Skip to content

Instantly share code, notes, and snippets.

@david-martin

david-martin/dashboard.json

Last active April 7, 2020 08:28
Show Gist options
  • Save david-martin/5651cd085c8dd7b8cc0e5a1025023b1b to your computer and use it in GitHub Desktop.
Save david-martin/5651cd085c8dd7b8cc0e5a1025023b1b to your computer and use it in GitHub Desktop.
Download ZIP
rhmi slo dashboard
Raw
dashboard.json
{
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": "-- Grafana --",
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"type": "dashboard"
}
]
},
"editable": true,
"gnetId": null,
"graphTooltip": 0,
"id": 17,
"iteration": 1586247995722,
"links": [],
"panels": [
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 0
},
"id": 2,
"panels": [],
"title": "SLO Summary (based on critical Alerts over the last 28 days & SLO of 99.9%)",
"type": "row"
},
{
"cacheTimeout": null,
"colorBackground": true,
"colorValue": false,
"colors": [
"#C4162A",
"rgba(237, 129, 40, 0.89)",
"#299c46"
],
"decimals": 2,
"description": "% of time where *no* critical alerts were firing over the last 28 days",
"format": "percentunit",
"gauge": {
"maxValue": 100,
"minValue": 0,
"show": false,
"thresholdLabels": false,
"thresholdMarkers": true
},
"gridPos": {
"h": 4,
"w": 3,
"x": 0,
"y": 1
},
"id": 6,
"interval": null,
"links": [],
"mappingType": 1,
"mappingTypes": [
{
"name": "value to text",
"value": 1
},
{
"name": "range to text",
"value": 2
}
],
"maxDataPoints": 100,
"nullPointMode": "connected",
"nullText": null,
"options": {},
"postfix": "",
"postfixFontSize": "50%",
"prefix": "",
"prefixFontSize": "50%",
"rangeMaps": [
{
"from": "null",
"text": "N/A",
"to": "null"
}
],
"sparkline": {
"fillColor": "rgba(31, 118, 189, 0.18)",
"full": false,
"lineColor": "rgb(31, 120, 193)",
"show": false
},
"tableColumn": "",
"targets": [
{
"expr": "clamp_max(\n sum_over_time(\n (clamp_max(\n sum(absent(ALERTS{alertstate=\"firing\", severity=\"critical\"}))\n , 1\n ))[28d:10m]\n ) / (28 * 24 * 6) > 0, 1\n)",
"format": "time_series",
"instant": false,
"intervalFactor": 1,
"refId": "A"
}
],
"thresholds": "0.999,0.999",
"timeFrom": null,
"timeShift": null,
"title": "Overall SLO %",
"type": "singlestat",
"valueFontSize": "80%",
"valueMaps": [
{
"op": "=",
"text": "N/A",
"value": "null"
}
],
"valueName": "current"
},
{
"cacheTimeout": null,
"colorBackground": false,
"colorValue": false,
"colors": [
"#299c46",
"rgba(237, 129, 40, 0.89)",
"#d44a3a"
],
"decimals": null,
"description": "Total time where at least 1 critical alert was firing over the last 28 days",
"format": "ms",
"gauge": {
"maxValue": 100,
"minValue": 0,
"show": false,
"thresholdLabels": false,
"thresholdMarkers": true
},
"gridPos": {
"h": 4,
"w": 3,
"x": 3,
"y": 1
},
"hideTimeOverride": true,
"id": 10,
"interval": null,
"links": [],
"mappingType": 1,
"mappingTypes": [
{
"name": "value to text",
"value": 1
},
{
"name": "range to text",
"value": 2
}
],
"maxDataPoints": 100,
"nullPointMode": "connected",
"nullText": null,
"options": {},
"postfix": "",
"postfixFontSize": "50%",
"prefix": "",
"prefixFontSize": "50%",
"rangeMaps": [
{
"from": "null",
"text": "N/A",
"to": "null"
}
],
"sparkline": {
