forked from open-telemetry/opentelemetry-collector-contrib
-
Notifications
You must be signed in to change notification settings - Fork 0
/
metadata.yaml
690 lines (686 loc) · 19.8 KB
/
metadata.yaml
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
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
type: apachespark
status:
class: receiver
stability:
development: [metrics]
distributions: [contrib]
codeowners:
active: [djaglowski, Caleb-Hurshman, mrsillydog]
resource_attributes:
spark.application.id:
description: The ID of the application for which the metric was recorded.
type: string
enabled: true
spark.application.name:
description: The name of the application for which the metric was recorded.
type: string
enabled: true
spark.stage.id:
description: The ID of the application stage for which the metric was recorded.
type: int
enabled: true
spark.stage.attempt.id:
description: The ID of the stage attempt for which the metric was recorded.
type: int
spark.executor.id:
description: The ID of the executor for which the metric was recorded.
type: string
enabled: true
spark.job.id:
description: The ID of the job for which the metric was recorded.
type: int
enabled: true
attributes:
stage_active:
name_override: active
description: Whether the stage for which the metric was recorded is active.
type: bool
stage_complete:
name_override: complete
description: Whether the stage for which the metric was recorded is complete.
type: bool
stage_pending:
name_override: pending
description: Whether the stage for which the metric was recorded is pending.
type: bool
stage_failed:
name_override: failed
description: Whether the stage for which the metric was recorded is failed.
type: bool
stage_task_result:
name_override: result
description: The result of the stage tasks for which the metric was recorded.
type: string
enum:
- completed
- failed
- killed
executor_task_result:
name_override: result
description: The result of the executor tasks for which the metric was recorded.
type: string
enum:
- completed
- failed
job_result:
name_override: result
description: The result of the job stages or tasks for which the metric was recorded.
type: string
enum:
- completed
- failed
- skipped
direction:
description: Whether the metric is in regards to input or output operations.
type: string
enum:
- in
- out
source:
description: The source from which data was fetched for the metric.
type: string
enum:
- local
- remote
location:
description: The location of the memory for which the metric was recorded..
type: string
enum:
- on_heap
- off_heap
state:
description: The state of the memory for which the metric was recorded.
type: string
enum:
- used
- free
scheduler_status:
name_override: status
description: The status of the DAGScheduler stages for which the metric was recorded.
type: string
enum:
- waiting
- running
pool_memory_type:
name_override: type
description: The type of pool memory for which the metric was recorded.
type: string
enum:
- direct
- mapped
gc_type:
description: The type of the garbage collection performed for the metric.
type: string
enum:
- major
- minor
metrics:
#stage
spark.stage.status:
description: A one-hot encoding representing the status of this stage.
enabled: true
sum:
monotonic: false
aggregation_temporality: cumulative
value_type: int
unit: "{ status }"
attributes:
[stage_active, stage_complete, stage_pending, stage_failed]
spark.stage.task.active:
description: Number of active tasks in this stage.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: false
value_type: int
unit: "{ task }"
attributes: []
spark.stage.task.result:
description: Number of tasks with a specific result in this stage.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: "{ task }"
attributes:
[stage_task_result]
spark.stage.executor.run_time:
description: Amount of time spent by the executor in this stage.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: ms
attributes: []
spark.stage.executor.cpu_time:
description: CPU time spent by the executor in this stage.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: ns
attributes: []
spark.stage.task.result_size:
description: The amount of data transmitted back to the driver by all the tasks in this stage.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: bytes
attributes: []
spark.stage.jvm_gc_time:
description: The amount of time the JVM spent on garbage collection in this stage.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: ms
attributes: []
spark.stage.memory.spilled:
description: The amount of memory moved to disk due to size constraints (spilled) in this stage.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: bytes
attributes: []
spark.stage.disk.spilled:
description: The amount of disk space used for storing portions of overly large data chunks that couldn't fit in memory in this stage.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: bytes
attributes: []
spark.stage.memory.peak:
description: Peak memory used by internal data structures created during shuffles, aggregations and joins in this stage.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: bytes
attributes: []
spark.stage.io.size:
description: Amount of data written and read at this stage.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: bytes
attributes:
[direction]
spark.stage.io.records:
description: Number of records written and read in this stage.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: "{ record }"
attributes:
[direction]
spark.stage.shuffle.blocks_fetched:
description: Number of blocks fetched in shuffle operations in this stage.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: "{ block }"
attributes:
[source]
spark.stage.shuffle.fetch_wait_time:
description: Time spent in this stage waiting for remote shuffle blocks.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: ms
attributes: []
spark.stage.shuffle.io.disk:
description: Amount of data read to disk in shuffle operations (sometimes required for large blocks, as opposed to the default behavior of reading into memory).
