From e42308e84c5428d0853efffadca7dc43f27e3dde Mon Sep 17 00:00:00 2001
From: Roman Khavronenko <roman@victoriametrics.com>
Date: Tue, 29 Nov 2022 19:26:31 +0100
Subject: [PATCH] dashboards: update vmalert dash (#3404)
The change list is the following:
* bump Grafana version to 9.2.6;
* replace old Graph panel with TimeSeries panel;
* add RemoteWrite section;
* allow configuring topK elements for some of the panels;
* Preer grouping by job instead of grouping by instance.
Signed-off-by: hagen1778 <roman@victoriametrics.com>
Signed-off-by: hagen1778 <roman@victoriametrics.com>
---
dashboards/vmalert.json | 3186 +++++++++++++++++++++++----------------
1 file changed, 1880 insertions(+), 1306 deletions(-)
diff --git a/dashboards/vmalert.json b/dashboards/vmalert.json
index 91ab8ef89b..e7973a1c29 100644
--- a/dashboards/vmalert.json
+++ b/dashboards/vmalert.json
@@ -1,17 +1,12 @@
{
"__inputs": [],
+ "__elements": {},
"__requires": [
{
"type": "grafana",
"id": "grafana",
"name": "Grafana",
- "version": "9.0.3"
- },
- {
- "type": "panel",
- "id": "graph",
- "name": "Graph (old)",
- "version": ""
+ "version": "9.2.6"
},
{
"type": "datasource",
@@ -60,12 +55,11 @@
}
]
},
- "description": "Overview for VictoriaMetrics vmalert v1.73.0 or higher",
+ "description": "Overview for VictoriaMetrics vmalert v1.83.0 or higher",
"editable": true,
"fiscalYearStartMonth": 0,
"graphTooltip": 1,
"id": null,
- "iteration": 1663341746917,
"links": [
{
"asDropdown": false,
@@ -108,28 +102,15 @@
"panels": [
{
"collapsed": false,
- "datasource": {
- "type": "datasource",
- "uid": "grafana"
- },
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 0
},
- "id": 11,
+ "id": 47,
"panels": [],
- "targets": [
- {
- "datasource": {
- "type": "datasource",
- "uid": "grafana"
- },
- "refId": "A"
- }
- ],
- "title": "General ($instance)",
+ "title": "Stats",
"type": "row"
},
{
@@ -178,7 +159,7 @@
},
"gridPos": {
"h": 3,
- "w": 3,
+ "w": 4,
"x": 0,
"y": 1
},
@@ -198,7 +179,7 @@
"text": {},
"textMode": "auto"
},
- "pluginVersion": "9.0.3",
+ "pluginVersion": "9.2.6",
"targets": [
{
"datasource": {
@@ -212,71 +193,7 @@
"refId": "A"
}
],
- "title": "Config error",
- "type": "stat"
- },
- {
- "datasource": {
- "type": "prometheus",
- "uid": "$ds"
- },
- "description": "Shows the total number of errors generated by recording/alerting rules for selected instances and groups.",
- "fieldConfig": {
- "defaults": {
- "mappings": [],
- "thresholds": {
- "mode": "absolute",
- "steps": [
- {
- "color": "green",
- "value": null
- },
- {
- "color": "red",
- "value": 1
- }
- ]
- }
- },
- "overrides": []
- },
- "gridPos": {
- "h": 3,
- "w": 4,
- "x": 3,
- "y": 1
- },
- "id": 8,
- "options": {
- "colorMode": "value",
- "graphMode": "area",
- "justifyMode": "auto",
- "orientation": "auto",
- "reduceOptions": {
- "calcs": [
- "last"
- ],
- "fields": "",
- "values": false
- },
- "text": {},
- "textMode": "auto"
- },
- "pluginVersion": "9.0.3",
- "targets": [
- {
- "datasource": {
- "type": "prometheus",
- "uid": "$ds"
- },
- "exemplar": false,
- "expr": "(sum(vmalert_alerting_rules_error{job=~\"$job\", instance=~\"$instance\", group=~\"$group\"}) or vector(0)) + \n(sum(vmalert_recording_rules_error{job=~\"$job\", instance=~\"$instance\", group=~\"$group\"}) or vector(0))",
- "interval": "",
- "legendFormat": "",
- "refId": "A"
- }
- ],
- "title": "Errors",
+ "title": "Config update",
"type": "stat"
},
{
@@ -302,8 +219,8 @@
},
"gridPos": {
"h": 3,
- "w": 4,
- "x": 7,
+ "w": 5,
+ "x": 4,
"y": 1
},
"id": 9,
@@ -322,7 +239,7 @@
"text": {},
"textMode": "auto"
},
- "pluginVersion": "9.0.3",
+ "pluginVersion": "9.2.6",
"targets": [
{
"datasource": {
@@ -362,8 +279,8 @@
},
"gridPos": {
"h": 3,
- "w": 4,
- "x": 11,
+ "w": 5,
+ "x": 9,
"y": 1
},
"id": 7,
@@ -382,7 +299,7 @@
"text": {},
"textMode": "auto"
},
- "pluginVersion": "9.0.3",
+ "pluginVersion": "9.2.6",
"targets": [
{
"datasource": {
@@ -399,6 +316,136 @@
"title": "Recording rules",
"type": "stat"
},
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "$ds"
+ },
+ "description": "Shows the total number of errors generated by recording/alerting rules for selected instances and groups.",
+ "fieldConfig": {
+ "defaults": {
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 1
+ }
+ ]
+ }
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 3,
+ "w": 5,
+ "x": 14,
+ "y": 1
+ },
+ "id": 8,
+ "options": {
+ "colorMode": "value",
+ "graphMode": "area",
+ "justifyMode": "auto",
+ "orientation": "auto",
+ "reduceOptions": {
+ "calcs": [
+ "last"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "text": {},
+ "textMode": "auto"
+ },
+ "pluginVersion": "9.2.6",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "$ds"
+ },
+ "exemplar": false,
+ "expr": "(sum(vmalert_alerting_rules_error{job=~\"$job\", instance=~\"$instance\", group=~\"$group\"}) or vector(0)) + \n(sum(vmalert_recording_rules_error{job=~\"$job\", instance=~\"$instance\", group=~\"$group\"}) or vector(0))",
+ "interval": "",
+ "legendFormat": "",
+ "refId": "A"
+ }
+ ],
+ "title": "Errors",
+ "type": "stat"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "$ds"
+ },
+ "description": "Shows number of Recording Rules which produce no data.\n\n Usually it means that such rules are misconfigured, since they give no output during the evaluation.\nPlease check if rule's expression is correct and it is working as expected.",
+ "fieldConfig": {
+ "defaults": {
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 1
+ }
+ ]
+ }
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 3,
+ "w": 5,
+ "x": 19,
+ "y": 1
+ },
+ "id": 48,
+ "options": {
+ "colorMode": "value",
+ "graphMode": "area",
+ "justifyMode": "auto",
+ "orientation": "auto",
+ "reduceOptions": {
+ "calcs": [
+ "last"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "text": {},
+ "textMode": "auto"
+ },
+ "pluginVersion": "9.2.6",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "$ds"
+ },
+ "editorMode": "code",
+ "exemplar": false,
+ "expr": "count(vmalert_recording_rules_last_evaluation_samples < 1) or 0",
+ "interval": "",
+ "legendFormat": "",
+ "range": true,
+ "refId": "A"
+ }
+ ],
+ "title": "No data errors",
+ "type": "stat"
+ },
{
"datasource": {
"type": "prometheus",
@@ -474,7 +521,7 @@
},
"showHeader": true
},
- "pluginVersion": "9.0.3",
+ "pluginVersion": "9.2.6",
"targets": [
{
"datasource": {
@@ -493,482 +540,669 @@
"type": "table"
},
{
- "aliasColors": {},
- "bars": false,
- "dashLength": 10,
- "dashes": false,
"datasource": {
"type": "prometheus",
