setting up resource monitoring for bob and jeeves

This commit is contained in:
2026-04-28 14:23:10 -04:00
parent 957110b7e9
commit e148eeb8cc
11 changed files with 1739 additions and 24 deletions
@@ -0,0 +1,351 @@
{
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": {
"type": "grafana",
"uid": "-- Grafana --"
},
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"type": "dashboard"
}
]
},
"editable": true,
"fiscalYearStartMonth": 0,
"graphTooltip": 0,
"links": [],
"panels": [
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"fieldConfig": {
"defaults": {
"unit": "percent"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 8,
"x": 0,
"y": 0
},
"id": 1,
"options": {
"legend": {
"displayMode": "list",
"placement": "bottom"
},
"tooltip": {
"mode": "multi"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"editorMode": "code",
"expr": "100 * (zfs_pool_allocated_bytes / zfs_pool_size_bytes)",
"legendFormat": "{{instance}} {{pool}}",
"range": true,
"refId": "A"
}
],
"title": "Pool Usage",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"fieldConfig": {
"defaults": {
"unit": "bytes"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 8,
"x": 8,
"y": 0
},
"id": 2,
"options": {
"legend": {
"displayMode": "list",
"placement": "bottom"
},
"tooltip": {
"mode": "multi"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"editorMode": "code",
"expr": "zfs_pool_free_bytes",
"legendFormat": "{{instance}} {{pool}}",
"range": true,
"refId": "A"
}
],
"title": "Pool Free Bytes",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"fieldConfig": {
"defaults": {
"unit": "bytes"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 8,
"x": 16,
"y": 0
},
"id": 3,
"options": {
"cellHeight": "sm",
"showHeader": true,
"sortBy": [
{
"desc": true,
"displayName": "Value"
}
]
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"editorMode": "code",
"expr": "topk(20, zfs_dataset_used_bytes{type=\"filesystem\"})",
"format": "table",
"instant": true,
"legendFormat": "{{instance}} {{name}}",
"refId": "A"
}
],
"title": "Top Filesystems by Used Bytes",
"type": "table"
},
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"fieldConfig": {
"defaults": {
"unit": "ns"
},
"overrides": []
},
"gridPos": {
"h": 9,
"w": 12,
"x": 0,
"y": 8
},
"id": 4,
"options": {
"legend": {
"displayMode": "list",
"placement": "bottom"
},
"tooltip": {
"mode": "multi"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"editorMode": "code",
"expr": "topk(20, zpool_iostat_total_wait_read_ns{vdev!=\"_pool\"})",
"legendFormat": "{{host}} {{pool}} {{vdev}}",
"range": true,
"refId": "A"
}
],
"title": "ZFS Read Wait",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"fieldConfig": {
"defaults": {
"unit": "ns"
},
"overrides": []
},
"gridPos": {
"h": 9,
"w": 12,
"x": 12,
"y": 8
},
"id": 5,
"options": {
"legend": {
"displayMode": "list",
"placement": "bottom"
},
"tooltip": {
"mode": "multi"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"editorMode": "code",
"expr": "topk(20, zpool_iostat_total_wait_write_ns{vdev!=\"_pool\"})",
"legendFormat": "{{host}} {{pool}} {{vdev}}",
"range": true,
"refId": "A"
}
],
"title": "ZFS Write Wait",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"fieldConfig": {
"defaults": {
"unit": "celsius"
},
"overrides": []
},
"gridPos": {
"h": 9,
"w": 12,
"x": 0,
"y": 17
},
"id": 6,
"options": {
"cellHeight": "sm",
"showHeader": true,
"sortBy": [
{
"desc": true,
"displayName": "Value"
}
]
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"editorMode": "code",
"expr": "smartctl_device_temperature{temperature_type=\"current\"}",
"format": "table",
"instant": true,
"legendFormat": "{{instance}} {{device}}",
"refId": "A"
}
],
"title": "Disk Temperature",
"type": "table"
},
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"fieldConfig": {
"defaults": {
"unit": "short"
},
"overrides": []
},
"gridPos": {
"h": 9,
"w": 12,
"x": 12,
"y": 17
},
"id": 7,
"options": {
"cellHeight": "sm",
"showHeader": true,
"sortBy": [
{
"desc": false,
"displayName": "Value"
}
]
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prom-main"
},
"editorMode": "code",
"expr": "smartctl_device_smart_status",
"format": "table",
"instant": true,
"legendFormat": "{{instance}} {{device}}",
"refId": "A"
}
],
"title": "SMART Health",
"type": "table"
}
],
"refresh": "30s",
"schemaVersion": 39,
"style": "dark",
"tags": [
"monitoring",
"zfs"
],
"templating": {
"list": []
},
"time": {
"from": "now-24h",
"to": "now"
},
"timepicker": {},
"timezone": "",
"title": "Storage and ZFS",
"uid": "monitor-storage",
"version": 1,
"weekStart": ""
}