CoCalc -- node-problem-detector.json

GitHub Repository: gitpod-io/gitpod
Path: blob/main/operations/observability/mixins/workspace/dashboards/node-problem-detector.json
²⁵⁰¹ views
1
{
2
  "annotations": {
3
    "list": [
4
      {
5
        "builtIn": 1,
6
        "datasource": {
7
          "type": "datasource",
8
          "uid": "grafana"
9
        },
10
        "enable": true,
11
        "hide": true,
12
        "iconColor": "rgba(0, 211, 255, 1)",
13
        "name": "Annotations & Alerts",
14
        "target": {
15
          "limit": 100,
16
          "matchAny": false,
17
          "tags": [],
18
          "type": "dashboard"
19
        },
20
        "type": "dashboard"
21
      }
22
    ]
23
  },
24
  "description": "",
25
  "editable": true,
26
  "fiscalYearStartMonth": 0,
27
  "graphTooltip": 1,
28
  "id": 71,
29
  "links": [],
30
  "liveNow": false,
31
  "panels": [
32
    {
33
      "collapsed": false,
34
      "datasource": {
35
        "type": "datasource",
36
        "uid": "grafana"
37
      },
38
      "gridPos": {
39
        "h": 1,
40
        "w": 24,
41
        "x": 0,
42
        "y": 0
43
      },
44
      "id": 4,
45
      "panels": [],
46
      "targets": [
47
        {
48
          "datasource": {
49
            "type": "datasource",
50
            "uid": "grafana"
51
          },
52
          "refId": "A"
53
        }
54
      ],
55
      "title": "Totals",
56
      "type": "row"
57
    },
58
    {
59
      "datasource": {
60
        "type": "prometheus",
61
        "uid": "${datasource}"
62
      },
63
      "fieldConfig": {
64
        "defaults": {
65
          "color": {
66
            "mode": "palette-classic"
67
          },
68
          "custom": {
69
            "axisLabel": "",
70
            "axisPlacement": "auto",
71
            "barAlignment": 0,
72
            "drawStyle": "line",
73
            "fillOpacity": 0,
74
            "gradientMode": "none",
75
            "hideFrom": {
76
              "legend": false,
77
              "tooltip": false,
78
              "viz": false
79
            },
80
            "lineInterpolation": "linear",
81
            "lineWidth": 1,
82
            "pointSize": 5,
83
            "scaleDistribution": {
84
              "type": "linear"
85
            },
86
            "showPoints": "auto",
87
            "spanNulls": false,
88
            "stacking": {
89
              "group": "A",
90
              "mode": "none"
91
            },
92
            "thresholdsStyle": {
93
              "mode": "off"
94
            }
95
          },
96
          "mappings": [],
97
          "min": 0,
98
          "thresholds": {
99
            "mode": "absolute",
100
            "steps": [
101
              {
102
                "color": "green",
103
                "value": null
104
              },
105
              {
106
                "color": "red",
107
                "value": 80
108
              }
109
            ]
110
          }
111
        },
112
        "overrides": []
113
      },
114
      "gridPos": {
115
        "h": 6,
116
        "w": 8,
117
        "x": 0,
118
        "y": 1
119
      },
120
      "id": 40,
121
      "options": {
122
        "legend": {
123
          "calcs": [],
124
          "displayMode": "hidden",
125
          "placement": "bottom"
126
        },
127
        "tooltip": {
128
          "mode": "single",
129
          "sort": "none"
130
        }
131
      },
132
      "targets": [
133
        {
134
          "datasource": {
135
            "type": "prometheus",
136
            "uid": "${datasource}"
137
          },
138
          "exemplar": true,
139
          "expr": " sum(problem_gauge) by (node)",
140
          "interval": "",
141
          "legendFormat": "{{node}}",
142
          "refId": "A"
143
        }
144
      ],
145
      "title": "Problem affects a node",
146
      "type": "timeseries"
147
    },
148
    {
149
      "datasource": {
150
        "type": "prometheus",
151
        "uid": "${datasource}"
152
      },
153
      "fieldConfig": {
154
        "defaults": {
155
          "color": {
156
            "mode": "palette-classic"
157
          },
158
          "custom": {
159
            "axisLabel": "",
160
            "axisPlacement": "auto",
161
            "barAlignment": 0,
162
            "drawStyle": "line",
163
            "fillOpacity": 0,
164
            "gradientMode": "none",
165
            "hideFrom": {
166
              "legend": false,
167
              "tooltip": false,
168
              "viz": false
169
            },
170
            "lineInterpolation": "linear",
171
            "lineWidth": 1,
172
            "pointSize": 5,
173
            "scaleDistribution": {
174