"uid": "$ds"
},
"fieldConfig": {
"defaults": {
- "links": []
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "lineInterpolation": "stepAfter",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "decimals": 0,
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "short"
},
"overrides": []
},
- "fill": 0,
- "fillGradient": 0,
"gridPos": {
"h": 4,
"w": 15,
"x": 9,
"y": 4
},
- "hiddenSeries": false,
"id": 4,
- "legend": {
- "alignAsTable": true,
- "avg": false,
- "current": true,
- "hideEmpty": false,
- "hideZero": false,
- "max": false,
- "min": false,
- "rightSide": true,
- "show": true,
- "sort": "current",
- "sortDesc": false,
- "total": false,
- "values": true
- },
- "lines": true,
- "linewidth": 1,
- "nullPointMode": "null as zero",
"options": {
- "alertThreshold": true
+ "legend": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "displayMode": "table",
+ "placement": "right",
+ "showLegend": true,
+ "sortBy": "Last *",
+ "sortDesc": true
+ },
+ "tooltip": {
+ "mode": "multi",
+ "sort": "asc"
+ }
},
- "percentage": false,
- "pluginVersion": "9.0.3",
- "pointradius": 2,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": true,
+ "pluginVersion": "9.2.6",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "$ds"
},
+ "editorMode": "code",
"exemplar": false,
- "expr": "sort(sum(up{job=~\"$job\", instance=~\"$instance\"}) by (job, instance))",
+ "expr": "sum(min_over_time(up{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (job)",
"format": "time_series",
"instant": false,
"interval": "",
- "legendFormat": "{{instance}}",
+ "legendFormat": "{{job}}",
"refId": "A"
}
],
- "thresholds": [],
- "timeRegions": [],
"title": "Uptime",
- "tooltip": {
- "shared": true,
- "sort": 1,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "mode": "time",
- "show": true,
- "values": []
- },
- "yaxes": [
- {
- "$$hashKey": "object:170",
- "decimals": 0,
- "format": "short",
- "logBase": 1,
- "min": "0",
- "show": true
- },
- {
- "$$hashKey": "object:171",
- "format": "short",
- "label": "",
- "logBase": 1,
- "show": true
- }
- ],
- "yaxis": {
- "align": false,
- "alignLevel": 2
- }
+ "type": "timeseries"
+ },
+ {
+ "collapsed": false,
+ "datasource": {
+ "type": "datasource",
+ "uid": "grafana"
+ },
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 8
+ },
+ "id": 11,
+ "panels": [],
+ "targets": [
+ {
+ "datasource": {
+ "type": "datasource",
+ "uid": "grafana"
+ },
+ "refId": "A"
+ }
+ ],
+ "title": "Overview ($instance)",
+ "type": "row"
},
{
- "aliasColors": {},
- "bars": false,
- "dashLength": 10,
- "dashes": false,
"datasource": {
"type": "prometheus",
"uid": "$ds"
},
- "description": "Shows the number of fired alerts by instance.",
- "fill": 0,
- "fillGradient": 0,
+ "description": "Shows the number of fired alerts by job.",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": []
+ },
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
- "y": 8
+ "y": 9
},
- "hiddenSeries": false,
"id": 15,
- "legend": {
- "alignAsTable": true,
- "avg": true,
- "current": true,
- "max": true,
- "min": false,
- "show": true,
- "sort": "current",
- "sortDesc": true,
- "total": false,
- "values": true
- },
- "lines": true,
- "linewidth": 1,
- "nullPointMode": "null",
"options": {
- "alertThreshold": true
+ "legend": {
+ "calcs": [
+ "mean",
+ "lastNotNull",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true,
+ "sortBy": "Last *",
+ "sortDesc": true
+ },
+ "tooltip": {
+ "mode": "multi",
+ "sort": "desc"
+ }
},
- "percentage": false,
- "pluginVersion": "9.0.3",
- "pointradius": 2,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
+ "pluginVersion": "9.2.6",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "$ds"
},
+ "editorMode": "code",
"exemplar": false,
- "expr": "sum(increase(vmalert_alerts_fired_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by(instance)",
+ "expr": "sum(increase(vmalert_alerts_fired_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by(job)",
"interval": "",
- "legendFormat": "{{instance}}",
+ "legendFormat": "{{job}}",
+ "range": true,
"refId": "A"
}
],
- "thresholds": [],
- "timeRegions": [],
- "title": "Alerts fired total",
- "tooltip": {
- "shared": true,
- "sort": 2,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "mode": "time",
- "show": true,
- "values": []
- },
- "yaxes": [
- {
- "$$hashKey": "object:62",
- "format": "short",
- "logBase": 1,
- "show": true
- },
- {
- "$$hashKey": "object:63",
- "format": "short",
- "logBase": 1,
- "show": true
- }
- ],
- "yaxis": {
- "align": false
- }
+ "title": "Alerts fired total ($instance)",
+ "type": "timeseries"
},
{
- "aliasColors": {},
- "bars": false,
- "dashLength": 10,
- "dashes": false,
"datasource": {
"type": "prometheus",
"uid": "$ds"
},
- "description": "Average evaluation duration by group. Basically means how long it takes to execute all the rules per each group.",
+ "description": "Top $topk groups by evaluation duration. Shows groups that take the most of time during the evaluation across all instances.\n\nThe panel uses MetricsQL functions and may not work with Prometheus.",
"fieldConfig": {
"defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
"unit": "s"
},
"overrides": []
},
- "fill": 0,
- "fillGradient": 0,
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
- "y": 8
+ "y": 9
},
- "hiddenSeries": false,
"id": 23,
- "legend": {
- "alignAsTable": true,
- "avg": true,
- "current": true,
- "max": true,
- "min": false,
- "show": true,
- "sort": "current",
- "sortDesc": true,
- "total": false,
- "values": true
- },
- "lines": true,
- "linewidth": 1,
- "nullPointMode": "null",
"options": {
- "alertThreshold": false
+ "legend": {
+ "calcs": [
+ "mean",
+ "lastNotNull",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true,
+ "sortBy": "Last *",
+ "sortDesc": true
+ },
+ "tooltip": {
+ "mode": "multi",
+ "sort": "desc"
+ }
},
- "percentage": false,
- "pluginVersion": "9.0.3",
- "pointradius": 2,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
+ "pluginVersion": "9.2.6",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "$ds"
},
+ "editorMode": "code",
"exemplar": false,
- "expr": "sum(rate(vmalert_iteration_duration_seconds_sum{job=~\"$job\", instance=~\"$instance\", group=~\"$group\"}[$__rate_interval])) by(group) / \nsum(rate(vmalert_iteration_duration_seconds_count{job=~\"$job\", instance=~\"$instance\", group=~\"$group\"}[$__rate_interval])) by(group)",
