Christian Schwarz
3f751277c2
Co-authored-by: Orsiris de Jong <ozy@netpower.fr> This PR obsoletes https://github.com/zrepl/zrepl/pull/847. Changes: * Rearrange dashboard into sections sections: About, Top, Replication, Internals. * consistently force selection of a single prom_job_name (no more multi-value) * Replace the repeated Gauge panel for failed replications with a 'status history' panel. * Use `zrepl_start_time` as the metric underlying the `prom_job_name` variable. * Replace `zrepl_job_name` with internal dashboard variable `zrepl_replication_jobid` and use that _only_ in the `Replication` section of the dashboard * Update to Grafana v12.4
1648 lines
41 KiB
JSON
1648 lines
41 KiB
JSON
{
|
|
"__inputs": [
|
|
{
|
|
"name": "DS_PROMETHEUS",
|
|
"label": "prometheus",
|
|
"description": "",
|
|
"type": "datasource",
|
|
"pluginId": "prometheus",
|
|
"pluginName": "Prometheus"
|
|
}
|
|
],
|
|
"__elements": {},
|
|
"__requires": [
|
|
{
|
|
"type": "grafana",
|
|
"id": "grafana",
|
|
"name": "Grafana",
|
|
"version": "12.4.0-20983762500"
|
|
},
|
|
{
|
|
"type": "datasource",
|
|
"id": "prometheus",
|
|
"name": "Prometheus",
|
|
"version": "1.0.0"
|
|
},
|
|
{
|
|
"type": "panel",
|
|
"id": "state-timeline",
|
|
"name": "State timeline",
|
|
"version": ""
|
|
},
|
|
{
|
|
"type": "panel",
|
|
"id": "status-history",
|
|
"name": "Status history",
|
|
"version": ""
|
|
},
|
|
{
|
|
"type": "panel",
|
|
"id": "table",
|
|
"name": "Table",
|
|
"version": ""
|
|
},
|
|
{
|
|
"type": "panel",
|
|
"id": "text",
|
|
"name": "Text",
|
|
"version": ""
|
|
},
|
|
{
|
|
"type": "panel",
|
|
"id": "timeseries",
|
|
"name": "Time series",
|
|
"version": ""
|
|
}
|
|
],
|
|
"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": [],
|
|
"panels": [
|
|
{
|
|
"collapsed": true,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 0
|
|
},
|
|
"id": 57,
|
|
"panels": [
|
|
{
|
|
"fieldConfig": {
|
|
"defaults": {},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 1
|
|
},
|
|
"id": 35,
|
|
"options": {
|
|
"code": {
|
|
"language": "plaintext",
|
|
"showLineNumbers": false,
|
|
"showMiniMap": false
|
|
},
|
|
"content": "# zrepl Prometheus Metrics\n\nzrepl exposes Prometheus metrics and ships with this Grafana dashboard.\nThe exported metrics are suitable for health checks:\n\n* The log should generally be warning & error-free\n * The `Log Messages that require attention` graph visualizes log message at levels that generally indicate problems.\n* In most setups, there shouldn't be any unmatched filesystem filter rules.\n* The number of goroutines should not grow unboundedly over time.\n * During replication, the number of goroutines can be way higher than during idle time.\n * If the goroutine count grows with each replication, there is clearly a goroutine leak. Please open a bug report.\n* Memory consumption should not grow unboundedly over time.\n * Note that the Go runtime pre-allocates some of its heap from the OS.\n * zrepl actually uses much less memory than allocated from the OS.\n * Since Go 1.11, Go pre-allocates more aggressively.\n* Monitor that some data is replicated, although that metric does not guarantee that replication was successful.\n\n**In general, note that the exported metrics are not stable unless declared otherwise.**",
|
|
"mode": "markdown"
|
|
},
|
|
"pluginVersion": "12.4.0-20983762500",
|
|
"title": "",
|
|
"type": "text"
|
|
}
|
|
],
|
|
"title": "About",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 1
|
|
},
|
|
"id": 60,
|
|
"panels": [],
|
|
"title": "Top",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisBorderShow": false,
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"barWidthFactor": 0.6,
|
|
"drawStyle": "line",
|
|
"fillOpacity": 10,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 1,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "never",
|
|
"showValues": false,
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "normal"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"links": [],
|
|
"mappings": [],
|
|
"max": 5,
|
|
"min": 0,
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 80
|
|
}
|
|
]
|
|
},
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 6,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 2
|
|
},
|
|
"id": 48,
|
|
"options": {
|
|
"alertThreshold": true,
|
|
"legend": {
|
|
"calcs": [],
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"hideZeros": false,
|
|
"mode": "multi",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"pluginVersion": "12.4.0-20983762500",
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"editorMode": "code",
|
|
"expr": "sgn(zrepl_start_time{job='$prom_job_name'})",
|
|
"format": "time_series",
|
|
"interval": "",
|
|
"intervalFactor": 1,
|
|
"legendFormat": "{{instance}}@version={{raw}}",
|
|
"range": true,