              "type": "linear"
175
            },
176
            "showPoints": "auto",
177
            "spanNulls": false,
178
            "stacking": {
179
              "group": "A",
180
              "mode": "none"
181
            },
182
            "thresholdsStyle": {
183
              "mode": "off"
184
            }
185
          },
186
          "mappings": [],
187
          "min": 0,
188
          "thresholds": {
189
            "mode": "absolute",
190
            "steps": [
191
              {
192
                "color": "green",
193
                "value": null
194
              },
195
              {
196
                "color": "red",
197
                "value": 80
198
              }
199
            ]
200
          }
201
        },
202
        "overrides": []
203
      },
204
      "gridPos": {
205
        "h": 6,
206
        "w": 8,
207
        "x": 8,
208
        "y": 1
209
      },
210
      "id": 23,
211
      "options": {
212
        "legend": {
213
          "calcs": [],
214
          "displayMode": "hidden",
215
          "placement": "bottom"
216
        },
217
        "tooltip": {
218
          "mode": "single",
219
          "sort": "none"
220
        }
221
      },
222
      "targets": [
223
        {
224
          "datasource": {
225
            "type": "prometheus",
226
            "uid": "${datasource}"
227
          },
228
          "exemplar": true,
229
          "expr": "sum(rate(problem_counter[5m])) by (node)",
230
          "interval": "",
231
          "legendFormat": "{{node}}",
232
          "refId": "A"
233
        }
234
      ],
235
      "title": "Problem rates by node",
236
      "type": "timeseries"
237
    },
238
    {
239
      "datasource": {
240
        "type": "prometheus",
241
        "uid": "${datasource}"
242
      },
243
      "fieldConfig": {
244
        "defaults": {
245
          "color": {
246
            "mode": "palette-classic"
247
          },
248
          "custom": {
249
            "axisLabel": "",
250
            "axisPlacement": "auto",
251
            "barAlignment": 0,
252
            "drawStyle": "line",
253
            "fillOpacity": 0,
254
            "gradientMode": "none",
255
            "hideFrom": {
256
              "legend": false,
257
              "tooltip": false,
258
              "viz": false
259
            },
260
            "lineInterpolation": "linear",
261
            "lineWidth": 1,
262
            "pointSize": 5,
263
            "scaleDistribution": {
264
              "type": "linear"
265
            },
266
            "showPoints": "auto",
267
            "spanNulls": false,
268
            "stacking": {
269
              "group": "A",
270
              "mode": "none"
271
            },
272
            "thresholdsStyle": {
273
              "mode": "off"
274
            }
275
          },
276
          "mappings": [],
277
          "thresholds": {
278
            "mode": "absolute",
279
            "steps": [
280
              {
281
                "color": "green",
282
                "value": null
283
              },
284
              {
285
                "color": "red",
286
                "value": 80
287
              }
288
            ]
289
          }
290
        },
291
        "overrides": []
292
      },
293
      "gridPos": {
294
        "h": 6,
295
        "w": 8,
296
        "x": 16,
297
        "y": 1
298
      },
299
      "id": 2,
300
      "options": {
301
        "legend": {
302
          "calcs": [],
303
          "displayMode": "hidden",
304
          "placement": "bottom"
305
        },
306
        "tooltip": {
307
          "mode": "single",
308
          "sort": "none"
309
        }
310
      },
311
      "targets": [
312
        {
313
          "datasource": {
314
            "type": "prometheus",
315
            "uid": "${datasource}"
316
          },
317
          "exemplar": true,
318
          "expr": "sum(rate(problem_counter[5m]))",
319
          "interval": "",
320
          "legendFormat": "total",
321
          "refId": "A"
322
        }
323
      ],
324
      "title": "Problem rates",
325
      "type": "timeseries"
326
    },
327
    {
328
      "collapsed": false,
329
      "datasource": {
330
        "type": "datasource",
331
        "uid": "grafana"
332
      },
333
      "gridPos": {
334
        "h": 1,
335
        "w": 24,
336
        "x": 0,
337
        "y": 7
338
      },
339
      "id": 25,
340
      "panels": [],
341
      "targets": [
342
        {
343
          "datasource": {
344
            "type": "datasource",
345
            "uid": "grafana"
346
          },
347
          "refId": "A"
348
        }
349
      ],
350
      "title": "Gauges",
351
      "type": "row"
352
    },
353
