ALPHA +- name: request_duration_seconds + subsystem: externaljwt + namespace: apiserver + help: Request duration and time for calls to external-jwt-signer + type: Histogram + stabilityLevel: ALPHA + labels: + - code + - method + buckets: + - 0.001 + - 0.005 + - 0.01 + - 0.025 + - 0.05 + - 0.1 + - 0.25 + - 0.5 + - 1 + - 2.5 + - 5 + - 10 + - 30 + - 60 +- name: sign_request_total + subsystem: externaljwt + namespace: apiserver + help: Total attempts at signing JWT + type: Counter + stabilityLevel: ALPHA + labels: + - code +- name: event_handling_duration_seconds + subsystem: scheduler + help: Event handling latency in seconds. + type: Histogram + stabilityLevel: ALPHA + labels: + - event + 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: goroutines subsystem: scheduler help: Number of running goroutines split by the work they do such as binding. @@ -2140,6 +2335,13 @@ stabilityLevel: ALPHA labels: - operation +- name: inflight_events + subsystem: scheduler + help: Number of events currently tracked in the scheduling queue. + type: Gauge + stabilityLevel: ALPHA + labels: + - event - name: permit_wait_duration_seconds subsystem: scheduler help: Duration of waiting on permit. @@ -2203,6 +2405,71 @@ - 0.009852612533569338 - 0.014778918800354007 - 0.02216837820053101 +- name: preemption_goroutines_duration_seconds + subsystem: scheduler + help: Duration in seconds for running goroutines for the preemption. + type: Histogram + stabilityLevel: ALPHA + labels: + - result + 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_goroutines_execution_total + subsystem: scheduler + help: Number of preemption goroutines executed. + type: Counter + stabilityLevel: ALPHA + labels: + - result +- name: queueing_hint_execution_duration_seconds + subsystem: scheduler + help: Duration for running a queueing hint function of a plugin. + type: Histogram + stabilityLevel: ALPHA + labels: + - event + - hint + - plugin + buckets: + - 1e-05 + - 1.5000000000000002e-05 + - 2.2500000000000005e-05 + - 3.375000000000001e-05 + - 5.062500000000001e-05 + - 7.593750000000002e-05 + - 0.00011390625000000003 + - 0.00017085937500000006 + - 0.0002562890625000001 + - 0.00038443359375000017 + - 0.0005766503906250003 + - 0.0008649755859375004 + - 0.0012974633789062506 + - 0.0019461950683593758 + - 0.0029192926025390638 + - 0.004378938903808595 + - 0.006568408355712893 + - 0.009852612533569338 + - 0.014778918800354007 + - 0.02216837820053101 - name: scheduler_cache_size subsystem: scheduler help: Number of nodes, pods, and assumed (bound) pods in the scheduler cache. @@ -2241,6 +2508,20 @@ labels: - plugin - profile +- name: binder_cache_requests_total + subsystem: scheduler_volume + help: Total number for request volume binding cache + type: Counter + stabilityLevel: ALPHA + labels: + - operation +- name: scheduling_stage_error_total + subsystem: scheduler_volume + help: Volume scheduling stage error count + type: Counter + stabilityLevel: ALPHA + labels: + - operation - name: invalid_legacy_auto_token_uses_total subsystem: serviceaccount help: Cumulative invalid auto-generated legacy tokens used @@ -2271,50 +2552,6 @@ help: Cumulative valid projected service account tokens used type: Counter stabilityLevel: ALPHA -- name: storage_operation_duration_seconds - help: Storage operation duration - type: Histogram - stabilityLevel: ALPHA - labels: - - migrated - - operation_name - - status - - volume_plugin - buckets: - - 0.1 - - 0.25 - - 0.5 - - 1 - - 2.5 - - 5 - - 10 - - 15 - - 25 - - 50 - - 120 - - 300 - - 600 -- name: volume_operation_total_seconds - help: Storage operation end to end duration in seconds - type: Histogram - stabilityLevel: ALPHA - labels: - - operation_name - - plugin_name - buckets: - - 0.1 - - 0.25 - - 0.5 - - 1 - - 2.5 - - 5 - - 10 - - 15 - - 25 - - 50 - - 120 - - 300 - - 600 - name: pod_scheduling_sli_duration_seconds subsystem: scheduler help: E2e latency for a pod being scheduled, from the time the pod enters the scheduling @@ -2505,6 +2742,31 @@ - 4.096 - 8.192 - 16.384 +- name: operations_seconds + subsystem: csi + help: Container Storage Interface operation duration with gRPC error code status + total + type: Histogram + stabilityLevel: ALPHA + labels: + - driver_name + - grpc_status_code + - method_name + - migrated + buckets: + - 0.1 + - 0.25 + - 0.5 + - 1 + - 2.5 + - 5 + - 10 + - 15 + - 25 + - 50 + - 120 + - 300 + - 600 - name: graph_actions_duration_seconds subsystem: node_authorizer help: Histogram of duration of graph actions in node authorizer. @@ -2525,6 +2787,86 @@ - 0.0512 - 0.1024 - 0.2048 +- name: storage_operation_duration_seconds + help: Storage operation duration + type: Histogram + stabilityLevel: ALPHA + labels: + - migrated + - operation_name + - status + - volume_plugin + buckets: + - 0.1 + - 0.25 + - 0.5 + - 1 + - 2.5 + - 5 + - 10 + - 15 + - 25 + - 50 + - 120 + - 300 + - 600 +- name: volume_operation_total_seconds + help: Storage operation end to end duration in seconds + type: Histogram + stabilityLevel: ALPHA + labels: + - operation_name + - plugin_name + buckets: + - 0.1 + - 0.25 + - 0.5 + - 1 + - 2.5 + - 5 + - 10 + - 15 + - 25 + - 50 + - 120 + - 300 + - 600 +- 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: apiextensions_openapi_v2_regeneration_count + help: Counter of OpenAPI v2 spec regeneration count broken down by causing CRD name + and reason. + type: Counter + stabilityLevel: ALPHA + labels: + - crd + - reason +- name: apiextensions_openapi_v3_regeneration_count + help: Counter of OpenAPI v3 spec regeneration count broken down by group, version, + causing CRD and reason. + type: Counter + stabilityLevel: ALPHA + labels: + - crd + - group + - reason + - version - name: conversion_webhook_duration_seconds namespace: apiserver help: Conversion webhook request latency @@ -2583,42 +2925,6 @@ - 4.096 - 8.192 - 16.384 -- 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: apiextensions_openapi_v2_regeneration_count - help: Counter of OpenAPI v2 spec regeneration count broken down by causing CRD name - and reason. - type: Counter - stabilityLevel: ALPHA - labels: - - crd - - reason -- name: apiextensions_openapi_v3_regeneration_count - help: Counter of OpenAPI v3 spec regeneration count broken down by group, version, - causing CRD and reason. - type: Counter - stabilityLevel: ALPHA - labels: - - crd - - group - - reason - - version - name: match_condition_evaluation_errors_total subsystem: admission namespace: apiserver @@ -2683,7 +2989,7 @@ subsystem: admission namespace: apiserver help: Admission webhook fail open count, identified by name and broken out for each - admission type (validating or mutating). + admission type (validating or admit). type: Counter stabilityLevel: ALPHA labels: @@ -2711,7 +3017,7 @@ subsystem: admission namespace: apiserver help: Admission webhook request total, identified by name and broken out for each - admission type (validating or mutating) and operation. Additional labels specify + admission type (validating or admit) and operation. Additional labels specify whether the request was rejected or not and an HTTP status code. Codes greater than 600 are truncated to 600, to keep the metrics cardinality bounded. type: Counter @@ -2726,15 +3032,14 @@ subsystem: validating_admission_policy namespace: apiserver help: Validation admission latency for individual validation expressions in seconds, - labeled by policy and further including binding, state and enforcement action - taken. + labeled by policy and further including binding and enforcement action taken. type: Histogram - stabilityLevel: ALPHA + stabilityLevel: BETA labels: - enforcement_action + - error_type - policy - policy_binding - - state buckets: - 5e-07 - 0.001 @@ -2745,24 +3050,14 @@ subsystem: validating_admission_policy namespace: apiserver help: Validation admission policy check total, labeled by policy and further identified - by binding, enforcement action taken, and state. + by binding and enforcement action taken. type: Counter - stabilityLevel: ALPHA + stabilityLevel: BETA labels: - enforcement_action + - error_type - policy - policy_binding - - state -- 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: controller_admission_duration_seconds subsystem: admission namespace: apiserver @@ -2821,10 +3116,6 @@ - 2.5 - 10 - 25 -- name: aggregator_discovery_aggregation_count_total - help: Counter of number of times discovery was aggregated - type: Counter - stabilityLevel: ALPHA - name: error_total subsystem: apiserver_audit help: Counter of audit events that failed to be audited properly. Plugin identifies @@ -2899,18 +3190,6 @@ labels: - name - type -- name: compilation_duration_seconds - subsystem: cel - namespace: apiserver - help: CEL compilation time in seconds. - type: Histogram - stabilityLevel: ALPHA -- name: evaluation_duration_seconds - subsystem: cel - namespace: apiserver - help: CEL evaluation time in seconds. - type: Histogram - stabilityLevel: ALPHA - name: certificate_expiration_seconds subsystem: client namespace: apiserver @@ -2933,14 +3212,6 @@ - 7.776e+06 - 1.5552e+07 - 3.1104e+07 -- name: current_inqueue_requests - subsystem: apiserver - help: Maximal number of queued requests in this apiserver per request kind in last - second. - type: Gauge - stabilityLevel: ALPHA - labels: - - request_kind - name: apiserver_delegated_authn_request_duration_seconds help: Request latency in seconds. Broken down by status code. type: Histogram @@ -2983,6 +3254,177 @@ stabilityLevel: ALPHA labels: - code +- name: active_fetch_count + subsystem: token_cache + namespace: authentication + type: Gauge + stabilityLevel: ALPHA + labels: + - status +- name: fetch_total + subsystem: token_cache + namespace: authentication + type: Counter + stabilityLevel: ALPHA + labels: + - status +- name: request_duration_seconds + subsystem: token_cache + namespace: authentication + type: Histogram + stabilityLevel: ALPHA + labels: + - status +- name: request_total + subsystem: token_cache + namespace: authentication + type: Counter + stabilityLevel: ALPHA + labels: + - status +- name: compilation_duration_seconds + subsystem: cel + namespace: apiserver + help: CEL compilation time in seconds. + type: Histogram + stabilityLevel: BETA +- name: evaluation_duration_seconds + subsystem: cel + namespace: apiserver + help: CEL evaluation time in seconds. + type: Histogram + stabilityLevel: BETA +- name: aggregator_discovery_aggregation_count_total + help: Counter of number of times discovery was aggregated + type: Counter + stabilityLevel: ALPHA +- name: automatic_reload_last_timestamp_seconds + subsystem: authentication_config_controller + namespace: apiserver + help: Timestamp of the last automatic reload of authentication configuration split + by status and apiserver identity. + type: Gauge + stabilityLevel: ALPHA + labels: + - apiserver_id_hash + - status +- name: automatic_reloads_total + subsystem: authentication_config_controller + namespace: apiserver + help: Total number of automatic reloads of authentication configuration split by + status and apiserver identity. + type: Counter + stabilityLevel: ALPHA + labels: + - apiserver_id_hash + - status +- name: automatic_reload_last_timestamp_seconds + subsystem: authorization_config_controller + namespace: apiserver + help: Timestamp of the last automatic reload of authorization configuration split + by status and apiserver identity. + type: Gauge + stabilityLevel: ALPHA + labels: + - apiserver_id_hash + - status +- name: automatic_reloads_total + subsystem: authorization_config_controller + namespace: apiserver + help: Total number of automatic reloads of authorization configuration split by + status and apiserver identity. + type: Counter + stabilityLevel: ALPHA + labels: + - apiserver_id_hash + - status +- name: current_inqueue_requests + subsystem: apiserver + help: Maximal number of queued requests in this apiserver per request kind in last + second. + type: Gauge + stabilityLevel: ALPHA + labels: + - request_kind +- name: dial_duration_seconds + subsystem: egress_dialer + namespace: apiserver + help: Dial latency histogram in seconds, labeled by the protocol (http-connect or + grpc), transport (tcp or uds) + type: Histogram + stabilityLevel: ALPHA + labels: + - protocol + - transport + buckets: + - 0.005 + - 0.025 + - 0.1 + - 0.5 + - 2.5 + - 12.5 +- name: dial_failure_count + subsystem: egress_dialer + namespace: apiserver + help: Dial failure count, labeled by the protocol (http-connect or grpc), transport + (tcp or uds), and stage (connect or proxy). The stage indicates at which stage + the dial failed + type: Counter + stabilityLevel: ALPHA + labels: + - protocol + - stage + - transport +- name: dial_start_total + subsystem: egress_dialer + namespace: apiserver + help: Dial starts, labeled by the protocol (http-connect or grpc) and transport + (tcp or uds). + type: Counter + stabilityLevel: ALPHA + labels: + - protocol + - transport +- name: automatic_reload_failures_total + subsystem: encryption_config_controller + namespace: apiserver + help: Total number of failed automatic reloads of encryption configuration split + by apiserver identity. + type: Counter + deprecatedVersion: 1.30.0 + stabilityLevel: ALPHA + labels: + - apiserver_id_hash +- name: automatic_reload_last_timestamp_seconds + subsystem: encryption_config_controller + namespace: apiserver + help: Timestamp of the last successful or failed automatic reload of encryption + configuration split by apiserver identity. + type: Gauge + stabilityLevel: ALPHA + labels: + - apiserver_id_hash + - status +- name: automatic_reload_success_total + subsystem: encryption_config_controller + namespace: apiserver + help: Total number of successful automatic reloads