From 683f8c2780fccd9fcc8fae2d2925f3410fc0a9b1 Mon Sep 17 00:00:00 2001 From: Artem Fetishev <149964189+rtm0@users.noreply.github.com> Date: Wed, 30 Oct 2024 16:44:08 +0100 Subject: [PATCH] dashboards: add Restarts panel (#7394) Reopening PR #7373 from a branch in VictoriaMetrics repo in order to enable edits and rebase. - [x] My change adheres [VictoriaMetrics contributing guidelines](https://docs.victoriametrics.com/contributing/). --------- Signed-off-by: Artem Fetishev Signed-off-by: hagen1778 Co-authored-by: hagen1778 --- dashboards/victorialogs.json | 172 ++++-- dashboards/victoriametrics-cluster.json | 107 +++- dashboards/victoriametrics.json | 267 ++++++--- dashboards/vm/victoriametrics-cluster.json | 107 +++- dashboards/vm/victoriametrics.json | 267 ++++++--- dashboards/vm/vmagent.json | 263 ++++++--- dashboards/vm/vmalert.json | 639 ++++++++++++--------- dashboards/vm/vmauth.json | 150 ++++- dashboards/vmagent.json | 263 ++++++--- dashboards/vmalert.json | 639 ++++++++++++--------- dashboards/vmauth.json | 150 ++++- docs/changelog/CHANGELOG.md | 1 + 12 files changed, 2095 insertions(+), 930 deletions(-) diff --git a/dashboards/victorialogs.json b/dashboards/victorialogs.json index 68c0d630a..de8cd19fe 100644 --- a/dashboards/victorialogs.json +++ b/dashboards/victorialogs.json @@ -1108,13 +1108,118 @@ "title": "Log stream churn rate", "type": "timeseries" }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows the number of restarts per job. The chart can be useful to identify periodic process restarts and correlate them with potential issues or anomalies. Normally, processes shouldn't restart unless restart was inited by user. The reason of restarts should be figured out by checking the logs of each specific service. ", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "axisSoftMin": 0, + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "stepAfter", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "decimals": 0, + "links": [], + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "none" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 22 + }, + "id": 62, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "9.1.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(changes(vm_app_start_timestamp{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]) > 0) by(job)", + "format": "time_series", + "instant": false, + "legendFormat": "{{job}}", + "refId": "A" + } + ], + "title": "Restarts ($job)", + "type": "timeseries" + }, { "collapsed": true, "gridPos": { "h": 1, "w": 24, "x": 0, - "y": 22 + "y": 30 }, "id": 28, "panels": [ @@ -1168,8 +1273,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -1185,7 +1289,7 @@ "h": 8, "w": 12, "x": 0, - "y": 3 + "y": 11 }, "id": 38, "options": { @@ -1275,8 +1379,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -1292,7 +1395,7 @@ "h": 8, "w": 12, "x": 12, - "y": 3 + "y": 11 }, "id": 40, "options": { @@ -1432,8 +1535,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -1449,7 +1551,7 @@ "h": 8, "w": 12, "x": 0, - "y": 11 + "y": 19 }, "id": 42, "options": { @@ -1538,8 +1640,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -1555,7 +1656,7 @@ "h": 8, "w": 12, "x": 12, - "y": 11 + "y": 19 }, "id": 44, "options": { @@ -1648,8 +1749,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -1681,7 +1781,7 @@ "h": 8, "w": 12, "x": 0, - "y": 19 + "y": 27 }, "id": 46, "options": { @@ -1773,8 +1873,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -1806,7 +1905,7 @@ "h": 8, "w": 12, "x": 12, - "y": 19 + "y": 27 }, "id": 48, "options": { @@ -1911,8 +2010,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -1928,7 +2026,7 @@ "h": 8, "w": 12, "x": 0, - "y": 27 + "y": 35 }, "id": 50, "options": { @@ -2017,8 +2115,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -2047,7 +2144,7 @@ "h": 8, "w": 12, "x": 12, - "y": 27 + "y": 35 }, "id": 52, "options": { @@ -2150,8 +2247,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -2167,7 +2263,7 @@ "h": 8, "w": 12, "x": 0, - "y": 35 + "y": 43 }, "id": 54, "options": { @@ -2256,8 +2352,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -2286,7 +2381,7 @@ "h": 8, "w": 12, "x": 12, - "y": 35 + "y": 43 }, "id": 56, "options": { @@ -2393,8 +2488,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -2410,7 +2504,7 @@ "h": 8, "w": 12, "x": 0, - "y": 43 + "y": 51 }, "id": 58, "options": { @@ -2501,8 +2595,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -2518,7 +2611,7 @@ "h": 8, "w": 12, "x": 12, - "y": 43 + "y": 51 }, "id": 60, "options": { @@ -2610,8 +2703,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -2627,7 +2719,7 @@ "h": 8, "w": 12, "x": 0, - "y": 51 + "y": 59 }, "id": 61, "options": { diff --git a/dashboards/victoriametrics-cluster.json b/dashboards/victoriametrics-cluster.json index df30817d0..bead53552 100644 --- a/dashboards/victoriametrics-cluster.json +++ b/dashboards/victoriametrics-cluster.json @@ -4124,6 +4124,111 @@ ], "title": "Rows ignored for last 1h ($instance)", "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows the number of restarts per job. The chart can be useful to identify periodic process restarts and correlate them with potential issues or anomalies. Normally, processes shouldn't restart unless restart was inited by user. The reason of restarts should be figured out by checking the logs of each specific service. ", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "axisSoftMin": 0, + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "stepAfter", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "decimals": 0, + "links": [], + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "none" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 70 + }, + "id": 214, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "9.1.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(changes(vm_app_start_timestamp{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]) > 0) by(job)", + "format": "time_series", + "instant": false, + "legendFormat": "{{job}}", + "refId": "A" + } + ], + "title": "Restarts ($job)", + "type": "timeseries" } ], "title": "Troubleshooting", @@ -9895,4 +10000,4 @@ "uid": "oS7Bi_0Wz", "version": 1, "weekStart": "" -} \ No newline at end of file +} diff --git a/dashboards/victoriametrics.json b/dashboards/victoriametrics.json index 6210a460b..674eb3180 100644 --- a/dashboards/victoriametrics.json +++ b/dashboards/victoriametrics.json @@ -1569,7 +1569,7 @@ "h": 8, "w": 12, "x": 0, - "y": 3 + "y": 11 }, "id": 112, "links": [], @@ -1677,7 +1677,7 @@ "h": 8, "w": 12, "x": 12, - "y": 3 + "y": 11 }, "id": 44, "options": { @@ -1844,7 +1844,7 @@ "h": 8, "w": 12, "x": 0, - "y": 11 + "y": 19 }, "id": 123, "links": [], @@ -1951,7 +1951,7 @@ "h": 8, "w": 12, "x": 12, - "y": 11 + "y": 19 }, "id": 114, "options": { @@ -2044,8 +2044,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -2077,7 +2076,7 @@ "h": 8, "w": 12, "x": 0, - "y": 19 + "y": 27 }, "id": 75, "options": { @@ -2169,8 +2168,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -2202,7 +2200,7 @@ "h": 8, "w": 12, "x": 12, - "y": 19 + "y": 27 }, "id": 57, "options": { @@ -2309,8 +2307,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -2326,7 +2323,7 @@ "h": 8, "w": 12, "x": 0, - "y": 27 + "y": 35 }, "id": 47, "options": { @@ -2415,8 +2412,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -2445,7 +2441,7 @@ "h": 8, "w": 12, "x": 12, - "y": 27 + "y": 35 }, "id": 76, "options": { @@ -2552,8 +2548,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -2569,7 +2564,7 @@ "h": 8, "w": 12, "x": 0, - "y": 35 + "y": 43 }, "id": 48, "options": { @@ -2658,8 +2653,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -2688,7 +2682,7 @@ "h": 8, "w": 12, "x": 12, - "y": 35 + "y": 43 }, "id": 124, "options": { @@ -2795,8 +2789,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -2812,7 +2805,7 @@ "h": 8, "w": 12, "x": 0, - "y": 43 + "y": 51 }, "id": 49, "options": { @@ -2903,8 +2896,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -2920,7 +2912,7 @@ "h": 8, "w": 12, "x": 12, - "y": 43 + "y": 51 }, "id": 37, "options": { @@ -3010,8 +3002,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -3040,7 +3031,7 @@ "h": 8, "w": 12, "x": 0, - "y": 51 + "y": 59 }, "id": 127, "options": { @@ -3146,8 +3137,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -3163,7 +3153,7 @@ "h": 8, "w": 12, "x": 12, - "y": 51 + "y": 59 }, "id": 125, "options": { @@ -3253,8 +3243,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -3270,7 +3259,7 @@ "h": 8, "w": 12, "x": 0, - "y": 59 + "y": 67 }, "id": 128, "options": { @@ -3386,7 +3375,8 @@ "mode": "absolute", "steps": [ { - "color": "green" + "color": "green", + "value": null }, { "color": "red", @@ -3394,8 +3384,7 @@ } ] }, - "unit": "short", - "unitScale": true + "unit": "short" }, "overrides": [] }, @@ -3403,7 +3392,7 @@ "h": 8, "w": 12, "x": 0, - "y": 4 + "y": 32 }, "id": 66, "options": { @@ -3505,7 +3494,8 @@ "mode": "absolute", "steps": [ { - "color": "transparent" + "color": "transparent", + "value": null }, { "color": "red", @@ -3513,8 +3503,7 @@ } ] }, - "unit": "percentunit", - "unitScale": true + "unit": "percentunit" }, "overrides": [] }, @@ -3522,10 +3511,9 @@ "h": 8, "w": 12, "x": 12, - "y": 4 + "y": 32 }, "id": 68, - "links": [], "options": { "legend": { "calcs": [ @@ -3615,7 +3603,8 @@ "mode": "absolute", "steps": [ { - "color": "green" + "color": "green", + "value": null }, { "color": "red", @@ -3623,8 +3612,7 @@ } ] }, - "unit": "short", - "unitScale": true + "unit": "short" }, "overrides": [] }, @@ -3632,10 +3620,9 @@ "h": 8, "w": 12, "x": 0, - "y": 12 + "y": 40 }, "id": 116, - "links": [], "options": { "legend": { "calcs": [ @@ -3723,7 +3710,8 @@ "mode": "absolute", "steps": [ { - "color": "green" + "color": "green", + "value": null }, { "color": "red", @@ -3731,8 +3719,7 @@ } ] }, - "unit": "short", - "unitScale": true + "unit": "short" }, "overrides": [] }, @@ -3740,10 +3727,9 @@ "h": 8, "w": 12, "x": 12, - "y": 12 + "y": 40 }, "id": 60, - "links": [], "options": { "legend": { "calcs": [ @@ -3830,7 +3816,8 @@ "mode": "absolute", "steps": [ { - "color": "green" + "color": "green", + "value": null }, { "color": "red", @@ -3838,8 +3825,7 @@ } ] }, - "unit": "percentunit", - "unitScale": true + "unit": "percentunit" }, "overrides": [] }, @@ -3847,7 +3833,7 @@ "h": 9, "w": 12, "x": 0, - "y": 20 + "y": 48 }, "id": 90, "options": { @@ -3938,7 +3924,8 @@ "mode": "absolute", "steps": [ { - "color": "green" + "color": "green", + "value": null }, { "color": "red", @@ -3946,8 +3933,7 @@ } ] }, - "unit": "percentunit", - "unitScale": true + "unit": "percentunit" }, "overrides": [] }, @@ -3955,10 +3941,9 @@ "h": 9, "w": 12, "x": 12, - "y": 20 + "y": 48 }, "id": 118, - "links": [], "options": { "legend": { "calcs": [ @@ -4022,15 +4007,15 @@ "mode": "absolute", "steps": [ { - "color": "green" + "color": "green", + "value": null }, { "color": "red", "value": 80 } ] - }, - "unitScale": true + } }, "overrides": [ { @@ -4075,7 +4060,7 @@ "h": 8, "w": 12, "x": 0, - "y": 29 + "y": 57 }, "id": 126, "options": { @@ -4090,7 +4075,7 @@ }, "showHeader": true }, - "pluginVersion": "10.3.1", + "pluginVersion": "10.4.2", "targets": [ { "datasource": { @@ -4161,7 +4146,8 @@ "mode": "absolute", "steps": [ { - "color": "green" + "color": "green", + "value": null }, { "color": "red", @@ -4169,8 +4155,7 @@ } ] }, - "unit": "short", - "unitScale": true + "unit": "short" }, "overrides": [] }, @@ -4178,10 +4163,9 @@ "h": 8, "w": 12, "x": 12, - "y": 29 + "y": 57 }, "id": 74, - "links": [], "options": { "legend": { "calcs": [ @@ -4218,6 +4202,111 @@ ], "title": "Labels limit exceeded", "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows the number of restarts per job. The chart can be useful to identify periodic process restarts and correlate them with potential issues or anomalies. Normally, processes shouldn't restart unless restart was inited by user. The reason of restarts should be figured out by checking the logs of each specific service. ", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "axisSoftMin": 0, + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "stepAfter", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "decimals": 0, + "links": [], + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "none" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 65 + }, + "id": 129, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "9.1.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(changes(vm_app_start_timestamp{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]) > 0) by(job)", + "format": "time_series", + "instant": false, + "legendFormat": "{{job}}", + "refId": "A" + } + ], + "title": "Restarts ($job)", + "type": "timeseries" } ], "targets": [ @@ -4313,7 +4402,7 @@ "h": 8, "w": 12, "x": 0, - "y": 5 + "y": 13 }, "id": 10, "links": [], @@ -4422,7 +4511,7 @@ "h": 8, "w": 12, "x": 12, - "y": 5 + "y": 13 }, "id": 73, "links": [], @@ -4532,7 +4621,7 @@ "h": 8, "w": 12, "x": 0, - "y": 13 + "y": 21 }, "id": 53, "links": [], @@ -4686,7 +4775,7 @@ "h": 8, "w": 12, "x": 12, - "y": 13 + "y": 21 }, "id": 34, "links": [], @@ -4824,7 +4913,7 @@ "h": 8, "w": 12, "x": 0, - "y": 21 + "y": 29 }, "id": 30, "links": [], @@ -4946,7 +5035,7 @@ "h": 8, "w": 12, "x": 12, - "y": 21 + "y": 29 }, "id": 36, "links": [], @@ -5054,7 +5143,7 @@ "h": 8, "w": 12, "x": 0, - "y": 29 + "y": 37 }, "id": 58, "links": [], @@ -5164,7 +5253,7 @@ "h": 8, "w": 12, "x": 12, - "y": 29 + "y": 37 }, "id": 62, "options": { @@ -5284,7 +5373,7 @@ "h": 8, "w": 12, "x": 0, - "y": 37 + "y": 45 }, "id": 59, "links": [], @@ -5404,7 +5493,7 @@ "h": 8, "w": 12, "x": 12, - "y": 37 + "y": 45 }, "id": 64, "options": { @@ -5510,7 +5599,7 @@ "h": 8, "w": 12, "x": 0, - "y": 45 + "y": 53 }, "id": 99, "links": [], @@ -5620,7 +5709,7 @@ "h": 8, "w": 12, "x": 12, - "y": 45 + "y": 53 }, "id": 103, "links": [], @@ -5730,7 +5819,7 @@ "h": 8, "w": 12, "x": 0, - "y": 53 + "y": 61 }, "id": 122, "links": [], @@ -5840,7 +5929,7 @@ "h": 8, "w": 12, "x": 12, - "y": 53 + "y": 61 }, "id": 105, "links": [], diff --git a/dashboards/vm/victoriametrics-cluster.json b/dashboards/vm/victoriametrics-cluster.json index bbc000252..bbdcd6e47 100644 --- a/dashboards/vm/victoriametrics-cluster.json +++ b/dashboards/vm/victoriametrics-cluster.json @@ -4125,6 +4125,111 @@ ], "title": "Rows ignored for last 1h ($instance)", "type": "timeseries" + }, + { + "datasource": { + "type": "victoriametrics-datasource", + "uid": "$ds" + }, + "description": "Shows the number of restarts per job. The chart can be useful to identify periodic process restarts and correlate them with potential issues or anomalies. Normally, processes shouldn't restart unless restart was inited by user. The reason of restarts should be figured out by checking the logs of each specific service. ", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "axisSoftMin": 0, + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "stepAfter", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "decimals": 0, + "links": [], + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "none" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 70 + }, + "id": 214, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "9.1.0", + "targets": [ + { + "datasource": { + "type": "victoriametrics-datasource", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(changes(vm_app_start_timestamp{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]) > 0) by(job)", + "format": "time_series", + "instant": false, + "legendFormat": "{{job}}", + "refId": "A" + } + ], + "title": "Restarts ($job)", + "type": "timeseries" } ], "title": "Troubleshooting", @@ -9896,4 +10001,4 @@ "uid": "oS7Bi_0Wz_vm", "version": 1, "weekStart": "" -} \ No newline at end of file +} diff --git a/dashboards/vm/victoriametrics.json b/dashboards/vm/victoriametrics.json index cbd11bfd3..7bf01e0f2 100644 --- a/dashboards/vm/victoriametrics.json +++ b/dashboards/vm/victoriametrics.json @@ -1570,7 +1570,7 @@ "h": 8, "w": 12, "x": 0, - "y": 3 + "y": 11 }, "id": 112, "links": [], @@ -1678,7 +1678,7 @@ "h": 8, "w": 12, "x": 12, - "y": 3 + "y": 11 }, "id": 44, "options": { @@ -1845,7 +1845,7 @@ "h": 8, "w": 12, "x": 0, - "y": 11 + "y": 19 }, "id": 123, "links": [], @@ -1952,7 +1952,7 @@ "h": 8, "w": 12, "x": 12, - "y": 11 + "y": 19 }, "id": 114, "options": { @@ -2045,8 +2045,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -2078,7 +2077,7 @@ "h": 8, "w": 12, "x": 0, - "y": 19 + "y": 27 }, "id": 75, "options": { @@ -2170,8 +2169,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -2203,7 +2201,7 @@ "h": 8, "w": 12, "x": 12, - "y": 19 + "y": 27 }, "id": 57, "options": { @@ -2310,8 +2308,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -2327,7 +2324,7 @@ "h": 8, "w": 12, "x": 0, - "y": 27 + "y": 35 }, "id": 47, "options": { @@ -2416,8 +2413,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -2446,7 +2442,7 @@ "h": 8, "w": 12, "x": 12, - "y": 27 + "y": 35 }, "id": 76, "options": { @@ -2553,8 +2549,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -2570,7 +2565,7 @@ "h": 8, "w": 12, "x": 0, - "y": 35 + "y": 43 }, "id": 48, "options": { @@ -2659,8 +2654,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -2689,7 +2683,7 @@ "h": 8, "w": 12, "x": 12, - "y": 35 + "y": 43 }, "id": 124, "options": { @@ -2796,8 +2790,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -2813,7 +2806,7 @@ "h": 8, "w": 12, "x": 0, - "y": 43 + "y": 51 }, "id": 49, "options": { @@ -2904,8 +2897,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -2921,7 +2913,7 @@ "h": 8, "w": 12, "x": 12, - "y": 43 + "y": 51 }, "id": 37, "options": { @@ -3011,8 +3003,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -3041,7 +3032,7 @@ "h": 8, "w": 12, "x": 0, - "y": 51 + "y": 59 }, "id": 127, "options": { @@ -3147,8 +3138,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -3164,7 +3154,7 @@ "h": 8, "w": 12, "x": 12, - "y": 51 + "y": 59 }, "id": 125, "options": { @@ -3254,8 +3244,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -3271,7 +3260,7 @@ "h": 8, "w": 12, "x": 0, - "y": 59 + "y": 67 }, "id": 128, "options": { @@ -3387,7 +3376,8 @@ "mode": "absolute", "steps": [ { - "color": "green" + "color": "green", + "value": null }, { "color": "red", @@ -3395,8 +3385,7 @@ } ] }, - "unit": "short", - "unitScale": true + "unit": "short" }, "overrides": [] }, @@ -3404,7 +3393,7 @@ "h": 8, "w": 12, "x": 0, - "y": 4 + "y": 32 }, "id": 66, "options": { @@ -3506,7 +3495,8 @@ "mode": "absolute", "steps": [ { - "color": "transparent" + "color": "transparent", + "value": null }, { "color": "red", @@ -3514,8 +3504,7 @@ } ] }, - "unit": "percentunit", - "unitScale": true + "unit": "percentunit" }, "overrides": [] }, @@ -3523,10 +3512,9 @@ "h": 8, "w": 12, "x": 12, - "y": 4 + "y": 32 }, "id": 68, - "links": [], "options": { "legend": { "calcs": [ @@ -3616,7 +3604,8 @@ "mode": "absolute", "steps": [ { - "color": "green" + "color": "green", + "value": null }, { "color": "red", @@ -3624,8 +3613,7 @@ } ] }, - "unit": "short", - "unitScale": true + "unit": "short" }, "overrides": [] }, @@ -3633,10 +3621,9 @@ "h": 8, "w": 12, "x": 0, - "y": 12 + "y": 40 }, "id": 116, - "links": [], "options": { "legend": { "calcs": [ @@ -3724,7 +3711,8 @@ "mode": "absolute", "steps": [ { - "color": "green" + "color": "green", + "value": null }, { "color": "red", @@ -3732,8 +3720,7 @@ } ] }, - "unit": "short", - "unitScale": true + "unit": "short" }, "overrides": [] }, @@ -3741,10 +3728,9 @@ "h": 8, "w": 12, "x": 12, - "y": 12 + "y": 40 }, "id": 60, - "links": [], "options": { "legend": { "calcs": [ @@ -3831,7 +3817,8 @@ "mode": "absolute", "steps": [ { - "color": "green" + "color": "green", + "value": null }, { "color": "red", @@ -3839,8 +3826,7 @@ } ] }, - "unit": "percentunit", - "unitScale": true + "unit": "percentunit" }, "overrides": [] }, @@ -3848,7 +3834,7 @@ "h": 9, "w": 12, "x": 0, - "y": 20 + "y": 48 }, "id": 90, "options": { @@ -3939,7 +3925,8 @@ "mode": "absolute", "steps": [ { - "color": "green" + "color": "green", + "value": null }, { "color": "red", @@ -3947,8 +3934,7 @@ } ] }, - "unit": "percentunit", - "unitScale": true + "unit": "percentunit" }, "overrides": [] }, @@ -3956,10 +3942,9 @@ "h": 9, "w": 12, "x": 12, - "y": 20 + "y": 48 }, "id": 118, - "links": [], "options": { "legend": { "calcs": [ @@ -4023,15 +4008,15 @@ "mode": "absolute", "steps": [ { - "color": "green" + "color": "green", + "value": null }, { "color": "red", "value": 80 } ] - }, - "unitScale": true + } }, "overrides": [ { @@ -4076,7 +4061,7 @@ "h": 8, "w": 12, "x": 0, - "y": 29 + "y": 57 }, "id": 126, "options": { @@ -4091,7 +4076,7 @@ }, "showHeader": true }, - "pluginVersion": "10.3.1", + "pluginVersion": "10.4.2", "targets": [ { "datasource": { @@ -4162,7 +4147,8 @@ "mode": "absolute", "steps": [ { - "color": "green" + "color": "green", + "value": null }, { "color": "red", @@ -4170,8 +4156,7 @@ } ] }, - "unit": "short", - "unitScale": true + "unit": "short" }, "overrides": [] }, @@ -4179,10 +4164,9 @@ "h": 8, "w": 12, "x": 12, - "y": 29 + "y": 57 }, "id": 74, - "links": [], "options": { "legend": { "calcs": [ @@ -4219,6 +4203,111 @@ ], "title": "Labels limit exceeded", "type": "timeseries" + }, + { + "datasource": { + "type": "victoriametrics-datasource", + "uid": "$ds" + }, + "description": "Shows the number of restarts per job. The chart can be useful to identify periodic process restarts and correlate them with potential issues or anomalies. Normally, processes shouldn't restart unless restart was inited by user. The reason of restarts should be figured out by checking the logs of each specific service. ", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "axisSoftMin": 0, + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "stepAfter", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "decimals": 0, + "links": [], + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "none" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 65 + }, + "id": 129, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "9.1.0", + "targets": [ + { + "datasource": { + "type": "victoriametrics-datasource", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(changes(vm_app_start_timestamp{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]) > 0) by(job)", + "format": "time_series", + "instant": false, + "legendFormat": "{{job}}", + "refId": "A" + } + ], + "title": "Restarts ($job)", + "type": "timeseries" } ], "targets": [ @@ -4314,7 +4403,7 @@ "h": 8, "w": 12, "x": 0, - "y": 5 + "y": 13 }, "id": 10, "links": [], @@ -4423,7 +4512,7 @@ "h": 8, "w": 12, "x": 12, - "y": 5 + "y": 13 }, "id": 73, "links": [], @@ -4533,7 +4622,7 @@ "h": 8, "w": 12, "x": 0, - "y": 13 + "y": 21 }, "id": 53, "links": [], @@ -4687,7 +4776,7 @@ "h": 8, "w": 12, "x": 12, - "y": 13 + "y": 21 }, "id": 34, "links": [], @@ -4825,7 +4914,7 @@ "h": 8, "w": 12, "x": 0, - "y": 21 + "y": 29 }, "id": 30, "links": [], @@ -4947,7 +5036,7 @@ "h": 8, "w": 12, "x": 12, - "y": 21 + "y": 29 }, "id": 36, "links": [], @@ -5055,7 +5144,7 @@ "h": 8, "w": 12, "x": 0, - "y": 29 + "y": 37 }, "id": 58, "links": [], @@ -5165,7 +5254,7 @@ "h": 8, "w": 12, "x": 12, - "y": 29 + "y": 37 }, "id": 62, "options": { @@ -5285,7 +5374,7 @@ "h": 8, "w": 12, "x": 0, - "y": 37 + "y": 45 }, "id": 59, "links": [], @@ -5405,7 +5494,7 @@ "h": 8, "w": 12, "x": 12, - "y": 37 + "y": 45 }, "id": 64, "options": { @@ -5511,7 +5600,7 @@ "h": 8, "w": 12, "x": 0, - "y": 45 + "y": 53 }, "id": 99, "links": [], @@ -5621,7 +5710,7 @@ "h": 8, "w": 12, "x": 12, - "y": 45 + "y": 53 }, "id": 103, "links": [], @@ -5731,7 +5820,7 @@ "h": 8, "w": 12, "x": 0, - "y": 53 + "y": 61 }, "id": 122, "links": [], @@ -5841,7 +5930,7 @@ "h": 8, "w": 12, "x": 12, - "y": 53 + "y": 61 }, "id": 105, "links": [], diff --git a/dashboards/vm/vmagent.json b/dashboards/vm/vmagent.json index 9a64ed834..64cbb72ed 100644 --- a/dashboards/vm/vmagent.json +++ b/dashboards/vm/vmagent.json @@ -1336,8 +1336,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -1440,8 +1439,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -1619,7 +1617,8 @@ "mode": "absolute", "steps": [ { - "color": "green" + "color": "green", + "value": null }, { "color": "red", @@ -1635,7 +1634,7 @@ "h": 8, "w": 12, "x": 0, - "y": 35 + "y": 3 }, "id": 109, "options": { @@ -1750,7 +1749,7 @@ "h": 8, "w": 12, "x": 12, - "y": 35 + "y": 3 }, "id": 111, "options": { @@ -1875,7 +1874,7 @@ "h": 8, "w": 12, "x": 0, - "y": 43 + "y": 11 }, "id": 81, "options": { @@ -2011,7 +2010,7 @@ "h": 8, "w": 12, "x": 12, - "y": 43 + "y": 11 }, "id": 7, "options": { @@ -2130,7 +2129,7 @@ "h": 8, "w": 12, "x": 0, - "y": 51 + "y": 19 }, "id": 83, "options": { @@ -2236,7 +2235,7 @@ "h": 8, "w": 12, "x": 12, - "y": 51 + "y": 19 }, "id": 39, "options": { @@ -2343,7 +2342,7 @@ "h": 8, "w": 12, "x": 0, - "y": 59 + "y": 27 }, "id": 135, "options": { @@ -2450,7 +2449,7 @@ "h": 8, "w": 12, "x": 12, - "y": 59 + "y": 27 }, "id": 149, "options": { @@ -2556,7 +2555,7 @@ "h": 8, "w": 12, "x": 12, - "y": 67 + "y": 35 }, "id": 41, "options": { @@ -2669,7 +2668,8 @@ "mode": "absolute", "steps": [ { - "color": "green" + "color": "green", + "value": null }, { "color": "red", @@ -2685,7 +2685,7 @@ "h": 8, "w": 12, "x": 0, - "y": 20 + "y": 4 }, "id": 92, "options": { @@ -2773,7 +2773,8 @@ "mode": "absolute", "steps": [ { - "color": "green" + "color": "green", + "value": null }, { "color": "red", @@ -2789,7 +2790,7 @@ "h": 8, "w": 12, "x": 12, - "y": 20 + "y": 4 }, "id": 95, "options": { @@ -2880,7 +2881,8 @@ "mode": "absolute", "steps": [ { - "color": "transparent" + "color": "transparent", + "value": null }, { "color": "red", @@ -2896,7 +2898,7 @@ "h": 8, "w": 12, "x": 0, - "y": 28 + "y": 12 }, "id": 98, "options": { @@ -2987,7 +2989,8 @@ "mode": "absolute", "steps": [ { - "color": "transparent" + "color": "transparent", + "value": null }, { "color": "red", @@ -3003,7 +3006,7 @@ "h": 8, "w": 12, "x": 12, - "y": 28 + "y": 12 }, "id": 99, "options": { @@ -3055,6 +3058,7 @@ "mode": "palette-classic" }, "custom": { + "axisBorderShow": false, "axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", @@ -3068,6 +3072,7 @@ "tooltip": false, "viz": false }, + "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 1, "pointSize": 5, @@ -3091,7 +3096,8 @@ "mode": "absolute", "steps": [ { - "color": "green" + "color": "green", + "value": null }, { "color": "red", @@ -3107,7 +3113,7 @@ "h": 8, "w": 12, "x": 0, - "y": 36 + "y": 20 }, "id": 79, "options": { @@ -3159,6 +3165,7 @@ "mode": "palette-classic" }, "custom": { + "axisBorderShow": false, "axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", @@ -3172,6 +3179,7 @@ "tooltip": false, "viz": false }, + "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 1, "pointSize": 5, @@ -3195,7 +3203,8 @@ "mode": "absolute", "steps": [ { - "color": "green" + "color": "green", + "value": null }, { "color": "red", @@ -3211,7 +3220,7 @@ "h": 8, "w": 12, "x": 12, - "y": 36 + "y": 20 }, "id": 18, "links": [ @@ -3269,6 +3278,7 @@ "mode": "palette-classic" }, "custom": { + "axisBorderShow": false, "axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", @@ -3282,6 +3292,7 @@ "tooltip": false, "viz": false }, + "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 1, "pointSize": 5, @@ -3305,7 +3316,8 @@ "mode": "absolute", "steps": [ { - "color": "green" + "color": "green", + "value": null }, { "color": "red", @@ -3321,7 +3333,7 @@ "h": 8, "w": 12, "x": 0, - "y": 44 + "y": 28 }, "id": 127, "options": { @@ -3371,6 +3383,7 @@ "mode": "palette-classic" }, "custom": { + "axisBorderShow": false, "axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", @@ -3384,6 +3397,7 @@ "tooltip": false, "viz": false }, + "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 1, "pointSize": 5, @@ -3407,7 +3421,8 @@ "mode": "absolute", "steps": [ { - "color": "green" + "color": "green", + "value": null }, { "color": "red", @@ -3423,7 +3438,7 @@ "h": 8, "w": 12, "x": 12, - "y": 44 + "y": 28 }, "id": 50, "options": { @@ -3483,7 +3498,8 @@ "mode": "absolute", "steps": [ { - "color": "green" + "color": "green", + "value": null }, { "color": "red", @@ -3521,13 +3537,15 @@ }, "gridPos": { "h": 7, - "w": 24, + "w": 12, "x": 0, - "y": 52 + "y": 36 }, "id": 129, "options": { + "cellHeight": "sm", "footer": { + "countRows": false, "fields": "", "reducer": [ "sum" @@ -3542,7 +3560,7 @@ } ] }, - "pluginVersion": "9.2.6", + "pluginVersion": "10.4.2", "targets": [ { "datasource": { @@ -3585,6 +3603,111 @@ } ], "type": "table" + }, + { + "datasource": { + "type": "victoriametrics-datasource", + "uid": "$ds" + }, + "description": "Shows the number of restarts per job. The chart can be useful to identify periodic process restarts and correlate them with potential issues or anomalies. Normally, processes shouldn't restart unless restart was inited by user. The reason of restarts should be figured out by checking the logs of each specific service. ", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "axisSoftMin": 0, + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "stepAfter", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "decimals": 0, + "links": [], + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "none" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 36 + }, + "id": 150, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "9.1.0", + "targets": [ + { + "datasource": { + "type": "victoriametrics-datasource", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(changes(vm_app_start_timestamp{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]) > 0) by(job)", + "format": "time_series", + "instant": false, + "legendFormat": "{{job}}", + "refId": "A" + } + ], + "title": "Restarts ($job)", + "type": "timeseries" } ], "targets": [ @@ -3678,7 +3801,7 @@ "h": 7, "w": 12, "x": 0, - "y": 45 + "y": 53 }, "id": 48, "options": { @@ -3784,7 +3907,7 @@ "h": 7, "w": 12, "x": 12, - "y": 45 + "y": 53 }, "id": 76, "options": { @@ -3888,7 +4011,7 @@ "h": 7, "w": 12, "x": 0, - "y": 52 + "y": 60 }, "id": 132, "options": { @@ -3994,7 +4117,7 @@ "h": 7, "w": 12, "x": 12, - "y": 52 + "y": 60 }, "id": 133, "options": { @@ -4099,7 +4222,7 @@ "h": 8, "w": 12, "x": 0, - "y": 59 + "y": 67 }, "id": 20, "options": { @@ -4203,7 +4326,7 @@ "h": 8, "w": 12, "x": 12, - "y": 59 + "y": 67 }, "id": 126, "options": { @@ -4306,7 +4429,7 @@ "h": 8, "w": 12, "x": 0, - "y": 67 + "y": 75 }, "id": 46, "options": { @@ -4409,7 +4532,7 @@ "h": 8, "w": 12, "x": 12, - "y": 67 + "y": 75 }, "id": 148, "options": { @@ -4512,7 +4635,7 @@ "h": 8, "w": 12, "x": 12, - "y": 75 + "y": 83 }, "id": 31, "options": { @@ -4691,7 +4814,7 @@ "h": 8, "w": 12, "x": 0, - "y": 22 + "y": 30 }, "id": 73, "options": { @@ -4808,7 +4931,7 @@ "h": 8, "w": 12, "x": 12, - "y": 14 + "y": 22 }, "id": 131, "options": { @@ -4912,7 +5035,7 @@ "h": 8, "w": 12, "x": 0, - "y": 22 + "y": 30 }, "id": 130, "options": { @@ -5029,7 +5152,7 @@ "h": 8, "w": 12, "x": 12, - "y": 22 + "y": 30 }, "id": 77, "options": { @@ -5163,7 +5286,7 @@ "h": 8, "w": 12, "x": 0, - "y": 15 + "y": 23 }, "id": 146, "options": { @@ -5265,7 +5388,7 @@ "h": 8, "w": 12, "x": 12, - "y": 15 + "y": 23 }, "id": 143, "options": { @@ -5361,7 +5484,7 @@ "h": 8, "w": 12, "x": 0, - "y": 23 + "y": 31 }, "id": 147, "options": { @@ -5464,7 +5587,7 @@ "h": 8, "w": 12, "x": 12, - "y": 23 + "y": 31 }, "id": 139, "options": { @@ -5575,7 +5698,7 @@ "h": 8, "w": 12, "x": 0, - "y": 31 + "y": 39 }, "id": 142, "options": { @@ -5672,7 +5795,7 @@ "h": 8, "w": 12, "x": 12, - "y": 31 + "y": 39 }, "id": 137, "options": { @@ -5785,7 +5908,7 @@ "h": 8, "w": 12, "x": 12, - "y": 39 + "y": 47 }, "id": 141, "options": { @@ -5916,7 +6039,7 @@ "h": 8, "w": 12, "x": 0, - "y": 16 + "y": 24 }, "id": 60, "options": { @@ -6020,7 +6143,7 @@ "h": 8, "w": 12, "x": 12, - "y": 16 + "y": 24 }, "id": 66, "options": { @@ -6124,7 +6247,7 @@ "h": 8, "w": 12, "x": 0, - "y": 24 + "y": 32 }, "id": 61, "options": { @@ -6228,7 +6351,7 @@ "h": 8, "w": 12, "x": 12, - "y": 24 + "y": 32 }, "id": 65, "options": { @@ -6331,7 +6454,7 @@ "h": 8, "w": 12, "x": 0, - "y": 32 + "y": 40 }, "id": 88, "options": { @@ -6430,7 +6553,7 @@ "h": 8, "w": 12, "x": 12, - "y": 32 + "y": 40 }, "id": 84, "options": { @@ -6533,7 +6656,7 @@ "h": 8, "w": 12, "x": 0, - "y": 40 + "y": 48 }, "id": 90, "options": { @@ -6599,7 +6722,7 @@ "h": 2, "w": 24, "x": 0, - "y": 25 + "y": 33 }, "id": 115, "options": { @@ -6677,7 +6800,7 @@ "h": 8, "w": 12, "x": 0, - "y": 27 + "y": 35 }, "id": 119, "options": { @@ -6781,7 +6904,7 @@ "h": 8, "w": 12, "x": 12, - "y": 27 + "y": 35 }, "id": 117, "options": { @@ -6887,7 +7010,7 @@ "h": 8, "w": 12, "x": 0, - "y": 35 + "y": 43 }, "id": 125, "links": [ @@ -7009,7 +7132,7 @@ "h": 8, "w": 12, "x": 12, - "y": 35 + "y": 43 }, "id": 123, "options": { @@ -7139,7 +7262,7 @@ "h": 8, "w": 12, "x": 0, - "y": 43 + "y": 51 }, "id": 121, "options": { @@ -7212,8 +7335,8 @@ { "current": { "selected": false, - "text": "VictoriaMetrics", - "value": "P4169E866C3094E38" + "text": "VictoriaMetrics - cluster", + "value": "PAF93674D0B4E9963" }, "hide": 0, "includeAll": false, @@ -7338,4 +7461,4 @@ "uid": "G7Z9GzMGz_vm", "version": 1, "weekStart": "" -} +} \ No newline at end of file diff --git a/dashboards/vm/vmalert.json b/dashboards/vm/vmalert.json index 3d71e5c18..61fa88537 100644 --- a/dashboards/vm/vmalert.json +++ b/dashboards/vm/vmalert.json @@ -1126,234 +1126,6 @@ "title": "Rules execution errors ($instance)", "type": "timeseries" }, - { - "datasource": { - "type": "victoriametrics-datasource", - "uid": "$ds" - }, - "fieldConfig": { - "defaults": { - "color": { - "mode": "thresholds" - }, - "custom": { - "align": "auto", - "cellOptions": { - "type": "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": 7, - "w": 12, - "x": 0, - "y": 25 - }, - "id": 50, - "options": { - "footer": { - "fields": "", - "reducer": [ - "sum" - ], - "show": false - }, - "showHeader": true, - "sortBy": [ - { - "desc": true, - "displayName": "job" - } - ] - }, - "pluginVersion": "9.2.7", - "targets": [ - { - "datasource": { - "type": "victoriametrics-datasource", - "uid": "$ds" - }, - "editorMode": "code", - "exemplar": false, - "expr": "sum(flag{is_set=\"true\", job=~\"$job\", instance=~\"$instance\"}) by(job, instance, name, value)", - "format": "table", - "instant": true, - "legendFormat": "__auto", - "range": false, - "refId": "A" - } - ], - "title": "Non-default flags", - "transformations": [ - { - "id": "groupBy", - "options": { - "fields": { - "instance": { - "aggregations": [ - "uniqueValues" - ], - "operation": "aggregate" - }, - "job": { - "aggregations": [], - "operation": "groupby" - }, - "name": { - "aggregations": [], - "operation": "groupby" - }, - "value": { - "aggregations": [], - "operation": "groupby" - } - } - } - } - ], - "type": "table" - }, - { - "datasource": { - "type": "victoriametrics-datasource", - "uid": "$ds" - }, - "description": "Missed evaluation means that group evaluation time takes longer than the configured evaluation interval. \nThis may result in missed alerting notifications or recording rules samples. Try increasing evaluation interval or concurrency for such groups. See https://docs.victoriametrics.com/vmalert/#groups\n\nIf rule expressions are taking longer than expected, please see https://docs.victoriametrics.com/troubleshooting/#slow-queries.