"fillColor": "rgba(31, 118, 189, 0.18)",
"full": false,
"lineColor": "rgb(31, 120, 193)",
"show": false
},
"tableColumn": "",
"targets": [
{
"expr": " sum_over_time(\n (clamp_max(\n sum(ALERTS{alertstate=\"firing\", severity=\"critical\"})\n , 1\n ))[28d:10m]\n ) * (10 * 60 * 1000)",
"format": "time_series",
"intervalFactor": 1,
"refId": "A"
}
],
"thresholds": "",
"timeFrom": null,
"timeShift": null,
"title": "Firing Time ",
"type": "singlestat",
"valueFontSize": "80%",
"valueMaps": [
{
"op": "=",
"text": "N/A",
"value": "null"
}
],
"valueName": "current"
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"description": "Total number of critical alerts firing over the last 28 days. ",
"fill": 1,
"gridPos": {
"h": 8,
"w": 18,
"x": 6,
"y": 1
},
"id": 12,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {},
"percentage": false,
"pointradius": 2,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(ALERTS{severity='critical', alertstate='firing'}) or vector(0)",
"format": "time_series",
"intervalFactor": 1,
"refId": "A"
}
],
"thresholds": [],
"timeFrom": "28d",
"timeRegions": [],
"timeShift": null,
"title": "Number of alerts firing ",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"decimals": 0,
"format": "none",
"label": "",
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"cacheTimeout": null,
"colorBackground": true,
"colorValue": false,
"colors": [
"#299c46",
"rgba(237, 129, 40, 0.89)",
"#C4162A"
],
"datasource": "Prometheus",
"description": "Total number of critical alerts currently firing",
"format": "none",
"gauge": {
"maxValue": 100,
"minValue": 0,
"show": false,
"thresholdLabels": false,
"thresholdMarkers": true
},
"gridPos": {
"h": 4,
"w": 3,
"x": 0,
"y": 5
},
"id": 4,
"interval": null,
"links": [],
"mappingType": 1,
"mappingTypes": [
{
"name": "value to text",
"value": 1
},
{
"name": "range to text",
"value": 2
}
],
"maxDataPoints": 100,
"nullPointMode": "connected",
"nullText": null,
"options": {},
"postfix": "",
"postfixFontSize": "50%",
"prefix": "",
"prefixFontSize": "50%",
"rangeMaps": [
{
"from": "null",
"text": "N/A",
"to": "null"
}
],
"sparkline": {
"fillColor": "rgba(31, 118, 189, 0.18)",
"full": false,
"lineColor": "rgb(31, 120, 193)",
"show": false
},
"tableColumn": "",
"targets": [
{
"expr": "sum(ALERTS {severity='critical', alertstate='firing'})",
"format": "time_series",
"intervalFactor": 1,
"refId": "A"
}
],
"thresholds": "1,1",
"timeFrom": null,
"timeShift": null,
"title": "Alerts Firing",
"type": "singlestat",
"valueFontSize": "80%",
"valueMaps": [
{
"op": "=",
"text": "N/A",
"value": "null"
}
],
"valueName": "current"
},
{
"cacheTimeout": null,
"colorBackground": true,
"colorValue": false,
"colors": [
"#C4162A",
"rgba(237, 129, 40, 0.89)",
"#299c46"
],
"decimals": 2,
"description": "Amount of time left where at least 1 critical alert can be firing before the SLO is breached for the last 28 days",
"format": "ms",
"gauge": {
"maxValue": 100,
"minValue": 0,
"show": false,
"thresholdLabels": false,
"thresholdMarkers": true
},
"gridPos": {
"h": 4,
"w": 3,
"x": 3,
"y": 5
},
"id": 8,
"interval": null,
"links": [],
"mappingType": 1,
"mappingTypes": [
{
"name": "value to text",
"value": 1
},
{
