Merge pull request #102 from frezes/feat/kube-prometheus-stack

[kube-prometheus-stack] update values

Author: benjaminhuo

charts/kube-prometheus-stack/Chart.yaml

@@ -31,7 +31,7 @@ name: kube-prometheus-stack
 sources:
   - https://github.com/prometheus-community/helm-charts
   - https://github.com/prometheus-operator/kube-prometheus
-version: 70.5.0
+version: 70.5.1
 appVersion: v0.81.0
 kubeVersion: ">=1.19.0-0"
 home: https://github.com/prometheus-operator/kube-prometheus

charts/kube-prometheus-stack/values.yaml

@@ -1501,7 +1501,7 @@ kubeApiServer:
     metricRelabelings:
       # Drop excessively noisy apiserver buckets.
       - action: drop
-        regex: (etcd_request|apiserver_request_slo|apiserver_request_sli|apiserver_request)_duration_seconds_bucket;(0\.15|0\.2|0\.3|0\.35|0\.4|0\.45|0\.6|0\.7|0\.8|0\.9|1\.25|1\.5|1\.75|2|3|3\.5|4|4\.5|6|7|8|9|15|20|30|40|45|50)(\.0)?
+        regex: (etcd_request|apiserver_request_slo|apiserver_request_sli|apiserver_request)_duration_seconds_bucket;(0\.15|0\.2|0\.3|0\.35|0\.4|0\.45|0\.6|0\.7|0\.8|0\.9|1\.25|1\.5|1\.75|2|3|3\.5|4|4\.5|6|7|8|9|15|20|40|45|50)(\.0)?
         sourceLabels:
           - __name__
           - le
@@ -1557,8 +1557,8 @@ kubeApiServer:
       - action: drop
         regex: apiserver_request_body_size_bytes_bucket;(150000|350000|550000|650000|850000|950000|(1\.15|1\.35|1\.55|1\.65|1\.85|1\.95|2\.15|2\.35|2\.55|2\.65|2\.85|2\.95)e\+06)
         sourceLabels:
-          - __name__
-          - le
+        - __name__
+        - le
     # - action: keep
     #   regex: 'kube_(daemonset|deployment|pod|namespace|node|statefulset).+'
     #   sourceLabels: [__name__]
@@ -1714,6 +1714,21 @@ kubelet:
       - sourceLabels: [id, pod]
         action: drop
         regex: '.+;'
+      - action: drop
+        regex: container_(network_tcp_usage_total|network_udp_usage_total|tasks_state|cpu_load_average_10s)
+        sourceLabels:
+        - __name__
+      - action: drop
+        regex: (container_spec_.*|container_file_descriptors|container_sockets|container_threads_max|container_threads|container_start_time_seconds|container_last_seen);;
+        sourceLabels:
+        - __name__
+        - pod
+        - namespace
+      - action: drop
+        regex: (container_blkio_device_usage_total);.+
+        sourceLabels:
+        - __name__
+        - container
       - sourceLabels: [__name__]
         action: keep
         regex: container_cpu_cfs_.*periods_total|container_cpu_usage_seconds_total|container_fs_(limit|usage)_bytes|container_fs_(reads|writes)_bytes_total|container_fs_(reads|writes)_total|container_memory_(cache|mapped_file|rss|usage_bytes|working_set_bytes)|container_network_(receive|transmit)_(bytes|packets|packets_dropped)_total|container_processes.*|container_threads.*
@@ -1796,8 +1811,40 @@ kubelet:
       - action: drop
         sourceLabels: [__name__, le]
         regex: (csi_operations|storage_operation_duration)_seconds_bucket;(0.25|2.5|15|25|120|600)(\.0)?