\"", - "fieldConfig": { - "defaults": { - "color": { - "mode": "palette-classic" - }, - "custom": { - "axisCenteredZero": false, - "axisColorMode": "text", - "axisLabel": "", - "axisPlacement": "auto", - "barAlignment": 0, - "drawStyle": "bars", - "fillOpacity": 10, - "gradientMode": "none", - "hideFrom": { - "legend": false, - "tooltip": false, - "viz": false - }, - "lineInterpolation": "linear", - "lineWidth": 1, - "pointSize": 5, - "scaleDistribution": { - "type": "linear" - }, - "showPoints": "never", - "spanNulls": false, - "stacking": { - "group": "A", - "mode": "none" - }, - "thresholdsStyle": { - "mode": "off" - } - }, - "mappings": [], - "thresholds": { - "mode": "absolute", - "steps": [ - { - "color": "green" - }, - { - "color": "red", - "value": 80 - } - ] - }, - "unit": "short" - }, - "overrides": [] - }, - "gridPos": { - "h": 7, - "w": 12, - "x": 12, - "y": 25 - }, - "id": 58, - "options": { - "legend": { - "calcs": [ - "mean", - "lastNotNull", - "max" - ], - "displayMode": "table", - "placement": "bottom", - "showLegend": true - }, - "tooltip": { - "mode": "multi", - "sort": "none" - } - }, - "pluginVersion": "9.2.6", - "targets": [ - { - "datasource": { - "type": "victoriametrics-datasource", - "uid": "$ds" - }, - "editorMode": "code", - "exemplar": false, - "expr": "sum(increase(vmalert_iteration_missed_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by(job, group) > 0", - "interval": "1m", - "legendFormat": "__auto", - "range": true, - "refId": "A" - } - ], - "title": "Missed evaluations ($instance)", - "type": "timeseries" - }, { "collapsed": true, "datasource": { @@ -1364,7 +1136,7 @@ "h": 1, "w": 24, "x": 0, - "y": 32 + "y": 25 }, "id": 43, "panels": [ @@ -1435,7 +1207,7 @@ "h": 8, "w": 12, "x": 0, - "y": 3 + "y": 11 }, "id": 37, "links": [ @@ -1532,8 +1304,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -1549,7 +1320,7 @@ "h": 8, "w": 12, "x": 12, - "y": 3 + "y": 11 }, "id": 57, "links": [ @@ -1663,7 +1434,7 @@ "h": 8, "w": 12, "x": 0, - "y": 11 + "y": 19 }, "id": 35, "links": [ @@ -1779,7 +1550,7 @@ "h": 8, "w": 12, "x": 12, - "y": 11 + "y": 19 }, "id": 56, "links": [ @@ -1912,7 +1683,7 @@ "h": 8, "w": 12, "x": 0, - "y": 19 + "y": 27 }, "id": 39, "links": [], @@ -2020,7 +1791,7 @@ "h": 8, "w": 12, "x": 12, - "y": 19 + "y": 27 }, "id": 41, "links": [], @@ -2128,7 +1899,7 @@ "h": 8, "w": 12, "x": 0, - "y": 27 + "y": 35 }, "id": 59, "links": [], @@ -2219,8 +1990,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -2236,7 +2006,7 @@ "h": 8, "w": 12, "x": 12, - "y": 27 + "y": 35 }, "id": 61, "options": { @@ -2288,6 +2058,359 @@ "title": "Resource usage", "type": "row" }, + { + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 26 + }, + "id": 62, + "panels": [ + { + "datasource": { + "type": "victoriametrics-datasource", + "uid": "$ds" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "custom": { + "align": "auto", + "cellOptions": { + "type": "auto" + }, + "inspect": false + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "Value" + }, + "properties": [ + { + "id": "custom.hidden", + "value": true + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Time" + }, + "properties": [ + { + "id": "custom.hidden", + "value": true + } + ] + } + ] + }, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 27 + }, + "id": 50, + "options": { + "cellHeight": "sm", + "footer": { + "countRows": false, + "fields": "", + "reducer": [ + "sum" + ], + "show": false + }, + "showHeader": true, + "sortBy": [ + { + "desc": true, + "displayName": "job" + } + ] + }, + "pluginVersion": "10.4.2", + "targets": [ + { + "datasource": { + "type": "victoriametrics-datasource", + "uid": "$ds" + }, + "editorMode": "code", + "exemplar": false, + "expr": "sum(flag{is_set=\"true\", job=~\"$job\", instance=~\"$instance\"}) by(job, instance, name, value)", + "format": "table", + "instant": true, + "legendFormat": "__auto", + "range": false, + "refId": "A" + } + ], + "title": "Non-default flags", + "transformations": [ + { + "id": "groupBy", + "options": { + "fields": { + "instance": { + "aggregations": [ + "uniqueValues" + ], + "operation": "aggregate" + }, + "job": { + "aggregations": [], + "operation": "groupby" + }, + "name": { + "aggregations": [], + "operation": "groupby" + }, + "value": { + "aggregations": [], + "operation": "groupby" + } + } + } + } + ], + "type": "table" + }, + { + "datasource": { + "type": "victoriametrics-datasource", + "uid": "$ds" + }, + "description": "Missed evaluation means that group evaluation time takes longer than the configured evaluation interval. \nThis may result in missed alerting notifications or recording rules samples. Try increasing evaluation interval or concurrency for such groups. See https://docs.victoriametrics.com/vmalert/#groups\n\nIf rule expressions are taking longer than expected, please see https://docs.victoriametrics.com/troubleshooting/#slow-queries.\"", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "bars", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 27 + }, + "id": 58, + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "9.2.6", + "targets": [ + { + "datasource": { + "type": "victoriametrics-datasource", + "uid": "$ds" + }, + "editorMode": "code", + "exemplar": false, + "expr": "sum(increase(vmalert_iteration_missed_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by(job, group) > 0", + "interval": "1m", + "legendFormat": "__auto", + "range": true, + "refId": "A" + } + ], + "title": "Missed evaluations ($instance)", + "type": "timeseries" + }, + { + "datasource": { + "type": "victoriametrics-datasource", + "uid": "$ds" + }, + "description": "Shows the number of restarts per job. The chart can be useful to identify periodic process restarts and correlate them with potential issues or anomalies. Normally, processes shouldn't restart unless restart was inited by user. The reason of restarts should be figured out by checking the logs of each specific service. ", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "axisSoftMin": 0, + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "stepAfter", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "decimals": 0, + "links": [], + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "none" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 34 + }, + "id": 63, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "9.1.0", + "targets": [ + { + "datasource": { + "type": "victoriametrics-datasource", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(changes(vm_app_start_timestamp{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]) > 0) by(job)", + "format": "time_series", + "instant": false, + "legendFormat": "{{job}}", + "refId": "A" + } + ], + "title": "Restarts ($job)", + "type": "timeseries" + } + ], + "title": "Troubleshooting", + "type": "row" + }, { "collapsed": true, "datasource": { @@ -2298,7 +2421,7 @@ "h": 1, "w": 24, "x": 0, - "y": 33 + "y": 27 }, "id": 17, "panels": [ @@ -2364,7 +2487,7 @@ "h": 8, "w": 12, "x": 0, - "y": 44 + "y": 52 }, "id": 14, "options": { @@ -2466,7 +2589,7 @@ "h": 8, "w": 12, "x": 12, - "y": 44 + "y": 52 }, "id": 13, "options": { @@ -2568,7 +2691,7 @@ "h": 8, "w": 12, "x": 0, - "y": 52 + "y": 60 }, "id": 20, "options": { @@ -2671,7 +2794,7 @@ "h": 8, "w": 12, "x": 12, - "y": 52 + "y": 60 }, "id": 32, "options": { @@ -2770,7 +2893,7 @@ "h": 8, "w": 12, "x": 0, - "y": 60 + "y": 68 }, "id": 26, "options": { @@ -2831,7 +2954,7 @@ "h": 1, "w": 24, "x": 0, - "y": 34 + "y": 28 }, "id": 28, "panels": [ @@ -2897,7 +3020,7 @@ "h": 8, "w": 12, "x": 0, - "y": 59 + "y": 67 }, "id": 31, "options": { @@ -2999,7 +3122,7 @@ "h": 8, "w": 12, "x": 12, - "y": 59 + "y": 67 }, "id": 33, "options": { @@ -3100,7 +3223,7 @@ "h": 8, "w": 12, "x": 0, - "y": 67 + "y": 75 }, "id": 30, "options": { @@ -3157,7 +3280,7 @@ "h": 1, "w": 24, "x": 0, - "y": 35 + "y": 29 }, "id": 55, "panels": [ @@ -3221,7 +3344,7 @@ "h": 8, "w": 12, "x": 0, - "y": 25 + "y": 33 }, "id": 52, "options": { @@ -3313,7 +3436,7 @@ "h": 8, "w": 12, "x": 12, - "y": 25 + "y": 33 }, "id": 53, "options": { @@ -3410,7 +3533,7 @@ "h": 8, "w": 12, "x": 0, - "y": 52 + "y": 60 }, "id": 54, "options": { @@ -3513,7 +3636,7 @@ "h": 8, "w": 12, "x": 12, - "y": 52 + "y": 60 }, "id": 60, "options": { @@ -3566,8 +3689,8 @@ { "current": { "selected": false, - "text": "VictoriaMetrics", - "value": "P4169E866C3094E38" + "text": "VictoriaMetrics - cluster", + "value": "PAF93674D0B4E9963" }, "hide": 0, "includeAll": false, diff --git a/dashboards/vm/vmauth.json b/dashboards/vm/vmauth.json index b4a7d4012..5bc9d8b5b 100644 --- a/dashboards/vm/vmauth.json +++ b/dashboards/vm/vmauth.json @@ -1209,8 +1209,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -1226,7 +1225,7 @@ "h": 8, "w": 12, "x": 0, - "y": 11 + "y": 19 }, "id": 25, "options": { @@ -1315,8 +1314,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -1332,7 +1330,7 @@ "h": 8, "w": 12, "x": 12, - "y": 11 + "y": 19 }, "id": 26, "options": { @@ -1424,8 +1422,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -1441,7 +1438,7 @@ "h": 8, "w": 12, "x": 0, - "y": 19 + "y": 27 }, "id": 27, "options": { @@ -1581,8 +1578,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -1614,7 +1610,7 @@ "h": 8, "w": 12, "x": 12, - "y": 19 + "y": 27 }, "id": 28, "options": { @@ -1717,8 +1713,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -1734,7 +1729,7 @@ "h": 8, "w": 12, "x": 0, - "y": 27 + "y": 35 }, "id": 23, "options": { @@ -1823,8 +1818,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -1840,7 +1834,7 @@ "h": 8, "w": 12, "x": 12, - "y": 27 + "y": 35 }, "id": 24, "options": { @@ -1932,8 +1926,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -1965,7 +1958,7 @@ "h": 8, "w": 12, "x": 0, - "y": 35 + "y": 43 }, "id": 20, "options": { @@ -2057,8 +2050,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -2074,7 +2066,7 @@ "h": 8, "w": 12, "x": 12, - "y": 35 + "y": 43 }, "id": 21, "options": { @@ -2162,8 +2154,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -2179,7 +2170,7 @@ "h": 8, "w": 12, "x": 0, - "y": 43 + "y": 51 }, "id": 29, "options": { @@ -2453,6 +2444,111 @@ ], "title": "Log errors", "type": "timeseries" + }, + { + "datasource": { + "type": "victoriametrics-datasource", + "uid": "$ds" + }, + "description": "Shows the number of restarts per job. The chart can be useful to identify periodic process restarts and correlate them with potential issues or anomalies. Normally, processes shouldn't restart unless restart was inited by user. The reason of restarts should be figured out by checking the logs of each specific service. ", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "axisSoftMin": 0, + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "stepAfter", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "decimals": 0, + "links": [], + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "none" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 47 + }, + "id": 37, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "9.1.0", + "targets": [ + { + "datasource": { + "type": "victoriametrics-datasource", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(changes(vm_app_start_timestamp{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]) > 0) by(job)", + "format": "time_series", + "instant": false, + "legendFormat": "{{job}}", + "refId": "A" + } + ], + "title": "Restarts ($job)", + "type": "timeseries" } ], "title": "Troubleshooting", diff --git a/dashboards/vmagent.json b/dashboards/vmagent.json index 8fa8b9acd..1f2fb0312 100644 --- a/dashboards/vmagent.json +++ b/dashboards/vmagent.json @@ -1335,8 +1335,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -1439,8 +1438,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -1618,7 +1616,8 @@ "mode": "absolute", "steps": [ { - "color": "green" + "color": "green", + "value": null }, { "color": "red", @@ -1634,7 +1633,7 @@ "h": 8, "w": 12, "x": 0, - "y": 35 + "y": 3 }, "id": 109, "options": { @@ -1749,7 +1748,7 @@ "h": 8, "w": 12, "x": 12, - "y": 35 + "y": 3 }, "id": 111, "options": { @@ -1874,7 +1873,7 @@ "h": 8, "w": 12, "x": 0, - "y": 43 + "y": 11 }, "id": 81, "options": { @@ -2010,7 +2009,7 @@ "h": 8, "w": 12, "x": 12, - "y": 43 + "y": 11 }, "id": 7, "options": { @@ -2129,7 +2128,7 @@ "h": 8, "w": 12, "x": 0, - "y": 51 + "y": 19 }, "id": 83, "options": { @@ -2235,7 +2234,7 @@ "h": 8, "w": 12, "x": 12, - "y": 51 + "y": 19 }, "id": 39, "options": { @@ -2342,7 +2341,7 @@ "h": 8, "w": 12, "x": 0, - "y": 59 + "y": 27 }, "id": 135, "options": { @@ -2449,7 +2448,7 @@ "h": 8, "w": 12, "x": 12, - "y": 59 + "y": 27 }, "id": 149, "options": { @@ -2555,7 +2554,7 @@ "h": 8, "w": 12, "x": 12, - "y": 67 + "y": 35 }, "id": 41, "options": { @@ -2668,7 +2667,8 @@ "mode": "absolute", "steps": [ { - "color": "green" + "color": "green", + "value": null }, { "color": "red", @@ -2684,7 +2684,7 @@ "h": 8, "w": 12, "x": 0, - "y": 20 + "y": 4 }, "id": 92, "options": { @@ -2772,7 +2772,8 @@ "mode": "absolute", "steps": [ { - "color": "green" + "color": "green", + "value": null }, { "color": "red", @@ -2788,7 +2789,7 @@ "h": 8, "w": 12, "x": 12, - "y": 20 + "y": 4 }, "id": 95, "options": { @@ -2879,7 +2880,8 @@ "mode": "absolute", "steps": [ { - "color": "transparent" + "color": "transparent", + "value": null }, { "color": "red", @@ -2895,7 +2897,7 @@ "h": 8, "w": 12, "x": 0, - "y": 28 + "y": 12 }, "id": 98, "options": { @@ -2986,7 +2988,8 @@ "mode": "absolute", "steps": [ { - "color": "transparent" + "color": "transparent", + "value": null }, { "color": "red", @@ -3002,7 +3005,7 @@ "h": 8, "w": 12, "x": 12, - "y": 28 + "y": 12 }, "id": 99, "options": { @@ -3054,6 +3057,7 @@ "mode": "palette-classic" }, "custom": { + "axisBorderShow": false, "axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", @@ -3067,6 +3071,7 @@ "tooltip": false, "viz": false }, + "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 1, "pointSize": 5, @@ -3090,7 +3095,8 @@ "mode": "absolute", "steps": [ { - "color": "green" + "color": "green", + "value": null }, { "color": "red", @@ -3106,7 +3112,7 @@ "h": 8, "w": 12, "x": 0, - "y": 36 + "y": 20 }, "id": 79, "options": { @@ -3158,6 +3164,7 @@ "mode": "palette-classic" }, "custom": { + "axisBorderShow": false, "axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", @@ -3171,6 +3178,7 @@ "tooltip": false, "viz": false }, + "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 1, "pointSize": 5, @@ -3194,7 +3202,8 @@ "mode": "absolute", "steps": [ { - "color": "green" + "color": "green", + "value": null }, { "color": "red", @@ -3210,7 +3219,7 @@ "h": 8, "w": 12, "x": 12, - "y": 36 + "y": 20 }, "id": 18, "links": [ @@ -3268,6 +3277,7 @@ "mode": "palette-classic" }, "custom": { + "axisBorderShow": false, "axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", @@ -3281,6 +3291,7 @@ "tooltip": false, "viz": false }, + "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 1, "pointSize": 5, @@ -3304,7 +3315,8 @@ "mode": "absolute", "steps": [ { - "color": "green" + "color": "green", + "value": null }, { "color": "red", @@ -3320,7 +3332,7 @@ "h": 8, "w": 12, "x": 0, - "y": 44 + "y": 28 }, "id": 127, "options": { @@ -3370,6 +3382,7 @@ "mode": "palette-classic" }, "custom": { + "axisBorderShow": false, "axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", @@ -3383,6 +3396,7 @@ "tooltip": false, "viz": false }, + "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 1, "pointSize": 5, @@ -3406,7 +3420,8 @@ "mode": "absolute", "steps": [ { - "color": "green" + "color": "green", + "value": null }, { "color": "red", @@ -3422,7 +3437,7 @@ "h": 8, "w": 12, "x": 12, - "y": 44 + "y": 28 }, "id": 50, "options": { @@ -3482,7 +3497,8 @@ "mode": "absolute", "steps": [ { - "color": "green" + "color": "green", + "value": null }, { "color": "red", @@ -3520,13 +3536,15 @@ }, "gridPos": { "h": 7, - "w": 24, + "w": 12, "x": 0, - "y": 52 + "y": 36 }, "id": 129, "options": { + "cellHeight": "sm", "footer": { + "countRows": false, "fields": "", "reducer": [ "sum" @@ -3541,7 +3559,7 @@ } ] }, - "pluginVersion": "9.2.6", + "pluginVersion": "10.4.2", "targets": [ { "datasource": { @@ -3584,6 +3602,111 @@ } ], "type": "table" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows the number of restarts per job. The chart can be useful to identify periodic process restarts and correlate them with potential issues or anomalies. Normally, processes shouldn't restart unless restart was inited by user. The reason of restarts should be figured out by checking the logs of each specific service. ", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "axisSoftMin": 0, + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "stepAfter", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "decimals": 0, + "links": [], + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "none" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 36 + }, + "id": 150, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "9.1.