-
Notifications
You must be signed in to change notification settings - Fork 542
/
Copy pathvalues.yaml
4791 lines (4119 loc) · 175 KB
/
values.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
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
# Grafana Enterprise Metrics specific values and features are found after the `enterprise:` key
#
# The default values specified in this file are enough to deploy all of the
# Grafana Mimir or Grafana Enterprise Metrics microservices but are not suitable for
# production load.
# To configure the resources for production load, refer to the small.yaml or
# large.yaml values files.
# Note: The values in this file are not backward compatible. Copying and pasting the values is discouraged, but if you do so,
# make sure to use the values.yaml from the branch or tag that matches the mimir-distributed Helm chart version that you
# want to install. You also can see values.yaml for a specific version by running
# `helm show values grafana/mimir-distributed --version <version>`
# If you want to get the values file from Github, build the URL as follows because we git tag every release:
# `https://github.com/grafana/mimir/blob/mimir-distributed-<chart-version>/operations/helm/charts/mimir-distributed/values.yaml`.
# For example, https://github.com/grafana/mimir/blob/mimir-distributed-3.1.0/operations/helm/charts/mimir-distributed/values.yaml.
# -- Overrides the version used to determine compatibility of resources with the target Kubernetes cluster.
# This is useful when using `helm template`, because then helm will use the client version of kubectl as the Kubernetes version,
# which may or may not match your cluster's server version. Example: 'v1.24.4'. Set to null to use the version that helm
# devises.
kubeVersionOverride: null
# -- Overrides the chart's name. Used to change mimir/enterprise-metrics infix in the resource names. E.g. myRelease-mimir-ingester-1 to myRelease-nameOverride-ingester-1.
# This option is used to align resource names with Cortex, when doing a migration from Cortex to Grafana Mimir.
# Note: Grafana provided dashboards rely on the default naming and will need changes.
nameOverride: null
# -- Overrides the chart's computed fullname. Used to change the full prefix of resource names. E.g. myRelease-mimir-ingester-1 to fullnameOverride-ingester-1.
# Note: Grafana provided dashboards rely on the default naming and will need changes.
fullnameOverride: null
image:
# -- Grafana Mimir container image repository. Note: for Grafana Enterprise Metrics use the value 'enterprise.image.repository'
repository: grafana/mimir
# -- Grafana Mimir container image tag. Note: for Grafana Enterprise Metrics use the value 'enterprise.image.tag'
tag: 2.15.0
# -- Container pull policy - shared between Grafana Mimir and Grafana Enterprise Metrics
pullPolicy: IfNotPresent
# -- Optionally specify an array of imagePullSecrets - shared between Grafana Mimir and Grafana Enterprise Metrics
# Secrets must be manually created in the namespace.
# ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/
# pullSecrets:
# - myRegistryKeySecretName
global:
# -- Definitions to set up nginx resolver
dnsService: kube-dns
dnsNamespace: kube-system
clusterDomain: cluster.local.
# -- Common environment variables to add to all pods directly managed by this chart.
# scope: admin-api, alertmanager, compactor, continuous-test, distributor, gateway, graphite-proxy, ingester, memcached, nginx, overrides-exporter, querier, query-frontend, query-scheduler, ruler, store-gateway, smoke-test, tokengen, federation-frontend
extraEnv: []
# -- Common source of environment injections to add to all pods directly managed by this chart.
# scope: admin-api, alertmanager, compactor, continuous-test, distributor, gateway, graphite-proxy, ingester, memcached, nginx, overrides-exporter, querier, query-frontend, query-scheduler, ruler, store-gateway, smoke-test, tokengen, federation-frontend
# For example to inject values from a Secret, use:
# extraEnvFrom:
# - secretRef:
# name: mysecret
extraEnvFrom: []
# -- Common volumes to add to all pods directly managed by this chart.
# scope: admin-api, alertmanager, compactor, continuous-test, distributor, gateway, graphite-proxy, ingester, memcached, nginx, overrides-exporter, querier, query-frontend, query-scheduler, ruler, store-gateway, smoke-test, tokengen, federation-frontend
extraVolumes: []
# -- Common mount points to add to all pods directly managed by this chart.
# scope: admin-api, alertmanager, compactor, continuous-test, distributor, gateway, graphite-proxy, ingester, memcached, nginx, overrides-exporter, querier, query-frontend, query-scheduler, ruler, store-gateway, smoke-test, tokengen, federation-frontend
extraVolumeMounts: []
# -- Pod annotations for all pods directly managed by this chart. Usable for example to associate a version to 'global.extraEnv' and 'global.extraEnvFrom' and trigger a restart of the affected services.
