Commit 9304b0d
Changed files (3)
hosts
chaser-pardofelis
grafana
dashboards
hosts/chaser-pardofelis/grafana/dashboards/servers/node-exporter-full-1860_rev41.json
@@ -0,0 +1,16114 @@
+{
+ "__inputs": [
+ {
+ "name": "DS_PROMETHEUS",
+ "label": "prometheus",
+ "description": "",
+ "type": "datasource",
+ "pluginId": "prometheus",
+ "pluginName": "Prometheus"
+ }
+ ],
+ "__elements": {},
+ "__requires": [
+ {
+ "type": "panel",
+ "id": "bargauge",
+ "name": "Bar gauge",
+ "version": ""
+ },
+ {
+ "type": "panel",
+ "id": "gauge",
+ "name": "Gauge",
+ "version": ""
+ },
+ {
+ "type": "grafana",
+ "id": "grafana",
+ "name": "Grafana",
+ "version": "11.6.1"
+ },
+ {
+ "type": "datasource",
+ "id": "prometheus",
+ "name": "Prometheus",
+ "version": "1.0.0"
+ },
+ {
+ "type": "panel",
+ "id": "stat",
+ "name": "Stat",
+ "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",
+ "target": {
+ "limit": 100,
+ "matchAny": false,
+ "tags": [],
+ "type": "dashboard"
+ },
+ "type": "dashboard"
+ }
+ ]
+ },
+ "editable": true,
+ "fiscalYearStartMonth": 0,
+ "graphTooltip": 1,
+ "id": null,
+ "links": [
+ {
+ "icon": "external link",
+ "tags": [],
+ "targetBlank": true,
+ "title": "GitHub",
+ "type": "link",
+ "url": "https://github.com/rfmoz/grafana-dashboards"
+ },
+ {
+ "icon": "external link",
+ "tags": [],
+ "targetBlank": true,
+ "title": "Grafana",
+ "type": "link",
+ "url": "https://grafana.com/grafana/dashboards/1860"
+ }
+ ],
+ "panels": [
+ {
+ "collapsed": false,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 0
+ },
+ "id": 261,
+ "panels": [],
+ "title": "Quick CPU / Mem / Disk",
+ "type": "row"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Resource pressure via PSI",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "decimals": 1,
+ "links": [],
+ "mappings": [],
+ "max": 1,
+ "min": 0,
+ "thresholds": {
+ "mode": "percentage",
+ "steps": [
+ {
+ "color": "green"
+ },
+ {
+ "color": "dark-yellow",
+ "value": 70
+ },
+ {
+ "color": "dark-red",
+ "value": 90
+ }
+ ]
+ },
+ "unit": "percentunit"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 4,
+ "w": 3,
+ "x": 0,
+ "y": 1
+ },
+ "id": 323,
+ "options": {
+ "displayMode": "basic",
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": false
+ },
+ "maxVizHeight": 300,
+ "minVizHeight": 10,
+ "minVizWidth": 0,
+ "namePlacement": "auto",
+ "orientation": "horizontal",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showUnfilled": true,
+ "sizing": "auto",
+ "text": {},
+ "valueMode": "color"
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "exemplar": false,
+ "expr": "irate(node_pressure_cpu_waiting_seconds_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "instant": true,
+ "intervalFactor": 1,
+ "legendFormat": "CPU",
+ "range": false,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "exemplar": false,
+ "expr": "irate(node_pressure_memory_waiting_seconds_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "hide": false,
+ "instant": true,
+ "intervalFactor": 1,
+ "legendFormat": "Mem",
+ "range": false,
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "exemplar": false,
+ "expr": "irate(node_pressure_io_waiting_seconds_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "hide": false,
+ "instant": true,
+ "intervalFactor": 1,
+ "legendFormat": "I/O",
+ "range": false,
+ "refId": "C",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "exemplar": false,
+ "expr": "irate(node_pressure_irq_stalled_seconds_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "hide": false,
+ "instant": true,
+ "intervalFactor": 1,
+ "legendFormat": "Irq",
+ "range": false,
+ "refId": "D",
+ "step": 240
+ }
+ ],
+ "title": "Pressure",
+ "type": "bargauge"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Overall CPU busy percentage (averaged across all cores)",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "decimals": 1,
+ "mappings": [
+ {
+ "options": {
+ "match": "null",
+ "result": {
+ "text": "N/A"
+ }
+ },
+ "type": "special"
+ }
+ ],
+ "max": 100,
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "rgba(50, 172, 45, 0.97)"
+ },
+ {
+ "color": "rgba(237, 129, 40, 0.89)",
+ "value": 85
+ },
+ {
+ "color": "rgba(245, 54, 54, 0.9)",
+ "value": 95
+ }
+ ]
+ },
+ "unit": "percent"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 4,
+ "w": 3,
+ "x": 3,
+ "y": 1
+ },
+ "id": 20,
+ "options": {
+ "minVizHeight": 75,
+ "minVizWidth": 75,
+ "orientation": "auto",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showThresholdLabels": false,
+ "showThresholdMarkers": true,
+ "sizing": "auto"
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "exemplar": false,
+ "expr": "100 * (1 - avg(rate(node_cpu_seconds_total{mode=\"idle\", instance=\"$node\"}[$__rate_interval])))",
+ "hide": false,
+ "instant": true,
+ "intervalFactor": 1,
+ "legendFormat": "",
+ "range": false,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "CPU Busy",
+ "type": "gauge"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "System load over all CPU cores together",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "decimals": 1,
+ "mappings": [
+ {
+ "options": {
+ "match": "null",
+ "result": {
+ "text": "N/A"
+ }
+ },
+ "type": "special"
+ }
+ ],
+ "max": 100,
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "rgba(50, 172, 45, 0.97)"
+ },
+ {
+ "color": "rgba(237, 129, 40, 0.89)",
+ "value": 85
+ },
+ {
+ "color": "rgba(245, 54, 54, 0.9)",
+ "value": 95
+ }
+ ]
+ },
+ "unit": "percent"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 4,
+ "w": 3,
+ "x": 6,
+ "y": 1
+ },
+ "id": 155,
+ "options": {
+ "minVizHeight": 75,
+ "minVizWidth": 75,
+ "orientation": "auto",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showThresholdLabels": false,
+ "showThresholdMarkers": true,
+ "sizing": "auto"
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "exemplar": false,
+ "expr": "scalar(node_load1{instance=\"$node\",job=\"$job\"}) * 100 / count(count(node_cpu_seconds_total{instance=\"$node\",job=\"$job\"}) by (cpu))",
+ "format": "time_series",
+ "hide": false,
+ "instant": true,
+ "intervalFactor": 1,
+ "range": false,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "Sys Load",
+ "type": "gauge"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Real RAM usage excluding cache and reclaimable memory",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "decimals": 1,
+ "mappings": [],
+ "max": 100,
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "rgba(50, 172, 45, 0.97)"
+ },
+ {
+ "color": "rgba(237, 129, 40, 0.89)",
+ "value": 80
+ },
+ {
+ "color": "rgba(245, 54, 54, 0.9)",
+ "value": 90
+ }
+ ]
+ },
+ "unit": "percent"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 4,
+ "w": 3,
+ "x": 9,
+ "y": 1
+ },
+ "id": 16,
+ "options": {
+ "minVizHeight": 75,
+ "minVizWidth": 75,
+ "orientation": "auto",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showThresholdLabels": false,
+ "showThresholdMarkers": true,
+ "sizing": "auto"
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "exemplar": false,
+ "expr": "(1 - (node_memory_MemAvailable_bytes{instance=\"$node\", job=\"$job\"} / node_memory_MemTotal_bytes{instance=\"$node\", job=\"$job\"})) * 100",
+ "format": "time_series",
+ "hide": false,
+ "instant": true,
+ "intervalFactor": 1,
+ "range": false,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "RAM Used",
+ "type": "gauge"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Percentage of swap space currently used by the system",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "decimals": 1,
+ "mappings": [
+ {
+ "options": {
+ "match": "null",
+ "result": {
+ "text": "N/A"
+ }
+ },
+ "type": "special"
+ }
+ ],
+ "max": 100,
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "rgba(50, 172, 45, 0.97)"
+ },
+ {
+ "color": "rgba(237, 129, 40, 0.89)",
+ "value": 10
+ },
+ {
+ "color": "rgba(245, 54, 54, 0.9)",
+ "value": 25
+ }
+ ]
+ },
+ "unit": "percent"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 4,
+ "w": 3,
+ "x": 12,
+ "y": 1
+ },
+ "id": 21,
+ "options": {
+ "minVizHeight": 75,
+ "minVizWidth": 75,
+ "orientation": "auto",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showThresholdLabels": false,
+ "showThresholdMarkers": true,
+ "sizing": "auto"
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "exemplar": false,
+ "expr": "((node_memory_SwapTotal_bytes{instance=\"$node\",job=\"$job\"} - node_memory_SwapFree_bytes{instance=\"$node\",job=\"$job\"}) / (node_memory_SwapTotal_bytes{instance=\"$node\",job=\"$job\"})) * 100",
+ "instant": true,
+ "intervalFactor": 1,
+ "range": false,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "SWAP Used",
+ "type": "gauge"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Used Root FS",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "decimals": 1,
+ "mappings": [
+ {
+ "options": {
+ "match": "null",
+ "result": {
+ "text": "N/A"
+ }
+ },
+ "type": "special"
+ }
+ ],
+ "max": 100,
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "rgba(50, 172, 45, 0.97)"
+ },
+ {
+ "color": "rgba(237, 129, 40, 0.89)",
+ "value": 80
+ },
+ {
+ "color": "rgba(245, 54, 54, 0.9)",
+ "value": 90
+ }
+ ]
+ },
+ "unit": "percent"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 4,
+ "w": 3,
+ "x": 15,
+ "y": 1
+ },
+ "id": 154,
+ "options": {
+ "minVizHeight": 75,
+ "minVizWidth": 75,
+ "orientation": "auto",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showThresholdLabels": false,
+ "showThresholdMarkers": true,
+ "sizing": "auto"
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "exemplar": false,
+ "expr": "(\n (node_filesystem_size_bytes{instance=\"$node\", job=\"$job\", mountpoint=\"/\", fstype!=\"rootfs\"}\n - node_filesystem_avail_bytes{instance=\"$node\", job=\"$job\", mountpoint=\"/\", fstype!=\"rootfs\"})\n / node_filesystem_size_bytes{instance=\"$node\", job=\"$job\", mountpoint=\"/\", fstype!=\"rootfs\"}\n) * 100\n",
+ "format": "time_series",
+ "instant": true,
+ "intervalFactor": 1,
+ "range": false,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "Root FS Used",
+ "type": "gauge"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "mappings": [
+ {
+ "options": {
+ "match": "null",
+ "result": {
+ "text": "N/A"
+ }
+ },
+ "type": "special"
+ }
+ ],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 2,
+ "w": 2,
+ "x": 18,
+ "y": 1
+ },
+ "id": 14,
+ "maxDataPoints": 100,
+ "options": {
+ "colorMode": "none",
+ "graphMode": "none",
+ "justifyMode": "auto",
+ "orientation": "horizontal",
+ "percentChangeColorMode": "standard",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showPercentChange": false,
+ "textMode": "auto",
+ "wideLayout": true
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "exemplar": false,
+ "expr": "count(count(node_cpu_seconds_total{instance=\"$node\",job=\"$job\"}) by (cpu))",
+ "instant": true,
+ "legendFormat": "__auto",
+ "range": false,
+ "refId": "A"
+ }
+ ],
+ "title": "CPU Cores",
+ "type": "stat"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "decimals": 1,
+ "mappings": [
+ {
+ "options": {
+ "match": "null",
+ "result": {
+ "text": "N/A"
+ }
+ },
+ "type": "special"
+ }
+ ],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "bool_yes_no"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 2,
+ "w": 2,
+ "x": 20,
+ "y": 1
+ },
+ "id": 328,
+ "maxDataPoints": 100,
+ "options": {
+ "colorMode": "none",
+ "graphMode": "none",
+ "justifyMode": "auto",
+ "orientation": "horizontal",
+ "percentChangeColorMode": "standard",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showPercentChange": false,
+ "textMode": "auto",
+ "wideLayout": true
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "exemplar": false,
+ "expr": "node_reboot_required{instance=\"$node\",job=\"$job\"}",
+ "instant": true,
+ "intervalFactor": 1,
+ "range": false,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "Reboot Required",
+ "type": "stat"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "decimals": 1,
+ "mappings": [
+ {
+ "options": {
+ "match": "null",
+ "result": {
+ "text": "N/A"
+ }
+ },
+ "type": "special"
+ }
+ ],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "s"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 2,
+ "w": 2,
+ "x": 22,
+ "y": 1
+ },
+ "id": 15,
+ "maxDataPoints": 100,
+ "options": {
+ "colorMode": "none",
+ "graphMode": "none",
+ "justifyMode": "auto",
+ "orientation": "horizontal",
+ "percentChangeColorMode": "standard",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showPercentChange": false,
+ "textMode": "auto",
+ "wideLayout": true
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "exemplar": false,
+ "expr": "node_time_seconds{instance=\"$node\",job=\"$job\"} - node_boot_time_seconds{instance=\"$node\",job=\"$job\"}",
+ "instant": true,
+ "intervalFactor": 1,
+ "range": false,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "Uptime",
+ "type": "stat"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "decimals": 0,
+ "mappings": [
+ {
+ "options": {
+ "match": "null",
+ "result": {
+ "text": "N/A"
+ }
+ },
+ "type": "special"
+ }
+ ],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "rgba(50, 172, 45, 0.97)"
+ },
+ {
+ "color": "rgba(237, 129, 40, 0.89)",
+ "value": 70
+ },
+ {
+ "color": "rgba(245, 54, 54, 0.9)",
+ "value": 90
+ }
+ ]
+ },
+ "unit": "bytes"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 2,
+ "w": 2,
+ "x": 18,
+ "y": 3
+ },
+ "id": 23,
+ "maxDataPoints": 100,
+ "options": {
+ "colorMode": "none",
+ "graphMode": "none",
+ "justifyMode": "auto",
+ "orientation": "horizontal",
+ "percentChangeColorMode": "standard",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showPercentChange": false,
+ "textMode": "auto",
+ "wideLayout": true
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "exemplar": false,
+ "expr": "node_filesystem_size_bytes{instance=\"$node\",job=\"$job\",mountpoint=\"/\",fstype!=\"rootfs\"}",
+ "format": "time_series",
+ "hide": false,
+ "instant": true,
+ "intervalFactor": 1,
+ "range": false,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "RootFS Total",
+ "type": "stat"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "decimals": 0,
+ "mappings": [
+ {
+ "options": {
+ "match": "null",
+ "result": {
+ "text": "N/A"
+ }
+ },
+ "type": "special"
+ }
+ ],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "bytes"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 2,
+ "w": 2,
+ "x": 20,
+ "y": 3
+ },
+ "id": 75,
+ "maxDataPoints": 100,
+ "options": {
+ "colorMode": "none",
+ "graphMode": "none",
+ "justifyMode": "auto",
+ "orientation": "horizontal",
+ "percentChangeColorMode": "standard",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showPercentChange": false,
+ "textMode": "auto",
+ "wideLayout": true
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "exemplar": false,
+ "expr": "node_memory_MemTotal_bytes{instance=\"$node\",job=\"$job\"}",
+ "instant": true,
+ "intervalFactor": 1,
+ "range": false,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "RAM Total",
+ "type": "stat"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "decimals": 0,
+ "mappings": [
+ {
+ "options": {
+ "match": "null",
+ "result": {
+ "text": "N/A"
+ }
+ },
+ "type": "special"
+ }
+ ],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "bytes"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 2,
+ "w": 2,
+ "x": 22,
+ "y": 3
+ },
+ "id": 18,
+ "maxDataPoints": 100,
+ "options": {
+ "colorMode": "none",
+ "graphMode": "none",
+ "justifyMode": "auto",
+ "orientation": "horizontal",
+ "percentChangeColorMode": "standard",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showPercentChange": false,
+ "textMode": "auto",
+ "wideLayout": true
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "exemplar": false,
+ "expr": "node_memory_SwapTotal_bytes{instance=\"$node\",job=\"$job\"}",
+ "instant": true,
+ "intervalFactor": 1,
+ "range": false,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "SWAP Total",
+ "type": "stat"
+ },
+ {
+ "collapsed": false,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 5
+ },
+ "id": 263,
+ "panels": [],
+ "title": "Basic CPU / Mem / Net / Disk",
+ "type": "row"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "CPU time spent busy vs idle, split by activity type",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 40,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "smooth",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "percent"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "percentunit"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Busy Iowait"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#890F02",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Idle"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#052B51",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Busy System"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#EAB839",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Busy User"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#0A437C",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Busy Other"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#6D1F62",
+ "mode": "fixed"
+ }
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 7,
+ "w": 12,
+ "x": 0,
+ "y": 6
+ },
+ "id": 77,
+ "options": {
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true,
+ "width": 250
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "desc"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "exemplar": false,
+ "expr": "sum(irate(node_cpu_seconds_total{instance=\"$node\",job=\"$job\", mode=\"system\"}[$__rate_interval])) / scalar(count(count(node_cpu_seconds_total{instance=\"$node\",job=\"$job\"}) by (cpu)))",
+ "format": "time_series",
+ "hide": false,
+ "instant": false,
+ "intervalFactor": 1,
+ "legendFormat": "Busy System",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "sum(irate(node_cpu_seconds_total{instance=\"$node\",job=\"$job\", mode=\"user\"}[$__rate_interval])) / scalar(count(count(node_cpu_seconds_total{instance=\"$node\",job=\"$job\"}) by (cpu)))",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "Busy User",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "sum(irate(node_cpu_seconds_total{instance=\"$node\",job=\"$job\", mode=\"iowait\"}[$__rate_interval])) / scalar(count(count(node_cpu_seconds_total{instance=\"$node\",job=\"$job\"}) by (cpu)))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Busy Iowait",
