dashboards: update troubleshooting row (#505)

* Slow metrics load panel was removed since it is hard to interpret without
additional metrics and stats;
* Slow inserts panel was updated to display percentage of slow inserts comparing
to total number of inserts to show the real impact.
This commit is contained in:
Roman Khavronenko 2020-05-19 22:48:45 +01:00 committed by GitHub
parent 7705c19720
commit 9a3afea123
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23

View file

@ -65,7 +65,7 @@
"gnetId": 10229,
"graphTooltip": 0,
"id": null,
"iteration": 1589727903402,
"iteration": 1589923637424,
"links": [
{
"icon": "doc",
@ -2074,7 +2074,7 @@
"h": 8,
"w": 12,
"x": 0,
"y": 37
"y": 13
},
"hiddenSeries": false,
"id": 66,
@ -2155,14 +2155,14 @@
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"description": "Slow queries according to `search.logSlowQueryDuration` flag, which is `5s` by default.",
"description": "Slow queries rate according to `search.logSlowQueryDuration` flag, which is `5s` by default.",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 37
"y": 13
},
"hiddenSeries": false,
"id": 60,
@ -2204,7 +2204,7 @@
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Slow queries",
"title": "Slow queries rate",
"tooltip": {
"shared": true,
"sort": 0,
@ -2248,14 +2248,14 @@
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"description": "The number of slow inserts during the last 5 minutes. If this number remains high during extended periods of time, then it is likely more RAM is needed for optimal handling of the current number of active time series.\n\nIn general, VictoriaMetrics requires ~1KB or RAM per active time series, so it should be easy calculating the required amounts of RAM for the current workload according to capacity planning docs. But the resulting number may be far from the real number because the required amounts of memory depends on may other factors such as the number of labels per time series and the length of label values.",
"description": "The percentage of slow inserts comparing to total insertion rate during the last 5 minutes. \n\nThe less value is better. If percentage remains high (>50%) during extended periods of time, then it is likely more RAM is needed for optimal handling of the current number of active time series. \n\nIn general, VictoriaMetrics requires ~1KB or RAM per active time series, so it should be easy calculating the required amounts of RAM for the current workload according to capacity planning docs. But the resulting number may be far from the real number because the required amounts of memory depends on may other factors such as the number of labels per time series and the length of label values.",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 8,
"w": 12,
"w": 24,
"x": 0,
"y": 45
"y": 21
},
"hiddenSeries": false,
"id": 68,
@ -2285,12 +2285,12 @@
"steppedLine": false,
"targets": [
{
"expr": "sum(increase(vm_slow_row_inserts_total{job=\"$job\"}[5m]))",
"expr": "sum(rate(vm_slow_row_inserts_total{job=\"$job\"}[5m])) / sum(rate(vm_rows_inserted_total{job=\"$job\"}[5m]))",
"format": "time_series",
"hide": false,
"interval": "",
"intervalFactor": 1,
"legendFormat": "slow inserts rate",
"legendFormat": "slow inserts percentage",
"refId": "A"
}
],
@ -2314,102 +2314,8 @@
},
"yaxes": [
{
"decimals": null,
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"description": "The number of slow loads of metric names during the last 5 minutes. If this number remains high during extended periods of time, then it is likely more RAM is needed for optimal handling of the current number of active time series.\n\nUsually VictoriaMetrics requires ~1KB or RAM per active time series, so it should be easy calculating the required amounts of RAM for the current workload according to capacity planning docs. But the resulting number may be far from the real number because the required amounts of memory depends on may other factors such as the number of labels per time series and the length of label values.",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 45
},
"hiddenSeries": false,
"id": 69,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": false,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 2,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(increase(vm_slow_metric_name_loads_total{job=\"$job\"}[5m]))",
"format": "time_series",
"hide": false,
"interval": "",
"intervalFactor": 1,
"legendFormat": "slow metrics loads rate",
"refId": "A"
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Slow metric loads",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"decimals": null,
"format": "short",
"decimals": 2,
"format": "percentunit",
"label": null,
"logBase": 1,
"max": null,