diff --git a/charts/internal/machine-controller-manager/seed/mcm-monitoring-dashboard.json b/charts/internal/machine-controller-manager/seed/mcm-monitoring-dashboard.json index 7e7cd9106..b0e364c35 100644 --- a/charts/internal/machine-controller-manager/seed/mcm-monitoring-dashboard.json +++ b/charts/internal/machine-controller-manager/seed/mcm-monitoring-dashboard.json @@ -547,14 +547,14 @@ "refId": "A" }, { - "expr": "mcm_machineset_items_total", + "expr": "mcm_machine_set_items_total", "format": "time_series", "intervalFactor": 1, "legendFormat": "machine set(s)", "refId": "B" }, { - "expr": "mcm_machinedeployment_items_total", + "expr": "mcm_machine_deployment_items_total", "format": "time_series", "intervalFactor": 1, "legendFormat": "machine deployment(s)", diff --git a/charts/internal/machine-controller-manager/seed/templates/configmap-monitoring.yaml b/charts/internal/machine-controller-manager/seed/templates/configmap-monitoring.yaml index 425a980d4..ab736fe26 100644 --- a/charts/internal/machine-controller-manager/seed/templates/configmap-monitoring.yaml +++ b/charts/internal/machine-controller-manager/seed/templates/configmap-monitoring.yaml @@ -26,7 +26,7 @@ data: target_label: pod metric_relabel_configs: - source_labels: [ __name__ ] - regex: ^(mcm_cloud_api_requests_failed_total|mcm_cloud_api_requests_total|mcm_machine_controller_frozen|mcm_machine_current_status_phase|mcm_machine_deployment_failed_machines|mcm_machine_items_total|mcm_machine_set_failed_machines|mcm_machinedeployment_items_total|mcm_machineset_items_total|mcm_scrape_failure_total|machine_adds|machine_depth|machine_queue_latency|machine_retries|machine_work_duration|machinedeployment_adds|machinedeployment_depth|machinedeployment_queue_latency|machinedeployment_retries|machinedeployment_work_duration|machinesafetyapiserver_adds|machinesafetyapiserver_depth|machinesafetyapiserver_queue_latency|machinesafetyapiserver_retries|machinesafetyapiserver_work_duration|machinesafetyorphanvms_adds|machinesafetyorphanvms_depth|machinesafetyorphanvms_queue_latency|machinesafetyorphanvms_retries|machinesafetyorphanvms_work_duration|machinesafetyovershooting_adds|machinesafetyovershooting_depth|machinesafetyovershooting_latency|machinesafetyovershooting_retries|machinesafetyovershooting_work_duration|machineset_adds|machineset_depth|machineset_queue_latency|machineset_retries|machineset_work_duration|node_adds|node_depth|node_queue_latency|node_retries|node_work_duration|secret_adds|secret_depth|secret_queue_latency|secret_retries|secret_work_duration|process_max_fds|process_open_fds)$ + regex: ^(mcm_cloud_api_requests_failed_total|mcm_cloud_api_requests_total|mcm_machine_controller_frozen|mcm_machine_current_status_phase|mcm_machine_deployment_failed_machines|mcm_machine_items_total|mcm_machine_set_failed_machines|mcm_machine_deployment_items_total|mcm_machine_set_items_total|mcm_scrape_failure_total|process_max_fds|process_open_fds|mcm_workqueue_adds_total|mcm_workqueue_depth|mcm_workqueue_queue_duration_seconds_bucket|mcm_workqueue_queue_duration_seconds_sum|mcm_workqueue_queue_duration_seconds_count|mcm_workqueue_work_duration_seconds_bucket|mcm_workqueue_work_duration_seconds_sum|mcm_workqueue_work_duration_seconds_count|mcm_workqueue_unfinished_work_seconds|mcm_workqueue_longest_running_processor_seconds|mcm_workqueue_retries_total)$ action: keep alerting_rules: |