+ "range": true,
+ "refId": "C",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "sum(irate(node_cpu_seconds_total{instance=\"$node\",job=\"$job\", mode=~\".*irq\"}[$__rate_interval])) / scalar(count(count(node_cpu_seconds_total{instance=\"$node\",job=\"$job\"}) by (cpu)))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Busy IRQs",
+ "range": true,
+ "refId": "D",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "sum(irate(node_cpu_seconds_total{instance=\"$node\",job=\"$job\", mode!='idle',mode!='user',mode!='system',mode!='iowait',mode!='irq',mode!='softirq'}[$__rate_interval])) / scalar(count(count(node_cpu_seconds_total{instance=\"$node\",job=\"$job\"}) by (cpu)))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Busy Other",
+ "range": true,
+ "refId": "E",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "sum(irate(node_cpu_seconds_total{instance=\"$node\",job=\"$job\", mode=\"idle\"}[$__rate_interval])) / scalar(count(count(node_cpu_seconds_total{instance=\"$node\",job=\"$job\"}) by (cpu)))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Idle",
+ "range": true,
+ "refId": "F",
+ "step": 240
+ }
+ ],
+ "title": "CPU Basic",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "RAM and swap usage overview, including caches",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 40,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "normal"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "bytes"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Swap used"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#BF1B00",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Total"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#E0F9D7",
+ "mode": "fixed"
+ }
+ },
+ {
+ "id": "custom.fillOpacity",
+ "value": 0
+ },
+ {
+ "id": "custom.stacking",
+ "value": {
+ "group": false,
+ "mode": "normal"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Cache + Buffer"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#052B51",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Free"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#7EB26D",
+ "mode": "fixed"
+ }
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 7,
+ "w": 12,
+ "x": 12,
+ "y": 6
+ },
+ "id": 78,
+ "options": {
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true,
+ "width": 350
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_memory_MemTotal_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "Total",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_memory_MemTotal_bytes{instance=\"$node\",job=\"$job\"} - node_memory_MemFree_bytes{instance=\"$node\",job=\"$job\"} - (node_memory_Cached_bytes{instance=\"$node\",job=\"$job\"} + node_memory_Buffers_bytes{instance=\"$node\",job=\"$job\"} + node_memory_SReclaimable_bytes{instance=\"$node\",job=\"$job\"})",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "Used",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_memory_Cached_bytes{instance=\"$node\",job=\"$job\"} + node_memory_Buffers_bytes{instance=\"$node\",job=\"$job\"} + node_memory_SReclaimable_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Cache + Buffer",
+ "range": true,
+ "refId": "C",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_memory_MemFree_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Free",
+ "range": true,
+ "refId": "D",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "(node_memory_SwapTotal_bytes{instance=\"$node\",job=\"$job\"} - node_memory_SwapFree_bytes{instance=\"$node\",job=\"$job\"})",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Swap used",
+ "range": true,
+ "refId": "E",
+ "step": 240
+ }
+ ],
+ "title": "Memory Basic",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Per-interface network traffic (receive and transmit) in bits per second",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 40,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "bps"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*Tx.*/"
+ },
+ "properties": [
+ {
+ "id": "custom.transform",
+ "value": "negative-Y"
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 7,
+ "w": 12,
+ "x": 0,
+ "y": 13
+ },
+ "id": 74,
+ "options": {
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "rate(node_network_receive_bytes_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])*8",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Rx {{device}}",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "rate(node_network_transmit_bytes_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])*8",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Tx {{device}} ",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "Network Traffic Basic",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Percentage of filesystem space used for each mounted device",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 40,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "max": 100,
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "percent"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 7,
+ "w": 12,
+ "x": 12,
+ "y": 13
+ },
+ "id": 152,
+ "options": {
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "((node_filesystem_size_bytes{instance=\"$node\", job=\"$job\", device!~\"rootfs\"} - node_filesystem_avail_bytes{instance=\"$node\", job=\"$job\", device!~\"rootfs\"}) / node_filesystem_size_bytes{instance=\"$node\", job=\"$job\", device!~\"rootfs\"}) * 100",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{mountpoint}}",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "Disk Space Used Basic",
+ "type": "timeseries"
+ },
+ {
+ "collapsed": true,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 20
+ },
+ "id": 265,
+ "panels": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "CPU time usage split by state, normalized across all CPU cores",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 70,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "smooth",
+ "lineWidth": 2,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "percent"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "percentunit"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Idle - Waiting for something to happen"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#052B51",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Iowait - Waiting for I/O to complete"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#EAB839",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Irq - Servicing interrupts"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#BF1B00",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Nice - Niced processes executing in user mode"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#C15C17",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Softirq - Servicing softirqs"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#E24D42",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Steal - Time spent in other operating systems when running in a virtualized environment"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#FCE2DE",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "System - Processes executing in kernel mode"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#508642",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "User - Normal processes executing in user mode"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#5195CE",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Guest CPU usage"
+ },
+ "properties": [
+ {
+ "id": "custom.fillOpacity",
+ "value": 0
+ },
+ {
+ "id": "custom.lineStyle",
+ "value": {
+ "dash": [
+ 10,
+ 10
+ ],
+ "fill": "dash"
+ }
+ },
+ {
+ "id": "custom.stacking",
+ "value": {
+ "group": "A",
+ "mode": "none"
+ }
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 12,
+ "w": 12,
+ "x": 0,
+ "y": 21
+ },
+ "id": 3,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true,
+ "width": 250
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "desc"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "sum(irate(node_cpu_seconds_total{mode=\"system\",instance=\"$node\",job=\"$job\"}[$__rate_interval])) / scalar(count(count(node_cpu_seconds_total{instance=\"$node\",job=\"$job\"}) by (cpu)))",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "System - Processes executing in kernel mode",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "sum(irate(node_cpu_seconds_total{mode=\"user\",instance=\"$node\",job=\"$job\"}[$__rate_interval])) / scalar(count(count(node_cpu_seconds_total{instance=\"$node\",job=\"$job\"}) by (cpu)))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "User - Normal processes executing in user mode",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "sum(irate(node_cpu_seconds_total{mode=\"nice\",instance=\"$node\",job=\"$job\"}[$__rate_interval])) / scalar(count(count(node_cpu_seconds_total{instance=\"$node\",job=\"$job\"}) by (cpu)))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Nice - Niced processes executing in user mode",
+ "range": true,
+ "refId": "C",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "sum(irate(node_cpu_seconds_total{mode=\"iowait\",instance=\"$node\",job=\"$job\"}[$__rate_interval])) / scalar(count(count(node_cpu_seconds_total{instance=\"$node\",job=\"$job\"}) by (cpu)))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Iowait - Waiting for I/O to complete",
+ "range": true,
+ "refId": "D",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "sum(irate(node_cpu_seconds_total{mode=\"irq\",instance=\"$node\",job=\"$job\"}[$__rate_interval])) / scalar(count(count(node_cpu_seconds_total{instance=\"$node\",job=\"$job\"}) by (cpu)))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Irq - Servicing interrupts",
+ "range": true,
+ "refId": "E",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "sum(irate(node_cpu_seconds_total{mode=\"softirq\",instance=\"$node\",job=\"$job\"}[$__rate_interval])) / scalar(count(count(node_cpu_seconds_total{instance=\"$node\",job=\"$job\"}) by (cpu)))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Softirq - Servicing softirqs",
+ "range": true,
+ "refId": "F",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "sum(irate(node_cpu_seconds_total{mode=\"steal\",instance=\"$node\",job=\"$job\"}[$__rate_interval])) / scalar(count(count(node_cpu_seconds_total{instance=\"$node\",job=\"$job\"}) by (cpu)))",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Steal - Time spent in other operating systems when running in a virtualized environment",
+ "range": true,
+ "refId": "G",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "sum(irate(node_cpu_seconds_total{mode=\"idle\",instance=\"$node\",job=\"$job\"}[$__rate_interval])) / scalar(count(count(node_cpu_seconds_total{instance=\"$node\",job=\"$job\"}) by (cpu)))",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "Idle - Waiting for something to happen",
+ "range": true,
+ "refId": "H",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "sum by(instance) (irate(node_cpu_guest_seconds_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])) / on(instance) group_left sum by (instance)((irate(node_cpu_seconds_total{instance=\"$node\",job=\"$job\"}[$__rate_interval]))) > 0",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "Guest CPU usage",
+ "range": true,
+ "refId": "I",
+ "step": 240
+ }
+ ],
+ "title": "CPU",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Breakdown of physical memory and swap usage. Hardware-detected memory errors are also displayed",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 40,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "normal"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "bytes"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Apps"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#629E51",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Buffers"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#614D93",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Cache"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#6D1F62",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Cached"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#511749",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Committed"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#508642",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Free"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#0A437C",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Hardware Corrupted - Amount of RAM that the kernel identified as corrupted / not working"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#CFFAFF",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Inactive"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#584477",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "PageTables"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#0A50A1",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Page_Tables"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#0A50A1",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "RAM_Free"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#E0F9D7",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Slab"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#806EB7",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Slab_Cache"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#E0752D",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Swap"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#BF1B00",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Swap - Swap memory usage"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#BF1B00",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Swap_Cache"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#C15C17",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Swap_Free"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#2F575E",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Unused"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#EAB839",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Unused - Free memory unassigned"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#052B51",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*Hardware Corrupted - *./"
+ },
+ "properties": [
+ {
+ "id": "custom.stacking",
+ "value": {
+ "group": false,
+ "mode": "normal"
+ }
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 12,
+ "w": 12,
+ "x": 12,
+ "y": 21
+ },
+ "id": 24,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true,
+ "width": 350
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_memory_MemTotal_bytes{instance=\"$node\",job=\"$job\"} - node_memory_MemFree_bytes{instance=\"$node\",job=\"$job\"} - node_memory_Buffers_bytes{instance=\"$node\",job=\"$job\"} - node_memory_Cached_bytes{instance=\"$node\",job=\"$job\"} - node_memory_Slab_bytes{instance=\"$node\",job=\"$job\"} - node_memory_PageTables_bytes{instance=\"$node\",job=\"$job\"} - node_memory_SwapCached_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "Apps - Memory used by user-space applications",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_memory_PageTables_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "PageTables - Memory used to map between virtual and physical memory addresses",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_memory_SwapCached_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "SwapCache - Memory that keeps track of pages that have been fetched from swap but not yet been modified",
+ "range": true,
+ "refId": "C",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_memory_Slab_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "Slab - Memory used by the kernel to cache data structures for its own use (caches like inode, dentry, etc)",
+ "range": true,
+ "refId": "D",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_memory_Cached_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "Cache - Parked file data (file content) cache",
+ "range": true,
+ "refId": "E",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_memory_Buffers_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "Buffers - Block device (e.g. harddisk) cache",
+ "range": true,
+ "refId": "F",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_memory_MemFree_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "Unused - Free memory unassigned",
+ "range": true,
+ "refId": "G",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "(node_memory_SwapTotal_bytes{instance=\"$node\",job=\"$job\"} - node_memory_SwapFree_bytes{instance=\"$node\",job=\"$job\"})",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "Swap - Swap space used",
+ "range": true,
+ "refId": "H",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_memory_HardwareCorrupted_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "Hardware Corrupted - Amount of RAM that the kernel identified as corrupted / not working",
+ "range": true,
+ "refId": "I",
+ "step": 240
+ }
+ ],
+ "title": "Memory",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Incoming and outgoing network traffic per interface",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "out (-) / in (+)",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 40,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "bps"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*out.*/"
+ },
+ "properties": [
+ {
+ "id": "custom.transform",
+ "value": "negative-Y"
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 12,
+ "w": 12,
+ "x": 0,
+ "y": 303
+ },
+ "id": 84,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "rate(node_network_receive_bytes_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])*8",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} - Rx in",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "rate(node_network_transmit_bytes_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])*8",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} - Tx out",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "Network Traffic",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Network interface utilization as a percentage of its maximum capacity",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "out (-) / in (+)",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 40,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "percentunit"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*out.*/"