+ "expr": "topk_max($topk, max(sum(\n rate(vmalert_iteration_duration_seconds_sum{job=~\"$job\", instance=~\"$instance\", group=~\"$group\"}[$__rate_interval])\n/\n rate(vmalert_iteration_duration_seconds_count{job=~\"$job\", instance=~\"$instance\", group=~\"$group\"}[$__rate_interval])\n) by(job, instance, group)) \nby(job, group))",
"interval": "",
- "legendFormat": "{{group}}",
+ "legendFormat": "{{group}} ({{job}})",
+ "range": true,
"refId": "A"
}
],
- "thresholds": [],
- "timeRegions": [],
- "title": "Groups avg evaluation duration ($group)",
- "tooltip": {
- "shared": true,
- "sort": 2,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "mode": "time",
- "show": true,
- "values": []
- },
- "yaxes": [
- {
- "format": "s",
- "logBase": 1,
- "show": true
- },
- {
- "format": "short",
- "logBase": 1,
- "show": true
- }
- ],
- "yaxis": {
- "align": false
- }
+ "title": "Top $topk groups avg evaluation duration ($group)",
+ "type": "timeseries"
},
{
- "aliasColors": {},
- "bars": false,
- "dashLength": 10,
- "dashes": false,
"datasource": {
"type": "prometheus",
"uid": "$ds"
},
"description": "Shows how many requests (executions) per second vmalert sends to the configured datasource.",
- "fill": 0,
- "fillGradient": 0,
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": []
+ },
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
- "y": 16
+ "y": 17
},
- "hiddenSeries": false,
"id": 24,
- "legend": {
- "alignAsTable": true,
- "avg": true,
- "current": true,
- "max": true,
- "min": false,
- "show": true,
- "sort": "current",
- "sortDesc": true,
- "total": false,
- "values": true
- },
- "lines": true,
- "linewidth": 1,
- "nullPointMode": "null",
"options": {
- "alertThreshold": true
+ "legend": {
+ "calcs": [
+ "mean",
+ "lastNotNull",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "multi",
+ "sort": "desc"
+ }
},
- "percentage": false,
- "pluginVersion": "9.0.3",
- "pointradius": 2,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
+ "pluginVersion": "9.2.6",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "$ds"
},
+ "editorMode": "code",
"exemplar": false,
- "expr": "sum(rate(vmalert_execution_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (instance)",
+ "expr": "sum(rate(vmalert_execution_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (job)",
"interval": "",
- "legendFormat": "{{instance}}",
+ "legendFormat": "{{job}}",
+ "range": true,
"refId": "A"
}
],
- "thresholds": [],
- "timeRegions": [],
"title": "Rules execution rate ($instance)",
- "tooltip": {
- "shared": true,
- "sort": 2,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "mode": "time",
- "show": true,
- "values": []
- },
- "yaxes": [
- {
- "$$hashKey": "object:182",
- "format": "short",
- "logBase": 1,
- "show": true
- },
- {
- "$$hashKey": "object:183",
- "format": "short",
- "logBase": 1,
- "show": true
- }
- ],
- "yaxis": {
- "align": false
- }
+ "type": "timeseries"
},
{
- "aliasColors": {},
- "bars": false,
- "dashLength": 10,
- "dashes": false,
"datasource": {
"type": "prometheus",
"uid": "$ds"
},
"description": "Shows the error rate while executing configured rules. Non-zero value means there are some issues with existing rules. Check the logs to get more details.",
- "fill": 1,
- "fillGradient": 0,
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 10,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": []
+ },
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
- "y": 16
+ "y": 17
},
- "hiddenSeries": false,
"id": 25,
- "legend": {
- "alignAsTable": true,
- "avg": true,
- "current": true,
- "max": true,
- "min": false,
- "show": true,
- "sort": "current",
- "sortDesc": true,
- "total": false,
- "values": true
- },
- "lines": true,
- "linewidth": 1,
- "nullPointMode": "null",
"options": {
- "alertThreshold": true
+ "legend": {
+ "calcs": [
+ "mean",
+ "lastNotNull",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "multi",
+ "sort": "none"
+ }
},
- "percentage": false,
- "pluginVersion": "9.0.3",
- "pointradius": 2,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
+ "pluginVersion": "9.2.6",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "$ds"
},
+ "editorMode": "code",
"exemplar": false,
- "expr": "sum(increase(vmalert_execution_errors_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by(instance) > 0",
+ "expr": "sum(rate(vmalert_execution_errors_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by(job) > 0",
"interval": "",
- "legendFormat": "{{instance}}",
+ "legendFormat": "__auto",
+ "range": true,
"refId": "A"
}
],
- "thresholds": [],
- "timeRegions": [],
"title": "Rules execution errors ($instance)",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "$ds"
},
- "type": "graph",
- "xaxis": {
- "mode": "time",
- "show": true,
- "values": []
- },
- "yaxes": [
- {
- "$$hashKey": "object:244",
- "format": "short",
- "logBase": 1,
- "show": true
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "custom": {
+ "align": "auto",
+ "displayMode": "auto",
+ "inspect": false
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ }
},
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Value"
+ },
+ "properties": [
+ {
+ "id": "custom.hidden",
+ "value": true
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Time"
+ },
+ "properties": [
+ {
+ "id": "custom.hidden",
+ "value": true
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 7,
+ "w": 24,
+ "x": 0,
+ "y": 25
+ },
+ "id": 50,
+ "options": {
+ "footer": {
+ "fields": "",
+ "reducer": [
+ "sum"
+ ],
+ "show": false
+ },
+ "showHeader": true,
+ "sortBy": [
+ {
+ "desc": true,
+ "displayName": "job"
+ }
+ ]
+ },
+ "pluginVersion": "9.2.6",
+ "targets": [
{
- "$$hashKey": "object:245",
- "format": "short",
- "logBase": 1,
- "show": true
+ "datasource": {
+ "type": "prometheus",
+ "uid": "$ds"
+ },
+ "editorMode": "code",
+ "exemplar": false,
+ "expr": "sum(flag{is_set=\"true\", job=~\"$job\", instance=~\"$instance\"}) by(job, instance, name, value)",
+ "format": "table",
+ "instant": true,
+ "legendFormat": "__auto",
+ "range": false,
+ "refId": "A"
}
],
- "yaxis": {
- "align": false
- }
+ "title": "Non-default flags",
+ "transformations": [
+ {
+ "id": "groupBy",
+ "options": {
+ "fields": {
+ "instance": {
+ "aggregations": [
+ "uniqueValues"
+ ],
+ "operation": "aggregate"
+ },
+ "job": {
+ "aggregations": [],
+ "operation": "groupby"
+ },
+ "name": {
+ "aggregations": [],
+ "operation": "groupby"
+ },
+ "value": {
+ "aggregations": [],
+ "operation": "groupby"
+ }
+ }
+ }
+ }
+ ],
+ "type": "table"
},
{
"collapsed": true,
@@ -980,421 +1214,868 @@
"h": 1,
"w": 24,
"x": 0,
- "y": 24
+ "y": 32
},
- "id": 17,
+ "id": 43,
