-
Notifications
You must be signed in to change notification settings - Fork 183
/
values.yaml
2685 lines (2415 loc) · 94.1 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
## Sumo Logic Kubernetes Collection configuration file
## All the comments start with two or more # characters
nameOverride: ""
fullnameOverride: ""
## Use the same namespace as namespaceOverride in 'kube-prometheus-stack.namespaceOverride' if Prometheus setup is also enabled
namespaceOverride: ""
sumologic:
### Setup
## If enabled, a pre-install hook will create Collector and Sources in Sumo Logic
setupEnabled: true
## If enabled, a pre-delete hook will destroy Collector in Sumo Logic
cleanupEnabled: false
## If enabled, accessId and accessKey will be sourced from Secret Name given
## Be sure to include at least the following env variables in your secret
## (1) SUMOLOGIC_ACCESSID, (2) SUMOLOGIC_ACCESSKEY
# envFromSecret: sumo-api-secret
## Sumo access ID
# accessId: ""
## Sumo access key
# accessKey: ""
## Sumo API endpoint; Leave blank for automatic endpoint discovery and redirection
## ref: https://help.sumologic.com/docs/api/getting-started#sumo-logic-endpoints-by-deployment-and-firewall-security
endpoint: ""
## proxy urls
httpProxy: ""
httpsProxy: ""
## Exclude Kubernetes internal traffic from proxy
noProxy: kubernetes.default.svc
## Collector name
# collectorName: ""
## Cluster name: Note spaces are not allowed and will be replaced with dashes.
clusterName: "kubernetes"
## Cluster DNS Domain
## We use the DNS domain in internal urls to speed up DNS resolution, see https://github.com/kubernetes/kubernetes/issues/56903
## Change this if you have set a non-default DNS domain in your cluster
clusterDNSDomain: "cluster.local"
## Configuration of Kubernetes for Terraform client
## https://www.terraform.io/docs/providers/kubernetes/index.html#argument-reference
## All double quotes should be escaped here regarding Terraform syntax
cluster:
host: "https://kubernetes.default.svc"
# username:
# password:
# insecure:
# client_certificate:
# client_key:
cluster_ca_certificate: '${file("/var/run/secrets/kubernetes.io/serviceaccount/ca.crt")}'
# config_path:
# config_context:
# config_context_auth_info:
# config_context_cluster:
token: '${file("/var/run/secrets/kubernetes.io/serviceaccount/token")}'
# exec:
# api_version:
# command:
# args: []
# env: {}
## Enable autoscaling for components that support it: logs metadata, metrics metadata, metrics collector, otelcol instrumentation, and traces gateway
autoscaling:
enabled: true
## If you set it to false, it would set EXCLUDE_NAMESPACE=<release-namespace>
## and not add the Otelcol logs and Prometheus remotestorage metrics.
collectionMonitoring: true
## Optionally specify an array of pullSecrets.
## They will be added to serviceaccount that is used for Sumo Logic's
## deployments and statefulsets.
## Secrets must be manually created in the namespace.
## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/
##
# pullSecrets:
# - name: myRegistryKeySecretName
## Add custom labels to the following sumologic resources(otelcol sts, setup job, otelcol deployment)
podLabels: {}
## Add custom annotations to the following sumologic resources(otelcol sts, setup job, otelcol deployment)
podAnnotations: {}
## Global configuration of node selectors
nodeSelector: {}
## Global configuration of tolerations
tolerations: []
## Global configuration of affinity
affinity: {}
## Add custom annotations to sumologic serviceAccounts
serviceAccount:
annotations: {}
## creation of Security Context Constraints in Openshift
scc:
create: false
setup:
## uncomment to force collection installation (disables k8s version verification)
# force: true
job:
image:
repository: public.ecr.aws/sumologic/kubernetes-setup
tag: 3.15.1
pullPolicy: IfNotPresent
initContainerImage:
