-
Notifications
You must be signed in to change notification settings - Fork 158
/
influxdb2_operational_monitoring.yml
593 lines (569 loc) · 18.8 KB
/
influxdb2_operational_monitoring.yml
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
apiVersion: influxdata.com/v2alpha1
kind: Label
metadata:
name: affectionate-jackson-9aa001
spec:
color: '#ebadf8'
description: tasks and cardinality monitoring
name: operational_monitoring
---
apiVersion: influxdata.com/v2alpha1
kind: Bucket
metadata:
name: sharp-thompson-daa003
spec:
associations:
- kind: Label
name: affectionate-jackson-9aa001
name: cardinality
---
apiVersion: influxdata.com/v2alpha1
kind: Task
metadata:
name: alerting-northcutt-daa003
spec:
associations:
- kind: Label
name: affectionate-jackson-9aa001
every: 1h
name: cardinality_by_bucket
query: |-
import "influxdata/influxdb"
buckets()
|> map(fn: (r) => {
cardinality = influxdb.cardinality(bucket: r.name, start: -task.every)
|> findRecord(idx: 0, fn: (key) =>
(true))
return {
_time: now(),
_measurement: "buckets",
bucket: r.name,
_field: "cardinality",
_value: cardinality._value,
}
})
|> to(bucket: "cardinality")
---
apiVersion: influxdata.com/v2alpha1
kind: Variable
metadata:
name: eager-proskuriakova-9aa003
spec:
associations:
- kind: Label
name: affectionate-jackson-9aa001
language: flux
name: bucket
query: |-
buckets()
|> filter(fn: (r) => r.name !~ /^_/)
|> rename(columns: {name: "_value"})
|> keep(columns: ["_value"])
type: query
---
apiVersion: influxdata.com/v2alpha1
kind: Variable
metadata:
name: relaxed-archimedes-5aa003
spec:
associations:
- kind: Label
name: affectionate-jackson-9aa001
language: flux
name: measurement
query: |-
import "influxdata/influxdb/v1"
v1.measurements(bucket: v.bucket)
type: query
---
apiVersion: influxdata.com/v2alpha1
kind: Dashboard
metadata:
name: magical-brahmagupta-5aa001
spec:
associations:
- kind: Label
name: affectionate-jackson-9aa001
charts:
- colors:
- hex: '#00C9FF'
id: base
name: laser
type: text
decimalPlaces: 2
height: 4
kind: Single_Stat
name: Total Runs
queries:
- query: |-
import "strings"
import "regexp"
from(bucket: "_tasks")
|> range(start: v.timeRangeStart, stop: v.timeRangeStop)
|> filter(fn: (r) => r["_measurement"] == "runs")
|> filter(fn: (r) => r["_field"] == "logs")
|> map(
fn: (r) => {
ind = regexp.findStringIndex(r: /name: \\\\\\".+?\\\\\\"/, v: r._value)
finalstring = if length(arr: ind) > 1 then strings.trimSuffix(v: strings.trimPrefix(v: strings.substring(end: ind[1], start: ind[0], v: r._value ), prefix: "name: \\\\\\\""), suffix: "\\\\\\\"") else "none"
return {r with name: finalstring }
}
)
|> group(columns: ["_start"])
|> count()
|> rename(columns: {_start: "_time"})
width: 4
- colors:
- hex: '#ffffff'
id: base
name: white
type: text
fieldOptions:
- displayName: name
fieldName: name
visible: true
- displayName: taskID
fieldName: taskID
visible: true
- displayName: success
fieldName: success
visible: true
- displayName: failed
fieldName: failed
visible: true
- displayName: errorRate
fieldName: errorRate
visible: true
height: 4
kind: Table
name: Error Rates Per Task
queries:
- query: |-
import "influxdata/influxdb/v1"
import "strings"
import "regexp"
from(bucket: "_tasks")
|> range(start: v.timeRangeStart, stop: v.timeRangeStop)
|> filter(fn: (r) => r["_measurement"] == "runs")
|> filter(fn: (r) => r["_field"] == "logs" or r._field == "name")
|> v1.fieldsAsCols()
|> group(columns: ["taskID", "name", "status"])
|> count(column: "logs")
|> group()
|> pivot(rowKey:["taskID", "name"], columnKey: ["status"], valueColumn: "logs")
|> map(fn: (r) => ({r with success: if exists r.success then r.success else 0, failed: if exists r.failed then r.failed else 0}))
|> map(fn: (r)=> ({r with errorRate: float(v: r.failed)/float(v: r.success+r.failed) }))
tableOptions:
sortBy: failed
verticalTimeAxis: true
timeFormat: YYYY-MM-DD HH:mm:ss
width: 12
yPos: 4
- colors:
- hex: '#ffffff'
id: base
name: white
type: text
fieldOptions:
- displayName: _time
fieldName: _time
visible: true
- displayName: name
fieldName: name
visible: true
- displayName: taskID
fieldName: taskID
visible: true
- displayName: runID
fieldName: runID
visible: true
- displayName: _value
fieldName: _value
- displayName: status
fieldName: status
- displayName: failed
fieldName: failed
- displayName: success
fieldName: success
- displayName: errorRate
fieldName: errorRate
- displayName: _measurement
fieldName: _measurement
- displayName: _start
fieldName: _start
- displayName: _stop
fieldName: _stop
- displayName: logs
fieldName: logs
- displayName: message
fieldName: message
visible: true
height: 3
kind: Table
name: Error List
queries:
- query: |-
import "influxdata/influxdb/v1"
import "strings"
import "regexp"
from(bucket: "_tasks")
|> range(start: v.timeRangeStart, stop: v.timeRangeStop)
|> filter(fn: (r) => r["_measurement"] == "runs" and r.status == "failed")
|> filter(fn: (r) => r["_field"] == "errorMessage" or r._field == "runID" or r._field == "name")
|> v1.fieldsAsCols()
|> group()
// |> group(columns: ["taskID", "runID", "name", "status"])
tableOptions:
sortBy: failed
verticalTimeAxis: true
timeFormat: YYYY-MM-DD HH:mm:ss
width: 12
yPos: 8
- axes:
- base: "10"
name: x
scale: linear
- base: "2"
name: y
scale: linear
colors:
- hex: '#31C0F6'
id: fcee9956-f868-405d-8f3b-863ab456067d
name: Nineteen Eighty Four
type: scale
- hex: '#A500A5'
id: 613dba11-30be-4d41-91d8-ffeac3ee9458
name: Nineteen Eighty Four
type: scale
- hex: '#FF7E27'
id: 4b074fc6-f802-4b2d-aad3-fe0624970891
name: Nineteen Eighty Four
type: scale
geom: line
height: 4
kind: Xy
name: Error Rates Over Time (All tasks)
position: overlaid
queries:
- query: |-
import "strings"
import "regexp"
from(bucket: "_tasks")
|> range(start: v.timeRangeStart, stop: v.timeRangeStop)
|> filter(fn: (r) => r["_measurement"] == "runs")
|> filter(fn: (r) => r["_field"] == "logs")
|> map(fn: (r) => {
ind = regexp.findStringIndex(r: /name: \\\\\\".+?\\\\\\"/, v: r._value)
finalstring = strings.trimSuffix(v: strings.trimPrefix(v: strings.substring(end: ind[1], start: ind[0], v: r._value ), prefix: "name: \\\\\\\""), suffix: "\\\\\\\"")
return {r with name: finalstring }
}
)
|> group(columns: ["status"])
|> aggregateWindow(every: 1h, fn: count)