"panels": [
{
- "aliasColors": {},
- "bars": false,
- "dashLength": 10,
- "dashes": false,
"datasource": {
"type": "prometheus",
"uid": "$ds"
},
- "description": "Shows the current active (firing) alerting rules per group.",
- "fill": 0,
- "fillGradient": 0,
+ "description": "Shows the CPU usage percentage per vmalert instance. \nIf you think that usage is abnormal or unexpected pls file an issue and attach CPU profile if possible.",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "percentunit"
+ },
+ "overrides": []
+ },
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
- "y": 25
+ "y": 35
},
- "hiddenSeries": false,
- "id": 14,
- "legend": {
- "alignAsTable": true,
- "avg": true,
- "current": true,
- "max": true,
- "min": false,
- "show": true,
- "sort": "current",
- "sortDesc": true,
- "total": false,
- "values": true
- },
- "lines": true,
- "linewidth": 1,
- "nullPointMode": "null",
+ "id": 35,
+ "links": [
+ {
+ "targetBlank": true,
+ "title": "Profiling",
+ "url": "https://docs.victoriametrics.com/vmagent.html#profiling"
+ }
+ ],
"options": {
- "alertThreshold": true
+ "legend": {
+ "calcs": [
+ "mean",
+ "lastNotNull",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true,
+ "sortBy": "Last *",
+ "sortDesc": true
+ },
+ "tooltip": {
+ "mode": "multi",
+ "sort": "desc"
+ }
},
- "percentage": false,
- "pluginVersion": "9.0.3",
- "pointradius": 2,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
+ "pluginVersion": "9.2.6",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "$ds"
},
+ "editorMode": "code",
"exemplar": false,
- "expr": "sum(vmalert_alerts_firing{job=~\"$job\", instance=~\"$instance\", group=~\"$group\"}) by(group, alertname) > 0",
+ "expr": "max(\n rate(process_cpu_seconds_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]) \n / \n vm_available_cpu_cores{job=~\"$job\", instance=~\"$instance\"}\n) by(job)",
+ "format": "time_series",
"interval": "",
- "legendFormat": "{{alertname}} ({{group}})",
+ "intervalFactor": 1,
+ "legendFormat": "{{job}}",
+ "range": true,
"refId": "A"
}
],
- "thresholds": [],
- "timeRegions": [],
- "title": "Active ($group)",
- "tooltip": {
- "shared": true,
- "sort": 2,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "mode": "time",
- "show": true,
- "values": []
- },
- "yaxes": [
- {
- "format": "short",
- "logBase": 1,
- "show": true
- },
- {
- "format": "short",
- "logBase": 1,
- "show": true
- }
- ],
- "yaxis": {
- "align": false
- }
+ "title": "CPU usage %($instance)",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "$ds"
+ },
+ "description": "Amount of used memory\n\nResident memory shows share which can be freed by OS when needed.\n\nAnonymous shows share for memory allocated by the process itself. This share cannot be freed by the OS, so it must be taken into account by OOM killer.\n\nIf you think that usage is abnormal or unexpected, please file an issue and attach memory profile if possible.",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "percentunit"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 8,
+ "w": 12,
+ "x": 12,
+ "y": 35
+ },
+ "id": 37,
+ "links": [
+ {
+ "targetBlank": true,
+ "title": "Profiling",
+ "url": "https://docs.victoriametrics.com/vmagent.html#profiling"
+ }
+ ],
+ "options": {
+ "legend": {
+ "calcs": [
+ "mean",
+ "lastNotNull",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true,
+ "sortBy": "Last *",
+ "sortDesc": true
+ },
+ "tooltip": {
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "9.2.6",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "$ds"
+ },
+ "editorMode": "code",
+ "exemplar": false,
+ "expr": "max(\n max_over_time(process_resident_memory_bytes{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])\n /\n vm_available_memory_bytes{job=~\"$job\", instance=~\"$instance\"}\n) by(job)",
+ "interval": "",
+ "legendFormat": "__auto",
+ "range": true,
+ "refId": "A"
+ }
+ ],
+ "title": "Memory usage % ($instance)",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "$ds"
+ },
+ "description": "Panel shows the percentage of open file descriptors in the OS.\nReaching the limit of open files can cause various issues and must be prevented.\n\nSee how to change limits here https://medium.com/@muhammadtriwibowo/set-permanently-ulimit-n-open-files-in-ubuntu-4d61064429a",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "decimals": 3,
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "percentunit"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 8,
+ "w": 12,
+ "x": 0,
+ "y": 43
+ },
+ "id": 39,
+ "links": [],
+ "options": {
+ "legend": {
+ "calcs": [
+ "mean",
+ "lastNotNull",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "9.2.6",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "$ds"
+ },
+ "editorMode": "code",
+ "exemplar": false,
+ "expr": "max(\n max_over_time(process_open_fds{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])\n /\n process_max_fds{job=~\"$job\", instance=~\"$instance\"}\n) by(job)",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "__auto",
+ "range": true,
+ "refId": "A"
+ }
+ ],
+ "title": "Open FDs usage % ($instance)",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "$ds"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "decimals": 0,
+ "links": [],
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 8,
+ "w": 12,
+ "x": 12,
+ "y": 43
+ },
+ "id": 41,
+ "links": [],
+ "options": {
+ "legend": {
+ "calcs": [
+ "mean",
+ "lastNotNull",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "9.2.6",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "$ds"
+ },
+ "editorMode": "code",
+ "expr": "sum(go_goroutines{job=~\"$job\", instance=~\"$instance\"}) by(job)",
+ "format": "time_series",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "__auto",
+ "range": true,
+ "refId": "A"
+ }
+ ],
+ "title": "Goroutines ($instance)",
+ "type": "timeseries"
+ }
+ ],
+ "targets": [
+ {
+ "datasource": {
+ "type": "datasource",
+ "uid": "grafana"
+ },
+ "refId": "A"
+ }
+ ],
+ "title": "Resource usage",
+ "type": "row"
+ },
+ {
+ "collapsed": true,
+ "datasource": {
+ "type": "datasource",
+ "uid": "grafana"
+ },
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 33
+ },
+ "id": 17,
+ "panels": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "$ds"
+ },
+ "description": "Shows top $topk current active (firing) alerting rules.\n\nThe panel uses MetricsQL functions and may not work with Prometheus.",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 8,
+ "w": 12,
+ "x": 0,
+ "y": 28
+ },