repository: public.ecr.aws/sumologic/busybox
tag: latest
## Optionally specify an array of pullSecrets.
## They will be added to serviceaccount that is used for Sumo Logic's
## setup job.
## Secrets must be manually created in the namespace.
## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/
##
# pullSecrets:
# - name: myRegistryKeySecretName
resources:
limits:
memory: 256Mi
cpu: 2000m
requests:
memory: 64Mi
cpu: 200m
nodeSelector: {}
## Add custom labels only to setup job pod
## Node tolerations for server scheduling to nodes with taints
## Ref: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/
##
tolerations: []
# - key: null
# operator: Exists
# effect: "NoSchedule"
## Affinity and anti-affinity
## Ref: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/#affinity-and-anti-affinity
##
affinity: {}
podLabels: {}
## Add custom annotations only to setup job pod
podAnnotations: {}
## Time in seconds after which the job result will be removed from the Kubernetes cluster
ttlSecondsAfterFinished: 120
## uncomment for the debug mode (disables the automatic run of the setup.sh script)
# debug: true
monitors:
## If enabled, a pre-install hook will create k8s monitors in Sumo Logic
enabled: true
## The installed monitors default status: enabled/disabled
monitorStatus: enabled
## A list of emails to send notifications from monitors
notificationEmails: []
dashboards:
## If enabled, a pre-install hook will install k8s dashboards in Sumo Logic
enabled: true
collector:
## Configuration of additional collector fields
## https://help.sumologic.com/docs/manage/fields/#http-source-fields
fields: {}
## Configuration of http sources
## See docs/Terraform.md for more information
## name: source name visible in sumologic platform
## config-name: This is mostly for backward compatibility
sources:
metrics:
default:
name: (default-metrics)
config-name: endpoint-metrics
default-otlp:
name: metrics-otlp
config-name: endpoint-metrics-otlp
properties:
content_type: Otlp
apiserver:
name: apiserver-metrics
config-name: endpoint-metrics-apiserver
controller:
name: kube-controller-manager-metrics
config-name: endpoint-metrics-kube-controller-manager
scheduler:
name: kube-scheduler-metrics
config-name: endpoint-metrics-kube-scheduler
state:
name: kube-state-metrics
config-name: endpoint-metrics-kube-state
kubelet:
name: kubelet-metrics
config-name: endpoint-metrics-kubelet
node:
name: node-exporter-metrics
config-name: endpoint-metrics-node-exporter
control-plane:
name: control-plane-metrics
logs:
default:
name: logs
config-name: endpoint-logs
## Properties can be used to extend default settings, such as processing rules, fields etc
properties:
default_date_formats:
## Ensures that timestamp key has precedence over timestamp auto discovery
- format: epoch
locator: '\"timestamp\":(\\d+)'
# filters:
# - name: "Test Exclude Debug"
# filter_type: "Exclude"
# regexp: ".*DEBUG.*"
default-otlp:
name: logs-otlp
config-name: endpoint-logs-otlp
properties:
content_type: Otlp
events:
default:
name: events
config-name: endpoint-events
properties:
default_date_formats:
## Ensures that timestamp key has precedence over timestamp auto discovery
- format: epoch
locator: '\"timestamp\":(\\d+)'
default-otlp:
name: events-otlp
config-name: endpoint-events-otlp
properties:
content_type: Otlp
traces:
default:
name: traces
config-name: endpoint-traces
properties:
content_type: Zipkin
default-otlp:
name: traces-otlp
config-name: endpoint-traces-otlp
properties:
content_type: Otlp
### Global configuration for OpenTelemetry Collector
otelcolImage:
repository: "public.ecr.aws/sumologic/sumologic-otel-collector"
tag: "0.102.1-sumo-0"
## Add a -fips suffix to all image tags. With default tags, this results in FIPS-compliant otel images.
## See https://github.com/SumoLogic/sumologic-otel-collector/blob/main/docs/fips.md for more information.
addFipsSuffix: false
### Configuration for collection of Kubernetes events
events:
enabled: true
## Source name for the Events source. Default: "events"
sourceName: "events"
## Source category for the Events source. Default: "" which is resolved to "{clusterName}/events"
# sourceCategory: "kubernetes/events"
## Used to replace '-' with another character.
sourceCategoryReplaceDash: "/"
persistence:
enabled: true
size: 10Gi
## Configuration for the Persistent Volume and Persistent Volume Claim
## where the storage is kept
persistentVolume:
path: /var/lib/storage/events
accessMode: ReadWriteOnce
## Add custom labels to otelcol event statefulset PVC
pvcLabels: {}
# storageClass:
sourceType: otlp
### Logs configuration
## Set the enabled flag to false for disabling logs ingestion altogether.
logs:
enabled: true
collector:
otelcol:
enabled: true
## Experimental
otellogswindows:
enabled: false
otelcloudwatch:
enabled: false
roleArn: ""
## Configure persistence for the cloudwatch collector
persistence:
enabled: true
region: ""
pollInterval: 1m
## A map of log group and stream prefixes
## This is a map of log group and stream prefix, for example:
## logGroups:
## fluent-bit:
## names: [fluent-bit]
logGroups: {}
multiline:
enabled: true
first_line_regex: "^\\[?\\d{4}-\\d{1,2}-\\d{1,2}.\\d{2}:\\d{2}:\\d{2}"
## Additional configuration takes precedence over first_line_regex and are executed only for first matching condition
##
## Example:
## - first_line_regex: "^@@@@ First Line"
## condition: 'attributes["k8s.namespace.name"] == "foo"'
## - first_line_regex: "^--- First Line"
## condition: 'attributes["k8s.container.name"] matches "^bar-.*'
##
## NOTE: See below link for full reference:
## https://help.sumologic.com/docs/send-data/kubernetes/collecting-logs/#conditional-multiline-log-parsing
additional: []
container:
enabled: true
## Format to post logs into Sumo: fields, json, json_merge, or text.
## NOTE: json is an alias for fields
## NOTE: Multiline log detection works differently for `text` format. See below link for full reference:
## https://help.sumologic.com/docs/send-data/kubernetes/collecting-logs/#text-log-format
format: fields
## When set to `true`, preserves the `time` attribute, which is a string representation of the `timestamp` attribute.
keep_time_attribute: false
otelcol:
## Extra processors for container logs. See https://help.sumologic.com/docs/send-data/kubernetes/collecting-logs/ for details.
extraProcessors: []
## Set the _sourceHost metadata field in Sumo Logic.
sourceHost: ""
## Set the _sourceName metadata field in Sumo Logic.
sourceName: "%{namespace}.%{pod}.%{container}"
## Set the _sourceCategory metadata field in Sumo Logic.
sourceCategory: "%{namespace}/%{pod_name}"
## Set the prefix, for _sourceCategory metadata.
sourceCategoryPrefix: "kubernetes/"
## Used to replace - with another character.
sourceCategoryReplaceDash: "/"
## A regular expression for containers.
## Matching containers will be excluded from Sumo. The logs will still be sent to logs metadata provider (otelcol).
excludeContainerRegex: ""
## A regular expression for hosts.
## Matching hosts will be excluded from Sumo. The logs will still be sent to logs metadata provider (otelcol).
excludeHostRegex: ""
## A regular expression for namespaces.
## Matching namespaces will be excluded from Sumo. The logs will still be sent to logs metadata provider (otelcol).
excludeNamespaceRegex: ""
## A regular expression for pods.
## Matching pods will be excluded from Sumo. The logs will still be sent to logs metadata provider (otelcol).
excludePodRegex: ""
## Defines whether container-level pod annotations are enabled.
perContainerAnnotationsEnabled: false
## Defines the list of prefixes of container-level pod annotations.
perContainerAnnotationPrefixes: []
systemd:
enabled: true
## systemd units to collect logs from
# units:
# - docker.service
otelcol:
## Extra processors for systemd logs. See https://help.sumologic.com/docs/send-data/kubernetes/collecting-logs/ for details.
extraProcessors: []
## Set the _sourceName metadata field in Sumo Logic.
sourceName: "%{_sourceName}"
## Set the _sourceCategory metadata field in Sumo Logic.
sourceCategory: "system"
## Set the prefix, for _sourceCategory metadata.
sourceCategoryPrefix: "kubernetes/"
## Used to replace - with another character.
sourceCategoryReplaceDash: "/"
## A regular expression for facility.
## Matching facility will be excluded from Sumo. The logs will still be sent to logs metadata provider (otelcol).
excludeFacilityRegex: ""
## A regular expression for hosts.
## Matching hosts will be excluded from Sumo. The logs will still be sent to logs metadata provider (otelcol).
excludeHostRegex: ""
## A regular expression for priority.
## Matching priority will be excluded from Sumo. The logs will still be sent to logs metadata provider (otelcol).
excludePriorityRegex: ""
## A regular expression for unit.
## Matching unit will be excluded from Sumo. The logs will still be sent to logs metadata provider (otelcol).
excludeUnitRegex: ""
kubelet:
otelcol:
## Extra processors for kubelet logs. See https://help.sumologic.com/docs/send-data/kubernetes/collecting-logs/ for details.
