Saravana Kumar
fe8338c2c5
12-panel dashboard auto-provisioned via /var/lib/grafana/dashboards:
- 4 stat tiles (disk %, RAM avail, swap used, CPU steal) with
threshold colouring matching vm-health-check.sh
- 4 time-series (disk %, RAM trend, steal, sda write GB/hr) — 7d default
- 2 bargauge top-10 by RAM and CPU (cAdvisor container_memory_working_set,
container_cpu_usage)
- Load average (1/5/15) + network throughput (RX/TX, host interfaces)
uid: vm-overview. Picked up on next Grafana boot.
Closes Phase 5: "Add Grafana" item from VM observability roadmap.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
315 lines
8.8 KiB
JSON
315 lines
8.8 KiB
JSON
{
|
|
"annotations": { "list": [] },
|
|
"editable": true,
|
|
"fiscalYearStartMonth": 0,
|
|
"graphTooltip": 1,
|
|
"id": null,
|
|
"links": [],
|
|
"title": "VM Overview — srv1491630",
|
|
"tags": ["vm", "infrastructure"],
|
|
"uid": "vm-overview",
|
|
"schemaVersion": 38,
|
|
"version": 1,
|
|
"refresh": "1m",
|
|
"time": { "from": "now-7d", "to": "now" },
|
|
"timepicker": {
|
|
"refresh_intervals": ["30s", "1m", "5m", "15m", "30m", "1h"]
|
|
},
|
|
"templating": { "list": [] },
|
|
"panels": [
|
|
{
|
|
"title": "Disk Used %",
|
|
"type": "stat",
|
|
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
|
"gridPos": { "h": 4, "w": 6, "x": 0, "y": 0 },
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "percent",
|
|
"decimals": 1,
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{ "color": "green", "value": null },
|
|
{ "color": "yellow", "value": 55 },
|
|
{ "color": "red", "value": 70 }
|
|
]
|
|
}
|
|
}
|
|
},
|
|
"options": {
|
|
"graphMode": "area",
|
|
"colorMode": "value",
|
|
"reduceOptions": { "calcs": ["lastNotNull"] }
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"expr": "(1 - node_filesystem_avail_bytes{mountpoint=\"/\"} / node_filesystem_size_bytes{mountpoint=\"/\"}) * 100"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "RAM Available (GB)",
|
|
"type": "stat",
|
|
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
|
"gridPos": { "h": 4, "w": 6, "x": 6, "y": 0 },
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "decgbytes",
|
|
"decimals": 1,
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{ "color": "red", "value": null },
|
|
{ "color": "yellow", "value": 3 },
|
|
{ "color": "green", "value": 6 }
|
|
]
|
|
}
|
|
}
|
|
},
|
|
"options": {
|
|
"graphMode": "area",
|
|
"colorMode": "value",
|
|
"reduceOptions": { "calcs": ["lastNotNull"] }
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"expr": "node_memory_MemAvailable_bytes / 1073741824"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Swap Used (GB)",
|
|
"type": "stat",
|
|
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
|
"gridPos": { "h": 4, "w": 6, "x": 12, "y": 0 },
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "decgbytes",
|
|
"decimals": 2,
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{ "color": "green", "value": null },
|
|
{ "color": "yellow", "value": 1.5 },
|
|
{ "color": "red", "value": 3 }
|
|
]
|
|
}
|
|
}
|
|
},
|
|
"options": {
|
|
"graphMode": "area",
|
|
"colorMode": "value",
|
|
"reduceOptions": { "calcs": ["lastNotNull"] }
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"expr": "(node_memory_SwapTotal_bytes - node_memory_SwapFree_bytes) / 1073741824"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "CPU Steal %",
|
|
"type": "stat",
|
|
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
|
"gridPos": { "h": 4, "w": 6, "x": 18, "y": 0 },
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "percent",
|
|
"decimals": 2,
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{ "color": "green", "value": null },
|
|
{ "color": "yellow", "value": 5 },
|
|
{ "color": "red", "value": 15 }
|
|
]
|
|
}
|
|
}
|
|
},
|
|
"options": {
|
|
"graphMode": "area",
|
|
"colorMode": "value",
|
|
"reduceOptions": { "calcs": ["lastNotNull"] }
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"expr": "avg(rate(node_cpu_seconds_total{mode=\"steal\"}[5m])) * 100"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Disk Used % — 7d trend",
|
|
"type": "timeseries",
|
|
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
|
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 4 },
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "percent",
|
|
"custom": { "fillOpacity": 15, "lineWidth": 2 }
