diff --git a/dashboards/victoriametrics.json b/dashboards/victoriametrics.json index b730e045b..f5bce5bd0 100644 --- a/dashboards/victoriametrics.json +++ b/dashboards/victoriametrics.json @@ -6,13 +6,7 @@ "type": "grafana", "id": "grafana", "name": "Grafana", - "version": "9.0.3" - }, - { - "type": "panel", - "id": "graph", - "name": "Graph (old)", - "version": "" + "version": "9.2.6" }, { "type": "datasource", @@ -26,11 +20,23 @@ "name": "Stat", "version": "" }, + { + "type": "panel", + "id": "table", + "name": "Table", + "version": "" + }, { "type": "panel", "id": "text", "name": "Text", "version": "" + }, + { + "type": "panel", + "id": "timeseries", + "name": "Time series", + "version": "" } ], "annotations": { @@ -52,16 +58,26 @@ "type": "dashboard" }, "type": "dashboard" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "enable": true, + "expr": "sum(ALERTS{alertgroup=\"vmsingle\",alertstate=\"firing\",show_at=\"dashboard\"}) by(alertname)", + "iconColor": "red", + "name": "alerts", + "titleFormat": "{{alertname}}" } ] }, - "description": "Overview for single node VictoriaMetrics v1.79.0 or higher", + "description": "Overview for single node VictoriaMetrics v1.83.0 or higher", "editable": true, "fiscalYearStartMonth": 0, "gnetId": 10229, "graphTooltip": 0, "id": null, - "iteration": 1663928777219, "links": [ { "icon": "doc", @@ -131,10 +147,15 @@ }, "id": 85, "options": { + "code": { + "language": "plaintext", + "showLineNumbers": false, + "showMiniMap": false + }, "content": "
$version
", "mode": "markdown" }, - "pluginVersion": "9.0.3", + "pluginVersion": "9.2.6", "targets": [ { "datasource": { @@ -196,14 +217,14 @@ "text": {}, "textMode": "auto" }, - "pluginVersion": "9.0.3", + "pluginVersion": "9.2.6", "targets": [ { "datasource": { "type": "prometheus", "uid": "$ds" }, - "exemplar": true, + "exemplar": false, "expr": "sum(vm_rows{job=~\"$job\", instance=~\"$instance\", type!=\"indexdb\"})", "format": "time_series", "instant": true, @@ -221,7 +242,7 @@ "type": "prometheus", "uid": "$ds" }, - "description": "Total amount of used disk space", + "description": "Shows the datapoints ingestion rate.", "fieldConfig": { "defaults": { "color": { @@ -237,7 +258,7 @@ } ] }, - "unit": "bytes" + "unit": "short" }, "overrides": [] }, @@ -247,7 +268,7 @@ "x": 9, "y": 1 }, - "id": 81, + "id": 107, "links": [], "maxDataPoints": 100, "options": { @@ -265,15 +286,16 @@ "text": {}, "textMode": "auto" }, - "pluginVersion": "9.0.3", + "pluginVersion": "9.2.6", "targets": [ { "datasource": { "type": "prometheus", "uid": "$ds" }, + "editorMode": "code", "exemplar": false, - "expr": "sum(vm_data_size_bytes{job=~\"$job\"})", + "expr": "sum(rate(vm_rows_inserted_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))", "format": "time_series", "instant": true, "interval": "", @@ -282,7 +304,7 @@ "refId": "A" } ], - "title": "Disk space usage", + "title": "Ingestion rate", "type": "stat" }, { @@ -290,7 +312,7 @@ "type": "prometheus", "uid": "$ds" }, - "description": "Average disk usage per datapoint.", + "description": "Shows the rate of HTTP read requests.", "fieldConfig": { "defaults": { "color": { @@ -306,7 +328,7 @@ } ] }, - "unit": "bytes" + "unit": "short" }, "overrides": [] }, @@ -316,7 +338,7 @@ "x": 14, "y": 1 }, - "id": 82, + "id": 108, "links": [], "maxDataPoints": 100, "options": { @@ -334,15 +356,16 @@ "text": {}, "textMode": "auto" }, - "pluginVersion": "9.0.3", + "pluginVersion": "9.2.6", "targets": [ { "datasource": { "type": "prometheus", "uid": "$ds" }, - "exemplar": true, - "expr": "sum(vm_data_size_bytes{job=~\"$job\"}) / sum(vm_rows{job=~\"$job\"})", + "editorMode": "code", + "exemplar": false, + "expr": "sum(rate(vm_http_requests_total{job=~\"$job\", instance=~\"$instance\", path!~\".*(/write|/metrics)\"}[$__rate_interval]))", "format": "time_series", "instant": true, "interval": "", @@ -351,7 +374,7 @@ "refId": "A" } ], - "title": "Bytes per point", + "title": "Read requests", "type": "stat" }, { @@ -359,7 +382,7 @@ "type": "prometheus", "uid": "$ds" }, - "description": "Total size of allowed memory via flag `-memory.allowedPercent`", + "description": "Total number of available CPUs for VM process", "fieldConfig": { "defaults": { "color": { @@ -372,10 +395,14 @@ { "color": "green", "value": null + }, + { + "color": "red", + "value": 80 } ] }, - "unit": "bytes" + "unit": "short" }, "overrides": [] }, @@ -385,7 +412,7 @@ "x": 19, "y": 1 }, - "id": 79, + "id": 77, "links": [], "maxDataPoints": 100, "options": { @@ -403,15 +430,15 @@ "text": {}, "textMode": "auto" }, - "pluginVersion": "9.0.3", + "pluginVersion": "9.2.6", "targets": [ { "datasource": { "type": "prometheus", "uid": "$ds" }, - "exemplar": true, - "expr": "sum(vm_allowed_memory_bytes{job=~\"$job\", instance=~\"$instance\"})", + "exemplar": false, + "expr": "sum(vm_available_cpu_cores{job=~\"$job\", instance=~\"$instance\"})", "format": "time_series", "instant": true, "interval": "", @@ -420,7 +447,7 @@ "refId": "A" } ], - "title": "Allowed memory", + "title": "Available CPU", "type": "stat" }, { @@ -473,14 +500,15 @@ "text": {}, "textMode": "auto" }, - "pluginVersion": "9.0.3", + "pluginVersion": "9.2.6", "targets": [ { "datasource": { "type": "prometheus", "uid": "$ds" }, - "exemplar": true, + "editorMode": "code", + "exemplar": false, "expr": "vm_app_uptime_seconds{job=~\"$job\", instance=~\"$instance\"}", "instant": true, "interval": "", @@ -540,14 +568,14 @@ "text": {}, "textMode": "auto" }, - "pluginVersion": "9.0.3", + "pluginVersion": "9.2.6", "targets": [ { "datasource": { "type": "prometheus", "uid": "$ds" }, - "exemplar": true, + "exemplar": false, "expr": "vm_cache_entries{job=~\"$job\", instance=~\"$instance\", type=\"storage/hour_metric_ids\"}", "format": "time_series", "instant": true, @@ -565,7 +593,7 @@ "type": "prometheus", "uid": "$ds" }, - "description": "The minimum free disk space left", + "description": "Total amount of used disk space", "fieldConfig": { "defaults": { "color": { @@ -573,7 +601,7 @@ }, "mappings": [], "thresholds": { - "mode": "percentage", + "mode": "absolute", "steps": [ { "color": "green", @@ -591,7 +619,7 @@ "x": 9, "y": 3 }, - "id": 80, + "id": 81, "links": [], "maxDataPoints": 100, "options": { @@ -609,15 +637,16 @@ "text": {}, "textMode": "auto" }, - "pluginVersion": "9.0.3", + "pluginVersion": "9.2.6", "targets": [ { "datasource": { "type": "prometheus", "uid": "$ds" }, - "exemplar": true, - "expr": "min(vm_free_disk_space_bytes{job=~\"$job\", instance=~\"$instance\"})", + "editorMode": "code", + "exemplar": false, + "expr": "sum(vm_data_size_bytes{job=~\"$job\", instance=~\"$instance\"})", "format": "time_series", "instant": true, "interval": "", @@ -626,7 +655,7 @@ "refId": "A" } ], - "title": "Min free disk space", + "title": "Disk space usage", "type": "stat" }, { @@ -634,7 +663,7 @@ "type": "prometheus", "uid": "$ds" }, - "description": "Total number of available CPUs for VM process", + "description": "Average disk usage per datapoint.", "fieldConfig": { "defaults": { "color": { @@ -647,14 +676,10 @@ { "color": "green", "value": null - }, - { - "color": "red", - "value": 80 } ] }, - "unit": "short" + "unit": "bytes" }, "overrides": [] }, @@ -664,7 +689,7 @@ "x": 14, "y": 3 }, - "id": 77, + "id": 82, "links": [], "maxDataPoints": 100, "options": { @@ -682,15 +707,16 @@ "text": {}, "textMode": "auto" }, - "pluginVersion": "9.0.3", + "pluginVersion": "9.2.6", "targets": [ { "datasource": { "type": "prometheus", "uid": "$ds" }, - "exemplar": true, - "expr": "sum(vm_available_cpu_cores{job=~\"$job\", instance=~\"$instance\"})", + "editorMode": "code", + "exemplar": false, + "expr": "sum(vm_data_size_bytes{job=~\"$job\", instance=~\"$instance\"}) / sum(vm_rows{job=~\"$job\", instance=~\"$instance\"})", "format": "time_series", "instant": true, "interval": "", @@ -699,7 +725,7 @@ "refId": "A" } ], - "title": "Available CPU", + "title": "Bytes per point", "type": "stat" }, { @@ -751,14 +777,13 @@ "text": {}, "textMode": "auto" }, - "pluginVersion": "9.0.3", + "pluginVersion": "9.2.6", "targets": [ { "datasource": { - "type": "prometheus", "uid": "$ds" }, - "exemplar": true, + "exemplar": false, "expr": "sum(vm_available_memory_bytes{job=~\"$job\", instance=~\"$instance\"})", "format": "time_series", "instant": true, @@ -794,14 +819,115 @@ "refId": "A" } ], - "title": "Performance", + "title": "Overview", "type": "row" }, { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "How many datapoints are inserted into storage per second", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 6 + }, + "id": 106, + "links": [], + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "9.1.0", + "targets": [ + { + "datasource": { + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(rate(vm_rows_inserted_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (type) > 0", + "format": "time_series", + "hide": false, + "intervalFactor": 1, + "legendFormat": "__auto", + "range": true, + "refId": "A" + } + ], + "title": "Datapoints ingestion rate ($instance)", + "type": "timeseries" + }, + { "datasource": { "type": "prometheus", "uid": "$ds" @@ -809,200 +935,106 @@ "description": "* `*` - unsupported query path\n* `/write` - insert into VM\n* `/metrics` - query VM system metrics\n* `/query` - query instant values\n* `/query_range` - query over a range of time\n* `/series` - match a certain label set\n* `/label/{}/values` - query a list of label values (variables mostly)", "fieldConfig": { "defaults": { - "links": [] - }, - "overrides": [] - }, - "fill": 0, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 0, - "y": 6 - }, - "hiddenSeries": false, - "id": 12, - "legend": { - "alignAsTable": true, - "avg": true, - "current": true, - "max": true, - "min": false, - "show": true, - "sort": "current", - "sortDesc": true, - "total": false, - "values": true - }, - "lines": true, - "linewidth": 1, - "links": [], - "nullPointMode": "null as zero", - "options": { - "alertThreshold": true - }, - "percentage": false, - "pluginVersion": "9.0.3", - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "datasource": { - "type": "prometheus", - "uid": "$ds" + "color": { + "mode": "palette-classic" }, - "expr": "sum(rate(vm_http_requests_total{job=~\"$job\", instance=~\"$instance\", path!~\"/favicon.ico\"}[$__interval])) by (path) > 0", - "format": "time_series", - "interval": "", - "intervalFactor": 1, - "legendFormat": "{{path}}", - "refId": "A" - } - ], - "thresholds": [], - "timeRegions": [], - "title": "Requests rate ($instance)", - "tooltip": { - "shared": true, - "sort": 2, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "mode": "time", - "show": true, - "values": [] - }, - "yaxes": [ - { - "$$hashKey": "object:758", - "format": "short", - "logBase": 1, - "min": "0", - "show": true - }, - { - "$$hashKey": "object:759", - "format": "short", - "logBase": 1, - "min": "0", - "show": true - } - ], - "yaxis": { - "align": false - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "description": "The less time it takes is better.\n* `*` - unsupported query path\n* `/write` - insert into VM\n* `/metrics` - query VM system metrics\n* `/query` - query instant values\n* `/query_range` - query over a range of time\n* `/series` - match a certain label set\n* `/label/{}/values` - query a list of label values (variables mostly)", - "fieldConfig": { - "defaults": { - "links": [] + "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": "short" }, "overrides": [] }, - "fill": 1, - "fillGradient": 0, "gridPos": { "h": 8, "w": 12, "x": 12, "y": 6 }, - "hiddenSeries": false, - "id": 22, - "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, + "id": 12, "links": [], - "nullPointMode": "null as zero", "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": "9.1.0", "targets": [ { "datasource": { "type": "prometheus", "uid": "$ds" }, - "expr": "max(vm_request_duration_seconds{job=~\"$job\", instance=~\"$instance\", quantile=~\"(0.5|0.99)\"}) by (path, quantile) > 0", + "editorMode": "code", + "expr": "sum(rate(vm_http_requests_total{job=~\"$job\", instance=~\"$instance\", path!