# scope: admin-api, alertmanager, compactor, distributor, gateway, ingester, memcached, nginx, overrides-exporter, querier, query-frontend, query-scheduler, ruler, store-gateway, tokengen, federation-frontend
podAnnotations: {}
# -- Pod labels for all pods directly managed by this chart.
# scope: admin-api, alertmanager, compactor, distributor, gateway, ingester, memcached, nginx, overrides-exporter, querier, query-frontend, query-scheduler, ruler, store-gateway, tokengen, federation-frontend
podLabels: {}
serviceAccount:
# -- Whether to create a service account or not. In case 'create' is false, do set 'name' to an existing service account name.
create: true
# -- Override for the generated service account name.
name:
annotations: {}
labels: {}
# -- Configuration is loaded from the secret called 'externalConfigSecretName'. If 'useExternalConfig' is true, then the configuration is not generated, just consumed.
useExternalConfig: false
# -- Defines what kind of object stores the configuration, a ConfigMap or a Secret.
# In order to move sensitive information (such as credentials) from the ConfigMap/Secret to a more secure location (e.g. vault), it is possible to use [environment variables in the configuration](https://grafana.com/docs/mimir/latest/reference-configuration-parameters/#use-environment-variables-in-the-configuration).
# Such environment variables can be then stored in a separate Secret and injected via the global.extraEnvFrom value. For details about environment injection from a Secret please see [Secrets](https://kubernetes.io/docs/concepts/configuration/secret/#use-case-as-container-environment-variables).
configStorageType: ConfigMap
# -- Name of the Secret or ConfigMap that contains the configuration (used for naming even if config is internal).
externalConfigSecretName: '{{ include "mimir.resourceName" (dict "ctx" . "component" "config") }}'
# -- When 'useExternalConfig' is true, then changing 'externalConfigVersion' triggers restart of services - otherwise changes to the configuration cause a restart.
externalConfigVersion: "0"
# --Vault Agent config to mount secrets to TLS configurable components. This requires Vault and Vault Agent to already be running.
vaultAgent:
enabled: false
# -- Vault Kubernetes Authentication role
roleName: ""
# -- Path to client certificate in Vault
clientCertPath: ""
# -- Path to client key in Vault
clientKeyPath: ""
# -- Path to server certificate in Vault
serverCertPath: ""
# -- Path to server key in Vault
serverKeyPath: ""
# -- Path to client CA certificate in Vault
caCertPath: ""
mimir:
# -- Base config file for Grafana Mimir and Grafana Enterprise Metrics. Contains Helm templates that are evaulated at install/upgrade.
# To modify the resulting configuration, either copy and alter 'mimir.config' as a whole or use the 'mimir.structuredConfig' to add and modify certain YAML elements.
config: |
usage_stats:
installation_mode: helm
activity_tracker:
filepath: /active-query-tracker/activity.log
{{- if .Values.enterprise.enabled }}
admin_api:
leader_election:
enabled: true
ring:
kvstore:
store: "memberlist"
admin_client:
storage:
{{- if .Values.minio.enabled }}
type: s3
s3:
access_key_id: {{ .Values.minio.rootUser }}
bucket_name: enterprise-metrics-admin
endpoint: {{ template "minio.fullname" .Subcharts.minio }}.{{ .Release.Namespace }}.svc:{{ .Values.minio.service.port }}
insecure: true
secret_access_key: {{ .Values.minio.rootPassword }}
{{- end }}
{{- if (index .Values "admin-cache" "enabled") }}
cache:
backend: memcached
memcached:
addresses: {{ include "mimir.adminCacheAddress" . }}
max_item_size: {{ mul (index .Values "admin-cache").maxItemMemory 1024 1024 }}
{{- end }}
{{- end }}
alertmanager:
data_dir: /data
enable_api: true
external_url: /alertmanager
{{- if .Values.alertmanager.zoneAwareReplication.enabled }}
sharding_ring:
zone_awareness_enabled: true
{{- end }}
{{- if .Values.alertmanager.fallbackConfig }}
fallback_config_file: /configs/alertmanager_fallback_config.yaml
{{- end }}
{{- if .Values.minio.enabled }}
alertmanager_storage:
backend: s3
s3:
access_key_id: {{ .Values.minio.rootUser }}
bucket_name: {{ include "mimir.minioBucketPrefix" . }}-ruler
endpoint: {{ template "minio.fullname" .Subcharts.minio }}.{{ .Release.Namespace }}.svc:{{ .Values.minio.service.port }}
insecure: true
secret_access_key: {{ .Values.minio.rootPassword }}
{{- end }}
{{- if .Values.enterprise.enabled }}
auth:
type: enterprise
admin:
pass_access_policy_name: true
pass_token_name: true
{{- end }}
# This configures how the store-gateway synchronizes blocks stored in the bucket. It uses Minio by default for getting started (configured via flags) but this should be changed for production deployments.
