Erich Blume
483db74a3c
Adds smartctl_exporter alongside the existing node_exporter on sifaka, routed through Caddy L4 TCP proxy at nas.ops.eblu.me, with a Grafana dashboard for disk health visibility. Introduces the first Ansible playbook for sifaka (mise run provision-sifaka) and shared exporter port variables in group_vars/all.yml. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
314 lines
12 KiB
YAML
314 lines
12 KiB
YAML
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
name: grafana-dashboard-sifaka-disks
|
|
namespace: monitoring
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
data:
|
|
sifaka-disks.json: |
|
|
{
|
|
"annotations": { "list": [] },
|
|
"editable": true,
|
|
"fiscalYearStartMonth": 0,
|
|
"graphTooltip": 1,
|
|
"id": null,
|
|
"links": [],
|
|
"panels": [
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": { "h": 1, "w": 24, "x": 0, "y": 0 },
|
|
"id": 100,
|
|
"panels": [],
|
|
"title": "Health Overview",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": { "mode": "thresholds" },
|
|
"mappings": [
|
|
{ "options": { "0": { "color": "red", "text": "FAILING" }, "1": { "color": "green", "text": "HEALTHY" } }, "type": "value" }
|
|
],
|
|
"thresholds": { "mode": "absolute", "steps": [{ "color": "red", "value": null }, { "color": "green", "value": 1 }] }
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": { "h": 4, "w": 24, "x": 0, "y": 1 },
|
|
"id": 1,
|
|
"options": {
|
|
"colorMode": "background",
|
|
"graphMode": "none",
|
|
"justifyMode": "center",
|
|
"orientation": "horizontal",
|
|
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
|
"textMode": "value_and_name"
|
|
},
|
|
"targets": [
|
|
{ "datasource": { "type": "prometheus", "uid": "prometheus" }, "expr": "smartctl_device_smart_healthy{job=\"smartctl-sifaka\"}", "legendFormat": "{{device}} ({{model_name}})", "refId": "A" }
|
|
],
|
|
"title": "SMART Health Status",
|
|
"type": "stat"
|
|
},
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": { "h": 1, "w": 24, "x": 0, "y": 5 },
|
|
"id": 101,
|
|
"panels": [],
|
|
"title": "Temperature",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": { "mode": "thresholds" },
|
|
"mappings": [],
|
|
"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }, { "color": "yellow", "value": 40 }, { "color": "red", "value": 50 }] },
|
|
"unit": "celsius"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": { "h": 4, "w": 24, "x": 0, "y": 6 },
|
|
"id": 2,
|
|
"options": {
|
|
"colorMode": "value",
|
|
"graphMode": "none",
|
|
"justifyMode": "center",
|
|
"orientation": "horizontal",
|
|
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
|
"textMode": "value_and_name"
|
|
},
|
|
"targets": [
|
|
{ "datasource": { "type": "prometheus", "uid": "prometheus" }, "expr": "smartctl_device_temperature{job=\"smartctl-sifaka\"}", "legendFormat": "{{device}}", "refId": "A" }
|
|
],
|
|
"title": "Current Temperature",
|
|
"type": "stat"
|
|
},
|
|
{
|
|
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": { "mode": "palette-classic" },
|
|
"custom": {
|
|
"axisBorderShow": false,
|
|
"axisCenteredZero": false,
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"drawStyle": "line",
|
|
"fillOpacity": 10,
|
|
"gradientMode": "none",
|
|
"hideFrom": { "legend": false, "tooltip": false, "viz": false },
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 1,
|
|
"pointSize": 5,
|
|
"showPoints": "never",
|
|
"spanNulls": false,
|
|
"stacking": { "group": "A", "mode": "none" },
|
|
"thresholdsStyle": { "mode": "line+area" }
|
|
},
|
|
"mappings": [],
|
|
"thresholds": { "mode": "absolute", "steps": [{ "color": "transparent", "value": null }, { "color": "red", "value": 50 }] },
|
|
"unit": "celsius"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": { "h": 8, "w": 24, "x": 0, "y": 10 },
|
|
"id": 3,
|
|
"options": {
|
|
"legend": { "calcs": ["mean", "max"], "displayMode": "table", "placement": "right", "showLegend": true },
|
|
"tooltip": { "mode": "multi", "sort": "desc" }
|
|
},
|
|
"targets": [
|
|
{ "datasource": { "type": "prometheus", "uid": "prometheus" }, "expr": "smartctl_device_temperature{job=\"smartctl-sifaka\"}", "legendFormat": "{{device}}", "refId": "A" }
|
|
],
|
|
"title": "Temperature Over Time",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": { "h": 1, "w": 24, "x": 0, "y": 18 },
|
|
"id": 102,
|
|
"panels": [],
|
|
"title": "Wear Indicators",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": { "mode": "thresholds" },
|
|
"mappings": [],
|
|
"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }, { "color": "yellow", "value": 1 }, { "color": "red", "value": 10 }] }
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": { "h": 4, "w": 12, "x": 0, "y": 19 },
|
|
"id": 4,
|
|
"options": {
|
|
"colorMode": "value",
|
|
"graphMode": "none",
|
|
"justifyMode": "center",
|
|
"orientation": "horizontal",
|
|
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
|
"textMode": "value_and_name"
|
|
},
|
|
"targets": [
|
|