~\"/favicon.ico\"}[$__rate_interval])) by (path) > 0", "format": "time_series", + "interval": "", "intervalFactor": 1, - "legendFormat": "{{quantile}} ({{path}})", + "legendFormat": "{{path}}", + "range": true, "refId": "A" } ], - "thresholds": [], - "timeRegions": [], - "title": "Query duration ($instance)", - "tooltip": { - "shared": true, - "sort": 2, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "mode": "time", - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "s", - "logBase": 1, - "min": "0", - "show": true - }, - { - "format": "short", - "logBase": 1, - "min": "0", - "show": true - } - ], - "yaxis": { - "align": false - } + "title": "Requests rate ($instance)", + "type": "timeseries" }, { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, "datasource": { "type": "prometheus", "uid": "$ds" @@ -1010,34 +1042,66 @@ "description": "Shows the number of active time series with new data points inserted during the last hour. High value may result in ingestion slowdown. \n\nSee following link for details:", "fieldConfig": { "defaults": { - "links": [] + "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" + } + }, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" }, "overrides": [] }, - "fill": 1, - "fillGradient": 0, "gridPos": { "h": 8, "w": 12, "x": 0, "y": 14 }, - "hiddenSeries": false, "id": 51, - "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, @@ -1045,19 +1109,23 @@ "url": "https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/README.md#troubleshooting" } ], - "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": "9.1.0", "targets": [ { "datasource": { @@ -1071,625 +1139,97 @@ "refId": "A" } ], - "thresholds": [], - "timeRegions": [], "title": "Active time series ($instance)", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "mode": "time", - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "short", - "logBase": 1, - "min": "0", - "show": true - }, - { - "format": "short", - "logBase": 1, - "min": "0", - "show": true - } - ], - "yaxis": { - "align": false - } + "type": "timeseries" }, { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, "datasource": { "type": "prometheus", "uid": "$ds" }, - "description": "* `*` - unsupported query path\n* `/write` - insert into VM\n* `/metrics` - query VM system metrics\n* `/query` - query instant values\n* `/query_range` - query over a range of time\n* `/series` - match a certain label set\n* `/label/{}/values` - query a list of label values (variables mostly)", + "description": "The less time it takes is better.\n* `*` - unsupported query path\n* `/write` - insert into VM\n* `/metrics` - query VM system metrics\n* `/query` - query instant values\n* `/query_range` - query over a range of time\n* `/series` - match a certain label set\n* `/label/{}/values` - query a list of label values (variables mostly)", "fieldConfig": { "defaults": { - "links": [] + "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" + } + }, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "s" }, "overrides": [] }, - "fill": 1, - "fillGradient": 0, "gridPos": { "h": 8, "w": 12, "x": 12, "y": 14 }, - "hiddenSeries": false, - "id": 35, - "legend": { - "alignAsTable": true, - "avg": true, - "current": true, - "max": false, - "min": false, - "show": true, - "sort": "current", - "sortDesc": true, - "total": false, - "values": true - }, - "lines": true, - "linewidth": 1, + "id": 22, "links": [], - "nullPointMode": "null as zero", "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": "$ds" - }, - "exemplar": false, - "expr": "sum(rate(vm_http_request_errors_total{job=~\"$job\", instance=~\"$instance\"}[$__interval])) by (path) > 0", - "format": "time_series", - "interval": "", - "intervalFactor": 1, - "legendFormat": "{{path}}", - "refId": "A" - } - ], - "thresholds": [], - "timeRegions": [], - "title": "Requests error rate ($instance)", - "tooltip": { - "shared": true, - "sort": 2, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "mode": "time", - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "short", - "logBase": 1, - "min": "0", - "show": true + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true }, - { - "format": "short", - "logBase": 1, - "min": "0", - "show": true + "tooltip": { + "mode": "multi", + "sort": "desc" } - ], - "yaxis": { - "align": false - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": { - "type": "prometheus", - "uid": "$ds" }, - "description": "Shows how many ongoing insertions (not API /write calls) on disk are taking place, where:\n* `max` - equal to number of CPUs;\n* `current` - current number of goroutines busy with inserting rows into underlying storage.\n\nEvery successful API /write call results into flush on disk. However, these two actions are separated and controlled via different concurrency limiters. The `max` on this panel can't be changed and always equal to number of CPUs. \n\nWhen `current` hits `max` constantly, it means storage is overloaded and requires more CPU.\n\n", - "fieldConfig": { - "defaults": { - "links": [] - }, - "overrides": [] - }, - "fill": 0, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 0, - "y": 22 - }, - "hiddenSeries": false, - "id": 59, - "legend": { - "alignAsTable": true, - "avg": true, - "current": true, - "hideEmpty": false, - "hideZero": false, - "max": false, - "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": [ - { - "$$hashKey": "object:840", - "alias": "max", - "color": "#C4162A" - } - ], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "expr": "sum(vm_concurrent_addrows_capacity{job=~\"$job\", instance=~\"$instance\"})", - "format": "time_series", - "interval": "", - "intervalFactor": 1, - "legendFormat": "max", - "refId": "A" - }, - { - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "expr": "sum(vm_concurrent_addrows_current{job=~\"$job\", instance=~\"$instance\"})", - "format": "time_series", - "intervalFactor": 1, - "legendFormat": "current", - "refId": "B" - } - ], - "thresholds": [], - "timeRegions": [], - "title": "Concurrent flushes on disk ($instance)", - "tooltip": { - "shared": true, - "sort": 2, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "mode": "time", - "show": true, - "values": [] - }, - "yaxes": [ - { - "$$hashKey": "object:425", - "decimals": 0, - "format": "short", - "logBase": 1, - "min": "0", - "show": true - }, - { - "$$hashKey": "object:426", - "decimals": 0, - "format": "short", - "logBase": 1, - "min": "0", - "show": true - } - ], - "yaxis": { - "align": false - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "description": "99th percentile of number of raw samples read per query.", - "fieldConfig": { - "defaults": { - "links": [] - }, - "overrides": [] - }, - "fill": 0, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 12, - "y": 22 - }, - "hiddenSeries": false, - "id": 101, - "legend": { - "alignAsTable": true, - "avg": true, - "current": true, - "max": true, - "min": false, - "show": true, - "sort": "current", - "sortDesc": true, - "total": false, - "values": true - }, - "lines": true, - "linewidth": 1, - "links": [], - "nullPointMode": "null as zero", - "options": { - "alertThreshold": true - }, - "percentage": false, - "pluginVersion": "9.0.3", - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "expr": "histogram_quantile(0.99, sum(rate(vm_rows_read_per_query_bucket{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (vmrange))", - "format": "time_series", - "interval": "", - "intervalFactor": 1, - "legendFormat": "{{instance}}", - "refId": "A" - } - ], - "thresholds": [], - "timeRegions": [], - "title": "Rows read per query ($instance)", - "tooltip": { - "shared": true, - "sort": 2, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "mode": "time", - "show": true, - "values": [] - }, - "yaxes": [ - { - "$$hashKey": "object:2848", - "decimals": 2, - "format": "short", - "logBase": 1, - "min": "0", - "show": true - }, - { - "$$hashKey": "object:2849", - "format": "short", - "logBase": 1, - "min": "0", - "show": true - } - ], - "yaxis": { - "align": false - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "description": "99th percentile of number of series read per query.", - "fieldConfig": { - "defaults": { - "links": [] - }, - "overrides": [] - }, - "fill": 0, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 0, - "y": 30 - }, - "hiddenSeries": false, - "id": 99, - "legend": { - "alignAsTable": true, - "avg": true, - "current": true, - "max": true, - "min": false, - "show": true, - "sort": "current", - "sortDesc": true, - "total": false, - "values": true - }, - "lines": true, - "linewidth": 1, - "links": [], - "nullPointMode": "null as zero", - "options": { - "alertThreshold": true - }, - "percentage": false, - "pluginVersion": "9.0.3", - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "expr": "histogram_quantile(0.99, sum(rate(vm_series_read_per_query_bucket{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (vmrange))", - "format": "time_series", - "interval": "", - "intervalFactor": 1, - "legendFormat": "{{instance}}", - "refId": "A" - } - ], - "thresholds": [], - "timeRegions": [], - "title": "Series read per query ($instance)", - "tooltip": { - "shared": true, - "sort": 2, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "mode": "time", - "show": true, - "values": [] - }, - "yaxes": [ - { - "$$hashKey": "object:2848", - "decimals": 2, - "format": "short", - "logBase": 1, - "min": "0", - "show": true - }, - { - "$$hashKey": "object:2849", - "format": "short", - "logBase": 1, - "min": "0", - "show": true - } - ], - "yaxis": { - "align": false - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "description": "99th percentile of number of raw samples scanner per query.\n\nThis number can exceed number of RowsReadPerQuery if `step` query arg passed to [/api/v1/query_range](https://prometheus.io/docs/prometheus/latest/querying/api/#range-queries) is smaller than the lookbehind window set in square brackets of [rollup function](https://docs.victoriametrics.com/MetricsQL.html#rollup-functions). For example, if `increase(some_metric[1h])` is executed with the `step=5m`, then the same raw samples on a hour time range are scanned `1h/5m=12` times. See [this article](https://valyala.medium.com/how-to-optimize-promql-and-metricsql-queries-85a1b75bf986) for details.", - "fieldConfig": { - "defaults": { - "links": [] - }, - "overrides": [] - }, - "fill": 0, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 12, - "y": 30 - }, - "hiddenSeries": false, - "id": 105, - "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 as zero", - "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" - }, - "expr": "histogram_quantile(0.99, sum(rate(vm_rows_scanned_per_query_bucket{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (vmrange))", - "format": "time_series", - "interval": "", - "intervalFactor": 1, - "legendFormat": "{{instance}}", - "refId": "A" - } - ], - "thresholds": [], - "timeRegions": [], - "title": "Rows scanned per series ($instance)", - "tooltip": { - "shared": true, - "sort": 2, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "mode": "time", - "show": true, - "values": [] - }, - "yaxes": [ - { - "$$hashKey": "object:2848", - "decimals": 2, - "format": "short", - "logBase": 1, - "min": "0", - "show": true - }, - { - "$$hashKey": "object:2849", - "format": "short", - "logBase": 1, - "min": "0", - "show": true - } - ], - "yaxis": { - "align": false - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "description": "99th percentile of number of raw samples read per queried series.", - "fieldConfig": { - "defaults": { - "links": [] - }, - "overrides": [] - }, - "fill": 0, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 0, - "y": 38 - }, - "hiddenSeries": false, - "id": 103, - "legend": { - "alignAsTable": true, - "avg": true, - "current": true, - "max": true, - "min": false, - "show": true, - "sort": "current", - "sortDesc": true, - "total": false, - "values": true - }, - "lines": true, - "linewidth": 