debian-forge-composer/templates/dashboards/grafana-dashboard-image-builder-worker-general.configmap.yml
Florian Schüller 30198922a5 templates/dashboards: increase timespan readability
Also introduces "50min." as we use this now and
shorten some titles to see which charts are affected by
the `target_duration`.
2025-03-05 10:27:54 +01:00

2074 lines
61 KiB
YAML

apiVersion: v1
kind: ConfigMap
metadata:
name: grafana-dashboard-image-builder-worker-general
labels:
grafana_dashboard: "true"
annotations:
grafana-folder: /grafana-dashboard-definitions/Image-Builder
data:
grafana.json: |-
{
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": {
"type": "datasource",
"uid": "grafana"
},
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"target": {
"limit": 100,
"matchAny": false,
"tags": [],
"type": "dashboard"
},
"type": "dashboard"
}
]
},
"editable": true,
"fiscalYearStartMonth": 0,
"graphTooltip": 1,
"links": [],
"liveNow": false,
"panels": [
{
"collapsed": false,
"datasource": {
"uid": "${datasource}"
},
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 0
},
"id": 212,
"panels": [],
"title": "Job Success Rate",
"type": "row"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "The percentage of successful jobs for the selected job type(s) and time range",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"decimals": 0,
"mappings": [
{
"options": {
"match": "null",
"result": {
"index": 0,
"text": "0%"
}
},
"type": "special"
}
],
"noValue": "0",
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "red",
"value": null
},
{
"color": "#EAB839",
"value": "0.95"
},
{
"color": "green",
"value": "0.955"
}
]
},
"unit": "percentunit"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 4,
"x": 0,
"y": 1
},
"id": 197,
"mappings": [
{
"options": {
"match": "null",
"result": {
"text": "N/A"
}
},
"type": "special"
}
],
"options": {
"colorMode": "value",
"graphMode": "none",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showPercentChange": false,
"text": {},
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "10.4.1",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"exemplar": true,
"expr": "1 - (\n (\n sum(increase(image_builder_worker_total_jobs{type=~\"$jobtype\", status=\"5xx\", tenant=~\"$tenant\", arch=~\"$arch\"}[$__range]))\n /\n sum(increase(image_builder_worker_total_jobs{type=~\"$jobtype\", status!=\"4xx\", tenant=~\"$tenant\", arch=~\"$arch\"}[$__range])) \n ) OR on() vector(0) # set a fallback if the query result is empty\n)",
"interval": "",
"legendFormat": "",
"refId": "A"
}
],
"title": "Job Success Rate",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "The throughput rate of job errors and non-errors over time for the selected job type(s) and time range",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 11,
"gradientMode": "opacity",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 1,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "red",
"value": null
}
]
},
"unit": "none"
},
"overrides": [
{
"matcher": {
"id": "byName",
"options": "success/sec"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "green",
"mode": "fixed"
}
}
]
}
]
},
"gridPos": {
"h": 8,
"w": 12,
"x": 4,
"y": 1
},
"id": 202,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"exemplar": true,
"expr": "(sum(rate(image_builder_worker_total_jobs{type=~\"$jobtype\", status!=\"4xx\", tenant=~\"$tenant\", arch=~\"$arch\"}[$__rate_interval])) OR on() vector(0))\n- \n(sum(rate(image_builder_worker_total_jobs{type=~\"$jobtype\", status=\"5xx\", tenant=~\"$tenant\", arch=~\"$arch\"}[$__rate_interval])) OR on() vector(0))",
"hide": false,
"interval": "300",
"legendFormat": "success/sec",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"exemplar": true,
"expr": "(sum(rate(image_builder_worker_total_jobs{type=~\"$jobtype\", status=\"5xx\", tenant=~\"$tenant\", arch=~\"$arch\"}[$__rate_interval])) OR on() vector(0))",
"hide": false,
"interval": "300",
"legendFormat": "errors/sec",
"range": true,
"refId": "B"
}
],
"title": "Job Throughput Rate",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "The number of job errors (as a percentage) over time for the selected job type(s) and time range",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "bars",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"max": 1,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "red",
"value": null
}
]
},