+ "id": 14,
+ "options": {
+ "legend": {
+ "calcs": [
+ "mean",
+ "lastNotNull",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true,
+ "sortBy": "Last *",
+ "sortDesc": true
+ },
+ "tooltip": {
+ "mode": "multi",
+ "sort": "desc"
+ }
+ },
+ "pluginVersion": "9.2.6",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "$ds"
+ },
+ "editorMode": "code",
+ "exemplar": false,
+ "expr": "topk_max($topk, sum(vmalert_alerts_firing{job=~\"$job\", instance=~\"$instance\", group=~\"$group\"}) by(job, group, alertname) > 0)",
+ "interval": "",
+ "legendFormat": "{{group}}.{{alertname}} ({{job}})",
+ "range": true,
+ "refId": "A"
+ }
+ ],
+ "title": "Top $topk active alerts ($group)",
+ "type": "timeseries"
},
{
- "aliasColors": {},
- "bars": false,
- "dashLength": 10,
- "dashes": false,
"datasource": {
"type": "prometheus",
"uid": "$ds"
},
"description": "Shows the events when rule execution resulted into an error. Check the logs for more details.",
- "fill": 0,
- "fillGradient": 0,
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": []
+ },
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
- "y": 25
+ "y": 28
},
- "hiddenSeries": false,
"id": 13,
- "legend": {
- "alignAsTable": true,
- "avg": true,
- "current": true,
- "max": true,
- "min": false,
- "show": true,
- "sort": "current",
- "sortDesc": true,
- "total": false,
- "values": true
- },
- "lines": true,
- "linewidth": 1,
- "nullPointMode": "null",
"options": {
- "alertThreshold": true
+ "legend": {
+ "calcs": [
+ "mean",
+ "lastNotNull",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true,
+ "sortBy": "Last *",
+ "sortDesc": true
+ },
+ "tooltip": {
+ "mode": "multi",
+ "sort": "desc"
+ }
},
- "percentage": false,
- "pluginVersion": "9.0.3",
- "pointradius": 2,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
+ "pluginVersion": "9.2.6",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "$ds"
},
+ "editorMode": "code",
"exemplar": false,
- "expr": "sum(vmalert_alerting_rules_error{job=~\"$job\", instance=~\"$instance\", group=~\"$group\"}) by(group, alertname) > 0",
+ "expr": "sum(vmalert_alerting_rules_error{job=~\"$job\", instance=~\"$instance\", group=~\"$group\"}) by(job, group, alertname) > 0",
"interval": "",
- "legendFormat": "{{alertname}} ({{group}})",
+ "legendFormat": "{{group}}.{{alertname}} ({{job}})",
+ "range": true,
"refId": "A"
}
],
- "thresholds": [],
- "timeRegions": [],
"title": "Errors ($group)",
- "tooltip": {
- "shared": true,
- "sort": 2,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "mode": "time",
- "show": true,
- "values": []
- },
- "yaxes": [
- {
- "format": "short",
- "logBase": 1,
- "show": true
- },
- {
- "format": "short",
- "logBase": 1,
- "show": true
- }
- ],
- "yaxis": {
- "align": false
- }
+ "type": "timeseries"
},
{
- "aliasColors": {},
- "bars": false,
- "dashLength": 10,
- "dashes": false,
"datasource": {
"type": "prometheus",
"uid": "$ds"
},
"description": "Shows the current pending alerting rules per group.\nBy pending means the rule which remains active less than configured `for` parameter.",
- "fill": 0,
- "fillGradient": 0,
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": []
+ },
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
- "y": 33
+ "y": 36
},
- "hiddenSeries": false,
"id": 20,
- "legend": {
- "alignAsTable": true,
- "avg": true,
- "current": true,
- "max": true,
- "min": false,
- "show": true,
- "sort": "current",
- "sortDesc": true,
- "total": false,
- "values": true
- },
- "lines": true,
- "linewidth": 1,
- "nullPointMode": "null",
"options": {
- "alertThreshold": true
+ "legend": {
+ "calcs": [
+ "mean",
+ "lastNotNull",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true,
+ "sortBy": "Mean",
+ "sortDesc": true
+ },
+ "tooltip": {
+ "mode": "multi",
+ "sort": "desc"
+ }
},
- "percentage": false,
- "pluginVersion": "9.0.3",
- "pointradius": 2,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
+ "pluginVersion": "9.2.6",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "$ds"
},
+ "editorMode": "code",
"exemplar": false,
- "expr": "sum(vmalert_alerts_pending{job=~\"$job\", instance=~\"$instance\", group=~\"$group\"}) by(group, alertname) > 0",
+ "expr": "sum(vmalert_alerts_pending{job=~\"$job\", instance=~\"$instance\", group=~\"$group\"}) by(job, group, alertname) > 0",
"interval": "",
- "legendFormat": "{{alertname}} ({{group}})",
+ "legendFormat": "{{group}}.{{alertname}} ({{job}})",
+ "range": true,
"refId": "A"
}
],
- "thresholds": [],
- "timeRegions": [],
"title": "Pending ($group)",
- "tooltip": {
- "shared": true,
- "sort": 2,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "mode": "time",
- "show": true,
- "values": []
- },
- "yaxes": [
- {
- "format": "short",
- "logBase": 1,
- "show": true
- },
- {
- "format": "short",
- "logBase": 1,
- "show": true
- }
- ],
- "yaxis": {
- "align": false
- }
+ "type": "timeseries"
},
{
- "aliasColors": {},
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": {
- "type": "prometheus",
- "uid": "$ds"
- },
- "description": "Shows how many alerts are sent to Alertmanager per second. Only active alerts are sent.",
- "fill": 0,
- "fillGradient": 0,
- "gridPos": {
- "h": 8,
- "w": 12,
- "x": 12,
- "y": 33
- },
- "hiddenSeries": false,
- "id": 26,
- "legend": {
- "alignAsTable": true,
- "avg": true,
- "current": true,
- "max": true,
- "min": false,
- "show": true,
- "sort": "current",
- "sortDesc": true,
- "total": false,
- "values": true
- },
- "lines": true,
- "linewidth": 1,
- "nullPointMode": "null",
- "options": {
- "alertThreshold": true
- },
- "percentage": false,
- "pluginVersion": "9.0.3",
- "pointradius": 2,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "datasource": {
- "type": "prometheus",
- "uid": "$ds"
- },
- "exemplar": false,
- "expr": "sum(rate(vmalert_alerts_sent_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by(instance, addr) > 0",
- "interval": "",
- "legendFormat": "{{instance}} => {{addr}}",
- "refId": "A"
- }
- ],
- "thresholds": [],
- "timeRegions": [],
- "title": "Requests rate to Alertmanager ($group)",
- "tooltip": {
- "shared": true,
- "sort": 2,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "mode": "time",
- "show": true,
- "values": []
- },
- "yaxes": [
- {
- "$$hashKey": "object:229",
- "format": "short",
- "logBase": 1,
- "min": "0",
- "show": true
- },
- {
- "$$hashKey": "object:230",
- "format": "short",
- "logBase": 1,
- "min": "0",
- "show": true
- }
- ],
- "yaxis": {
- "align": false
- }
- },
- {
- "aliasColors": {},
- "bars": false,