1, - "links": [], - "nullPointMode": "null as zero", - "options": { - "alertThreshold": true - }, - "percentage": false, - "pluginVersion": "9.0.3", - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, + "pluginVersion": "9.1.0", "targets": [ { "datasource": { @@ -1697,1567 +1237,219 @@ "uid": "$ds" }, "editorMode": "code", - "expr": "histogram_quantile(0.99, sum(rate(vm_rows_read_per_series_bucket{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (vmrange))", + "expr": "max(vm_request_duration_seconds{job=~\"$job\", instance=~\"$instance\", quantile=\"0.99\"}) by (path) > 0", "format": "time_series", - "interval": "", "intervalFactor": 1, - "legendFormat": "{{label_name}}", + "legendFormat": "__auto", "range": true, "refId": "A" } ], - "thresholds": [], - "timeRegions": [], - "title": "Rows read per series ($instance)", - "tooltip": { - "shared": true, - "sort": 2, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "mode": "time", - "show": true, - "values": [] - }, - "yaxes": [ - { - "$$hashKey": "object:2848", - "decimals": 2, - "format": "short", - "logBase": 1, - "min": "0", - "show": true - }, - { - "$$hashKey": "object:2849", - "format": "short", - "logBase": 1, - "min": "0", - "show": true - } - ], - "yaxis": { - "align": false - } + "title": "Query duration 0.99 quantile ($instance)", + "type": "timeseries" }, { - "collapsed": true, "datasource": { "type": "prometheus", "uid": "$ds" }, - "gridPos": { - "h": 1, - "w": 24, - "x": 0, - "y": 46 + "description": "* `*` - unsupported query path\n* `/write` - insert into VM\n* `/metrics` - query VM system metrics\n* `/query` - query instant values\n* `/query_range` - query over a range of time\n* `/series` - match a certain label set\n* `/label/{}/values` - query a list of label values (variables mostly)", + "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" + } + }, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] }, - "id": 92, - "panels": [ - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "description": "VictoriaMetrics stores various caches in RAM. Memory size for these caches may be limited with -`memory.allowedPercent` flag. Line `max allowed` shows max allowed memory size for cache.", - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 24, - "x": 0, - "y": 31 - }, - "hiddenSeries": false, - "id": 94, - "legend": { - "alignAsTable": true, - "avg": true, - "current": true, - "max": false, - "min": false, - "rightSide": true, - "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": [ - { - "$$hashKey": "object:85", - "alias": "max allowed", - "color": "#F2495C", - "fill": 0, - "stack": false - } + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 22 + }, + "id": 35, + "links": [], + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull" ], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "exemplar": true, - "expr": "sum(vm_cache_size_bytes{job=~\"$job\", instance=~\"$instance\"}) by(type)", - "interval": "", - "legendFormat": "{{type}}", - "refId": "A" - }, - { - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "exemplar": false, - "expr": "sum(vm_allowed_memory_bytes{job=~\"$job\", instance=~\"$instance\"})", - "hide": false, - "interval": "", - "legendFormat": "max allowed", - "refId": "B" - } - ], - "thresholds": [], - "timeRegions": [], - "title": "Cache size ($instance)", - "tooltip": { - "shared": true, - "sort": 2, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "mode": "time", - "show": true, - "values": [] - }, - "yaxes": [ - { - "$$hashKey": "object:111", - "format": "bytes", - "logBase": 1, - "show": true - }, - { - "$$hashKey": "object:112", - "format": "short", - "logBase": 1, - "show": true - } - ], - "yaxis": { - "align": false - } + "displayMode": "table", + "placement": "bottom", + "showLegend": true }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "description": "Shows the percentage of used cache size from the allowed size by type. \nValues close to 100% show the maximum potential utilization.\nValues close to 0% show that cache is underutilized.", - "fill": 0, - "fillGradient": 0, - "gridPos": { - "h": 7, - "w": 24, - "x": 0, - "y": 39 - }, - "hiddenSeries": false, - "id": 97, - "legend": { - "avg": false, - "current": false, - "max": false, - "min": false, - "show": false, - "total": false, - "values": false - }, - "lines": true, - "linewidth": 1, - "nullPointMode": "null", - "options": { - "alertThreshold": true - }, - "percentage": false, - "pluginVersion": "9.0.3", - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "exemplar": true, - "expr": "vm_cache_size_bytes{job=~\"$job\", instance=~\"$instance\"} / vm_cache_size_max_bytes{job=~\"$job\", instance=~\"$instance\"}", - "interval": "", - "legendFormat": "{{type}}", - "refId": "A" - } - ], - "thresholds": [], - "timeRegions": [], - "title": "Cache usage % ($instance)", - "tooltip": { - "shared": true, - "sort": 2, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "mode": "time", - "show": true, - "values": [] - }, - "yaxes": [ - { - "$$hashKey": "object:235", - "format": "percentunit", - "logBase": 1, - "show": true - }, - { - "$$hashKey": "object:236", - "format": "short", - "logBase": 1, - "show": true - } - ], - "yaxis": { - "align": false - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "description": "Cache hit ratio shows cache efficiency. The higher is hit rate the better.", - "fill": 0, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 24, - "x": 0, - "y": 46 - }, - "hiddenSeries": false, - "id": 95, - "legend": { - "alignAsTable": true, - "avg": true, - "current": true, - "max": false, - "min": false, - "rightSide": true, - "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": [ - { - "$$hashKey": "object:85", - "alias": "max allowed", - "color": "#F2495C", - "fill": 0, - "stack": false - } - ], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "exemplar": true, - "expr": "1 - (\n sum(rate(vm_cache_misses_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (type) /\n sum(rate(vm_cache_requests_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (type)\n)", - "interval": "", - "legendFormat": "{{type}}", - "refId": "A" - } - ], - "thresholds": [], - "timeRegions": [], - "title": "Cache hit ratio ($instance)", - "tooltip": { - "shared": true, - "sort": 2, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "mode": "time", - "show": true, - "values": [] - }, - "yaxes": [ - { - "$$hashKey": "object:111", - "format": "percentunit", - "logBase": 1, - "show": true - }, - { - "$$hashKey": "object:112", - "format": "short", - "logBase": 1, - "show": true - } - ], - "yaxis": { - "align": false - } + "tooltip": { + "mode": "multi", + "sort": "desc" } - ], + }, + "pluginVersion": "9.1.0", "targets": [ { "datasource": { "type": "prometheus", "uid": "$ds" }, + "editorMode": "code", + "exemplar": false, + "expr": "sum(rate(vm_http_request_errors_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (path) > 0", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "legendFormat": "__auto", + "range": true, "refId": "A" } ], - "title": "Caches", - "type": "row" + "title": "Requests error rate ($instance)", + "type": "timeseries" }, { - "collapsed": true, "datasource": { "type": "prometheus", "uid": "$ds" }, - "gridPos": { - "h": 1, - "w": 24, - "x": 0, - "y": 47 + "description": "Shows the rate of logging the messages by their level. Unexpected spike in rate is a good reason to check logs.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "bars", + "fillOpacity": 100, + "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" + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [] }, - "id": 14, - "panels": [ - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "description": "How many datapoints are inserted into storage per second", - "fieldConfig": { - "defaults": { - "links": [] - }, - "overrides": [] - }, - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 0, - "y": 4 - }, - "hiddenSeries": false, - "id": 10, - "legend": { - "alignAsTable": true, - "avg": true, - "current": true, - "hideZero": true, - "max": false, - "min": false, - "show": true, - "sort": "current", - "sortDesc": true, - "total": false, - "values": true - }, - "lines": true, - "linewidth": 1, - "links": [], - "nullPointMode": "null as zero", - "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" - }, - "expr": "sum(rate(vm_rows_inserted_total{job=~\"$job\", instance=~\"$instance\"}[$__interval])) by (type) > 0", - "format": "time_series", - "hide": false, - "intervalFactor": 1, - "legendFormat": "{{type}}", - "refId": "A" - } + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 22 + }, + "id": 110, + "options": { + "legend": { + "calcs": [ + "lastNotNull", + "mean", + "max" ], - "thresholds": [], - "timeRegions": [], - "title": "Datapoints ingestion rate ($instance)", - "tooltip": { - "shared": true, - "sort": 2, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "mode": "time", - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "short", - "logBase": 1, - "min": "0", - "show": true - }, - { - "format": "short", - "logBase": 1, - "min": "0", - "show": true - } - ], - "yaxis": { - "align": false - } + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "description": "Shows the time needed to reach the 100% of disk capacity based on the following params:\n* free disk space;\n* row ingestion rate;\n* dedup rate;\n* compression.\n\nUse this panel for capacity planning in order to estimate the time remaining for running out of the disk space.\n\n", - "fieldConfig": { - "defaults": { - "links": [] - }, - "overrides": [] - }, - "fill": 0, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 12, - "y": 4 - }, - "hiddenSeries": false, - "id": 73, - "legend": { - "alignAsTable": true, - "avg": true, - "current": true, - "hideZero": true, - "max": false, - "min": true, - "show": true, - "sort": "current", - "sortDesc": true, - "total": false, - "values": true - }, - "lines": true, - "linewidth": 1, - "links": [], - "nullPointMode": "null as zero", - "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" - }, - "expr": "vm_free_disk_space_bytes{job=~\"$job\", instance=~\"$instance\"} / ignoring(path) ((rate(vm_rows_added_to_storage_total{job=~\"$job\", instance=~\"$instance\"}[1d]) - ignoring(type) rate(vm_deduplicated_samples_total{job=~\"$job\", instance=~\"$instance\", type=\"merge\"}[1d])) * scalar(sum(vm_data_size_bytes{job=~\"$job\", instance=~\"$instance\", type!=\"indexdb\"}) / sum(vm_rows{job=~\"$job\", instance=~\"$instance\", type!=\"indexdb\"})))", - "format": "time_series", - "hide": false, - "interval": "", - "intervalFactor": 1, - "legendFormat": "", - "refId": "A" - } - ], - "thresholds": [], - "timeRegions": [], - "title": "Storage full ETA ($instance)", - "tooltip": { - "shared": true, - "sort": 2, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "mode": "time", - "show": true, - "values": [] - }, - "yaxes": [ - { - "$$hashKey": "object:919", - "format": "s", - "logBase": 1, - "min": "0", - "show": true - }, - { - "$$hashKey": "object:920", - "format": "short", - "logBase": 1, - "min": "0", - "show": true - } - ], - "yaxis": { - "align": false - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "description": "Shows how many datapoints are in the storage and what is average disk usage per datapoint.", - "fieldConfig": { - "defaults": { - "links": [] - }, - "overrides": [] - }, - "fill": 0, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 0, - "y": 12 - }, - "hiddenSeries": false, - "id": 30, - "legend": { - "alignAsTable": true, - "avg": true, - "current": true, - "max": true, - "min": false, - "show": true, - "sort": "current", - "sortDesc": true, - "total": false, - "values": true - }, - "lines": true, - "linewidth": 1, - "links": [], - "nullPointMode": "null", - "options": { - "alertThreshold": true - }, - "percentage": false, - "pluginVersion": "9.0.3", - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [ - { - "$$hashKey": "object:997", - "alias": "bytes-per-datapoint", - "yaxis": 2 - } - ], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "expr": "sum(vm_rows{job=~\"$job\", instance=~\"$instance\", type != \"indexdb\"})", - "format": "time_series", - "interval": "", - "intervalFactor": 1, - "legendFormat": "total datapoints", - "refId": "A" - }, - { - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "expr": "sum(vm_data_size_bytes{job=~\"$job\", instance=~\"$instance\", type!