-
Notifications
You must be signed in to change notification settings - Fork 418
/
values.yaml
2395 lines (2209 loc) · 96.2 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
global:
# zone: cluster.local (use only if your DNS server doesn't live in the same zone as kubecost)
prometheus:
enabled: true # Kubecost depends on Prometheus data, it is not optional. When enabled: false, Prometheus will not be installed and you must configure your own Prometheus to scrape kubecost as well as provide the fqdn below. -- Warning: Before changing this setting, please read to understand the risks https://docs.kubecost.com/install-and-configure/install/custom-prom
fqdn: http://cost-analyzer-prometheus-server.default.svc # example address of a prometheus to connect to. Include protocol (http:// or https://) Ignored if enabled: true
# insecureSkipVerify: false # If true, kubecost will not check the TLS cert of prometheus
# queryServiceBasicAuthSecretName: dbsecret # kubectl create secret generic dbsecret -n kubecost --from-file=USERNAME --from-file=PASSWORD
# queryServiceBearerTokenSecretName: mcdbsecret # kubectl create secret generic mcdbsecret -n kubecost --from-file=TOKEN
# kubeRBACProxy: false # If true, kubecost will use kube-rbac-proxy to authenticate with in cluster Prometheus for openshift
grafana:
enabled: true # If false, Grafana will not be installed
domainName: cost-analyzer-grafana.default.svc # example grafana domain Ignored if enabled: true
scheme: "http" # http or https, for the domain name above.
proxy: true # If true, the kubecost frontend will route to your grafana through its service endpoint
# fqdn: cost-analyzer-grafana.default.svc
# Enable only when you are using GCP Marketplace ENT listing. Learn more at https://console.cloud.google.com/marketplace/product/kubecost-public/kubecost-ent
gcpstore:
enabled: false
# Google Cloud Managed Service for Prometheus
gmp:
# Remember to set up these parameters when install the Kubecost Helm chart with `global.gmp.enabled=true` if you want to use GMP self-deployed collection (Recommended) to utilize Kubecost scrape configs.
# If enabling GMP, it is highly recommended to utilize Google's distribution of Prometheus.
# Learn more at https://cloud.google.com/stackdriver/docs/managed-prometheus/setup-unmanaged
# --set prometheus.server.image.repository="gke.gcr.io/prometheus-engine/prometheus" \
# --set prometheus.server.image.tag="v2.35.0-gmp.2-gke.0"
enabled: false # If true, kubecost will be configured to use GMP Prometheus image and query from Google Cloud Managed Service for Prometheus.
prometheusServerEndpoint: http://localhost:8085/ # The prometheus service endpoint used by kubecost. The calls are forwarded through the GMP Prom proxy side car to the GMP database.
gmpProxy:
enabled: false
image: gke.gcr.io/prometheus-engine/frontend:v0.4.1-gke.0 # GMP Prometheus proxy image that serve as an endpoint to query metrics from GMP
imagePullPolicy: IfNotPresent
name: gmp-proxy
port: 8085
projectId: YOUR_PROJECT_ID # example GCP project ID
# Amazon Managed Service for Prometheus
amp:
enabled: false # If true, kubecost will be configured to remote_write and query from Amazon Managed Service for Prometheus.
prometheusServerEndpoint: http://localhost:8005/workspaces/<workspaceId>/ # The prometheus service endpoint used by kubecost. The calls are forwarded through the SigV4Proxy side car to the AMP workspace.
remoteWriteService: https://aps-workspaces.us-west-2.amazonaws.com/workspaces/<workspaceId>/api/v1/remote_write # The remote_write endpoint for the AMP workspace.
sigv4:
region: us-west-2
# access_key: ACCESS_KEY # AWS Access key
# secret_key: SECRET_KEY # AWS Secret key
# role_arn: ROLE_ARN # AWS role arn
# profile: PROFILE # AWS profile
# Mimir Proxy to help Kubecost to query metrics from multi-tenant Grafana Mimir.
# Set `global.mimirProxy.enabled=true` and `global.prometheus.enabled=false` to enable Mimir Proxy.
# You also need to set `global.prometheus.fqdn=http://kubecost-cost-analyzer-mimir-proxy.kubecost.svc:8085/prometheus`
# or `global.prometheus.fqdn=http://{{ template "cost-analyzer.fullname" . }}-mimir-proxy.{{ .Release.Namespace }}.svc:8085/prometheus'
# Learn more at https://grafana.com/docs/mimir/latest/operators-guide/secure/authentication-and-authorization/#without-an-authenticating-reverse-proxy
mimirProxy:
enabled: false
## Annotations to be added to the Mimir Proxy deployment template
annotations: {}
name: mimir-proxy
image: nginxinc/nginx-unprivileged
port: 8085
mimirEndpoint: $mimir_endpoint # Your Mimir query endpoint. If your Mimir query endpoint is http://example.com/prometheus, replace $mimir_endpoint with http://example.com/
orgIdentifier: $your_tenant_ID # Your Grafana Mimir tenant ID
# basicAuth:
# username: user
# password: pwd
## Azure Monitor Managed Service for Prometheus
## Ref: https://learn.microsoft.com/en-us/azure/azure-monitor/essentials/prometheus-remote-write-virtual-machines
ammsp:
enabled: false
prometheusServerEndpoint: http://localhost:8081/
remoteWriteService: $<AMMSP_METRICS_INGESTION_ENDPOINT>
queryEndpoint: $<AMMSP_QUERY_ENDPOINT>
aadAuthProxy:
enabled: false
# per https://github.com/Azure/aad-auth-proxy/releases/tag/0.1.0-main-04-10-2024-7067ac84
image: $<IMAGE> # Example: mcr.microsoft.com/azuremonitor/auth-proxy/prod/aad-auth-proxy/images/aad-auth-proxy:0.1.0-main-04-10-2024-7067ac84
imagePullPolicy: IfNotPresent
name: aad-auth-proxy
port: 8081
audience: https://prometheus.monitor.azure.com/.default
identityType: userAssigned
aadClientId: $<AZURE_MANAGED_IDENTITY_CLIENT_ID>
aadTenantId: $<AZURE_MANAGED_IDENTITY_TENANT_ID>
## Kubecost Alerting
## Ref: http://docs.kubecost.com/alerts
notifications:
# alertConfigs:
# frontendUrl: http://localhost:9090 # Optional
# globalSlackWebhookUrl: https://hooks.slack.com/services/T00000000/B00000000/XXXXXXXXXXXXXXXXXXXXXXXX # Optional
# globalMsTeamsWebhookUrl: https://xxxxx.webhook.office.com/webhookb2/XXXXXXXXXXXXXXXXXXXXXXXX/IncomingWebhook/XXXXXXXXXXXXXXXXXXXXXXXX # Optional
# globalAlertEmails:
# globalEmailSubject: Custom Subject
# alerts:
# # Daily namespace budget alert on namespace `kubecost`
# - type: budget # supported: budget, recurringUpdate
# threshold: 50 # optional, required for budget alerts
# window: daily # or 1d
# aggregation: namespace
# filter: kubecost
# ownerContact: # optional, overrides globalAlertEmails default
# slackWebhookUrl: https://hooks.slack.com/services/T00000000/B00000000/XXXXXXXXXXXXXXXXXXXXXXXX # Optional
# msTeamsWebhookUrl: https://xxxxx.webhook.office.com/webhookb2/XXXXXXXXXXXXXXXXXXXXXXXX/IncomingWebhook/XXXXXXXXXXXXXXXXXXXXXXXX # Optional
# # Daily cluster budget alert on cluster `cluster-one`
# - type: budget
# threshold: 200.8 # optional, required for budget alerts
# window: daily # or 1d
# aggregation: cluster
# filter: cluster-one # does not accept csv
# # Recurring weekly update (weeklyUpdate alert)
# - type: recurringUpdate
# window: weekly # or 7d
# aggregation: namespace
# filter: '*'
# # Recurring weekly namespace update on kubecost namespace
# - type: recurringUpdate
# window: weekly # or 7d
# aggregation: namespace
# filter: kubecost
# # Spend Change Alert
# - type: spendChange # change relative to moving avg
# relativeThreshold: 0.20 # Proportional change relative to baseline. Must be greater than -1 (can be negative)
# window: 1d # accepts ‘d’, ‘h’
# baselineWindow: 30d # previous window, offset by window
# aggregation: namespace
# filter: kubecost, default # accepts csv
# # Health Score Alert
# - type: health # Alerts when health score changes by a threshold
# window: 10m
# threshold: 5 # Send Alert if health scores changes by 5 or more
# # Kubecost Health Diagnostic
# - type: diagnostic # Alerts when kubecost is unable to compute costs - ie: Prometheus unreachable
# window: 10m
alertmanager: # Supply an alertmanager FQDN to receive notifications from the app.