+      - action: drop
+        regex: kubelet_(pod_worker_latency_microseconds|pod_start_latency_microseconds|cgroup_manager_latency_microseconds|pod_worker_start_latency_microseconds|pleg_relist_latency_microseconds|pleg_relist_interval_microseconds|runtime_operations|runtime_operations_latency_microseconds|runtime_operations_errors|eviction_stats_age_microseconds|device_plugin_registration_count|device_plugin_alloc_latency_microseconds|network_plugin_operations_latency_microseconds)
+        sourceLabels:
+        - __name__
+      - action: drop
+        regex: scheduler_(e2e_scheduling_latency_microseconds|scheduling_algorithm_predicate_evaluation|scheduling_algorithm_priority_evaluation|scheduling_algorithm_preemption_evaluation|scheduling_algorithm_latency_microseconds|binding_latency_microseconds|scheduling_latency_seconds)
+        sourceLabels:
+        - __name__
+      - action: drop
+        regex: apiserver_(request_count|request_latencies|request_latencies_summary|dropped_requests|storage_data_key_generation_latencies_microseconds|storage_transformation_failures_total|storage_transformation_latencies_microseconds|proxy_tunnel_sync_latency_secs|longrunning_gauge|registered_watchers|storage_db_total_size_in_bytes|flowcontrol_request_concurrency_limit|flowcontrol_request_concurrency_in_use)
+        sourceLabels:
+        - __name__
+      - action: drop
+        regex: kubelet_docker_(operations|operations_latency_microseconds|operations_errors|operations_timeout)
+        sourceLabels:
+        - __name__
+      - action: drop
+        regex: reflector_(items_per_list|items_per_watch|list_duration_seconds|lists_total|short_watches_total|watch_duration_seconds|watches_total)
+        sourceLabels:
+        - __name__
+      - action: drop
+        regex: etcd_(helper_cache_hit_count|helper_cache_miss_count|helper_cache_entry_count|object_counts|request_cache_get_latencies_summary|request_cache_add_latencies_summary|request_latencies_summary)
+        sourceLabels:
+        - __name__
+      - action: drop
+        regex: transformation_(transformation_latencies_microseconds|failures_total)
+        sourceLabels:
+        - __name__
+      - action: drop
+        regex: (admission_quota_controller_adds|admission_quota_controller_depth|admission_quota_controller_longest_running_processor_microseconds|admission_quota_controller_queue_latency|admission_quota_controller_unfinished_work_seconds|admission_quota_controller_work_duration|APIServiceOpenAPIAggregationControllerQueue1_adds|APIServiceOpenAPIAggregationControllerQueue1_depth|APIServiceOpenAPIAggregationControllerQueue1_longest_running_processor_microseconds|APIServiceOpenAPIAggregationControllerQueue1_queue_latency|APIServiceOpenAPIAggregationControllerQueue1_retries|APIServiceOpenAPIAggregationControllerQueue1_unfinished_work_seconds|APIServiceOpenAPIAggregationControllerQueue1_work_duration|APIServiceRegistrationController_adds|APIServiceRegistrationController_depth|APIServiceRegistrationController_longest_running_processor_microseconds|APIServiceRegistrationController_queue_latency|APIServiceRegistrationController_retries|APIServiceRegistrationController_unfinished_work_seconds|APIServiceRegistrationController_work_duration|autoregister_adds|autoregister_depth|autoregister_longest_running_processor_microseconds|autoregister_queue_latency|autoregister_retries|autoregister_unfinished_work_seconds|autoregister_work_duration|AvailableConditionController_adds|AvailableConditionController_depth|AvailableConditionController_longest_running_processor_microseconds|AvailableConditionController_queue_latency|AvailableConditionController_retries|AvailableConditionController_unfinished_work_seconds|AvailableConditionController_work_duration|crd_autoregistration_controller_adds|crd_autoregistration_controller_depth|crd_autoregistration_controller_longest_running_processor_microseconds|crd_autoregistration_controller_queue_latency|crd_autoregistration_controller_retries|crd_autoregistration_controller