=\"indexdb\"}) / sum(vm_rows{job=~\"$job\", instance=~\"$instance\", type != \"indexdb\"})", - "format": "time_series", - "interval": "", - "intervalFactor": 1, - "legendFormat": "bytes-per-datapoint", - "refId": "B" - } - ], - "thresholds": [], - "timeRegions": [], - "title": "Datapoints ($instance)", - "tooltip": { - "shared": true, - "sort": 2, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "mode": "time", - "show": true, - "values": [] - }, - "yaxes": [ - { - "$$hashKey": "object:1004", - "format": "short", - "logBase": 1, - "min": "0", - "show": true - }, - { - "$$hashKey": "object:1005", - "decimals": 2, - "format": "bytes", - "logBase": 1, - "min": "0", - "show": true - } - ], - "yaxis": { - "align": false - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "description": "How many datapoints are in RAM queue waiting to be written into storage. The number of pending data points should be in the range from 0 to `2*`, since VictoriaMetrics pushes pending data to persistent storage every second.", - "fieldConfig": { - "defaults": { - "links": [] - }, - "overrides": [] - }, - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 12, - "y": 12 - }, - "hiddenSeries": false, - "id": 34, - "legend": { - "alignAsTable": true, - "avg": true, - "current": true, - "max": true, - "min": false, - "show": true, - "sort": "current", - "sortDesc": true, - "total": false, - "values": true - }, - "lines": true, - "linewidth": 1, - "links": [], - "nullPointMode": "null", - "options": { - "alertThreshold": true - }, - "percentage": false, - "pluginVersion": "9.0.3", - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [ - { - "alias": "pending index entries", - "yaxis": 2 - } - ], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "expr": "vm_pending_rows{job=~\"$job\", instance=~\"$instance\", type=\"storage\"}", - "format": "time_series", - "hide": false, - "intervalFactor": 1, - "legendFormat": "pending datapoints", - "refId": "A" - }, - { - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "expr": "vm_pending_rows{job=~\"$job\", instance=~\"$instance\", type=\"indexdb\"}", - "format": "time_series", - "hide": false, - "intervalFactor": 1, - "legendFormat": "pending index entries", - "refId": "B" - } - ], - "thresholds": [], - "timeRegions": [], - "title": "Pending datapoints ($instance)", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "mode": "time", - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "short", - "logBase": 1, - "min": "0", - "show": true - }, - { - "decimals": 3, - "format": "none", - "logBase": 1, - "min": "0", - "show": true - } - ], - "yaxis": { - "align": false - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "description": "Shows amount of on-disk space occupied by data points and the remaining disk space at `-storageDataPath`", - "fieldConfig": { - "defaults": { - "links": [] - }, - "overrides": [] - }, - "fill": 0, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 0, - "y": 20 - }, - "hiddenSeries": false, - "id": 53, - "legend": { - "alignAsTable": true, - "avg": true, - "current": true, - "max": true, - "min": false, - "rightSide": false, - "show": true, - "sort": "current", - "sortDesc": true, - "total": false, - "values": true - }, - "lines": true, - "linewidth": 1, - "links": [], - "nullPointMode": "null", - "options": { - "alertThreshold": true - }, - "percentage": false, - "pluginVersion": "9.0.3", - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "expr": "sum(vm_data_size_bytes{job=~\"$job\", instance=~\"$instance\", type!=\"indexdb\"})", - "format": "time_series", - "interval": "", - "intervalFactor": 1, - "legendFormat": "Used", - "refId": "A" - }, - { - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "expr": "vm_free_disk_space_bytes{job=~\"$job\", instance=~\"$instance\"}", - "format": "time_series", - "interval": "", - "intervalFactor": 1, - "legendFormat": "Free", - "refId": "B" - } - ], - "thresholds": [], - "timeRegions": [], - "title": "Disk space usage - datapoints ($instance)", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "mode": "time", - "show": true, - "values": [] - }, - "yaxes": [ - { - "$$hashKey": "object:1136", - "format": "bytes", - "logBase": 1, - "min": "0", - "show": true - }, - { - "$$hashKey": "object:1137", - "format": "short", - "logBase": 1, - "min": "0", - "show": true - } - ], - "yaxis": { - "align": false - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "description": "Data parts of LSM tree.\nHigh number of parts could be an evidence of slow merge performance - check the resource utilization.\n* `indexdb` - inverted index\n* `storage/small` - recently added parts of data ingested into storage(hot data)\n* `storage/big` - small parts gradually merged into big parts (cold data)", - "fieldConfig": { - "defaults": { - "links": [] - }, - "overrides": [] - }, - "fill": 0, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 12, - "y": 20 - }, - "hiddenSeries": false, - "id": 36, - "legend": { - "alignAsTable": true, - "avg": true, - "current": true, - "max": true, - "min": false, - "show": true, - "sort": "current", - "sortDesc": true, - "total": false, - "values": true - }, - "lines": true, - "linewidth": 1, - "links": [], - "nullPointMode": "null", - "options": { - "alertThreshold": true - }, - "percentage": false, - "pluginVersion": "9.0.3", - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "expr": "sum(vm_parts{job=~\"$job\", instance=~\"$instance\"}) by (type)", - "format": "time_series", - "intervalFactor": 1, - "legendFormat": "{{type}}", - "refId": "A" - } - ], - "thresholds": [], - "timeRegions": [], - "title": "LSM parts ($instance)", - "tooltip": { - "shared": true, - "sort": 2, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "mode": "time", - "show": true, - "values": [] - }, - "yaxes": [ - { - "$$hashKey": "object:1066", - "format": "short", - "logBase": 1, - "min": "0", - "show": true - }, - { - "$$hashKey": "object:1067", - "format": "short", - "logBase": 1, - "min": "0", - "show": true - } - ], - "yaxis": { - "align": false - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "description": "Shows amount of on-disk space occupied by inverted index.", - "fieldConfig": { - "defaults": { - "links": [] - }, - "overrides": [] - }, - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 0, - "y": 28 - }, - "hiddenSeries": false, - "id": 55, - "legend": { - "alignAsTable": true, - "avg": true, - "current": true, - "max": true, - "min": false, - "show": true, - "sort": "current", - "sortDesc": true, - "total": false, - "values": true - }, - "lines": true, - "linewidth": 1, - "links": [], - "nullPointMode": "null", - "options": { - "alertThreshold": true - }, - "percentage": false, - "pluginVersion": "9.0.3", - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "exemplar": true, - "expr": "vm_data_size_bytes{job=~\"$job\", instance=~\"$instance\", type=\"indexdb\"}", - "format": "time_series", - "interval": "", - "intervalFactor": 1, - "legendFormat": "disk space used", - "refId": "A" - } - ], - "thresholds": [], - "timeRegions": [], - "title": "Disk space usage - index ($instance)", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "mode": "time", - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "bytes", - "logBase": 1, - "min": "0", - "show": true - }, - { - "format": "short", - "logBase": 1, - "min": "0", - "show": true - } - ], - "yaxis": { - "align": false - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "description": "The number of on-going merges in storage nodes. It is expected to have high numbers for `storage/small` metric.", - "fieldConfig": { - "defaults": { - "links": [] - }, - "overrides": [] - }, - "fill": 0, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 12, - "y": 28 - }, - "hiddenSeries": false, - "id": 62, - "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": "$ds" - }, - "expr": "sum(vm_active_merges{job=~\"$job\", instance=~\"$instance\"}) by(type)", - "legendFormat": "{{type}}", - "refId": "A" - } - ], - "thresholds": [], - "timeRegions": [], - "title": "Active merges ($instance)", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "mode": "time", - "show": true, - "values": [] - }, - "yaxes": [ - { - "$$hashKey": "object:1262", - "decimals": 0, - "format": "short", - "logBase": 1, - "min": "0", - "show": true - }, - { - "$$hashKey": "object:1263", - "format": "short", - "logBase": 1, - "min": "0", - "show": true - } - ], - "yaxis": { - "align": false - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "description": "Shows how many rows were ignored on insertion due to corrupted or out of retention timestamps.", - "fieldConfig": { - "defaults": { - "links": [] - }, - "overrides": [] - }, - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 0, - "y": 36 - }, - "hiddenSeries": false, - "id": 58, - "legend": { - "alignAsTable": true, - "avg": true, - "current": true, - "max": true, - "min": false, - "show": true, - "sort": "current", - "sortDesc": true, - "total": false, - "values": true - }, - "lines": true, - "linewidth": 1, - "links": [], - "nullPointMode": "null", - "options": { - "alertThreshold": true - }, - "percentage": false, - "pluginVersion": "9.0.3", - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "exemplar": true, - "expr": "sum(vm_rows_ignored_total{job=~\"$job\", instance=~\"$instance\"}) by (reason)", - "format": "time_series", - "hide": false, - "interval": "", - "intervalFactor": 1, - "legendFormat": "{{reason}}", - "refId": "A" - } - ], - "thresholds": [], - "timeRegions": [], - "title": "Rows ignored ($instance)", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "mode": "time", - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "short", - "logBase": 1, - "min": "0", - "show": true - }, - { - "format": "short", - "logBase": 1, - "min": "0", - "show": true - } - ], - "yaxis": { - "align": false - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "description": "The number of rows merged per second by storage nodes.", - "fieldConfig": { - "defaults": { - "links": [] - }, - "overrides": [] - }, - "fill": 0, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 12, - "y": 36 - }, - "hiddenSeries": false, - "id": 64, - "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": "$ds" - }, - "expr": "sum(rate(vm_rows_merged_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by(type)", - "legendFormat": "{{type}}", - "refId": "A" - } - ], - "thresholds": [], - "timeRegions": [], - "title": "Merge speed ($instance)", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "mode": "time", - "show": true, - "values": [] - }, - "yaxes": [ - { - "$$hashKey": "object:867", - "decimals": 0, - "format": "short", - "logBase": 1, - "min": "0", - "show": true - }, - { - "$$hashKey": "object:868", - "format": "short", - "logBase": 1, - "min": "0", - "show": true - } - ], - "yaxis": { - "align": false - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "description": "Shows the rate of logging the messages by their level. Unexpected spike in rate is a good reason to check logs.", - "fieldConfig": { - "defaults": { - "links": [] - }, - "overrides": [] - }, - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 12, - "y": 44 - }, - "hiddenSeries": false, - "id": 67, - "legend": { - "alignAsTable": true, - "avg": true, - "current": true, - "max": true, - "min": false, - "show": true, - "sort": "current", - "sortDesc": true, - "total": false, - "values": true - }, - "lines": true, - "linewidth": 1, - "links": [], - "nullPointMode": "null", - "options": { - "alertThreshold": true - }, - "percentage": false, - "pluginVersion": "9.0.3", - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "expr": "sum(rate(vm_log_messages_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (level) ", - "format": "time_series", - "hide": false, - "intervalFactor": 1, - "legendFormat": "{{level}}", - "refId": "A" - } - ], - "thresholds": [], - "timeRegions": [], - "title": "Logging rate ($instance)", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "mode": "time", - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "short", - "logBase": 1, - "min": "0", - "show": true - }, - { - "format": "short", - "logBase": 1, - "min": "0", - "show": true - } - ], - "yaxis": { - "align": false - } + "tooltip": { + "mode": "single", + "sort": "none" } - ], + }, "targets": [ { "datasource": { "type": "prometheus", "uid": "$ds" }, + "editorMode": "code", + "expr": "sum(rate(vm_log_messages_total{job=~\"$job\",instance=~\"$instance\", level!