+ },
+ "properties": [
+ {
+ "id": "custom.transform",
+ "value": "negative-Y"
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 12,
+ "w": 12,
+ "x": 12,
+ "y": 303
+ },
+ "id": 338,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "(rate(node_network_receive_bytes_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])\n / ignoring(speed) node_network_speed_bytes{instance=\"$node\",job=\"$job\", speed!=\"-1\"}) * 100",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} - Rx in",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "(rate(node_network_transmit_bytes_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])\n / ignoring(speed) node_network_speed_bytes{instance=\"$node\",job=\"$job\", speed!=\"-1\"}) * 100",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} - Tx out",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "Network Saturation",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Disk I/O operations per second for each device",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "read (-) / write (+)",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "iops"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*Read.*/"
+ },
+ "properties": [
+ {
+ "id": "custom.transform",
+ "value": "negative-Y"
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 12,
+ "w": 12,
+ "x": 0,
+ "y": 315
+ },
+ "id": 229,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "single",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "irate(node_disk_reads_completed_total{instance=\"$node\",job=\"$job\",device=~\"$diskdevices\"}[$__rate_interval])",
+ "intervalFactor": 4,
+ "legendFormat": "{{device}} - Read",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_disk_writes_completed_total{instance=\"$node\",job=\"$job\",device=~\"$diskdevices\"}[$__rate_interval])",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} - Write",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "Disk IOps",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Disk I/O throughput per device",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "read (-) / write (+)",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 40,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "Bps"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*Read*./"
+ },
+ "properties": [
+ {
+ "id": "custom.transform",
+ "value": "negative-Y"
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 12,
+ "w": 12,
+ "x": 12,
+ "y": 315
+ },
+ "id": 42,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "irate(node_disk_read_bytes_total{instance=\"$node\",job=\"$job\",device=~\"$diskdevices\"}[$__rate_interval])",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} - Read",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_disk_written_bytes_total{instance=\"$node\",job=\"$job\",device=~\"$diskdevices\"}[$__rate_interval])",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} - Write",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "Disk Throughput",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Amount of available disk space per mounted filesystem, excluding rootfs. Based on block availability to non-root users",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "bytes"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 12,
+ "w": 12,
+ "x": 0,
+ "y": 327
+ },
+ "id": 43,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_filesystem_avail_bytes{instance=\"$node\",job=\"$job\",device!~'rootfs'}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "{{mountpoint}}",
+ "metric": "",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_filesystem_free_bytes{instance=\"$node\",job=\"$job\",device!~'rootfs'}",
+ "format": "time_series",
+ "hide": true,
+ "intervalFactor": 1,
+ "legendFormat": "{{mountpoint}} - Free",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_filesystem_size_bytes{instance=\"$node\",job=\"$job\",device!~'rootfs'}",
+ "format": "time_series",
+ "hide": true,
+ "intervalFactor": 1,
+ "legendFormat": "{{mountpoint}} - Size",
+ "range": true,
+ "refId": "C",
+ "step": 240
+ }
+ ],
+ "title": "Filesystem Space Available",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Disk usage (used = total - available) per mountpoint",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "bytes"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 12,
+ "w": 12,
+ "x": 12,
+ "y": 327
+ },
+ "id": 156,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_filesystem_size_bytes{instance=\"$node\",job=\"$job\",device!~'rootfs'} - node_filesystem_avail_bytes{instance=\"$node\",job=\"$job\",device!~'rootfs'}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{mountpoint}}",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "Filesystem Used",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Percentage of time the disk was actively processing I/O operations",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 40,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "percentunit"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 12,
+ "w": 12,
+ "x": 0,
+ "y": 339
+ },
+ "id": 127,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "irate(node_disk_io_time_seconds_total{instance=\"$node\",job=\"$job\",device=~\"$diskdevices\"} [$__rate_interval])",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}}",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "Disk I/O Utilization",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "How often tasks experience CPU, memory, or I/O delays. “Some” indicates partial slowdown; “Full” indicates all tasks are stalled. Based on Linux PSI metrics:\nhttps://docs.kernel.org/accounting/psi.html",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "some (-) / full (+)",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 10,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "percentunit"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*Some.*/"
+ },
+ "properties": [
+ {
+ "id": "custom.fillOpacity",
+ "value": 0
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*Some.*/"
+ },
+ "properties": [
+ {
+ "id": "custom.transform",
+ "value": "negative-Y"
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 12,
+ "w": 12,
+ "x": 12,
+ "y": 339
+ },
+ "id": 322,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "rate(node_pressure_cpu_waiting_seconds_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "CPU - Some",
+ "range": true,
+ "refId": "CPU some",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "rate(node_pressure_memory_waiting_seconds_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "Memory - Some",
+ "range": true,
+ "refId": "Memory some",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "rate(node_pressure_memory_stalled_seconds_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "Memory - Full",
+ "range": true,
+ "refId": "Memory full",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "rate(node_pressure_io_waiting_seconds_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "I/O - Some",
+ "range": true,
+ "refId": "I/O some",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "rate(node_pressure_io_stalled_seconds_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "I/O - Full",
+ "range": true,
+ "refId": "I/O full",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "rate(node_pressure_irq_stalled_seconds_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "IRQ - Full",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "Pressure Stall Information",
+ "type": "timeseries"
+ }
+ ],
+ "title": "CPU / Memory / Net / Disk",
+ "type": "row"
+ },
+ {
+ "collapsed": true,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 21
+ },
+ "id": 266,
+ "panels": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Displays committed memory usage versus the system's commit limit. Exceeding the limit is allowed under Linux overcommit policies but may increase OOM risks under high load",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "bytes"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*CommitLimit - *./"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#BF1B00",
+ "mode": "fixed"
+ }
+ },
+ {
+ "id": "custom.fillOpacity",
+ "value": 0
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 602
+ },
+ "id": 135,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true,
+ "width": 350
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_memory_Committed_AS_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Committed_AS – Memory promised to processes (not necessarily used)",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_memory_CommitLimit_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "CommitLimit - Max allowable committed memory",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "Memory Committed",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Memory currently dirty (modified but not yet written to disk), being actively written back, or held by writeback buffers. High dirty or writeback memory may indicate disk I/O pressure or delayed flushing",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "bytes"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 602
+ },
+ "id": 130,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_memory_Writeback_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Writeback – Memory currently being flushed to disk",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_memory_WritebackTmp_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "WritebackTmp – FUSE temporary writeback buffers",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_memory_Dirty_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Dirty – Memory marked dirty (pending write to disk)",
+ "range": true,
+ "refId": "C",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_memory_NFS_Unstable_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "NFS Unstable – Pages sent to NFS server, awaiting storage commit",
+ "range": true,
+ "refId": "D",
+ "step": 240
+ }
+ ],
+ "title": "Memory Writeback and Dirty",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Kernel slab memory usage, separated into reclaimable and non-reclaimable categories. Reclaimable memory can be freed under memory pressure (e.g., caches), while unreclaimable memory is locked by the kernel for core functions",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "normal"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "bytes"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 802
+ },
+ "id": 131,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_memory_SUnreclaim_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "SUnreclaim – Non-reclaimable slab memory (kernel objects)",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_memory_SReclaimable_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "SReclaimable – Potentially reclaimable slab memory (e.g., inode cache)",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "Memory Slab",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Memory used for mapped files (such as libraries) and shared memory (shmem and tmpfs), including variants backed by huge pages",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "bytes"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 802
+ },
+ "id": 138,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true,
+ "width": 350
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_memory_Mapped_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Mapped – Memory mapped from files (e.g., libraries, mmap)",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_memory_Shmem_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Shmem – Shared memory used by processes and tmpfs",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_memory_ShmemHugePages_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "ShmemHugePages – Shared memory (shmem/tmpfs) allocated with HugePages",
+ "range": true,
+ "refId": "C",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_memory_ShmemPmdMapped_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "PMD Mapped – Shmem/tmpfs backed by Transparent HugePages (PMD)",
+ "range": true,
+ "refId": "D",
+ "step": 240
+ }
+ ],
+ "title": "Memory Shared and Mapped",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Proportion of memory pages in the kernel's active and inactive LRU lists relative to total RAM. Active pages have been recently used, while inactive pages are less recently accessed but still resident in memory",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "normal"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "percentunit"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*Active.*/"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "green",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*Inactive.*/"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "dark-blue",
+ "mode": "fixed"
+ }
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 812
+ },
+ "id": 136,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true,
+ "width": 350
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "(node_memory_Inactive_bytes{instance=\"$node\",job=\"$job\"}) \n/ \n(node_memory_MemTotal_bytes{instance=\"$node\",job=\"$job\"})",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Inactive – Less recently used memory, more likely to be reclaimed",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "(node_memory_Active_bytes{instance=\"$node\",job=\"$job\"}) \n/ \n(node_memory_MemTotal_bytes{instance=\"$node\",job=\"$job\"})\n",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Active – Recently used memory, retained unless under pressure",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "Memory LRU Active / Inactive (%)",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Breakdown of memory pages in the kernel's active and inactive LRU lists, separated by anonymous (heap, tmpfs) and file-backed (caches, mmap) pages.",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "normal"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "bytes"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 812
+ },
+ "id": 191,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true,
+ "width": 350
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_memory_Inactive_file_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "Inactive_file - File-backed memory on inactive LRU list",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_memory_Inactive_anon_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "Inactive_anon – Anonymous memory on inactive LRU (incl. tmpfs & swap cache)",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_memory_Active_file_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "Active_file - File-backed memory on active LRU list",
+ "range": true,
+ "refId": "C",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_memory_Active_anon_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "Active_anon – Anonymous memory on active LRU (incl. tmpfs & swap cache)",
+ "range": true,
+ "refId": "D",
+ "step": 240
+ }
+ ],
+ "title": "Memory LRU Active / Inactive Detail",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Tracks kernel memory used for CPU-local structures, per-thread stacks, and bounce buffers used for I/O on DMA-limited devices. These areas are typically small but critical for low-level operations",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "bytes"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 822
+ },
+ "id": 160,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true,
+ "width": 350
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_memory_KernelStack_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "KernelStack – Kernel stack memory (per-thread, non-reclaimable)",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_memory_Percpu_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "PerCPU – Dynamically allocated per-CPU memory (used by kernel modules)",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_memory_Bounce_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "Bounce Memory – I/O buffer for DMA-limited devices",
+ "range": true,
+ "refId": "C",
+ "step": 240
+ }
+ ],
+ "title": "Memory Kernel / CPU / IO",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Usage of the kernel's vmalloc area, which provides virtual memory allocations for kernel modules and drivers. Includes total, used, and largest free block sizes",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "bytes"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*Total.*/"
+ },
+ "properties": [
+ {
+ "id": "custom.fillOpacity",
+ "value": 0
+ },
+ {
+ "id": "custom.lineStyle",
+ "value": {
+ "dash": [
+ 10,
+ 10
+ ],
+ "fill": "dash"
+ }
+ },
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "dark-red",
+ "mode": "fixed"
+ }
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 822
+ },
+ "id": 70,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_memory_VmallocChunk_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "Vmalloc Free Chunk – Largest available block in vmalloc area",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_memory_VmallocTotal_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "Vmalloc Total – Total size of the vmalloc memory area",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_memory_VmallocUsed_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "Vmalloc Used – Portion of vmalloc area currently in use",
+ "range": true,
+ "refId": "C",
+ "step": 240
+ }
+ ],
+ "title": "Memory Vmalloc",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Memory used by anonymous pages (not backed by files), including standard and huge page allocations. Includes heap, stack, and memory-mapped anonymous regions",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "bytes"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 832
+ },