blocks_storage:
backend: s3
bucket_store:
{{- if index .Values "chunks-cache" "enabled" }}
chunks_cache:
backend: memcached
memcached:
addresses: {{ include "mimir.chunksCacheAddress" . }}
max_item_size: {{ mul (index .Values "chunks-cache").maxItemMemory 1024 1024 }}
timeout: 750ms
max_idle_connections: 150
{{- end }}
{{- if index .Values "index-cache" "enabled" }}
index_cache:
backend: memcached
memcached:
addresses: {{ include "mimir.indexCacheAddress" . }}
max_item_size: {{ mul (index .Values "index-cache").maxItemMemory 1024 1024 }}
timeout: 750ms
max_idle_connections: 150
{{- end }}
{{- if index .Values "metadata-cache" "enabled" }}
metadata_cache:
backend: memcached
memcached:
addresses: {{ include "mimir.metadataCacheAddress" . }}
max_item_size: {{ mul (index .Values "metadata-cache").maxItemMemory 1024 1024 }}
max_idle_connections: 150
{{- end }}
sync_dir: /data/tsdb-sync
{{- if .Values.minio.enabled }}
s3:
access_key_id: {{ .Values.minio.rootUser }}
bucket_name: {{ include "mimir.minioBucketPrefix" . }}-tsdb
endpoint: {{ template "minio.fullname" .Subcharts.minio }}.{{ .Release.Namespace }}.svc:{{ .Values.minio.service.port }}
insecure: true
secret_access_key: {{ .Values.minio.rootPassword }}
{{- end }}
tsdb:
dir: /data/tsdb
head_compaction_interval: 15m
wal_replay_concurrency: 3
{{- if .Values.enterprise.enabled }}
cluster_name: "{{ .Release.Name }}"
{{- end }}
compactor:
compaction_interval: 30m
deletion_delay: 2h
max_closing_blocks_concurrency: 2
max_opening_blocks_concurrency: 4
symbols_flushers_concurrency: 4
first_level_compaction_wait_period: 25m
data_dir: "/data"
sharding_ring:
wait_stability_min_duration: 1m
heartbeat_period: 1m
heartbeat_timeout: 4m
distributor:
ring:
heartbeat_period: 1m
heartbeat_timeout: 4m
frontend:
parallelize_shardable_queries: true
{{- if index .Values "results-cache" "enabled" }}
results_cache:
backend: memcached
memcached:
timeout: 500ms
addresses: {{ include "mimir.resultsCacheAddress" . }}
max_item_size: {{ mul (index .Values "results-cache").maxItemMemory 1024 1024 }}
cache_results: true
query_sharding_target_series_per_shard: 2500
{{- end }}
{{- if and .Values.query_scheduler.enabled (not .Values.federation_frontend.disableOtherComponents) }}
scheduler_address: {{ template "mimir.fullname" . }}-query-scheduler-headless.{{ .Release.Namespace }}.svc:{{ include "mimir.serverGrpcListenPort" . }}
{{- end }}
{{- if .Values.enterprise.enabled }}
log_query_request_headers: X-Access-Policy-Name,X-Token-Name
{{- end }}
frontend_worker:
grpc_client_config:
max_send_msg_size: 419430400 # 400MiB
{{- if .Values.query_scheduler.enabled }}
scheduler_address: {{ template "mimir.fullname" . }}-query-scheduler-headless.{{ .Release.Namespace }}.svc:{{ include "mimir.serverGrpcListenPort" . }}
{{- else }}
frontend_address: {{ template "mimir.fullname" . }}-query-frontend-headless.{{ .Release.Namespace }}.svc:{{ include "mimir.serverGrpcListenPort" . }}
{{- end }}
{{- if and .Values.enterprise.enabled }}
gateway:
proxy:
admin_api:
url: http://{{ template "mimir.fullname" . }}-admin-api.{{ .Release.Namespace }}.svc:{{ include "mimir.serverHttpListenPort" . }}
alertmanager:
url: http://{{ template "mimir.fullname" . }}-alertmanager-headless.{{ .Release.Namespace }}.svc:{{ include "mimir.serverHttpListenPort" . }}
compactor:
url: http://{{ template "mimir.fullname" . }}-compactor.{{ .Release.Namespace }}.svc:{{ include "mimir.serverHttpListenPort" . }}
default:
url: http://{{ template "mimir.fullname" . }}-admin-api.{{ .Release.Namespace }}.svc:{{ include "mimir.serverHttpListenPort" . }}
{{- if and .Values.distributor.enabled (not .Values.federation_frontend.disableOtherComponents) }}
distributor:
url: dns:///{{ template "mimir.fullname" . }}-distributor-headless.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}:{{ include "mimir.serverGrpcListenPort" . }}
{{- end }}
ingester:
url: http://{{ template "mimir.fullname" . }}-ingester-headless.{{ .Release.Namespace }}.svc:{{ include "mimir.serverHttpListenPort" . }}
query_frontend:
{{ if .Values.federation_frontend.enabled }}
url: http://{{ template "mimir.fullname" . }}-federation-frontend.{{ .Release.Namespace }}.svc:{{ include "mimir.serverHttpListenPort" . }}
{{ else }}
url: http://{{ template "mimir.fullname" . }}-query-frontend.{{ .Release.Namespace }}.svc:{{ include "mimir.serverHttpListenPort" . }}
{{ end }}
ruler:
url: http://{{ template "mimir.fullname" . }}-ruler.{{ .Release.Namespace }}.svc:{{ include "mimir.serverHttpListenPort" . }}
store_gateway:
url: http://{{ template "mimir.fullname" . }}-store-gateway-headless.{{ .Release.Namespace }}.svc:{{ include "mimir.serverHttpListenPort" . }}
{{- if and .Values.enterprise.enabled .Values.graphite.enabled }}
graphite_write_proxy:
url: http://{{ template "mimir.fullname" . }}-graphite-write-proxy.{{ .Release.Namespace }}.svc:{{ include "mimir.serverHttpListenPort" . }}
graphite_querier:
url: http://{{ template "mimir.fullname" . }}-graphite-querier.{{ .Release.Namespace }}.svc:{{ include "mimir.serverHttpListenPort" . }}
{{- end}}
{{- end }}
ingester:
ring:
final_sleep: 0s
num_tokens: 512
tokens_file_path: /data/tokens
unregister_on_shutdown: false
heartbeat_period: 2m
heartbeat_timeout: 10m
{{- if .Values.ingester.zoneAwareReplication.enabled }}
zone_awareness_enabled: true
{{- end }}
ingester_client:
grpc_client_config:
max_recv_msg_size: 104857600
max_send_msg_size: 104857600
{{- if .Values.enterprise.enabled }}
instrumentation:
enabled: {{ and .Values.distributor.enabled (not .Values.federation_frontend.disableOtherComponents) }}
{{- if and .Values.distributor.enabled (not .Values.federation_frontend.disableOtherComponents) }}
distributor_client:
address: dns:///{{ template "mimir.fullname" . }}-distributor-headless.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}:{{ include "mimir.serverGrpcListenPort" . }}
{{- end }}
license:
path: "/license/license.jwt"
{{- end }}
limits:
# Limit queries to 500 days. You can override this on a per-tenant basis.
max_total_query_length: 12000h
# Adjust max query parallelism to 16x sharding, without sharding we can run 15d queries fully in parallel.
# With sharding we can further shard each day another 16 times. 15 days * 16 shards = 240 subqueries.
max_query_parallelism: 240
# Avoid caching results newer than 10m because some samples can be delayed
# This presents caching incomplete results
max_cache_freshness: 10m
memberlist:
abort_if_cluster_join_fails: false
compression_enabled: false
join_members:
- dns+{{ include "mimir.fullname" . }}-gossip-ring.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}:{{ include "mimir.memberlistBindPort" . }}
querier:
# With query sharding we run more but smaller queries. We must strike a balance
# which allows us to process more sharded queries in parallel when requested, but not overload
# queriers during non-sharded queries.
max_concurrent: 16
query_scheduler:
# Increase from default of 100 to account for queries created by query sharding
max_outstanding_requests_per_tenant: 800
ruler:
alertmanager_url: dnssrvnoa+http://_http-metrics._tcp.{{ template "mimir.fullname" . }}-alertmanager-headless.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}/alertmanager
enable_api: true
rule_path: /data
{{- if .Values.ruler.remoteEvaluationDedicatedQueryPath }}
query_frontend:
address: dns:///{{ template "mimir.fullname" . }}-ruler-query-frontend.{{ .Release.Namespace }}.svc:{{ include "mimir.serverGrpcListenPort" . }}
{{- end }}
{{- if or (.Values.minio.enabled) (index .Values "metadata-cache" "enabled") }}
ruler_storage:
{{- if .Values.minio.enabled }}
backend: s3
s3:
endpoint: {{ template "minio.fullname" .Subcharts.minio }}.{{ .Release.Namespace }}.svc:{{ .Values.minio.service.port }}
bucket_name: {{ include "mimir.minioBucketPrefix" . }}-ruler
access_key_id: {{ .Values.minio.rootUser }}
secret_access_key: {{ .Values.minio.rootPassword }}
insecure: true
{{- end }}
{{- if index .Values "metadata-cache" "enabled" }}
cache:
backend: memcached
memcached:
addresses: {{ include "mimir.metadataCacheAddress" . }}
max_item_size: {{ mul (index .Values "metadata-cache").maxItemMemory 1024 1024 }}
{{- end }}
{{- end }}
{{- if not .Values.federation_frontend.disableOtherComponents }}
runtime_config:
file: /var/{{ include "mimir.name" . }}/runtime.yaml
{{- end }}
store_gateway:
sharding_ring:
heartbeat_period: 1m
heartbeat_timeout: 4m
wait_stability_min_duration: 1m
{{- if .Values.store_gateway.zoneAwareReplication.enabled }}
kvstore:
prefix: multi-zone/
{{- end }}
tokens_file_path: /data/tokens
unregister_on_shutdown: false
{{- if .Values.store_gateway.zoneAwareReplication.enabled }}
zone_awareness_enabled: true
{{- end }}
{{- if and .Values.enterprise.enabled .Values.graphite.enabled }}
graphite:
enabled: true
write_proxy:
distributor_client:
address: dns:///{{ template "mimir.fullname" . }}-distributor.{{ .Release.Namespace }}.svc:{{ include "mimir.serverGrpcListenPort" . }}
querier:
remote_read:
query_address: http://{{ template "mimir.fullname" . }}-query-frontend.{{ .Release.Namespace }}.svc:{{ include "mimir.serverHttpListenPort" . }}/prometheus
proxy_bad_requests: false
schemas:
default_storage_schemas_file: /etc/graphite-proxy/storage-schemas.conf
default_storage_aggregations_file: /etc/graphite-proxy/storage-aggregations.conf
aggregation_cache:
memcached:
addresses: dnssrvnoa+{{ template "mimir.fullname" . }}-gr-aggr-cache.{{ .Release.Namespace}}.svc:11211
timeout: 1s
metric_name_cache:
memcached:
addresses: dnssrvnoa+{{ template "mimir.fullname" . }}-gr-metricname-cache.{{ .Release.Namespace}}.svc:11211
timeout: 1s
{{- end}}
# -- Additional structured values on top of the text based 'mimir.config'. Applied after the text based config is evaluated for templates. Enables adding and modifying YAML elements in the evaulated 'mimir.config'.