enabled: false # If true, allow kubecost to write to your alertmanager
fqdn: http://cost-analyzer-prometheus-server.default.svc # example fqdn. Ignored if prometheus.enabled: true
## Kubecost Saved Reports
## Ref: http://docs.kubecost.com/saved-reports
savedReports:
enabled: false # If true, overwrites report parameters set through UI
reports:
- title: "Example Saved Report 0"
window: "today"
aggregateBy: "namespace"
chartDisplay: "category"
idle: "separate"
rate: "cumulative"
accumulate: false # daily resolution
filters: # Ref: https://docs.kubecost.com/apis/filters-api
- key: "cluster" # Ref: https://docs.kubecost.com/apis/filters-api#allocation-apis-request-sizing-v2-api
operator: ":" # Ref: https://docs.kubecost.com/apis/filters-api#filter-operators
value: "dev"
- title: "Example Saved Report 1"
window: "month"
aggregateBy: "controllerKind"
chartDisplay: "category"
idle: "share"
rate: "monthly"
accumulate: false
filters: # Ref: https://docs.kubecost.com/apis/filters-api
- key: "namespace" # Ref: https://docs.kubecost.com/apis/filters-api#allocation-apis-request-sizing-v2-api
operator: "!:" # Ref: https://docs.kubecost.com/apis/filters-api#filter-operators
value: "kubecost"
- title: "Example Saved Report 2"
window: "2020-11-11T00:00:00Z,2020-12-09T23:59:59Z"
aggregateBy: "service"
chartDisplay: "category"
idle: "hide"
rate: "daily"
accumulate: true # entire window resolution
filters: [] # if no filters, specify empty array
assetReports:
enabled: false # If true, overwrites report parameters set through UI
reports:
- title: "Example Asset Report 0"
window: "today"
aggregateBy: "type"
accumulate: false # daily resolution
filters:
- property: "cluster"
value: "cluster-one"
cloudCostReports:
enabled: false # If true, overwrites report parameters set through UI
reports:
- title: "Cloud Cost Report 0"
window: "today"
aggregateBy: "service"
accumulate: false # daily resolution
# filters:
# - property: "service"
# value: "service1" # corresponds to a value to filter cloud cost aggregate by service data on.
podAnnotations: {}
# iam.amazonaws.com/role: role-arn
# Annotations to be added for all controllers (StatefulSets, Deployments, DaemonSets)
annotations: {}
# iam.amazonaws.com/role: role-arn
# Applies these labels to all Deployments, StatefulSets, DaemonSets, and their pod templates.
additionalLabels: {}
securityContext:
runAsNonRoot: true
seccompProfile:
type: RuntimeDefault
fsGroup: 1001
runAsGroup: 1001
runAsUser: 1001
fsGroupChangePolicy: OnRootMismatch
containerSecurityContext:
allowPrivilegeEscalation: false
privileged: false
readOnlyRootFilesystem: true
capabilities:
drop:
- ALL
# Platforms is a higher-level abstraction for platform-specific values and settings.
platforms:
# Deploying to OpenShift (OCP) requires enabling this option.
openshift:
enabled: false # Deploy Kubecost to OpenShift.
route:
enabled: false # Create an OpenShift Route.
annotations: {} # Add annotations to the Route.
# host: kubecost.apps.okd4.example.com # Add a custom host for your Route.
# Create Security Context Constraint resources for the DaemonSets requiring additional privileges.
scc:
nodeExporter: false # Creates an SCC for Prometheus Node Exporter. This requires Node Exporter be enabled.
networkCosts: false # Creates an SCC for Kubecost network-costs. This requires network-costs be enabled.
# When OpenShift is enabled, the following securityContext will be applied to all resources unless they define their own.
securityContext:
runAsNonRoot: true
seccompProfile:
type: RuntimeDefault
# Set options for deploying with CI/CD tools like Argo CD.
cicd:
enabled: false # Set to true when using affected CI/CD tools for access to the below configuration options.
skipSanityChecks: false # If true, skip all sanity/existence checks for resources like Secrets.
## Kubecost Integrations
## Ref: https://docs.kubecost.com/integrations
integrations:
turbonomic:
enabled: false # Set to true to enable the Turbonomic integration
clientId: "" # Client ID generated from the OAuth Client created
clientSecret: "" # Client Secret generated from the OAuth Client created
role: "" # Role that the OAuth Client was created with (e.g. ADMINISTRATOR, SITE_ADMIN, etc.)
host: "" # URL to your turbonomic API. EG: https://turbonomic.example.com/
insecureClient: false # Do not verify certificate
postgres:
enabled: false
runInterval: "12h" # How frequently to run the integration.
databaseHost: "" # REQUIRED. ex: my.postgres.database.azure.com
databasePort: "" # REQUIRED. ex: 5432
databaseName: "" # REQUIRED. ex: postgres
databaseUser: "" # REQUIRED. ex: myusername
databasePassword: "" # REQUIRED. ex: mypassword
databaseSecretName: "" # OPTIONAL. Specify your own k8s secret containing the above credentials. Must have key "creds.json".