+ "id": 129,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_memory_AnonHugePages_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "AnonHugePages – Anonymous memory using HugePages",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_memory_AnonPages_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "AnonPages – Anonymous memory (non-file-backed)",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "Memory Anonymous",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Memory that is locked in RAM and cannot be swapped out. Includes both kernel-unevictable memory and user-level memory locked with mlock()",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "bytes"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Hardware Corrupted - Amount of RAM that the kernel identified as corrupted / not working"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#CFFAFF",
+ "mode": "fixed"
+ }
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 832
+ },
+ "id": 137,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true,
+ "width": 350
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_memory_Unevictable_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Unevictable – Kernel-pinned memory (not swappable)",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_memory_Mlocked_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Mlocked – Application-locked memory via mlock()",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "Memory Unevictable and MLocked",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "How much memory is directly mapped in the kernel using different page sizes (4K, 2M, 1G). Helps monitor large page utilization in the direct map region",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "bytes"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Active"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#99440A",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Buffers"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#58140C",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Cache"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#6D1F62",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Cached"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#511749",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Committed"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#508642",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Dirty"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#6ED0E0",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Free"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#B7DBAB",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Inactive"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#EA6460",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Mapped"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#052B51",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "PageTables"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#0A50A1",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Page_Tables"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#0A50A1",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Slab_Cache"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#EAB839",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Swap"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#BF1B00",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Swap_Cache"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#C15C17",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Total"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#511749",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Total RAM"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#052B51",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Total RAM + Swap"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#052B51",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "VmallocUsed"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#EA6460",
+ "mode": "fixed"
+ }
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 842
+ },
+ "id": 128,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_memory_DirectMap1G_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "DirectMap 1G – Memory mapped with 1GB pages",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_memory_DirectMap2M_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "DirectMap 2M – Memory mapped with 2MB pages",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_memory_DirectMap4k_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "DirectMap 4K – Memory mapped with 4KB pages",
+ "range": true,
+ "refId": "C",
+ "step": 240
+ }
+ ],
+ "title": "Memory DirectMap",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Displays HugePages memory usage in bytes, including allocated, free, reserved, and surplus memory. All values are calculated based on the number of huge pages multiplied by their configured size",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "bytes"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 842
+ },
+ "id": 140,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_memory_HugePages_Free{instance=\"$node\",job=\"$job\"} * node_memory_Hugepagesize_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "HugePages Used – Currently allocated",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_memory_HugePages_Rsvd{instance=\"$node\",job=\"$job\"} * node_memory_Hugepagesize_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "HugePages Reserved – Promised but unused",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_memory_HugePages_Surp{instance=\"$node\",job=\"$job\"} * node_memory_Hugepagesize_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "HugePages Surplus – Dynamic pool extension",
+ "range": true,
+ "refId": "C",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_memory_HugePages_Total{instance=\"$node\",job=\"$job\"} * node_memory_Hugepagesize_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "HugePages Total – Reserved memory",
+ "range": true,
+ "refId": "D",
+ "step": 240
+ }
+ ],
+ "title": "Memory HugePages",
+ "type": "timeseries"
+ }
+ ],
+ "title": "Memory Meminfo",
+ "type": "row"
+ },
+ {
+ "collapsed": true,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 22
+ },
+ "id": 267,
+ "panels": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Rate of memory pages being read from or written to disk (page-in and page-out operations). High page-out may indicate memory pressure or swapping activity",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "out (-) / in (+)",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "ops"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*out.*/"
+ },
+ "properties": [
+ {
+ "id": "custom.transform",
+ "value": "negative-Y"
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 603
+ },
+ "id": 176,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "irate(node_vmstat_pgpgin{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Pagesin - Page in ops",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_vmstat_pgpgout{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Pagesout - Page out ops",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "Memory Pages In / Out",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Rate at which memory pages are being swapped in from or out to disk. High swap-out activity may indicate memory pressure",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "out (-) / in (+)",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "ops"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*out.*/"
+ },
+ "properties": [
+ {
+ "id": "custom.transform",
+ "value": "negative-Y"
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 603
+ },
+ "id": 22,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "irate(node_vmstat_pswpin{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Pswpin - Pages swapped in",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_vmstat_pswpout{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Pswpout - Pages swapped out",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "Memory Pages Swap In / Out",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Rate of memory page faults, split into total, major (disk-backed), and derived minor (non-disk) faults. High major fault rates may indicate memory pressure or insufficient RAM",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "normal"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "ops"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Pgfault - Page major and minor fault ops"
+ },
+ "properties": [
+ {
+ "id": "custom.fillOpacity",
+ "value": 0
+ },
+ {
+ "id": "custom.stacking",
+ "value": {
+ "group": false,
+ "mode": "none"
+ }
+ },
+ {
+ "id": "custom.lineStyle",
+ "value": {
+ "dash": [
+ 10,
+ 10
+ ],
+ "fill": "dash"
+ }
+ },
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "dark-red",
+ "mode": "fixed"
+ }
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 783
+ },
+ "id": 175,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true,
+ "width": 350
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "irate(node_vmstat_pgfault{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "Pgfault - Page major and minor fault ops",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_vmstat_pgmajfault{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "Pgmajfault - Major page fault ops",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_vmstat_pgfault{instance=\"$node\",job=\"$job\"}[$__rate_interval]) - irate(node_vmstat_pgmajfault{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "Pgminfault - Minor page fault ops",
+ "range": true,
+ "refId": "C",
+ "step": 240
+ }
+ ],
+ "title": "Memory Page Faults",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Rate of Out-of-Memory (OOM) kill events. A non-zero value indicates the kernel has terminated one or more processes due to memory exhaustion",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "ops"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "OOM Kills"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "dark-red",
+ "mode": "fixed"
+ }
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 783
+ },
+ "id": 307,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "irate(node_vmstat_oom_kill{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "OOM Kills",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "OOM Killer",
+ "type": "timeseries"
+ }
+ ],
+ "title": "Memory Vmstat",
+ "type": "row"
+ },
+ {
+ "collapsed": true,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 23
+ },
+ "id": 293,
+ "panels": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Tracks the system clock's estimated and maximum error, as well as its offset from the reference clock (e.g., via NTP). Useful for detecting synchronization drift",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "s"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 604
+ },
+ "id": 260,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_timex_estimated_error_seconds{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "Estimated error",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_timex_offset_seconds{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "Offset local vs reference",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_timex_maxerror_seconds{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "Maximum error",
+ "range": true,
+ "refId": "C",
+ "step": 240
+ }
+ ],
+ "title": "Time Synchronized Drift",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "NTP phase-locked loop (PLL) time constant used by the kernel to control time adjustments. Lower values mean faster correction but less stability",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 604
+ },
+ "id": 291,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_timex_loop_time_constant{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "PLL Time Constant",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "Time PLL Adjust",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Shows whether the system clock is synchronized to a reliable time source, and the current frequency correction ratio applied by the kernel to maintain synchronization",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 754
+ },
+ "id": 168,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_timex_sync_status{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "Sync status (1 = ok)",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_timex_frequency_adjustment_ratio{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "Frequency Adjustment",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_timex_tick_seconds{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": true,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "Tick Interval",
+ "range": true,
+ "refId": "C",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_timex_tai_offset_seconds{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": true,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "TAI Offset",
+ "range": true,
+ "refId": "D",
+ "step": 240
+ }
+ ],
+ "title": "Time Synchronized Status",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Displays the PPS signal's frequency offset and stability (jitter) in hertz. Useful for monitoring high-precision time sources like GPS or atomic clocks",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "rothz"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 754
+ },
+ "id": 333,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_timex_pps_frequency_hertz{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "PPS Frequency Offset",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_timex_pps_stability_hertz{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "PPS Frequency Stability",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "PPS Frequency / Stability",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Tracks PPS signal timing jitter and shift compared to system clock",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "s"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 764
+ },
+ "id": 334,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_timex_pps_jitter_seconds{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "PPS Jitter",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_timex_pps_shift_seconds{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "PPS Shift",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "PPS Time Accuracy",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Rate of PPS synchronization diagnostics including calibration events, jitter violations, errors, and frequency stability exceedances",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "ops"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 764
+ },
+ "id": 335,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "irate(node_timex_pps_calibration_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "PPS Calibrations/sec",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_timex_pps_error_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "PPS Errors/sec",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_timex_pps_stability_exceeded_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "PPS Stability Exceeded/sec",
+ "range": true,
+ "refId": "C",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_timex_pps_jitter_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "PPS Jitter Events/sec",
+ "range": true,
+ "refId": "D",
+ "step": 240
+ }
+ ],
+ "title": "PPS Sync Events",
+ "type": "timeseries"
+ }
+ ],
+ "title": "System Timesync",
+ "type": "row"
+ },
+ {
+ "collapsed": true,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 24
+ },
+ "id": 312,
+ "panels": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Processes currently in runnable or blocked states. Helps identify CPU contention or I/O wait bottlenecks.",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 605
+ },
+ "id": 62,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_procs_blocked{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Blocked (I/O Wait)",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_procs_running{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Runnable (Ready for CPU)",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "Processes Status",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Current number of processes in each state (e.g., running, sleeping, zombie). Requires --collector.processes to be enabled in node_exporter",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "normal"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "D"
+ },
+ "properties": [
+ {
+ "id": "displayName",
+ "value": "Uninterruptible Sleeping"
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "I"
+ },
+ "properties": [
+ {
+ "id": "displayName",
+ "value": "Idle Kernel Thread"
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "R"
+ },
+ "properties": [
+ {
+ "id": "displayName",
+ "value": "Running"
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "S"
+ },
+ "properties": [
+ {
+ "id": "displayName",
+ "value": "Interruptible Sleeping"
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "T"
+ },
+ "properties": [
+ {
+ "id": "displayName",
+ "value": "Stopped"
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "X"
+ },
+ "properties": [
+ {
+ "id": "displayName",
+ "value": "Dead"
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Z"
+ },
+ "properties": [
+ {
+ "id": "displayName",
+ "value": "Zombie"
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 605
+ },
+ "id": 315,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_processes_state{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "{{ state }}",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "Processes Detailed States",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Rate of new processes being created on the system (forks/sec).",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "ops"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 635
+ },
