incus-contrib/incusos/observability-dashboards/core/cluster-overview.json

675 lines
22 KiB
JSON

{
"uid": "incus-cluster-overview",
"title": "Incus Cluster Overview",
"description": "Overview of all Incus instances: CPU, memory, network, disk I/O, and instance status table with drill-down links.",
"tags": ["incus", "cluster", "containers"],
"timezone": "browser",
"schemaVersion": 39,
"refresh": "30s",
"time": { "from": "now-1h", "to": "now" },
"fiscalYearStartMonth": 0,
"liveNow": false,
"editable": true,
"graphTooltip": 1,
"links": [
{
"asDropdown": true,
"icon": "external link",
"includeVars": true,
"keepTime": true,
"tags": ["incus"],
"targetBlank": false,
"title": "Incus Dashboards",
"tooltip": "Navigate to other Incus dashboards",
"type": "dashboards"
}
],
"templating": {
"list": [
{
"current": {},
"datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
"definition": "label_values(incus_uptime_seconds, name)",
"includeAll": true,
"multi": true,
"name": "instance",
"query": "label_values(incus_uptime_seconds, name)",
"refresh": 2,
"regex": "",
"sort": 1,
"type": "query",
"label": "Instance"
},
{
"current": {},
"datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
"definition": "label_values(incus_uptime_seconds, instance)",
"includeAll": true,
"multi": true,
"name": "node",
"query": "label_values(incus_uptime_seconds, instance)",
"refresh": 2,
"regex": "",
"sort": 1,
"type": "query",
"label": "Node"
}
]
},
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": { "type": "grafana", "uid": "-- Grafana --" },
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"type": "dashboard"
}
]
},
"panels": [
{
"type": "row",
"title": "Cluster Status",
"collapsed": false,
"gridPos": { "h": 1, "w": 24, "x": 0, "y": 0 },
"id": 1,
"panels": []
},
{
"type": "stat",
"title": "Total Instances",
"description": "Number of running Incus instances (reporting uptime).",
"gridPos": { "h": 4, "w": 6, "x": 0, "y": 1 },
"id": 2,
"datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
"targets": [
{
"expr": "count(incus_uptime_seconds{instance=~\"$node\", name=~\"$instance\"})",
"legendFormat": "Instances",
"refId": "A"
}
],
"fieldConfig": {
"defaults": {
"thresholds": {
"mode": "absolute",
"steps": [
{ "color": "green", "value": null },
{ "color": "yellow", "value": 10 },
{ "color": "red", "value": 50 }
]
},
"unit": "none",
"color": { "mode": "thresholds" }
},
"overrides": []
},
"options": {
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
"orientation": "auto",
"textMode": "auto",
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto"
}
},
{
"type": "stat",
"title": "Total CPUs",
"description": "Sum of effective CPUs across all Incus instances.",
"gridPos": { "h": 4, "w": 6, "x": 6, "y": 1 },
"id": 3,
"datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
"targets": [
{
"expr": "sum(incus_cpu_effective_total{instance=~\"$node\", name=~\"$instance\"})",
"legendFormat": "CPUs",
"refId": "A"
}
],
"fieldConfig": {
"defaults": {
"thresholds": {
"mode": "absolute",
"steps": [{ "color": "green", "value": null }]
},
"unit": "none",
"color": { "mode": "thresholds" }
},
"overrides": []
},
"options": {
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
"orientation": "auto",
"textMode": "auto",
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto"
}
},
{
"type": "stat",
"title": "Total Memory",
"description": "Sum of total memory across all Incus instances.",
"gridPos": { "h": 4, "w": 6, "x": 12, "y": 1 },
"id": 4,
"datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
"targets": [
{
"expr": "sum(incus_memory_MemTotal_bytes{instance=~\"$node\", name=~\"$instance\"})",
"legendFormat": "Total Memory",
"refId": "A"
}
],
"fieldConfig": {
"defaults": {
"thresholds": {
"mode": "absolute",
"steps": [{ "color": "green", "value": null }]
},
"unit": "bytes",
"color": { "mode": "thresholds" }
},
"overrides": []
},
"options": {
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
"orientation": "auto",
"textMode": "auto",
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto"
}
},
{
"type": "gauge",
"title": "Cluster Memory Utilization",