_unfinished_work_seconds|crd_autoregistration_controller_work_duration|crdEstablishing_adds|crdEstablishing_depth|crdEstablishing_longest_running_processor_microseconds|crdEstablishing_queue_latency|crdEstablishing_retries|crdEstablishing_unfinished_work_seconds|crdEstablishing_work_duration|crd_finalizer_adds|crd_finalizer_depth|crd_finalizer_longest_running_processor_microseconds|crd_finalizer_queue_latency|crd_finalizer_retries|crd_finalizer_unfinished_work_seconds|crd_finalizer_work_duration|crd_naming_condition_controller_adds|crd_naming_condition_controller_depth|crd_naming_condition_controller_longest_running_processor_microseconds|crd_naming_condition_controller_queue_latency|crd_naming_condition_controller_retries|crd_naming_condition_controller_unfinished_work_seconds|crd_naming_condition_controller_work_duration|crd_openapi_controller_adds|crd_openapi_controller_depth|crd_openapi_controller_longest_running_processor_microseconds|crd_openapi_controller_queue_latency|crd_openapi_controller_retries|crd_openapi_controller_unfinished_work_seconds|crd_openapi_controller_work_duration|DiscoveryController_adds|DiscoveryController_depth|DiscoveryController_longest_running_processor_microseconds|DiscoveryController_queue_latency|DiscoveryController_retries|DiscoveryController_unfinished_work_seconds|DiscoveryController_work_duration|kubeproxy_sync_proxy_rules_latency_microseconds|non_structural_schema_condition_controller_adds|non_structural_schema_condition_controller_depth|non_structural_schema_condition_controller_longest_running_processor_microseconds|non_structural_schema_condition_controller_queue_latency|non_structural_schema_condition_controller_retries|non_structural_schema_condition_controller_unfinished_work_seconds|non_structural_schema_condition_controller_work_duration|rest_client_request_latency_seconds|storage_operation_errors_total|storage_operation_status_count)
+        sourceLabels:
+        - __name__
       - action: keep
-        regex: kubelet_node_name|kubelet_running_container_count|kubelet_running_pod_count|kubelet_volume_stats.*|kubelet_pleg_relist_duration_seconds_.+|kubelet_certificate_manager_.+|kubelet_server_expiration_.+|kubelet_pod_worker_.+
+        regex: kubelet_node_name|kubelet_running_container_count|kubelet_running_pod_count|kubelet_volume_stats.*|kubelet_pleg_relist_duration_seconds_.+|kubelet_certificate_manager_.+|kubelet_server_expiration_.+|kubelet_pod_worker_.+|kubelet_runtime_operations_.+|storage_operation_.+
         sourceLabels:
           - __name__
     # - sourceLabels: [__name__, image]
@@ -1920,6 +1967,42 @@ kubeControllerManager:
     ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/api-reference/api.md#relabelconfig
     ##
     metricRelabelings:
+      - action: drop
+        regex: kubelet_(pod_worker_latency_microseconds|pod_start_latency_microseconds|cgroup_manager_latency_microseconds|pod_worker_start_latency_microseconds|pleg_relist_latency_microseconds|pleg_relist_interval_microseconds|runtime_operations|runtime_operations_latency_microseconds|runtime_operations_errors|eviction_stats_age_microseconds|device_plugin_registration_count|device_plugin_alloc_latency_microseconds|network_plugin_operations_latency_microseconds)
+        sourceLabels:
+        - __name__
+      - action: drop
+        regex: scheduler_(e2e_scheduling_latency_microseconds|scheduling_algorithm_predicate_evaluation|scheduling_algorithm_priority_evaluation|scheduling_algorithm_preemption_evaluation|scheduling_algorithm_latency_microseconds|binding_latency_microseconds|scheduling_latency_seconds)
+        sourceLabels:
+        - __name__
+      - action: drop
+        regex: apiserver_(request_count|request_latencies|request_latencies_summary|dropped_requests|storage_data_key_generation_latencies_microseconds|storage_transformation_failures_total|storage_transformation_latencies_microseconds|proxy_tunnel_sync_latency_secs|longrunning_gauge|registered_watchers|storage_db_total_size_in_bytes|flowcontrol_request_concurrency_limit|flowcontrol_request_concurrency_in_use)