## Configure what Postgres table to write to, and what parameters to pass
## when querying Kubecost's APIs. Ensure all parameters are enclosed in
## quotes. Ref: https://docs.kubecost.com/apis/apis-overview
queryConfigs:
allocations: []
# - databaseTable: "kubecost_allocation_data"
# window: "7d"
# aggregate: "namespace"
# idle: "true"
# shareIdle: "true"
# shareNamespaces: "kubecost,kube-system"
# shareLabels: ""
# - databaseTable: "kubecost_allocation_data_by_cluster"
# window: "10d"
# aggregate: "cluster"
# idle: "true"
# shareIdle: "false"
# shareNamespaces: ""
# shareLabels: ""
assets: []
# - databaseTable: "kubecost_assets_data"
# window: "7d"
# aggregate: "cluster"
cloudCosts: []
# - databaseTable: "kubecost_cloudcosts_data"
# window: "7d"
# aggregate: "service"
## Provide a name override for the chart.
# nameOverride: ""
## Provide a full name override option for the chart.
# fullnameOverride: ""
## Provide additional labels for the chart.
# chartLabels:
# app.kubernetes.io/name: kubecost-cost-analyzer
## This flag is only required for users upgrading to a new version of Kubecost.
## The flag is used to ensure users are aware of important
## (potentially breaking) changes included in the new version.
##
upgrade:
toV2: false
# generated at http://kubecost.com/install, used for alerts tracking and free trials
kubecostToken: # ""
# Advanced pipeline for custom prices, enterprise key required
pricingCsv:
enabled: false
location:
provider: "AWS"
region: "us-east-1"
URI: s3://kc-csv-test/pricing_schema.csv # a valid file URI
csvAccessCredentials: pricing-schema-access-secret
## Kubecost SAML (enterprise key required)
## Ref: https://docs.kubecost.com/install-and-configure/advanced-configuration/user-management-saml
saml:
enabled: false
# secretName: ""
# metadataSecretName: "" # One of metadataSecretName or idpMetadataURL must be set. Defaults to idpMetadataURL if set.
# idpMetadataURL: ""
# appRootURL: ""
# authTimeout: 1440 # Number of minutes the JWT will be valid
# redirectURL: "" # Callback URL redirected to after logout
# audienceURI: "" # Usually the same as the appRootURL. Optionally any string uniquely identifying kubecost to your SAML IDP.
# nameIDFormat: "" # If your SAML provider requires a specific nameid format
# isGLUUProvider: false # An additional URL parameter must be appended for GLUU providers
# encryptionCertSecret: "" # K8s secret storing the x509 certificate used to encrypt an Okta SAML response
# decryptionKeySecret: "" # K8s secret storing the private key associated with the encryptionCertSecret
# authSecret: "" # Value of SAML secret used to issue tokens, will be autogenerated as random string if not provided
# authSecretName: "" # Name of K8s secret where the authSecret will be stored. Defaults to "kubecost-saml-secret" if not provided.
rbac:
enabled: false
# groups:
# - name: admin
# enabled: false # If admin is disabled, all SAML users will be able to make configuration changes to the Kubecost frontend
# assertionName: ""
# assertionValues:
# - "admin"
# - "superusers"
# - name: readonly
# enabled: false # If readonly is disabled, all users authorized on SAML will default to readonly
# assertionName: ""
# assertionValues:
# - "readonly"
# - name: editor
# enabled: true # If editor is enabled, editors will be allowed to edit reports/alerts scoped to them, and act as readers otherwise. Users will never default to editor.
# assertionName: ""
# assertionValues:
# - "editor"
## Kubecost OIDC (enterprise key required)
## Ref: https://docs.kubecost.com/install-and-configure/advanced-configuration/user-management-oidc
oidc:
enabled: false
clientID: "" # Application client_id parameter obtained from provider. Used to make requests to server.
clientSecret: "" # Application/client client_secret parameter obtained from provider. Used to make requests to server.
secretName: "kubecost-oidc-secret" # K8s secret where clientsecret will be stored
existingCustomSecret:
enabled: false
name: "" # Name of an existing clientSecret. Overrides the usage of oidc.clientSecret and oidc.secretName.
authURL: "" # Authorization endpoint for your identity provider
loginRedirectURL: "" # Kubecost URL endpoint which handles auth flow
discoveryURL: "" # Your identity provider's endpoint sharing OIDC configuration
skipOnlineTokenValidation: false # If true, validate JWT claims locally
useClientSecretPost: false # If true, only use client_secret_post method. Otherwise attempt to send the secret in both the header and the body.
hostedDomain: "" # Optional, blocks access to the auth domain specified in the hd claim of the provider ID token
rbac:
enabled: false
# groups:
# - name: admin # Admins have permissions to edit Kubecost settings and save reports
# enabled: false
# claimName: "roles" # Kubecost matches this string against the JWT's payload key containing RBAC info (this value is unique across identity providers)
