{ "annotations": { "list": [ { "builtIn": 1, "datasource": { "type": "grafana", "uid": "-- Grafana --" }, "enable": true, "hide": true, "iconColor": "rgba(0, 211, 255, 1)", "name": "Annotations & Alerts", "type": "dashboard" } ] }, "description": "Infrastructure health across Kubernetes nodes and PVCs, using kube-state-metrics and node-exporter.", "editable": true, "fiscalYearStartMonth": 0, "graphTooltip": 1, "id": null, "liveNow": false, "panels": [ { "datasource": { "type": "prometheus", "uid": "${datasource}" }, "description": "Node CPU utilization percentage per host.", "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { "drawStyle": "line", "fillOpacity": 15, "gradientMode": "opacity", "lineInterpolation": "smooth", "lineWidth": 2, "pointSize": 5, "showPoints": "never", "spanNulls": true }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "orange", "value": 75 }, { "color": "red", "value": 90 } ] }, "unit": "percent" } }, "gridPos": { "h": 8, "w": 12, "x": 0, "y": 0 }, "id": 1, "options": { "legend": { "calcs": ["mean", "max"], "displayMode": "table", "placement": "right", "showLegend": true }, "tooltip": { "mode": "multi", "sort": "desc" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "${datasource}" }, "editorMode": "code", "expr": "100 - (avg by (instance) (rate(node_cpu_seconds_total{mode=\"idle\",instance=~\"$node\"}[5m])) * 100)", "legendFormat": "{{instance}}", "range": true, "refId": "A" } ], "title": "Node CPU Utilization", "type": "timeseries" }, { "datasource": { "type": "prometheus", "uid": "${datasource}" }, "description": "Node memory usage percentage (1 - MemAvailable/MemTotal).", "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { "drawStyle": "line", "fillOpacity": 15, "gradientMode": "opacity", "lineInterpolation": "smooth", "lineWidth": 2, "pointSize": 5, "showPoints": "never", "spanNulls": true }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "orange", "value": 80 }, { "color": "red", "value": 95 } ] }, "unit": "percent" } }, "gridPos": { "h": 8, "w": 12, "x": 12, "y": 0 }, "id": 2, "options": { "legend": { "calcs": ["mean", "max"], "displayMode": "table", "placement": "right", "showLegend": true }, "tooltip": { "mode": "multi", "sort": "desc" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "${datasource}" }, "editorMode": "code", "expr": "100 * (1 - node_memory_MemAvailable_bytes{instance=~\"$node\"} / node_memory_MemTotal_bytes{instance=~\"$node\"})", "legendFormat": "{{instance}}", "range": true, "refId": "A" } ], "title": "Node Memory Usage", "type": "timeseries" }, { "datasource": { "type": "prometheus", "uid": "${datasource}" }, "description": "Filesystem disk usage per mount point.", "fieldConfig": { "defaults": { "color": { "mode": "thresholds" }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "orange", "value": 75 }, { "color": "red", "value": 90 } ] }, "unit": "percent" } }, "gridPos": { "h": 8, "w": 12, "x": 0, "y": 8 }, "id": 3, "options": { "displayMode": "gradient", "maxVizHeight": 300, "minVizHeight": 10, "minVizWidth": 0, "namePlacement": "auto", "orientation": "horizontal", "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false }, "showUnfilled": true, "sizing": "auto", "valueMode": "color" }, "pluginVersion": "10.2.0", "targets": [ { "datasource": { "type": "prometheus", "uid": "${datasource}" }, "editorMode": "code", "expr": "100 * (1 - node_filesystem_avail_bytes{fstype!~\"tmpfs|overlay|squashfs\",instance=~\"$node\"} / node_filesystem_size_bytes{fstype!~\"tmpfs|overlay|squashfs\",instance=~\"$node\"})", "legendFormat": "{{instance}} {{mountpoint}}", "range": true, "refId": "A" } ], "title": "Filesystem Usage", "type": "bargauge" }, { "datasource": { "type": "prometheus", "uid": "${datasource}" }, "description": "Pod count per namespace, from kube-state-metrics.", "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { "drawStyle": "line", "fillOpacity": 25, "gradientMode": "opacity", "lineInterpolation": "stepAfter", "lineWidth": 2, "pointSize": 5, "showPoints": "never", "spanNulls": true, "stacking": { "group": "A", "mode": "normal" } }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null } ] }, "unit": "short" } }, "gridPos": { "h": 8, "w": 12, "x": 12, "y": 8 }, "id": 4, "options": { "legend": { "calcs": ["mean", "max"], "displayMode": "table", "placement": "right", "showLegend": true }, "tooltip": { "mode": "multi", "sort": "desc" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "${datasource}" }, "editorMode": "code", "expr": "sum by (namespace) (kube_pod_status_phase{namespace=~\"$namespace\",phase=\"Running\"})", "legendFormat": "{{namespace}}", "range": true, "refId": "A" } ], "title": "Running Pod Count by Namespace", "type": "timeseries" }, { "datasource": { "type": "prometheus", "uid": "${datasource}" }, "description": "Container restart count (rate