"unit": "percentunit"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 8,
"x": 16,
"y": 1
},
"id": 228,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": false
},
"tooltip": {
"mode": "multi",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"exemplar": true,
"expr": "(\n sum(rate(image_builder_worker_total_jobs{type=~\"$jobtype\", status=\"5xx\", tenant=~\"$tenant\", arch=~\"$arch\"}[$__rate_interval]))\n /\n sum(rate(image_builder_worker_total_jobs{type=~\"$jobtype\", status!=\"4xx\", tenant=~\"$tenant\", arch=~\"$arch\"}[$__rate_interval]))\n)\nOR on() vector(0) # set fallback incase the above query result is empty",
"interval": "300",
"legendFormat": "",
"range": true,
"refId": "A"
}
],
"title": "Job Error Rate",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "How long will it take to consume all our budget if our error consumption remains at the current rate for the selected date range.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"decimals": 2,
"mappings": [
{
"options": {
"match": "null",
"result": {
"color": "green",
"index": 0,
"text": "∞"
}
},
"type": "special"
},
{
"options": {
"from": 672,
"result": {
"index": 1,
"text": "∞"
},
"to": 3360100
},
"type": "range"
}
],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "red",
"value": null
},
{
"color": "#EAB839",
"value": 504
},
{
"color": "green",
"value": 672
}
]
},
"unit": "h"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 4,
"x": 0,
"y": 9
},
"id": 238,
"maxDataPoints": 100,
"options": {
"colorMode": "value",
"graphMode": "none",
"justifyMode": "auto",
"orientation": "horizontal",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showPercentChange": false,
"text": {
"valueSize": 80
},
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "10.4.1",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"exemplar": true,
"expr": "28 * 24 * (1 - $stability_slo)\n/ \n(\n (\n sum(rate(image_builder_worker_total_jobs{type=~\"$jobtype\", status=\"5xx\", tenant=~\"$tenant\", arch=~\"$arch\"}[28d]))\n / \n sum(rate(image_builder_worker_total_jobs{type=~\"$jobtype\", status!=\"4xx\", tenant=~\"$tenant\", arch=~\"$arch\"}[28d]))\n ) OR on() vector(0.01) # set fallback incase the above query result is empty\n)",
"format": "time_series",
"interval": "",
"intervalFactor": 1,
"legendFormat": "",
"refId": "A"
}
],
"title": "Error Budget Remaining",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "The percentage of error budget consumed for the selected time range. ",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 100,
"gradientMode": "scheme",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineStyle": {
"fill": "solid"
},
"lineWidth": 0,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": true,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"links": [],
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "#EAB839",
"value": 0.95
},
{
"color": "red",
"value": 1
}
]
},
"unit": "percentunit"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 20,
"x": 4,
"y": 9
},
"id": 239,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": false
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "8.1.5",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"exemplar": true,
"expr": "1 - (\n (\n 1 - $stability_slo - (\n (\n sum(increase(image_builder_worker_total_jobs{type=~\"$jobtype\", status=\"5xx\", tenant=~\"$tenant\", arch=~\"$arch\"}[28d]))\n /\n sum(increase(image_builder_worker_total_jobs{type=~\"$jobtype\", status!=\"4xx\", tenant=~\"$tenant\", arch=~\"$arch\"}[28d]))\n ) OR on() vector(0) # set fallback for empty query result\n ) \n ) \n)\n/ \n(1 - $stability_slo)",
"instant": false,
"interval": "",
"intervalFactor": 10,
"legendFormat": "errorbudget",
"refId": "A"
}
],
"title": "Error Budget Consumed",
"type": "timeseries"
},
{
"collapsed": false,
"datasource": {
"uid": "${datasource}"
},
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 17
},
"id": 129,
"panels": [],
"title": "Job Duration",
"type": "row"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "The duration of 95% of jobs for the selected job type(s).",
"fieldConfig": {
"defaults": {
"color": {
"fixedColor": "blue",
"mode": "fixed"
},
"decimals": 0,
"mappings": [
{
"options": {
"match": "null",
"result": {
"index": 0,
"text": "N/A"
}
},
"type": "special"
}
],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "#EAB839",
"value": "1228"
},
{
"color": "red",
"value": "1536"
}