+ "id": 148,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "irate(node_forks_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "Process Forks per second",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "Processes Forks",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Shows CPU saturation per core, calculated as the proportion of time spent waiting to run relative to total time demanded (running + waiting).",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "percentunit"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*waiting.*/"
+ },
+ "properties": [
+ {
+ "id": "custom.transform",
+ "value": "negative-Y"
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 635
+ },
+ "id": 305,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "irate(node_schedstat_running_seconds_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "hide": true,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "CPU {{ cpu }} - Running",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_schedstat_waiting_seconds_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "hide": true,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "CPU {{cpu}} - Waiting Queue",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_schedstat_waiting_seconds_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])\n/\n(irate(node_schedstat_running_seconds_total{instance=\"$node\",job=\"$job\"}[$__rate_interval]) + irate(node_schedstat_waiting_seconds_total{instance=\"$node\",job=\"$job\"}[$__rate_interval]))\n",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "CPU {{cpu}}",
+ "range": true,
+ "refId": "C",
+ "step": 240
+ }
+ ],
+ "title": "CPU Saturation per Core",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Number of active PIDs on the system and the configured maximum allowed. Useful for detecting PID exhaustion risk. Requires --collector.processes in node_exporter",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "PIDs limit"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#F2495C",
+ "mode": "fixed"
+ }
+ },
+ {
+ "id": "custom.fillOpacity",
+ "value": 0
+ },
+ {
+ "id": "custom.lineStyle",
+ "value": {
+ "dash": [
+ 10,
+ 10
+ ],
+ "fill": "dash"
+ }
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 645
+ },
+ "id": 313,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_processes_pids{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "Number of PIDs",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_processes_max_processes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "PIDs limit",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "PIDs Number and Limit",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Number of active threads on the system and the configured thread limit. Useful for monitoring thread pressure. Requires --collector.processes in node_exporter",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Threads limit"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#F2495C",
+ "mode": "fixed"
+ }
+ },
+ {
+ "id": "custom.fillOpacity",
+ "value": 0
+ },
+ {
+ "id": "custom.lineStyle",
+ "value": {
+ "dash": [
+ 10,
+ 10
+ ],
+ "fill": "dash"
+ }
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 645
+ },
+ "id": 314,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_processes_threads{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "Allocated threads",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_processes_max_threads{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "Threads limit",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "Threads Number and Limit",
+ "type": "timeseries"
+ }
+ ],
+ "title": "System Processes",
+ "type": "row"
+ },
+ {
+ "collapsed": true,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 25
+ },
+ "id": 269,
+ "panels": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Per-second rate of context switches and hardware interrupts. High values may indicate intense CPU or I/O activity",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "ops"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 686
+ },
+ "id": 8,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "irate(node_context_switches_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Context switches",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_intr_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "Interrupts",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "Context Switches / Interrupts",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "System load average over 1, 5, and 15 minutes. Reflects the number of active or waiting processes. Values above CPU core count may indicate overload",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "CPU Core Count"
+ },
+ "properties": [
+ {
+ "id": "custom.fillOpacity",
+ "value": 0
+ },
+ {
+ "id": "custom.lineStyle",
+ "value": {
+ "dash": [
+ 10,
+ 10
+ ],
+ "fill": "dash"
+ }
+ },
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "dark-red",
+ "mode": "fixed"
+ }
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 686
+ },
+ "id": 7,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_load1{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Load 1m",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_load5{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Load 5m",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_load15{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Load 15m",
+ "range": true,
+ "refId": "C",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "count(count(node_cpu_seconds_total{instance=\"$node\",job=\"$job\"}) by (cpu))",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "CPU Core Count",
+ "range": true,
+ "refId": "D",
+ "step": 240
+ }
+ ],
+ "title": "System Load",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Real-time CPU frequency scaling per core, including average minimum and maximum allowed scaling frequencies",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "hertz"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Max"
+ },
+ "properties": [
+ {
+ "id": "custom.lineStyle",
+ "value": {
+ "dash": [
+ 10,
+ 10
+ ],
+ "fill": "dash"
+ }
+ },
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "dark-red",
+ "mode": "fixed"
+ }
+ },
+ {
+ "id": "custom.hideFrom",
+ "value": {
+ "legend": true,
+ "tooltip": false,
+ "viz": false
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Min"
+ },
+ "properties": [
+ {
+ "id": "custom.lineStyle",
+ "value": {
+ "dash": [
+ 10,
+ 10
+ ],
+ "fill": "dash"
+ }
+ },
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "blue",
+ "mode": "fixed"
+ }
+ },
+ {
+ "id": "custom.hideFrom",
+ "value": {
+ "legend": true,
+ "tooltip": false,
+ "viz": false
+ }
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 696
+ },
+ "id": 321,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "desc"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_cpu_scaling_frequency_hertz{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "CPU {{ cpu }}",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "avg(node_cpu_scaling_frequency_max_hertz{instance=\"$node\",job=\"$job\"})",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "Max",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "avg(node_cpu_scaling_frequency_min_hertz{instance=\"$node\",job=\"$job\"})",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "Min",
+ "range": true,
+ "refId": "C",
+ "step": 240
+ }
+ ],
+ "title": "CPU Frequency Scaling",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Rate of scheduling timeslices executed per CPU. Reflects how frequently the scheduler switches tasks on each core",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "ops"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 696
+ },
+ "id": 306,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "irate(node_schedstat_timeslices_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "CPU {{ cpu }}",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "CPU Schedule Timeslices",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Breaks down hardware interrupts by type and device. Useful for diagnosing IRQ load on network, disk, or CPU interfaces. Requires --collector.interrupts to be enabled in node_exporter",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "ops"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 706
+ },
+ "id": 259,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "irate(node_interrupts_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "{{ type }} - {{ info }}",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "IRQ Detail",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Number of bits of entropy currently available to the system's random number generators (e.g., /dev/random). Low values may indicate that random number generation could block or degrade performance of cryptographic operations",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "decbits"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Entropy pool max"
+ },
+ "properties": [
+ {
+ "id": "custom.fillOpacity",
+ "value": 0
+ },
+ {
+ "id": "custom.lineStyle",
+ "value": {
+ "dash": [
+ 10,
+ 10
+ ],
+ "fill": "dash"
+ }
+ },
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "dark-red",
+ "mode": "fixed"
+ }
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 706
+ },
+ "id": 151,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_entropy_available_bits{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Entropy available",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_entropy_pool_size_bits{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "Entropy pool max",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "Entropy",
+ "type": "timeseries"
+ }
+ ],
+ "title": "System Misc",
+ "type": "row"
+ },
+ {
+ "collapsed": true,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 26
+ },
+ "id": 304,
+ "panels": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Monitors hardware sensor temperatures and critical thresholds as exposed by Linux hwmon. Includes CPU, GPU, and motherboard sensors where available",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "celsius"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*Critical*./"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#E24D42",
+ "mode": "fixed"
+ }
+ },
+ {
+ "id": "custom.fillOpacity",
+ "value": 0
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 607
+ },
+ "id": 158,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_hwmon_temp_celsius{instance=\"$node\",job=\"$job\"} * on(chip) group_left(chip_name) node_hwmon_chip_names{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "{{ chip_name }} {{ sensor }}",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr": "node_hwmon_temp_crit_alarm_celsius{instance=\"$node\",job=\"$job\"} * on(chip) group_left(chip_name) node_hwmon_chip_names{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": true,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "{{ chip_name }} {{ sensor }} Critical Alarm",
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_hwmon_temp_crit_celsius{instance=\"$node\",job=\"$job\"} * on(chip) group_left(chip_name) node_hwmon_chip_names{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "{{ chip_name }} {{ sensor }} Critical",
+ "range": true,
+ "refId": "C",
+ "step": 240
+ },
+ {
+ "expr": "node_hwmon_temp_crit_hyst_celsius{instance=\"$node\",job=\"$job\"} * on(chip) group_left(chip_name) node_hwmon_chip_names{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": true,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "{{ chip_name }} {{ sensor }} Critical Historical",
+ "refId": "D",
+ "step": 240
+ },
+ {
+ "expr": "node_hwmon_temp_max_celsius{instance=\"$node\",job=\"$job\"} * on(chip) group_left(chip_name) node_hwmon_chip_names{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": true,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "{{ chip_name }} {{ sensor }} Max",
+ "refId": "E",
+ "step": 240
+ }
+ ],
+ "title": "Hardware Temperature Monitor",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Shows how hard each cooling device (fan/throttle) is working relative to its maximum capacity",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "percent"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*Max*./"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#EF843C",
+ "mode": "fixed"
+ }
+ },
+ {
+ "id": "custom.fillOpacity",
+ "value": 0
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 607
+ },
+ "id": 300,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "100 * node_cooling_device_cur_state{instance=\"$node\",job=\"$job\"} / node_cooling_device_max_state{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "{{ name }} - {{ type }} ",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "Cooling Device Utilization",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Shows the online status of power supplies (e.g., AC, battery). A value of 1-Yes indicates the power supply is active/online",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "bool_yes_no"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 617
+ },
+ "id": 302,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_power_supply_online{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "{{ power_supply }} online",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "Power Supply",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Displays the current fan speeds (RPM) from hardware sensors via the hwmon interface",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "rotrpm"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 617
+ },
+ "id": 325,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_hwmon_fan_rpm{instance=\"$node\",job=\"$job\"} * on(chip) group_left(chip_name) node_hwmon_chip_names{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "{{ chip_name }} {{ sensor }}",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_hwmon_fan_min_rpm{instance=\"$node\",job=\"$job\"} * on(chip) group_left(chip_name) node_hwmon_chip_names{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": true,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "{{ chip_name }} {{ sensor }} rpm min",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "Hardware Fan Speed",
+ "type": "timeseries"
+ }
+ ],
+ "title": "Hardware Misc",
+ "type": "row"
+ },
+ {
+ "collapsed": true,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 27
+ },
+ "id": 296,
+ "panels": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Current number of systemd units in each operational state, such as active, failed, inactive, or transitioning",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "normal"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Failed"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#F2495C",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Active"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#73BF69",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Activating"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#C8F2C2",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Deactivating"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "orange",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Inactive"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "dark-blue",
+ "mode": "fixed"
+ }
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 4098
+ },
+ "id": 298,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_systemd_units{instance=\"$node\",job=\"$job\",state=\"activating\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "Activating",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_systemd_units{instance=\"$node\",job=\"$job\",state=\"active\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "Active",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_systemd_units{instance=\"$node\",job=\"$job\",state=\"deactivating\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "Deactivating",
+ "range": true,
+ "refId": "C",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_systemd_units{instance=\"$node\",job=\"$job\",state=\"failed\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "Failed",
+ "range": true,
+ "refId": "D",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_systemd_units{instance=\"$node\",job=\"$job\",state=\"inactive\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "Inactive",
+ "range": true,
+ "refId": "E",
+ "step": 240
+ }
+ ],
+ "title": "Systemd Units State",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Current number of active connections per systemd socket, as reported by the Node Exporter systemd collector",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 4098
+ },
+ "id": 331,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_systemd_socket_current_connections{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "{{ name }}",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "Systemd Sockets Current",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Rate of accepted connections per second for each systemd socket",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "eps"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 4108
+ },
+ "id": 297,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "irate(node_systemd_socket_accepted_connections_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "{{ name }}",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "Systemd Sockets Accepted",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Rate of systemd socket connection refusals per second, typically due to service unavailability or backlog overflow",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "eps"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 4108
+ },
+ "id": 332,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "irate(node_systemd_socket_refused_connections_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "{{ name }}",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "Systemd Sockets Refused",
+ "type": "timeseries"
+ }
+ ],
+ "title": "Systemd",
+ "type": "row"
+ },
+ {
+ "collapsed": true,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 28
+ },
+ "id": 270,