over 15m) indicates crash loops.", "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { "drawStyle": "bars", "fillOpacity": 80, "gradientMode": "none", "lineWidth": 1, "pointSize": 5, "showPoints": "never", "spanNulls": false }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "red", "value": 1 } ] }, "unit": "short" } }, "gridPos": { "h": 8, "w": 12, "x": 0, "y": 16 }, "id": 5, "options": { "legend": { "calcs": ["sum"], "displayMode": "table", "placement": "right", "showLegend": true }, "tooltip": { "mode": "multi", "sort": "desc" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "${datasource}" }, "editorMode": "code", "expr": "sum by (namespace, pod) (increase(kube_pod_container_status_restarts_total{namespace=~\"$namespace\"}[15m]))", "legendFormat": "{{namespace}}/{{pod}}", "range": true, "refId": "A" } ], "title": "Container Restarts (15m)", "type": "timeseries" }, { "datasource": { "type": "prometheus", "uid": "${datasource}" }, "description": "PersistentVolumeClaim fullness percentage.", "fieldConfig": { "defaults": { "color": { "mode": "thresholds" }, "mappings": [], "max": 100, "min": 0, "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "orange", "value": 75 }, { "color": "red", "value": 90 } ] }, "unit": "percent" } }, "gridPos": { "h": 8, "w": 12, "x": 12, "y": 16 }, "id": 6, "options": { "minVizHeight": 75, "minVizWidth": 75, "orientation": "auto", "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false }, "showThresholdLabels": false, "showThresholdMarkers": true, "sizing": "auto" }, "pluginVersion": "10.2.0", "targets": [ { "datasource": { "type": "prometheus", "uid": "${datasource}" }, "editorMode": "code", "expr": "100 * (kubelet_volume_stats_used_bytes{namespace=~\"$namespace\"} / kubelet_volume_stats_capacity_bytes{namespace=~\"$namespace\"})", "legendFormat": "{{namespace}}/{{persistentvolumeclaim}}", "range": true, "refId": "A" } ], "title": "PVC Usage", "type": "gauge" }, { "datasource": { "type": "prometheus", "uid": "${datasource}" }, "description": "Network receive bytes per second by node interface.", "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { "drawStyle": "line", "fillOpacity": 10, "gradientMode": "opacity", "lineInterpolation": "smooth", "lineWidth": 2, "pointSize": 5, "showPoints": "never", "spanNulls": true }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null } ] }, "unit": "Bps" } }, "gridPos": { "h": 8, "w": 24, "x": 0, "y": 24 }, "id": 7, "options": { "legend": { "calcs": ["mean", "max"], "displayMode": "table", "placement": "right", "showLegend": true }, "tooltip": { "mode": "multi", "sort": "desc" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "${datasource}" }, "editorMode": "code", "expr": "sum by (instance) (rate(node_network_receive_bytes_total{device!~\"lo|veth.*|docker.*|br-.*\",instance=~\"$node\"}[5m]))", "legendFormat": "{{instance}} rx", "range": true, "refId": "A" }, { "datasource": { "type": "prometheus", "uid": "${datasource}" }, "editorMode": "code", "expr": "sum by (instance) (rate(node_network_transmit_bytes_total{device!~\"lo|veth.*|docker.*|br-.*\",instance=~\"$node\"}[5m]))", "legendFormat": "{{instance}} tx", "range": true, "refId": "B" } ], "title": "Network Throughput", "type": "timeseries" } ], "refresh": "30s", "schemaVersion": 39, "tags": ["oshun", "infrastructure", "kubernetes"], "templating": { "list": [ { "current": { "selected": false, "text": "Prometheus", "value": "prometheus" }, "hide": 0, "includeAll": false, "label": "Datasource", "multi": false, "name": "datasource", "options": [], "query": "prometheus", "refresh": 1, "regex": "", "skipUrlSync": false, "type": "datasource" }, { "allValue": ".+", "current": { "selected": true, "text": ["All"], "value": ["$__all"] }, "datasource": { "type": "prometheus", "uid": "${datasource}" }, "definition": "label_values(node_cpu_seconds_total, instance)", "hide": 0, "includeAll": true, "label": "Node", "multi": true, "name": "node", "options": [], "query": { "query": "label_values(node_cpu_seconds_total, instance)", "refId": "StandardVariableQuery" }, "refresh": 2, "regex": "", "skipUrlSync": false, "sort": 1, "type": "query" }, { "allValue": ".+", "current": { "selected": true, "text": ["All"], "value": ["$__all"] }, "datasource": { "type": "prometheus", "uid": "${datasource}" }, "definition": "label_values(kube_pod_status_phase, namespace)", "hide": 0, "includeAll": true, "label": "Namespace", "multi": true, "name": "namespace", "options": [], "query": { "query": "label_values(kube_pod_status_phase, namespace)", "refId": "StandardVariableQuery" }, "refresh": 2, "regex": "", "skipUrlSync": false, "sort": 1, "type": "query" } ] }, "time": { "from": "now-6h", "to": "now" }, "timepicker": {}, "timezone": "", "title": "Oshun Infrastructure", "uid": "oshun-infrastructure", "version": 1, "weekStart": "" }