From 5a99928c6fad943276d9aff5b71633523922c2d5 Mon Sep 17 00:00:00 2001 From: Hermes Agent service account Date: Fri, 19 Jun 2026 18:26:54 -0500 Subject: [PATCH] Add ServiceMonitors and Grafana dashboards for Harbor, External-DNS, and Ingress-NGINX - Created ServiceMonitor for Harbor (harbor-core, harbor-exporter, harbor-jobservice, harbor-registry) - Port: http-metrics (8001) - Scrape interval: 30s - Verified metrics: harbor_core_http_request_duration_seconds_count - Created ServiceMonitor for External-DNS - Port: http (7979) - Scrape interval: 30s - Verified metrics: external_dns_registry_endpoints_total - Created ServiceMonitor for Ingress-NGINX - Port: metrics (10254) - Scrape interval: 30s - Verified metrics: nginx_ingress_controller_requests - Added Grafana dashboards: - Harbor Overview (dashboard 16366) - External-DNS (dashboard 15038) - Ingress-NGINX Controller (dashboard 9614) All ServiceMonitors deployed and actively scraping. Prometheus targets confirmed UP. --- .../applications/monitoring/dashboards.yaml | 5798 +++++++++++++++++ .../platform/external-dns/servicemonitor.yaml | 36 + cluster/platform/harbor/servicemonitor.yaml | 49 + .../ingress-nginx/servicemonitor.yaml | 37 + 4 files changed, 5920 insertions(+) create mode 100644 cluster/platform/external-dns/servicemonitor.yaml create mode 100644 cluster/platform/harbor/servicemonitor.yaml create mode 100644 cluster/platform/ingress-nginx/servicemonitor.yaml diff --git a/cluster/applications/monitoring/dashboards.yaml b/cluster/applications/monitoring/dashboards.yaml index 6b96432..fd75c43 100644 --- a/cluster/applications/monitoring/dashboards.yaml +++ b/cluster/applications/monitoring/dashboards.yaml @@ -3400,4 +3400,5802 @@ data: "uid": "kq1L0kKVk", "version": 75, "weekStart": "" + } +--- +apiVersion: v1 +kind: ConfigMap +metadata: + name: dashboard-harbor-overview + namespace: monitoring + labels: + grafana_dashboard: "1" +data: + harbor-overview.json: | + { + "__inputs": [ + { + "name": "DS_PROMETHEUS", + "label": "Prometheus", + "description": "", + "type": "datasource", + "pluginId": "prometheus", + "pluginName": "Prometheus" + } + ], + "__elements": [], + "__requires": [ + { + "type": "grafana", + "id": "grafana", + "name": "Grafana", + "version": "8.5.3" + }, + { + "type": "panel", + "id": "graph", + "name": "Graph (old)", + "version": "" + }, + { + "type": "datasource", + "id": "prometheus", + "name": "Prometheus", + "version": "1.0.0" + }, + { + "type": "panel", + "id": "table-old", + "name": "Table (old)", + "version": "" + } + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": { + "type": "grafana", + "uid": "-- Grafana --" + }, + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "target": { + "limit": 100, + "matchAny": false, + "tags": [], + "type": "dashboard" + }, + "type": "dashboard" + } + ] + }, + "editable": true, + "fiscalYearStartMonth": 0, + "graphTooltip": 0, + "id": null, + "iteration": 1654077581711, + "links": [], + "liveNow": false, + "panels": [ + { + "collapsed": false, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 0 + }, + "id": 14, + "panels": [], + "title": "CPU Usage", + "type": "row" + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": { + "uid": "$datasource" + }, + "fill": 10, + "gridPos": { + "h": 7, + "w": 24, + "x": 0, + "y": 1 + }, + "id": 1, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "quota - requests", + "color": "#F2495C", + "dashes": true, + "fill": 0, + "hiddenSeries": true, + "hideTooltip": true, + "legend": true, + "linewidth": 2, + "stack": false + }, + { + "alias": "quota - limits", + "color": "#FF9830", + "dashes": true, + "fill": 0, + "hiddenSeries": true, + "hideTooltip": true, + "legend": true, + "linewidth": 2, + "stack": false + } + ], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{workload}} - {{workload_type}}", + "refId": "A", + "step": 10, + "datasource": "${DS_PROMETHEUS}" + }, + { + "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.cpu\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "quota - requests", + "refId": "B", + "step": 10, + "datasource": "${DS_PROMETHEUS}" + }, + { + "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.cpu\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "quota - limits", + "refId": "C", + "step": 10, + "datasource": "${DS_PROMETHEUS}" + } + ], + "thresholds": [], + "title": "CPU Usage", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "logBase": 1, + "min": 0, + "show": true + }, + { + "format": "short", + "logBase": 1, + "show": false + } + ] + }, + { + "collapsed": false, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 8 + }, + "id": 15, + "panels": [], + "title": "CPU Quota", + "type": "row" + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": { + "uid": "$datasource" + }, + "fill": 1, + "gridPos": { + "h": 7, + "w": 24, + "x": 0, + "y": 9 + }, + "id": 2, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "align": "auto", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Running Pods", + "align": "auto", + "colors": [], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 0, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Usage", + "align": "auto", + "colors": [], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Requests", + "align": "auto", + "colors": [], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Requests %", + "align": "auto", + "colors": [], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "CPU Limits", + "align": "auto", + "colors": [], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Limits %", + "align": "auto", + "colors": [], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Workload", + "align": "auto", + "colors": [], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "/d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-workload=$__cell&var-type=$__cell_2", + "pattern": "workload", + "thresholds": [], + "type": "number", + "unit": "short" + }, + { + "alias": "Workload Type", + "align": "auto", + "colors": [], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "workload_type", + "thresholds": [], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "align": "auto", + "colors": [], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "count(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload, workload_type)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10, + "datasource": "${DS_PROMETHEUS}" + }, + { + "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10, + "datasource": "${DS_PROMETHEUS}" + }, + { + "expr": "sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10, + "datasource": "${DS_PROMETHEUS}" + }, + { + "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10, + "datasource": "${DS_PROMETHEUS}" + }, + { + "expr": "sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10, + "datasource": "${DS_PROMETHEUS}" + }, + { + "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10, + "datasource": "${DS_PROMETHEUS}" + } + ], + "thresholds": [], + "title": "CPU Quota", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "transform": "table", + "type": "table-old", + "xaxis": { + "mode": "time", + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "logBase": 1, + "min": 0, + "show": true + }, + { + "format": "short", + "logBase": 1, + "show": false + } + ] + }, + { + "collapsed": false, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 16 + }, + "id": 16, + "panels": [], + "title": "Memory Usage", + "type": "row" + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": { + "uid": "$datasource" + }, + "fill": 10, + "gridPos": { + "h": 7, + "w": 24, + "x": 0, + "y": 17 + }, + "id": 3, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "quota - requests", + "color": "#F2495C", + "dashes": true, + "fill": 0, + "hiddenSeries": true, + "hideTooltip": true, + "legend": true, + "linewidth": 2, + "stack": false + }, + { + "alias": "quota - limits", + "color": "#FF9830", + "dashes": true, + "fill": 0, + "hiddenSeries": true, + "hideTooltip": true, + "legend": true, + "linewidth": 2, + "stack": false + } + ], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(\n container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{workload}} - {{workload_type}}", + "refId": "A", + "step": 10, + "datasource": "${DS_PROMETHEUS}" + }, + { + "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.memory\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "quota - requests", + "refId": "B", + "step": 10, + "datasource": "${DS_PROMETHEUS}" + }, + { + "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.memory\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "quota - limits", + "refId": "C", + "step": 10, + "datasource": "${DS_PROMETHEUS}" + } + ], + "thresholds": [], + "title": "Memory Usage", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "logBase": 1, + "min": 0, + "show": true + }, + { + "format": "short", + "logBase": 1, + "show": false + } + ] + }, + { + "collapsed": false, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 24 + }, + "id": 17, + "panels": [], + "title": "Memory Quota", + "type": "row" + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": { + "uid": "$datasource" + }, + "fill": 1, + "gridPos": { + "h": 7, + "w": 24, + "x": 0, + "y": 25 + }, + "id": 4, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "align": "auto", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Running Pods", + "align": "auto", + "colors": [], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 0, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [], + "type": "number", + "unit": "short" + }, + { + "alias": "Memory Usage", + "align": "auto", + "colors": [], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Requests", + "align": "auto", + "colors": [], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Requests %", + "align": "auto", + "colors": [], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Memory Limits", + "align": "auto", + "colors": [], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Limits %", + "align": "auto", + "colors": [], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Workload", + "align": "auto", + "colors": [], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "/d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-workload=$__cell&var-type=$__cell_2", + "pattern": "workload", + "thresholds": [], + "type": "number", + "unit": "short" + }, + { + "alias": "Workload Type", + "align": "auto", + "colors": [], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "workload_type", + "thresholds": [], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "align": "auto", + "colors": [], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "count(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload, workload_type)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10, + "datasource": "${DS_PROMETHEUS}" + }, + { + "expr": "sum(\n container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10, + "datasource": "${DS_PROMETHEUS}" + }, + { + "expr": "sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10, + "datasource": "${DS_PROMETHEUS}" + }, + { + "expr": "sum(\n container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10, + "datasource": "${DS_PROMETHEUS}" + }, + { + "expr": "sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10, + "datasource": "${DS_PROMETHEUS}" + }, + { + "expr": "sum(\n container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10, + "datasource": "${DS_PROMETHEUS}" + } + ], + "thresholds": [], + "title": "Memory Quota", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "transform": "table", + "type": "table-old", + "xaxis": { + "mode": "time", + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "logBase": 1, + "min": 0, + "show": true + }, + { + "format": "short", + "logBase": 1, + "show": false + } + ] + }, + { + "collapsed": false, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 32 + }, + "id": 18, + "panels": [], + "title": "Current Network Usage", + "type": "row" + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": { + "uid": "$datasource" + }, + "fill": 1, + "gridPos": { + "h": 7, + "w": 24, + "x": 0, + "y": 33 + }, + "id": 5, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "align": "auto", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Current Receive Bandwidth", + "align": "auto", + "colors": [], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Current Transmit Bandwidth", + "align": "auto", + "colors": [], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Rate of Received Packets", + "align": "auto", + "colors": [], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets", + "align": "auto", + "colors": [], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Received Packets Dropped", + "align": "auto", + "colors": [], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets Dropped", + "align": "auto", + "colors": [], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [], + "type": "number", + "unit": "pps" + }, + { + "alias": "Workload", + "align": "auto", + "colors": [], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down to pods", + "linkUrl": "/d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-workload=$__cell&var-type=$type", + "pattern": "workload", + "thresholds": [], + "type": "number", + "unit": "short" + }, + { + "alias": "Workload Type", + "align": "auto", + "colors": [], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "workload_type", + "thresholds": [], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "align": "auto", + "colors": [], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "(sum(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10, + "datasource": "${DS_PROMETHEUS}" + }, + { + "expr": "(sum(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10, + "datasource": "${DS_PROMETHEUS}" + }, + { + "expr": "(sum(irate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10, + "datasource": "${DS_PROMETHEUS}" + }, + { + "expr": "(sum(irate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10, + "datasource": "${DS_PROMETHEUS}" + }, + { + "expr": "(sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10, + "datasource": "${DS_PROMETHEUS}" + }, + { + "expr": "(sum(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10, + "datasource": "${DS_PROMETHEUS}" + } + ], + "thresholds": [], + "title": "Current Network Usage", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "transform": "table", + "type": "table-old", + "xaxis": { + "mode": "time", + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "logBase": 1, + "min": 0, + "show": true + }, + { + "format": "short", + "logBase": 1, + "show": false + } + ] + }, + { + "collapsed": false, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 40 + }, + "id": 19, + "panels": [], + "title": "Bandwidth", + "type": "row" + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": { + "uid": "$datasource" + }, + "fill": 10, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 41 + }, + "id": 6, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{workload}}", + "refId": "A", + "step": 10, + "datasource": "${DS_PROMETHEUS}" + } + ], + "thresholds": [], + "title": "Receive Bandwidth", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "Bps", + "logBase": 1, + "min": 0, + "show": true + }, + { + "format": "short", + "logBase": 1, + "show": false + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": { + "uid": "$datasource" + }, + "fill": 10, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 41 + }, + "id": 7, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{workload}}", + "refId": "A", + "step": 10, + "datasource": "${DS_PROMETHEUS}" + } + ], + "thresholds": [], + "title": "Transmit Bandwidth", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "Bps", + "logBase": 1, + "min": 0, + "show": true + }, + { + "format": "short", + "logBase": 1, + "show": false + } + ] + }, + { + "collapsed": false, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 48 + }, + "id": 20, + "panels": [], + "title": "Average Container Bandwidth by Workload", + "type": "row" + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": { + "uid": "$datasource" + }, + "fill": 10, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 49 + }, + "id": 8, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(avg(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{workload}}", + "refId": "A", + "step": 10, + "datasource": "${DS_PROMETHEUS}" + } + ], + "thresholds": [], + "title": "Average Container Bandwidth by Workload: Received", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "Bps", + "logBase": 1, + "min": 0, + "show": true + }, + { + "format": "short", + "logBase": 1, + "show": false + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": { + "uid": "$datasource" + }, + "fill": 10, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 49 + }, + "id": 9, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(avg(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{workload}}", + "refId": "A", + "step": 10, + "datasource": "${DS_PROMETHEUS}" + } + ], + "thresholds": [], + "title": "Average Container Bandwidth by Workload: Transmitted", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "Bps", + "logBase": 1, + "min": 0, + "show": true + }, + { + "format": "short", + "logBase": 1, + "show": false + } + ] + }, + { + "collapsed": false, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 56 + }, + "id": 21, + "panels": [], + "title": "Rate of Packets", + "type": "row" + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": { + "uid": "$datasource" + }, + "fill": 10, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 57 + }, + "id": 10, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{workload}}", + "refId": "A", + "step": 10, + "datasource": "${DS_PROMETHEUS}" + } + ], + "thresholds": [], + "title": "Rate of Received Packets", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "pps", + "logBase": 1, + "min": 0, + "show": true + }, + { + "format": "short", + "logBase": 1, + "show": false + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": { + "uid": "$datasource" + }, + "fill": 10, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 57 + }, + "id": 11, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{workload}}", + "refId": "A", + "step": 10, + "datasource": "${DS_PROMETHEUS}" + } + ], + "thresholds": [], + "title": "Rate of Transmitted Packets", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "pps", + "logBase": 