#
# Additionally, consider the optional "insecure_skip_verify" key below, it allows you to skip_verify_false in case the s3_endpoint certificate is not trusted.
# For more information see https://grafana.com/docs/mimir/latest/references/configuration-parameters/
#
# Example:
#
# structuredConfig:
# common:
# storage:
# backend: s3
# s3:
# bucket_name: "${BUCKET_NAME}"
# endpoint: "${BUCKET_HOST}:${BUCKET_PORT}"
# access_key_id: "${AWS_ACCESS_KEY_ID}" # This is a secret injected via an environment variable
# secret_access_key: "${AWS_SECRET_ACCESS_KEY}" # This is a secret injected via an environment variable
# http:
# insecure_skip_verify: true
structuredConfig: {}
# -- runtimeConfig provides a reloadable runtime configuration. Changing the runtimeConfig doesn't require a restart of all components.
# For more infromation see https://grafana.com/docs/mimir/latest/configure/about-runtime-configuration/
#
# Example:
#
# runtimeConfig:
# ingester_limits: # limits that each ingester replica enforces
# max_ingestion_rate: 20000
# max_series: 1500000
# max_tenants: 1000
# max_inflight_push_requests: 30000
# distributor_limits: # limits that each distributor replica enforces
# max_ingestion_rate: 20000
# max_inflight_push_requests: 30000
# max_inflight_push_requests_bytes: 50000000
# overrides:
# tenant-1: # limits for tenant-1 that the whole cluster enforces
# ingestion_tenant_shard_size: 9
# max_global_series_per_user: 1500000
# max_fetched_series_per_query: 100000
runtimeConfig: {}
# RBAC configuration
rbac:
# -- If true, PodSecurityPolicy will be rendered by the chart on Kuberentes 1.24.
# By default the PodSecurityPolicy is not rendered on version 1.24.
create: true
# -- PSP configuration
podSecurityPolicy:
seccompProfile: runtime/default
privileged: false
allowPrivilegeEscalation: false
hostNetwork: false
hostIPC: false
hostPID: false
readOnlyRootFilesystem: true
runAsUser:
rule: "MustRunAsNonRoot"
seLinux:
rule: "RunAsAny"
supplementalGroups:
rule: "MustRunAs"
ranges:
- min: 1
max: 65535
fsGroup:
rule: "MustRunAs"
ranges:
- min: 1
max: 65535
additionalVolumes: []
forcePSPOnKubernetes124: false
# -- For GKE/EKS/AKS use 'type: psp'. For OpenShift use 'type: scc'
type: psp
# -- podSecurityContext is the default pod security context for Mimir, GEM, gateway, and cache components.
# When installing on OpenShift, override podSecurityContext settings with
#
# rbac:
# podSecurityContext:
# fsGroup: null
# runAsGroup: null
# runAsUser: null
podSecurityContext:
fsGroup: 10001
runAsGroup: 10001
runAsNonRoot: true
runAsUser: 10001
seccompProfile:
type: RuntimeDefault
# -- KEDA Autoscaling configuration
kedaAutoscaling:
# -- A Prometheus-compatible URL. Cadvisor and Mimir metrics for the Mimir pods are expected in this server.
# For more information on the required metrics see [Monitor system health](https://grafana.com/docs/helm-charts/mimir-distributed/latest/run-production-environment-with-helm/monitor-system-health/).
# If empty, the helm chart uses the metamonitoring URL from metaMonitoring.grafanaAgent.metrics.remote.url.
# If that is empty, then the Mimir cluster is used.
prometheusAddress: ""
customHeaders: {}
pollingInterval: 10
alertmanager:
enabled: true
# -- Total number of replicas for the alertmanager across all availability zones
# If alertmanager.zoneAwareReplication.enabled=false, this number is taken as is.
# Otherwise each zone starts `ceil(replicas / number_of_zones)` number of pods.
# E.g. if 'replicas' is set to 4 and there are 3 zones, then 4/3=1.33 and after rounding up it means 2 pods per zone are started.