    {
354
      "datasource": {
355
        "type": "prometheus",
356
        "uid": "${datasource}"
357
      },
358
      "fieldConfig": {
359
        "defaults": {
360
          "color": {
361
            "mode": "palette-classic"
362
          },
363
          "custom": {
364
            "axisLabel": "",
365
            "axisPlacement": "auto",
366
            "barAlignment": 0,
367
            "drawStyle": "line",
368
            "fillOpacity": 0,
369
            "gradientMode": "none",
370
            "hideFrom": {
371
              "legend": false,
372
              "tooltip": false,
373
              "viz": false
374
            },
375
            "lineInterpolation": "linear",
376
            "lineWidth": 1,
377
            "pointSize": 5,
378
            "scaleDistribution": {
379
              "type": "linear"
380
            },
381
            "showPoints": "auto",
382
            "spanNulls": false,
383
            "stacking": {
384
              "group": "A",
385
              "mode": "none"
386
            },
387
            "thresholdsStyle": {
388
              "mode": "off"
389
            }
390
          },
391
          "mappings": [],
392
          "thresholds": {
393
            "mode": "absolute",
394
            "steps": [
395
              {
396
                "color": "green",
397
                "value": null
398
              },
399
              {
400
                "color": "red",
401
                "value": 80
402
              }
403
            ]
404
          }
405
        },
406
        "overrides": []
407
      },
408
      "gridPos": {
409
        "h": 5,
410
        "w": 8,
411
        "x": 0,
412
        "y": 8
413
      },
414
      "id": 8,
415
      "maxPerRow": 4,
416
      "options": {
417
        "legend": {
418
          "calcs": [],
419
          "displayMode": "hidden",
420
          "placement": "bottom"
421
        },
422
        "tooltip": {
423
          "mode": "single",
424
          "sort": "none"
425
        }
426
      },
427
      "repeat": "problem_type",
428
      "repeatDirection": "h",
429
      "targets": [
430
        {
431
          "datasource": {
432
            "type": "prometheus",
433
            "uid": "${datasource}"
434
          },
435
          "exemplar": true,
436
          "expr": "sum(problem_gauge{type=~\"$problem_type\"})",
437
          "interval": "",
438
          "legendFormat": "$problem_type",
439
          "refId": "A"
440
        }
441
      ],
442
      "title": "Problem Type - $problem_type",
443
      "type": "timeseries"
444
    },
445
    {
446
      "collapsed": false,
447
      "datasource": {
448
        "type": "datasource",
449
        "uid": "grafana"
450
      },
451
      "gridPos": {
452
        "h": 1,
453
        "w": 24,
454
        "x": 0,
455
        "y": 13
456
      },
457
      "id": 6,
458
      "panels": [],
459
      "targets": [
460
        {
461
          "datasource": {
462
            "type": "datasource",
463
            "uid": "grafana"
464
          },
465
          "refId": "A"
466
        }
467
      ],
468
      "title": "Counters",
469
      "type": "row"
470
    },
471
    {
472
      "datasource": {
473
        "type": "prometheus",
474
        "uid": "${datasource}"
475
      },
476
      "fieldConfig": {
477
        "defaults": {
478
          "color": {
479
            "mode": "palette-classic"
480
          },
481
          "custom": {
482
            "axisLabel": "",
483
            "axisPlacement": "auto",
484
            "barAlignment": 0,
485
            "drawStyle": "line",
486
            "fillOpacity": 0,
487
            "gradientMode": "none",
488
            "hideFrom": {
489
              "legend": false,
490
              "tooltip": false,
491
              "viz": false
492
            },
493
            "lineInterpolation": "linear",
494
            "lineWidth": 1,
495
            "pointSize": 5,
496
            "scaleDistribution": {
497
              "type": "linear"
498
            },
499
            "showPoints": "auto",
500
            "spanNulls": false,
501
            "stacking": {
502
              "group": "A",
503
              "mode": "none"
504
            },
505
            "thresholdsStyle": {
506
              "mode": "off"
507
            }
508
          },
509
          "mappings": [],
510
          "thresholds": {
511
            "mode": "absolute",
512
            "steps": [
513
              {
514
                "color": "green",
515
                "value": null
516
              },
517
              {
518
                "color": "red",
519
                "value": 80
520
              }
521
            ]
522
          }
523
        },
524