"description": "Overall cluster memory utilization (RSS / Total) across all instances.",
"gridPos": { "h": 4, "w": 6, "x": 18, "y": 1 },
"id": 40,
"datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
"targets": [
{
"expr": "(sum(incus_memory_RSS_bytes{instance=~\"$node\", name=~\"$instance\"}) / sum(incus_memory_MemTotal_bytes{instance=~\"$node\", name=~\"$instance\"})) * 100",
"legendFormat": "Utilization",
"refId": "A"
}
],
"fieldConfig": {
"defaults": {
"thresholds": {
"mode": "absolute",
"steps": [
{ "color": "green", "value": null },
{ "color": "yellow", "value": 60 },
{ "color": "orange", "value": 80 },
{ "color": "red", "value": 90 }
]
},
"unit": "percent",
"min": 0,
"max": 100,
"color": { "mode": "thresholds" }
},
"overrides": []
},
"options": {
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
"showThresholdLabels": false,
"showThresholdMarkers": true,
"orientation": "auto"
}
},
{
"type": "row",
"title": "Instance Status",
"collapsed": false,
"gridPos": { "h": 1, "w": 24, "x": 0, "y": 5 },
"id": 50,
"panels": []
},
{
"type": "table",
"title": "Instance Status Table",
"description": "Per-instance summary: uptime, CPU usage, memory RSS, total memory. Click instance name to drill down.",
"gridPos": { "h": 8, "w": 24, "x": 0, "y": 6 },
"id": 51,
"datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
"targets": [
{
"expr": "incus_uptime_seconds{instance=~\"$node\", name=~\"$instance\"}",
"legendFormat": "",
"refId": "A",
"format": "table",
"instant": true
},
{
"expr": "sum by (name, instance) (rate(incus_cpu_seconds_total{instance=~\"$node\", name=~\"$instance\"}[$__rate_interval]))",
"legendFormat": "",
"refId": "B",
"format": "table",
"instant": true
},
{
"expr": "incus_memory_RSS_bytes{instance=~\"$node\", name=~\"$instance\"}",
"legendFormat": "",
"refId": "C",
"format": "table",
"instant": true
},
{
"expr": "incus_memory_MemTotal_bytes{instance=~\"$node\", name=~\"$instance\"}",
"legendFormat": "",
"refId": "D",
"format": "table",
"instant": true
}
],
"fieldConfig": {
"defaults": {
"custom": {
"align": "auto",
"displayMode": "auto",
"inspect": false,
"filterable": true
},
"thresholds": {
"mode": "absolute",
"steps": [{ "color": "green", "value": null }]
},
"color": { "mode": "thresholds" }
},
"overrides": [
{
"matcher": { "id": "byName", "options": "name" },
"properties": [
{ "id": "displayName", "value": "Instance" },
{ "id": "custom.width", "value": 200 },
{
"id": "links",
"value": [
{
"title": "View instance details",
"url": "/d/incus-instance-deep-dive?var-instance=${__value.text}&${__url_time_range}",
"targetBlank": false
}
]
}
]
},
{
"matcher": { "id": "byName", "options": "instance" },
"properties": [{ "id": "displayName", "value": "Node" }]
},
{
"matcher": { "id": "byName", "options": "Value #A" },
"properties": [
{ "id": "displayName", "value": "Uptime" },
{ "id": "unit", "value": "s" }
]
},
{
"matcher": { "id": "byName", "options": "Value #B" },
"properties": [
{ "id": "displayName", "value": "CPU/s" },
{ "id": "unit", "value": "short" },
{ "id": "decimals", "value": 3 }
]
},
{
"matcher": { "id": "byName", "options": "Value #C" },
"properties": [
{ "id": "displayName", "value": "Memory RSS" },
{ "id": "unit", "value": "bytes" }
]
},
{
"matcher": { "id": "byName", "options": "Value #D" },
"properties": [
{ "id": "displayName", "value": "Total Memory" },
{ "id": "unit", "value": "bytes" }
]
}
]
},
"options": {
"showHeader": true,
"sortBy": [{ "displayName": "Instance", "desc": false }],
"footer": { "show": false, "reducer": ["sum"], "fields": "" }
},
"transformations": [
{ "id": "merge", "options": {} },
{
"id": "organize",
"options": {
"excludeByName": { "Time": true, "__name__": true, "job": true },
"indexByName": {
"name": 0, "instance": 1,
"Value #A": 2, "Value #B": 3, "Value #C": 4, "Value #D": 5
},
"renameByName": {}
}
}
]
},
{
"type": "row",
"title": "Per-Instance CPU",
"collapsed": false,
"gridPos": { "h": 1, "w": 24, "x": 0, "y": 14 },
"id": 5,
"panels": []
},
{
"type": "timeseries",
"title": "CPU Usage by Instance",
"description": "Per-second CPU time consumed by each Incus instance.",