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: bytes
attributes: []
spark.stage.shuffle.io.read.size:
description: Amount of data read in shuffle operations in this stage.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: bytes
attributes:
[source]
spark.stage.shuffle.io.write.size:
description: Amount of data written in shuffle operations in this stage.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: bytes
attributes:
[]
spark.stage.shuffle.io.records:
description: Number of records written or read in shuffle operations in this stage.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: "{ record }"
attributes:
[direction]
spark.stage.shuffle.write_time:
description: Time spent blocking on writes to disk or buffer cache in this stage.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: ns
attributes: []
#executor
spark.executor.memory.usage:
description: Storage memory used by this executor.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: false
value_type: int
unit: bytes
attributes: []
spark.executor.disk.usage:
description: Disk space used by this executor for RDD storage.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: false
value_type: int
unit: bytes
attributes: []
spark.executor.task.limit:
description: Maximum number of tasks that can run concurrently in this executor.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: false
value_type: int
unit: "{ task }"
attributes: []
spark.executor.task.active:
description: Number of tasks currently running in this executor.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: false
value_type: int
unit: "{ task }"
attributes: []
spark.executor.task.result:
description: Number of tasks with a specific result in this executor.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: "{ task }"
attributes: [executor_task_result]
spark.executor.time:
description: Elapsed time the JVM spent executing tasks in this executor.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: ms
attributes: []
spark.executor.gc_time:
description: Elapsed time the JVM spent in garbage collection in this executor.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: ms
attributes: []
spark.executor.input_size:
description: Amount of data input for this executor.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: bytes
attributes: []
spark.executor.shuffle.io.size:
description: Amount of data written and read during shuffle operations for this executor.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: bytes
attributes: [direction]
spark.executor.storage_memory.usage:
description: The executor's storage memory usage.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: false
value_type: int
unit: bytes
attributes: [location, state]
#job
spark.job.task.active:
description: Number of active tasks in this job.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: false
value_type: int
unit: "{ task }"
attributes: []
spark.job.task.result:
description: Number of tasks with a specific result in this job.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: "{ task }"
attributes: [job_result]
spark.job.stage.active:
description: Number of active stages in this job.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: false
value_type: int
unit: "{ task }"
attributes: []
spark.job.stage.result:
description: Number of stages with a specific result in this job.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: "{ task }"
attributes: [job_result]
# metrics
spark.driver.block_manager.disk.usage:
description: Disk space used by the BlockManager.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: false
value_type: int
unit: mb
attributes: []
spark.driver.block_manager.memory.usage:
description: Memory usage for the driver's BlockManager.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: false
value_type: int
unit: mb
attributes: [location, state]
spark.driver.hive_external_catalog.file_cache_hits:
description: Number of file cache hits on the HiveExternalCatalog.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: "{ hit }"
attributes: []
spark.driver.hive_external_catalog.files_discovered:
description: Number of files discovered while listing the partitions of a table in the Hive metastore
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: "{ file }"
attributes: []
spark.driver.hive_external_catalog.hive_client_calls:
description: Number of calls to the underlying Hive Metastore client made by the Spark application.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: "{ call }"
attributes: []
spark.driver.hive_external_catalog.parallel_listing_jobs:
description: Number of parallel listing jobs initiated by the HiveExternalCatalog when listing partitions of a table.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: "{ listing_job }"
attributes: []
spark.driver.hive_external_catalog.partitions_fetched:
description: Table partitions fetched by the HiveExternalCatalog.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: "{ partition }"
attributes: []
spark.driver.code_generator.compilation.count:
description: Number of source code compilation operations performed by the CodeGenerator.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: "{ compilation }"
attributes: []
spark.driver.code_generator.compilation.average_time:
description: Average time spent during CodeGenerator source code compilation operations.