1, + "min": 0, + "show": true + }, + { + "format": "short", + "logBase": 1, + "show": false + } + ] + }, + { + "collapsed": false, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 64 + }, + "id": 22, + "panels": [], + "title": "Rate of Packets Dropped", + "type": "row" + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": { + "uid": "$datasource" + }, + "fill": 10, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 65 + }, + "id": 12, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{workload}}", + "refId": "A", + "step": 10, + "datasource": "${DS_PROMETHEUS}" + } + ], + "thresholds": [], + "title": "Rate of Received Packets Dropped", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "pps", + "logBase": 1, + "min": 0, + "show": true + }, + { + "format": "short", + "logBase": 1, + "show": false + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": { + "uid": "$datasource" + }, + "fill": 10, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 65 + }, + "id": 13, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{workload}}", + "refId": "A", + "step": 10, + "datasource": "${DS_PROMETHEUS}" + } + ], + "thresholds": [], + "title": "Rate of Transmitted Packets Dropped", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "pps", + "logBase": 1, + "min": 0, + "show": true + }, + { + "format": "short", + "logBase": 1, + "show": false + } + ] + } + ], + "refresh": "10s", + "schemaVersion": 36, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "selected": false, + "text": "default", + "value": "default" + }, + "hide": 0, + "includeAll": false, + "label": "Data Source", + "multi": false, + "name": "datasource", + "options": [], + "query": "prometheus", + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "type": "datasource" + }, + { + "current": {}, + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "definition": "", + "hide": 2, + "includeAll": false, + "multi": false, + "name": "cluster", + "options": [], + "query": { + "query": "label_values(up{job=\"kube-state-metrics\"}, cluster)", + "refId": "Prometheus-cluster-Variable-Query" + }, + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "current": {}, + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "definition": "", + "hide": 0, + "includeAll": false, + "multi": false, + "name": "namespace", + "options": [], + "query": { + "query": "label_values(kube_pod_info{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)", + "refId": "Prometheus-namespace-Variable-Query" + }, + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": {}, + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "definition": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\"}, workload_type)", + "hide": 0, + "includeAll": false, + "multi": false, + "name": "type", + "options": [], + "query": { + "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\"}, workload_type)", + "refId": "Prometheus-type-Variable-Query" + }, + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 0, + "tagValuesQuery": "", + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Kubernetes / Compute Resources / Namespace (Workloads)", + "uid": "a87fb0d919ec0ea5f6543124e16c42a5", + "version": 1, + "weekStart": "", + "gnetId": 16366, + "description": "Kubernetes" + } +--- +apiVersion: v1 +kind: ConfigMap +metadata: + name: dashboard-external-dns + namespace: monitoring + labels: + grafana_dashboard: "1" +data: + external-dns.json: | + { + "__inputs": [], + "__elements": {}, + "__requires": [ + { + "type": "panel", + "id": "bargauge", + "name": "Bar gauge", + "version": "" + }, + { + "type": "panel", + "id": "gauge", + "name": "Gauge", + "version": "" + }, + { + "type": "grafana", + "id": "grafana", + "name": "Grafana", + "version": "10.1.5" + }, + { + "type": "datasource", + "id": "prometheus", + "name": "Prometheus", + "version": "1.0.0" + }, + { + "type": "panel", + "id": "table", + "name": "Table", + "version": "" + }, + { + "type": "panel", + "id": "timeseries", + "name": "Time series", + "version": "" + } + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": { + "type": "datasource", + "uid": "grafana" + }, + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "type": "dashboard" + } + ] + }, + "description": "Grafana dashboard to display external-dns metrics", + "editable": true, + "fiscalYearStartMonth": 0, + "gnetId": 15038, + "graphTooltip": 0, + "id": null, + "links": [], + "liveNow": false, + "panels": [ + { + "collapsed": false, + "datasource": { + "uid": "$datasource" + }, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 0 + }, + "id": 2, + "panels": [], + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "refId": "A" + } + ], + "title": "External-dns endpoints", + "type": "row" + }, + { + "datasource": { + "uid": "$datasource" + }, + "description": "Number of Endpoints in the registry", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 18, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 5, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "auto", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 1 + }, + "id": 28, + "options": { + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "exemplar": true, + "expr": "external_dns_registry_endpoints_total {pod=~\".*external-dns.*\",pod=~\"$pod\"}", + "interval": "", + "legendFormat": "{{pod}}", + "refId": "A" + } + ], + "title": "Number of Endpoints in the registry", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "description": "Number of Endpoints in all sources", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 18, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 5, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "auto", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 1 + }, + "id": 30, + "options": { + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "editorMode": "code", + "exemplar": true, + "expr": "external_dns_source_endpoints_total {pod=~\".*external-dns.*\",pod=~\"$pod\"}", + "interval": "", + "legendFormat": "{{pod}}", + "range": true, + "refId": "A" + } + ], + "title": "Number of Endpoints in all sources", + "type": "timeseries" + }, + { + "collapsed": false, + "datasource": { + "uid": "$datasource" + }, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 9 + }, + "id": 26, + "panels": [], + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "refId": "A" + } + ], + "title": "External-dns sync", + "type": "row" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "description": "Timestamp of last attempted sync with the DNS provider", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "purple", + "value": null + } + ] + }, + "unit": "dateTimeAsLocal" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 10 + }, + "id": 36, + "options": { + "displayMode": "lcd", + "minVizHeight": 10, + "minVizWidth": 0, + "orientation": "horizontal", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "showUnfilled": true, + "text": { + "valueSize": 24 + }, + "valueMode": "color" + }, + "pluginVersion": "10.1.5", + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "editorMode": "code", + "exemplar": true, + "expr": "1000 * (external_dns_controller_last_reconcile_timestamp_seconds{pod=~\".*external-dns.*\",pod=~\"$pod\"})", + "interval": "", + "legendFormat": "{{pod}}", + "range": true, + "refId": "A" + } + ], + "title": "Timestamp of last attempted sync with the DNS provider", + "type": "bargauge" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "description": "Timestamp of last successful sync with the DNS provider", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "purple", + "value": null + } + ] + }, + "unit": "dateTimeAsLocal" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 10 + }, + "id": 24, + "options": { + "displayMode": "lcd", + "minVizHeight": 10, + "minVizWidth": 0, + "orientation": "horizontal", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "showUnfilled": true, + "text": { + "valueSize": 24 + }, + "valueMode": "color" + }, + "pluginVersion": "10.1.5", + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "editorMode": "code", + "exemplar": true, + "expr": "1000 * (external_dns_controller_last_sync_timestamp_seconds{pod=~\".*external-dns.*\",pod=~\"$pod\"})", + "interval": "", + "legendFormat": "{{pod}}", + "range": true, + "refId": "A" + } + ], + "title": "Timestamp of last successful sync with the DNS provider", + "type": "bargauge" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "description": "External-dns controller no_op runs total", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "purple", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 5, + "x": 0, + "y": 18 + }, + "id": 37, + "options": { + "orientation": "auto", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "showThresholdLabels": false, + "showThresholdMarkers": true + }, + "pluginVersion": "10.1.5", + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "editorMode": "code", + "exemplar": true, + "expr": "external_dns_controller_no_op_runs_total {pod=~\".*external-dns.