- "dashLength": 10,
- "dashes": false,
"datasource": {
"type": "prometheus",
"uid": "$ds"
},
"description": "Shows the error rate for the attempts to send alerts to Alertmanager. If not zero it means there issues on attempt to send notification to Alertmanager and some alerts may be not delivered properly. Check the logs for more details.",
- "fill": 0,
- "fillGradient": 0,
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": []
+ },
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
- "y": 41
+ "y": 36
},
- "hiddenSeries": false,
"id": 32,
- "legend": {
- "alignAsTable": true,
- "avg": true,
- "current": true,
- "max": true,
- "min": false,
- "show": true,
- "sort": "current",
- "sortDesc": true,
- "total": false,
- "values": true
- },
- "lines": true,
- "linewidth": 1,
- "nullPointMode": "null",
"options": {
- "alertThreshold": true
+ "legend": {
+ "calcs": [
+ "mean",
+ "lastNotNull",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "multi",
+ "sort": "none"
+ }
},
- "percentage": false,
- "pluginVersion": "9.0.3",
- "pointradius": 2,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
+ "pluginVersion": "9.2.6",
"targets": [
{
"datasource": {
@@ -1408,39 +2089,110 @@
"refId": "A"
}
],
- "thresholds": [],
- "timeRegions": [],
"title": "Errors rate to Alertmanager ($group)",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "$ds"
},
- "type": "graph",
- "xaxis": {
- "mode": "time",
- "show": true,
- "values": []
- },
- "yaxes": [
- {
- "$$hashKey": "object:229",
- "format": "short",
- "logBase": 1,
- "min": "0",
- "show": true
+ "description": "Shows how many alerts are sent to Alertmanager per second. Only active alerts are sent.",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "mappings": [],
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "short"
},
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 8,
+ "w": 12,
+ "x": 0,
+ "y": 44
+ },
+ "id": 26,
+ "options": {
+ "legend": {
+ "calcs": [
+ "mean",
+ "lastNotNull",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "multi",
+ "sort": "desc"
+ }
+ },
+ "pluginVersion": "9.2.6",
+ "targets": [
{
- "$$hashKey": "object:230",
- "format": "short",
- "logBase": 1,
- "min": "0",
- "show": true
+ "datasource": {
+ "type": "prometheus",
+ "uid": "$ds"
+ },
+ "editorMode": "code",
+ "exemplar": false,
+ "expr": "sum(rate(vmalert_alerts_sent_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by(job, addr) > 0",
+ "interval": "",
+ "legendFormat": "{{job}} => {{addr}}",
+ "range": true,
+ "refId": "A"
}
],
- "yaxis": {
- "align": false
- }
+ "title": "Requests rate to Alertmanager by job ($group)",
+ "type": "timeseries"
}
],
"targets": [
@@ -1465,99 +2217,112 @@
"h": 1,
"w": 24,
"x": 0,
- "y": 25
+ "y": 34
},
"id": 28,
"panels": [
{
- "aliasColors": {},
- "bars": false,
- "dashLength": 10,
- "dashes": false,
"datasource": {
"type": "prometheus",
"uid": "$ds"
},
- "description": "Shows the top 10 recording rules which generate the most of samples. Each generated sample is basically a time series which then ingested into configured remote storage. Rules with high numbers may cause the most pressure on the remote database and become a source of too high cardinality.",
- "fill": 0,
- "fillGradient": 0,
+ "description": "Shows the top $topk recording rules which generate the most of samples. Each generated sample is basically a time series which then ingested into configured remote storage. Rules with high numbers may cause the most pressure on the remote database and become a source of too high cardinality.\n\nThe panel uses MetricsQL functions and may not work with Prometheus.",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": []
+ },
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
- "y": 50
+ "y": 43
},
- "hiddenSeries": false,
"id": 31,
- "legend": {
- "alignAsTable": true,
- "avg": true,
- "current": true,
- "max": true,
- "min": false,
- "show": true,
- "sort": "current",
- "sortDesc": true,
- "total": false,
- "values": true
- },
- "lines": true,
- "linewidth": 1,
- "nullPointMode": "null",
"options": {
- "alertThreshold": true
+ "legend": {
+ "calcs": [
+ "mean",
+ "lastNotNull",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true,
+ "sortBy": "Last *",
+ "sortDesc": true
+ },
+ "tooltip": {
+ "mode": "multi",
+ "sort": "none"
+ }
},
- "percentage": false,
- "pluginVersion": "9.0.3",
- "pointradius": 2,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
+ "pluginVersion": "9.2.6",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "$ds"
},
+ "editorMode": "code",
"exemplar": false,
- "expr": "topk(10, sum(vmalert_recording_rules_last_evaluation_samples{job=~\"$job\", instance=~\"$instance\", group=~\"$group\"}) by(group, recording) > 0)",
+ "expr": "topk_max($topk, \n max(\n sum(vmalert_recording_rules_last_evaluation_samples{job=~\"$job\", instance=~\"$instance\", group=~\"$group\"}) by(job, instance, group, recording) > 0\n ) by(job, group, recording)\n)",
"interval": "",
- "legendFormat": "{{recording}} ({{group}})",
+ "legendFormat": "{{group}}.{{recording}} ({{job}})",
+ "range": true,
"refId": "A"
}
],
- "thresholds": [],
- "timeRegions": [],
- "title": "Top 10 rules by produced samples ($group)",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "mode": "time",
- "show": true,
- "values": []
- },
- "yaxes": [
- {
- "format": "short",
- "logBase": 1,
- "show": true
- },
- {
- "format": "short",
- "logBase": 1,
- "show": true
- }
- ],
- "yaxis": {
- "align": false
- }
+ "title": "Top $topk rules by produced samples ($group)",
+ "type": "timeseries"
},
{
"datasource": {
@@ -1571,6 +2336,8 @@
"mode": "palette-classic"
},
"custom": {
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
@@ -1603,7 +2370,8 @@
"mode": "absolute",
"steps": [
{
- "color": "green"
+ "color": "green",
+ "value": null
},
{
"color": "red",
@@ -1619,22 +2387,25 @@
"h": 8,
"w": 12,
"x": 12,
- "y": 50
+ "y": 43
},
"id": 33,
"options": {
"legend": {
"calcs": [
- "max",
"lastNotNull",
+ "max",
"mean"
],
"displayMode": "table",
- "placement": "bottom"
+ "placement": "bottom",
+ "showLegend": true,
+ "sortBy": "Last *",
+ "sortDesc": true
},
"tooltip": {
- "mode": "single",
- "sort": "none"
+ "mode": "multi",
+ "sort": "desc"
}
},
"pluginVersion": "8.0.3",
@@ -1644,10 +2415,12 @@
"type": "prometheus",
"uid": "$ds"
},
+ "editorMode": "code",
"exemplar": false,
- "expr": "sum(vmalert_recording_rules_last_evaluation_samples{job=~\"$job\", instance=~\"$instance\", group=~\"$group\"}) by(group, recording) < 1",