extraProcessors: []
## Set the _sourceName metadata field in Sumo Logic.
sourceName: "k8s_kubelet"
## Set the _sourceCategory metadata field in Sumo Logic.
sourceCategory: "kubelet"
## Set the prefix, for _sourceCategory metadata.
sourceCategoryPrefix: "kubernetes/"
## Used to replace - with another character.
sourceCategoryReplaceDash: "/"
## A regular expression for facility.
## Matching facility will be excluded from Sumo. The logs will still be sent to logs metadata provider (otelcol).
excludeFacilityRegex: ""
## A regular expression for hosts.
## Matching hosts will be excluded from Sumo. The logs will still be sent to logs metadata provider (otelcol).
excludeHostRegex: ""
## A regular expression for priority.
## Matching priority will be excluded from Sumo. The logs will still be sent to logs metadata provider (otelcol).
excludePriorityRegex: ""
## A regular expression for unit.
## Matching unit will be excluded from Sumo. The logs will still be sent to logs metadata provider (otelcol).
excludeUnitRegex: ""
otelcol:
## additional exporters which may be used in any of the pipeline
extraExporters: {}
## useDefaultExporters uses default helm chart exporters and always sends all data to them
useDefaultExporters: true
## routing defines how to route data
routing:
## fallbackExporters is a list of exporters to be used when data do not match any of the table's statement
fallbackExporters: []
table: []
## -
## ## exporter is name of the exporter
## exporter: sumologic/otlp
## ## statement is an OTTL condition which defines what data should be send to the exporter
## ## see routing processor documentation for more details:
## ## https://github.com/open-telemetry/opentelemetry-collector-contrib/blob/aee4b75100530bce7edbf736fbcf76ac4f6ced6d/processor/routingprocessor/README.md#tech-preview-opentelemetry-transformation-language-statements-as-routing-conditions
## statement: ""
## Fields to be created at Sumo Logic to ensure logs are tagged with
## relevant metadata.
## https://help.sumologic.com/docs/manage/fields/#manage-fields
fields:
- cluster
- container
- daemonset
- deployment
- host
- namespace
- node
- pod
- service
- statefulset
## Additional fields to be created in Sumo Logic.
## https://help.sumologic.com/docs/manage/fields/#manage-fields
additionalFields: []
sourceType: otlp
### Metrics configuration
## Set the enabled flag to false for disabling metrics ingestion altogether.
metrics:
enabled: true
collector:
### Otel metrics collector. Replaces Prometheus.
## To enable, you need opentelemetry-operator enabled as well.
otelcol:
enabled: true
## Configure image for Opentelemetry Collector
image:
# repository: ""
# tag: ""
pullPolicy: IfNotPresent
## Default scrape interval
scrapeInterval: 30s
## Option to turn autoscaling on for otelcol and specify params for HPA.
## Autoscaling needs metrics-server to access cpu metrics.
autoscaling:
# enabled: false
minReplicas: 1
maxReplicas: 10
targetCPUUtilizationPercentage: 70
targetMemoryUtilizationPercentage: 70
nodeSelector: {}
## Add custom annotations only to merics otelcol sts pods
podAnnotations: {}
## Add custom labels only to metrics otelcol sts pods
podLabels: {}
## Option to define priorityClassName to assign a priority class to pods.
priorityClassName:
replicaCount: 1
resources:
limits:
memory: 2Gi
cpu: 1000m
requests:
memory: 768Mi
cpu: 100m
## Selector for ServiceMonitors used for target discovery. By default, this selects resources created by this Chart.
## See https://github.com/open-telemetry/opentelemetry-operator/blob/main/docs/api.md#opentelemetrycollectorspectargetallocatorprometheuscr
# serviceMonitorSelector:
## Selector for PodMonitors used for target discovery. By default, this selects resources created by this Chart.
## See https://github.com/open-telemetry/opentelemetry-operator/blob/main/docs/api.md#opentelemetrycollectorspectargetallocatorprometheuscr
# podMonitorSelector:
securityContext:
## The group ID of all processes in the statefulset containers. This can be anything, but it does need to be set.
## The default is 0 (root), and containers don't have write permissions for volumes in that case.
fsGroup: 999
tolerations: []
affinity: {}
## Configuration for kubelet metrics
kubelet:
enabled: true
metricRegex: (?:kubelet_docker_operations_errors(?:|_total)|kubelet_(?:docker|runtime)_operations_duration_seconds_(?:count|sum)|kubelet_running_(?:container|pod)(?:_count|s)|kubelet_(:?docker|runtime)_operations_latency_microseconds(?:|_count|_sum))
## Configuration for cAdvisor metrics
cAdvisor:
enabled: true
metricRegex: (?:container_cpu_usage_seconds_total|container_memory_working_set_bytes|container_fs_usage_bytes|container_fs_limit_bytes|container_cpu_cfs_throttled_seconds_total|container_network_receive_bytes_total|container_network_transmit_bytes_total)
## Enable collection of metrics from Pods annotated with prometheus.io/* keys.
## See https://help.sumologic.com/docs/send-data/kubernetes/collecting-metrics#application-metrics-are-exposed-one-endpoint-scenario for more information.
annotatedPods:
enabled: true
## Allocation strategy for the scrape target allocator. Valid values are: least-weighted and consistent-hashing.
## See: https://github.com/open-telemetry/opentelemetry-operator/blob/main/docs/api.md#opentelemetrycollectorspectargetallocator
# allocationStrategy: least-weighted
config:
## Directly alter the OT configuration. The value of this key should be a dictionary, that will
## be directly merged with the generated configuration, overriding existing values.
## For example:
# override:
# processors:
# batch:
# send_batch_size: 512
## will change the batch size of the pipeline.
##
## WARNING: This field is not subject to backwards-compatibility guarantees offered by the rest
## of this chart. It involves implementation details that may change even in minor versions.
## Use with caution, and consider opening an issue, so your customization can be added in a safer way.
merge: {}
## Completely override existing config and replace it with the contents of this value.
## The value of this key should be a dictionary, that will replace the normal configuration.
## This is an advanced feature, use with caution, and review the generated configuration first.
override: {}
## Configuraton specific for target allocator
targetAllocator:
resources: {}
## Default metric filters for Sumo Apps
enableDefaultFilters: false
## By default, the Helm Chart collects some high-cardinality histogram metrics, as Sumo Apps make use of the sum and count components.
## This setting causes the metrics collector to drop the actual histogram buckets, keeping only the sum and the count.
## This affects the following metrics:
## - apiserver_request_duration_seconds
## - coredns_dns_request_duration_seconds
## - kubelet_runtime_operations_duration_seconds
dropHistogramBuckets: true
## A regular expression for namespaces.
## Metrics that match these namespaces will be excluded from Sumo.
excludeNamespaceRegex: ""
otelcol:
## Includes additional processors into pipelines.
## It can be used for filtering metrics, renaming, changing metadata and so on.
## This is list of objects, for example:
## extraProcessors:
## - filterprocessor:
## exclude:
## match_type: strict
## metric_names:
## - hello_world
## - hello/world
extraProcessors: []
### Enable a load balancing proxy for Prometheus remote writes.
## Prometheus remote write uses a single persistent HTTP connection per target,
## which interacts poorly with TCP load balancing with iptables that K8s Services do.
## Use a real HTTP load balancer for this instead.
## This is an advanced feature, enable only if you're experiencing performance
## issues with metrics metadata enrichment.
remoteWriteProxy:
enabled: false
config:
## Increase this if you've increased samples_per_send in Prometheus to prevent nginx
## from spilling proxied request bodies to disk
clientBodyBufferSize: "64k"