*\",pod=~\"$pod\"}", + "interval": "", + "legendFormat": "{{pod}}", + "range": true, + "refId": "A" + } + ], + "title": "External-dns controller no_op runs total", + "type": "gauge" + }, + { + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 25 + }, + "id": 29, + "panels": [], + "title": "External-dns records", + "type": "row" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "description": "Number of A records in registry", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "light-blue", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 5, + "x": 0, + "y": 26 + }, + "id": 32, + "options": { + "orientation": "auto", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "showThresholdLabels": false, + "showThresholdMarkers": true + }, + "pluginVersion": "10.1.5", + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "editorMode": "code", + "exemplar": true, + "expr": "external_dns_registry_a_records {pod=~\".*external-dns.*\",pod=~\"$pod\"}", + "interval": "", + "legendFormat": "{{pod}}", + "range": true, + "refId": "A" + } + ], + "title": "Number of A records in registry", + "type": "gauge" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "description": "Number of AAAA records in registry", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "light-blue", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 5, + "x": 5, + "y": 26 + }, + "id": 33, + "options": { + "orientation": "auto", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "showThresholdLabels": false, + "showThresholdMarkers": true + }, + "pluginVersion": "10.1.5", + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "editorMode": "code", + "exemplar": true, + "expr": "external_dns_registry_aaaa_records {pod=~\".*external-dns.*\",pod=~\"$pod\"}", + "interval": "", + "legendFormat": "{{pod}}", + "range": true, + "refId": "A" + } + ], + "title": "Number of AAAA records in registry", + "type": "gauge" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "description": "Number of A records in source", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "light-blue", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 5, + "x": 10, + "y": 26 + }, + "id": 34, + "options": { + "orientation": "auto", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "showThresholdLabels": false, + "showThresholdMarkers": true + }, + "pluginVersion": "10.1.5", + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "editorMode": "code", + "exemplar": true, + "expr": "external_dns_source_a_records {pod=~\".*external-dns.*\",pod=~\"$pod\"}", + "interval": "", + "legendFormat": "{{pod}}", + "range": true, + "refId": "A" + } + ], + "title": "Number of A records in source", + "type": "gauge" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "description": "Number of AAAA records in source", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "light-blue", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 5, + "x": 0, + "y": 33 + }, + "id": 35, + "options": { + "orientation": "auto", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "showThresholdLabels": false, + "showThresholdMarkers": true + }, + "pluginVersion": "10.1.5", + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "editorMode": "code", + "exemplar": true, + "expr": "external_dns_source_aaaa_records {pod=~\".*external-dns.*\",pod=~\"$pod\"}", + "interval": "", + "legendFormat": "{{pod}}", + "range": true, + "refId": "A" + } + ], + "title": "Number of AAAA records in source", + "type": "gauge" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "description": "Number of DNS A-records that exists both in source and registry", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "light-blue", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 5, + "x": 5, + "y": 33 + }, + "id": 6, + "options": { + "orientation": "auto", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "showThresholdLabels": false, + "showThresholdMarkers": true + }, + "pluginVersion": "10.1.5", + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "editorMode": "code", + "exemplar": true, + "expr": "external_dns_controller_verified_a_records {pod=~\".*external-dns.*\",pod=~\"$pod\"}", + "interval": "", + "legendFormat": "{{pod}}", + "range": true, + "refId": "A" + } + ], + "title": "Number of DNS A-records that exists both in source and registry", + "type": "gauge" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "description": "Number of DNS AAAA-records that exists both in source and registry", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "light-blue", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 5, + "x": 10, + "y": 33 + }, + "id": 31, + "options": { + "orientation": "auto", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "showThresholdLabels": false, + "showThresholdMarkers": true + }, + "pluginVersion": "10.1.5", + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "editorMode": "code", + "exemplar": true, + "expr": "external_dns_controller_verified_aaaa_records {pod=~\".*external-dns.*\",pod=~\"$pod\"}", + "interval": "", + "legendFormat": "{{pod}}", + "range": true, + "refId": "A" + } + ], + "title": "Number of DNS AAAA-records that exists both in source and registry", + "type": "gauge" + }, + { + "collapsed": false, + "datasource": { + "uid": "$datasource" + }, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 40 + }, + "id": 8, + "panels": [], + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "refId": "A" + } + ], + "title": "External-dns errors", + "type": "row" + }, + { + "datasource": { + "uid": "$datasource" + }, + "description": "Number of Registry errors", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "light-red", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 5, + "x": 0, + "y": 41 + }, + "id": 10, + "options": { + "orientation": "auto", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "showThresholdLabels": false, + "showThresholdMarkers": true + }, + "pluginVersion": "10.1.5", + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "exemplar": true, + "expr": "external_dns_registry_errors_total {pod=~\".*external-dns.*\",pod=~\"$pod\"}", + "interval": "", + "legendFormat": "{{pod}}", + "refId": "A" + } + ], + "title": "Total external-dns registry errors", + "type": "gauge" + }, + { + "datasource": { + "uid": "$datasource" + }, + "description": "Number of Source errors", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "light-red", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 5, + "x": 5, + "y": 41 + }, + "id": 12, + "options": { + "orientation": "auto", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "showThresholdLabels": false, + "showThresholdMarkers": true + }, + "pluginVersion": "10.1.5", + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "exemplar": true, + "expr": "external_dns_source_errors_total {pod=~\".*external-dns.*\",pod=~\"$pod\"}", + "interval": "", + "legendFormat": "{{pod}}", + "refId": "A" + } + ], + "title": "Total external-dns source errors", + "type": "gauge" + }, + { + "collapsed": false, + "datasource": { + "uid": "$datasource" + }, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 48 + }, + "id": 16, + "panels": [], + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "refId": "A" + } + ], + "title": "External-dns pods", + "type": "row" + }, + { + "datasource": { + "uid": "$datasource" + }, + "description": "", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 100, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "stepBefore", + "lineStyle": { + "fill": "solid" + }, + "lineWidth": 0, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "quota - requests" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#F2495C", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineWidth", + "value": 2 + }, + { + "id": "custom.stacking", + "value": { + "group": "A", + "mode": "none" + } + }, + { + "id": "custom.lineStyle", + "value": { + "dash": [ + 10, + 10 + ], + "fill": "dash" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "quota - limits" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#FF9830", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineWidth", + "value": 2 + }, + { + "id": "custom.stacking", + "value": { + "group": "A", + "mode": "none" + } + }, + { + "id": "custom.lineStyle", + "value": { + "dash": [ + 10, + 10 + ], + "fill": "dash" + } + } + ] + } + ] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 49 + }, + "id": 18, + "links": [], + "options": { + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "pluginVersion": "10.1.5", + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "exemplar": true, + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{pod=~\".*external-dns.*\",pod=~\"$pod\"}) by (pod)", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "refId": "A", + "step": 10 + }, + { + "datasource": { + "uid": "$datasource" + }, + "exemplar": true, + "expr": "scalar(kube_resourcequota{pod=~\".*external-dns.*\",pod=~\"$pod\", type=\"hard\",resource=\"requests.cpu\"})", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "quota - requests", + "refId": "B", + "step": 10 + }, + { + "datasource": { + "uid": "$datasource" + }, + "exemplar": true, + "expr": "scalar(kube_resourcequota{pod=~\".*external-dns.