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"expr": "(1 - node_filesystem_avail_bytes{mountpoint=\"/\"} / node_filesystem_size_bytes{mountpoint=\"/\"}) * 100",
|
|
"legendFormat": "/"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "RAM Available — 7d trend",
|
|
"type": "timeseries",
|
|
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
|
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 4 },
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "decgbytes",
|
|
"custom": { "fillOpacity": 15, "lineWidth": 2 }
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"expr": "node_memory_MemAvailable_bytes / 1073741824",
|
|
"legendFormat": "Available"
|
|
},
|
|
{
|
|
"refId": "B",
|
|
"expr": "(node_memory_SwapTotal_bytes - node_memory_SwapFree_bytes) / 1073741824",
|
|
"legendFormat": "Swap used"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "CPU Steal % — 7d trend",
|
|
"type": "timeseries",
|
|
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
|
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 12 },
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "percent",
|
|
"custom": { "fillOpacity": 15, "lineWidth": 2 }
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"expr": "avg(rate(node_cpu_seconds_total{mode=\"steal\"}[5m])) * 100",
|
|
"legendFormat": "steal"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Disk Writes (sda) — GB/hr",
|
|
"type": "timeseries",
|
|
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
|
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 12 },
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "decgbytes",
|
|
"custom": { "fillOpacity": 15, "lineWidth": 2 }
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"expr": "rate(node_disk_written_bytes_total{device=\"sda\"}[5m]) * 3600 / 1073741824",
|
|
"legendFormat": "GB/hr"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Top 10 Containers by Memory",
|
|
"type": "bargauge",
|
|
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
|
"gridPos": { "h": 10, "w": 12, "x": 0, "y": 20 },
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "decmbytes",
|
|
"decimals": 1
|
|
}
|
|
},
|
|
"options": {
|
|
"orientation": "horizontal",
|
|
"displayMode": "gradient",
|
|
"reduceOptions": { "calcs": ["lastNotNull"] }
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"expr": "topk(10, container_memory_working_set_bytes{name!=\"\"} / 1048576)",
|
|
"legendFormat": "{{name}}"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Top 10 Containers by CPU",
|
|
"type": "bargauge",
|
|
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
|
"gridPos": { "h": 10, "w": 12, "x": 12, "y": 20 },
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "percent",
|
|
"decimals": 2
|
|
}
|
|
},
|
|
"options": {
|
|
"orientation": "horizontal",
|
|
"displayMode": "gradient",
|
|
"reduceOptions": { "calcs": ["lastNotNull"] }
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"expr": "topk(10, sum by (name) (rate(container_cpu_usage_seconds_total{name!=\"\"}[5m])) * 100)",
|
|
"legendFormat": "{{name}}"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Load Average (1m / 5m / 15m)",
|
|
"type": "timeseries",
|
|
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
|
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 30 },
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": { "fillOpacity": 10, "lineWidth": 2 }
|
|
}
|
|
},
|
|
"targets": [
|
|
{ "refId": "A", "expr": "node_load1", "legendFormat": "1m" },
|
|
{ "refId": "B", "expr": "node_load5", "legendFormat": "5m" },
|
|
{ "refId": "C", "expr": "node_load15", "legendFormat": "15m" }
|
|
]
|
|
},
|
|
{
|
|
"title": "Network Throughput (sum of all interfaces)",
|
|
"type": "timeseries",
|
|
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
|
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 30 },
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "Bps",
|
|
"custom": { "fillOpacity": 10, "lineWidth": 2 }
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"expr": "sum(rate(node_network_receive_bytes_total{device!~\"lo|veth.*|docker.*|br-.*\"}[5m]))",
|
|
"legendFormat": "RX"
|
|
},
|
|
{
|
|
"refId": "B",
|
|
"expr": "sum(rate(node_network_transmit_bytes_total{device!~\"lo|veth.*|docker.*|br-.*\"}[5m]))",
|
|
"legendFormat": "TX"
|
|
}
|
|
]
|
|
}
|
|
]
|
|
}
|