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(changes(vm_app_start_timestamp{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]) > 0) by(job)", + "format": "time_series", + "instant": false, + "legendFormat": "{{job}}", + "refId": "A" + } + ], + "title": "Restarts ($job)", + "type": "timeseries" } ], "targets": [ @@ -3677,7 +3800,7 @@ "h": 7, "w": 12, "x": 0, - "y": 45 + "y": 53 }, "id": 48, "options": { @@ -3783,7 +3906,7 @@ "h": 7, "w": 12, "x": 12, - "y": 45 + "y": 53 }, "id": 76, "options": { @@ -3887,7 +4010,7 @@ "h": 7, "w": 12, "x": 0, - "y": 52 + "y": 60 }, "id": 132, "options": { @@ -3993,7 +4116,7 @@ "h": 7, "w": 12, "x": 12, - "y": 52 + "y": 60 }, "id": 133, "options": { @@ -4098,7 +4221,7 @@ "h": 8, "w": 12, "x": 0, - "y": 59 + "y": 67 }, "id": 20, "options": { @@ -4202,7 +4325,7 @@ "h": 8, "w": 12, "x": 12, - "y": 59 + "y": 67 }, "id": 126, "options": { @@ -4305,7 +4428,7 @@ "h": 8, "w": 12, "x": 0, - "y": 67 + "y": 75 }, "id": 46, "options": { @@ -4408,7 +4531,7 @@ "h": 8, "w": 12, "x": 12, - "y": 67 + "y": 75 }, "id": 148, "options": { @@ -4511,7 +4634,7 @@ "h": 8, "w": 12, "x": 12, - "y": 75 + "y": 83 }, "id": 31, "options": { @@ -4690,7 +4813,7 @@ "h": 8, "w": 12, "x": 0, - "y": 22 + "y": 30 }, "id": 73, "options": { @@ -4807,7 +4930,7 @@ "h": 8, "w": 12, "x": 12, - "y": 14 + "y": 22 }, "id": 131, "options": { @@ -4911,7 +5034,7 @@ "h": 8, "w": 12, "x": 0, - "y": 22 + "y": 30 }, "id": 130, "options": { @@ -5028,7 +5151,7 @@ "h": 8, "w": 12, "x": 12, - "y": 22 + "y": 30 }, "id": 77, "options": { @@ -5162,7 +5285,7 @@ "h": 8, "w": 12, "x": 0, - "y": 15 + "y": 23 }, "id": 146, "options": { @@ -5264,7 +5387,7 @@ "h": 8, "w": 12, "x": 12, - "y": 15 + "y": 23 }, "id": 143, "options": { @@ -5360,7 +5483,7 @@ "h": 8, "w": 12, "x": 0, - "y": 23 + "y": 31 }, "id": 147, "options": { @@ -5463,7 +5586,7 @@ "h": 8, "w": 12, "x": 12, - "y": 23 + "y": 31 }, "id": 139, "options": { @@ -5574,7 +5697,7 @@ "h": 8, "w": 12, "x": 0, - "y": 31 + "y": 39 }, "id": 142, "options": { @@ -5671,7 +5794,7 @@ "h": 8, "w": 12, "x": 12, - "y": 31 + "y": 39 }, "id": 137, "options": { @@ -5784,7 +5907,7 @@ "h": 8, "w": 12, "x": 12, - "y": 39 + "y": 47 }, "id": 141, "options": { @@ -5915,7 +6038,7 @@ "h": 8, "w": 12, "x": 0, - "y": 16 + "y": 24 }, "id": 60, "options": { @@ -6019,7 +6142,7 @@ "h": 8, "w": 12, "x": 12, - "y": 16 + "y": 24 }, "id": 66, "options": { @@ -6123,7 +6246,7 @@ "h": 8, "w": 12, "x": 0, - "y": 24 + "y": 32 }, "id": 61, "options": { @@ -6227,7 +6350,7 @@ "h": 8, "w": 12, "x": 12, - "y": 24 + "y": 32 }, "id": 65, "options": { @@ -6330,7 +6453,7 @@ "h": 8, "w": 12, "x": 0, - "y": 32 + "y": 40 }, "id": 88, "options": { @@ -6429,7 +6552,7 @@ "h": 8, "w": 12, "x": 12, - "y": 32 + "y": 40 }, "id": 84, "options": { @@ -6532,7 +6655,7 @@ "h": 8, "w": 12, "x": 0, - "y": 40 + "y": 48 }, "id": 90, "options": { @@ -6598,7 +6721,7 @@ "h": 2, "w": 24, "x": 0, - "y": 25 + "y": 33 }, "id": 115, "options": { @@ -6676,7 +6799,7 @@ "h": 8, "w": 12, "x": 0, - "y": 27 + "y": 35 }, "id": 119, "options": { @@ -6780,7 +6903,7 @@ "h": 8, "w": 12, "x": 12, - "y": 27 + "y": 35 }, "id": 117, "options": { @@ -6886,7 +7009,7 @@ "h": 8, "w": 12, "x": 0, - "y": 35 + "y": 43 }, "id": 125, "links": [ @@ -7008,7 +7131,7 @@ "h": 8, "w": 12, "x": 12, - "y": 35 + "y": 43 }, "id": 123, "options": { @@ -7138,7 +7261,7 @@ "h": 8, "w": 12, "x": 0, - "y": 43 + "y": 51 }, "id": 121, "options": { @@ -7211,8 +7334,8 @@ { "current": { "selected": false, - "text": "VictoriaMetrics", - "value": "P4169E866C3094E38" + "text": "VictoriaMetrics - cluster", + "value": "PAF93674D0B4E9963" }, "hide": 0, "includeAll": false, @@ -7337,4 +7460,4 @@ "uid": "G7Z9GzMGz", "version": 1, "weekStart": "" -} +} \ No newline at end of file diff --git a/dashboards/vmalert.json b/dashboards/vmalert.json index 405f438b0..929b9b2bb 100644 --- a/dashboards/vmalert.json +++ b/dashboards/vmalert.json @@ -1125,234 +1125,6 @@ "title": "Rules execution errors ($instance)", "type": "timeseries" }, - { - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "fieldConfig": { - "defaults": { - "color": { - "mode": "thresholds" - }, - "custom": { - "align": "auto", - "cellOptions": { - "type": "auto" - }, - "inspect": false - }, - "mappings": [], - "thresholds": { - "mode": "absolute", - "steps": [ - { - "color": "green" - }, - { - "color": "red", - "value": 80 - } - ] - } - }, - "overrides": [ - { - "matcher": { - "id": "byName", - "options": "Value" - }, - "properties": [ - { - "id": "custom.hidden", - "value": true - } - ] - }, - { - "matcher": { - "id": "byName", - "options": "Time" - }, - "properties": [ - { - "id": "custom.hidden", - "value": true - } - ] - } - ] - }, - "gridPos": { - "h": 7, - "w": 12, - "x": 0, - "y": 25 - }, - "id": 50, - "options": { - "footer": { - "fields": "", - "reducer": [ - "sum" - ], - "show": false - }, - "showHeader": true, - "sortBy": [ - { - "desc": true, - "displayName": "job" - } - ] - }, - "pluginVersion": "9.2.7", - "targets": [ - { - "datasource": { - "type": "prometheus", - "uid": "$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": [ - "uniqueValues" - ], - "operation": "aggregate" - }, - "job": { - "aggregations": [], - "operation": "groupby" - }, - "name": { - "aggregations": [], - "operation": "groupby" - }, - "value": { - "aggregations": [], - "operation": "groupby" - } - } - } - } - ], - "type": "table" - }, - { - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "description": "Missed evaluation means that group evaluation time takes longer than the configured evaluation interval. \nThis may result in missed alerting notifications or recording rules samples. Try increasing evaluation interval or concurrency for such groups. See https://docs.victoriametrics.com/vmalert/#groups\n\nIf rule expressions are taking longer than expected, please see https://docs.victoriametrics.com/troubleshooting/#slow-queries.\"", - "fieldConfig": { - "defaults": { - "color": { - "mode": "palette-classic" - }, - "custom": { - "axisCenteredZero": false, - "axisColorMode": "text", - "axisLabel": "", - "axisPlacement": "auto", - "barAlignment": 0, - "drawStyle": "bars", - "fillOpacity": 10, - "gradientMode": "none", - "hideFrom": { - "legend": false, - "tooltip": false, - "viz": false - }, - "lineInterpolation": "linear", - "lineWidth": 1, - "pointSize": 5, - "scaleDistribution": { - "type": "linear" - }, - "showPoints": "never", - "spanNulls": false, - "stacking": { - "group": "A", - "mode": "none" - }, - "thresholdsStyle": { - "mode": "off" - } - }, - "mappings": [], - "thresholds": { - "mode": "absolute", - "steps": [ - { - "color": "green" - }, - { - "color": "red", - "value": 80 - } - ] - }, - "unit": "short" - }, - "overrides": [] - }, - "gridPos": { - "h": 7, - "w": 12, - "x": 12, - "y": 25 - }, - "id": 58, - "options": { - "legend": { - "calcs": [ - "mean", - "lastNotNull", - "max" - ], - "displayMode": "table", - "placement": "bottom", - "showLegend": true - }, - "tooltip": { - "mode": "multi", - "sort": "none" - } - }, - "pluginVersion": "9.2.6", - "targets": [ - { - "datasource": { - "type": "prometheus", - "uid": "$ds" - }, - "editorMode": "code", - "exemplar": false, - "expr": "sum(increase(vmalert_iteration_missed_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by(job, group) > 0", - "interval": "1m", - "legendFormat": "__auto", - "range": true, - "refId": "A" - } - ], - "title": "Missed evaluations ($instance)", - "type": "timeseries" - }, { "collapsed": true, "datasource": { @@ -1363,7 +1135,7 @@ "h": 1, "w": 24, "x": 0, - "y": 32 + "y": 25 }, "id": 43, "panels": [ @@ -1434,7 +1206,7 @@ "h": 8, "w": 12, "x": 0, - "y": 3 + "y": 11 }, "id": 37, "links": [ @@ -1531,8 +1303,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -1548,7 +1319,7 @@ "h": 8, "w": 12, "x": 12, - "y": 3 + "y": 11 }, "id": 57, "links": [ @@ -1662,7 +1433,7 @@ "h": 8, "w": 12, "x": 0, - "y": 11 + "y": 19 }, "id": 35, "links": [ @@ -1778,7 +1549,7 @@ "h": 8, "w": 12, "x": 12, - "y": 11 + "y": 19 }, "id": 56, "links": [ @@ -1911,7 +1682,7 @@ "h": 8, "w": 12, "x": 0, - "y": 19 + "y": 27 }, "id": 39, "links": [], @@ -2019,7 +1790,7 @@ "h": 8, "w": 12, "x": 12, - "y": 19 + "y": 27 }, "id": 41, "links": [], @@ -2127,7 +1898,7 @@ "h": 8, "w": 12, "x": 0, - "y": 27 + "y": 35 }, "id": 59, "links": [], @@ -2218,8 +1989,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -2235,7 +2005,7 @@ "h": 8, "w": 12, "x": 12, - "y": 27 + "y": 35 }, "id": 61, "options": { @@ -2287,6 +2057,359 @@ "title": "Resource usage", "type": "row" }, + { + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 26 + }, + "id": 62, + "panels": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "custom": { + "align": "auto", + "cellOptions": { + "type": "auto" + }, + "inspect": false + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "Value" + }, + "properties": [ + { + "id": "custom.hidden", + "value": true + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Time" + }, + "properties": [ + { + "id": "custom.hidden", + "value": true + } + ] + } + ] + }, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 27 + }, + "id": 50, + "options": { + "cellHeight": "sm", + "footer": { + "countRows": false, + "fields": "", + "reducer": [ + "sum" + ], + "show": false + }, + "showHeader": true, + "sortBy": [ + { + "desc": true, + "displayName": "job" + } + ] + }, + "pluginVersion": "10.4.2", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$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": [ + "uniqueValues" + ], + "operation": "aggregate" + }, + "job": { + "aggregations": [], + "operation": "groupby" + }, + "name": { + "aggregations": [], + "operation": "groupby" + }, + "value": { + "aggregations": [], + "operation": "groupby" + } + } + } + } + ], + "type": "table" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Missed evaluation means that group evaluation time takes longer than the configured evaluation interval. \nThis may result in missed alerting notifications or recording rules samples. Try increasing evaluation interval or concurrency for such groups. See https://docs.victoriametrics.com/vmalert/#groups\n\nIf rule expressions are taking longer than expected, please see https://docs.victoriametrics.com/troubleshooting/#slow-queries.