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "zrepl Instances running",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"description": "zrepl maintains event counters for each `job x log_level`, independent of the logging outlet configuration in the config.",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisBorderShow": false,
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"barWidthFactor": 0.6,
|
|
"drawStyle": "line",
|
|
"fillOpacity": 10,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 1,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "never",
|
|
"showValues": false,
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "none"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"links": [],
|
|
"mappings": [],
|
|
"min": 0,
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 80
|
|
}
|
|
]
|
|
},
|
|
"unit": "eps"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 6,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 2
|
|
},
|
|
"id": 23,
|
|
"options": {
|
|
"alertThreshold": true,
|
|
"legend": {
|
|
"calcs": [],
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"hideZeros": false,
|
|
"mode": "multi",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"pluginVersion": "12.4.0-20983762500",
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"editorMode": "code",
|
|
"expr": "sum(rate(zrepl_daemon_log_entries{job=\"$prom_job_name\"}[$__rate_interval])) by (instance,zrepl_job)",
|
|
"format": "time_series",
|
|
"intervalFactor": 1,
|
|
"range": true,
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Log events by zrepl job",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"description": "A functioning setup should not be logging `warn` / `error` messages.",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisBorderShow": false,
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"barWidthFactor": 0.6,
|
|
"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",
|
|
"showValues": false,
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "none"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"links": [],
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 0.000001
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 5,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 8
|
|
},
|
|
"id": 22,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": [],
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"hideZeros": false,
|
|
"mode": "single",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"pluginVersion": "12.4.0-20983762500",
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"editorMode": "code",
|
|
"expr": "rate(zrepl_daemon_log_entries{job='$prom_job_name',level=~'warn|error'}[$__rate_interval]) > 0",
|
|
"format": "time_series",
|
|
"intervalFactor": 1,
|
|
"range": true,
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Log Messages that require attention",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 13
|
|
},
|
|
"id": 58,
|
|
"panels": [],
|
|
"title": "Replication",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"description": "Number of filesystems that failed replications.\nGauge is updated after the invocation has finished and remains at the resulting value until it is updated at the end of the next invocation.",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "thresholds"
|
|
},
|
|
"custom": {
|
|
"axisPlacement": "auto",
|
|
"fillOpacity": 70,
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"lineWidth": 1
|
|
},
|
|
"mappings": [
|
|
{
|
|
"options": {
|
|
"0": {
|
|
"index": 1,
|
|
"text": "All OK"
|
|
},
|
|
"-1": {
|
|
"index": 0,
|
|
"text": "All failed"
|
|
}
|
|
},
|
|
"type": "value"
|
|
}
|
|
],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "#bf1b00",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "dark-red",
|
|
"value": 0.1
|
|
}
|
|
]
|
|
},
|
|
"unit": "none"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 5,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 14
|
|
},
|
|
"id": 50,
|
|
"maxDataPoints": 100,
|
|
"options": {
|
|
"colWidth": 0.87,
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": false
|
|
},
|
|
"rowHeight": 0.9,
|
|
"showValue": "never",
|
|
"tooltip": {
|
|
"hideZeros": false,
|
|
"mode": "single",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"pluginVersion": "12.4.0-20983762500",
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"editorMode": "code",
|
|
"exemplar": false,
|
|
"expr": "sum by (instance,zrepl_job) (zrepl_replication_filesystem_errors{job=\"$prom_job_name\",zrepl_job=~\"$zrepl_replication_jobid\"})",
|
|
"format": "time_series",
|
|
"groupBy": [
|
|
{
|
|
"params": [
|
|
"$__interval"
|
|
],
|
|
"type": "time"
|
|
},
|
|
{
|
|
"params": [
|
|
"null"
|
|
],
|
|
"type": "fill"
|
|
}
|
|
],
|
|
"instant": false,
|
|
"interval": "",
|
|
"intervalFactor": 1,
|
|
"legendFormat": "{{instance}}/{{zrepl_job}}",
|
|
"orderByTime": "ASC",
|
|
"policy": "default",
|
|
"range": true,
|
|
"refId": "A",
|
|
"resultFormat": "time_series",
|
|
"select": [
|
|
[
|
|