of encryption configuration split + by apiserver identity. + type: Counter + deprecatedVersion: 1.30.0 + stabilityLevel: ALPHA + labels: + - apiserver_id_hash +- name: automatic_reloads_total + subsystem: encryption_config_controller + namespace: apiserver + help: Total number of reload successes and failures of encryption configuration + split by apiserver identity. + type: Counter + stabilityLevel: ALPHA + labels: + - apiserver_id_hash + - status - name: request_aborts_total subsystem: apiserver help: Number of requests which apiserver aborted possibly due to a timeout, for @@ -3278,34 +3720,6 @@ - 4.096 - 8.192 - 16.384 -- name: active_fetch_count - subsystem: token_cache - namespace: authentication - type: Gauge - stabilityLevel: ALPHA - labels: - - status -- name: fetch_total - subsystem: token_cache - namespace: authentication - type: Counter - stabilityLevel: ALPHA - labels: - - status -- name: request_duration_seconds - subsystem: token_cache - namespace: authentication - type: Histogram - stabilityLevel: ALPHA - labels: - - status -- name: request_total - subsystem: token_cache - namespace: authentication - type: Counter - stabilityLevel: ALPHA - labels: - - status - name: authorization_attempts_total help: Counter of authorization attempts broken down by result. It can be either 'allowed', 'denied', 'no-opinion' or 'error'. @@ -3474,46 +3888,69 @@ - 1e+07 - 1e+08 - 1e+09 -- name: automatic_reload_last_timestamp_seconds - subsystem: authentication_config_controller +- name: jwt_authenticator_latency_seconds + subsystem: authentication namespace: apiserver - help: Timestamp of the last automatic reload of authentication configuration split - by status and apiserver identity. - type: Gauge + help: Latency of jwt authentication operations in seconds. This is the time spent + authenticating a token for cache miss only (i.e. when the token is not found in + the cache). + type: Histogram stabilityLevel: ALPHA labels: - - apiserver_id_hash - - status -- name: automatic_reloads_total - subsystem: authentication_config_controller + - jwt_issuer_hash + - result + buckets: + - 0.001 + - 0.005 + - 0.01 + - 0.025 + - 0.05 + - 0.1 + - 0.25 + - 0.5 + - 1 + - 2.5 + - 5 + - 10 +- name: webhook_duration_seconds + subsystem: authorization namespace: apiserver - help: Total number of automatic reloads of authentication configuration split by - status and apiserver identity. + help: Request latency in seconds. + type: Histogram + stabilityLevel: ALPHA + labels: + - name + - result + buckets: + - 0.005 + - 0.01 + - 0.025 + - 0.05 + - 0.1 + - 0.25 + - 0.5 + - 1 + - 2.5 + - 5 + - 10 +- name: webhook_evaluations_fail_open_total + subsystem: authorization + namespace: apiserver + help: NoOpinion results due to webhook timeout or error. type: Counter stabilityLevel: ALPHA labels: - - apiserver_id_hash - - status -- name: automatic_reload_last_timestamp_seconds - subsystem: authorization_config_controller + - name + - result +- name: webhook_evaluations_total + subsystem: authorization namespace: apiserver - help: Timestamp of the last automatic reload of authorization configuration split - by status and apiserver identity. - type: Gauge - stabilityLevel: ALPHA - labels: - - apiserver_id_hash - - status -- name: automatic_reloads_total - subsystem: authorization_config_controller - namespace: apiserver - help: Total number of automatic reloads of authorization configuration split by - status and apiserver identity. + help: Round-trips to authorization webhooks. type: Counter stabilityLevel: ALPHA labels: - - apiserver_id_hash - - status + - name + - result - name: cache_list_fetched_objects_total namespace: apiserver help: Number of objects read from watch cache in the course of serving a LIST request @@ -3537,85 +3974,6 @@ labels: - index - resource_prefix -- name: dial_duration_seconds - subsystem: egress_dialer - namespace: apiserver - help: Dial latency histogram in seconds, labeled by the protocol (http-connect or - grpc), transport (tcp or uds) - type: Histogram - stabilityLevel: ALPHA - labels: - - protocol - - transport - buckets: - - 0.005 - - 0.025 - - 0.1 - - 0.5 - - 2.5 - - 12.5 -- name: dial_failure_count - subsystem: egress_dialer - namespace: apiserver - help: Dial failure count, labeled by the protocol (http-connect or grpc), transport - (tcp or uds), and stage (connect or proxy). The stage indicates at which stage - the dial failed - type: Counter - stabilityLevel: ALPHA - labels: - - protocol - - stage - - transport -- name: dial_start_total - subsystem: egress_dialer - namespace: apiserver - help: Dial starts, labeled by the protocol (http-connect or grpc) and transport - (tcp or uds). - type: Counter - stabilityLevel: ALPHA - labels: - - protocol - - transport -- name: automatic_reload_failures_total - subsystem: encryption_config_controller - namespace: apiserver - help: Total number of failed automatic reloads of encryption configuration split - by apiserver identity. - type: Counter - deprecatedVersion: 1.30.0 - stabilityLevel: ALPHA - labels: - - apiserver_id_hash -- name: automatic_reload_last_timestamp_seconds - subsystem: encryption_config_controller - namespace: apiserver - help: Timestamp of the last successful or failed automatic reload of encryption - configuration split by apiserver identity. - type: Gauge - stabilityLevel: ALPHA - labels: - - apiserver_id_hash - - status -- name: automatic_reload_success_total - subsystem: encryption_config_controller - namespace: apiserver - help: Total number of successful automatic reloads of encryption configuration split - by apiserver identity. - type: Counter - deprecatedVersion: 1.30.0 - stabilityLevel: ALPHA - labels: - - apiserver_id_hash -- name: automatic_reloads_total - subsystem: encryption_config_controller - namespace: apiserver - help: Total number of reload successes and failures of encryption configuration - split by apiserver identity. - type: Counter - stabilityLevel: ALPHA - labels: - - apiserver_id_hash - - status - name: dek_cache_fill_percent subsystem: envelope_encryption namespace: apiserver @@ -4068,6 +4426,14 @@ stabilityLevel: ALPHA labels: - resource +- name: rerouted_request_total + subsystem: apiserver + help: Total number of requests that were proxied to a peer kube apiserver because + the local apiserver was not capable of serving it + type: Counter + stabilityLevel: ALPHA + labels: + - code - name: data_key_generation_duration_seconds subsystem: storage namespace: apiserver @@ -4186,15 +4552,35 @@ subsystem: storage namespace: apiserver help: Total number of transformations. Successful transformation will have a status - 'OK' and a varied status string when the transformation fails. This status and - transformation_type fields may be used for alerting on encryption/decryption failure - using transformation_type from_storage for decryption and to_storage for encryption + 'OK' and a varied status string when the transformation fails. The status, resource, + and transformation_type fields can be used for alerting purposes. For example, + you can monitor for encryption/decryption failures using the transformation_type + (e.g., from_storage for decryption and to_storage for encryption). Additionally, + these fields can be used to ensure that the correct transformers are applied to + each resource. type: Counter stabilityLevel: ALPHA labels: + - resource - status - transformation_type - transformer_prefix +- name: stream_translator_requests_total + subsystem: apiserver + help: Total number of requests that were handled by the StreamTranslatorProxy, which + processes streaming RemoteCommand/V5 + type: Counter + stabilityLevel: ALPHA + labels: + - code +- name: stream_tunnel_requests_total + subsystem: apiserver + help: Total number of requests that were handled by the StreamTunnelProxy, which + processes streaming PortForward/V2 + type: Counter + stabilityLevel: ALPHA + labels: + - code - name: terminated_watchers_total namespace: apiserver help: Counter of watchers closed due to unresponsiveness broken by resource type. @@ -4202,6 +4588,16 @@ stabilityLevel: ALPHA labels: - resource +- name: consistent_read_total + subsystem: watch_cache + namespace: apiserver + help: Counter for consistent reads from cache. + type: Counter + stabilityLevel: ALPHA + labels: + - fallback + - resource + - success - name: events_dispatched_total subsystem: watch_cache namespace: apiserver @@ -4256,6 +4652,22 @@ stabilityLevel: ALPHA labels: - resource +- name: x509_insecure_sha1_total + subsystem: webhooks + 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: webhooks + 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: etcd_bookmark_counts help: Number of etcd bookmarks (progress notify events) split by kind. type: Gauge @@ -4435,101 +4847,6 @@ stabilityLevel: STABLE labels: - storage_cluster_id -- name: jwt_authenticator_latency_seconds - subsystem: authentication - namespace: apiserver - help: Latency of jwt authentication operations in seconds. This is the time spent - authenticating a token for cache miss only (i.e. when the token is not found in - the cache). - type: Histogram - stabilityLevel: ALPHA - labels: - - jwt_issuer_hash - - result - buckets: - - 0.001 - - 0.005 - - 0.01 - - 0.025 - - 0.05 - - 0.1 - - 0.25 - - 0.5 - - 1 - - 2.5 - - 5 - - 10 -- name: webhook_duration_seconds - subsystem: authorization - namespace: apiserver - help: Request latency in seconds. - type: Histogram - stabilityLevel: ALPHA - labels: - - name - - result - buckets: - - 0.005 - - 0.01 - - 0.025 - - 0.05 - - 0.1 - - 0.25 - - 0.5 - - 1 - - 2.5 - - 5 - - 10 -- name: webhook_evaluations_fail_open_total - subsystem: authorization - namespace: apiserver - help: NoOpinion results due to webhook timeout or error. - type: Counter - stabilityLevel: ALPHA - labels: - - name - - result -- name: webhook_evaluations_total - subsystem: authorization - namespace: apiserver - help: Round-trips to authorization webhooks. - type: Counter - stabilityLevel: ALPHA - labels: - - name - - result -- name: rerouted_request_total - subsystem: apiserver - help: Total number of requests that were proxied to a peer kube apiserver because - the local apiserver was not capable of serving it - type: Counter - stabilityLevel: ALPHA - labels: - - code -- name: stream_translator_requests_total - subsystem: apiserver - help: Total number of requests that were handled by the StreamTranslatorProxy, which - processes streaming RemoteCommand/V5 - type: Counter - stabilityLevel: ALPHA - labels: - - code -- name: x509_insecure_sha1_total - subsystem: webhooks - 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: webhooks - 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: request_duration_seconds subsystem: cloud_provider_webhook help: Request latency in seconds. Broken down by status code. @@ -4636,6 +4953,92 @@ - 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 + - traffic_distribution +- name: num_endpoint_slices + subsystem: endpoint_slice_controller + help: Number of EndpointSlices + type: Gauge + stabilityLevel: ALPHA +- name: services_count_by_traffic_distribution + subsystem: endpoint_slice_controller + help: Number of Services using some specific trafficDistribution + type: Gauge + stabilityLevel: ALPHA + labels: + - traffic_distribution +- 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 @@ -4992,92 +5395,6 @@ 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 - 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 - - traffic_distribution -- name: num_endpoint_slices - subsystem: endpoint_slice_controller - help: Number of EndpointSlices - type: Gauge - stabilityLevel: ALPHA -- name: services_count_by_traffic_distribution - subsystem: endpoint_slice_controller - help: Number of Services using some specific trafficDistribution - type: Gauge - stabilityLevel: ALPHA - labels: - - traffic_distribution -- name: syncs - subsystem: endpoint_slice_controller - help: Number of EndpointSlice syncs - type: Counter - stabilityLevel: ALPHA - labels: - - result - name: pod_security_errors_total help: Number of errors preventing normal evaluation. Non-fatal errors may result in the latest restricted profile being used for evaluation. diff --git a/test/instrumentation/documentation/documentation.md b/test/instrumentation/documentation/documentation.md index 1abb15733cf..bb64782fa53 100644 --- a/test/instrumentation/documentation/documentation.md +++ b/test/instrumentation/documentation/documentation.md @@ -6,10 +6,10 @@ description: >- Details of the metric data that Kubernetes components export. --- -## Metrics (v1.31) +## Metrics (v1.32) - - + + 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 current metrics data in Prometheus format. @@ -291,6 +291,20 @@ Stable metrics observe strict API contracts and no labels can be added or remove Beta metrics observe a looser API contract than its stable counterparts. No labels can be removed from beta metrics during their lifetime, however, labels can be added while the metric is in the beta stage. This offers the assurance that beta metrics will honor existing dashboards and alerts, while allowing for amendments in the future.
+
apiserver_cel_compilation_duration_seconds
+
CEL compilation time in seconds.
+ +
+
apiserver_cel_evaluation_duration_seconds
+
CEL evaluation time in seconds.
+ +
apiserver_flowcontrol_current_executing_requests
Number of requests in initial (for a WATCH) or any (for a non-WATCH) execution stage in the API Priority and Fairness subsystem
+
apiserver_validating_admission_policy_check_duration_seconds
+
Validation admission latency for individual validation expressions in seconds, labeled by policy and further including binding and enforcement action taken.