=\"info\"}[$__rate_interval])) by (job, level) > 0", + "interval": "5m", + "legendFormat": "{{job}} - {{level}}", + "range": true, "refId": "A" } ], - "title": "Storage", - "type": "row" + "title": "Logging rate", + "type": "timeseries" }, { "collapsed": true, @@ -3269,656 +1461,234 @@ "h": 1, "w": 24, "x": 0, - "y": 48 - }, - "id": 71, - "panels": [ - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "description": "Shows the rate and total number of new series created over last 24h.\n\nHigh churn rate tightly connected with database performance and may result in unexpected OOM's or slow queries. It is recommended to always keep an eye on this metric to avoid unexpected cardinality \"explosions\".\n\nThe higher churn rate is, the more resources required to handle it. Consider to keep the churn rate as low as possible.\n\nGood references to read:\n* https://www.robustperception.io/cardinality-is-key\n* https://www.robustperception.io/using-tsdb-analyze-to-investigate-churn-and-cardinality", - "fieldConfig": { - "defaults": { - "links": [] - }, - "overrides": [] - }, - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 0, - "y": 5 - }, - "hiddenSeries": false, - "id": 66, - "legend": { - "alignAsTable": true, - "avg": true, - "current": true, - "max": true, - "min": false, - "show": true, - "sort": "current", - "sortDesc": true, - "total": false, - "values": true - }, - "lines": true, - "linewidth": 1, - "nullPointMode": "null", - "options": { - "alertThreshold": true - }, - "percentage": false, - "pluginVersion": "9.0.3", - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [ - { - "alias": "new series over 24h", - "yaxis": 2 - } - ], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "expr": "sum(rate(vm_new_timeseries_created_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))", - "interval": "", - "legendFormat": "churn rate", - "refId": "A" - }, - { - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "expr": "sum(increase(vm_new_timeseries_created_total{job=~\"$job\", instance=~\"$instance\"}[24h]))", - "interval": "", - "legendFormat": "new series over 24h", - "refId": "B" - } - ], - "thresholds": [], - "timeRegions": [], - "title": "Churn rate ($instance)", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "mode": "time", - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "short", - "logBase": 1, - "min": "0", - "show": true - }, - { - "format": "short", - "logBase": 1, - "min": "0", - "show": true - } - ], - "yaxis": { - "align": false - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "description": "Shows the rate of adding new items to the index. It should correlate with `Slow inserts` and `Churn rate` graphs and could help to determine the pressure on indexdb.", - "fieldConfig": { - "defaults": { - "links": [] - }, - "overrides": [] - }, - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 12, - "y": 5 - }, - "hiddenSeries": false, - "id": 96, - "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": "$ds" - }, - "exemplar": true, - "expr": "sum(rate(vm_indexdb_items_added_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))", - "interval": "", - "legendFormat": "items", - "refId": "A" - } - ], - "thresholds": [], - "timeRegions": [], - "title": "IndexDB items rate ($instance)", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "mode": "time", - "show": true, - "values": [] - }, - "yaxes": [ - { - "$$hashKey": "object:76", - "format": "short", - "logBase": 1, - "min": "0", - "show": true - }, - { - "$$hashKey": "object:77", - "format": "short", - "logBase": 1, - "min": "0", - "show": true - } - ], - "yaxis": { - "align": false - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "description": "The percentage of slow inserts comparing to total insertion rate during the last 5 minutes. \n\nThe less value is better. If percentage remains high (>10%) during extended periods of time, then it is likely more RAM is needed for optimal handling of the current number of active time series. \n\nIn general, VictoriaMetrics requires ~1KB or RAM per active time series, so it should be easy calculating the required amounts of RAM for the current workload according to capacity planning docs. But the resulting number may be far from the real number because the required amounts of memory depends on may other factors such as the number of labels per time series and the length of label values.", - "fieldConfig": { - "defaults": { - "links": [] - }, - "overrides": [] - }, - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 0, - "y": 13 - }, - "hiddenSeries": false, - "id": 68, - "legend": { - "alignAsTable": true, - "avg": true, - "current": true, - "max": true, - "min": false, - "show": true, - "sort": "current", - "sortDesc": true, - "total": false, - "values": true - }, - "lines": true, - "linewidth": 1, - "links": [], - "nullPointMode": "null", - "options": { - "alertThreshold": true - }, - "percentage": false, - "pluginVersion": "9.0.3", - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "expr": "sum(rate(vm_slow_row_inserts_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) / sum(rate(vm_rows_inserted_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))", - "format": "time_series", - "hide": false, - "interval": "", - "intervalFactor": 1, - "legendFormat": "slow inserts percentage", - "refId": "A" - } - ], - "thresholds": [ - { - "$$hashKey": "object:60", - "colorMode": "critical", - "fill": true, - "line": true, - "op": "gt", - "value": 0.1, - "yaxis": "left" - } - ], - "timeRegions": [], - "title": "Slow inserts ($instance)", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "mode": "time", - "show": true, - "values": [] - }, - "yaxes": [ - { - "decimals": 2, - "format": "percentunit", - "logBase": 1, - "min": "0", - "show": true - }, - { - "format": "short", - "logBase": 1, - "min": "0", - "show": true - } - ], - "yaxis": { - "align": false - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "description": "Slow queries rate according to `search.logSlowQueryDuration` flag, which is `5s` by default.", - "fieldConfig": { - "defaults": { - "links": [] - }, - "overrides": [] - }, - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 12, - "y": 13 - }, - "hiddenSeries": false, - "id": 60, - "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": { - "type": "prometheus", - "uid": "$ds" - }, - "expr": "sum(rate(vm_slow_queries_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))", - "format": "time_series", - "hide": false, - "intervalFactor": 1, - "legendFormat": "slow queries rate", - "refId": "A" - } - ], - "thresholds": [], - "timeRegions": [], - "title": "Slow queries rate ($instance)", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "mode": "time", - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "short", - "logBase": 1, - "min": "0", - "show": true - }, - { - "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 percentage of used cache size from the allowed size by type. \nValues close to 100% show the maximum potential utilization.\nValues close to 0% show that cache is underutilized.", - "fill": 0, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 0, - "y": 21 - }, - "hiddenSeries": false, - "id": 90, - "legend": { - "avg": false, - "current": false, - "max": false, - "min": false, - "show": false, - "total": false, - "values": false - }, - "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": true, - "expr": "vm_cache_size_bytes{job=~\"$job\", instance=~\"$instance\"} / vm_cache_size_max_bytes{job=~\"$job\", instance=~\"$instance\"}", - "interval": "", - "legendFormat": "{{type}}", - "refId": "A" - } - ], - "thresholds": [], - "timeRegions": [], - "title": "Cache usage % ($instance)", - "tooltip": { - "shared": true, - "sort": 2, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "mode": "time", - "show": true, - "values": [] - }, - "yaxes": [ - { - "$$hashKey": "object:235", - "format": "percentunit", - "logBase": 1, - "show": true - }, - { - "$$hashKey": "object:236", - "format": "short", - "logBase": 1, - "show": true - } - ], - "yaxis": { - "align": false - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "description": "VictoriaMetrics limits the number of labels per each metric with `-maxLabelsPerTimeseries` command-line flag.\n\nThis prevents from ingesting metrics with too many labels. The value of `maxLabelsPerTimeseries` must be adjusted for your workload.\n\nWhen limit is exceeded (graph is > 0) - extra labels are dropped, which could result in unexpected identical time series.", - "fieldConfig": { - "defaults": { - "links": [] - }, - "overrides": [] - }, - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 12, - "y": 21 - }, - "hiddenSeries": false, - "id": 74, - "legend": { - "alignAsTable": true, - "avg": true, - "current": true, - "max": true, - "min": false, - "show": false, - "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": { - "type": "prometheus", - "uid": "$ds" - }, - "exemplar": true, - "expr": "sum(increase(vm_metrics_with_dropped_labels_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))", - "format": "time_series", - "hide": false, - "interval": "", - "intervalFactor": 1, - "legendFormat": "limit exceeded", - "refId": "A" - } - ], - "thresholds": [], - "timeRegions": [], - "title": "Labels limit exceeded ($instance)", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "mode": "time", - "show": true, - "values": [] - }, - "yaxes": [ - { - "decimals": 2, - "format": "short", - "logBase": 1, - "min": "0", - "show": true - }, - { - "format": "short", - "logBase": 1, - "min": "0", - "show": true - } - ], - "yaxis": { - "align": false - } - } - ], - "targets": [ - { - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "refId": "A" - } - ], - "title": "Troubleshooting", - "type": "row" - }, - { - "collapsed": true, - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "gridPos": { - "h": 1, - "w": 24, - "x": 0, - "y": 49 + "y": 30 }, "id": 46, "panels": [ { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Percentage of used memory (resident).\nThe application's performance will significantly degrade when memory usage is close to 100%.", + "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": [ + { + "targetBlank": true, + "title": "Drilldown", + "url": "/d/oS7Bi_0Wz?viewPanel=189&var-job=${__field.labels.job}&var-ds=$ds&var-instance=$instance&${__url_time_range}" + } + ], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "percentunit" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 31 + }, + "id": 112, + "links": [], + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "9.1.0", + "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": "RSS memory % 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" + } + }, + "links": [ + { + "targetBlank": true, + "title": "Drilldown", + "url": "/d/oS7Bi_0Wz?viewPanel=192&var-job=${__field.labels.job}&var-ds=$ds&var-instance=$instance&${__url_time_range}" + } + ], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "percentunit" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 31 + }, + "id": 114, + "links": [], + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "9.1.