## This feature autodetects how much CPU is assigned to the nginx instance and sets
## the right amount of workers based on that. Disable to use the default of 8 workers.
workerCountAutotune: true
## Nginx listen port
port: 8080
## Nginx access logs
enableAccessLogs: false
replicaCount: 3
image:
repository: public.ecr.aws/sumologic/nginx-unprivileged
## This is simply 1.26.0-alpine with a newer version of Alpine
## In the nginx repo, this a moving tag, so I've chosen to add a -sumo-1 suffix to indicate the change
tag: 1.26.0-alpine-sumo-0
pullPolicy: IfNotPresent
resources:
limits:
cpu: 1000m
memory: 256Mi
requests:
cpu: 100m
memory: 128Mi
livenessProbe:
initialDelaySeconds: 30
periodSeconds: 10
timeoutSeconds: 5
successThreshold: 1
failureThreshold: 6
readinessProbe:
initialDelaySeconds: 5
periodSeconds: 5
timeoutSeconds: 3
successThreshold: 1
failureThreshold: 3
securityContext: {}
nodeSelector: {}
tolerations: []
affinity: {}
## Option to define priorityClassName to assign a priority class to pods.
priorityClassName:
## Add custom labels only to metrics sts pods
podLabels: {}
## Add custom annotations only to metrics sts pods
podAnnotations: {}
## Prometheus serviceMonitors related to Sumo Logic services
## They are applied only if kube-prometheus-stack is enabled
serviceMonitors:
- name: collection-sumologic-otelcol-logs
additionalLabels:
sumologic.com/app: otelcol-logs
endpoints:
- port: otelcol-metrics
selector:
matchLabels:
sumologic.com/app: otelcol-logs
sumologic.com/scrape: "true"
- name: collection-sumologic-otelcol-metrics
additionalLabels:
sumologic.com/app: otelcol-metrics
endpoints:
- port: otelcol-metrics
selector:
matchLabels:
sumologic.com/app: otelcol-metrics
sumologic.com/scrape: "true"
- name: collection-sumologic-metrics-collector
additionalLabels:
sumologic.com/app: otelcol-metrics
endpoints:
- port: monitoring
selector:
matchLabels:
sumologic.com/app: otelcol
sumologic.com/component: metrics
sumologic.com/scrape: "true"
- name: collection-sumologic-otelcol-logs-collector
additionalLabels:
sumologic.com/app: otelcol-logs-collector
endpoints:
- port: metrics
selector:
matchLabels:
sumologic.com/app: otelcol-logs-collector
sumologic.com/scrape: "true"
- name: collection-sumologic-otelcol-events
additionalLabels:
sumologic.com/app: otelcol-events
endpoints:
- port: otelcol-metrics
selector:
matchLabels:
sumologic.com/app: otelcol-events
sumologic.com/scrape: "true"
- name: collection-sumologic-otelcol-traces
additionalLabels:
sumologic.com/app: otelcol
endpoints:
- port: metrics
selector:
matchLabels:
sumologic.com/component: instrumentation
sumologic.com/scrape: "true"
- name: collection-sumologic-prometheus
endpoints:
- port: http-web
path: /metrics
metricRelabelings:
- action: keep
regex: prometheus_remote_storage_.*
sourceLabels: [__name__]
selector:
matchLabels:
app: kube-prometheus-stack-prometheus
## User-defined ServiceMonitors go here
additionalServiceMonitors: []
## The type of source we send to in Sumo. The possible values are http and otlp.
## Consult the documentation for more information.
sourceType: otlp
### Traces configuration
## Set the enabled flag to false to disable traces from instrumentation ingestion.
traces:
enabled: true
## How many spans per request should be send to receiver
spans_per_request: 100
sourceType: otlp
## Configure metrics-server
## ref: https://github.com/bitnami/charts/blob/master/bitnami/metrics-server/values.yaml
metrics-server:
image:
registry: public.ecr.aws
repository: sumologic/metrics-server
## Optionally specify an array of imagePullSecrets.
## Secrets must be manually created in the namespace.
## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/
##
# pullSecrets:
# - imagepullsecret
## Set the enabled flag to true for enabling metrics-server.
## This is required before enabling autoscaling unless you have an existing metrics-server in the cluster.
enabled: false
## Put here the new name if you want to override the full name used for metrics-server components.
# fullnameOverride: ""
apiService:
create: true
extraArgs:
- --kubelet-insecure-tls=true
- --kubelet-preferred-address-types=InternalIP,ExternalIP,Hostname
## Configure kube-prometheus-stack
## ref: https://github.com/prometheus-community/helm-charts/blob/main/charts/kube-prometheus-stack/values.yaml
kube-prometheus-stack:
## Uncomment the flag below to not install kube-prometheus-stack helm chart
## as a dependency along with this helm chart.
## This is needed e.g. if you want to use a different version of kube-prometheus-stack -
## see https://help.sumologic.com/docs/send-data/kubernetes/best-practices/#using-newer-kube-prometheus-stack.
## To disable metrics collection, set `sumologic.metrics.enabled: false` and leave this flag commented out or set it to `false`.