+ "panels": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Number of I/O operations completed per second for the device (after merges), including both reads and writes",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "read (–) / write (+)",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "iops"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*Read.*/"
+ },
+ "properties": [
+ {
+ "id": "custom.transform",
+ "value": "negative-Y"
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/sda.*/"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "orange",
+ "mode": "fixed"
+ }
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 29
+ },
+ "id": 9,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "single",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "irate(node_disk_reads_completed_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} - Read",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_disk_writes_completed_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} - Write",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "Disk Read/Write IOps",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Number of bytes read from or written to the device per second",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "read (–) / write (+)",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "Bps"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*Read.*/"
+ },
+ "properties": [
+ {
+ "id": "custom.transform",
+ "value": "negative-Y"
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/sda.*/"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "orange",
+ "mode": "fixed"
+ }
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 29
+ },
+ "id": 33,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "single",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "irate(node_disk_read_bytes_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} - Read",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "exemplar": false,
+ "expr": "irate(node_disk_written_bytes_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "instant": false,
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} - Write",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "Disk Read/Write Data",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Average time for requests issued to the device to be served. This includes the time spent by the requests in queue and the time spent servicing them.",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "read (–) / write (+)",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "s"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*Read.*/"
+ },
+ "properties": [
+ {
+ "id": "custom.transform",
+ "value": "negative-Y"
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/sda.*/"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "orange",
+ "mode": "fixed"
+ }
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 259
+ },
+ "id": 37,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "single",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "irate(node_disk_read_time_seconds_total{instance=\"$node\",job=\"$job\"}[$__rate_interval]) / irate(node_disk_reads_completed_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} - Read",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_disk_write_time_seconds_total{instance=\"$node\",job=\"$job\"}[$__rate_interval]) / irate(node_disk_writes_completed_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} - Write",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "Disk Average Wait Time",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Average queue length of the requests that were issued to the device",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "none"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/sda_*/"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#7EB26D",
+ "mode": "fixed"
+ }
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 259
+ },
+ "id": 35,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "single",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "irate(node_disk_io_time_weighted_seconds_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}}",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "Average Queue Size",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Number of read and write requests merged per second that were queued to the device",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "read (–) / write (+)",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "iops"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*Read.*/"
+ },
+ "properties": [
+ {
+ "id": "custom.transform",
+ "value": "negative-Y"
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/sda.*/"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "orange",
+ "mode": "fixed"
+ }
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 269
+ },
+ "id": 133,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "single",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "irate(node_disk_reads_merged_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} - Read",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_disk_writes_merged_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} - Write",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "Disk R/W Merged",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Percentage of time the disk spent actively processing I/O operations, including general I/O, discards (TRIM), and write cache flushes",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "percentunit"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/sda.*/"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "orange",
+ "mode": "fixed"
+ }
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 269
+ },
+ "id": 36,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "single",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "irate(node_disk_io_time_seconds_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} - General IO",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_disk_discard_time_seconds_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} - Discard/TRIM",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_disk_flush_requests_time_seconds_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} - Flush (write cache)",
+ "range": true,
+ "refId": "C",
+ "step": 240
+ }
+ ],
+ "title": "Time Spent Doing I/Os",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Per-second rate of discard (TRIM) and flush (write cache) operations. Useful for monitoring low-level disk activity on SSDs and advanced storage",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "ops"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/sda.*/"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "orange",
+ "mode": "fixed"
+ }
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 279
+ },
+ "id": 301,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "single",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "irate(node_disk_discards_completed_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} - Discards completed",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_disk_discards_merged_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} - Discards merged",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_disk_flush_requests_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} - Flush",
+ "range": true,
+ "refId": "C",
+ "step": 240
+ }
+ ],
+ "title": "Disk Ops Discards / Flush",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Shows how many disk sectors are discarded (TRIMed) per second. Useful for monitoring SSD behavior and storage efficiency",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/sda.*/"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "orange",
+ "mode": "fixed"
+ }
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 279
+ },
+ "id": 326,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "single",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "irate(node_disk_discarded_sectors_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}}",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "Disk Sectors Discarded Successfully",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Number of in-progress I/O requests at the time of sampling (active requests in the disk queue)",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "none"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/sda.*/"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "orange",
+ "mode": "fixed"
+ }
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 289
+ },
+ "id": 34,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "single",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_disk_io_now{instance=\"$node\",job=\"$job\"}",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}}",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "Instantaneous Queue Size",
+ "type": "timeseries"
+ }
+ ],
+ "title": "Storage Disk",
+ "type": "row"
+ },
+ {
+ "collapsed": true,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 29
+ },
+ "id": 271,
+ "panels": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Number of file descriptors currently allocated system-wide versus the system limit. Important for detecting descriptor exhaustion risks",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "sishort"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*Max.*/"
+ },
+ "properties": [
+ {
+ "id": "custom.fillOpacity",
+ "value": 0
+ },
+ {
+ "id": "custom.lineStyle",
+ "value": {
+ "dash": [
+ 10,
+ 10
+ ],
+ "fill": "dash"
+ }
+ },
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "dark-red",
+ "mode": "fixed"
+ }
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 30
+ },
+ "id": 28,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "single",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_filefd_maximum{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Max open files",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_filefd_allocated{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "Open files",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "File Descriptor",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Number of free file nodes (inodes) available per mounted filesystem. A low count may prevent file creation even if disk space is available",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 30
+ },
+ "id": 41,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_filesystem_files_free{instance=\"$node\",job=\"$job\",device!~'rootfs'}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "{{mountpoint}}",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "File Nodes Free",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Indicates filesystems mounted in read-only mode or reporting device-level I/O errors.",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "normal"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "max": 1,
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "bool_yes_no"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 240
+ },
+ "id": 44,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_filesystem_readonly{instance=\"$node\",job=\"$job\",device!~'rootfs'}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{mountpoint}} - ReadOnly",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_filesystem_device_error{instance=\"$node\",job=\"$job\",device!~'rootfs',fstype!~'tmpfs'}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "{{mountpoint}} - Device error",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "Filesystem in ReadOnly / Error",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Number of file nodes (inodes) available per mounted filesystem. Reflects maximum file capacity regardless of disk size",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "sishort"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 240
+ },
+ "id": 219,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_filesystem_files{instance=\"$node\",job=\"$job\",device!~'rootfs'}",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "{{mountpoint}}",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "File Nodes Size",
+ "type": "timeseries"
+ }
+ ],
+ "title": "Storage Filesystem",
+ "type": "row"
+ },
+ {
+ "collapsed": true,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 30
+ },
+ "id": 272,
+ "panels": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Number of network packets received and transmitted per second, by interface.",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "out (-) / in (+)",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "pps"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*out.*/"
+ },
+ "properties": [
+ {
+ "id": "custom.transform",
+ "value": "negative-Y"
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 31
+ },
+ "id": 60,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true,
+ "width": 300
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "rate(node_network_receive_packets_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} - Rx in",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "rate(node_network_transmit_packets_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} - Tx out",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "Network Traffic by Packets",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Rate of packet-level errors for each network interface. Receive errors may indicate physical or driver issues; transmit errors may reflect collisions or hardware faults",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "out (-) / in (+)",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "pps"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*out.*/"
+ },
+ "properties": [
+ {
+ "id": "custom.transform",
+ "value": "negative-Y"
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 31
+ },
+ "id": 142,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true,
+ "width": 300
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "rate(node_network_receive_errs_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} - Rx in",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "rate(node_network_transmit_errs_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} - Tx out",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "Network Traffic Errors",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Rate of dropped packets per network interface. Receive drops can indicate buffer overflow or driver issues; transmit drops may result from outbound congestion or queuing limits",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "out (-) / in (+)",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "pps"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*out.*/"
+ },
+ "properties": [
+ {
+ "id": "custom.transform",
+ "value": "negative-Y"
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 121
+ },
+ "id": 143,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true,
+ "width": 300
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "rate(node_network_receive_drop_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} - Rx in",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "rate(node_network_transmit_drop_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} - Tx out",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "Network Traffic Drop",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Rate of compressed network packets received and transmitted per interface. These are common in low-bandwidth or special interfaces like PPP or SLIP",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "out (-) / in (+)",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "pps"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*out.*/"
+ },
+ "properties": [
+ {
+ "id": "custom.transform",
+ "value": "negative-Y"
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 121
+ },
+ "id": 141,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true,
+ "width": 300
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "rate(node_network_receive_compressed_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} - Rx in",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "rate(node_network_transmit_compressed_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} - Tx out",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "Network Traffic Compressed",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Rate of incoming multicast packets received per network interface. Multicast is used by protocols such as mDNS, SSDP, and some streaming or cluster services",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "out (-) / in (+)",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "pps"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*out.*/"
+ },
+ "properties": [
+ {
+ "id": "custom.transform",
+ "value": "negative-Y"
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 131
+ },
+ "id": 146,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true,
+ "width": 300
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "rate(node_network_receive_multicast_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} - Rx in",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "Network Traffic Multicast",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Rate of received packets that could not be processed due to missing protocol or handler in the kernel. May indicate unsupported traffic or misconfiguration",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "out (-) / in (+)",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "pps"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*out.*/"
+ },
+ "properties": [
+ {
+ "id": "custom.transform",
+ "value": "negative-Y"
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 131
+ },
+ "id": 327,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true,
+ "width": 300
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "rate(node_network_receive_nohandler_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} - Rx in",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "Network Traffic NoHandler",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Rate of frame errors on received packets, typically caused by physical layer issues such as bad cables, duplex mismatches, or hardware problems",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "out (-) / in (+)",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "pps"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*out.*/"
