CoCalc -- node-psi.json

GitHub Repository: gitpod-io/gitpod
Path: blob/main/operations/observability/mixins/workspace/dashboards/node-psi.json
²⁵⁰¹ views
1
{
2
  "annotations": {
3
    "list": [
4
      {
5
        "builtIn": 1,
6
        "datasource": {
7
          "type": "grafana",
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
  "editable": true,
25
  "fiscalYearStartMonth": 0,
26
  "graphTooltip": 1,
27
  "id": 86,
28
  "links": [],
29
  "liveNow": false,
30
  "panels": [
31
    {
32
      "collapsed": false,
33
      "datasource": {
34
        "type": "datasource",
35
        "uid": "grafana"
36
      },
37
      "gridPos": {
38
        "h": 1,
39
        "w": 24,
40
        "x": 0,
41
        "y": 0
42
      },
43
      "id": 13,
44
      "panels": [],
45
      "targets": [
46
        {
47
          "datasource": {
48
            "type": "datasource",
49
            "uid": "grafana"
50
          },
51
          "refId": "A"
52
        }
53
      ],
54
      "title": "Workspace node's normalized Load Average",
55
      "type": "row"
56
    },
57
    {
58
      "aliasColors": {},
59
      "bars": false,
60
      "dashLength": 10,
61
      "dashes": false,
62
      "datasource": {
63
        "type": "prometheus",
64
        "uid": "$datasource"
65
      },
66
      "description": "Nodes with a high normalized load average do not represent a real problem, it only means that pods should probably not be scheduled to them.\n\nIf you'd like to see more details about resource consumption of a particular node, you can do so by clicking at the node name.\n",
67
      "fill": 1,
68
      "fillGradient": 5,
69
      "gridPos": {
70
        "h": 7,
71
        "w": 12,
72
        "x": 0,
73
        "y": 1
74
      },
75
      "hiddenSeries": false,
76
      "id": 6,
77
      "legend": {
78
        "alignAsTable": false,
79
        "avg": false,
80
        "current": false,
81
        "max": false,
82
        "min": false,
83
        "rightSide": false,
84
        "show": true,
85
        "total": false,
86
        "values": false
87
      },
88
      "lines": true,
89
      "linewidth": 1,
90
      "links": [],
91
      "nullPointMode": "null",
92
      "options": {
93
        "alertThreshold": true
94
      },
95
      "percentage": false,
96
      "pluginVersion": "9.5.3",
97
      "pointradius": 5,
98
      "points": false,
99
      "renderer": "flot",
100
      "repeat": "cluster",
101
      "seriesOverrides": [
102
        {
103
          "$$hashKey": "object:1617",
104
          "alias": "Node Max Load Avg",
105
          "color": "#FF0000"
106
        }
107
      ],
108
      "spaceLength": 10,
109
      "stack": false,
110
      "steppedLine": false,
111
      "targets": [
112
        {
113
          "datasource": {
114
            "uid": "$datasource"
115
          },
116
          "editorMode": "code",
117
          "expr": "topk(5, sum(nodepool:node_load1:normalized{cluster=~\"$cluster\", nodepool=~\".*workspace.*\", node=~\"$node\"}) by (node))\n",
118
          "format": "time_series",
119
          "intervalFactor": 2,
120
          "legendFormat": "{{node}}",
121
          "range": true,
122
          "refId": "A"
123
        },
124
        {
125
          "datasource": {
126
            "uid": "$datasource"
127
          },
128
          "expr": "1\n",
129
          "format": "time_series",
130
          "intervalFactor": 2,
131
          "legendFormat": "Node Max Load Avg",
132
          "refId": "B"
133
        }
134
      ],
135
      "thresholds": [],
136
      "timeRegions": [],
137
      "title": "$cluster: Workspace node's normalized load average",
138
      "tooltip": {
139
        "shared": true,
140
        "sort": 0,
141
        "value_type": "individual"
142
      },
143
      "type": "graph",
144
      "xaxis": {
145
        "mode": "time",
146
        "show": true,
147
        "values": []
148
      },
149
      "yaxes": [
150
        {
151
          "$$hashKey": "object:1630",
152
          "format": "none",
153
          "logBase": 1,
154
          "min": 0,
155
          "show": true
156
        },
157
        {
158
          "$$hashKey": "object:1631",
159
          "format": "none",