]
},
"unit": "s"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 4,
"x": 0,
"y": 18
},
"id": 200,
"mappings": [
{
"options": {
"match": "null",
"result": {
"text": "N/A"
}
},
"type": "special"
}
],
"options": {
"colorMode": "value",
"graphMode": "none",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showPercentChange": false,
"text": {},
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "10.4.1",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"exemplar": true,
"expr": "histogram_quantile(0.95, sum(rate(image_builder_worker_job_duration_seconds_bucket{type=~\"$jobtype\", tenant=~\"$tenant\", arch=~\"$arch\"}[$__range])) by (le))",
"interval": "",
"legendFormat": "",
"refId": "A"
}
],
"title": "Job Duration",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "The duration of selected jobs over the selected date range, organized by percentiles. The purple line indicates the SLO target.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "seconds",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 35,
"gradientMode": "scheme",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 3,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": true,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "line"
}
},
"mappings": [],
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "dark-purple",
"value": 30
},
{
"color": "dark-purple",
"value": 2400
}
]
},
"unit": "s"
},
"overrides": [
{
"matcher": {
"id": "byName",
"options": "p50"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "light-red",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "p95"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "yellow",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "p99"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "blue",
"mode": "fixed"
}
}
]
}
]
},
"gridPos": {
"h": 8,
"w": 12,
"x": 4,
"y": 18
},
"id": 201,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"exemplar": true,
"expr": "histogram_quantile(0.99, sum(rate(image_builder_worker_job_duration_seconds_bucket{type=~\"$jobtype\", tenant=~\"$tenant\", arch=~\"$arch\"}[$__rate_interval])) by (le))",
"hide": false,
"interval": "300",
"legendFormat": "p99",
"range": true,
"refId": "C"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"exemplar": true,
"expr": "histogram_quantile(0.95, sum(rate(image_builder_worker_job_duration_seconds_bucket{type=~\"$jobtype\", tenant=~\"$tenant\", arch=~\"$arch\"}[$__rate_interval])) by (le))",
"hide": false,
"interval": "300",
"legendFormat": "p95",
"range": true,
"refId": "B"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"exemplar": true,
"expr": "histogram_quantile(0.5, sum(rate(image_builder_worker_job_duration_seconds_bucket{type=~\"$jobtype\", tenant=~\"$tenant\", arch=~\"$arch\"}[$__rate_interval])) by (le))",
"interval": "300",
"legendFormat": "p50",
"range": true,
"refId": "A"
}
],
"title": "Job Duration",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "Percent of requests exceeding the duration allowed by SLO.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 1,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"max": 1,
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "percentunit"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 8,
"x": 16,
"y": 18
},
"id": 210,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": false
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"exemplar": true,
"expr": "1 - (\n sum(rate(image_builder_worker_job_duration_seconds_bucket{le=\"$target_duration\",type=~\"$jobtype\", tenant=~\"$tenant\", arch=~\"$arch\"}[$__rate_interval]))\n /\n sum(rate(image_builder_worker_job_duration_seconds_count{type=~\"$jobtype\", tenant=~\"$tenant\", arch=~\"$arch\"}[$__rate_interval]))\n)",
"interval": "300",
"legendFormat": "",
"range": true,
"refId": "A"
}
],
"title": "Slow Request Rate ($target_duration)",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "How long will it take to consume all our budget if our error consumption remains at the current rate for the selected date range.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"decimals": 2,
"mappings": [
{
"options": {
"match": "null",
"result": {
"index": 0,
"text": "∞"
}
},
"type": "special"
},
{
"options": {
"from": 672,
"result": {
"index": 1,
"text": "∞"
},
"to": 3360100
},
"type": "range"
}
],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "red",
"value": null
},
{
"color": "#EAB839",