replicas: 1
# -- Allows to override the container image of the alertmanager component.
# When set it takes precedence over what is defined in global "image" or "enterprise.image" sections.
image:
# repository: grafana/mimir
# tag: 2.15.0
statefulSet:
enabled: true
# -- Dedicated service account for alertmanager pods.
# If not set, the default service account defined at the begining of this file will be used.
# This service account can be used even if the default one is not set.
serviceAccount:
create: false
# -- Alertmanager specific service account name. If not set and create is set to true, the default
# name will be the default mimir service account's name with the "-alertmanager" suffix.
name: ""
annotations: {}
labels: {}
service:
annotations: {}
labels: {}
# -- https://kubernetes.io/docs/concepts/services-networking/service-traffic-policy/
internalTrafficPolicy: Cluster
type: ClusterIP
# -- Optionally set the scheduler for pods of the alertmanager
schedulerName: ""
resources:
requests:
cpu: 10m
memory: 32Mi
# -- Fallback config for alertmanager.
# When a tenant doesn't have an Alertmanager configuration, the Grafana Mimir Alertmanager uses the fallback configuration.
fallbackConfig: |
receivers:
- name: default-receiver
route:
receiver: default-receiver
extraArgs: {}
# Pod Labels
podLabels: {}
# Pod Annotations
podAnnotations: {}
# -- Pod Disruption Budget for alertmanager, this will be applied across availability zones to prevent losing redundancy
podDisruptionBudget:
maxUnavailable: 1
# -- The name of the PriorityClass for alertmanager pods
priorityClassName: null
# -- NodeSelector to pin alertmanager pods to certain set of nodes. This is ignored when alertmanager.zoneAwareReplication.enabled=true.
nodeSelector: {}
# -- Pod affinity settings for the alertmanager. This is ignored when alertmanager.zoneAwareReplication.enabled=true.
affinity: {}
# -- topologySpreadConstraints allows to customize the default topologySpreadConstraints. This can be either a single dict as shown below or a slice of topologySpreadConstraints.
# labelSelector is taken from the constraint itself (if it exists) or is generated by the chart using the same selectors as for services.
topologySpreadConstraints:
maxSkew: 1
topologyKey: kubernetes.io/hostname
whenUnsatisfiable: ScheduleAnyway
# minDomains: 1
# nodeAffinityPolicy: Honor
# nodeTaintsPolicy: Honor
# matchLabelKeys:
# - pod-template-hash
annotations: {}
persistence:
# SubPath in emptyDir for persistence, only enabled if alertmanager.statefulSet.enabled is false
subPath:
persistentVolume:
# If true and alertmanager.statefulSet.enabled is true,
# Alertmanager will create/use a Persistent Volume Claim
# If false, use emptyDir
enabled: true
# Alertmanager data Persistent Volume Claim annotations
#
annotations: {}
# Alertmanager data Persistent Volume access modes
# Must match those of existing PV or dynamic provisioner
# Ref: http://kubernetes.io/docs/user-guide/persistent-volumes/
#
accessModes:
- ReadWriteOnce
# Alertmanager data Persistent Volume size
#
size: 1Gi
# Subdirectory of Alertmanager data Persistent Volume to mount
# Useful if the volume's root directory is not empty
#
subPath: ""
# Alertmanager data Persistent Volume Storage Class
# If defined, storageClassName: <storageClass>
# If set to "-", storageClassName: "", which disables dynamic provisioning
# If undefined (the default) or set to null, no storageClassName spec is
# set, choosing the default provisioner.
#
# A per-zone storageClass configuration in `alertmanager.zoneAwareReplication.zones[*].storageClass` takes precedence over this field.
# storageClass: "-"
# -- Enable StatefulSetAutoDeletePVC feature
# https://kubernetes.io/docs/concepts/workloads/controllers/statefulset/#persistentvolumeclaim-retention
enableRetentionPolicy: false
whenDeleted: Retain
whenScaled: Retain
readinessProbe:
httpGet:
path: /ready
port: http-metrics
initialDelaySeconds: 45
# -- SecurityContext override for alermeneger pods
securityContext: {}
# -- The SecurityContext for alertmanager containers
containerSecurityContext:
allowPrivilegeEscalation: false
readOnlyRootFilesystem: true
capabilities:
drop: [ALL]
# Tolerations for pod assignment
# ref: https://kubernetes.io/docs/concepts/configuration/taint-and-toleration/
tolerations: []
strategy:
type: RollingUpdate
rollingUpdate:
maxSurge: 0
maxUnavailable: 1
# -- updateStrategy of the alertmanager statefulset. This is ignored when alertmanager.zoneAwareReplication.enabled=true.