*\",pod=~\"$pod\", type=\"hard\",resource=\"limits.cpu\"})", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "quota - limits", + "refId": "C", + "step": 10 + } + ], + "title": "CPU Usage", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "description": "", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 100, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "stepBefore", + "lineWidth": 0, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "bytes" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "quota - requests" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#F2495C", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineWidth", + "value": 2 + }, + { + "id": "custom.stacking", + "value": { + "group": "A", + "mode": "none" + } + }, + { + "id": "custom.lineStyle", + "value": { + "dash": [ + 10, + 10 + ], + "fill": "dash" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "quota - limits" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#FF9830", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineWidth", + "value": 2 + }, + { + "id": "custom.stacking", + "value": { + "group": "A", + "mode": "none" + } + }, + { + "id": "custom.lineStyle", + "value": { + "dash": [ + 10, + 10 + ], + "fill": "dash" + } + } + ] + } + ] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 49 + }, + "id": 14, + "links": [], + "options": { + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "pluginVersion": "10.1.5", + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "exemplar": true, + "expr": "sum(container_memory_working_set_bytes{pod=~\".*external-dns.*\",pod=~\"$pod\",container!=\"\", image!=\"\"}) by (pod)", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "refId": "A", + "step": 10 + }, + { + "datasource": { + "uid": "$datasource" + }, + "editorMode": "code", + "exemplar": true, + "expr": "scalar(kube_resourcequota{pod=~\".*external-dns.*\", type=\"hard\",resource=\"requests.memory\"})", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "quota - requests", + "range": true, + "refId": "B", + "step": 10 + }, + { + "datasource": { + "uid": "$datasource" + }, + "editorMode": "code", + "exemplar": true, + "expr": "scalar(kube_resourcequota{pod=~\".*external-dns.*\",pod=~\"$pod\",type=\"hard\",resource=\"limits.memory\"})", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "quota - limits", + "range": true, + "refId": "C", + "step": 10 + } + ], + "title": "Memory Usage (w/o cache)", + "type": "timeseries" + }, + { + "datasource": { + "uid": "$datasource" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "custom": { + "align": "auto", + "cellOptions": { + "type": "auto" + }, + "inspect": false + }, + "decimals": 2, + "displayName": "", + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "Time" + }, + "properties": [ + { + "id": "displayName", + "value": "Time" + }, + { + "id": "custom.align" + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Value #A" + }, + "properties": [ + { + "id": "displayName", + "value": "CPU Usage" + }, + { + "id": "unit", + "value": "short" + }, + { + "id": "decimals", + "value": 2 + }, + { + "id": "custom.align" + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Value #B" + }, + "properties": [ + { + "id": "displayName", + "value": "CPU Requests" + }, + { + "id": "unit", + "value": "short" + }, + { + "id": "decimals", + "value": 2 + }, + { + "id": "custom.align" + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Value #C" + }, + "properties": [ + { + "id": "displayName", + "value": "CPU Requests %" + }, + { + "id": "unit", + "value": "percentunit" + }, + { + "id": "decimals", + "value": 2 + }, + { + "id": "custom.align" + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Value #D" + }, + "properties": [ + { + "id": "displayName", + "value": "CPU Limits" + }, + { + "id": "unit", + "value": "short" + }, + { + "id": "decimals", + "value": 2 + }, + { + "id": "custom.align" + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Value #E" + }, + "properties": [ + { + "id": "displayName", + "value": "CPU Limits %" + }, + { + "id": "unit", + "value": "percentunit" + }, + { + "id": "decimals", + "value": 2 + }, + { + "id": "custom.align" + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "pod" + }, + "properties": [ + { + "id": "displayName", + "value": "Pod" + }, + { + "id": "unit", + "value": "short" + }, + { + "id": "decimals", + "value": 2 + }, + { + "id": "links", + "value": [ + { + "targetBlank": false, + "title": "Drill down", + "url": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell" + } + ] + }, + { + "id": "custom.align" + } + ] + } + ] + }, + "gridPos": { + "h": 7, + "w": 24, + "x": 0, + "y": 57 + }, + "id": 20, + "links": [], + "options": { + "cellHeight": "sm", + "footer": { + "countRows": false, + "fields": "", + "reducer": [ + "sum" + ], + "show": false + }, + "showHeader": true + }, + "pluginVersion": "10.1.5", + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "exemplar": true, + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{pod=~\".*external-dns.*\",pod=~\"$pod\"}) by (pod)", + "format": "table", + "instant": true, + "interval": "", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "datasource": { + "uid": "$datasource" + }, + "exemplar": true, + "expr": "sum(kube_pod_container_resource_requests{pod=~\".*external-dns.*\",pod=~\"$pod\",resource=\"cpu\"}) by (pod)", + "format": "table", + "instant": true, + "interval": "", + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "datasource": { + "uid": "$datasource" + }, + "exemplar": true, + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{pod=~\".*external-dns.*\",pod=~\"$pod\"}) by (pod) / sum(kube_pod_container_resource_requests{pod=~\".*external-dns.*\",pod=~\"$pod\",resource=\"cpu\"}) by (pod)", + "format": "table", + "instant": true, + "interval": "", + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "datasource": { + "uid": "$datasource" + }, + "exemplar": true, + "expr": "sum(kube_pod_container_resource_limits{pod=~\".*external-dns.*\",pod=~\"$pod\",resource=\"cpu\"}) by (pod)", + "format": "table", + "instant": true, + "interval": "", + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "datasource": { + "uid": "$datasource" + }, + "exemplar": true, + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{pod=~\".*external-dns.*\",pod=~\"$pod\"}) by (pod) / sum(kube_pod_container_resource_limits{pod=~\".*external-dns.*\",pod=~\"$pod\",resource=\"cpu\"}) by (pod)", + "format": "table", + "instant": true, + "interval": "", + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + } + ], + "title": "CPU Quota", + "transformations": [ + { + "id": "merge", + "options": { + "reducers": [] + } + } + ], + "type": "table" + }, + { + "datasource": { + "uid": "$datasource" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "custom": { + "cellOptions": { + "type": "auto" + }, + "inspect": false + }, + "decimals": 2, + "displayName": "", + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "Time" + }, + "properties": [ + { + "id": "displayName", + "value": "Time" + }, + { + "id": "custom.align" + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Value #A" + }, + "properties": [ + { + "id": "displayName", + "value": "Memory Usage" + }, + { + "id": "unit", + "value": "bytes" + }, + { + "id": "decimals", + "value": 2 + }, + { + "id": "custom.align" + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Value #B" + }, + "properties": [ + { + "id": "displayName", + "value": "Memory Requests" + }, + { + "id": "unit", + "value": "bytes" + }, + { + "id": "decimals", + "value": 2 + }, + { + "id": "custom.align" + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Value #C" + }, + "properties": [ + { + "id": "displayName", + "value": "Memory Requests %" + }, + { + "id": "unit", + "value": "percentunit" + }, + { + "id": "decimals", + "value": 2 + }, + { + "id": "custom.align" + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Value #D" + }, + "properties": [ + { + "id": "displayName", + "value": "Memory Limits" + }, + { + "id": "unit", + "value": "bytes" + }, + { + "id": "decimals", + "value": 2 + }, + { + "id": "custom.align" + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Value #E" + }, + "properties": [ + { + "id": "displayName", + "value": "Memory Limits %" + }, + { + "id": "unit", + "value": "percentunit" + }, + { + "id": "decimals", + "value": 2 + }, + { + "id": "custom.align" + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Value #F" + }, + "properties": [ + { + "id": "displayName", + "value": "Memory Usage (RSS)" + }, + { + "id": "unit", + "value": "bytes" + }, + { + "id": "decimals", + "value": 2 + }, + { + "id": "custom.align" + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Value #G" + }, + "properties": [ + { + "id": "displayName", + "value": "Memory Usage (Cache)" + }, + { + "id": "unit", + "value": "bytes" + }, + { + "id": "decimals", + "value": 2 + }, + { + "id": "custom.align" + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Value #H" + }, + "properties": [ + { + "id": "displayName", + "value": "Memory Usage (Swap)" + }, + { + "id": "unit", + "value": "bytes" + }, + { + "id": "decimals", + "value": 2 + }, + { + "id": "custom.align" + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "pod" + }, + "properties": [ + { + "id": "displayName", + "value": "Pod" + }, + { + "id": "unit", + "value": "short" + }, + { + "id": "decimals", + "value": 2 + }, + { + "id": "links", + "value": [ + { + "targetBlank": false, + "title": "Drill down", + "url": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell" + } + ] + }, + { + "id": "custom.align" + } + ] + } + ] + }, + "gridPos": { + "h": 7, + "w": 24, + "x": 0, + "y": 64 + }, + "id": 22, + "links": [], + "options": { + "cellHeight": "sm", + "footer": { + "countRows": false, + "fields": "", + "reducer": [ + "sum" + ], + "show": false + }, + "showHeader": true + }, + "pluginVersion": "10.1.5", + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "exemplar": true, + "expr": "sum(container_memory_working_set_bytes{pod=~\".