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "exemplar": false, + "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": "", + "intervalFactor": 1, + "legendFormat": "__auto", + "range": true, + "refId": "A" + } + ], + "title": "CPU % usage ($instance)", + "type": "timeseries" + }, + { "datasource": { "type": "prometheus", "uid": "$ds" @@ -3926,48 +1696,85 @@ "description": "", "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": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "bytes" }, "overrides": [] }, - "fill": 0, - "fillGradient": 0, "gridPos": { "h": 8, "w": 12, "x": 0, - "y": 50 + "y": 39 }, - "hiddenSeries": false, "id": 44, - "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 + "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": "9.1.0", "targets": [ { "datasource": { @@ -4023,7 +1830,7 @@ "type": "prometheus", "uid": "$ds" }, - "exemplar": true, + "exemplar": false, "expr": "sum(process_resident_memory_anon_bytes{job=~\"$job\", instance=~\"$instance\"})", "format": "time_series", "hide": false, @@ -4033,45 +1840,10 @@ "refId": "E" } ], - "thresholds": [], - "timeRegions": [], "title": "Memory usage ($instance)", - "tooltip": { - "shared": true, - "sort": 2, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "mode": "time", - "show": true, - "values": [] - }, - "yaxes": [ - { - "$$hashKey": "object:1432", - "format": "bytes", - "logBase": 1, - "min": "0", - "show": true - }, - { - "$$hashKey": "object:1433", - "format": "short", - "logBase": 1, - "min": "0", - "show": true - } - ], - "yaxis": { - "align": false - } + "type": "timeseries" }, { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, "datasource": { "type": "prometheus", "uid": "$ds" @@ -4079,54 +1851,101 @@ "description": "", "fieldConfig": { "defaults": { - "links": [] + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" }, - "overrides": [] + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "Limit" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#F2495C", + "mode": "fixed" + } + } + ] + } + ] }, - "fill": 0, - "fillGradient": 0, "gridPos": { "h": 8, "w": 12, "x": 12, - "y": 50 + "y": 39 }, - "hiddenSeries": false, "id": 57, - "legend": { - "alignAsTable": true, - "avg": true, - "current": true, - "max": true, - "min": false, - "show": true, - "sort": "current", - "sortDesc": true, - "total": false, - "values": true - }, - "lines": true, - "linewidth": 1, "links": [], - "nullPointMode": "null", "options": { - "alertThreshold": true - }, - "percentage": false, - "pluginVersion": "9.0.3", - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [ - { - "$$hashKey": "object:85", - "alias": "Limit", - "color": "#F2495C" + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" } - ], - "spaceLength": 10, - "stack": false, - "steppedLine": false, + }, + "pluginVersion": "9.1.0", "targets": [ { "datasource": { @@ -4155,166 +1974,134 @@ "refId": "B" } ], - "thresholds": [], - "timeRegions": [], "title": "CPU ($instance)", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "mode": "time", - "show": true, - "values": [] - }, - "yaxes": [ - { - "$$hashKey": "object:1370", - "format": "short", - "logBase": 1, - "min": "0", - "show": true - }, - { - "$$hashKey": "object:1371", - "format": "short", - "logBase": 1, - "min": "0", - "show": true - } - ], - "yaxis": { - "align": false - } + "type": "timeseries" }, { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, "datasource": { "type": "prometheus", "uid": "$ds" }, - "description": "Panel shows the number 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", + "description": "Shows the percentage of open file descriptors compared to the limit set 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": [] + "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": 2, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "percentunit" }, - "overrides": [] + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "max" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#C4162A", + "mode": "fixed" + } + } + ] + } + ] }, - "fill": 0, - "fillGradient": 0, "gridPos": { "h": 8, "w": 12, "x": 0, - "y": 58 + "y": 47 }, - "hiddenSeries": false, "id": 75, - "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": [ - { - "$$hashKey": "object:1514", - "alias": "max", - "color": "#C4162A" + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "none" } - ], - "spaceLength": 10, - "stack": false, - "steppedLine": false, + }, + "pluginVersion": "9.1.0", "targets": [ { "datasource": { "type": "prometheus", "uid": "$ds" }, - "expr": "sum(process_open_fds{job=~\"$job\", instance=~\"$instance\"})", + "editorMode": "code", + "expr": "max_over_time(process_open_fds{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])\n/\nprocess_max_fds{job=~\"$job\", instance=~\"$instance\"}", "format": "time_series", + "hide": false, "interval": "", "intervalFactor": 2, - "legendFormat": "open", + "legendFormat": "{{job}}", + "range": true, "refId": "A" - }, - { - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "expr": "min(process_max_fds{job=~\"$job\", instance=~\"$instance\"})", - "format": "time_series", - "interval": "", - "intervalFactor": 2, - "legendFormat": "max", - "refId": "B" } ], - "thresholds": [], - "timeRegions": [], "title": "Open FDs ($instance)", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "mode": "time", - "show": true, - "values": [] - }, - "yaxes": [ - { - "$$hashKey": "object:1521", - "decimals": 0, - "format": "short", - "logBase": 2, - "min": "0", - "show": true - }, - { - "$$hashKey": "object:1522", - "format": "short", - "logBase": 1, - "min": "0", - "show": true - } - ], - "yaxis": { - "align": false - } + "type": "timeseries" }, { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, "datasource": { "type": "prometheus", "uid": "$ds" @@ -4322,53 +2109,97 @@ "description": "Shows the number of bytes read/write from the storage layer.", "fieldConfig": { "defaults": { - "links": [] + "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" + } + }, + "links": [], + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "bytes" }, - "overrides": [] + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "read" + }, + "properties": [ + { + "id": "custom.transform", + "value": "negative-Y" + } + ] + } + ] }, - "fill": 1, - "fillGradient": 0, "gridPos": { "h": 8, "w": 12, "x": 12, - "y": 58 + "y": 47 }, - "hiddenSeries": false, "id": 76, - "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": [ - { - "alias": "read", - "transform": "negative-Y" + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "none" } - ], - "spaceLength": 10, - "stack": false, - "steppedLine": false, + }, + "pluginVersion": "9.1.0", "targets": [ { "datasource": { @@ -4397,90 +2228,96 @@ "refId": "B" } ], - "thresholds": [], - "timeRegions": [], "title": "Disk writes/reads ($instance)", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "mode": "time", - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "bytes", - "logBase": 1, - "show": true - }, - { - "format": "short", - "logBase": 1, - "min": "0", - "show": true - } - ], - "yaxis": { - "align": false - } + "type": "timeseries" }, { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, "datasource": { "type": "prometheus", "uid": "$ds" }, "fieldConfig": { "defaults": { - "links": [] + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "decimals": 0, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" }, "overrides": [] }, - "fill": 1, - "fillGradient": 0, "gridPos": { "h": 8, "w": 12, "x": 0, - "y": 66 + "y": 55 }, - "hiddenSeries": false, "id": 47, - "legend": { - "alignAsTable": true, - "avg": true, - "current": true, - "max": true, - "min": false, - "show": true, - "sort": "current", - "sortDesc": true, - "total": false, - "values": true - }, - "lines": true, - "linewidth": 1, "links": [], - "nullPointMode": "null", "options": { - "alertThreshold": true + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "none" + } }, - "percentage": false, - "pluginVersion": "9.0.3", - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, + "pluginVersion": "9.1.0", "targets": [ { "datasource": { @@ -4494,242 +2331,10 @@ "refId": "A" } ], - "thresholds": [], - "timeRegions": [], "title": "Goroutines ($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, - "min": "0", - "show": true - } - ], - "yaxis": { - "align": false - } + "type": "timeseries" }, { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "description": "Shows avg GC duration", - "fieldConfig": { - "defaults": { - "links": [] - }, - "overrides": [] - }, - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 12, - "y": 66 - }, - "hiddenSeries": false, - "id": 42, - "legend": { - "alignAsTable": true, - "avg": true, - "current": true, - "max": true, - "min": false, - "show": true, - "sort": "current", - "sortDesc": true, - "total": false, - "values": true - }, - "lines": true, - "linewidth": 1, - "links": [], - "nullPointMode": "null", - "options": { - "alertThreshold": true - }, - "percentage": false, - "pluginVersion": "9.0.3", - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, - "targets": [ - { - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "expr": "sum(rate(go_gc_duration_seconds_sum{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))\n/\nsum(rate(go_gc_duration_seconds_count{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))", - "format": "time_series", - "intervalFactor": 2, - "legendFormat": "avg gc duration", - "refId": "A" - } - ], - "thresholds": [], - "timeRegions": [], - "title": "GC duration ($instance)", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "mode": "time", - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "s", - "logBase": 1, - "min": "0", - "show": true - }, - { - "format": "short", - "logBase": 1, - "min": "0", - "show": true - } - ], - "yaxis": { - "align": false - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "fieldConfig": { - "defaults": { - "links": [] - }, - "overrides": [] - }, - "fill": 1, - "fillGradient": 0, - "gridPos": { - "h": 8, - "w": 12, - "x": 0, - "y": 74 - }, - "hiddenSeries": false, - "id": 48, - "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": { - "type": "prometheus", - "uid": "$ds" - }, - "expr": "sum(process_num_threads{job=~\"$job\", instance=~\"$instance\"})", - "format": "time_series", - "intervalFactor": 2, - "legendFormat": "threads", - "refId": "A" - } - ], - "thresholds": [], - "timeRegions": [], - "title": "Threads ($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, - "min": "0", - "show": true - } - ], - "yaxis": { - "align": false - } - }, - { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, "datasource": { "type": "prometheus", "uid": "$ds" @@ -4737,48 +2342,85 @@ "description": "", "fieldConfig": { "defaults": { - "links": [] + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" }, "overrides": [] }, - "fill": 1, - "fillGradient": 0, "gridPos": { "h": 8, "w": 12, "x": 12, - "y": 74 + "y": 55 }, - "hiddenSeries": false, "id": 37, - "legend": { - "alignAsTable": true, - "avg": true, - "current": true, - "max": true, - "min": false, - "show": true, - "sort": "current", - "sortDesc": true, - "total": false, - "values": true - }, - "lines": true, - "linewidth": 1, "links": [], - "nullPointMode": "null", "options": { - "alertThreshold": true + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "none" + } }, - "percentage": false, - "pluginVersion": "9.0.3", - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, + "pluginVersion": "9.1.0", "targets": [ { "datasource": { @@ -4793,43 +2435,113 @@ "refId": "A" } ], - "thresholds": [], - "timeRegions": [], "title": "TCP connections ($instance)", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "mode": "time", - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "short", - "logBase": 1, - "min": "0", - "show": true - }, - { - "format": "short", - "logBase": 1, - "min": "0", - "show": true - } - ], - "yaxis": { - "align": false - } + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "decimals": 0, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 63 + }, + "id": 48, + "links": [], + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "9.1.