{ "description": "Controller Runtime", "graphTooltip": 1, "panels": [ { "datasource": { "type": "datasource", "uid": "-- Mixed --" }, "fieldConfig": { "defaults": { "decimals": 0, "unit": null } }, "gridPos": { "h": 8, "w": 24, "x": 0, "y": 0 }, "id": 1, "pluginVersion": "v11.0.0", "targets": [ { "datasource": { "type": "prometheus", "uid": "prometheus" }, "expr": "controller_runtime_active_workers{job=\"$job\", namespace=\"$namespace\"}", "legendFormat": "{{controller}} {{instance}}" } ], "title": "Number of Workers in Use", "type": "stat" }, { "datasource": { "type": "datasource", "uid": "-- Mixed --" }, "fieldConfig": { "defaults": { "decimals": null, "unit": null } }, "gridPos": { "h": 8, "w": 24, "x": 0, "y": 8 }, "id": 2, "pluginVersion": "v11.0.0", "targets": [ { "datasource": { "type": "prometheus", "uid": "prometheus" }, "expr": "sum(rate(controller_runtime_reconcile_errors_total{job=\"$job\", namespace=\"$namespace\"}[5m])) by (instance, pod)", "legendFormat": "{{instance}} {{pod}}" } ], "title": "Reconciliation Error Count per Controller", "type": "timeseries" }, { "datasource": { "type": "datasource", "uid": "-- Mixed --" }, "fieldConfig": { "defaults": { "decimals": null, "unit": null } }, "gridPos": { "h": 8, "w": 24, "x": 0, "y": 16 }, "id": 3, "pluginVersion": "v11.0.0", "targets": [ { "datasource": { "type": "prometheus", "uid": "prometheus" }, "expr": "sum(rate(controller_runtime_reconcile_total{job=\"$job\", namespace=\"$namespace\"}[5m])) by (instance, pod)", "legendFormat": "{{instance}} {{pod}}" } ], "title": "Total Reconciliation Count per Controller", "type": "timeseries" }, { "datasource": { "type": "datasource", "uid": "-- Mixed --" }, "fieldConfig": { "defaults": { "decimals": 0, "unit": null } }, "gridPos": { "h": 8, "w": 24, "x": 0, "y": 24 }, "id": 4, "pluginVersion": "v11.0.0", "targets": [ { "datasource": { "type": "prometheus", "uid": "prometheus" }, "expr": "workqueue_depth{job=\"$job\", namespace=\"$namespace\"}", "legendFormat": "{{instance}} {{pod}}" } ], "title": "WorkQueue Depth", "type": "stat" }, { "datasource": { "type": "datasource", "uid": "-- Mixed --" }, "fieldConfig": { "defaults": { "decimals": null, "unit": null } }, "gridPos": { "h": 8, "w": 24, "x": 0, "y": 32 }, "id": 5, "pluginVersion": "v11.0.0", "targets": [ { "datasource": { "type": "prometheus", "uid": "prometheus" }, "expr": "histogram_quantile(0.50, sum(rate(workqueue_queue_duration_seconds_bucket{job=\"$job\", namespace=\"$namespace\"}[5m])) by (instance, name, le))", "legendFormat": "P50 {{name}}" } ], "title": "Seconds for Items Stay in Queue (before being requested) P50", "type": "timeseries" }, { "datasource": { "type": "datasource", "uid": "-- Mixed --" }, "fieldConfig": { "defaults": { "decimals": null, "unit": null } }, "gridPos": { "h": 8, "w": 24, "x": 0, "y": 40 }, "id": 6, "pluginVersion": "v11.0.0", "targets": [ { "datasource": { "type": "prometheus", "uid": "prometheus" }, "expr": "histogram_quantile(0.90, sum(rate(workqueue_queue_duration_seconds_bucket{job=\"$job\", namespace=\"$namespace\"}[5m])) by (instance, name, le))", "legendFormat": "P90 {{name}}" } ], "title": "Seconds for Items Stay in Queue (before being requested) P90", "type": "timeseries" }, { "datasource": { "type": "datasource", "uid": "-- Mixed --" }, "fieldConfig": { "defaults": { "decimals": null, "unit": null } }, "gridPos": { "h": 8, "w": 24, "x": 0, "y": 48 }, "id": 7, "pluginVersion": "v11.0.0", "targets": [ { "datasource": { "type": "prometheus", "uid": "prometheus" }, "expr": "histogram_quantile(0.99, sum(rate(workqueue_queue_duration_seconds_bucket{job=\"$job\", namespace=\"$namespace\"}[5m])) by (instance, name, le))", "legendFormat": "P99 {{name}}" } ], "title": "Seconds for Items Stay in Queue (before being