*external-dns.*\",pod=~\"$pod\",container!=\"\", image!=\"\"}) by (pod)", + "format": "table", + "instant": true, + "interval": "", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "datasource": { + "uid": "$datasource" + }, + "exemplar": true, + "expr": "sum(kube_pod_container_resource_requests{pod=~\".*external-dns.*\",pod=~\"$pod\",resource=\"memory\"}) by (pod)", + "format": "table", + "instant": true, + "interval": "", + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "datasource": { + "uid": "$datasource" + }, + "exemplar": true, + "expr": "sum(container_memory_working_set_bytes{pod=~\".*external-dns.*\",pod=~\"$pod\",container!=\"\", image!=\"\"}) by (pod) / sum(kube_pod_container_resource_requests{pod=~\".*external-dns.*\",pod=~\"$pod\",resource=\"memory\"}) by (pod)", + "format": "table", + "instant": true, + "interval": "", + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "datasource": { + "uid": "$datasource" + }, + "exemplar": true, + "expr": "sum(kube_pod_container_resource_limits{pod=~\".*external-dns.*\",pod=~\"$pod\", resource=\"memory\"}) by (pod)", + "format": "table", + "instant": true, + "interval": "", + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "datasource": { + "uid": "$datasource" + }, + "exemplar": true, + "expr": "sum(container_memory_working_set_bytes{pod=~\".*external-dns.*\",pod=~\"$pod\",container!=\"\", image!=\"\"}) by (pod) / sum(kube_pod_container_resource_limits{pod=~\".*external-dns.*\",pod=~\"$pod\",resource=\"memory\"}) by (pod)", + "format": "table", + "instant": true, + "interval": "", + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "datasource": { + "uid": "$datasource" + }, + "exemplar": true, + "expr": "sum(container_memory_rss{pod=~\".*external-dns.*\",pod=~\"$pod\",container!=\"\"}) by (pod)", + "format": "table", + "instant": true, + "interval": "", + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + }, + { + "datasource": { + "uid": "$datasource" + }, + "exemplar": true, + "expr": "sum(container_memory_cache{pod=~\".*external-dns.*\",pod=~\"$pod\",container!=\"\"}) by (pod)", + "format": "table", + "instant": true, + "interval": "", + "intervalFactor": 2, + "legendFormat": "", + "refId": "G", + "step": 10 + }, + { + "datasource": { + "uid": "$datasource" + }, + "exemplar": true, + "expr": "sum(container_memory_swap{pod=~\".*external-dns.*\",pod=~\"$pod\",container!=\"\"}) by (pod)", + "format": "table", + "instant": true, + "interval": "", + "intervalFactor": 2, + "legendFormat": "", + "refId": "H", + "step": 10 + } + ], + "title": "Memory Quota", + "transformations": [ + { + "id": "merge", + "options": { + "reducers": [] + } + } + ], + "type": "table" + } + ], + "refresh": "", + "schemaVersion": 38, + "style": "dark", + "tags": [ + "external-dns", + "dns" + ], + "templating": { + "list": [ + { + "current": { + "selected": false, + "text": "default", + "value": "default" + }, + "hide": 2, + "includeAll": false, + "label": "Datasource", + "multi": false, + "name": "datasource", + "options": [], + "query": "prometheus", + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "type": "datasource" + }, + { + "current": {}, + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "definition": "label_values(kube_pod_info{pod=~\".*external-dns.*\"}, pod)", + "hide": 0, + "includeAll": true, + "label": "pod", + "multi": false, + "name": "pod", + "options": [], + "query": { + "query": "label_values(kube_pod_info{pod=~\".*external-dns.*\"}, pod)", + "refId": "StandardVariableQuery" + }, + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 0, + "type": "query" + } + ] + }, + "time": { + "from": "now-24h", + "to": "now" + }, + "timepicker": {}, + "timezone": "utc", + "title": "External DNS", + "uid": "eea5u_I7z", + "version": 19, + "weekStart": "" + } +--- +apiVersion: v1 +kind: ConfigMap +metadata: + name: dashboard-ingress-nginx-controller + namespace: monitoring + labels: + grafana_dashboard: "1" +data: + ingress-nginx-controller.json: | + { + "__inputs": [ + { + "name": "DS_PROMETHEUS", + "label": "Prometheus", + "description": "", + "type": "datasource", + "pluginId": "prometheus", + "pluginName": "Prometheus" + } + ], + "__requires": [ + { + "type": "grafana", + "id": "grafana", + "name": "Grafana", + "version": "5.2.1" + }, + { + "type": "datasource", + "id": "prometheus", + "name": "Prometheus", + "version": "5.0.0" + }, + { + "type": "panel", + "id": "singlestat", + "name": "Singlestat", + "version": "5.0.0" + } + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "type": "dashboard" + }, + { + "datasource": "${DS_PROMETHEUS}", + "enable": true, + "expr": "sum(changes(nginx_ingress_controller_config_last_reload_successful_timestamp_seconds{instance!=\"unknown\",controller_class=~\"$controller_class\",namespace=~\"$namespace\"}[30s])) by (controller_class)", + "hide": false, + "iconColor": "rgba(255, 96, 96, 1)", + "limit": 100, + "name": "Config Reloads", + "showIn": 0, + "step": "30s", + "tagKeys": "controller_class", + "tags": [], + "titleFormat": "Config Reloaded", + "type": "tags" + } + ] + }, + "editable": true, + "gnetId": 9614, + "graphTooltip": 0, + "iteration": 1534359654832, + "links": [], + "panels": [ + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "datasource": "${DS_PROMETHEUS}", + "format": "ops", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 3, + "w": 6, + "x": 0, + "y": 0 + }, + "id": 20, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": true, + "lineColor": "rgb(31, 120, 193)", + "show": true + }, + "tableColumn": "", + "targets": [ + { + "expr": "round(sum(irate(nginx_ingress_controller_requests{controller_pod=~\"$controller\",controller_class=~\"$controller_class\",namespace=~\"$namespace\"}[2m])), 0.001)", + "format": "time_series", + "intervalFactor": 1, + "refId": "A", + "step": 4 + } + ], + "thresholds": "", + "title": "Controller Request Volume", + "transparent": false, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "avg" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "datasource": "${DS_PROMETHEUS}", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 3, + "w": 6, + "x": 6, + "y": 0 + }, + "id": 82, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": true, + "lineColor": "rgb(31, 120, 193)", + "show": true + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(avg_over_time(nginx_ingress_controller_nginx_process_connections{controller_pod=~\"$controller\",controller_class=~\"$controller_class\",controller_namespace=~\"$namespace\"}[2m]))", + "format": "time_series", + "instant": false, + "intervalFactor": 1, + "refId": "A", + "step": 4 + } + ], + "thresholds": "", + "title": "Controller Connections", + "transparent": false, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "avg" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "datasource": "${DS_PROMETHEUS}", + "format": "percentunit", + "gauge": { + "maxValue": 100, + "minValue": 80, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": false + }, + "gridPos": { + "h": 3, + "w": 6, + "x": 12, + "y": 0 + }, + "id": 21, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": true, + "lineColor": "rgb(31, 120, 193)", + "show": true + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(rate(nginx_ingress_controller_requests{controller_pod=~\"$controller\",controller_class=~\"$controller_class\",namespace=~\"$namespace\",status!~\"[4-5].