## Do not set this flag explicitly to `true` while at the same time setting `sumologic.metrics.enabled: false`,
## as this will make Prometheus try to write to an non-existent metrics enrichment service.
# enabled: false
# global:
## Reference to one or more secrets to be used when pulling images
## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/
##
# imagePullSecrets:
# - name: "image-pull-secret"
## Put here the new name if you want to override the full name used for Kube Prometheus Stack components.
# fullnameOverride: ""
## Put here the new namespace if you want to override the namespace used for Kube Prometheus Stack components.
# namespaceOverride: ""
## Provide a target gitVersion of K8S, in case .Capabilites.KubeVersion is not available (e.g. helm template).
## Changing this may break Sumo Logic apps.
# kubeTargetVersionOverride: ""
## Labels to apply to all kube-prometheus-stack resources
commonLabels: {}
defaultRules:
rules:
alertmanager: false
etcd: false
configReloaders: false
general: false
k8s: false
kubeApiserverAvailability: false
kubeApiserverBurnrate: false
kubeApiserverHistogram: false
kubeApiserverSlos: false
kubeControllerManager: false
kubelet: false
kubeProxy: false
kubePrometheusGeneral: false
kubePrometheusNodeRecording: false
kubernetesApps: false
kubernetesResources: false
kubernetesStorage: false
kubernetesSystem: false
kubeSchedulerAlerting: false
kubeSchedulerRecording: false
kubeStateMetrics: false
network: false
node: false
nodeExporterAlerting: false
nodeExporterRecording: false
prometheus: false
prometheusOperator: false
windows: false
## NOTE changing the serviceMonitor scrape interval to be >1m can result in metrics from recording
## rules to be missing and empty panels in Sumo Logic Kubernetes apps.
kubeApiServer:
serviceMonitor:
## Scrape interval. If not set, the Prometheus default scrape interval is used.
interval:
## see docs/scraped_metrics.md
## apiserver_request_count
## apiserver_request_total
## apiserver_request_duration_seconds_count
## apiserver_request_duration_seconds_sum
metricRelabelings:
- action: keep
regex: (?:apiserver_request_(?:count|total)|apiserver_request_(?:duration_seconds)_(?:count|sum))
sourceLabels: [__name__]
kubelet:
serviceMonitor:
## Scrape interval. If not set, the Prometheus default scrape interval is used.
interval:
## Enable scraping /metrics/probes from kubelet's service
probes: false
## Enable scraping /metrics/resource/v1alpha1 from kubelet's service
resource: false
## see docs/scraped_metrics.md
## kubelet metrics:
## kubelet_docker_operations_errors
## kubelet_docker_operations_errors_total
## kubelet_docker_operations_duration_seconds_count
## kubelet_docker_operations_duration_seconds_sum
## kubelet_runtime_operations_duration_seconds_count
## kubelet_runtime_operations_duration_seconds_sum
## kubelet_running_container_count
## kubelet_running_containers
## kubelet_running_pod_count
## kubelet_running_pods
## kubelet_docker_operations_latency_microseconds
## kubelet_docker_operations_latency_microseconds_count
## kubelet_docker_operations_latency_microseconds_sum
## kubelet_runtime_operations_latency_microseconds
## kubelet_runtime_operations_latency_microseconds_count
## kubelet_runtime_operations_latency_microseconds_sum
metricRelabelings:
- action: keep
regex: (?:kubelet_docker_operations_errors(?:|_total)|kubelet_(?:docker|runtime)_operations_duration_seconds_(?:count|sum)|kubelet_running_(?:container|pod)(?:_count|s)|kubelet_(:?docker|runtime)_operations_latency_microseconds(?:|_count|_sum))
sourceLabels: [__name__]
- action: labeldrop
regex: id
## see docs/scraped_metrics.md
## cadvisor container metrics
## container_cpu_usage_seconds_total
## container_fs_limit_bytes
## container_fs_usage_bytes
## container_memory_working_set_bytes
## container_cpu_cfs_throttled_seconds_total
##
## cadvisor aggregate container metrics
## container_network_receive_bytes_total
## container_network_transmit_bytes_total
cAdvisorMetricRelabelings:
- action: keep
regex: (?:container_cpu_usage_seconds_total|container_memory_working_set_bytes|container_fs_usage_bytes|container_fs_limit_bytes|container_cpu_cfs_throttled_seconds_total|container_network_receive_bytes_total|container_network_transmit_bytes_total)
sourceLabels: [__name__]