"gridPos": { "h": 8, "w": 24, "x": 0, "y": 15 },
"id": 6,
"datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
"targets": [
{
"expr": "sum by (name) (rate(incus_cpu_seconds_total{instance=~\"$node\", name=~\"$instance\"}[$__rate_interval]))",
"legendFormat": "{{name}}",
"refId": "A"
}
],
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"lineInterpolation": "smooth",
"lineWidth": 1,
"fillOpacity": 15,
"gradientMode": "scheme",
"spanNulls": false,
"showPoints": "never",
"pointSize": 5,
"stacking": { "mode": "none", "group": "A" },
"axisPlacement": "auto",
"axisLabel": "",
"scaleDistribution": { "type": "linear" },
"thresholdsStyle": { "mode": "off" }
},
"unit": "short",
"color": { "mode": "palette-classic" },
"thresholds": {
"mode": "absolute",
"steps": [{ "color": "green", "value": null }]
},
"links": [
{
"title": "Drill down to ${__field.labels.name}",
"url": "/d/incus-instance-deep-dive?var-instance=${__field.labels.name}&${__url_time_range}",
"targetBlank": false
}
]
},
"overrides": []
},
"options": {
"tooltip": { "mode": "multi", "sort": "desc" },
"legend": { "displayMode": "table", "placement": "right", "calcs": ["mean", "max", "lastNotNull"] }
}
},
{
"type": "row",
"title": "Per-Instance Memory",
"collapsed": false,
"gridPos": { "h": 1, "w": 24, "x": 0, "y": 23 },
"id": 7,
"panels": []
},
{
"type": "timeseries",
"title": "Memory RSS by Instance",
"description": "Resident set size (RSS) memory usage per Incus instance over time.",
"gridPos": { "h": 8, "w": 14, "x": 0, "y": 24 },
"id": 8,
"datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
"targets": [
{
"expr": "incus_memory_RSS_bytes{instance=~\"$node\", name=~\"$instance\"}",
"legendFormat": "{{name}}",
"refId": "A"
}
],
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"lineInterpolation": "smooth",
"lineWidth": 1,
"fillOpacity": 15,
"gradientMode": "none",
"spanNulls": false,
"showPoints": "never",
"pointSize": 5,
"stacking": { "mode": "none", "group": "A" },
"axisPlacement": "auto",
"axisLabel": "",
"scaleDistribution": { "type": "linear" },
"thresholdsStyle": { "mode": "off" }
},
"unit": "bytes",
"color": { "mode": "palette-classic" },
"thresholds": {
"mode": "absolute",
"steps": [{ "color": "green", "value": null }]
}
},
"overrides": []
},
"options": {
"tooltip": { "mode": "multi", "sort": "desc" },
"legend": { "displayMode": "table", "placement": "right", "calcs": ["mean", "max", "lastNotNull"] }
}
},
{
"type": "bargauge",
"title": "Memory Usage % (RSS / Total)",
"description": "Current memory utilization per instance as RSS divided by total memory.",
"gridPos": { "h": 8, "w": 10, "x": 14, "y": 24 },
"id": 9,
"datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
"targets": [
{
"expr": "(incus_memory_RSS_bytes{instance=~\"$node\", name=~\"$instance\"} / incus_memory_MemTotal_bytes{instance=~\"$node\", name=~\"$instance\"}) * 100",
"legendFormat": "{{name}}",
"refId": "A"
}
],
"fieldConfig": {
"defaults": {
"thresholds": {
"mode": "absolute",
"steps": [
{ "color": "green", "value": null },
{ "color": "yellow", "value": 60 },
{ "color": "orange", "value": 80 },
{ "color": "red", "value": 90 }
]
},
"unit": "percent",
"min": 0,
"max": 100,
"color": { "mode": "thresholds" }
},
"overrides": []
},
"options": {
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
"orientation": "horizontal",
"displayMode": "gradient",
"showUnfilled": true,
"minVizWidth": 8,
"minVizHeight": 16,
"valueMode": "color"
}
},
{
"type": "row",
"title": "Network I/O",
"collapsed": false,
"gridPos": { "h": 1, "w": 24, "x": 0, "y": 32 },
"id": 10,
"panels": []
},
{
"type": "timeseries",
"title": "Network Receive Rate by Instance",
"description": "Inbound network throughput per Incus instance.",
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 33 },
"id": 11,
"datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
"targets": [
{
"expr": "sum by (name) (rate(incus_network_receive_bytes_total{instance=~\"$node\", name=~\"$instance\"}[$__rate_interval]))",
"legendFormat": "{{name}}",
"refId": "A"
}
],
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line", "lineInterpolation": "smooth", "lineWidth": 1,