+ "expr": "count(vmalert_recording_rules_last_evaluation_samples{job=~\"$job\", instance=~\"$instance\", group=~\"$group\"} < 1) by(job, group, recording)",
"interval": "",
- "legendFormat": "{{recording}} ({{group}})",
+ "legendFormat": "{{group}}.{{recording}} ({{job}})",
+ "range": true,
"refId": "A"
}
],
@@ -1655,93 +2428,104 @@
"type": "timeseries"
},
{
- "aliasColors": {},
- "bars": false,
- "dashLength": 10,
- "dashes": false,
"datasource": {
"type": "prometheus",
"uid": "$ds"
},
- "fill": 0,
- "fillGradient": 0,
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": []
+ },
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
- "y": 58
+ "y": 51
},
- "hiddenSeries": false,
"id": 30,
- "legend": {
- "alignAsTable": true,
- "avg": true,
- "current": true,
- "max": true,
- "min": false,
- "show": true,
- "sort": "current",
- "sortDesc": true,
- "total": false,
- "values": true
- },
- "lines": true,
- "linewidth": 1,
- "nullPointMode": "null",
"options": {
- "alertThreshold": true
+ "legend": {
+ "calcs": [
+ "mean",
+ "lastNotNull",
+ "max"
+ ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "multi",
+ "sort": "none"
+ }
},
- "percentage": false,
- "pluginVersion": "9.0.3",
- "pointradius": 2,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
+ "pluginVersion": "9.2.6",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "$ds"
},
+ "editorMode": "code",
"exemplar": false,
- "expr": "sum(vmalert_recording_rules_error{job=~\"$job\", instance=~\"$instance\", group=~\"$group\"}) by(group, recording) > 0",
+ "expr": "sum(vmalert_recording_rules_error{job=~\"$job\", instance=~\"$instance\", group=~\"$group\"}) by(job, group, recording) > 0",
"interval": "",
- "legendFormat": "{{recording}} ({{group}})",
+ "legendFormat": "{{group}}.{{recording}} ({{job}})",
+ "range": true,
"refId": "A"
}
],
- "thresholds": [],
- "timeRegions": [],
"title": "Errors ($group)",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "mode": "time",
- "show": true,
- "values": []
- },
- "yaxes": [
- {
- "format": "short",
- "logBase": 1,
- "show": true
- },
- {
- "format": "short",
- "logBase": 1,
- "show": true
- }
- ],
- "yaxis": {
- "align": false
- }
+ "type": "timeseries"
}
],
"targets": [
@@ -1758,296 +2542,90 @@
},
{
"collapsed": true,
- "datasource": {
- "type": "datasource",
- "uid": "grafana"
- },
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
- "y": 26
+ "y": 35
},
- "id": 43,
+ "id": 55,
"panels": [
{
- "aliasColors": {},
- "bars": false,
- "dashLength": 10,
- "dashes": false,
"datasource": {
"type": "prometheus",
"uid": "$ds"
},
- "description": "Shows the CPU usage percentage per vmalert instance. \nIf you think that usage is abnormal or unexpected pls file an issue and attach CPU profile if possible.",
"fieldConfig": {
"defaults": {
- "links": []
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "auto",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ }
},
"overrides": []
},
- "fill": 0,
- "fillGradient": 0,
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
- "y": 67
+ "y": 9
},
- "hiddenSeries": false,
- "id": 35,
- "legend": {
- "alignAsTable": true,
- "avg": true,
- "current": true,
- "max": true,
- "min": false,
- "show": true,
- "sort": "current",
- "sortDesc": true,
- "total": false,
- "values": true
- },
- "lines": true,
- "linewidth": 1,
- "links": [
- {
- "targetBlank": true,
- "title": "Profiling",
- "url": "https://docs.victoriametrics.com/vmagent.html#profiling"
- }
- ],
- "nullPointMode": "null",
+ "id": 52,
"options": {
- "alertThreshold": true
- },
- "percentage": false,
- "pluginVersion": "9.0.3",
- "pointradius": 2,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "datasource": {
- "type": "prometheus",
- "uid": "$ds"
- },
- "exemplar": false,
- "expr": "sum(rate(process_cpu_seconds_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by(instance) / min(process_cpu_cores_available{job=~\"$job\", instance=~\"$instance\"}) by(instance)",
- "format": "time_series",
- "interval": "",
- "intervalFactor": 1,
- "legendFormat": "{{instance}}",
- "refId": "A"
- }
- ],
- "thresholds": [],
- "timeRegions": [],
- "title": "CPU ($instance)",
- "tooltip": {
- "shared": true,
- "sort": 2,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "mode": "time",
- "show": true,
- "values": []
- },
- "yaxes": [
- {
- "$$hashKey": "object:473",
- "format": "percentunit",
- "logBase": 1,
- "min": "0",
- "show": true
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
},
- {
- "$$hashKey": "object:474",
- "format": "short",
- "logBase": 1,
- "show": true
+ "tooltip": {
+ "mode": "single",
+ "sort": "none"
}
- ],
- "yaxis": {
- "align": false
- }
- },
- {
- "aliasColors": {},
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": {
- "type": "prometheus",
- "uid": "$ds"
},
- "description": "Amount of used memory\n\nResident memory shows share which can be freed by OS when needed.\n\nAnonymous shows share for memory allocated by the process itself. This share cannot be freed by the OS, so it must be taken into account by OOM killer.\n\nIf you think that usage is abnormal or unexpected, please file an issue and attach memory profile if possible.",
- "fieldConfig": {
- "defaults": {
- "links": []
- },
- "overrides": []
- },
- "fill": 0,
- "fillGradient": 0,
- "gridPos": {
- "h": 8,
- "w": 12,
- "x": 12,
- "y": 67
- },
- "hiddenSeries": false,
- "id": 37,
- "legend": {
- "alignAsTable": true,
- "avg": true,
- "current": true,
- "max": true,
- "min": false,
- "show": true,
- "sort": "current",
- "sortDesc": true,
- "total": false,
- "values": true
- },
- "lines": true,
- "linewidth": 1,
- "links": [
- {
- "targetBlank": true,
- "title": "Profiling",
- "url": "https://docs.victoriametrics.com/vmagent.html#profiling"
- }
- ],
- "nullPointMode": "null",
- "options": {
- "alertThreshold": true
- },
- "percentage": false,
- "pluginVersion": "9.0.3",
- "pointradius": 2,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "datasource": {
- "type": "prometheus",
- "uid": "$ds"
- },
- "exemplar": false,
- "expr": "sum(process_resident_memory_bytes{job=~\"$job\", instance=~\"$instance\"}) by (instance)",
- "interval": "",
- "legendFormat": "resident {{instance}}",
- "refId": "A"
- },
- {
- "datasource": {
- "type": "prometheus",
- "uid": "$ds"
- },
- "exemplar": false,
- "expr": "sum(process_resident_memory_anon_bytes{job=~\"$job\", instance=~\"$instance\"}) by (instance)",
- "hide": false,
- "interval": "",
- "legendFormat": "anonymous {{instance}}",
- "refId": "B"
- }
- ],
- "thresholds": [],