{
|
|
"params": [
|
|
"value"
|
|
],
|
|
"type": "field"
|
|
},
|
|
{
|
|
"params": [],
|
|
"type": "mean"
|
|
}
|
|
]
|
|
],
|
|
"tags": []
|
|
}
|
|
],
|
|
"title": "Replication jobs Filesystems with failed replications.",
|
|
"type": "status-history"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisBorderShow": false,
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"barWidthFactor": 0.6,
|
|
"drawStyle": "bars",
|
|
"fillOpacity": 100,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 1,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "auto",
|
|
"showValues": false,
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "none"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"links": [],
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 80
|
|
}
|
|
]
|
|
},
|
|
"unit": "bytes"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 14
|
|
},
|
|
"id": 42,
|
|
"options": {
|
|
"alertThreshold": true,
|
|
"legend": {
|
|
"calcs": [],
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"hideZeros": false,
|
|
"mode": "single",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"pluginVersion": "12.4.0-20983762500",
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "sum(increase(zrepl_replication_bytes_replicated{job='$prom_job_name'}[1d])) by (zrepl_job)",
|
|
"format": "time_series",
|
|
"instant": false,
|
|
"interval": "1d",
|
|
"intervalFactor": 1,
|
|
"legendFormat": "zrepl_job={{zrepl_job}}",
|
|
"refId": "B"
|
|
}
|
|
],
|
|
"title": "Daily Replication Data Volume",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"gridPos": {
|
|
"h": 6,
|
|
"w": 3,
|
|
"x": 0,
|
|
"y": 19
|
|
},
|
|
"id": 56,
|
|
"options": {
|
|
"code": {
|
|
"language": "plaintext",
|
|
"showLineNumbers": false,
|
|
"showMiniMap": false
|
|
},
|
|
"content": "### Unmatched Rules\n\nFilesystem filter rules which mention datasets that didn't exist in the `zfs list` output.",
|
|
"mode": "markdown"
|
|
},
|
|
"pluginVersion": "12.4.0-20983762500",
|
|
"type": "text"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "thresholds"
|
|
},
|
|
"custom": {
|
|
"align": "auto",
|
|
"cellOptions": {
|
|
"mode": "basic",
|
|
"type": "color-background"
|
|
},
|
|
"footer": {
|
|
"reducers": []
|
|
},
|
|
"inspect": false
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "dark-red",
|
|
"value": 0.01
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": [
|
|
{
|
|
"matcher": {
|
|
"id": "byName",
|
|
"options": "jobid"
|
|
},
|
|
"properties": [
|
|
{
|
|
"id": "color",
|
|
"value": {
|
|
"fixedColor": "transparent",
|
|
"mode": "fixed"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"matcher": {
|
|
"id": "byName",
|
|
"options": "instance"
|
|
},
|
|
"properties": [
|
|
{
|
|
"id": "color",
|
|
"value": {
|
|
"fixedColor": "transparent",
|
|
"mode": "fixed"
|
|
}
|
|
}
|
|
]
|
|
}
|
|
]
|
|
},
|
|
"gridPos": {
|
|
"h": 6,
|
|
"w": 9,
|
|
"x": 3,
|
|
"y": 19
|
|
},
|
|
"id": 54,
|
|
"maxDataPoints": 20,
|
|
"options": {
|
|
"cellHeight": "sm",
|
|
"showHeader": true,
|
|
"sortBy": [
|
|
{
|
|
"desc": true,
|
|
"displayName": "Value"
|
|
}
|
|
]
|
|
},
|
|
"pluginVersion": "12.4.0-20983762500",
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"editorMode": "code",
|
|
"exemplar": false,
|
|
"expr": "increase(zrepl_zfs_list_unmatched_user_specified_dataset_count{job=\"$prom_job_name\",jobid=~\"$zrepl_replication_jobid\"}[$__range])",
|
|
"format": "table",
|
|
"instant": true,
|
|
"interval": "",
|
|
"legendFormat": "__auto",
|
|
"range": false,
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Unmatched rules [Dashboard Range]",
|
|
"transformations": [
|
|
{
|
|
"id": "organize",
|
|
"options": {
|
|
"excludeByName": {
|
|
"Time": true,
|
|
"Value": false,
|
|
"instance": false,
|
|
"job": true
|
|
},
|
|
"includeByName": {},
|
|
"indexByName": {},
|
|
"renameByName": {}
|
|
}
|
|
}
|
|
],
|
|
"type": "table"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisBorderShow": false,
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"barWidthFactor": 0.6,
|
|
"drawStyle": "line",
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 1,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "auto",
|
|
"showValues": false,
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "none"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"links": [],
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 80
|
|
}
|
|
]
|
|
},
|
|
"unit": "Bps"
|
|
},
|
|
"overrides": [
|
|
{
|
|
"matcher": {
|
|
"id": "byFrameRefID",
|
|
"options": "B"
|
|
},
|
|
"properties": [
|
|
{
|
|
"id": "unit",
|
|
"value": "bytes"
|
|
},
|
|
{
|
|
"id": "custom.axisPlacement",
|
|
"value": "right"
|
|
}
|
|
]
|
|
}
|
|
]
|
|
},
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 24
|
|
},
|
|
"id": 33,
|
|
"options": {
|
|
"alertThreshold": true,
|
|
"legend": {
|
|
"calcs": [],
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"hideZeros": false,
|
|