160
          "logBase": 1,
161
          "min": 0,
162
          "show": true
163
        }
164
      ],
165
      "yaxis": {
166
        "align": false
167
      }
168
    },
169
    {
170
      "collapsed": false,
171
      "gridPos": {
172
        "h": 1,
173
        "w": 24,
174
        "x": 0,
175
        "y": 8
176
      },
177
      "id": 86,
178
      "panels": [],
179
      "title": "Workspace node's cpu pressure stall information",
180
      "type": "row"
181
    },
182
    {
183
      "datasource": {
184
        "type": "prometheus",
185
        "uid": "${datasource}"
186
      },
187
      "fieldConfig": {
188
        "defaults": {
189
          "color": {
190
            "mode": "palette-classic"
191
          },
192
          "custom": {
193
            "axisCenteredZero": false,
194
            "axisColorMode": "text",
195
            "axisLabel": "",
196
            "axisPlacement": "auto",
197
            "barAlignment": 0,
198
            "drawStyle": "line",
199
            "fillOpacity": 0,
200
            "gradientMode": "none",
201
            "hideFrom": {
202
              "legend": false,
203
              "tooltip": false,
204
              "viz": false
205
            },
206
            "lineInterpolation": "linear",
207
            "lineWidth": 1,
208
            "pointSize": 5,
209
            "scaleDistribution": {
210
              "type": "linear"
211
            },
212
            "showPoints": "auto",
213
            "spanNulls": false,
214
            "stacking": {
215
              "group": "A",
216
              "mode": "none"
217
            },
218
            "thresholdsStyle": {
219
              "mode": "off"
220
            }
221
          },
222
          "mappings": [],
223
          "max": 1,
224
          "thresholds": {
225
            "mode": "absolute",
226
            "steps": [
227
              {
228
                "color": "green",
229
                "value": null
230
              },
231
              {
232
                "color": "red",
233
                "value": 80
234
              }
235
            ]
236
          }
237
        },
238
        "overrides": []
239
      },
240
      "gridPos": {
241
        "h": 8,
242
        "w": 12,
243
        "x": 0,
244
        "y": 9
245
      },
246
      "id": 49,
247
      "options": {
248
        "legend": {
249
          "calcs": [],
250
          "displayMode": "list",
251
          "placement": "bottom",
252
          "showLegend": true
253
        },
254
        "tooltip": {
255
          "mode": "multi",
256
          "sort": "none"
257
        }
258
      },
259
      "repeat": "cluster",
260
      "repeatDirection": "h",
261
      "targets": [
262
        {
263
          "datasource": {
264
            "type": "prometheus",
265
            "uid": "${datasource}"
266
          },
267
          "editorMode": "code",
268
          "expr": "topk(5, rate(node_pressure_cpu_waiting_seconds_total{cluster=\"$cluster\",node=~\"$node\"}[30s]))",
269
          "legendFormat": "{{node}}",
270
          "range": true,
271
          "refId": "A"
272
        }
273
      ],
274
      "title": "$cluster: Workspace node's cpu pressure stall information",
275
      "type": "timeseries"
276
    },
277
    {
278
      "collapsed": false,
279
      "gridPos": {
280
        "h": 1,
281
        "w": 24,
282
        "x": 0,
283
        "y": 17
284
      },
285
      "id": 165,
286
      "panels": [],
287
      "title": "Workspace node's memory pressure stall information",
288
      "type": "row"
289
    },
290
    {
291
      "datasource": {
292
        "type": "prometheus",
293
        "uid": "${datasource}"
294
      },
295
      "fieldConfig": {
296
        "defaults": {
297
          "color": {
298
            "mode": "palette-classic"
299
          },
300
          "custom": {
301
            "axisCenteredZero": false,
302
            "axisColorMode": "text",
303
            "axisLabel": "",
304
            "axisPlacement": "auto",
305
            "barAlignment": 0,
306
            "drawStyle": "line",
307
            "fillOpacity": 0,
308
            "gradientMode": "none",
309
            "hideFrom": {