"value": 504
},
{
"color": "green",
"value": 672
}
]
},
"unit": "h"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 4,
"x": 0,
"y": 26
},
"id": 198,
"maxDataPoints": 100,
"options": {
"colorMode": "value",
"graphMode": "none",
"justifyMode": "auto",
"orientation": "horizontal",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showPercentChange": false,
"text": {
"valueSize": 80
},
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "10.4.1",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"exemplar": true,
"expr": "28 * 24 * (1 - $latency_slo) \n/ \n( \n 1.001 - ( \n (\n sum(rate(image_builder_worker_job_duration_seconds_bucket{le=\"$target_duration\",type=~\"$jobtype\", tenant=~\"$tenant\", arch=~\"$arch\"}[28d]))\n /\n sum(rate(image_builder_worker_job_duration_seconds_count{type=~\"$jobtype\", tenant=~\"$tenant\", arch=~\"$arch\"}[28d]))\n ) OR on() vector(1) # set fallback incase the above query result is empty\n )\n)",
"format": "time_series",
"interval": "",
"intervalFactor": 1,
"legendFormat": "",
"range": true,
"refId": "A"
}
],
"title": "Err Budget Remain ($target_duration)",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "The percentage of error budget consumed for the selected time range. ",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 100,
"gradientMode": "scheme",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineStyle": {
"fill": "solid"
},
"lineWidth": 0,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": true,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"links": [],
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "#EAB839",
"value": 0.95
},
{
"color": "red",
"value": 1
}
]
},
"unit": "percentunit"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 20,
"x": 4,
"y": 26
},
"id": 199,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": false
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "8.1.5",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"exemplar": true,
"expr": "1 - (\n (\n (\n sum(increase(image_builder_worker_job_duration_seconds_bucket{le=\"$target_duration\",type=~\"$jobtype\", tenant=~\"$tenant\", arch=~\"$arch\"}[28d]))\n /\n sum(increase(image_builder_worker_job_duration_seconds_count{type=~\"$jobtype\", tenant=~\"$tenant\", arch=~\"$arch\"}[28d])) \n ) OR on() vector(1) \n ) - $latency_slo\n)\n/\n(1 - $latency_slo)",
"instant": false,
"interval": "",
"intervalFactor": 10,
"legendFormat": "errorbudget",
"refId": "A"
}
],
"title": "Error Budget Consumed ($target_duration)",
"type": "timeseries"
},
{
"collapsed": false,
"datasource": {
"uid": "${datasource}"
},
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 34
},
"id": 207,
"panels": [],
"title": "Job Wait Duration",
"type": "row"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "The duration of 95% of jobs waiting for execution in the job queue for the selection jobtype(s).",
"fieldConfig": {
"defaults": {
"color": {
"fixedColor": "blue",
"mode": "fixed"
},
"decimals": 0,
"mappings": [
{
"options": {
"match": "null",
"result": {
"index": 0,
"text": "N/A"
}
},
"type": "special"
}
],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green"
},
{
"color": "#EAB839",
"value": "1228"
},
{
"color": "red",
"value": "1536"
}
]
},
"unit": "s"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 4,
"x": 0,
"y": 35
},
"id": 208,
"mappings": [
{
"options": {
"match": "null",
"result": {
"text": "N/A"
}
},
"type": "special"
}
],
"options": {
"colorMode": "value",
"graphMode": "none",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showPercentChange": false,
"text": {},
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "10.4.1",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"exemplar": true,
"expr": "histogram_quantile(0.95, sum(rate(image_builder_worker_job_wait_duration_seconds_bucket{type=~\"$jobtype\",tenant=~\"$tenant\", arch=~\"$arch\"}[$__range])) by (le))",
"interval": "",
"legendFormat": "",
"range": true,
"refId": "A"
}
],
"title": "Job Wait Duration",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "The duration for jobs waiting in the job queue over the selected date range, for the selected job type(s).",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "seconds",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 35,
"gradientMode": "scheme",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 3,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": true,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green"