"mode": "single",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"pluginVersion": "12.4.0-20983762500",
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "sum(rate(zrepl_replication_bytes_replicated{job='$prom_job_name'}[10m])) by (zrepl_job)",
|
|
"format": "time_series",
|
|
"interval": "",
|
|
"intervalFactor": 1,
|
|
"legendFormat": "replication data ratein last 10min zrepl_job={{zrepl_job}}te zrepl_job={{zrepl_job}}",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "sum(increase(zrepl_replication_bytes_replicated{job='$prom_job_name'}[10m])) by (zrepl_job)",
|
|
"format": "time_series",
|
|
"interval": "",
|
|
"intervalFactor": 1,
|
|
"legendFormat": "replicated bytes in last 10min zrepl_job={{zrepl_job}}",
|
|
"refId": "B"
|
|
}
|
|
],
|
|
"title": "Replication Data Rate and Volume(over last 10min)",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "thresholds"
|
|
},
|
|
"custom": {
|
|
"axisPlacement": "auto",
|
|
"fillOpacity": 70,
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineWidth": 0,
|
|
"spanNulls": false
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 0.0001
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 9,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 25
|
|
},
|
|
"id": 52,
|
|
"maxDataPoints": 10,
|
|
"options": {
|
|
"alignValue": "left",
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": false
|
|
},
|
|
"mergeValues": false,
|
|
"rowHeight": 0.9,
|
|
"showValue": "auto",
|
|
"tooltip": {
|
|
"hideZeros": false,
|
|
"mode": "single",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"pluginVersion": "12.4.0-20983762500",
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"editorMode": "code",
|
|
"expr": "increase(zrepl_zfs_list_unmatched_user_specified_dataset_count{job=\"$prom_job_name\",jobid=~\"$zrepl_replication_jobid\"}[$__interval])",
|
|
"format": "time_series",
|
|
"legendFormat": "{{jobid}}",
|
|
"range": true,
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Unmatched rules increase[$__interval]",
|
|
"type": "state-timeline"
|
|
},
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 34
|
|
},
|
|
"id": 59,
|
|
"panels": [],
|
|
"title": "Internals",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisBorderShow": false,
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"barWidthFactor": 0.6,
|
|
"drawStyle": "line",
|
|
"fillOpacity": 10,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 1,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "never",
|
|
"showValues": false,
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "none"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"links": [],
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 80
|
|
}
|
|
]
|
|
},
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 5,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 35
|
|
},
|
|
"id": 44,
|
|
"options": {
|
|
"alertThreshold": true,
|
|
"legend": {
|
|
"calcs": [],
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"hideZeros": false,
|
|
"mode": "multi",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"pluginVersion": "12.4.0-20983762500",
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"editorMode": "code",
|
|
"expr": "zrepl_trace_active_tasks{job=\"$prom_job_name\"}",
|
|
"format": "time_series",
|
|
"intervalFactor": 1,
|
|
"range": true,
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "active tasks tracked by the zrepl trace module (should not grow unboundedly)",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisBorderShow": false,
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"barWidthFactor": 0.6,
|
|
"drawStyle": "line",
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 1,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "auto",
|
|
"showValues": false,
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "none"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"links": [],
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 80
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 5,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 40
|
|
},
|
|
"id": 19,
|
|
"options": {
|
|
"alertThreshold": true,
|
|
"legend": {
|
|
"calcs": [],
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"hideZeros": false,
|
|
"mode": "single",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"pluginVersion": "12.4.0-20983762500",
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "go_goroutines{job='$prom_job_name'}",
|
|
"format": "time_series",
|
|
"intervalFactor": 1,
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "number of goroutines (should not grow unboundedly)",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisBorderShow": false,
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"barWidthFactor": 0.6,
|
|
"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",
|
|
"showValues": false,
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "none"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"links": [],