310
              "legend": false,
311
              "tooltip": false,
312
              "viz": false
313
            },
314
            "lineInterpolation": "linear",
315
            "lineWidth": 1,
316
            "pointSize": 5,
317
            "scaleDistribution": {
318
              "type": "linear"
319
            },
320
            "showPoints": "auto",
321
            "spanNulls": false,
322
            "stacking": {
323
              "group": "A",
324
              "mode": "none"
325
            },
326
            "thresholdsStyle": {
327
              "mode": "off"
328
            }
329
          },
330
          "mappings": [],
331
          "max": 1,
332
          "thresholds": {
333
            "mode": "absolute",
334
            "steps": [
335
              {
336
                "color": "green",
337
                "value": null
338
              },
339
              {
340
                "color": "red",
341
                "value": 80
342
              }
343
            ]
344
          }
345
        },
346
        "overrides": []
347
      },
348
      "gridPos": {
349
        "h": 8,
350
        "w": 12,
351
        "x": 0,
352
        "y": 18
353
      },
354
      "id": 133,
355
      "options": {
356
        "legend": {
357
          "calcs": [],
358
          "displayMode": "list",
359
          "placement": "bottom",
360
          "showLegend": true
361
        },
362
        "tooltip": {
363
          "mode": "multi",
364
          "sort": "none"
365
        }
366
      },
367
      "repeat": "cluster",
368
      "repeatDirection": "h",
369
      "targets": [
370
        {
371
          "datasource": {
372
            "type": "prometheus",
373
            "uid": "${datasource}"
374
          },
375
          "editorMode": "code",
376
          "expr": "topk(5, rate(node_pressure_memory_waiting_seconds_total{cluster=\"$cluster\",node=~\"$node\"}[30s]))",
377
          "legendFormat": "{{node}}",
378
          "range": true,
379
          "refId": "A"
380
        }
381
      ],
382
      "title": "$cluster: Workspace node's memory pressure stall information",
383
      "type": "timeseries"
384
    },
385
    {
386
      "collapsed": false,
387
      "gridPos": {
388
        "h": 1,
389
        "w": 24,
390
        "x": 0,
391
        "y": 26
392
      },
393
      "id": 224,
394
      "panels": [],
395
      "title": "Workspace node's IO pressure stall information",
396
      "type": "row"
397
    },
398
    {
399
      "datasource": {
400
        "type": "prometheus",
401
        "uid": "${datasource}"
402
      },
403
      "fieldConfig": {
404
        "defaults": {
405
          "color": {
406
            "mode": "palette-classic"
407
          },
408
          "custom": {
409
            "axisCenteredZero": false,
410
            "axisColorMode": "text",
411
            "axisLabel": "",
412
            "axisPlacement": "auto",
413
            "barAlignment": 0,
414
            "drawStyle": "line",
415
            "fillOpacity": 0,
416
            "gradientMode": "none",
417
            "hideFrom": {
418
              "legend": false,
419
              "tooltip": false,
420
              "viz": false
421
            },
422
            "lineInterpolation": "linear",
423
            "lineWidth": 1,
424
            "pointSize": 5,
425
            "scaleDistribution": {
426
              "type": "linear"
427
            },
428
            "showPoints": "auto",
429
            "spanNulls": false,
430
            "stacking": {
431
              "group": "A",
432
              "mode": "none"
433
            },
434
            "thresholdsStyle": {
435
              "mode": "off"
436
            }
437
          },
438
          "mappings": [],
439
          "max": 1,
440
          "thresholds": {
441
            "mode": "absolute",
442
            "steps": [
443
              {
444
                "color": "green",
445
                "value": null
446
              },
447
              {
448
                "color": "red",
449
                "value": 80
450
              }
451
            ]
452
          }
453
        },
454
        "overrides": []
455
      },
456
      "gridPos": {
457