        "overrides": []
525
      },
526
      "gridPos": {
527
        "h": 5,
528
        "w": 8,
529
        "x": 0,
530
        "y": 14
531
      },
532
      "id": 7,
533
      "maxPerRow": 3,
534
      "options": {
535
        "legend": {
536
          "calcs": [],
537
          "displayMode": "hidden",
538
          "placement": "bottom"
539
        },
540
        "tooltip": {
541
          "mode": "multi",
542
          "sort": "none"
543
        }
544
      },
545
      "repeat": "problem_counter_reason",
546
      "repeatDirection": "h",
547
      "targets": [
548
        {
549
          "datasource": {
550
            "type": "prometheus",
551
            "uid": "${datasource}"
552
          },
553
          "exemplar": true,
554
          "expr": "sum(rate(problem_counter{reason=~\"$problem_counter_reason\"}[5m]))",
555
          "interval": "",
556
          "legendFormat": "$problem_counter_reason",
557
          "refId": "A"
558
        }
559
      ],
560
      "title": "Problem rates - $problem_counter_reason",
561
      "type": "timeseries"
562
    }
563
  ],
564
  "schemaVersion": 36,
565
  "style": "dark",
566
  "tags": [
567
    "node"
568
  ],
569
  "templating": {
570
    "list": [
571
      {
572
        "current": {
573
          "selected": true,
574
          "text": [
575
            "All"
576
          ],
577
          "value": [
578
            "$__all"
579
          ]
580
        },
581
        "datasource": {
582
          "type": "prometheus",
583
          "uid": "${datasource}"
584
        },
585
        "definition": "label_values(problem_counter,reason)",
586
        "hide": 0,
587
        "includeAll": true,
588
        "multi": true,
589
        "name": "problem_counter_reason",
590
        "options": [],
591
        "query": {
592
          "query": "label_values(problem_counter,reason)",
593
          "refId": "StandardVariableQuery"
594
        },
595
        "refresh": 2,
596
        "regex": "",
597
        "skipUrlSync": false,
598
        "sort": 1,
599
        "type": "query"
600
      },
601
      {
602
        "current": {
603
          "selected": true,
604
          "text": [
605
            "All"
606
          ],
607
          "value": [
608
            "$__all"
609
          ]
610
        },
611
        "datasource": {
612
          "type": "prometheus",
613
          "uid": "${datasource}"
614
        },
615
        "definition": "label_values(problem_counter,node)",
616
        "hide": 0,
617
        "includeAll": true,
618
        "multi": true,
619
        "name": "node",
620
        "options": [],
621
        "query": {
622
          "query": "label_values(problem_counter,node)",
623
          "refId": "StandardVariableQuery"
624
        },
625
        "refresh": 2,
626
        "regex": "",
627
        "skipUrlSync": false,
628
        "sort": 1,
629
        "type": "query"
630
      },
631
      {
632
        "current": {
633
          "selected": true,
634
          "text": [
635
            "All"
636
          ],
637
          "value": [
638
            "$__all"
639
          ]
640
        },
641
        "datasource": {
642
          "type": "prometheus",
643
          "uid": "${datasource}"
644
        },
645
        "definition": "label_values(problem_gauge,type)",
646
        "hide": 0,
647
        "includeAll": true,
648
        "multi": true,
649
        "name": "problem_type",
650
        "options": [],
651
        "query": {
652
          "query": "label_values(problem_gauge,type)",
653
          "refId": "StandardVariableQuery"
654
        },
655
        "refresh": 2,
656
        "regex": "",
657
        "skipUrlSync": false,
658
        "sort": 1,
659
        "type": "query"
660
      },
661
      {
662
        "current": {
663
          "selected": false,
664
          "text": "VictoriaMetrics",
665
          "value": "VictoriaMetrics"
666
        },
667
        "hide": 0,
668
        "includeAll": false,
669
        "multi": false,
670
        "name": "datasource",
671
        "options": [],
672
        "query": "prometheus",
673
        "refresh": 1,
674
        "regex": "",
675
        "skipUrlSync": false,
676
        "type": "datasource"
677
      }
678
    ]
679
  },
680
  "time": {
681
    "from": "now-3h",
682
    "to": "now"
683
  },
684
  "timepicker": {
685
    "refresh_intervals": [
686
      "10s",
687
      "30s",
688
      "1m",
689
      "5m",
690
      "15m",
691
      "30m",
692
      "1h",
693
      "2h",
694
      "1d"
695
    ]
696
  },
697
  "timezone": "utc",
698
  "title": "Node Problem Detector",
699
  "uid": "node-problem-detector",
700
  "version": 5,
701
  "weekStart": ""
702
}
703

704
Product

Resources

Company