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 80
|
|
}
|
|
]
|
|
},
|
|
"unit": "bytes"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 5,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 40
|
|
},
|
|
"id": 17,
|
|
"options": {
|
|
"alertThreshold": true,
|
|
"legend": {
|
|
"calcs": [],
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"hideZeros": false,
|
|
"mode": "single",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"pluginVersion": "12.4.0-20983762500",
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "go_memstats_sys_bytes{job='$prom_job_name'}",
|
|
"format": "time_series",
|
|
"intervalFactor": 1,
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Memory Allocated by the Go runtime from the OS (should not grow unboundedly)",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisBorderShow": false,
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"barWidthFactor": 0.6,
|
|
"drawStyle": "line",
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 1,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "auto",
|
|
"showValues": false,
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "none"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"links": [],
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 80
|
|
}
|
|
]
|
|
},
|
|
"unit": "bytes"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 5,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 45
|
|
},
|
|
"id": 41,
|
|
"options": {
|
|
"alertThreshold": true,
|
|
"legend": {
|
|
"calcs": [],
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"hideZeros": false,
|
|
"mode": "single",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"pluginVersion": "12.4.0-20983762500",
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "go_memstats_alloc_bytes{job='$prom_job_name'}",
|
|
"format": "time_series",
|
|
"intervalFactor": 1,
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Go Memory Allocations (should not grow unboundedly)",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisBorderShow": false,
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"barWidthFactor": 0.6,
|
|
"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",
|
|
"showValues": false,
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "none"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"links": [],
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 80
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 5,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 45
|
|
},
|
|
"id": 47,
|
|
"options": {
|
|
"alertThreshold": true,
|
|
"legend": {
|
|
"calcs": [],
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"hideZeros": false,
|
|
"mode": "single",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"pluginVersion": "12.4.0-20983762500",
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"editorMode": "code",
|
|
"expr": "zrepl_endpoint_abstractions_cache_entry_count",
|
|
"format": "time_series",
|
|
"intervalFactor": 1,
|
|
"range": true,
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "zfs abstractions cache entry count (should not be zero and not grow unboundedly)",
|
|
"type": "timeseries"
|
|
}
|
|
],
|
|
"preload": false,
|
|
"refresh": "5s",
|
|
"schemaVersion": 42,
|
|
"tags": [],
|
|
"templating": {
|
|
"list": [
|
|
{
|
|
"allowCustomValue": false,
|
|
"current": {},
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"definition": "label_values(zrepl_start_time,job)",
|
|
"includeAll": false,
|
|
"label": "Prometheus Job Name",
|
|
"name": "prom_job_name",
|
|
"options": [],
|
|
"query": {
|
|
"qryType": 1,
|
|
"query": "label_values(zrepl_start_time,job)",
|
|
"refId": "PrometheusVariableQueryEditor-VariableQuery"
|
|
},
|
|
"refresh": 1,
|
|
"regex": "",
|
|
"regexApplyTo": "value",
|
|
"sort": 1,
|
|
"type": "query"
|
|
},
|
|
{
|
|
"current": {},
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"definition": "label_values(zrepl_replication_filesystem_errors{job=\"$prom_job_name\"},zrepl_job)",
|
|
"description": "multi-value variable of all replication job ids\n(implementation detail of the dashboard)",
|
|
"hide": 2,
|
|
"includeAll": true,
|
|
"multi": true,
|
|
"name": "zrepl_replication_jobid",
|
|
"options": [],
|
|
"query": {
|
|
"qryType": 1,
|
|
"query": "label_values(zrepl_replication_filesystem_errors{job=\"$prom_job_name\"},zrepl_job)",
|
|
"refId": "PrometheusVariableQueryEditor-VariableQuery"
|
|
},
|
|
"refresh": 2,
|
|
"regex": "",
|
|
"regexApplyTo": "value",
|
|
"sort": 1,
|
|
"type": "query"
|
|
}
|
|
]
|
|
},
|
|
"time": {
|
|
"from": "now-7d",
|
|
"to": "now"
|
|
},
|
|
"timepicker": {
|
|
"refresh_intervals": [
|
|
"10s",
|
|
"30s",
|
|
"1m",
|
|
"5m",
|
|
"15m",
|
|
"30m",
|
|
"1h",
|
|
"2h",
|
|
"1d"
|
|
]
|
|
},
|
|
"timezone": "browser",
|
|
"title": "zrepl",
|
|
"uid": "etQuvaBnGz",
|
|
"version": 6,
|
|
"weekStart": "",
|
|
"id": null
|
|
}
|