}
]
},
"unit": "s"
},
"overrides": [
{
"matcher": {
"id": "byName",
"options": "p50"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "light-red",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "p95"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "yellow",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "p99"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "blue",
"mode": "fixed"
}
}
]
}
]
},
"gridPos": {
"h": 8,
"w": 12,
"x": 4,
"y": 35
},
"id": 209,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"exemplar": true,
"expr": "histogram_quantile(0.99, sum(rate(image_builder_worker_job_wait_duration_seconds_bucket{type=~\"$jobtype\",tenant=~\"$tenant\", arch=~\"$arch\"}[$__rate_interval])) by (le))",
"hide": false,
"interval": "300",
"legendFormat": "p99",
"range": true,
"refId": "C"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"exemplar": true,
"expr": "histogram_quantile(0.95, sum(rate(image_builder_worker_job_wait_duration_seconds_bucket{type=~\"$jobtype\",tenant=~\"$tenant\", arch=~\"$arch\"}[$__rate_interval])) by (le))",
"hide": false,
"interval": "300",
"legendFormat": "p95",
"range": true,
"refId": "B"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"exemplar": true,
"expr": "histogram_quantile(0.5, sum(rate(image_builder_worker_job_wait_duration_seconds_bucket{type=~\"$jobtype\",tenant=~\"$tenant\", arch=~\"$arch\"}[$__rate_interval])) by (le))",
"interval": "300",
"legendFormat": "p50",
"range": true,
"refId": "A"
}
],
"title": "Job Wait Duration",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "Percent of requests exceeding duration allowed by SLO.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 1,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"max": 1,
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green"
},
{
"color": "red",
"value": 80
}
]
},
"unit": "percentunit"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 8,
"x": 16,
"y": 35
},
"id": 204,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": false
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"exemplar": true,
"expr": "1 - sum(rate(image_builder_worker_job_wait_duration_seconds_bucket{le=\"$target_duration\",type=~\"$jobtype\",tenant=~\"$tenant\"}[$__rate_interval]))/sum(rate(image_builder_worker_job_wait_duration_seconds_count{type=~\"$jobtype\",tenant=~\"$tenant\"}[$__rate_interval]))",
"interval": "300",
"legendFormat": "",
"range": true,
"refId": "A"
}
],
"title": "Slow Request Rate ($target_duration)",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "Maximum number of pending Jobs per type",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green"
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 4,
"x": 0,
"y": 52
},
"id": 246,
"options": {
"colorMode": "value",
"graphMode": "none",
"justifyMode": "center",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"max"
],
"fields": "",
"values": false
},
"showPercentChange": false,
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "10.4.1",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"disableTextWrap": false,
"editorMode": "code",
"exemplar": false,
"expr": "sum(image_builder_worker_pending_jobs) by (type)",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "{{type}}",
"range": true,
"refId": "A",
"useBackend": false
}
],
"title": "Pending Jobs Max",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "Pending Jobs per type over time",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "number of jobs",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green"
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 4,
"y": 52
},
"id": 245,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "10.4.1",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "sum(image_builder_worker_pending_jobs) by (type)",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "{{type}}",
"range": true,
"refId": "A",
"useBackend": false
}
],
"title": "Pending Jobs",
"type": "timeseries"
}
],
"refresh": false,
"schemaVersion": 39,
"tags": [],
"templating": {
"list": [
{
"current": {
"selected": false,
"text": "app-sre-prod-04-prometheus",
"value": "app-sre-prod-04-prometheus"
},
"hide": 0,
"includeAll": false,
"multi": false,
"name": "datasource",
"options": [],
"query": "prometheus",
"queryValue": "",
"refresh": 1,
"regex": "/app-sre-(prod-04|stage-01)-prometheus/",