        "h": 8,
458
        "w": 12,
459
        "x": 0,
460
        "y": 27
461
      },
462
      "id": 197,
463
      "options": {
464
        "legend": {
465
          "calcs": [],
466
          "displayMode": "list",
467
          "placement": "bottom",
468
          "showLegend": true
469
        },
470
        "tooltip": {
471
          "mode": "multi",
472
          "sort": "none"
473
        }
474
      },
475
      "repeat": "cluster",
476
      "repeatDirection": "h",
477
      "targets": [
478
        {
479
          "datasource": {
480
            "type": "prometheus",
481
            "uid": "${datasource}"
482
          },
483
          "editorMode": "code",
484
          "expr": "topk(5, rate(node_pressure_io_waiting_seconds_total{cluster=\"$cluster\",node=~\"$node\"}[30s]))",
485
          "legendFormat": "{{node}}",
486
          "range": true,
487
          "refId": "A"
488
        }
489
      ],
490
      "title": "$cluster: Workspace node's IO pressure stall information",
491
      "type": "timeseries"
492
    }
493
  ],
494
  "refresh": "30s",
495
  "schemaVersion": 38,
496
  "style": "dark",
497
  "tags": [],
498
  "templating": {
499
    "list": [
500
      {
501
        "current": {
502
          "selected": false,
503
          "text": "VictoriaMetrics",
504
          "value": "VictoriaMetrics"
505
        },
506
        "hide": 0,
507
        "includeAll": false,
508
        "multi": false,
509
        "name": "datasource",
510
        "options": [],
511
        "query": "prometheus",
512
        "queryValue": "",
513
        "refresh": 1,
514
        "regex": "",
515
        "skipUrlSync": false,
516
        "type": "datasource"
517
      },
518
      {
519
        "current": {
520
          "selected": true,
521
          "text": [
522
            "All"
523
          ],
524
          "value": [
525
            "$__all"
526
          ]
527
        },
528
        "datasource": {
529
          "uid": "$datasource"
530
        },
531
        "definition": "",
532
        "hide": 0,
533
        "includeAll": true,
534
        "multi": true,
535
        "name": "cluster",
536
        "options": [],
537
        "query": {
538
          "query": "label_values(gitpod_ws_manager_mk2_workspace_phase_total, cluster)",
539
          "refId": "VictoriaMetrics-cluster-Variable-Query"
540
        },
541
        "refresh": 2,
542
        "regex": "",
543
        "skipUrlSync": false,
544
        "sort": 1,
545
        "tagValuesQuery": "",
546
        "tagsQuery": "",
547
        "type": "query",
548
        "useTags": false
549
      },
550
      {
551
        "current": {
552
          "selected": true,
553
          "text": [
554
            "All"
555
          ],
556
          "value": [
557
            "$__all"
558
          ]
559
        },
560
        "datasource": {
561
          "type": "prometheus",
562
          "uid": "${datasource}"
563
        },
564
        "definition": "label_values(node_pressure_memory_waiting_seconds_total,node)",
565
        "hide": 0,
566
        "includeAll": true,
567
        "multi": true,
568
        "name": "node",
569
        "options": [],
570
        "query": {
571
          "query": "label_values(node_pressure_memory_waiting_seconds_total,node)",
572
          "refId": "PrometheusVariableQueryEditor-VariableQuery"
573
        },
574
        "refresh": 2,
575
        "regex": "",
576
        "skipUrlSync": false,
577
        "sort": 0,
578
        "type": "query"
579
      }
580
    ]
581
  },
582
  "time": {
583
    "from": "now-1h",
584
    "to": "now"
585
  },
586
  "timepicker": {
587
    "refresh_intervals": [
588
      "5s",
589
      "10s",
590
      "30s",
591
      "1m",
592
      "5m",
593
      "15m",
594
      "30m",
595
      "1h",
596
      "2h",
597
      "1d"
598
    ],
599
    "time_options": [
600
      "5m",
601
      "15m",
602
      "1h",
603
      "6h",
604
      "12h",
605
      "24h",
606
      "2d",
607
      "7d",
608
      "30d"
609
    ]
610
  },
611
  "timezone": "utc",
612
  "title": "Node Pressure Stall Information",
613
  "uid": "T7pAXoVVk",
614
  "version": 1,
615
  "weekStart": ""
616
}
617

618
Product

Resources

Company