"name": "range to text",
"value": 2
}
],
"maxDataPoints": 100,
"nullPointMode": "connected",
"nullText": null,
"options": {},
"postfix": "",
"postfixFontSize": "50%",
"prefix": "",
"prefixFontSize": "50%",
"rangeMaps": [
{
"from": "null",
"text": "N/A",
"to": "null"
}
],
"sparkline": {
"fillColor": "rgba(31, 118, 189, 0.18)",
"full": false,
"lineColor": "rgb(31, 120, 193)",
"show": false
},
"tableColumn": "",
"targets": [
{
"expr": "$slo_001_ms - (sum_over_time(\n (clamp_max(\n sum(ALERTS{alertstate=\"firing\", severity=\"critical\"})\n , 1\n ))[28d:10m]\n ) * (10 * 60 * 1000))",
"format": "time_series",
"intervalFactor": 1,
"refId": "A"
}
],
"thresholds": "0,0",
"timeFrom": null,
"timeShift": null,
"title": "Remaining Error Budget",
"type": "singlestat",
"valueFontSize": "80%",
"valueMaps": [
{
"op": "=",
"text": "N/A",
"value": "null"
}
],
"valueName": "current"
}
],
"schemaVersion": 18,
"style": "dark",
"tags": [],
"templating": {
"list": [
{
"current": {
"text": "28",
"value": "28"
},
"hide": 2,
"label": "SLO in days",
"name": "slo_days",
"options": [
{
"selected": true,
"text": "28",
"value": "28"
}
],
"query": "28",
"skipUrlSync": false,
"type": "constant"
},
{
"allValue": null,
"current": {
"text": "2419200000",
"value": "2419200000"
},
"datasource": "Prometheus",
"definition": "query_result(vector($slo_days * 24 * 60 * 60 * 1000))",
"hide": 2,
"includeAll": false,
"label": "SLO in ms",
"multi": false,
"name": "slo_ms",
"options": [
{
"selected": true,
"text": "2419200000",
"value": "2419200000"
}
],
"query": "query_result(vector($slo_days * 24 * 60 * 60 * 1000))",
"refresh": 0,
"regex": "/.*\\s(.*)\\s.*/",
"skipUrlSync": false,
"sort": 0,
"tagValuesQuery": "",
"tags": [],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"current": {
"text": "2416780800",
"value": "2416780800"
},
"datasource": "Prometheus",
"definition": "query_result(vector($slo_ms * 0.999))",
"hide": 2,
"includeAll": false,
"label": "99.9% of SLO in ms",
"multi": false,
"name": "slo_999_ms",
"options": [
{
"selected": true,
"text": "2416780800",
"value": "2416780800"
}
],
"query": "query_result(vector($slo_ms * 0.999))",
"refresh": 0,
"regex": "/.*\\s(.*)\\s.*/",
"skipUrlSync": false,
"sort": 0,
"tagValuesQuery": "",
"tags": [],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"current": {
"text": "2419200",
"value": "2419200"
},
"datasource": "Prometheus",
"definition": "query_result(vector($slo_ms * 0.001))",
"hide": 2,
"includeAll": false,
"label": "0.1% in ms",
"multi": false,
"name": "slo_001_ms",
"options": [
{
"selected": true,
"text": "2419200",
"value": "2419200"
}
],
"query": "query_result(vector($slo_ms * 0.001))",
"refresh": 0,
"regex": "/.*\\s(.*)\\s.*/",
"skipUrlSync": false,
"sort": 0,
"tagValuesQuery": "",
"tags": [],
"tagsQuery": "",
"type": "query",
"useTags": false
}
]
},
"time": {
"from": "now-15m",
"to": "now"
},
"timepicker": {
"refresh_intervals": [
"5s",
"10s",
"30s",
"1m",
"5m",
"15m",
"30m",
"1h",
"2h",
"1d"
],
"time_options": [
"5m",
"15m",
"1h",
"6h",
"12h",
"24h",
"2d",
"7d",
"30d"
]
},
"timezone": "",
"title": "SLO summary",
"uid": "eT5llOjWz",
"version": 23
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment