-
Notifications
You must be signed in to change notification settings - Fork 5
/
Copy pathvalues.yaml
1052 lines (975 loc) · 43.1 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
global:
platforms:
openshift:
enabled: false
securityContext:
runAsNonRoot: true
seccompProfile:
type: RuntimeDefault
# runAsUser: 11111
# fsGroup: 22222
# runAsGroup: 33333
# zone: cluster.local (use only if your DNS server doesn't live in the same zone as kubecost)
prometheus:
enabled: true # If false, Prometheus will not be installed -- Warning: Before changing this setting, please read to understand this setting 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
# Durable storage option, product key required
thanos:
enabled: false
# queryService: http://kubecost-thanos-query-frontend-http.kubecost:{{ .Values.thanos.queryFrontend.http.port }} # an address of the thanos query-frontend endpoint, if different from installed thanos
# queryServiceBasicAuthSecretName: mcdbsecret # kubectl create secret generic mcdbsecret -n kubecost --from-file=USERNAME --from-file=PASSWORD <---enter basic auth credentials like that
# queryServiceBearerTokenSecretName mcdbsecret # kubectl create secret generic mcdbsecret -n kubecost --from-file=TOKEN
# queryOffset: 3h # The offset to apply to all thanos queries in order to achieve synchronization on all cluster block stores
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: Always
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: https://localhost:8085/<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
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
notifications:
# Kubecost alerting configuration
# Ref: http://docs.kubecost.com/alerts
# alertConfigs:
# frontendUrl: http://localhost:9090 # optional, used for linkbacks
# globalSlackWebhookUrl: https://hooks.slack.com/services/T00000000/B00000000/XXXXXXXXXXXXXXXXXXXXXXXX # optional, used for Slack alerts
# globalMsTeamsWebhookUrl: https://xxxxx.webhook.office.com/webhookb2/XXXXXXXXXXXXXXXXXXXXXXXX/IncomingWebhook/XXXXXXXXXXXXXXXXXXXXXXXX # optional, used for Microsoft Teams alerts
# globalAlertEmails:
# globalEmailSubject: Custom Subject
# Alerts generated by kubecost, about cluster data
# 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
# # optional, used for alert-specific Slack and Microsoft Teams alerts
# slackWebhookUrl: https://hooks.slack.com/services/T00000000/B00000000/XXXXXXXXXXXXXXXXXXXXXXXX
# msTeamsWebhookUrl: https://xxxxx.webhook.office.com/webhookb2/XXXXXXXXXXXXXXXXXXXXXXXX/IncomingWebhook/XXXXXXXXXXXXXXXXXXXXXXXX
# 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
# Set saved Cost Allocation report(s) accessible from /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:
- property: "cluster"
value: "cluster-one,cluster*" # supports wildcard filtering and multiple comma separated values
- property: "namespace"
value: "kubecost"
- title: "Example Saved Report 1"
window: "month"
aggregateBy: "controllerKind"
chartDisplay: "category"
idle: "share"
rate: "monthly"
accumulate: false
filters:
- property: "label"
value: "app:cost*,environment:kube*"
- property: "namespace"
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
# Set saved Asset report(s) accessible from /reports
# Ref: http://docs.kubecost.com/saved-reports
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"
# Set saved Advanced report(s) accessible from /reports
# Ref: http://docs.kubecost.com/saved-reports
advancedReports:
enabled: false # If true, overwrites report parameters set through UI
reports:
- title: "Example Advanced Report 0"
window: "7d"
aggregateBy: "namespace"
filters:
- property: "cluster"
value: "cluster-one"
cloudBreakdown: "service"
cloudJoin: "label:kubernetes_namespace"
# Set saved Cloud Cost report(s) accessible from /reports
# Ref: http://docs.kubecost.com/saved-reports
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
additionalLabels: {}
# When using OpenShift, remove or comment out the fields
# `fsGroup`, `runAsGroup`, and `runAsUser` in the `securityContext` section below.
securityContext:
runAsNonRoot: true
seccompProfile:
type: RuntimeDefault
fsGroup: 65534
runAsGroup: 65534
runAsUser: 65534
containerSecurityContext:
allowPrivilegeEscalation: false
privileged: false
readOnlyRootFilesystem: true
capabilities:
drop:
- ALL
# 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
# SAML integration for user management and RBAC, enterprise key required
# Ref: https://github.com/kubecost/docs/blob/main/user-management.md
saml:
enabled: false
secretName: "kubecost-authzero"
#metadataSecretName: "kubecost-authzero-metadata" # One of metadataSecretName or idpMetadataURL must be set. defaults to metadataURL if set
idpMetadataURL: "https://dev-elu2z98r.auth0.com/samlp/metadata/c6nY4M37rBP0qSO1IYIqBPPyIPxLS8v2"
appRootURL: "http://localhost:9090" # sample URL
authTimeout: 1440 # number of minutes the JWT will be valid
redirectURL: "https://dev-elu2z98r.auth0.com/v2/logout" # callback URL redirected to after logout
# audienceURI: "http://localhost:9090" # by convention, the same as the appRootURL, but any string uniquely identifying kubecost to your samp IDP. Optional if you follow the convention
# nameIDFormat: "urn:oasis:names:tc:SAML:1.1:nameid-format:unspecified" If your SAML provider requires a specific nameid format
# isGLUUProvider: false # An additional URL parameter must be appended for GLUU providers
# encryptionCertSecret: "kubecost-saml-cert" # k8s secret where the x509 certificate used to encrypt an Okta saml response is stored
# decryptionKeySecret: "kubecost-sank-decryption-key" # k8s secret where the private key associated with the encryptionCertSecret is stored
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: "http://schemas.auth0.com/userType" # a SAML Assertion, one of whose elements has a value that matches on of the values in assertionValues
assertionValues:
- "admin"
- "superusers"
- name: readonly
enabled: false # if readonly is disabled, all users authorized on SAML will default to readonly
assertionName: "http://schemas.auth0.com/userType"
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: "http://schemas.auth0.com/userType"
assertionValues:
- "editor"
oidc:
enabled: false
clientID: "" # application/client 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
authURL: "https://my.auth.server/authorize" # endpoint for login to auth server
loginRedirectURL: "http://my.kubecost.url/model/oidc/authorize" # Kubecost url configured in provider for redirect after authentication
discoveryURL: "https://my.auth.server/.well-known/openid-configuration" # url for OIDC endpoint discovery
# hostedDomain: "example.com" # optional, blocks access to the auth domain specified in the hd claim of the provider ID token
rbac:
enabled: false
groups:
- name: admin
enabled: false # if admin is disabled, all authenticated users will be able to make configuration changes to the kubecost frontend
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
enabled: false # if readonly is disabled, all authenticated users will default to readonly
claimName: "roles"
claimValues:
- "readonly"
- name: editor
enabled: false # 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.
claimName: "roles"
claimValues:
- "editor"
# Adds an httpProxy as an environment variable. systemProxy.enabled must be `true`to have any effect.
# 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"
kubecostFrontend:
image: "gcr.io/kubecost1/frontend"
imagePullPolicy: Always
# extraEnv:
# - name: NGINX_ENTRYPOINT_WORKER_PROCESSES_AUTOTUNE
# value: "1"
# securityContext:
# readOnlyRootFilesystem: true
resources:
requests:
cpu: "10m"
memory: "55Mi"
# limits:
# cpu: "100m"
# memory: "256Mi"
livenessProbe:
enabled: true
initialDelaySeconds: 30
periodSeconds: 10
failureThreshold: 200
ipv6:
enabled: true # disable if the cluster does not support ipv6
# 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;
# api:
# fqdn: kubecost-api.kubecost.svc.cluster.local:9001
# model:
# fqdn: kubecost-model.kubecost.svc.cluster.local:9003
# 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.
# Optional
# The metrics exporter is a separate deployment and service (for prometheus scrape auto-discovery)
# which emits metrics cost-model relies on. Enabling this deployment also removes the KSM dependency
# from the cost-model. If the deployment is not enabled, the metrics will continue to be emitted from
# the cost-model.
exporter:
enabled: false
port: 9005
# Adds the default Prometheus scrape annotations to the metrics exporter service.
# Set to false and use service.annotations (below) to set custom scrape annotations.
prometheusScrape: true
resources: {}
# requests:
# cpu: "200m"
# memory: "55Mi"
## Node tolerations for server scheduling to nodes with taints
## Ref: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/
tolerations: []
# - key: "key"
# operator: "Equal|Exists"
# value: "value"
# effect: "NoSchedule|PreferNoSchedule|NoExecute(1.6 only)"
affinity: {}
service:
annotations: {}
# Service Monitor for Kubecost Metrics
serviceMonitor: # the kubecost included prometheus uses scrapeConfigs and does not support service monitors. The following options assume an existing prometheus that supports serviceMonitors.
enabled: false
additionalLabels: {}
metricRelabelings: []
relabelings: []
## PriorityClassName
## Ref: https://kubernetes.io/docs/concepts/configuration/pod-priority-preemption/#priorityclass
priorityClassName: ""
additionalLabels: {}
nodeSelector: {}
extraArgs: []
sigV4Proxy:
image: public.ecr.aws/aws-observability/aws-sigv4-proxy:latest
imagePullPolicy: Always
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>
kubecostModel:
image: "gcr.io/kubecost1/cost-model"
imagePullPolicy: Always
# extraEnv:
# - name: SOME_VARIABLE
# value: "some_value"
# securityContext:
# readOnlyRootFilesystem: true
# Enables the emission of the kubecost_cloud_credit_total and
# kubecost_cloud_expense_total metrics
outOfClusterPromMetricsEnabled: false
# Build local cost allocation cache
warmCache: false
# Build local savings cache
warmSavingsCache: true
# Run allocation ETL pipelines
etl: true
# Enable the ETL filestore backing storage
etlFileStoreEnabled: 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 (not recommended)
etlHourlyStoreDurationHours: 49
# The total number of weeks the ETL pipelines will build
# Set to 0 to disable weekly ETL (not recommended)
# The default is 53 to ensure at least a year of coverage (371 days)
etlWeeklyStoreDurationWeeks: 53
# For deploying kubecost in a cluster that does not self-monitor
etlReadOnlyMode: false
## Feature to view your out-of-cluster costs and their k8s utilization
## Ref: https://docs.kubecost.com/using-kubecost/navigating-the-kubecost-ui/cloud-costs-explorer
cloudCost:
enabled: true
labelList:
IsIncludeList: false
# format labels as comma separated string (ex. "label1,label2,label3")
labels: ""
topNItems: 1000
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: false
# max number of concurrent Prometheus queries
maxQueryConcurrency: 5
resources:
requests:
cpu: "200m"
memory: "55Mi"
#limits:
# cpu: "800m"
# memory: "256Mi"
livenessProbe:
enabled: false
initialDelaySeconds: 30
periodSeconds: 10
failureThreshold: 200
extraArgs: []
# Basic Kubecost ingress, more examples available at https://github.com/kubecost/docs/blob/main/ingress-examples.md
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: []
# - key: "key"
# operator: "Equal|Exists"
# value: "value"
# effect: "NoSchedule|PreferNoSchedule|NoExecute(1.6 only)"
affinity: {}
# If true, creates a PriorityClass to be used by the cost-analyzer pod
priority:
enabled: false
name: "" # Provide name of existing priority class only. If left blank, upstream chart will create one from default template.
# value: 1000000
# If true, enable creation of NetworkPolicy resources.
networkPolicy:
enabled: false
denyEgress: true # create a network policy that denies egress from kubecost
sameNamespace: true # Set to true if cost analyzer and prometheus are on the same namespace
# namespace: kubecost # Namespace where prometheus is installed
# Cost-analyzer specific vars using the new template
costAnalyzer:
enabled: false # If true, create a network policy for cost-analyzer
annotations: {} # annotations to be added to the network policy
additionalLabels: {} # additional labels to be added to the network policy
# Examples rules:
# ingressRules:
# - selectors: # allow ingress from self on all ports
# - podSelector:
# matchLabels:
# app.kubernetes.io/name: cost-analyzer
# - selectors: # allow egress access to prometheus
# - namespaceSelector:
# matchLabels:
# name: prometheus
# podSelector:
# matchLabels:
# app: prometheus
# ports:
# - protocol: TCP
# port: 9090
# egressRules:
# - selectors: # restrict egress to inside cluster
# - namespaceSelector: {}
podSecurityPolicy:
enabled: false
## @param extraVolumes A list of volumes to be added to the pod
##
extraVolumes: []
## @param extraVolumeMounts A list of volume mounts to be added to the pod
##
extraVolumeMounts: []
# Define persistence volume for cost-analyzer, more information at https://github.com/kubecost/docs/blob/main/storage.md
persistentVolume:
size: 32Gi
dbSize: 32.0Gi
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: {}
# Enabling long-term durable storage with Postgres requires an enterprise license
remoteWrite:
postgres:
enabled: false
initImage: "gcr.io/kubecost1/sql-init"
initImagePullPolicy: Always
installLocal: true
remotePostgresAddress: "" # ignored if installing locally
## PriorityClassName
## Ref: https://kubernetes.io/docs/concepts/configuration/pod-priority-preemption/#priorityclass
priorityClassName: ""
persistentVolume:
size: 200Gi
auth:
password: admin # change me
prometheus:
podSecurityPolicy:
enabled: false
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]
action: keep
regex: {{ template "cost-analyzer.networkCostsName" . }}
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
resources: {}
# limits:
# cpu: 500m
# memory: 512Mi
# requests:
# cpu: 500m
# memory: 512Mi
global:
scrape_interval: 1m
scrape_timeout: 60s
evaluation_interval: 1m
external_labels:
cluster_id: cluster-one # Each cluster should have a unique ID
persistentVolume:
size: 32Gi
enabled: true
extraArgs:
query.max-concurrency: 1
query.max-samples: 100000000
tolerations: []
# - key: "key"
# operator: "Equal|Exists"
# value: "value"
# effect: "NoSchedule|PreferNoSchedule|NoExecute(1.6 only)"
alertmanager:
enabled: false
persistentVolume:
enabled: true
# node-export must be disabled if there is an existing daemonset: https://guide.kubecost.com/hc/en-us/articles/4407601830679-Troubleshoot-Install#a-name-node-exporter-a-issue-failedscheduling-kubecost-prometheus-node-exporter
nodeExporter:
enabled: true
# kubecost emits pre-2.0 KSM metrics, KSM is enabled by default here for backwards compatibility, but can be disabled to save resources without concern to kubecost metrics
kubeStateMetrics:
enabled: true
kube-state-metrics:
disabled: false
pushgateway:
enabled: false
persistentVolume:
enabled: true
serverFiles:
# prometheus.yml: # Sample block -- enable if using an in cluster durable store.
# remote_write:
# - url: "http://pgprometheus-adapter:9201/write"
# write_relabel_configs:
# - source_labels: [__name__]
# regex: 'container_.*_allocation|container_.*_allocation_bytes|.*_hourly_cost|kube_pod_container_resource_requests{resource="memory", unit="byte"}|container_memory_working_set_bytes|kube_pod_container_resource_requests{resource="cpu", unit="core"}|kube_pod_container_resource_requests|pod_pvc_allocation|kube_namespace_labels|kube_pod_labels'
# action: keep
# queue_config:
# max_samples_per_send: 1000
#remote_read:
# - url: "http://pgprometheus-adapter:9201/read"
rules:
groups:
- name: CPU
rules:
- expr: sum(rate(container_cpu_usage_seconds_total{container!=""}[5m]))
record: cluster:cpu_usage:rate5m
- expr: rate(container_cpu_usage_seconds_total{container!=""}[5m])
record: cluster:cpu_usage_nosum:rate5m
- expr: avg(irate(container_cpu_usage_seconds_total{container!="POD", container!=""}[5m])) by (container,pod,namespace)
record: kubecost_container_cpu_usage_irate
- expr: sum(container_memory_working_set_bytes{container!="POD",container!=""}) by (container,pod,namespace)
record: kubecost_container_memory_working_set_bytes
- expr: sum(container_memory_working_set_bytes{container!="POD",container!=""})
record: kubecost_cluster_memory_working_set_bytes
- name: Savings
rules:
- expr: sum(avg(kube_pod_owner{owner_kind!="DaemonSet"}) by (pod) * sum(container_cpu_allocation) by (pod))
record: kubecost_savings_cpu_allocation
labels:
daemonset: "false"
- expr: sum(avg(kube_pod_owner{owner_kind="DaemonSet"}) by (pod) * sum(container_cpu_allocation) by (pod)) / sum(kube_node_info)
record: kubecost_savings_cpu_allocation
labels:
daemonset: "true"
- expr: sum(avg(kube_pod_owner{owner_kind!="DaemonSet"}) by (pod) * sum(container_memory_allocation_bytes) by (pod))
record: kubecost_savings_memory_allocation_bytes
labels:
daemonset: "false"
- expr: sum(avg(kube_pod_owner{owner_kind="DaemonSet"}) by (pod) * sum(container_memory_allocation_bytes) by (pod)) / sum(kube_node_info)
record: kubecost_savings_memory_allocation_bytes
labels:
daemonset: "true"
## Module for measuring network costs
## Ref: https://github.com/kubecost/docs/blob/main/network-allocation.md
networkCosts:
enabled: false
podSecurityPolicy:
enabled: false
image: gcr.io/kubecost1/kubecost-network-costs:v0.17.2
imagePullPolicy: Always
updateStrategy:
type: RollingUpdate
# For existing Prometheus Installs, annotates the Service which generates Endpoints for each of the network-costs pods.
# The Service is annotated with prometheus.io/scrape: "true" to automatically get picked up by the prometheus config.
# NOTE: Setting this option to true and leaving the above extraScrapeConfig "job_name: kubecost-networking" configured will cause the
# NOTE: pods to be scraped twice.
prometheusScrape: false
# Traffic Logging will enable logging the top 5 destinations for each source
# every 30 minutes.
trafficLogging: true
# Port will set both the containerPort and hostPort to this value.
# These must be identical due to network-costs being run on hostNetwork
port: 3001
# this daemonset can use significant resources on large clusters: https://guide.kubecost.com/hc/en-us/articles/4407595973527-Network-Traffic-Cost-Allocation
resources:
limits: # remove the limits by setting cpu: null
cpu: 500m # can be less, will depend on cluster size
# memory: it is not recommended to set a memory limit
requests:
cpu: 50m
memory: 20Mi
extraArgs: []
config:
# Configuration for traffic destinations, including specific classification
# for IPs and CIDR blocks. This configuration will act as an override to the
# automatic classification provided by network-costs.
destinations:
# In Zone contains a list of address/range that will be
# classified as in zone.
in-zone:
# Loopback Addresses in "IANA IPv4 Special-Purpose Address Registry"
- "127.0.0.0/8"
# IPv4 Link Local Address Space
- "169.254.0.0/16"
# Private Address Ranges in RFC-1918
- "10.0.0.0/8" # Remove this entry if using Multi-AZ Kubernetes
- "172.16.0.0/12"
- "192.168.0.0/16"
# In Region contains a list of address/range that will be
# classified as in region. This is synonymous with cross
# zone traffic, where the regions between source and destinations
# are the same, but the zone is different.
in-region: []
# Cross Region contains a list of address/range that will be
# classified as non-internet egress from one region to another.
cross-region: []
# Internet contains a list of address/range that will be
# classified as internet traffic. This is synonymous with traffic
# that cannot be classified within the cluster.
# NOTE: Internet classification filters are executed _after_
# NOTE: direct-classification, but before in-zone, in-region,
# NOTE: and cross-region.
internet: []
# Direct Classification specifically maps an ip address or range
# to a region (required) and/or zone (optional). This classification
# takes priority over in-zone, in-region, and cross-region configurations.
direct-classification: []
# - region: "us-east1"
# zone: "us-east1-c"
# ips:
# - "10.0.0.0/24"
services:
# google-cloud-services: when set to true, enables labeling traffic metrics with google cloud
# service endpoints
google-cloud-services: false
# amazon-web-services: when set to true, enables labeling traffic metrics with amazon web service
# endpoints.
amazon-web-services: false
# azure-cloud-services: when set to true, enables labeling traffic metrics with azure cloud service
# endpoints
azure-cloud-services: false
# user defined services provide a way to define custom service endpoints which will label traffic metrics
# falling within the defined address range.
#services:
# - service: "test-service-1"
# ips:
# - "19.1.1.2"
# - service: "test-service-2"
# ips:
# - "15.128.15.2"
# - "20.0.0.0/8"
## Node tolerations for server scheduling to nodes with taints
## Ref: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/
##
tolerations: []
# - key: "key"
# operator: "Equal|Exists"
# value: "value"
# effect: "NoSchedule|PreferNoSchedule|NoExecute(1.6 only)"
affinity: {}
service:
annotations: {}
labels: {}
## PriorityClassName
## Ref: https://kubernetes.io/docs/concepts/configuration/pod-priority-preemption/#priorityclass
priorityClassName: ""
## PodMonitor
## Allows scraping of network metrics from a dedicated prometheus operator setup
podMonitor:
enabled: false
additionalLabels: {}
additionalLabels: {}
nodeSelector: {}
annotations: {}
healthCheckProbes: {}
# readinessProbe:
# tcpSocket:
# port: 3001
# initialDelaySeconds: 5
# periodSeconds: 10
# failureThreshold: 5
# livenessProbe:
# tcpSocket:
# port: 3001
# initialDelaySeconds: 5
# periodSeconds: 10
# failureThreshold: 5
additionalSecurityContext: {}
# readOnlyRootFilesystem: true
## Kubecost Deployment Configuration
## Used for HA mode in Business & Enterprise tier
##
kubecostDeployment:
replicas: 1
leaderFollower:
enabled: false
# deploymentStrategy:
# rollingUpdate:
# maxSurge: 1
# maxUnavailable: 1
# type: RollingUpdate
labels: {}
annotations: {}
## QueryServiceReplicas
## Ref: https://docs.kubecost.com/install-and-configure/advanced-configuration/query-service-replicas
##
queryServiceReplicas: 0
queryService:
securityContext:
fsGroup: 65534
runAsGroup: 65534
runAsUser: 65534
runAsNonRoot: false
seccompProfile:
type: RuntimeDefault
containerSecurityContext:
allowPrivilegeEscalation: true
readOnlyRootFilesystem: false
capabilities:
drop:
- ALL
resources:
requests:
## You can use the Kubecost savings report for 'Right-size your
## container requests' to determine the recommended resource requests
## once the pod has run for 24 hours.
cpu: 1000m
memory: 500Mi
## default storage class
storageClass: ""
databaseVolumeSize: 100Gi
configVolumeSize: 1Gi
# Kubecost Cluster Controller for Right Sizing and Cluster Turndown
clusterController:
enabled: false
image: gcr.io/kubecost1/cluster-controller:v0.11.0
imagePullPolicy: Always
## PriorityClassName
## Ref: https://kubernetes.io/docs/concepts/configuration/pod-priority-preemption/#priorityclass
priorityClassName: ""
kubescaler:
# If true, will cause all (supported) workloads to be have their requests
# automatically right-sized on a regular basis.
defaultResizeAll: false
# fqdn: kubecost-cluster-controller.kubecost.svc.cluster.local:9731
namespaceTurndown:
rbac:
enabled: true
reporting:
# Kubecost bug report feature: Logs access/collection limited to .Release.Namespace
# Ref: http://docs.kubecost.com/bug-report
logCollection: true
# Basic frontend analytics
productAnalytics: true
# Report Javascript errors
errorReporting: true
valuesReporting: true
# googleAnalyticsTag allows you to embed your Google Global Site Tag to track usage of Kubecost.
# googleAnalyticsTag is only included in our Enterprise offering.
# googleAnalyticsTag: G-XXXXXXXXX
serviceMonitor: # the kubecost included prometheus uses scrapeConfigs and does not support service monitors. The following options assume an existing prometheus that supports serviceMonitors.
enabled: false
additionalLabels: {}
metricRelabelings: []
relabelings: []
networkCosts:
enabled: false
scrapeTimeout: 10s
additionalLabels: {}
metricRelabelings: []
relabelings: []
prometheusRule:
enabled: false
additionalLabels: {}
supportNFS: false
# initChownDataImage ensures all Kubecost filepath permissions on PV or local storage are set up correctly.
initChownDataImage: "busybox" # Supports a fully qualified Docker image, e.g. registry.hub.docker.com/library/busybox:latest
initChownData:
resources: {}
#requests:
# cpu: "50m"
# memory: "20Mi"
grafana:
# namespace_datasources: kubecost # override the default namespace here
# namespace_dashboards: kubecost # override the default namespace here
rbac:
# Manage the Grafana Pod Security Policy
pspEnabled: false
# datasources:
# datasources.yaml:
# apiVersion: 1
# datasources:
# - name: prometheus-kubecost
# type: prometheus
# url: http://kubecost-prometheus-server.kubecost.svc.cluster.local
# access: proxy
# isDefault: false
# jsonData:
# httpMethod: POST
# prometheusType: Prometheus
# prometheusVersion: 2.35.0
# timeInterval: 1m
sidecar:
dashboards:
enabled: true