statefulStrategy:
type: RollingUpdate
terminationGracePeriodSeconds: 900
initContainers: []
# Init containers to be added to the alertmanager pod.
# - name: my-init-container
# image: busybox:latest
# command: ['sh', '-c', 'echo hello']
extraContainers: []
# Additional containers to be added to the alertmanager pod.
# - name: reverse-proxy
# image: angelbarrera92/basic-auth-reverse-proxy:dev
# args:
# - "serve"
# - "--upstream=http://localhost:3100"
# - "--auth-config=/etc/reverse-proxy-conf/authn.yaml"
# ports:
# - name: http
# containerPort: 11811
# protocol: TCP
# volumeMounts:
# - name: reverse-proxy-auth-config
# mountPath: /etc/reverse-proxy-conf
extraVolumes: []
# Additional volumes to the alertmanager pod.
# - name: reverse-proxy-auth-config
# secret:
# secretName: reverse-proxy-auth-config
# Extra volume mounts that will be added to the alertmanager container
extraVolumeMounts: []
# Extra env variables to pass to the alertmanager container
env: []
extraEnvFrom: []
# -- Jaeger reporter queue size
# Set to 'null' to use the Jaeger client's default value
jaegerReporterMaxQueueSize: null
# -- Options to configure zone-aware replication for alertmanager
# Example configuration with full geographical redundancy:
# rollout_operator:
# enabled: true
# alertmanager:
# zoneAwareReplication:
# enabled: true
# topologyKey: 'kubernetes.io/hostname' # This generates default anti-affinity rules
# zones: # Zone list has to be fully redefined for modification. Update with you actual zones or skip to use logical zones only.
# - name: zone-a
# nodeSelector:
# topology.kubernetes.io/zone: us-central1-a
# - name: zone-b
# nodeSelector:
# topology.kubernetes.io/zone: us-central1-b
# - name: zone-c
# nodeSelector:
# topology.kubernetes.io/zone: us-central1-c
#
zoneAwareReplication:
# -- Enable zone-aware replication for alertmanager
enabled: false
# -- Maximum number of alertmanagers that can be unavailable per zone during rollout
maxUnavailable: 2
# -- topologyKey to use in pod anti-affinity. If unset, no anti-affinity rules are generated. If set, the generated anti-affinity rule makes sure that pods from different zones do not mix.
# E.g.: topologyKey: 'kubernetes.io/hostname'
topologyKey: null
# -- Auxiliary values for migration, see https://grafana.com/docs/helm-charts/mimir-distributed/latest/migration-guides/migrate-from-single-zone-with-helm/
migration:
# -- Indicate if migration is ongoing for multi zone alertmanager
enabled: false
# -- Start zone-aware alertmanagers
writePath: false
# -- Zone definitions for alertmanager zones. Note: you have to redefine the whole list to change parts as YAML does not allow to modify parts of a list.
zones:
# -- Name of the zone, used in labels and selectors. Must follow Kubernetes naming restrictions: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/
- name: zone-a
# -- nodeselector to restrict where pods of this zone can be placed. E.g.:
# nodeSelector:
# topology.kubernetes.io/zone: zone-a
nodeSelector: null
# -- extraAffinity adds user defined custom affinity rules (merged with generated rules)
extraAffinity: {}
# -- Alertmanager data Persistent Volume Storage Class
# If defined, storageClassName: <storageClass>
# If set to "-", then use `storageClassName: ""`, which disables dynamic provisioning
# If undefined or set to null (the default), then fall back to the value of `alertmanager.persistentVolume.storageClass`.
storageClass: null
# -- Name of the zone, used in labels and selectors. Must follow Kubernetes naming restrictions: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/
- name: zone-b
# -- nodeselector to restrict where pods of this zone can be placed. E.g.:
# nodeSelector:
# topology.kubernetes.io/zone: zone-b
nodeSelector: null
# -- extraAffinity adds user defined custom affinity rules (merged with generated rules)
extraAffinity: {}
# -- Alertmanager data Persistent Volume Storage Class
# If defined, storageClassName: <storageClass>
# If set to "-", then use `storageClassName: ""`, which disables dynamic provisioning
# If undefined or set to null (the default), then fall back to the value of `alertmanager.persistentVolume.storageClass`.
storageClass: null
# -- Name of the zone, used in labels and selectors. Must follow Kubernetes naming restrictions: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/
- name: zone-c
# -- nodeselector to restrict where pods of this zone can be placed. E.g.:
# nodeSelector:
# topology.kubernetes.io/zone: zone-c
nodeSelector: null
# -- extraAffinity adds user defined custom affinity rules (merged with generated rules)
extraAffinity: {}
# -- Alertmanager data Persistent Volume Storage Class
# If defined, storageClassName: <storageClass>
# If set to "-", then use `storageClassName: ""`, which disables dynamic provisioning
# If undefined or set to null (the default), then fall back to the value of `alertmanager.persistentVolume.storageClass`.
storageClass: null
distributor:
# -- Whether to render the manifests related to the distributor component.
enabled: true
# -- Allows to override the container image of the distributor component.
# When set it takes precedence over what is defined in global "image" or "enterprise.image" sections.
image:
# repository: grafana/mimir
# tag: 2.15.0
# Setting it to null will produce a deployment without replicas set, allowing you to use autoscaling with the deployment
replicas: 1
# -- [Experimental] Configure autoscaling via KEDA (https://keda.sh). This requires having
# KEDA already installed in the Kubernetes cluster. The metrics for scaling are read
# according to top-level kedaAutoscaling.prometheusAddress (defaulting to metamonitoring remote-write destination).
# Basic auth and extra HTTP headers from metaMonitoring are ignored, please use customHeaders.
# The remote URL is used even if metamonitoring is disabled.
# See https://github.com/grafana/mimir/issues/7367 for more details on how to migrate to autoscaled resources without disruptions.
kedaAutoscaling:
enabled: false
# -- preserveReplicas gives you the option to migrate from non-autoscaled to autoscaled deployments without losing replicas. When set to true, the replica fields in the component will be left intact.