+ +
+
apiserver_validating_admission_policy_check_total
+
Validation admission policy check total, labeled by policy and further identified by binding and enforcement action taken.
+ +
disabled_metrics_total
The count of disabled metrics.
apiserver_admission_webhook_fail_open_count
-
Admission webhook fail open count, identified by name and broken out for each admission type (validating or mutating).
+
Admission webhook fail open count, identified by name and broken out for each admission type (validating or admit).
apiserver_admission_webhook_request_total
-
Admission webhook request total, identified by name and broken out for each admission type (validating or mutating) and operation. Additional labels specify whether the request was rejected or not and an HTTP status code. Codes greater than 600 are truncated to 600, to keep the metrics cardinality bounded.
+
Admission webhook request total, identified by name and broken out for each admission type (validating or admit) and operation. Additional labels specify whether the request was rejected or not and an HTTP status code. Codes greater than 600 are truncated to 600, to keep the metrics cardinality bounded.
-
apiserver_cel_compilation_duration_seconds
-
CEL compilation time in seconds.
- -
-
apiserver_cel_evaluation_duration_seconds
-
CEL evaluation time in seconds.
- -
apiserver_certificates_registry_csr_honored_duration_total
Total number of issued CSRs with a requested duration that was honored, sliced by signer (only kubernetes.io signer names are specifically identified)
+
apiserver_externaljwt_fetch_keys_data_timestamp
+
Unix Timestamp in seconds of the last successful FetchKeys data_timestamp value returned by the external signer
+ +
+
apiserver_externaljwt_fetch_keys_request_total
+
Total attempts at syncing supported JWKs
+ +
+
apiserver_externaljwt_fetch_keys_success_timestamp
+
Unix Timestamp in seconds of the last successful FetchKeys request
+ +
+
apiserver_externaljwt_request_duration_seconds
+
Request duration and time for calls to external-jwt-signer
+ +
+
apiserver_externaljwt_sign_request_total
+
Total attempts at signing JWT
+ +
apiserver_flowcontrol_current_inqueue_seats
Number of seats currently pending in queues of the API Priority and Fairness subsystem
apiserver_storage_transformation_operations_total
-
Total number of transformations. Successful transformation will have a status 'OK' and a varied status string when the transformation fails. This status and transformation_type fields may be used for alerting on encryption/decryption failure using transformation_type from_storage for decryption and to_storage for encryption
+
Total number of transformations. Successful transformation will have a status 'OK' and a varied status string when the transformation fails. The status, resource, and transformation_type fields can be used for alerting purposes. For example, you can monitor for encryption/decryption failures using the transformation_type (e.g., from_storage for decryption and to_storage for encryption). Additionally, these fields can be used to ensure that the correct transformers are applied to each resource.
+
  • resourcestatustransformation_typetransformer_prefix
    • apiserver_stream_translator_requests_total
    Total number of requests that were handled by the StreamTranslatorProxy, which processes streaming RemoteCommand/V5
    @@ -1215,6 +1264,13 @@ Alpha metrics do not have any API guarantees. These metrics must be used at your
  • Counter
  • code
    • +
    apiserver_stream_tunnel_requests_total
    +
    Total number of requests that were handled by the StreamTunnelProxy, which processes streaming PortForward/V2
    + +
    apiserver_terminated_watchers_total
    Counter of watchers closed due to unresponsiveness broken by resource type.
    -
    apiserver_validating_admission_policy_check_duration_seconds
    -
    Validation admission latency for individual validation expressions in seconds, labeled by policy and further including binding, state and enforcement action taken.
    - -
    -
    apiserver_validating_admission_policy_check_total
    -
    Validation admission policy check total, labeled by policy and further identified by binding, enforcement action taken, and state.
    +
    apiserver_watch_cache_consistent_read_total
    +
    Counter for consistent reads from cache.
    -
    -
    apiserver_validating_admission_policy_definition_total
    -
    Validation admission policy count total, labeled by state and enforcement action.
    - +
  • fallbackresourcesuccess
    • apiserver_watch_cache_events_dispatched_total
    Counter of events dispatched in watch cache broken by resource type.
    @@ -1411,6 +1453,20 @@ Alpha metrics do not have any API guarantees. These metrics must be used at your
  • Counter
  • codewebhook
    • +
    clustertrustbundle_publisher_sync_duration_seconds
    +
    The time it took to sync a cluster trust bundle.
    + +
    +
    clustertrustbundle_publisher_sync_total
    +
    Number of syncs that occurred in cluster trust bundle publisher.