- "timeRegions": [],
- "title": "Memory usage ($instance)",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "mode": "time",
- "show": true,
- "values": []
- },
- "yaxes": [
- {
- "format": "bytes",
- "logBase": 1,
- "min": "0",
- "show": true
- },
- {
- "format": "short",
- "logBase": 1,
- "show": true
- }
- ],
- "yaxis": {
- "align": false
- }
- },
- {
- "aliasColors": {},
- "bars": false,
- "dashLength": 10,
- "dashes": false,
- "datasource": {
- "type": "prometheus",
- "uid": "$ds"
- },
- "description": "Panel shows the percentage of open file descriptors in the OS.\nReaching the limit of open files can cause various issues and must be prevented.\n\nSee how to change limits here https://medium.com/@muhammadtriwibowo/set-permanently-ulimit-n-open-files-in-ubuntu-4d61064429a",
- "fieldConfig": {
- "defaults": {
- "links": []
- },
- "overrides": []
- },
- "fill": 0,
- "fillGradient": 0,
- "gridPos": {
- "h": 8,
- "w": 12,
- "x": 0,
- "y": 75
- },
- "hiddenSeries": false,
- "id": 39,
- "legend": {
- "alignAsTable": true,
- "avg": true,
- "current": true,
- "max": true,
- "min": false,
- "show": true,
- "sort": "current",
- "sortDesc": true,
- "total": false,
- "values": true
- },
- "lines": true,
- "linewidth": 1,
- "links": [],
- "nullPointMode": "null",
- "options": {
- "alertThreshold": true
- },
- "percentage": false,
- "pluginVersion": "9.0.3",
- "pointradius": 2,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
"targets": [
{
"datasource": {
@@ -2055,166 +2633,115 @@
"uid": "$ds"
},
"editorMode": "code",
- "exemplar": false,
- "expr": "sum(process_open_fds{job=~\"$job\", instance=~\"$instance\"}) by (instance) \n/\nmin(process_max_fds{job=~\"$job\", instance=~\"$instance\"}) by(instance)",
- "format": "time_series",
- "interval": "",
- "intervalFactor": 2,
- "legendFormat": "open {{instance}}",
+ "expr": "sum(rate(vmalert_remotewrite_sent_rows_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by(job)",
+ "legendFormat": "__auto",
"range": true,
"refId": "A"
}
],
- "thresholds": [],
- "timeRegions": [],
- "title": "Open FDs ($instance)",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "mode": "time",
- "show": true,
- "values": []
- },
- "yaxes": [
- {
- "$$hashKey": "object:540",
- "decimals": 3,
- "format": "percentunit",
- "logBase": 1,
- "min": "0",
- "show": true
- },
- {
- "$$hashKey": "object:541",
- "format": "short",
- "logBase": 1,
- "min": "0",
- "show": true
- }
- ],
- "yaxis": {
- "align": false
- }
+ "title": "Datapoints send rate ($instance)",
+ "type": "timeseries"
},
{
- "aliasColors": {},
- "bars": false,
- "dashLength": 10,
- "dashes": false,
"datasource": {
"type": "prometheus",
"uid": "$ds"
},
+ "description": "Shows the number of datapoints dropped by vmalert while sending to the configured remote write URL. vmalert performs up to 5 retries before dropping the data. Check vmalert's error logs for the specific error message.",
"fieldConfig": {
"defaults": {
- "links": []
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": 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",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ }
},
"overrides": []
},
- "fill": 0,
- "fillGradient": 0,
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
- "y": 75
+ "y": 9
},
- "hiddenSeries": false,
- "id": 41,
- "legend": {
- "alignAsTable": true,
- "avg": true,
- "current": true,
- "max": true,
- "min": false,
- "show": true,
- "sort": "current",
- "sortDesc": true,
- "total": false,
- "values": true
- },
- "lines": true,
- "linewidth": 1,
- "links": [],
- "nullPointMode": "null",
+ "id": 53,
"options": {
- "alertThreshold": true
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "single",
+ "sort": "none"
+ }
},
- "percentage": false,
- "pluginVersion": "9.0.3",
- "pointradius": 2,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [],
- "spaceLength": 10,
- "stack": false,
- "steppedLine": false,
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "$ds"
},
- "expr": "sum(go_goroutines{job=~\"$job\", instance=~\"$instance\"}) by(instance)",
- "format": "time_series",
- "interval": "",
- "intervalFactor": 2,
- "legendFormat": "{{instance}}",
+ "editorMode": "code",
+ "expr": "sum(rate(vmalert_remotewrite_dropped_rows_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by(job) > 0",
+ "legendFormat": "__auto",
+ "range": true,
"refId": "A"
}
],
- "thresholds": [],
- "timeRegions": [],
- "title": "Goroutines ($instance)",
- "tooltip": {
- "shared": true,
- "sort": 0,
- "value_type": "individual"
- },
- "type": "graph",
- "xaxis": {
- "mode": "time",
- "show": true,
- "values": []
- },
- "yaxes": [
- {
- "decimals": 0,
- "format": "short",
- "logBase": 1,
- "min": "0",
- "show": true
- },
- {
- "format": "short",
- "logBase": 1,
- "show": true
- }
- ],
- "yaxis": {
- "align": false
- }
+ "title": "Datapoints drop rate ($instance)",
+ "type": "timeseries"
}
],
- "targets": [
- {
- "datasource": {
- "type": "datasource",
- "uid": "grafana"
- },
- "refId": "A"
- }
- ],
- "title": "Resource usage",
+ "title": "Remote write",
"type": "row"
}
],
"refresh": false,
- "schemaVersion": 36,
+ "schemaVersion": 37,
"style": "dark",
"tags": [
"victoriametrics",
@@ -2224,9 +2751,9 @@
"list": [
{
"current": {
- "selected": false,
- "text": "VictoriaMetrics",
- "value": "VictoriaMetrics"
+ "selected": true,
+ "text": "VictoriaMetrics - cluster",
+ "value": "VictoriaMetrics - cluster"
},
"hide": 0,
"includeAll": false,
@@ -2248,8 +2775,8 @@
},
"definition": "label_values(vm_app_version{version=~\"^vmalert.*\"}, job)",
"hide": 0,
- "includeAll": false,
- "multi": false,
+ "includeAll": true,
+ "multi": true,
"name": "job",
"options": [],
"query": {
@@ -2308,6 +2835,53 @@
"sort": 0,
"type": "query"
},
+ {
+ "current": {
+ "selected": true,
+ "text": "5",
+ "value": "5"
+ },
+ "hide": 0,
+ "includeAll": false,
+ "multi": false,
+ "name": "topk",
+ "options": [
+ {
+ "selected": true,
+ "text": "5",
+ "value": "5"
+ },
+ {
+ "selected": false,
+ "text": "10",
+ "value": "10"
+ },
+ {
+ "selected": false,
+ "text": "20",
+ "value": "20"
+ },
+ {
+ "selected": false,
+ "text": "30",
+ "value": "30"
+ },
+ {
+ "selected": false,
+ "text": "40",
+ "value": "40"
+ },
+ {
+ "selected": false,
+ "text": "50",
+ "value": "50"
+ }
+ ],
+ "query": "5, 10, 20, 30, 40, 50",
+ "queryValue": "",
+ "skipUrlSync": false,
+ "type": "custom"
+ },
{
"datasource": {
"type": "prometheus",
@@ -2331,4 +2905,4 @@
"uid": "LzldHAVnz",
"version": 1,
"weekStart": ""
-}
+}
\ No newline at end of file