|> pivot(rowKey:["_time"], columnKey: ["status"], valueColumn: "_value")
|> filter(fn: (r) => r.failed + r.success != 0)
|> map(fn: (r)=> ({r with _value: float(v: r.failed)/float(v: r.success+r.failed) }))
width: 12
xCol: _time
yCol: _value
yPos: 11
- colors:
- hex: '#ffffff'
id: base
name: white
type: text
- hex: '#513CC6'
id: c749e60f-b9a3-436b-996a-d3eca0dc87b7
name: planet
type: text
value: 95
fieldOptions:
- displayName: _start
fieldName: _start
- displayName: _stop
fieldName: _stop
- displayName: name
fieldName: name
visible: true
- displayName: taskID
fieldName: taskID
- displayName: _time
fieldName: _time
visible: true
- displayName: runID
fieldName: runID
- displayName: scheduledFor
fieldName: scheduledFor
visible: true
- displayName: requestedAt
fieldName: requestedAt
visible: true
- displayName: startedAt
fieldName: startedAt
visible: true
- displayName: finishedAt
fieldName: finishedAt
visible: true
height: 4
kind: Table
name: Last Successful Run Per Task
queries:
- query: |-
import "influxdata/influxdb/v1"
import "strings"
import "regexp"
from(bucket: "_tasks")
|> range(start: v.timeRangeStart, stop: v.timeRangeStop)
|> filter(fn: (r) => r["_measurement"] == "runs")
|> filter(fn: (r) => r["status"] == "success")
|> group(columns: ["taskID"])
|> v1.fieldsAsCols()
|> map(fn: (r) => {
ind = regexp.findStringIndex(r: /name: \\\\\\".+?\\\\\\"/, v: r.logs)
finalstring = strings.trimSuffix(v: strings.trimPrefix(v: strings.substring(end: ind[1], start: ind[0], v: r.logs ), prefix: "name: \\\\\\\""), suffix: "\\\\\\\"")
return {r with name: finalstring }
}
)
|> group(columns: ["taskID", "name"])
|> rename(columns: {logs: "_value"})
|> last()
|> drop(columns: ["_value"])
|> group()
tableOptions:
verticalTimeAxis: true
timeFormat: YYYY-MM-DD HH:mm:ss
width: 12
yPos: 15
- colors:
- hex: '#7CE490'
id: base
name: honeydew
type: text
decimalPlaces: 2
height: 4
kind: Single_Stat
name: Total Succeeding
queries:
- query: |-
import "strings"
import "regexp"
from(bucket: "_tasks")
|> range(start: v.timeRangeStart, stop: v.timeRangeStop)
|> filter(fn: (r) => r["_measurement"] == "runs")
|> filter(fn: (r) => r["_field"] == "logs")
|> filter(fn: (r) => r.status == "success")
|> group(columns: ["_start"])
|> count()
|> rename(columns: {_start: "_time"})
width: 5
xPos: 4
- colors:
- hex: '#BF3D5E'
id: base
name: ruby
type: text
decimalPlaces: 2
height: 4
kind: Single_Stat
name: Total Failing
queries:
- query: |-
import "strings"
import "regexp"
from(bucket: "_tasks")
|> range(start: v.timeRangeStart, stop: v.timeRangeStop)
|> filter(fn: (r) => r["_measurement"] == "runs")
|> filter(fn: (r) => r["_field"] == "logs")
|> filter(fn: (r) => r.status != "success")
|> group(columns: ["_start"])
|> count()
|> rename(columns: {_start: "_time"})
width: 3
xPos: 9
name: Task Summary Dashboard
---
apiVersion: influxdata.com/v2alpha1
kind: Dashboard
metadata:
name: nostalgic-kirch-1aa001
spec:
associations:
- kind: Label
name: affectionate-jackson-9aa001
charts:
- height: 2
kind: Markdown
name: Name this Cell
note: |-
Explore the cardinality of the buckets in your account.