+ },
+ "properties": [
+ {
+ "id": "custom.transform",
+ "value": "negative-Y"
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 141
+ },
+ "id": 145,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true,
+ "width": 300
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "rate(node_network_receive_frame_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} - Rx in",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "Network Traffic Frame",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Tracks FIFO buffer overrun errors on network interfaces. These occur when incoming or outgoing packets are dropped due to queue or buffer overflows, often indicating congestion or hardware limits",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "out (-) / in (+)",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "pps"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*out.*/"
+ },
+ "properties": [
+ {
+ "id": "custom.transform",
+ "value": "negative-Y"
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 141
+ },
+ "id": 144,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true,
+ "width": 300
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "rate(node_network_receive_fifo_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} - Rx in",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "rate(node_network_transmit_fifo_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} - Tx out",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "Network Traffic Fifo",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Rate of packet collisions detected during transmission. Mostly relevant on half-duplex or legacy Ethernet networks",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "pps"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*out.*/"
+ },
+ "properties": [
+ {
+ "id": "custom.transform",
+ "value": "negative-Y"
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 151
+ },
+ "id": 232,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true,
+ "width": 300
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "rate(node_network_transmit_colls_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} - Tx out",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "Network Traffic Collision",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Rate of carrier errors during transmission. These typically indicate physical layer issues like faulty cabling or duplex mismatches",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "pps"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 151
+ },
+ "id": 231,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true,
+ "width": 300
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "rate(node_network_transmit_carrier_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{device}} - Tx out",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "Network Traffic Carrier Errors",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Number of ARP entries per interface. Useful for detecting excessive ARP traffic or table growth due to scanning or misconfiguration",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 161
+ },
+ "id": 230,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_arp_entries{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{ device }} ARP Table",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "ARP Entries",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Current and maximum connection tracking entries used by Netfilter (nf_conntrack). High usage approaching the limit may cause packet drops or connection issues",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "NF conntrack limit"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "dark-red",
+ "mode": "fixed"
+ }
+ },
+ {
+ "id": "custom.fillOpacity",
+ "value": 0
+ },
+ {
+ "id": "custom.lineStyle",
+ "value": {
+ "dash": [
+ 10,
+ 10
+ ],
+ "fill": "dash"
+ }
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 161
+ },
+ "id": 61,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_nf_conntrack_entries{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "NF conntrack entries",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_nf_conntrack_entries_limit{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "NF conntrack limit",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "NF Conntrack",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Operational and physical link status of each network interface. Values are Yes for 'up' or link present, and No for 'down' or no carrier.\"",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "bool_yes_no"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 171
+ },
+ "id": 309,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true,
+ "width": 300
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_network_up{operstate=\"up\",instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": true,
+ "intervalFactor": 1,
+ "legendFormat": "{{interface}} - Operational state UP",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_network_carrier{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "instant": false,
+ "legendFormat": "{{device}} - Physical link",
+ "refId": "B"
+ }
+ ],
+ "title": "Network Operational Status",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Maximum speed of each network interface as reported by the operating system. This is a static hardware capability, not current throughput",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "decimals": 0,
+ "fieldMinMax": false,
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "bps"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 6,
+ "x": 12,
+ "y": 171
+ },
+ "id": 280,
+ "options": {
+ "displayMode": "basic",
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": false
+ },
+ "maxVizHeight": 30,
+ "minVizHeight": 16,
+ "minVizWidth": 8,
+ "namePlacement": "auto",
+ "orientation": "horizontal",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showUnfilled": true,
+ "sizing": "manual",
+ "valueMode": "color"
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_network_speed_bytes{instance=\"$node\",job=\"$job\"} * 8",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{ device }}",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "Speed",
+ "type": "bargauge"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "MTU (Maximum Transmission Unit) in bytes for each network interface. Affects packet size and transmission efficiency",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "decimals": 0,
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "none"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 6,
+ "x": 18,
+ "y": 171
+ },
+ "id": 288,
+ "options": {
+ "displayMode": "basic",
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": false
+ },
+ "maxVizHeight": 30,
+ "minVizHeight": 16,
+ "minVizWidth": 8,
+ "namePlacement": "auto",
+ "orientation": "horizontal",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showUnfilled": true,
+ "sizing": "manual",
+ "valueMode": "color"
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_network_mtu_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "{{ device }}",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "MTU",
+ "type": "bargauge"
+ }
+ ],
+ "title": "Network Traffic",
+ "type": "row"
+ },
+ {
+ "collapsed": true,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 31
+ },
+ "id": 273,
+ "panels": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Tracks TCP socket usage and memory per node",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 32
+ },
+ "id": 63,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true,
+ "width": 300
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_sockstat_TCP_alloc{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "Allocated Sockets",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_sockstat_TCP_inuse{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "In-Use Sockets",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_sockstat_TCP_orphan{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "Orphaned Sockets",
+ "range": true,
+ "refId": "C",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_sockstat_TCP_tw{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "TIME_WAIT Sockets",
+ "range": true,
+ "refId": "D",
+ "step": 240
+ }
+ ],
+ "title": "Sockstat TCP",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Number of UDP and UDPLite sockets currently in use",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 32
+ },
+ "id": 124,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true,
+ "width": 300
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_sockstat_UDPLITE_inuse{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "UDPLite - In-Use Sockets",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_sockstat_UDP_inuse{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "UDP - In-Use Sockets",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "Sockstat UDP",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Total number of sockets currently in use across all protocols (TCP, UDP, UNIX, etc.), as reported by /proc/net/sockstat",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 122
+ },
+ "id": 126,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true,
+ "width": 300
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_sockstat_sockets_used{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "Total sockets",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "Sockstat Used",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Number of FRAG and RAW sockets currently in use. RAW sockets are used for custom protocols or tools like ping; FRAG sockets are used internally for IP packet defragmentation",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 122
+ },
+ "id": 125,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true,
+ "width": 300
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_sockstat_FRAG_inuse{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "FRAG - In-Use Sockets",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_sockstat_RAW_inuse{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "RAW - In-Use Sockets",
+ "range": true,
+ "refId": "C",
+ "step": 240
+ }
+ ],
+ "title": "Sockstat FRAG / RAW",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "TCP/UDP socket memory usage in kernel (in pages)",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 132
+ },
+ "id": 336,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true,
+ "width": 300
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_sockstat_TCP_mem{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "TCP",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_sockstat_UDP_mem{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "UDP",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "TCP/UDP Kernel Buffer Memory Pages",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Kernel memory used by TCP, UDP, and IP fragmentation buffers",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "bytes"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 132
+ },
+ "id": 220,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true,
+ "width": 300
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_sockstat_TCP_mem_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "TCP",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_sockstat_UDP_mem_bytes{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "UDP",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_sockstat_FRAG_memory{instance=\"$node\",job=\"$job\"}",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "Fragmentation",
+ "range": true,
+ "refId": "C"
+ }
+ ],
+ "title": "Sockstat Memory Size",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Packets processed and dropped by the softnet network stack per CPU. Drops may indicate CPU saturation or network driver limitations",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "drop (-) / process (+)",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "pps"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*Dropped.*/"
+ },
+ "properties": [
+ {
+ "id": "custom.transform",
+ "value": "negative-Y"
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 142
+ },
+ "id": 290,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true,
+ "width": 300
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "irate(node_softnet_processed_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "CPU {{cpu}} - Processed",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_softnet_dropped_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "CPU {{cpu}} - Dropped",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "Softnet Packets",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "How often the kernel was unable to process all packets in the softnet queue before time ran out. Frequent squeezes may indicate CPU contention or driver inefficiency",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "eps"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 142
+ },
+ "id": 310,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true,
+ "width": 300
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "irate(node_softnet_times_squeezed_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "CPU {{cpu}} - Times Squeezed",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "Softnet Out of Quota",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Tracks the number of packets processed or dropped by Receive Packet Steering (RPS), a mechanism to distribute packet processing across CPUs",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "pps"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*Dropped.*/"
+ },
+ "properties": [
+ {
+ "id": "custom.transform",
+ "value": "negative-Y"
+ },
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "dark-red",
+ "mode": "fixed"
+ }
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 152
+ },
+ "id": 330,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true,
+ "width": 300
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "irate(node_softnet_received_rps_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "CPU {{cpu}} - Processed",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_softnet_flow_limit_count_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "CPU {{cpu}} - Dropped",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "Softnet RPS",
+ "type": "timeseries"
+ }
+ ],
+ "title": "Network Sockstat",
+ "type": "row"
+ },
+ {
+ "collapsed": true,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 32
+ },
+ "id": 274,
+ "panels": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Rate of octets sent and received at the IP layer, as reported by /proc/net/netstat",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "out (-) / in (+)",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "Bps"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*out.*/"
+ },
+ "properties": [
+ {
+ "id": "custom.transform",
+ "value": "negative-Y"
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 33
+ },
+ "id": 221,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true,
+ "width": 300
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "irate(node_netstat_IpExt_InOctets{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "IP Rx in",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_netstat_IpExt_OutOctets{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "intervalFactor": 1,
+ "legendFormat": "IP Tx out",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "Netstat IP In / Out Octets",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Rate of TCP segments sent and received per second, including data and control segments",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "out (-) / in (+)",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "pps"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*out.*/"
+ },
+ "properties": [
+ {
+ "id": "custom.transform",
+ "value": "negative-Y"
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*Snd.*/"
+ },
+ "properties": []
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 33
+ },
+ "id": 299,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "irate(node_netstat_Tcp_InSegs{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "instant": false,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "TCP Rx in",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_netstat_Tcp_OutSegs{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "TCP Tx out",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "TCP In / Out",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Rate of UDP datagrams sent and received per second, based on /proc/net/netstat",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "out (-) / in (+)",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "pps"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*out.*/"
+ },
+ "properties": [
+ {
+ "id": "custom.transform",
+ "value": "negative-Y"
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 63
+ },
+ "id": 55,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "irate(node_netstat_Udp_InDatagrams{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "UDP Rx in",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_netstat_Udp_OutDatagrams{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "UDP Tx out",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "UDP In / Out",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Number of ICMP messages sent and received per second, including error and control messages",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "out (-) / in (+)",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "pps"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*out.*/"
+ },
+ "properties": [
+ {
+ "id": "custom.transform",
+ "value": "negative-Y"
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 63
+ },