enabled: true
gauge:
value_type: double
unit: ms
attributes: []
spark.driver.code_generator.generated_class.count:
description: Number of classes generated by the CodeGenerator.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: "{ class }"
attributes: []
spark.driver.code_generator.generated_class.average_size:
description: Average class size of the classes generated by the CodeGenerator.
enabled: true
gauge:
value_type: double
unit: bytes
attributes: []
spark.driver.code_generator.generated_method.count:
description: Number of methods generated by the CodeGenerator.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: "{ method }"
attributes: []
spark.driver.code_generator.generated_method.average_size:
description: Average method size of the classes generated by the CodeGenerator.
enabled: true
gauge:
value_type: double
unit: bytes
attributes: []
spark.driver.code_generator.source_code.operations:
description: Number of source code generation operations performed by the CodeGenerator.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: "{ operation }"
attributes: []
spark.driver.code_generator.source_code.average_size:
description: Average size of the source code generated by a CodeGenerator code generation operation.
enabled: true
gauge:
value_type: double
unit: bytes
attributes: []
spark.driver.dag_scheduler.job.active:
description: Number of active jobs currently being processed by the DAGScheduler.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: false
value_type: int
unit: "{ job }"
attributes: []
spark.driver.dag_scheduler.job.count:
description: Number of jobs that have been submitted to the DAGScheduler.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: "{ job }"
attributes: []
spark.driver.dag_scheduler.stage.failed:
description: Number of failed stages run by the DAGScheduler.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: "{ stage }"
attributes: []
spark.driver.dag_scheduler.stage.count:
description: Number of stages the DAGScheduler is either running or needs to run.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: false
value_type: int
unit: "{ stage }"
attributes: [scheduler_status]
spark.driver.live_listener_bus.posted:
description: Number of events that have been posted on the LiveListenerBus.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: "{ event }"
attributes: []
spark.driver.live_listener_bus.processing_time.average:
description: Average time taken for the LiveListenerBus to process an event posted to it.
enabled: true
gauge:
value_type: double
unit: ms
attributes: []
spark.driver.live_listener_bus.dropped:
description: Number of events that have been dropped by the LiveListenerBus.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: "{ event }"
attributes: []
spark.driver.live_listener_bus.queue_size:
description: Number of events currently waiting to be processed by the LiveListenerBus.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: false
value_type: int
unit: "{ event }"
attributes: []
spark.driver.jvm_cpu_time:
description: Current CPU time taken by the Spark driver.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: ns
attributes: []
spark.driver.executor.memory.jvm:
description: Amount of memory used by the driver's JVM.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: false
value_type: int
unit: bytes
attributes: [location]
spark.driver.executor.memory.execution:
description: Amount of execution memory currently used by the driver.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: false
value_type: int
unit: bytes
attributes: [location]
spark.driver.executor.memory.storage:
description: Amount of storage memory currently used by the driver.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: false
value_type: int
unit: bytes
attributes: [location]
spark.driver.executor.memory.pool:
description: Amount of pool memory currently used by the driver.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: false
value_type: int
unit: bytes
attributes: [pool_memory_type]
spark.driver.executor.gc.operations:
description: Number of garbage collection operations performed by the driver.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: "{ gc_operation }"
attributes: [gc_type]
spark.driver.executor.gc.time:
description: Total elapsed time during garbage collection operations performed by the driver.
enabled: true
sum:
aggregation_temporality: cumulative
monotonic: true
value_type: int
unit: ms
attributes: [gc_type]