\"", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "bars", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 27 + }, + "id": 58, + "options": { + "legend": { + "calcs": [ + "mean", + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "9.2.6", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "exemplar": false, + "expr": "sum(increase(vmalert_iteration_missed_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by(job, group) > 0", + "interval": "1m", + "legendFormat": "__auto", + "range": true, + "refId": "A" + } + ], + "title": "Missed evaluations ($instance)", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows the number of restarts per job. The chart can be useful to identify periodic process restarts and correlate them with potential issues or anomalies. Normally, processes shouldn't restart unless restart was inited by user. The reason of restarts should be figured out by checking the logs of each specific service. ", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "axisSoftMin": 0, + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "stepAfter", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "decimals": 0, + "links": [], + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "none" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 34 + }, + "id": 63, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "9.1.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(changes(vm_app_start_timestamp{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]) > 0) by(job)", + "format": "time_series", + "instant": false, + "legendFormat": "{{job}}", + "refId": "A" + } + ], + "title": "Restarts ($job)", + "type": "timeseries" + } + ], + "title": "Troubleshooting", + "type": "row" + }, { "collapsed": true, "datasource": { @@ -2297,7 +2420,7 @@ "h": 1, "w": 24, "x": 0, - "y": 33 + "y": 27 }, "id": 17, "panels": [ @@ -2363,7 +2486,7 @@ "h": 8, "w": 12, "x": 0, - "y": 44 + "y": 52 }, "id": 14, "options": { @@ -2465,7 +2588,7 @@ "h": 8, "w": 12, "x": 12, - "y": 44 + "y": 52 }, "id": 13, "options": { @@ -2567,7 +2690,7 @@ "h": 8, "w": 12, "x": 0, - "y": 52 + "y": 60 }, "id": 20, "options": { @@ -2670,7 +2793,7 @@ "h": 8, "w": 12, "x": 12, - "y": 52 + "y": 60 }, "id": 32, "options": { @@ -2769,7 +2892,7 @@ "h": 8, "w": 12, "x": 0, - "y": 60 + "y": 68 }, "id": 26, "options": { @@ -2830,7 +2953,7 @@ "h": 1, "w": 24, "x": 0, - "y": 34 + "y": 28 }, "id": 28, "panels": [ @@ -2896,7 +3019,7 @@ "h": 8, "w": 12, "x": 0, - "y": 59 + "y": 67 }, "id": 31, "options": { @@ -2998,7 +3121,7 @@ "h": 8, "w": 12, "x": 12, - "y": 59 + "y": 67 }, "id": 33, "options": { @@ -3099,7 +3222,7 @@ "h": 8, "w": 12, "x": 0, - "y": 67 + "y": 75 }, "id": 30, "options": { @@ -3156,7 +3279,7 @@ "h": 1, "w": 24, "x": 0, - "y": 35 + "y": 29 }, "id": 55, "panels": [ @@ -3220,7 +3343,7 @@ "h": 8, "w": 12, "x": 0, - "y": 25 + "y": 33 }, "id": 52, "options": { @@ -3312,7 +3435,7 @@ "h": 8, "w": 12, "x": 12, - "y": 25 + "y": 33 }, "id": 53, "options": { @@ -3409,7 +3532,7 @@ "h": 8, "w": 12, "x": 0, - "y": 52 + "y": 60 }, "id": 54, "options": { @@ -3512,7 +3635,7 @@ "h": 8, "w": 12, "x": 12, - "y": 52 + "y": 60 }, "id": 60, "options": { @@ -3565,8 +3688,8 @@ { "current": { "selected": false, - "text": "VictoriaMetrics", - "value": "P4169E866C3094E38" + "text": "VictoriaMetrics - cluster", + "value": "PAF93674D0B4E9963" }, "hide": 0, "includeAll": false, diff --git a/dashboards/vmauth.json b/dashboards/vmauth.json index c34ef9a8b..e81692876 100644 --- a/dashboards/vmauth.json +++ b/dashboards/vmauth.json @@ -1208,8 +1208,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -1225,7 +1224,7 @@ "h": 8, "w": 12, "x": 0, - "y": 11 + "y": 19 }, "id": 25, "options": { @@ -1314,8 +1313,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -1331,7 +1329,7 @@ "h": 8, "w": 12, "x": 12, - "y": 11 + "y": 19 }, "id": 26, "options": { @@ -1423,8 +1421,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -1440,7 +1437,7 @@ "h": 8, "w": 12, "x": 0, - "y": 19 + "y": 27 }, "id": 27, "options": { @@ -1580,8 +1577,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -1613,7 +1609,7 @@ "h": 8, "w": 12, "x": 12, - "y": 19 + "y": 27 }, "id": 28, "options": { @@ -1716,8 +1712,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -1733,7 +1728,7 @@ "h": 8, "w": 12, "x": 0, - "y": 27 + "y": 35 }, "id": 23, "options": { @@ -1822,8 +1817,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -1839,7 +1833,7 @@ "h": 8, "w": 12, "x": 12, - "y": 27 + "y": 35 }, "id": 24, "options": { @@ -1931,8 +1925,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -1964,7 +1957,7 @@ "h": 8, "w": 12, "x": 0, - "y": 35 + "y": 43 }, "id": 20, "options": { @@ -2056,8 +2049,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -2073,7 +2065,7 @@ "h": 8, "w": 12, "x": 12, - "y": 35 + "y": 43 }, "id": 21, "options": { @@ -2161,8 +2153,7 @@ "mode": "absolute", "steps": [ { - "color": "green", - "value": null + "color": "green" }, { "color": "red", @@ -2178,7 +2169,7 @@ "h": 8, "w": 12, "x": 0, - "y": 43 + "y": 51 }, "id": 29, "options": { @@ -2452,6 +2443,111 @@ ], "title": "Log errors", "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows the number of restarts per job. The chart can be useful to identify periodic process restarts and correlate them with potential issues or anomalies. Normally, processes shouldn't restart unless restart was inited by user. The reason of restarts should be figured out by checking the logs of each specific service. ", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "axisSoftMin": 0, + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "stepAfter", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "decimals": 0, + "links": [], + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "none" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 47 + }, + "id": 37, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "9.1.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(changes(vm_app_start_timestamp{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]) > 0) by(job)", + "format": "time_series", + "instant": false, + "legendFormat": "{{job}}", + "refId": "A" + } + ], + "title": "Restarts ($job)", + "type": "timeseries" } ], "title": "Troubleshooting", diff --git a/docs/changelog/CHANGELOG.md b/docs/changelog/CHANGELOG.md index 0eda6364c..551f983db 100644 --- a/docs/changelog/CHANGELOG.md +++ b/docs/changelog/CHANGELOG.md @@ -22,6 +22,7 @@ See also [LTS releases](https://docs.victoriametrics.com/lts-releases/). * FEATURE: [vmalert](https://docs.victoriametrics.com/vmalert/): `-rule` cmd-line flag now supports multi-document YAML files. This could be useful when rules are retrieved via HTTP URL where multiple rule files were merged together in one response. See [this issue](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/6753). Thanks to @Irene-123 for [the pull request](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6995). * FEATURE: [vmagent](https://docs.victoriametrics.com/vmagent/): support scraping from Kubernetes Native Sidecars. See [this issue](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/7287). * FEATURE: [Single-node VictoriaMetrics](https://docs.victoriametrics.com/) and `vmstorage` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/cluster-victoriametrics/): add a separate cache type for storing sparse entries when performing large index scans. This significantly reduces memory usage when applying [downsampling filters](https://docs.victoriametrics.com/#downsampling) and [retention filters](https://docs.victoriametrics.com/#retention-filters) during background merge. See [this issue](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/7182) for the details. +* FEATURE: [dashboards](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/dashboards) for VM single-node, cluster, vmalert, vmagent, VictoriaLogs: add `Restarts` panel to show the events of process restarts. This panel should help correlate events of restart with unexpected behavior of processes. * BUGFIX: [dashboards](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/dashboards) for Single-node VictoriaMetrics, cluster: The free disk space calculation now will subtract the size of the `-storage.minFreeDiskSpaceBytes` flag to correctly display the remaining available space of Single-node VictoriaMetrics/vmstorage rather than the actual available disk space, as well as the full ETA. See [this issue](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/7334) for the details. * BUGFIX: [vmalert](https://docs.victoriametrics.com/vmalert): properly set `group_name` and `file` fields for recording rules in `/api/v1/rules`.