+ "id": 115,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "irate(node_netstat_Icmp_InMsgs{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "ICMP Rx in",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_netstat_Icmp_OutMsgs{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "ICMP Tx out",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "ICMP In / Out",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Tracks various TCP error and congestion-related events, including retransmissions, timeouts, dropped connections, and buffer issues",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "pps"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 73
+ },
+ "id": 104,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "irate(node_netstat_TcpExt_ListenOverflows{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "Listen Overflows",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_netstat_TcpExt_ListenDrops{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "Listen Drops",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_netstat_TcpExt_TCPSynRetrans{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "SYN Retransmits",
+ "range": true,
+ "refId": "C",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_netstat_Tcp_RetransSegs{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "interval": "",
+ "legendFormat": "Segment Retransmits",
+ "range": true,
+ "refId": "D"
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_netstat_Tcp_InErrs{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "interval": "",
+ "legendFormat": "Receive Errors",
+ "range": true,
+ "refId": "E"
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_netstat_Tcp_OutRsts{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "interval": "",
+ "legendFormat": "RST Sent",
+ "range": true,
+ "refId": "F"
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_netstat_TcpExt_TCPRcvQDrop{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "hide": false,
+ "interval": "",
+ "legendFormat": "Receive Queue Drops",
+ "range": true,
+ "refId": "G"
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_netstat_TcpExt_TCPOFOQueue{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "hide": false,
+ "interval": "",
+ "legendFormat": "Out-of-order Queued",
+ "range": true,
+ "refId": "H"
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_netstat_TcpExt_TCPTimeouts{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "hide": false,
+ "interval": "",
+ "legendFormat": "TCP Timeouts",
+ "range": true,
+ "refId": "I"
+ }
+ ],
+ "title": "TCP Errors",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Rate of UDP and UDPLite datagram delivery errors, including missing listeners, buffer overflows, and protocol-specific issues",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "pps"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 73
+ },
+ "id": 109,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "irate(node_netstat_Udp_InErrors{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "UDP Rx in Errors",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_netstat_Udp_NoPorts{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "UDP No Listener",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_netstat_UdpLite_InErrors{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "interval": "",
+ "legendFormat": "UDPLite Rx in Errors",
+ "range": true,
+ "refId": "C"
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_netstat_Udp_RcvbufErrors{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "UDP Rx in Buffer Errors",
+ "range": true,
+ "refId": "D",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_netstat_Udp_SndbufErrors{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "UDP Tx out Buffer Errors",
+ "range": true,
+ "refId": "E",
+ "step": 240
+ }
+ ],
+ "title": "UDP Errors",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Rate of incoming ICMP messages that contained protocol-specific errors, such as bad checksums or invalid lengths",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "out (-) / in (+)",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "pps"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*out.*/"
+ },
+ "properties": [
+ {
+ "id": "custom.transform",
+ "value": "negative-Y"
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 83
+ },
+ "id": 50,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "irate(node_netstat_Icmp_InErrors{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "ICMP Rx In",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "ICMP Errors",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Rate of TCP SYN cookies sent, validated, and failed. These are used to protect against SYN flood attacks and manage TCP handshake resources under load",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "eps"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*Failed.*/"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "dark-red",
+ "mode": "fixed"
+ }
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 83
+ },
+ "id": 91,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "irate(node_netstat_TcpExt_SyncookiesFailed{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "SYN Cookies Failed",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_netstat_TcpExt_SyncookiesRecv{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "SYN Cookies Validated",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_netstat_TcpExt_SyncookiesSent{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "SYN Cookies Sent",
+ "range": true,
+ "refId": "C",
+ "step": 240
+ }
+ ],
+ "title": "TCP SynCookie",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Number of currently established TCP connections and the system's max supported limit. On Linux, MaxConn may return -1 to indicate a dynamic/unlimited configuration",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*Max*./"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#890F02",
+ "mode": "fixed"
+ }
+ },
+ {
+ "id": "custom.fillOpacity",
+ "value": 0
+ },
+ {
+ "id": "custom.lineStyle",
+ "value": {
+ "dash": [
+ 10,
+ 10
+ ],
+ "fill": "dash"
+ }
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 93
+ },
+ "id": 85,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_netstat_Tcp_CurrEstab{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "Current Connections",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_netstat_Tcp_MaxConn{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "Max Connections",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "TCP Connections",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Number of UDP packets currently queued in the receive (RX) and transmit (TX) buffers. A growing queue may indicate a bottleneck",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 93
+ },
+ "id": 337,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_udp_queues{instance=\"$node\",job=\"$job\",ip=\"v4\",queue=\"rx\"}",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "UDP Rx in Queue",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_udp_queues{instance=\"$node\",job=\"$job\",ip=\"v4\",queue=\"tx\"}",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "UDP Tx out Queue",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "UDP Queue",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Rate of TCP connection initiations per second. 'Active' opens are initiated by this host. 'Passive' opens are accepted from incoming connections",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "eps"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 103
+ },
+ "id": 82,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "irate(node_netstat_Tcp_ActiveOpens{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "Active Opens",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "irate(node_netstat_Tcp_PassiveOpens{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "Passive Opens",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "TCP Direct Transition",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Number of TCP sockets in key connection states. Requires the --collector.tcpstat flag on node_exporter",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "noValue": "0",
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 103
+ },
+ "id": 320,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_tcp_connection_states{state=\"established\",instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "Established",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_tcp_connection_states{state=\"fin_wait2\",instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "FIN_WAIT2",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_tcp_connection_states{state=\"listen\",instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "Listen",
+ "range": true,
+ "refId": "C",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_tcp_connection_states{state=\"time_wait\",instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "TIME_WAIT",
+ "range": true,
+ "refId": "D",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "node_tcp_connection_states{state=\"close_wait\", instance=\"$node\", job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "CLOSE_WAIT",
+ "range": true,
+ "refId": "E",
+ "step": 240
+ }
+ ],
+ "title": "TCP Stat",
+ "type": "timeseries"
+ }
+ ],
+ "title": "Network Netstat",
+ "type": "row"
+ },
+ {
+ "collapsed": true,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 33
+ },
+ "id": 279,
+ "panels": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Duration of each individual collector executed during a Node Exporter scrape. Useful for identifying slow or failing collectors",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "normal"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "s"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 0,
+ "y": 34
+ },
+ "id": 40,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_scrape_collector_duration_seconds{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "{{collector}}",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "Node Exporter Scrape Time",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Rate of CPU time used by the process exposing this metric (user + system mode)",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "percentunit"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 12,
+ "x": 12,
+ "y": 34
+ },
+ "id": 308,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "irate(process_cpu_seconds_total{instance=\"$node\",job=\"$job\"}[$__rate_interval])",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "Process CPU Usage",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ }
+ ],
+ "title": "Exporter Process CPU Usage",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Tracks the memory usage of the process exposing this metric (e.g., node_exporter), including current virtual memory and maximum virtual memory limit",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "bytes"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Virtual Memory Limit"
+ },
+ "properties": [
+ {
+ "id": "custom.fillOpacity",
+ "value": 0
+ },
+ {
+ "id": "custom.lineStyle",
+ "value": {
+ "dash": [
+ 10,
+ 10
+ ],
+ "fill": "dash"
+ }
+ },
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "dark-red",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "__systemRef": "hideSeriesFrom",
+ "matcher": {
+ "id": "byNames",
+ "options": {
+ "mode": "exclude",
+ "names": [
+ "Virtual Memory"
+ ],
+ "prefix": "All except:",
+ "readOnly": true
+ }
+ },
+ "properties": [
+ {
+ "id": "custom.hideFrom",
+ "value": {
+ "legend": false,
+ "tooltip": false,
+ "viz": true
+ }
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 10,
+ "x": 0,
+ "y": 44
+ },
+ "id": 149,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "process_virtual_memory_bytes{instance=\"$node\",job=\"$job\"}",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "Virtual Memory",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "process_virtual_memory_max_bytes{instance=\"$node\",job=\"$job\"}",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "Virtual Memory Limit",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "Exporter Processes Memory",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Number of file descriptors used by the exporter process versus its configured limit",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 20,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byRegexp",
+ "options": "/.*Max*./"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "#890F02",
+ "mode": "fixed"
+ }
+ },
+ {
+ "id": "custom.fillOpacity",
+ "value": 0
+ },
+ {
+ "id": "custom.lineStyle",
+ "value": {
+ "dash": [
+ 10,
+ 10
+ ],
+ "fill": "dash"
+ }
+ }
+ ]
+ },
+ {
+ "__systemRef": "hideSeriesFrom",
+ "matcher": {
+ "id": "byNames",
+ "options": {
+ "mode": "exclude",
+ "names": [
+ "Open file descriptors"
+ ],
+ "prefix": "All except:",
+ "readOnly": true
+ }
+ },
+ "properties": [
+ {
+ "id": "custom.hideFrom",
+ "value": {
+ "legend": false,
+ "tooltip": false,
+ "viz": true
+ }
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 10,
+ "x": 10,
+ "y": 44
+ },
+ "id": 64,
+ "options": {
+ "legend": {
+ "calcs": [
+ "min",
+ "mean",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "process_max_fds{instance=\"$node\",job=\"$job\"}",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "Maximum open file descriptors",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "process_open_fds{instance=\"$node\",job=\"$job\"}",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "Open file descriptors",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "Exporter File Descriptor Usage",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "description": "Shows whether each Node Exporter collector scraped successfully (1 = success, 0 = failure), and whether the textfile collector returned an error.",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "links": [],
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ },
+ {
+ "color": "dark-red",
+ "value": 0
+ },
+ {
+ "color": "green",
+ "value": 1
+ }
+ ]
+ },
+ "unit": "bool"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 10,
+ "w": 4,
+ "x": 20,
+ "y": 44
+ },
+ "id": 157,
+ "options": {
+ "displayMode": "basic",
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": false
+ },
+ "maxVizHeight": 300,
+ "minVizHeight": 16,
+ "minVizWidth": 8,
+ "namePlacement": "auto",
+ "orientation": "horizontal",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showUnfilled": true,
+ "sizing": "auto",
+ "valueMode": "color"
+ },
+ "pluginVersion": "11.6.1",
+ "targets": [
+ {
+ "editorMode": "code",
+ "expr": "node_scrape_collector_success{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "{{collector}}",
+ "range": true,
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "editorMode": "code",
+ "expr": "1 - node_textfile_scrape_error{instance=\"$node\",job=\"$job\"}",
+ "format": "time_series",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "textfile",
+ "range": true,
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "title": "Node Exporter Scrape",
+ "type": "bargauge"
+ }
+ ],
+ "title": "Node Exporter",
+ "type": "row"
+ }
+ ],
+ "refresh": "1m",
+ "schemaVersion": 41,
+ "tags": [
+ "linux"
+ ],
+ "templating": {
+ "list": [
+ {
+ "current": {},
+ "includeAll": false,
+ "label": "Datasource",
+ "name": "DS_PROMETHEUS",
+ "options": [],
+ "query": "prometheus",
+ "refresh": 1,
+ "regex": "",
+ "type": "datasource"
+ },
+ {
+ "current": {},
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "definition": "",
+ "includeAll": false,
+ "label": "Job",
+ "name": "job",
+ "options": [],
+ "query": {
+ "query": "label_values(node_uname_info, job)",
+ "refId": "Prometheus-job-Variable-Query"
+ },
+ "refresh": 1,
+ "regex": "",
+ "sort": 1,
+ "type": "query"
+ },
+ {
+ "current": {},
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "definition": "label_values(node_uname_info{job=\"$job\"}, nodename)",
+ "includeAll": false,
+ "label": "Nodename",
+ "name": "nodename",
+ "options": [],
+ "query": {
+ "query": "label_values(node_uname_info{job=\"$job\"}, nodename)",
+ "refId": "Prometheus-nodename-Variable-Query"
+ },
+ "refresh": 1,
+ "regex": "",
+ "sort": 1,
+ "type": "query"
+ },
+ {
+ "current": {},
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "definition": "label_values(node_uname_info{job=\"$job\", nodename=\"$nodename\"}, instance)",
+ "includeAll": false,
+ "label": "Instance",
+ "name": "node",
+ "options": [],
+ "query": {
+ "query": "label_values(node_uname_info{job=\"$job\", nodename=\"$nodename\"}, instance)",
+ "refId": "Prometheus-node-Variable-Query"
+ },
+ "refresh": 1,
+ "regex": "",
+ "sort": 1,
+ "type": "query"
+ },
+ {
+ "current": {
+ "text": "[a-z]+|nvme[0-9]+n[0-9]+|mmcblk[0-9]+",
+ "value": "[a-z]+|nvme[0-9]+n[0-9]+|mmcblk[0-9]+"
+ },
+ "hide": 2,
+ "includeAll": false,
+ "name": "diskdevices",
+ "options": [
+ {
+ "selected": true,
+ "text": "[a-z]+|nvme[0-9]+n[0-9]+|mmcblk[0-9]+",
+ "value": "[a-z]+|nvme[0-9]+n[0-9]+|mmcblk[0-9]+"
+ }
+ ],
+ "query": "[a-z]+|nvme[0-9]+n[0-9]+|mmcblk[0-9]+",
+ "type": "custom"
+ }
+ ]
+ },
+ "time": {
+ "from": "now-24h",
+ "to": "now"
+ },
+ "timepicker": {},
+ "timezone": "browser",
+ "title": "Node Exporter Full",
+ "uid": "rYdddlPWk",
+ "version": 96,
+ "weekStart": "",
+ "gnetId": 1860
+}
\ No newline at end of file
hosts/chaser-pardofelis/grafana/dashboards/README.md
@@ -0,0 +1,5 @@
+# Dashboards
+
+## Server
+
+- https://grafana.com/grafana/dashboards/1860-node-exporter-full/
\ No newline at end of file
hosts/chaser-pardofelis/grafana/default.nix
@@ -28,5 +28,32 @@
default_language = "detect";
};
};
+
+ provision = {
+ datasources.settings.datasources = [
+ {
+ name = "prometheus-pardofelis";
+ type = "prometheus";
+ access = "proxy";
+ url = "http://${config.services.victoriametrics.listenAddress}";
+ jsonData = {
+ httpMethod = "POST";
+ manageAlerts = true;
+ prometheusType = "Prometheus";
+ prometheusVersion = "2.49.0";
+ cacheLevel = "High";
+ disableRecordingRules = false;
+ incrementalQueryOverlapWindow = "10m";
+ };
+ }
+ ];
+ dashboards.settings.providers = [
+ {
+ name = "Default";
+ type = "file";
+ options.path = ./dashboards;
+ }
+ ];
+ };
};
}