*\"}[2m])) / sum(rate(nginx_ingress_controller_requests{controller_pod=~\"$controller\",controller_class=~\"$controller_class\",namespace=~\"$namespace\"}[2m]))", + "format": "time_series", + "intervalFactor": 1, + "refId": "A", + "step": 4 + } + ], + "thresholds": "95, 99, 99.5", + "title": "Controller Success Rate (non-4|5xx responses)", + "transparent": false, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "avg" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "datasource": "${DS_PROMETHEUS}", + "decimals": 0, + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 3, + "w": 3, + "x": 18, + "y": 0 + }, + "id": 81, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": true, + "lineColor": "rgb(31, 120, 193)", + "show": true + }, + "tableColumn": "", + "targets": [ + { + "expr": "avg(nginx_ingress_controller_success{controller_pod=~\"$controller\",controller_class=~\"$controller_class\",controller_namespace=~\"$namespace\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 1, + "refId": "A", + "step": 4 + } + ], + "thresholds": "", + "title": "Config Reloads", + "transparent": false, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "avg" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "datasource": "${DS_PROMETHEUS}", + "decimals": 0, + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 3, + "w": 3, + "x": 21, + "y": 0 + }, + "id": 83, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": true, + "lineColor": "rgb(31, 120, 193)", + "show": true + }, + "tableColumn": "", + "targets": [ + { + "expr": "count(nginx_ingress_controller_config_last_reload_successful{controller_pod=~\"$controller\",controller_namespace=~\"$namespace\"} == 0)", + "format": "time_series", + "instant": true, + "intervalFactor": 1, + "refId": "A", + "step": 4 + } + ], + "thresholds": "", + "title": "Last Config Failed", + "transparent": false, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "avg" + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "decimals": 2, + "editable": true, + "error": false, + "fill": 1, + "grid": {}, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 3 + }, + "height": "200px", + "id": 86, + "isNew": true, + "legend": { + "alignAsTable": true, + "avg": true, + "current": false, + "hideEmpty": false, + "hideZero": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": 300, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "repeatDirection": "h", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "round(sum(irate(nginx_ingress_controller_requests{controller_pod=~\"$controller\",controller_class=~\"$controller_class\",controller_namespace=~\"$namespace\",ingress=~\"$ingress\"}[2m])) by (ingress), 0.001)", + "format": "time_series", + "hide": false, + "instant": false, + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{ ingress }}", + "metric": "network", + "refId": "A", + "step": 10 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Ingress Request Volume", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 2, + "value_type": "cumulative" + }, + "transparent": false, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": { + "max - istio-proxy": "#890f02", + "max - master": "#bf1b00", + "max - prometheus": "#bf1b00" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "decimals": 2, + "editable": false, + "error": false, + "fill": 0, + "grid": {}, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 3 + }, + "id": 87, + "isNew": true, + "legend": { + "alignAsTable": true, + "avg": true, + "current": false, + "hideEmpty": true, + "hideZero": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": 300, + "sort": "avg", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(nginx_ingress_controller_requests{controller_pod=~\"$controller\",controller_class=~\"$controller_class\",namespace=~\"$namespace\",ingress=~\"$ingress\",status!~\"[4-5].*\"}[2m])) by (ingress) / sum(rate(nginx_ingress_controller_requests{controller_pod=~\"$controller\",controller_class=~\"$controller_class\",namespace=~\"$namespace\",ingress=~\"$ingress\"}[2m])) by (ingress)", + "format": "time_series", + "instant": false, + "interval": "10s", + "intervalFactor": 1, + "legendFormat": "{{ ingress }}", + "metric": "container_memory_usage:sort_desc", + "refId": "A", + "step": 10 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Ingress Success Rate (non-4|5xx responses)", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 1, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "decimals": 2, + "editable": true, + "error": false, + "fill": 1, + "grid": {}, + "gridPos": { + "h": 6, + "w": 8, + "x": 0, + "y": 10 + }, + "height": "200px", + "id": 32, + "isNew": true, + "legend": { + "alignAsTable": false, + "avg": true, + "current": true, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": 200, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum (irate (nginx_ingress_controller_request_size_sum{controller_pod=~\"$controller\",controller_class=~\"$controller_class\",controller_namespace=~\"$namespace\"}[2m]))", + "format": "time_series", + "instant": false, + "interval": "10s", + "intervalFactor": 1, + "legendFormat": "Received", + "metric": "network", + "refId": "A", + "step": 10 + }, + { + "expr": "- sum (irate (nginx_ingress_controller_response_size_sum{controller_pod=~\"$controller\",controller_class=~\"$controller_class\",controller_namespace=~\"$namespace\"}[2m]))", + "format": "time_series", + "hide": false, + "interval": "10s", + "intervalFactor": 1, + "legendFormat": "Sent", + "metric": "network", + "refId": "B", + "step": 10 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Network I/O pressure", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 0, + "value_type": "cumulative" + }, + "transparent": false, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": { + "max - istio-proxy": "#890f02", + "max - master": "#bf1b00", + "max - prometheus": "#bf1b00" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "decimals": 2, + "editable": false, + "error": false, + "fill": 0, + "grid": {}, + "gridPos": { + "h": 6, + "w": 8, + "x": 8, + "y": 10 + }, + "id": 77, + "isNew": true, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": 200, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "avg(nginx_ingress_controller_nginx_process_resident_memory_bytes{controller_pod=~\"$controller\",controller_class=~\"$controller_class\",controller_namespace=~\"$namespace\"}) ", + "format": "time_series", + "instant": false, + "interval": "10s", + "intervalFactor": 1, + "legendFormat": "nginx", + "metric": "container_memory_usage:sort_desc", + "refId": "A", + "step": 10 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Average Memory Usage", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 2, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": { + "max - istio-proxy": "#890f02", + "max - master": "#bf1b00" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "decimals": 3, + "editable": false, + "error": false, + "fill": 0, + "grid": {}, + "gridPos": { + "h": 6, + "w": 8, + "x": 16, + "y": 10 + }, + "height": "", + "id": 79, + "isNew": true, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sort": null, + "sortDesc": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum (rate (nginx_ingress_controller_nginx_process_cpu_seconds_total{controller_pod=~\"$controller\",controller_class=~\"$controller_class\",controller_namespace=~\"$namespace\"}[2m])) ", + "format": "time_series", + "interval": "10s", + "intervalFactor": 1, + "legendFormat": "nginx", + "metric": "container_cpu", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + { + "colorMode": "critical", + "fill": true, + "line": true, + "op": "gt" + } + ], + "timeFrom": null, + "timeShift": null, + "title": "Average CPU Usage", + "tooltip": { + "msResolution": true, + "shared": true, + "sort": 2, + "value_type": "cumulative" + }, + "transparent": false, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "none", + "label": "cores", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "columns": [], + "datasource": "${DS_PROMETHEUS}", + "fontSize": "100%", + "gridPos": { + "h": 8, + "w": 24, + "x": 0, + "y": 16 + }, + "hideTimeOverride": false, + "id": 75, + "links": [], + "pageSize": 7, + "repeat": null, + "repeatDirection": "h", + "scroll": true, + "showHeader": true, + "sort": { + "col": 1, + "desc": true + }, + "styles": [ + { + "alias": "Ingress", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "ingress", + "preserveFormat": false, + "sanitize": false, + "thresholds": [], + "type": "string", + "unit": "short" + }, + { + "alias": "Requests", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "Value #A", + "thresholds": [ + "" + ], + "type": "number", + "unit": "ops" + }, + { + "alias": "Errors", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "Value #B", + "thresholds": [], + "type": "number", + "unit": "ops" + }, + { + "alias": "P50 Latency", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 0, + "link": false, + "pattern": "Value #C", + "thresholds": [], + "type": "number", + "unit": "dtdurations" + }, + { + "alias": "P90 Latency", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 0, + "pattern": "Value #D", + "thresholds": [], + "type": "number", + "unit": "dtdurations" + }, + { + "alias": "P99 Latency", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 0, + "pattern": "Value #E", + "thresholds": [], + "type": "number", + "unit": "dtdurations" + }, + { + "alias": "IN", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "Value #F", + "thresholds": [ + "" + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "Time", + "thresholds": [], + "type": "hidden", + "unit": "short" + }, + { + "alias": "OUT", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "Value #G", + "thresholds": [], + "type": "number", + "unit": "Bps" + } + ], + "targets": [ + { + "expr": "histogram_quantile(0.50, sum(rate(nginx_ingress_controller_request_duration_seconds_bucket{ingress!=\"\",controller_pod=~\"$controller\",controller_class=~\"$controller_class\",controller_namespace=~\"$namespace\",ingress=~\"$ingress\"}[2m])) by (le, ingress))", + "format": "table", + "hide": false, + "instant": true, + "intervalFactor": 1, + "legendFormat": "{{ ingress }}", + "refId": "C" + }, + { + "expr": "histogram_quantile(0.90, sum(rate(nginx_ingress_controller_request_duration_seconds_bucket{ingress!