# claimValues: # Kubecost matches these strings with the roles created in your identity provider
# - "admin"
# - "superusers"
# - name: readonly # Readonly users do not have permissions to edit Kubecost settings or save reports.
# enabled: false
# claimName: "roles"
# claimValues:
# - "readonly"
# - name: editor # Editors have permissions to edit reports/alerts and act as readers otherwise
# enabled: false
# claimName: "roles"
# claimValues:
# - "editor"
## Adds the HTTP_PROXY, HTTPS_PROXY, and NO_PROXY environment variables to all
## containers. Typically used in environments that have firewall rules which
## prevent kubecost from accessing cloud provider resources.
## Ref: https://www.oreilly.com/library/view/security-with-go/9781788627917/5ea6a02b-3d96-44b1-ad3c-6ab60fcbbe4f.xhtml
##
systemProxy:
enabled: false
httpProxyUrl: ""
httpsProxyUrl: ""
noProxy: ""
# imagePullSecrets:
# - name: "image-pull-secret"
# imageVersion uses the base image name (image:) but overrides the version
# pulled. It should be avoided. If non-default behavior is needed, use
# fullImageName for the relevant component.
# imageVersion:
kubecostFrontend:
enabled: true
deployMethod: singlepod # haMode or singlepod - haMode is currently only supported with Enterprise tier
haReplicas: 2 # only used with haMode
image: "gcr.io/kubecost1/frontend"
imagePullPolicy: IfNotPresent
# fullImageName overrides the default image construction logic. The exact
# image provided (registry, image, tag) will be used for the frontend.
# fullImageName:
# extraEnv:
# - name: NGINX_ENTRYPOINT_WORKER_PROCESSES_AUTOTUNE
# value: "1"
# securityContext:
# readOnlyRootFilesystem: true
resources:
requests:
cpu: "10m"
memory: "55Mi"
deploymentStrategy: {}
readinessProbe:
enabled: true
initialDelaySeconds: 1
periodSeconds: 5
failureThreshold: 6
livenessProbe:
enabled: true
initialDelaySeconds: 1
periodSeconds: 5
failureThreshold: 6
ipv6:
enabled: true # disable if the cluster does not support ipv6
# timeoutSeconds: 600 # should be rarely used, but can be increased if needed
# allow customizing nginx-conf server block
# extraServerConfig: |-
# proxy_busy_buffers_size 512k;
# proxy_buffers 4 512k;
# proxy_buffer_size 256k;
# large_client_header_buffers 4 64k;
# hideDiagnostics: false # useful if the primary is not monitored. Supported in limited environments.
# hideOrphanedResources: false # OrphanedResources works on the primary-cluster's cloud-provider only.
# set to true to set all upstreams to use <service>.<namespace>.svc.cluster.local instead of just <service>.<namespace>
useDefaultFqdn: false
# api:
# fqdn: kubecost-api.kubecost.svc.cluster.local:9001
# model:
# fqdn: kubecost-model.kubecost.svc.cluster.local:9003
# forecasting:
# fqdn: kubecost-forcasting.kubecost.svc.cluster.local:5000
# aggregator:
# fqdn: kubecost-aggregator.kubecost.svc.cluster.local:9004
# cloudCost:
# fqdn: kubecost-cloud-cost.kubecost.svc.cluster.local:9005
# multiClusterDiagnostics:
# fqdn: kubecost-multi-diag.kubecost.svc.cluster.local:9007
# clusterController:
# fqdn: cluster-controller.kubecost.svc.cluster.local:9731
# Kubecost Metrics deploys a separate pod which will emit kubernetes specific metrics required
# by the cost-model. This pod is designed to remain active and decoupled from the cost-model itself.
# However, disabling this service/pod deployment will flag the cost-model to emit the metrics instead.
kubecostMetrics:
# emitPodAnnotations: false
# emitNamespaceAnnotations: false
# emitKsmV1Metrics: true # emit all KSM metrics in KSM v1.
# emitKsmV1MetricsOnly: false # emit only the KSM metrics missing from KSM v2. Advanced users only.
sigV4Proxy:
image: public.ecr.aws/aws-observability/aws-sigv4-proxy:latest
imagePullPolicy: IfNotPresent
name: aps
port: 8005
region: us-west-2 # The AWS region
host: aps-workspaces.us-west-2.amazonaws.com # The hostname for AMP service.
# role_arn: arn:aws:iam::<account>:role/role-name # The AWS IAM role to assume.
extraEnv: # Pass extra env variables to sigV4Proxy
# - name: AWS_ACCESS_KEY_ID
# value: <access_key>
# - name: AWS_SECRET_ACCESS_KEY
# value: <secret_key>
resources: {}
kubecostModel:
image: "gcr.io/kubecost1/cost-model"
imagePullPolicy: IfNotPresent
# fullImageName overrides the default image construction logic. The exact
# image provided (registry, image, tag) will be used for cost-model.
# fullImageName:
# Log level for the cost model container. Options are "trace", "debug", "info", "warn", "error", "fatal", "panic"
logLevel: info
# securityContext:
# readOnlyRootFilesystem: true
# The total number of days the ETL pipelines will build
# Set to 0 to disable daily ETL (not recommended)
etlDailyStoreDurationDays: 91
# The total number of hours the ETL pipelines will build
# Set to 0 to disable hourly ETL (recommended for large environments)
# Must be < prometheus server retention, otherwise empty data may overwrite
# known-good data
etlHourlyStoreDurationHours: 49
# For deploying kubecost in a cluster that does not self-monitor
etlReadOnlyMode: false
## The name of the Secret containing a bucket config for Federated storage.
## The contents should be stored under a key named federated-store.yaml.
## Ref: https://docs.kubecost.com/install-and-configure/install/multi-cluster/long-term-storage-configuration
# federatedStorageConfigSecret: federated-store
## Federated storage config can be supplied via a secret or the yaml block
## below when using the block below, only a single provider is supported,
## others are for example purposes.
## Ref: https://docs.kubecost.com/install-and-configure/install/multi-cluster/long-term-storage-configuration
# federatedStorageConfig: |-
# # AWS EXAMPLE
# type: S3
# config:
# bucket: kubecost-federated-storage-bucket
# endpoint: s3.amazonaws.com
# region: us-east-1
# # best practice is to use pod identities to access AWS resources. Otherwise it is possible to use an access_key and secret_key
# access_key: "<your-access-key>"
# secret_key: "<your-secret-key>"
# # AZURE EXAMPLE
# type: AZURE
# config:
# storage_account: ""
# storage_account_key: ""
# container: ""
# max_retries: 0
# # GCP EXAMPLE
# type: GCS
# config:
# bucket: kubecost-federated-storage-bucket
# service_account: |-
# {
# "type": "service_account",
# "project_id": "...",
# "private_key_id": "...",
# "private_key": "...",
# "client_email": "...",
# "client_id": "...",
# "auth_uri": "https://accounts.google.com/o/oauth2/auth",
# "token_uri": "https://oauth2.googleapis.com/token",
# "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",
# "client_x509_cert_url": ""
# }
# Installs Kubecost/OpenCost plugins
plugins:
enabled: false
install:
enabled: false
fullImageName: curlimages/curl:latest
securityContext:
allowPrivilegeEscalation: false
seccompProfile:
type: RuntimeDefault
capabilities:
drop:
- ALL
readOnlyRootFilesystem: true
runAsNonRoot: true
runAsUser: 1001
folder: /opt/opencost/plugin
# leave this commented to always download most recent version of plugins
# version: <INSERT_SPECIFIC_PLUGINS_VERSION>
# the list of enabled plugins
enabledPlugins: []
# - datadog
# pre-existing secret for plugin configuration
existingCustomSecret:
enabled: false
name: "" # name of the secret containing plugin config
secretName: kubecost-plugin-secret
# uncomment this to define plugin configuration via the values file
# configs:
# datadog: |
# {
# "datadog_site": "<INSERT_DATADOG_SITE>",
# "datadog_api_key": "<INSERT_DATADOG_API_KEY>",
# "datadog_app_key": "<INSERT_DATADOG_APP_KEY>"
# }
allocation:
# Enables or disables adding node labels to allocation data (i.e. workloads).
# Defaults to "true" and starts with a sensible includeList for basics like
# topology (e.g. zone, region) and instance type labels.
# nodeLabels:
# enabled: true
# includeList: "node.kubernetes.io/instance-type,topology.kubernetes.io/region,topology.kubernetes.io/zone"
# Enables or disables the ContainerStats pipeline, used for quantile-based
# queries like for request sizing recommendations.
# ContainerStats provides support for quantile-based request right-sizing
# recommendations.
#
# It is disabled by default to avoid problems in extremely high-scale Thanos
# environments. If you would like to try quantile-based request-sizing
# recommendations, enable this! If you are in a high-scale environment,
# please monitor Kubecost logs, Thanos query logs, and Thanos load closely.
# We hope to make major improvements at scale here soon!
#
containerStatsEnabled: true # enabled by default as of v2.2.0
# max number of concurrent Prometheus queries
maxQueryConcurrency: 5
resources:
requests:
cpu: "200m"
memory: "55Mi"
# limits:
# cpu: "800m"
# memory: "256Mi"
readinessProbe:
enabled: true
initialDelaySeconds: 10
periodSeconds: 10
failureThreshold: 200
livenessProbe:
enabled: true
initialDelaySeconds: 10
periodSeconds: 10
failureThreshold: 200
extraArgs: []
# Optional. A list of extra environment variables to be added to the cost-model container.
# extraEnv:
# - name: LOG_FORMAT
# value: json
# # When false, Kubecost will not show Asset costs for local disks physically
# # attached to nodes (e.g. ephemeral storage). This needs to be applied to
# # each cluster monitored.
# - name: ASSET_INCLUDE_LOCAL_DISK_COST
# value: "true"
utcOffset: "+00:00"
extraPorts: []