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "expr": "sum(process_num_threads{job=~\"$job\", instance=~\"$instance\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "threads", + "refId": "A" + } + ], + "title": "Threads ($instance)", + "type": "timeseries" }, { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, "datasource": { "type": "prometheus", "uid": "$ds" @@ -4837,93 +2549,103 @@ "description": "", "fieldConfig": { "defaults": { - "links": [] + "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" + } + }, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" }, "overrides": [] }, - "fill": 1, - "fillGradient": 0, "gridPos": { "h": 8, "w": 12, "x": 12, - "y": 82 + "y": 63 }, - "hiddenSeries": false, "id": 49, - "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 + "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": "9.1.0", "targets": [ { "datasource": { "type": "prometheus", "uid": "$ds" }, - "expr": "sum(rate(vm_tcplistener_accepts_total{job=~\"$job\", instance=~\"$instance\"}[$__interval]))", + "editorMode": "code", + "expr": "sum(rate(vm_tcplistener_accepts_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))", "format": "time_series", "hide": false, "intervalFactor": 1, "legendFormat": "connections", + "range": true, "refId": "A" } ], - "thresholds": [], - "timeRegions": [], "title": "TCP connections rate ($instance)", - "tooltip": { - "shared": true, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "mode": "time", - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "short", - "logBase": 1, - "min": "0", - "show": true - }, - { - "format": "short", - "logBase": 1, - "min": "0", - "show": true - } - ], - "yaxis": { - "align": false - } + "type": "timeseries" } ], "targets": [ @@ -4937,10 +2659,2507 @@ ], "title": "Resource usage", "type": "row" + }, + { + "collapsed": true, + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 31 + }, + "id": 71, + "panels": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows the rate and total number of new series created over last 24h.\n\nHigh churn rate tightly connected with database performance and may result in unexpected OOM's or slow queries. It is recommended to always keep an eye on this metric to avoid unexpected cardinality \"explosions\".\n\nThe higher churn rate is, the more resources required to handle it. Consider to keep the churn rate as low as possible.\n\nGood references to read:\n* https://www.robustperception.io/cardinality-is-key\n* https://www.robustperception.io/using-tsdb-analyze-to-investigate-churn-and-cardinality", + "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" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 8 + }, + "id": 66, + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "9.1.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "expr": "sum(rate(vm_new_timeseries_created_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))", + "interval": "", + "legendFormat": "churn rate", + "refId": "A" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "expr": "sum(increase(vm_new_timeseries_created_total{job=~\"$job\", instance=~\"$instance\"}[24h]))", + "interval": "", + "legendFormat": "new series over 24h", + "refId": "B" + } + ], + "title": "Churn rate ($instance)", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "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 (>10%) 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.", + "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": "line+area" + } + }, + "decimals": 2, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "transparent" + }, + { + "color": "red", + "value": 0.1 + } + ] + }, + "unit": "percentunit" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 8 + }, + "id": 68, + "links": [], + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "9.1.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "max(\n rate(vm_slow_row_inserts_total{job=~\"$job\"}[$__rate_interval]) \n / rate(vm_rows_added_to_storage_total{job=~\"$job\"}[$__rate_interval])\n)", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 1, + "legendFormat": "slow inserts percentage", + "range": true, + "refId": "A" + } + ], + "title": "Slow inserts ($instance)", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Merge assist happens when storage can't keep up with merging parts. This is usually a sign of overload for storage.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "bars", + "fillOpacity": 100, + "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" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 16 + }, + "id": 116, + "links": [], + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "9.1.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "exemplar": false, + "expr": "sum(increase(vm_assisted_merges_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by(type) > 0", + "format": "time_series", + "interval": "5m", + "intervalFactor": 1, + "legendFormat": "__auto", + "range": true, + "refId": "A" + } + ], + "title": "Assisted merges ($instance)", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Slow queries rate according to `search.logSlowQueryDuration` flag, which is `5s` by default.", + "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" + } + }, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 16 + }, + "id": 60, + "links": [], + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "9.1.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "expr": "sum(rate(vm_slow_queries_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))", + "format": "time_series", + "hide": false, + "intervalFactor": 1, + "legendFormat": "slow queries rate", + "refId": "A" + } + ], + "title": "Slow queries rate ($instance)", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows the percentage of used cache size from the allowed size by type. \nValues close to 100% show the maximum potential utilization.\nValues close to 0% show that cache is underutilized.", + "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" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "percentunit" + }, + "overrides": [] + }, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 24 + }, + "id": 90, + "options": { + "legend": { + "calcs": [ + "lastNotNull", + "mean", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "9.1.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "exemplar": false, + "expr": "vm_cache_size_bytes{job=~\"$job\", instance=~\"$instance\"} / vm_cache_size_max_bytes{job=~\"$job\", instance=~\"$instance\"}", + "interval": "", + "legendFormat": "{{type}}", + "range": true, + "refId": "A" + } + ], + "title": "Cache usage % by type ($instance)", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows cache miss ratio. Lower is better.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "max": 1, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "percentunit" + }, + "overrides": [] + }, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 24 + }, + "id": 118, + "links": [], + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "9.1.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "exemplar": false, + "expr": "(\n rate(vm_cache_misses_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])\n /\n rate(vm_cache_requests_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])\n) > 0", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{type}}", + "range": true, + "refId": "A" + } + ], + "title": "Cache miss ratio ($instance)", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "custom": { + "align": "auto", + "displayMode": "auto", + "inspect": false + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "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": 8, + "w": 12, + "x": 0, + "y": 33 + }, + "id": 120, + "options": { + "footer": { + "fields": "", + "reducer": [ + "sum" + ], + "show": false + }, + "showHeader": true, + "sortBy": [ + { + "desc": true, + "displayName": "job" + } + ] + }, + "pluginVersion": "9.1.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "exemplar": false, + "expr": "sum(flag{is_set=\"true\", job=~\"$job\", instance=~\"$instance\"}) by(job, instance, name, value)", + "format": "table", + "instant": true, + "legendFormat": "__auto", + "range": false, + "refId": "A" + } + ], + "title": "Non-default flags", + "transformations": [ + { + "id": "groupBy", + "options": { + "fields": { + "instance": { + "aggregations": [] + }, + "job": { + "aggregations": [] + }, + "name": { + "aggregations": [], + "operation": "groupby" + }, + "value": { + "aggregations": [], + "operation": "groupby" + } + } + } + } + ], + "type": "table" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "VictoriaMetrics limits the number of labels per each metric with `-maxLabelsPerTimeseries` command-line flag.\n\nThis prevents from ingesting metrics with too many labels. The value of `maxLabelsPerTimeseries` must be adjusted for your workload.\n\nWhen limit is exceeded (graph is > 0) - extra labels are dropped, which could result in unexpected identical time series.", + "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" + } + }, + "decimals": 2, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 33 + }, + "id": 74, + "links": [], + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "list", + "placement": "bottom", + "showLegend": false + }, + "tooltip": { + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "9.1.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "exemplar": false, + "expr": "sum(increase(vm_metrics_with_dropped_labels_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 1, + "legendFormat": "limit exceeded", + "refId": "A" + } + ], + "title": "Labels limit exceeded ($instance)", + "type": "timeseries" + } + ], + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "refId": "A" + } + ], + "title": "Troubleshooting", + "type": "row" + }, + { + "collapsed": true, + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 32 + }, + "id": 14, + "panels": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "How many datapoints are inserted into storage per second", + "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" + } + }, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 106 + }, + "id": 10, + "links": [], + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "9.1.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(rate(vm_rows_inserted_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (type) > 0", + "format": "time_series", + "hide": false, + "intervalFactor": 1, + "legendFormat": "{{type}}", + "range": true, + "refId": "A" + } + ], + "title": "Datapoints ingestion rate ($instance)", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows the time needed to reach the 100% of disk capacity based on the following params:\n* free disk space;\n* row ingestion rate;\n* dedup rate;\n* compression.\n\nUse this panel for capacity planning in order to estimate the time remaining for running out of the disk space.\n\n", + "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" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "s" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 106 + }, + "id": 73, + "links": [], + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "min" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "9.1.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "vm_free_disk_space_bytes{job=~\"$job\", instance=~\"$instance\"} \n/ ignoring(path) (\n (\n rate(vm_rows_added_to_storage_total{job=~\"$job\", instance=~\"$instance\"}[1d]) \n - ignoring(type) rate(vm_deduplicated_samples_total{job=~\"$job\", instance=~\"$instance\", type=\"merge\"}[1d])\n ) * scalar(\n sum(vm_data_size_bytes{job=~\"$job\", instance=~\"$instance\", type!=\"indexdb\"}) \n / sum(vm_rows{job=~\"$job\", instance=~\"$instance\", type!