=\"\",controller_pod=~\"$controller\",controller_class=~\"$controller_class\",controller_namespace=~\"$namespace\",ingress=~\"$ingress\"}[2m])) by (le, ingress))", + "format": "table", + "hide": false, + "instant": true, + "intervalFactor": 1, + "legendFormat": "{{ ingress }}", + "refId": "D" + }, + { + "expr": "histogram_quantile(0.99, sum(rate(nginx_ingress_controller_request_duration_seconds_bucket{ingress!=\"\",controller_pod=~\"$controller\",controller_class=~\"$controller_class\",controller_namespace=~\"$namespace\",ingress=~\"$ingress\"}[2m])) by (le, ingress))", + "format": "table", + "hide": false, + "instant": true, + "intervalFactor": 1, + "legendFormat": "{{ destination_service }}", + "refId": "E" + }, + { + "expr": "sum(irate(nginx_ingress_controller_request_size_sum{ingress!=\"\",controller_pod=~\"$controller\",controller_class=~\"$controller_class\",controller_namespace=~\"$namespace\",ingress=~\"$ingress\"}[2m])) by (ingress)", + "format": "table", + "hide": false, + "instant": true, + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{ ingress }}", + "refId": "F" + }, + { + "expr": "sum(irate(nginx_ingress_controller_response_size_sum{ingress!=\"\",controller_pod=~\"$controller\",controller_class=~\"$controller_class\",controller_namespace=~\"$namespace\",ingress=~\"$ingress\"}[2m])) by (ingress)", + "format": "table", + "instant": true, + "intervalFactor": 1, + "legendFormat": "{{ ingress }}", + "refId": "G" + } + ], + "timeFrom": null, + "title": "Ingress Percentile Response Times and Transfer Rates", + "transform": "table", + "transparent": false, + "type": "table" + }, + { + "columns": [ + { + "text": "Current", + "value": "current" + } + ], + "datasource": "${DS_PROMETHEUS}", + "fontSize": "100%", + "gridPos": { + "h": 8, + "w": 24, + "x": 0, + "y": 24 + }, + "height": "1024", + "id": 85, + "links": [], + "pageSize": 7, + "scroll": true, + "showHeader": true, + "sort": { + "col": 1, + "desc": false + }, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "date" + }, + { + "alias": "TTL", + "colorMode": "cell", + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 0, + "pattern": "Current", + "thresholds": [ + "0", + "691200" + ], + "type": "number", + "unit": "s" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "decimals": 2, + "pattern": "/.*/", + "thresholds": [], + "type": "number", + "unit": "short" + } + ], + "targets": [ + { + "expr": "avg(nginx_ingress_controller_ssl_expire_time_seconds{kubernetes_pod_name=~\"$controller\",namespace=~\"$namespace\",ingress=~\"$ingress\"}) by (host) - time()", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{ host }}", + "metric": "gke_letsencrypt_cert_expiration", + "refId": "A", + "step": 1 + } + ], + "title": "Ingress Certificate Expiry", + "transform": "timeseries_aggregations", + "type": "table" + } + ], + "refresh": "5s", + "schemaVersion": 16, + "style": "dark", + "tags": [ + "nginx" + ], + "templating": { + "list": [ + { + "allValue": ".*", + "current": { + "text": "All", + "value": "$__all" + }, + "datasource": "${DS_PROMETHEUS}", + "hide": 0, + "includeAll": true, + "label": "Namespace", + "multi": false, + "name": "namespace", + "options": [], + "query": "label_values(nginx_ingress_controller_config_hash, controller_namespace)", + "refresh": 1, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".*", + "current": { + "text": "All", + "value": "$__all" + }, + "datasource": "${DS_PROMETHEUS}", + "hide": 0, + "includeAll": true, + "label": "Controller Class", + "multi": false, + "name": "controller_class", + "options": [], + "query": "label_values(nginx_ingress_controller_config_hash{namespace=~\"$namespace\"}, controller_class) ", + "refresh": 1, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".*", + "current": { + "text": "All", + "value": "$__all" + }, + "datasource": "${DS_PROMETHEUS}", + "hide": 0, + "includeAll": true, + "label": "Controller", + "multi": false, + "name": "controller", + "options": [], + "query": "label_values(nginx_ingress_controller_config_hash{namespace=~\"$namespace\",controller_class=~\"$controller_class\"}, controller_pod) ", + "refresh": 1, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".*", + "current": { + "tags": [], + "text": "All", + "value": "$__all" + }, + "datasource": "${DS_PROMETHEUS}", + "hide": 0, + "includeAll": true, + "label": "Ingress", + "multi": false, + "name": "ingress", + "options": [], + "query": "label_values(nginx_ingress_controller_requests{namespace=~\"$namespace\",controller_class=~\"$controller_class\",controller=~\"$controller\"}, ingress) ", + "refresh": 1, + "regex": "", + "sort": 2, + "tagValuesQuery": "", + "tags": [], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "2m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "browser", + "title": "NGINX Ingress controller", + "uid": "nginx", + "version": 1, + "description": "Ingress-nginx supports a rich collection of prometheus metrics. If you have prometheus and grafana installed on your cluster then prometheus will already be scraping this data due to the scrape annotation on the deployment." } \ No newline at end of file diff --git a/cluster/platform/external-dns/servicemonitor.yaml b/cluster/platform/external-dns/servicemonitor.yaml new file mode 100644 index 0000000..d7c03d6 --- /dev/null +++ b/cluster/platform/external-dns/servicemonitor.yaml @@ -0,0 +1,36 @@ +# ------------------------------------------------------------------------------ +# External-DNS Metrics - ServiceMonitor +# +# Configures Prometheus Operator to scrape External-DNS metrics +# +# Scrape interval: 30s +# Endpoint: /metrics on port 7979 +# Metrics namespace: externaldns_* (externaldns_registry_endpoints_total, etc.) +# ------------------------------------------------------------------------------ +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: external-dns-metrics + namespace: external-dns + labels: + app.kubernetes.io/name: external-dns + app.kubernetes.io/component: metrics + # Label selector for kube-prometheus-stack discovery + release: monitoring +spec: + # Select the external-dns service + selector: + matchLabels: + app.kubernetes.io/name: external-dns + + # Namespace selector + namespaceSelector: + matchNames: + - external-dns + + # Scrape endpoint configuration + endpoints: + - port: http + interval: 30s + scrapeTimeout: 10s + path: /metrics diff --git a/cluster/platform/harbor/servicemonitor.yaml b/cluster/platform/harbor/servicemonitor.yaml new file mode 100644 index 0000000..c1e74a1 --- /dev/null +++ b/cluster/platform/harbor/servicemonitor.yaml @@ -0,0 +1,49 @@ +# ------------------------------------------------------------------------------ +# Harbor Metrics - ServiceMonitor +# +# Configures Prometheus Operator to scrape Harbor metrics +# +# Scrape interval: 30s +# Components scraped: +# - harbor-core: Core service HTTP metrics +# - harbor-registry: Registry-specific metrics +# - harbor-jobservice: Job and vulnerability scan metrics +# - harbor-exporter: Harbor metrics exporter +# Metrics namespace: harbor_* (harbor_core_*, harbor_project_*, etc.) +# ------------------------------------------------------------------------------ +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: harbor-metrics + namespace: harbor + labels: + app: harbor + app.kubernetes.io/name: harbor + app.kubernetes.io/component: metrics + # Label selector for kube-prometheus-stack discovery + release: monitoring +spec: + # Select Harbor services with metrics endpoints + selector: + matchLabels: + app: harbor + + # Namespace selector + namespaceSelector: + matchNames: + - harbor + + # Scrape endpoint configuration + endpoints: + # Harbor Core - main API and web UI metrics + - port: http-metrics + interval: 30s + scrapeTimeout: 10s + path: /metrics + relabelings: + - sourceLabels: [__meta_kubernetes_service_label_component] + targetLabel: component + action: replace + - sourceLabels: [__meta_kubernetes_service_name] + targetLabel: service + action: replace diff --git a/cluster/platform/ingress-nginx/servicemonitor.yaml b/cluster/platform/ingress-nginx/servicemonitor.yaml new file mode 100644 index 0000000..6abb8da --- /dev/null +++ b/cluster/platform/ingress-nginx/servicemonitor.yaml @@ -0,0 +1,37 @@ +# ------------------------------------------------------------------------------ +# Ingress-NGINX Controller Metrics - ServiceMonitor +# +# Configures Prometheus Operator to scrape Ingress-NGINX Controller metrics +# +# Scrape interval: 30s +# Endpoint: /metrics on port 10254 +# Metrics namespace: nginx_ingress_* (nginx_ingress_controller_requests, etc.) +# ------------------------------------------------------------------------------ +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: ingress-nginx-metrics + namespace: ingress-nginx + labels: + app.kubernetes.io/name: ingress-nginx + app.kubernetes.io/component: metrics + # Label selector for kube-prometheus-stack discovery + release: monitoring +spec: + # Select the ingress-nginx-controller-metrics service + selector: + matchLabels: + app.kubernetes.io/name: ingress-nginx + app.kubernetes.io/component: controller + + # Namespace selector + namespaceSelector: + matchNames: + - ingress-nginx + + # Scrape endpoint configuration + endpoints: + - port: metrics + interval: 30s + scrapeTimeout: 10s + path: /metrics