"skipUrlSync": false,
"type": "datasource"
},
{
"description": "Compose stability SLO target",
"hide": 2,
"name": "stability_slo",
"query": "0.95",
"skipUrlSync": false,
"type": "constant"
},
{
"description": "Compose Duration SLO target",
"hide": 2,
"name": "latency_slo",
"query": "0.95",
"skipUrlSync": false,
"type": "constant"
},
{
"allValue": ".*",
"current": {
"selected": true,
"text": [
"All"
],
"value": [
"$__all"
]
},
"hide": 0,
"includeAll": true,
"multi": true,
"name": "tenant",
"options": [
{
"selected": true,
"text": "All",
"value": "$__all"
},
{
"selected": false,
"text": "crc stage",
"value": "org-15877963"
},
{
"selected": false,
"text": "fedora stage",
"value": "org-15842261"
},
{
"selected": false,
"text": "brew stage",
"value": "org-16133643"
},
{
"selected": false,
"text": "community stage",
"value": "org-17546013"
},
{
"selected": false,
"text": "crc production",
"value": "org-15885990"
},
{
"selected": false,
"text": "fedora production",
"value": "org-16057323"
},
{
"selected": false,
"text": "brew production",
"value": "org-16135456"
}
],
"query": "crc stage : org-15877963,fedora stage : org-15842261,brew stage : org-16133643,community stage : org-17546013,crc production : org-15885990,fedora production : org-16057323,brew production : org-16135456",
"queryValue": "",
"skipUrlSync": false,
"type": "custom"
},
{
"allValue": ".*",
"current": {
"selected": true,
"text": [
"All"
],
"value": [
"$__all"
]
},
"hide": 0,
"includeAll": true,
"multi": true,
"name": "arch",
"options": [
{
"selected": true,
"text": "All",
"value": "$__all"
},
{
"selected": false,
"text": "x86_64",
"value": "x86_64"
},
{
"selected": false,
"text": "aarch64",
"value": "aarch64"
},
{
"selected": false,
"text": "ppc64le",
"value": "ppc64le"
},
{
"selected": false,
"text": "s390x",
"value": "s390x"
}
],
"query": "x86_64, aarch64, ppc64le, s390x",
"queryValue": "",
"skipUrlSync": false,
"type": "custom"
},
{
"allValue": ".*",
"current": {
"selected": true,
"text": [
"All"
],
"value": [
"$__all"
]
},
"description": "The job type to display results for",
"hide": 0,
"includeAll": true,
"label": "Job type",
"multi": true,
"name": "jobtype",
"options": [
{
"selected": true,
"text": "All",
"value": "$__all"
},
{
"selected": false,
"text": "osbuild",
"value": "osbuild"
},
{
"selected": false,
"text": "depsolve",
"value": "depsolve"
},
{
"selected": false,
"text": "manifest-id-only",
"value": "manifest-id-only"
},
{
"selected": false,
"text": "container-resolve",
"value": "container-resolve"
},
{
"selected": false,
"text": "ostree-resolve",
"value": "ostree-resolve"
},
{
"selected": false,
"text": "aws-ec2-copy",
"value": "aws-ec2-copy"
},
{
"selected": false,
"text": "aws-ec2-share",
"value": "aws-ec2-share"
},
{
"selected": false,
"text": "koji-init",
"value": "koji-init"
},
{
"selected": false,
"text": "koji-finalize",
"value": "koji-finalize"
}
],
"query": "osbuild, depsolve, manifest-id-only, container-resolve, ostree-resolve, aws-ec2-copy, aws-ec2-share, koji-init, koji-finalize",
"queryValue": "",
"skipUrlSync": false,
"type": "custom"
},
{
"current": {
"selected": false,
"text": "50min",
"value": "3000"
},
"description": "The duration in seconds 95% of jobs should adhere to.",
"hide": 0,
"includeAll": false,
"label": "Target duration",
"multi": false,
"name": "target_duration",
"options": [
{
"selected": false,
"text": "30sec",
"value": "30"
},
{
"selected": false,
"text": "1min",
"value": "60"
},
{
"selected": false,
"text": "10min",
"value": "600"
},
{
"selected": false,
"text": "20min",
"value": "1200"
},
{
"selected": false,
"text": "30min",
"value": "1800"
},
{
"selected": false,
"text": "40min",
"value": "2400"
},
{
"selected": true,
"text": "50min",
"value": "3000"
},
{
"selected": false,
"text": "1h",
"value": "3600"
},
{
"selected": false,
"text": "2h",
"value": "7200"
},
{
"selected": false,
"text": "1d",
"value": "86400"
},
{
"selected": false,
"text": "3d",
"value": "259200"
}
],
"query": "30sec : 30,1min : 60,10min : 600,20min : 1200,30min : 1800,40min : 2400,50min : 3000,1h : 3600,2h : 7200,1d : 86400,3d : 259200",
"queryValue": "",
"skipUrlSync": false,
"type": "custom"
}
]
},
"time": {
"from": "now-6h",
"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",
"28d"
]
},
"timezone": "",
"title": "Image Builder Worker Job Stats",
"uid": "image-builder-worker",
"version": 21,
"weekStart": ""
}