## Drop container metrics with container tag set to an empty string:
## these are the pod aggregated container metrics which can be aggregated
## in Sumo anyway. There's also some cgroup-specific time series we also
## do not need.
- action: drop
sourceLabels: [__name__, container]
regex: (?:container_cpu_usage_seconds_total|container_memory_working_set_bytes|container_fs_usage_bytes|container_fs_limit_bytes);$
- action: labelmap
regex: container_name
replacement: container
- action: drop
sourceLabels: [container]
regex: POD
- action: labeldrop
regex: (id|name)
kubeControllerManager:
serviceMonitor:
## Scrape interval. If not set, the Prometheus default scrape interval is used.
interval:
## see docs/scraped_metrics.md
## controller manager metrics
## https://kubernetes.io/docs/concepts/cluster-administration/monitoring/#kube-controller-manager-metrics
## e.g.
## cloudprovider_aws_api_request_duration_seconds_bucket
## cloudprovider_aws_api_request_duration_seconds_count
## cloudprovider_aws_api_request_duration_seconds_sum
metricRelabelings:
- action: keep
regex: (?:cloudprovider_.*_api_request_duration_seconds.*)
sourceLabels: [__name__]
coreDns:
serviceMonitor:
## Scrape interval. If not set, the Prometheus default scrape interval is used.
interval:
## see docs/scraped_metrics.md
## coredns:
## coredns_cache_entries
## coredns_cache_hits_total
## coredns_cache_misses_total
## coredns_dns_request_duration_seconds_count
## coredns_dns_request_duration_seconds_sum
## coredns_dns_requests_total
## coredns_dns_responses_total
## coredns_forward_requests_total
## coredns_proxy_request_duration_seconds_count
## coredns_proxy_request_duration_seconds_sum
## coredns_proxy_request_duration_seconds_bucket
## process_cpu_seconds_total
## process_open_fds
## process_resident_memory_bytes
## process_cpu_seconds_total
## process_open_fds
## process_resident_memory_bytes
metricRelabelings:
- action: keep
regex: (?:coredns_cache_(entries|(hits|misses)_total)|coredns_dns_request_duration_seconds_(count|sum)|coredns_(forward_requests|dns_requests|dns_responses)_total|process_(cpu_seconds_total|open_fds|resident_memory_bytes)|coredns_proxy_request_duration_seconds_(sum|count|bucket))
sourceLabels: [__name__]
kubeEtcd:
serviceMonitor:
## Scrape interval. If not set, the Prometheus default scrape interval is used.
interval:
## see docs/scraped_metrics.md
## etcd_request_cache_get_duration_seconds_count
## etcd_request_cache_get_duration_seconds_sum
## etcd_request_cache_add_duration_seconds_count
## etcd_request_cache_add_duration_seconds_sum
## etcd_request_cache_add_latencies_summary_count
## etcd_request_cache_add_latencies_summary_sum
## etcd_request_cache_get_latencies_summary_count
## etcd_request_cache_get_latencies_summary_sum
## etcd_helper_cache_hit_count
## etcd_helper_cache_hit_total
## etcd_helper_cache_miss_count
## etcd_helper_cache_miss_total
## etcd server:
## etcd_mvcc_db_total_size_in_bytes
## etcd_debugging_store_expires_total
## etcd_debugging_store_watchers
## etcd_disk_backend_commit_duration_seconds_bucket
## etcd_disk_wal_fsync_duration_seconds_bucket
## etcd_grpc_proxy_cache_hits_total
## etcd_grpc_proxy_cache_misses_total
## etcd_network_client_grpc_received_bytes_total
## etcd_network_client_grpc_sent_bytes_total
## etcd_server_has_leader
## etcd_server_leader_changes_seen_total
## etcd_server_proposals_applied_total
## etcd_server_proposals_committed_total
## etcd_server_proposals_failed_total