# For futher details see [helm: autoscaling migration procedure](https://github.com/grafana/mimir/issues/7367)
preserveReplicas: false
minReplicaCount: 1
maxReplicaCount: 10
targetCPUUtilizationPercentage: 100
targetMemoryUtilizationPercentage: 100
behavior:
scaleDown:
policies:
- periodSeconds: 600
type: Percent
value: 10
service:
annotations: {}
labels: {}
# -- https://kubernetes.io/docs/concepts/services-networking/service-traffic-policy/
internalTrafficPolicy: Cluster
type: ClusterIP
resources:
requests:
cpu: 100m
memory: 512Mi
# Additional distributor container arguments, e.g. log level (debug, info, warn, error)
extraArgs: {}
# Pod Labels
podLabels: {}
# Pod Annotations
podAnnotations: {}
# Pod Disruption Budget
podDisruptionBudget:
maxUnavailable: 1
# -- The name of the PriorityClass for distributor pods
priorityClassName: null
nodeSelector: {}
affinity: {}
# -- topologySpreadConstraints allows to customize the default topologySpreadConstraints. This can be either a single dict as shown below or a slice of topologySpreadConstraints.
# labelSelector is taken from the constraint itself (if it exists) or is generated by the chart using the same selectors as for services.
topologySpreadConstraints:
maxSkew: 1
topologyKey: kubernetes.io/hostname
whenUnsatisfiable: ScheduleAnyway
# minDomains: 1
# nodeAffinityPolicy: Honor
# nodeTaintsPolicy: Honor
# matchLabelKeys:
# - pod-template-hash
annotations: {}
persistence:
subPath:
readinessProbe:
httpGet:
path: /ready
port: http-metrics
initialDelaySeconds: 45
# -- SecurityContext override for distributor pods
securityContext: {}
# -- The SecurityContext for distributor containers
containerSecurityContext:
allowPrivilegeEscalation: false
readOnlyRootFilesystem: true
capabilities:
drop: [ALL]
strategy:
type: RollingUpdate
rollingUpdate:
maxUnavailable: 0
maxSurge: 15%
# Keep the termination grace period higher than the -shutdown-delay configured on the distributor.
terminationGracePeriodSeconds: 100
tolerations: []
initContainers: []
extraContainers: []
extraVolumes: []
extraVolumeMounts: []
env: []
extraEnvFrom: []
# -- Jaeger reporter queue size
# Set to 'null' to use the Jaeger client's default value
jaegerReporterMaxQueueSize: 1000
ingester:
# -- Whether to render the manifests related to the ingester component.
enabled: true
# -- Allows to override the container image of the ingester component.
# When set it takes precedence over what is defined in global "image" or "enterprise.image" sections.
image:
# repository: grafana/mimir
# tag: 2.15.0
# -- Total number of replicas for the ingester across all availability zones
# If ingester.zoneAwareReplication.enabled=false, this number is taken as is.
# Otherwise each zone starts `ceil(replicas / number_of_zones)` number of pods.
# E.g. if 'replicas' is set to 4 and there are 3 zones, then 4/3=1.33 and after rounding up it means 2 pods per zone are started.
replicas: 3
statefulSet:
enabled: true
service:
annotations: {}
labels: {}
# -- https://kubernetes.io/docs/concepts/services-networking/service-traffic-policy/
internalTrafficPolicy: Cluster
type: ClusterIP
# -- Optionally set the scheduler for pods of the ingester
schedulerName: ""
resources:
requests:
cpu: 100m
memory: 512Mi
# Additional ingester container arguments, e.g. log level (debug, info, warn, error)
extraArgs: {}
# Pod Labels
podLabels: {}
# Pod Annotations
podAnnotations: {}
# -- The name of the PriorityClass for ingester pods
priorityClassName: null
# -- Pod Disruption Budget for ingester, this will be applied across availability zones to prevent losing redundancy
podDisruptionBudget:
maxUnavailable: 1
podManagementPolicy: Parallel
# -- NodeSelector to pin ingester pods to certain set of nodes. This is ignored when ingester.zoneAwareReplication.enabled=true.
nodeSelector: {}
# -- Pod affinity settings for the ingester. This is ignored when ingester.zoneAwareReplication.enabled=true.
affinity: {}
# -- topologySpreadConstraints allows to customize the default topologySpreadConstraints. This can be either a single dict as shown below or a slice of topologySpreadConstraints.
# labelSelector is taken from the constraint itself (if it exists) or is generated by the chart using the same selectors as for services.
# It is recommended to replace this with requiredDuringSchedulingIgnoredDuringExecution podAntiAffinity rules when
# deploying to production.
topologySpreadConstraints:
maxSkew: 1
topologyKey: kubernetes.io/hostname