=\"indexdb\"})\n )\n )", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{instance}}", + "range": true, + "refId": "A" + } + ], + "title": "Storage full ETA ($instance)", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows amount of on-disk space occupied by data points and the remaining disk space at `-storageDataPath`", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "bytes" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 114 + }, + "id": 53, + "links": [], + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "9.1.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(vm_data_size_bytes{job=~\"$job\", instance=~\"$instance\", type!=\"indexdb\"})", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "legendFormat": "Used (datapoints)", + "range": true, + "refId": "A" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "expr": "vm_free_disk_space_bytes{job=~\"$job\", instance=~\"$instance\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "legendFormat": "Free", + "refId": "B" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(vm_data_size_bytes{job=~\"$job\", instance=~\"$instance\", type=\"indexdb\"})", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 1, + "legendFormat": "Used (index)", + "range": true, + "refId": "C" + } + ], + "title": "Disk space usage - datapoints ($instance)", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "How many datapoints are in RAM queue waiting to be written into storage. The number of pending data points should be in the range from 0 to `2*`, since VictoriaMetrics pushes pending data to persistent storage every second.", + "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" + } + }, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "pending index entries" + }, + "properties": [ + { + "id": "unit", + "value": "none" + }, + { + "id": "decimals", + "value": 3 + } + ] + } + ] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 114 + }, + "id": 34, + "links": [], + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "9.1.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "expr": "vm_pending_rows{job=~\"$job\", instance=~\"$instance\", type=\"storage\"}", + "format": "time_series", + "hide": false, + "intervalFactor": 1, + "legendFormat": "pending datapoints", + "refId": "A" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "expr": "vm_pending_rows{job=~\"$job\", instance=~\"$instance\", type=\"indexdb\"}", + "format": "time_series", + "hide": false, + "intervalFactor": 1, + "legendFormat": "pending index entries", + "refId": "B" + } + ], + "title": "Pending datapoints ($instance)", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows how many datapoints are in the storage and what is average disk usage per datapoint.", + "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" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "bytes-per-datapoint" + }, + "properties": [ + { + "id": "unit", + "value": "bytes" + }, + { + "id": "decimals", + "value": 2 + } + ] + } + ] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 122 + }, + "id": 30, + "links": [], + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "9.1.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "expr": "sum(vm_rows{job=~\"$job\", instance=~\"$instance\", type != \"indexdb\"})", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "legendFormat": "total datapoints", + "refId": "A" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(vm_data_size_bytes{job=~\"$job\", instance=~\"$instance\"}) \n/ sum(vm_rows{job=~\"$job\", instance=~\"$instance\"})", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "legendFormat": "bytes-per-datapoint", + "range": true, + "refId": "B" + } + ], + "title": "Datapoints ($instance)", + "type": "timeseries" + }, + { + "datasource": { + "uid": "$ds" + }, + "description": "Data parts of LSM tree.\nHigh number of parts could be an evidence of slow merge performance - check the resource utilization.\n* `indexdb` - inverted index\n* `storage/small` - recently added parts of data ingested into storage(hot data)\n* `storage/big` - small parts gradually merged into big parts (cold data)", + "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" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 122 + }, + "id": 36, + "links": [], + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "9.1.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "expr": "sum(vm_parts{job=~\"$job\", instance=~\"$instance\"}) by (type)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{type}}", + "refId": "A" + } + ], + "title": "LSM parts ($instance)", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows how many rows were ignored on insertion due to corrupted or out of retention timestamps.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 130 + }, + "id": 58, + "links": [], + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "9.1.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "exemplar": false, + "expr": "sum(increase(vm_rows_ignored_total{job=~\"$job\", instance=~\"$instance\"}[1h])) by (reason)", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{reason}}", + "range": true, + "refId": "A" + } + ], + "title": "Rows ignored for last 1h ($instance)", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "The number of on-going merges in storage nodes. It is expected to have high numbers for `storage/small` metric.", + "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" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 130 + }, + "id": 62, + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "9.1.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "expr": "sum(vm_active_merges{job=~\"$job\", instance=~\"$instance\"}) by(type)", + "legendFormat": "{{type}}", + "refId": "A" + } + ], + "title": "Active merges ($instance)", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows how many ongoing insertions (not API /write calls) on disk are taking place, where:\n* `max` - equal to number of CPUs;\n* `current` - current number of goroutines busy with inserting rows into underlying storage.\n\nEvery successful API /write call results into flush on disk. However, these two actions are separated and controlled via different concurrency limiters. The `max` on this panel can't be changed and always equal to number of CPUs. \n\nWhen `current` hits `max` constantly, it means storage is overloaded and requires more CPU.\n\n", + "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" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "max" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#C4162A", + "mode": "fixed" + } + } + ] + } + ] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 138 + }, + "id": 59, + "links": [], + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "9.1.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "max_over_time(vm_concurrent_addrows_capacity{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "legendFormat": "max", + "range": true, + "refId": "A" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "expr": "sum(vm_concurrent_addrows_current{job=~\"$job\", instance=~\"$instance\"})", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "current", + "refId": "B" + } + ], + "title": "Concurrent flushes on disk ($instance)", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "The number of rows merged per second by storage nodes.", + "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" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 138 + }, + "id": 64, + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "9.1.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "expr": "sum(rate(vm_rows_merged_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by(type)", + "legendFormat": "{{type}}", + "refId": "A" + } + ], + "title": "Merge speed ($instance)", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "99th percentile of number of series read per query.", + "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": 2, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 146 + }, + "id": 99, + "links": [], + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "9.1.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "expr": "histogram_quantile(0.99, sum(rate(vm_series_read_per_query_bucket{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (vmrange))", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "title": "Series read per query ($instance)", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "99th percentile of number of raw samples read per queried series.", + "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": 2, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 146 + }, + "id": 103, + "links": [], + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "9.1.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "histogram_quantile(0.99, sum(rate(vm_rows_read_per_series_bucket{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (vmrange))", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{label_name}}", + "range": true, + "refId": "A" + } + ], + "title": "Datapoints read per series ($instance)", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "99th percentile of number of raw datapoints read per query.", + "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": 2, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 154 + }, + "id": 122, + "links": [], + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "9.1.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(histogram_quantile(0.99, sum(rate(vm_rows_read_per_query_bucket{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (instance, vmrange)))", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "legendFormat": "datapoints", + "range": true, + "refId": "A" + } + ], + "title": "Datapoints read per query ($instance)", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "99th percentile of number of raw samples scanner per query.\n\nThis number can exceed number of RowsReadPerQuery if `step` query arg passed to [/api/v1/query_range](https://prometheus.io/docs/prometheus/latest/querying/api/#range-queries) is smaller than the lookbehind window set in square brackets of [rollup function](https://docs.victoriametrics.com/MetricsQL.html#rollup-functions). For example, if `increase(some_metric[1h])` is executed with the `step=5m`, then the same raw samples on a hour time range are scanned `1h/5m=12` times. See [this article](https://valyala.medium.com/how-to-optimize-promql-and-metricsql-queries-85a1b75bf986) for details.", + "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": 2, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 154 + }, + "id": 105, + "links": [], + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "9.1.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "expr": "histogram_quantile(0.99, sum(rate(vm_rows_scanned_per_query_bucket{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (vmrange))", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "title": "Datapoints scanned per series ($instance)", + "type": "timeseries" + } + ], + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "refId": "A" + } + ], + "title": "Storage", + "type": "row" } ], - "refresh": "30s", - "schemaVersion": 36, + "refresh": false, + "schemaVersion": 37, "style": "dark", "tags": [ "victoriametrics", @@ -5055,7 +5274,7 @@ ] }, "time": { - "from": "now-3h", + "from": "now-30m", "to": "now" }, "timepicker": { @@ -5087,4 +5306,4 @@ "uid": "wNf0q_kZk", "version": 1, "weekStart": "" -} +} \ No newline at end of file diff --git a/deployment/docker/alerts.yml b/deployment/docker/alerts.yml index bdcf625ec..5d478f0c7 100644 --- a/deployment/docker/alerts.yml +++ b/deployment/docker/alerts.yml @@ -54,6 +54,7 @@ groups: for: 15m labels: severity: warning + show_at: dashboard annotations: dashboard: "http://localhost:3000/d/wNf0q_kZk?viewPanel=35&var-instance={{ $labels.instance }}" summary: "Too many errors served for path {{ $labels.path }} (instance {{ $labels.instance }})" @@ -65,6 +66,7 @@ groups: for: 15m labels: severity: warning + show_at: dashboard annotations: dashboard: "http://localhost:3000/d/wNf0q_kZk?viewPanel=59&var-instance={{ $labels.instance }}" summary: "VictoriaMetrics on instance {{ $labels.instance }} is constantly hitting concurrent flushes limit"