"fillOpacity": 15, "gradientMode": "none", "spanNulls": false,
"showPoints": "never", "pointSize": 5,
"stacking": { "mode": "none", "group": "A" },
"axisPlacement": "auto", "axisLabel": "",
"scaleDistribution": { "type": "linear" },
"thresholdsStyle": { "mode": "off" }
},
"unit": "Bps",
"color": { "mode": "palette-classic" },
"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }] }
},
"overrides": []
},
"options": {
"tooltip": { "mode": "multi", "sort": "desc" },
"legend": { "displayMode": "table", "placement": "right", "calcs": ["mean", "max", "lastNotNull"] }
}
},
{
"type": "timeseries",
"title": "Network Transmit Rate by Instance",
"description": "Outbound network throughput per Incus instance.",
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 33 },
"id": 12,
"datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
"targets": [
{
"expr": "sum by (name) (rate(incus_network_transmit_bytes_total{instance=~\"$node\", name=~\"$instance\"}[$__rate_interval]))",
"legendFormat": "{{name}}",
"refId": "A"
}
],
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line", "lineInterpolation": "smooth", "lineWidth": 1,
"fillOpacity": 15, "gradientMode": "none", "spanNulls": false,
"showPoints": "never", "pointSize": 5,
"stacking": { "mode": "none", "group": "A" },
"axisPlacement": "auto", "axisLabel": "",
"scaleDistribution": { "type": "linear" },
"thresholdsStyle": { "mode": "off" }
},
"unit": "Bps",
"color": { "mode": "palette-classic" },
"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }] }
},
"overrides": []
},
"options": {
"tooltip": { "mode": "multi", "sort": "desc" },
"legend": { "displayMode": "table", "placement": "right", "calcs": ["mean", "max", "lastNotNull"] }
}
},
{
"type": "row",
"title": "Disk I/O",
"collapsed": false,
"gridPos": { "h": 1, "w": 24, "x": 0, "y": 41 },
"id": 13,
"panels": []
},
{
"type": "timeseries",
"title": "Disk Read Rate by Instance",
"description": "Disk read throughput per Incus instance.",
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 42 },
"id": 14,
"datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
"targets": [
{
"expr": "sum by (name) (rate(incus_disk_read_bytes_total{instance=~\"$node\", name=~\"$instance\"}[$__rate_interval]))",
"legendFormat": "{{name}}",
"refId": "A"
}
],
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line", "lineInterpolation": "smooth", "lineWidth": 1,
"fillOpacity": 15, "gradientMode": "none", "spanNulls": false,
"showPoints": "never", "pointSize": 5,
"stacking": { "mode": "none", "group": "A" },
"axisPlacement": "auto", "axisLabel": "",
"scaleDistribution": { "type": "linear" },
"thresholdsStyle": { "mode": "off" }
},
"unit": "Bps",
"color": { "mode": "palette-classic" },
"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }] }
},
"overrides": []
},
"options": {
"tooltip": { "mode": "multi", "sort": "desc" },
"legend": { "displayMode": "table", "placement": "right", "calcs": ["mean", "max", "lastNotNull"] }
}
},
{
"type": "timeseries",
"title": "Disk Write Rate by Instance",
"description": "Disk write throughput per Incus instance.",
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 42 },
"id": 15,
"datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
"targets": [
{
"expr": "sum by (name) (rate(incus_disk_written_bytes_total{instance=~\"$node\", name=~\"$instance\"}[$__rate_interval]))",
"legendFormat": "{{name}}",
"refId": "A"
}
],
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line", "lineInterpolation": "smooth", "lineWidth": 1,
"fillOpacity": 15, "gradientMode": "none", "spanNulls": false,
"showPoints": "never", "pointSize": 5,
"stacking": { "mode": "none", "group": "A" },
"axisPlacement": "auto", "axisLabel": "",
"scaleDistribution": { "type": "linear" },
"thresholdsStyle": { "mode": "off" }
},
"unit": "Bps",
"color": { "mode": "palette-classic" },
"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }] }
},
"overrides": []
},
"options": {
"tooltip": { "mode": "multi", "sort": "desc" },
"legend": { "displayMode": "table", "placement": "right", "calcs": ["mean", "max", "lastNotNull"] }
}
}
]
}