## etlUtils is a utility typically used by Enterprise customers transitioning
## from v1 to v2 of Kubecost. It translates the data from the "/etl" dir of the
## bucket, to the "/federated" dir of the bucket.
## Ref: https://docs.kubecost.com/install-and-configure/install/multi-cluster/federated-etl/thanos-migration-guide
##
etlUtils:
enabled: false
fullImageName: null
resources: {}
env: {}
nodeSelector: {}
tolerations: []
## Annotations to be added to etlutils deployment
annotations: {}
affinity: {}
# Basic Kubecost ingress, more examples available at https://docs.kubecost.com/install-and-configure/install/ingress-examples
ingress:
enabled: false
# className: nginx
labels:
# kubernetes.io/ingress.class: nginx
# kubernetes.io/tls-acme: "true"
annotations:
# kubernetes.io/ingress.class: nginx
# kubernetes.io/tls-acme: "true"
paths: ["/"] # There's no need to route specifically to the pods-- we have an nginx deployed that handles routing
pathType: ImplementationSpecific
hosts:
- cost-analyzer.local
tls: []
# - secretName: cost-analyzer-tls
# hosts:
# - cost-analyzer.local
nodeSelector: {}
tolerations: []
affinity: {}
topologySpreadConstraints: []
priority:
enabled: false
name: ""
extraVolumes: []
extraVolumeMounts: []
# Define persistence volume for cost-analyzer, more information at https://docs.kubecost.com/install-and-configure/install/storage
persistentVolume:
size: 32Gi
enabled: true # Note that setting this to false means configurations will be wiped out on pod restart.
# storageClass: "-" #
# existingClaim: kubecost-cost-analyzer # a claim in the same namespace as kubecost
labels: {}
annotations: {}
service:
type: ClusterIP
port: 9090
targetPort: 9090
nodePort: {}
labels: {}
annotations: {}
# loadBalancerSourceRanges: []
sessionAffinity:
enabled: false # Makes sure that connections from a client are passed to the same Pod each time, when set to `true`. You should set it when you enabled authentication through OIDC or SAML integration.
timeoutSeconds: 10800
prometheus:
## Provide a full name override for Prometheus.
# fullnameOverride: ""
## Provide a name override for Prometheus.
# nameOverride: ""
rbac:
create: true # Create the RBAC resources for Prometheus.
serviceAccounts:
alertmanager:
create: true
name:
nodeExporter:
create: true
name:
server:
create: true
name:
## Prometheus server ServiceAccount annotations.
## Can be used for AWS IRSA annotations when using Remote Write mode with Amazon Managed Prometheus.
annotations: {}
## Specify an existing ConfigMap to be used by Prometheus when using self-signed certificates.
##
# selfsignedCertConfigMapName: ""
imagePullSecrets:
extraScrapeConfigs: |
- job_name: kubecost
honor_labels: true
scrape_interval: 1m
scrape_timeout: 60s
metrics_path: /metrics
scheme: http
dns_sd_configs:
- names:
- {{ template "cost-analyzer.serviceName" . }}
type: 'A'
port: 9003
- job_name: kubecost-networking
kubernetes_sd_configs:
- role: pod
relabel_configs:
# Scrape only the the targets matching the following metadata
- source_labels: [__meta_kubernetes_pod_label_app_kubernetes_io_instance]
action: keep
regex: kubecost
- source_labels: [__meta_kubernetes_pod_label_app_kubernetes_io_name]
action: keep
regex: network-costs
- job_name: kubecost-aggregator
scrape_interval: 1m
scrape_timeout: 60s
metrics_path: /metrics
scheme: http
dns_sd_configs:
- names:
- {{ template "aggregator.serviceName" . }}
type: 'A'
{{- if or .Values.saml.enabled .Values.oidc.enabled }}
port: 9008
{{- else }}
port: 9004
{{- end }}
## Enables scraping of NVIDIA GPU metrics via dcgm-exporter. Scrapes all
## endpoints which contain "dcgm-exporter" in labels "app",
## "app.kubernetes.io/component", or "app.kubernetes.io/name" with a case
## insensitive match.
## Refs:
## https://github.com/NVIDIA/gpu-operator/blob/d4316a415bbd684ce8416a88042305fc1a093aa4/assets/state-dcgm-exporter/0600_service.yaml#L7
## https://github.com/NVIDIA/dcgm-exporter/blob/54fd1ca137c66511a87a720390613680b9bdabdd/deployment/templates/service.yaml#L23
- job_name: kubecost-dcgm-exporter
kubernetes_sd_configs:
- role: endpoints
relabel_configs:
- source_labels: [__meta_kubernetes_pod_label_app, __meta_kubernetes_pod_label_app_kubernetes_io_component, __meta_kubernetes_pod_label_app_kubernetes_io_name]
action: keep
regex: (?i)(.*dcgm-exporter.*|.*dcgm-exporter.*|.*dcgm-exporter.*)
server:
# If clusterIDConfigmap is defined, instead use user-generated configmap with key CLUSTER_ID
# to use as unique cluster ID in kubecost cost-analyzer deployment.
# This overrides the cluster_id set in prometheus.server.global.external_labels.
# NOTE: This does not affect the external_labels set in prometheus config.
# clusterIDConfigmap: cluster-id-configmap
## Provide a full name override for the Prometheus server.
# fullnameOverride: ""
enabled: true
name: server
sidecarContainers:
strategy:
type: Recreate
rollingUpdate: null
image:
repository: cgr.dev/chainguard/prometheus
tag: latest
pullPolicy: IfNotPresent
priorityClassName: ""
prefixURL: ""
baseURL: ""
env: []
extraFlags:
- web.enable-lifecycle
configPath: /etc/config/prometheus.yml
global:
scrape_interval: 1m
scrape_timeout: 60s
evaluation_interval: 1m
external_labels:
cluster_id: cluster-one # Each cluster should have a unique ID
remoteWrite: {}
remoteRead: {}
extraArgs:
query.max-concurrency: 1
query.max-samples: 100000000
extraInitContainers: []
extraVolumeMounts: []
extraVolumes: []
extraHostPathMounts: []
extraConfigmapMounts: []
extraSecretMounts: []
configMapOverrideName: ""
ingress:
enabled: false
# className: nginx
annotations: {}
extraLabels: {}
hosts: []
pathType: "Prefix"
extraPaths: []
tls: []
# strategy:
# type: Recreate
tolerations: []
nodeSelector: {}
affinity: {}
podDisruptionBudget:
enabled: false
maxUnavailable: 1
# schedulerName:
persistentVolume:
enabled: true
accessModes:
- ReadWriteOnce
annotations: {}
existingClaim: ""
mountPath: /data
size: 32Gi
# storageClass: "-"
# volumeBindingMode: ""
subPath: ""
emptyDir:
sizeLimit: ""
podAnnotations: {}
annotations: {}
podLabels: {}
alertmanagers: []
replicaCount: 1
statefulSet:
enabled: false
annotations: {}
labels: {}
podManagementPolicy: OrderedReady
headless:
annotations: {}
labels: {}
servicePort: 80
readinessProbeInitialDelay: 5
readinessProbeTimeout: 3
readinessProbeFailureThreshold: 3
readinessProbeSuccessThreshold: 1
livenessProbeInitialDelay: 5
livenessProbeTimeout: 3
livenessProbeFailureThreshold: 3
livenessProbeSuccessThreshold: 1
resources: {}
verticalAutoscaler:
enabled: false
## Optional. Defaults to "Auto" if not specified.
# updateMode: "Auto"
## Mandatory. Without, VPA will not be created.
# containerPolicies:
# - containerName: 'prometheus-server'
securityContext: {}
containerSecurityContext: {}
service:
annotations: {}
labels: {}
clusterIP: ""
externalIPs: []
loadBalancerIP: ""
loadBalancerSourceRanges: []
servicePort: 80
sessionAffinity: None
type: ClusterIP
gRPC:
enabled: false
servicePort: 10901
statefulsetReplica:
enabled: false
replica: 0
terminationGracePeriodSeconds: 300
## Prometheus data retention period (default if not specified is 97 hours)
##
## Kubecost builds up its own persistent store of metric data on the
## filesystem (usually a PV) and, when using ETL Backup and/or Federated
## ETL, in more durable object storage like S3 or GCS. Kubecost's data
## retention is _not_ tied to the configured Prometheus retention.
##
## For data durability, we recommend using ETL Backup instead of relying on
## Prometheus retention.
##
## Lower retention values will affect Prometheus by reducing resource
## consumption and increasing stability. It _must not_ be set below or equal
## to kubecostModel.etlHourlyStoreDurationHours, otherwise empty data sets
## may overwrite good data sets. For now, it must also be >= 49h for Daily
## ETL stability.
##
## "ETL Rebuild" and "ETL Repair" is only possible on data available within
## this retention window. This is an extremely rare operation.
##
## If you want maximum security in the event of a Kubecost agent
## (cost-model) outage, increase this value. The current default of 97h is
## intended to balance Prometheus stability and resource consumption
## against the event of an outage in Kubecost which would necessitate a
## version change. 4 days should provide enough time for most users to
## notice a problem and initiate corrective action.
retention: 97h
# retentionSize: should be significantly greater than the storage used in the number of hours set in etlHourlyStoreDurationHours
# Install Prometheus Alert Manager
alertmanager:
enabled: false
## Provide a full name override for Prometheus alertmanager.
# fullnameOverride: ""
strategy:
type: Recreate
rollingUpdate: null
name: alertmanager
image:
repository: cgr.dev/chainguard/prometheus-alertmanager
tag: latest
pullPolicy: IfNotPresent
priorityClassName: ""
extraArgs: {}
prefixURL: ""
baseURL: "http://localhost:9093"
extraEnv: {}
extraSecretMounts: []
configMapOverrideName: ""
configFromSecret: ""
configFileName: alertmanager.yml
ingress:
enabled: false
annotations: {}
extraLabels: {}
hosts: []
extraPaths: []
tls: []
# strategy:
# type: Recreate
tolerations: []