+        sourceLabels:
+        - __name__
+      - action: drop
+        regex: kubelet_docker_(operations|operations_latency_microseconds|operations_errors|operations_timeout)
+        sourceLabels:
+        - __name__
+      - action: drop
+        regex: reflector_(items_per_list|items_per_watch|list_duration_seconds|lists_total|short_watches_total|watch_duration_seconds|watches_total)
+        sourceLabels:
+        - __name__
+      - action: drop
+        regex: etcd_(helper_cache_hit_count|helper_cache_miss_count|helper_cache_entry_count|object_counts|request_cache_get_latencies_summary|request_cache_add_latencies_summary|request_latencies_summary)
+        sourceLabels:
+        - __name__
+      - action: drop
+        regex: transformation_(transformation_latencies_microseconds|failures_total)
+        sourceLabels:
+        - __name__
+      - action: drop
+        regex: (admission_quota_controller_adds|admission_quota_controller_depth|admission_quota_controller_longest_running_processor_microseconds|admission_quota_controller_queue_latency|admission_quota_controller_unfinished_work_seconds|admission_quota_controller_work_duration|APIServiceOpenAPIAggregationControllerQueue1_adds|APIServiceOpenAPIAggregationControllerQueue1_depth|APIServiceOpenAPIAggregationControllerQueue1_longest_running_processor_microseconds|APIServiceOpenAPIAggregationControllerQueue1_queue_latency|APIServiceOpenAPIAggregationControllerQueue1_retries|APIServiceOpenAPIAggregationControllerQueue1_unfinished_work_seconds|APIServiceOpenAPIAggregationControllerQueue1_work_duration|APIServiceRegistrationController_adds|APIServiceRegistrationController_depth|APIServiceRegistrationController_longest_running_processor_microseconds|APIServiceRegistrationController_queue_latency|APIServiceRegistrationController_retries|APIServiceRegistrationController_unfinished_work_seconds|APIServiceRegistrationController_work_duration|autoregister_adds|autoregister_depth|autoregister_longest_running_processor_microseconds|autoregister_queue_latency|autoregister_retries|autoregister_unfinished_work_seconds|autoregister_work_duration|AvailableConditionController_adds|AvailableConditionController_depth|AvailableConditionController_longest_running_processor_microseconds|AvailableConditionController_queue_latency|AvailableConditionController_retries|AvailableConditionController_unfinished_work_seconds|AvailableConditionController_work_duration|crd_autoregistration_controller_adds|crd_autoregistration_controller_depth|crd_autoregistration_controller_longest_running_processor_microseconds|crd_autoregistration_controller_queue_latency|crd_autoregistration_controller_retries|crd_autoregistration_controller_unfinished_work_seconds|crd_autoregistration_controller_work_duration|crdEstablishing_adds|crdEstablishing_depth|crdEstablishing_longest_running_processor_microseconds|crdEstablishing_queue_latency|crdEstablishing_retries|crdEstablishing_unfinished_work_seconds|crdEstablishing_work_duration|crd_finalizer_adds|crd_finalizer_depth|crd_finalizer_longest_running_processor_microseconds|crd_finalizer_queue_latency|crd_finalizer_retries|crd_finalizer_unfinished_work_seconds|crd_finalizer_work_duration|crd_naming_condition_controller_adds|crd_naming_condition_controller_depth|crd_naming_condition_controller_longest_running_processor_microseconds|crd_naming_condition_controller_queue_latency|crd_naming_condition_controller_retries|crd_naming_condition_controller_unfinished_work_seconds|crd_naming_condition_controller_work_duration|crd_openapi_controller_adds|crd_openapi_controller_depth|crd_openapi_controller_longest_running_processor_microseconds|crd_openapi_controller_queue_latency|crd_openapi_controller_retries|crd_openapi_controller_unfinished_work_seconds|crd_openapi_controller_work_duration|DiscoveryController_adds|DiscoveryController_depth|DiscoveryController_longest_running_processor_microseconds|DiscoveryController_queue_latency|DiscoveryController