requested) P99", "type": "timeseries" }, { "datasource": { "type": "datasource", "uid": "-- Mixed --" }, "fieldConfig": { "defaults": { "decimals": null, "unit": null } }, "gridPos": { "h": 8, "w": 24, "x": 0, "y": 56 }, "id": 8, "pluginVersion": "v11.0.0", "targets": [ { "datasource": { "type": "prometheus", "uid": "prometheus" }, "expr": "sum(rate(workqueue_adds_total{job=\"$job\", namespace=\"$namespace\"}[2m])) by (instance, name)", "legendFormat": "{{name}} {{instance}}" } ], "title": "Work Queue Add Rate", "type": "timeseries" }, { "datasource": { "type": "datasource", "uid": "-- Mixed --" }, "fieldConfig": { "defaults": { "decimals": null, "unit": null } }, "gridPos": { "h": 8, "w": 24, "x": 0, "y": 64 }, "id": 9, "pluginVersion": "v11.0.0", "targets": [ { "datasource": { "type": "prometheus", "uid": "prometheus" }, "expr": "rate(workqueue_unfinished_work_seconds{job=\"$job\", namespace=\"$namespace\"}[5m])", "legendFormat": "{{name}} {{instance}}" } ], "title": "Unfinished Seconds", "type": "stat" }, { "datasource": { "type": "datasource", "uid": "-- Mixed --" }, "fieldConfig": { "defaults": { "decimals": null, "unit": null } }, "gridPos": { "h": 8, "w": 24, "x": 0, "y": 72 }, "id": 10, "pluginVersion": "v11.0.0", "targets": [ { "datasource": { "type": "prometheus", "uid": "prometheus" }, "expr": "histogram_quantile(0.50, sum(rate(workqueue_work_duration_seconds_bucket{job=\"$job\", namespace=\"$namespace\"}[5m])) by (instance, name, le))", "legendFormat": "P50 {{name}}" } ], "title": "Seconds Processing Items from WorkQueue - 50th Percentile", "type": "timeseries" }, { "datasource": { "type": "datasource", "uid": "-- Mixed --" }, "fieldConfig": { "defaults": { "decimals": null, "unit": null } }, "gridPos": { "h": 8, "w": 24, "x": 0, "y": 80 }, "id": 11, "pluginVersion": "v11.0.0", "targets": [ { "datasource": { "type": "prometheus", "uid": "prometheus" }, "expr": "histogram_quantile(0.90, sum(rate(workqueue_work_duration_seconds_bucket{job=\"$job\", namespace=\"$namespace\"}[5m])) by (instance, name, le))", "legendFormat": "P90 {{name}}" } ], "title": "Seconds Processing Items from WorkQueue - 90th Percentile", "type": "timeseries" }, { "datasource": { "type": "datasource", "uid": "-- Mixed --" }, "fieldConfig": { "defaults": { "decimals": null, "unit": null } }, "gridPos": { "h": 8, "w": 24, "x": 0, "y": 88 }, "id": 12, "pluginVersion": "v11.0.0", "targets": [ { "datasource": { "type": "prometheus", "uid": "prometheus" }, "expr": "histogram_quantile(0.99, sum(rate(workqueue_work_duration_seconds_bucket{job=\"$job\", namespace=\"$namespace\"}[5m])) by (instance, name, le))", "legendFormat": "P99 {{name}}" } ], "title": "Seconds Processing Items from WorkQueue - 99th Percentile", "type": "timeseries" }, { "datasource": { "type": "datasource", "uid": "-- Mixed --" }, "fieldConfig": { "defaults": { "decimals": null, "unit": null } }, "gridPos": { "h": 8, "w": 24, "x": 0, "y": 96 }, "id": 13, "pluginVersion": "v11.0.0", "targets": [ { "datasource": { "type": "prometheus", "uid": "prometheus" }, "expr": "sum(rate(workqueue_retries_total{job=\"$job\", namespace=\"$namespace\"}[5m])) by (instance, name)", "legendFormat": "{{name}} {{instance}}" } ], "title": "Work Queue Retries Rate", "type": "timeseries" } ], "schemaVersion": 39, "templating": { "list": [ { "datasource": { "type": "prometheus", "uid": "prometheus" }, "name": "namespace", "query": "label_values(controller_runtime_reconcile_total, namespace)", "refresh": 2, "type": "query" }, { "datasource": { "type": "prometheus", "uid": "prometheus" }, "name": "job", "query": "label_values(controller_runtime_reconcile_total{namespace=~\"$namespace\"}, job)", "refresh": 2, "type": "query" } ] }, "time": { "from": "now-1h", "to": "now" }, "timezone": "utc", "title": "Fleet / Controller-Runtime", "uid": "fleet-controller-runtime" }