    + +
    container_swap_usage_bytes
    Current amount of the container swap usage in bytes. Reported only on non-windows systems
    +
    dra_grpc_operations_duration_seconds
    +
    Duration in seconds of the DRA gRPC operations
    + +
    +
    dra_operations_duration_seconds
    +
    Latency histogram in seconds for the duration of handling all ResourceClaims referenced by a pod when the pod starts or stops. Identified by the name of the operation (PrepareResources or UnprepareResources) and separated by the success of the operation. The number of failed operations is provided through the histogram's overall count.
    + +
    endpoint_slice_controller_changes
    Number of EndpointSlice changes
    ephemeral_volume_controller_create_failures_total
    -
    Number of PersistenVolumeClaims creation requests
    +
    Number of PersistentVolumeClaim creation requests
    ephemeral_volume_controller_create_total
    -
    Number of PersistenVolumeClaims creation requests
    +
    Number of PersistentVolumeClaim creation requests
    +
    kube_apiserver_clusterip_allocator_allocation_duration_seconds
    +
    Duration in seconds to allocate a Cluster IP by ServiceCIDR
    + +
    kube_apiserver_clusterip_allocator_allocation_errors_total
    Number of errors trying to allocate Cluster IPs
    +
    kubelet_admission_rejections_total
    +
    Cumulative number pod admission rejections by the Kubelet.
    + +
    kubelet_certificate_manager_client_expiration_renew_errors
    Counter of certificate renewal errors.
    +
    kubelet_cgroup_version
    +
    cgroup version on the hosts.
    + +
    +
    kubelet_container_aligned_compute_resources_count
    +
    Cumulative number of aligned compute resources allocated to containers by alignment type.
    + +
    kubelet_container_log_filesystem_used_bytes
    Bytes used by the container's logs on the filesystem.
    +
    kubelet_cpu_manager_exclusive_cpu_allocation_count
    +
    The total number of CPUs exclusively allocated to containers running on this node
    + +
    kubelet_cpu_manager_pinning_errors_total
    The number of cpu core allocations which required pinning failed.
    +
    kubelet_cpu_manager_shared_pool_size_millicores
    +
    The size of the shared CPU pool for non-guaranteed QoS pods, in millicores.
    + +
    kubelet_credential_provider_plugin_duration
    Duration of execution in seconds for credential provider plugin
    kubelet_graceful_shutdown_end_time_seconds
    -
    Last graceful shutdown start time since unix epoch in seconds
    +
    Last graceful shutdown end time since unix epoch in seconds
    pv_collector_total_pv_count
    Gauge measuring total number of persistent volumes
    @@ -2753,7 +2865,7 @@ Alpha metrics do not have any API guarantees. These metrics must be used at your +
  • namespacestorage_classvolume_attributes_class
    • reconstruct_volume_operations_errors_total
    The number of volumes that failed reconstruction from the operating system during kubelet startup.
    @@ -2776,6 +2888,13 @@ Alpha metrics do not have any API guarantees. These metrics must be used at your
  • Histogram
    • +
    resourceclaim_controller_allocated_resource_claims
    +
    Number of allocated ResourceClaims
    + +
    resourceclaim_controller_create_attempts_total
    Number of ResourceClaims creation requests
    +
    resourceclaim_controller_resource_claims
    +
    Number of ResourceClaims
    + +
    rest_client_dns_resolution_duration_seconds
    DNS resolver latency in seconds. Broken down by host.
    +
    scheduler_event_handling_duration_seconds
    +
    Event handling latency in seconds.
    + +
    scheduler_goroutines
    Number of running goroutines split by the work they do such as binding.
    +
    scheduler_inflight_events
    +
    Number of events currently tracked in the scheduling queue.
    + +
    scheduler_permit_wait_duration_seconds
    Duration of waiting on permit.
    +
    scheduler_preemption_goroutines_duration_seconds
    +
    Duration in seconds for running goroutines for the preemption.
    + +
    +
    scheduler_preemption_goroutines_execution_total
    +
    Number of preemption goroutines executed.
    + +
    +
    scheduler_queueing_hint_execution_duration_seconds
    +
    Duration for running a queueing hint function of a plugin.
    + +
    scheduler_scheduler_cache_size
    Number of nodes, pods, and assumed (bound) pods in the scheduler cache.
    +
    selinux_warning_controller_selinux_volume_conflict
    +
    Conflict between two Pods using the same volume
    + +
    service_controller_loadbalancer_sync_total
    A metric counting the amount of times any load balancer has been configured, as an effect of service/node changes on the cluster