_retries|DiscoveryController_unfinished_work_seconds|DiscoveryController_work_duration|kubeproxy_sync_proxy_rules_latency_microseconds|non_structural_schema_condition_controller_adds|non_structural_schema_condition_controller_depth|non_structural_schema_condition_controller_longest_running_processor_microseconds|non_structural_schema_condition_controller_queue_latency|non_structural_schema_condition_controller_retries|non_structural_schema_condition_controller_unfinished_work_seconds|non_structural_schema_condition_controller_work_duration|rest_client_request_latency_seconds|storage_operation_errors_total|storage_operation_status_count)
+        sourceLabels:
+        - __name__
+      - action: drop
+        regex: etcd_(debugging|disk|request|server).*
+        sourceLabels:
+        - __name__
       - action: keep
         regex: up
         sourceLabels:
@@ -2491,6 +2574,7 @@ kube-state-metrics:
             metricNamePrefix: "kubesphere_cluster"
             labelsFromPath:
               kubesphere_cluster: [metadata, name]
+              cluster_kubesphere_io_group: [metadata, labels, cluster.kubesphere.io/group]
               provider: [spec, provider]
             metrics:
               - name: "info"
@@ -2501,15 +2585,16 @@ kube-state-metrics:
                     labelsFromPath:
                       kubesphere_version: [status, kubeSphereVersion]
                       kubernetes_version: [status, kubernetesVersion]
-                      cluster_kubesphere_io_group: [metadata, labels, cluster.kubesphere.io/group]
+                      alias_name: [metadata, annotations, kubesphere.io/alias-name]
+                      description: [metadata, annotations, kubesphere.io/description]
               - name: "created"
                 help: "created timestamp about cluster.kubesphere.io/cluster."
                 each:
                   type: Gauge
                   gauge:
                     path: [metadata, creationTimestamp]
               - name: "label_keys"
-                help: "role about cluster.kubesphere.io/cluster."
+                help: "lalel keys about cluster.kubesphere.io/cluster."
                 each:
                   type: Info
                   info:
@@ -2568,7 +2653,6 @@ kube-state-metrics:
                     labelsFromPath:
                       kubesphere_cluster: [name]
               - name: "placement_selector"
-                errorLogV: 10
                 help: "cluster placement selector about tenant.kubesphere.io/workspacetemplate."
                 each:
                   type: Info
@@ -2610,6 +2694,12 @@ kube-state-metrics:
                     valueFrom: []
                 commonLabels:
                   type: "used"
+              - name: "created"
+                help: "created timestamp about quota.kubesphere.io/resourcequota."
+                each:
+                  type: Gauge
+                  gauge:
+                    path: [metadata, creationTimestamp]
 
   rbac:
     create: true
@@ -2645,8 +2735,10 @@ kube-state-metrics:
     - kube_(hpa|replicaset|replicationcontroller)_.+_generation
     - kube_(certificatesigningrequests|rolebinding|)_.+
   metricLabelsAllowlist:
-    - '*=[kubesphere.io/workspace,storage.kubesphere.io/storagetype]'
-  metricAnnotationsAllowList: []
+    - 'namespaces=[kubesphere.io/workspace]'
+    - 'storageclasses=[storage.kubesphere.io/storagetype]'
+  metricAnnotationsAllowList:
+    - 'namespaces=[kubesphere.io/alias-name]'
 
   ## Enable scraping via kubernetes-service-endpoints
   ## Disabled by default as we service monitor is enabled below
@@ -2715,8 +2807,8 @@ kube-state-metrics:
           regex: kube_namespace_labels;(.*)
           replacement: $1
           sourceLabels:
-          - __name__
-          - label_kubesphere_io_workspace
+            - __name__
+            - label_kubesphere_io_workspace
           targetLabel: workspace
       # - action: keep
       #   regex: 'kube_(daemonset|deployment|pod|namespace|node|statefulset).+'