{ "datasource": { "type": "prometheus", "uid": "prometheus" }, "expr": "smartctl_device_attribute{job=\"smartctl-sifaka\", attribute_name=\"Reallocated_Sector_Ct\", attribute_value_type=\"raw\"}", "legendFormat": "{{device}}", "refId": "A" }
|
|
],
|
|
"title": "Reallocated Sectors",
|
|
"type": "stat"
|
|
},
|
|
{
|
|
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": { "mode": "thresholds" },
|
|
"mappings": [],
|
|
"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }, { "color": "yellow", "value": 1 }, { "color": "red", "value": 10 }] }
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": { "h": 4, "w": 12, "x": 12, "y": 19 },
|
|
"id": 5,
|
|
"options": {
|
|
"colorMode": "value",
|
|
"graphMode": "none",
|
|
"justifyMode": "center",
|
|
"orientation": "horizontal",
|
|
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
|
"textMode": "value_and_name"
|
|
},
|
|
"targets": [
|
|
{ "datasource": { "type": "prometheus", "uid": "prometheus" }, "expr": "smartctl_device_attribute{job=\"smartctl-sifaka\", attribute_name=\"Current_Pending_Sector\", attribute_value_type=\"raw\"}", "legendFormat": "{{device}}", "refId": "A" }
|
|
],
|
|
"title": "Pending Sectors",
|
|
"type": "stat"
|
|
},
|
|
{
|
|
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": { "mode": "thresholds" },
|
|
"mappings": [],
|
|
"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }, { "color": "yellow", "value": 1 }, { "color": "red", "value": 100 }] }
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": { "h": 4, "w": 12, "x": 0, "y": 23 },
|
|
"id": 6,
|
|
"options": {
|
|
"colorMode": "value",
|
|
"graphMode": "none",
|
|
"justifyMode": "center",
|
|
"orientation": "horizontal",
|
|
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
|
"textMode": "value_and_name"
|
|
},
|
|
"targets": [
|
|
{ "datasource": { "type": "prometheus", "uid": "prometheus" }, "expr": "smartctl_device_attribute{job=\"smartctl-sifaka\", attribute_name=\"UDMA_CRC_Error_Count\", attribute_value_type=\"raw\"}", "legendFormat": "{{device}}", "refId": "A" }
|
|
],
|
|
"title": "UDMA CRC Errors",
|
|
"type": "stat"
|
|
},
|
|
{
|
|
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": { "mode": "thresholds" },
|
|
"mappings": [],
|
|
"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }, { "color": "yellow", "value": 1 }, { "color": "red", "value": 10 }] }
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": { "h": 4, "w": 12, "x": 12, "y": 23 },
|
|
"id": 7,
|
|
"options": {
|
|
"colorMode": "value",
|
|
"graphMode": "none",
|
|
"justifyMode": "center",
|
|
"orientation": "horizontal",
|
|
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
|
"textMode": "value_and_name"
|
|
},
|
|
"targets": [
|
|
{ "datasource": { "type": "prometheus", "uid": "prometheus" }, "expr": "smartctl_device_attribute{job=\"smartctl-sifaka\", attribute_name=\"Offline_Uncorrectable\", attribute_value_type=\"raw\"}", "legendFormat": "{{device}}", "refId": "A" }
|
|
],
|
|
"title": "Offline Uncorrectable Sectors",
|
|
"type": "stat"
|
|
},
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": { "h": 1, "w": 24, "x": 0, "y": 27 },
|
|
"id": 103,
|
|
"panels": [],
|
|
"title": "Lifetime",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": { "mode": "thresholds" },
|
|
"mappings": [],
|
|
"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }] },
|
|
"unit": "h"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": { "h": 4, "w": 12, "x": 0, "y": 28 },
|
|
"id": 8,
|
|
"options": {
|
|
"colorMode": "value",
|
|
"graphMode": "none",
|
|
"justifyMode": "center",
|
|
"orientation": "horizontal",
|
|
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
|
"textMode": "value_and_name"
|
|
},
|
|
"targets": [
|
|
{ "datasource": { "type": "prometheus", "uid": "prometheus" }, "expr": "smartctl_device_power_on_seconds{job=\"smartctl-sifaka\"} / 3600", "legendFormat": "{{device}}", "refId": "A" }
|
|
],
|
|
"title": "Power-On Hours",
|
|
"type": "stat"
|
|
},
|
|
{
|
|
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": { "mode": "thresholds" },
|
|
"mappings": [],
|
|
"thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }] }
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": { "h": 4, "w": 12, "x": 12, "y": 28 },
|
|
"id": 9,
|
|
"options": {
|
|
"colorMode": "value",
|
|
"graphMode": "none",
|
|
"justifyMode": "center",
|
|
"orientation": "horizontal",
|
|
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
|
"textMode": "value_and_name"
|
|
},
|
|
"targets": [
|
|
{ "datasource": { "type": "prometheus", "uid": "prometheus" }, "expr": "smartctl_device_power_cycle_count{job=\"smartctl-sifaka\"}", "legendFormat": "{{device}}", "refId": "A" }
|
|
],
|
|
"title": "Power Cycle Count",
|
|
"type": "stat"
|
|
}
|
|
],
|
|
"refresh": "1m",
|
|
"schemaVersion": 38,
|
|
"tags": ["sifaka", "storage", "smart"],
|
|
"templating": { "list": [] },
|
|
"time": { "from": "now-24h", "to": "now" },
|
|
"timepicker": {},
|
|
"timezone": "browser",
|
|
"title": "Sifaka Disk Health",
|
|
"uid": "sifaka-disk-health",
|
|
"version": 1,
|
|
"weekStart": ""
|
|
}
|