Quickly find buckets that have high cardinality then drill down by bucket measurement and tag to understand the cause of high cardinality.
width: 12
- axes:
- base: "10"
name: x
scale: linear
- base: "10"
name: y
scale: linear
colors:
- hex: '#31C0F6'
id: 75a22a5f-96e6-41ac-8fb0-d9d628b39311
name: Nineteen Eighty Four
type: scale
- hex: '#A500A5'
id: ec7e8c82-2aef-4682-9c64-64298feca9cf
name: Nineteen Eighty Four
type: scale
- hex: '#FF7E27'
id: d94bc95b-d1cf-4493-b0a9-c3ccb62f9b57
name: Nineteen Eighty Four
type: scale
geom: line
height: 4
hoverDimension: auto
kind: Xy
legendOpacity: 1
legendOrientationThreshold: 10
name: Cardinality by Bucket
note: View trends over time of how cardinality is changing for each of your
buckets
position: overlaid
queries:
- query: |-
import "influxdata/influxdb"
from(bucket: "cardinality")
|> range(start: v.timeRangeStart, stop: v.timeRangeStop)
|> filter(fn: (r) => r._measurement == "buckets" and r._field == "cardinality")
|> aggregateWindow(every:v.windowPeriod, fn: last)
width: 12
xCol: _time
yCol: _value
yPos: 2
- colors:
- hex: '#ffffff'
id: base
name: white
type: text
fieldOptions:
- displayName: _start
fieldName: _start
- displayName: _stop
fieldName: _stop
- displayName: _time
fieldName: _time
- displayName: bucket
fieldName: bucket
visible: true
- displayName: cardinality
fieldName: _value
visible: true
- displayName: _field
fieldName: _field
- displayName: _measurement
fieldName: _measurement
height: 4
kind: Table
name: Top Buckets
note: View the top 10 buckets with the highest cardinality
queries:
- query: |-
import "influxdata/influxdb"
from(bucket: "cardinality")
|> range(start: v.timeRangeStart, stop: v.timeRangeStop)
|> filter(fn: (r) => r._measurement == "buckets" and r._field == "cardinality")
|> last()
|> group()
|> top(n:10)
tableOptions:
verticalTimeAxis: true
timeFormat: YYYY-MM-DD HH:mm:ss
width: 12
yPos: 6
- colors:
- hex: '#ffffff'
id: base
name: white
type: text
fieldOptions:
- displayName: bucket
fieldName: bucket
visible: true
- displayName: measurement
fieldName: measurement
visible: true
- displayName: cardinality
fieldName: cardinality
visible: true
- displayName: tag
fieldName: tag
visible: true
- displayName: cardinality
fieldName: _value
visible: true
height: 4
kind: Table
name: Cardinality by Measurment
queries:
- query: |-
import "influxdata/influxdb"
import "influxdata/influxdb/schema"
schema.measurements(bucket: v.bucket)
|> map(fn: (r) => {
m = r._value
return {
bucket: v.bucket,
measurement: m,
_value: (influxdb.cardinality(bucket: v.bucket, start: v.timeRangeStart, predicate: (r) => r._measurement == m) |> findRecord(idx:0, fn:(key) => true))._value
}
})
|> sort(desc:true)
tableOptions:
verticalTimeAxis: true
timeFormat: YYYY-MM-DD HH:mm:ss
width: 12
yPos: 10
- colors:
- hex: '#ffffff'
id: base
name: white
type: text
fieldOptions:
- displayName: tag
fieldName: tag
visible: true
- displayName: cardinality
fieldName: _value
visible: true
- displayName: bucket
fieldName: bucket
visible: true
- displayName: measurement
fieldName: measurement
visible: true
height: 4
kind: Table
name: Cardinality By Tag
queries:
- query: |-
import "influxdata/influxdb/schema"
cardinalityByTag = (bucket, measurement) => schema.tagKeys(bucket: bucket, predicate: (r) => r._measurement == measurement)
|> filter(fn: (r) => r._value != "_start" and r._value != "_stop")
|> map(
fn: (r) => ({
tag: r._value,
_value: (schema.tagValues(bucket: bucket, tag: r._value)
|> count()
|> findRecord(fn: (key) => true, idx: 0))._value,
}),
)
|> group(columns: ["tag"])
|> sum()
cardinalityByTag(bucket: v.bucket, measurement: v.measurement)
|> group()
|> top(n: 10)
tableOptions:
verticalTimeAxis: true
timeFormat: YYYY-MM-DD HH:mm:ss
width: 12
yPos: 14
name: Cardinality Explorer