-
Notifications
You must be signed in to change notification settings - Fork 0
/
prometheus.yml
1322 lines (1135 loc) · 45.4 KB
/
prometheus.yml
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
# yaml-language-server: $schema=values.schema.json
# Default values for prometheus.
# This is a YAML-formatted file.
# Declare variables to be passed into your templates.
rbac:
create: true
podSecurityPolicy:
enabled: false
imagePullSecrets: []
# - name: "image-pull-secret"
## Define serviceAccount names for components. Defaults to component's fully qualified name.
##
serviceAccounts:
server:
create: true
name: ""
annotations: {}
## Opt out of automounting Kubernetes API credentials.
## It will be overriden by server.automountServiceAccountToken value, if set.
# automountServiceAccountToken: false
## Additional labels to attach to all resources
commonMetaLabels: {}
## Monitors ConfigMap changes and POSTs to a URL
## Ref: https://github.com/prometheus-operator/prometheus-operator/tree/main/cmd/prometheus-config-reloader
##
configmapReload:
## URL for configmap-reload to use for reloads
##
reloadUrl: ""
## env sets environment variables to pass to the container. Can be set as name/value pairs,
## read from secrets or configmaps.
env: []
# - name: SOMEVAR
# value: somevalue
# - name: PASSWORD
# valueFrom:
# secretKeyRef:
# name: mysecret
# key: password
# optional: false
prometheus:
## If false, the configmap-reload container will not be deployed
##
enabled: true
## configmap-reload container name
##
name: configmap-reload
## configmap-reload container image
##
image:
repository: quay.io/prometheus-operator/prometheus-config-reloader
tag: v0.74.0
# When digest is set to a non-empty value, images will be pulled by digest (regardless of tag value).
digest: ""
pullPolicy: IfNotPresent
## config-reloader's container port and port name for probes and metrics
containerPort: 8080
containerPortName: metrics
## Additional configmap-reload container arguments
## Set to null for argumentless flags
##
extraArgs: {}
## Additional configmap-reload volume directories
##
extraVolumeDirs: []
## Additional configmap-reload volume mounts
##
extraVolumeMounts: []
## Additional configmap-reload mounts
##
extraConfigmapMounts: []
# - name: prometheus-alerts
# mountPath: /etc/alerts.d
# subPath: ""
# configMap: prometheus-alerts
# readOnly: true
## Security context to be added to configmap-reload container
containerSecurityContext: {}
## Settings for Prometheus reloader's readiness, liveness and startup probes
## Ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-startup-probes/
##
livenessProbe:
httpGet:
path: /healthz
port: metrics
scheme: HTTP
periodSeconds: 10
initialDelaySeconds: 2
readinessProbe:
httpGet:
path: /healthz
port: metrics
scheme: HTTP
periodSeconds: 10
startupProbe:
enabled: false
httpGet:
path: /healthz
port: metrics
scheme: HTTP
periodSeconds: 10
## configmap-reload resource requests and limits
## Ref: http://kubernetes.io/docs/user-guide/compute-resources/
##
resources: {}
server:
## Prometheus server container name
##
name: server
## Opt out of automounting Kubernetes API credentials.
## If set it will override serviceAccounts.server.automountServiceAccountToken value for ServiceAccount.
# automountServiceAccountToken: false
## Use a ClusterRole (and ClusterRoleBinding)
## - If set to false - we define a RoleBinding in the defined namespaces ONLY
##
## NB: because we need a Role with nonResourceURL's ("/metrics") - you must get someone with Cluster-admin privileges to define this role for you, before running with this setting enabled.
## This makes prometheus work - for users who do not have ClusterAdmin privs, but wants prometheus to operate on their own namespaces, instead of clusterwide.
##
## You MUST also set namespaces to the ones you have access to and want monitored by Prometheus.
##
# useExistingClusterRoleName: nameofclusterrole
## If set it will override prometheus.server.fullname value for ClusterRole and ClusterRoleBinding
##
clusterRoleNameOverride: ""
# Enable only the release namespace for monitoring. By default all namespaces are monitored.
# If releaseNamespace and namespaces are both set a merged list will be monitored.
releaseNamespace: false
## namespaces to monitor (instead of monitoring all - clusterwide). Needed if you want to run without Cluster-admin privileges.
# namespaces:
# - yournamespace
# sidecarContainers - add more containers to prometheus server
# Key/Value where Key is the sidecar `- name: <Key>`
# Example:
# sidecarContainers:
# webserver:
# image: nginx
# OR for adding OAuth authentication to Prometheus
# sidecarContainers:
# oauth-proxy:
# image: quay.io/oauth2-proxy/oauth2-proxy:v7.1.2
# args:
# - --upstream=http://127.0.0.1:9090
# - --http-address=0.0.0.0:8081
# - ...
# ports:
# - containerPort: 8081
# name: oauth-proxy
# protocol: TCP
# resources: {}
sidecarContainers: {}
# sidecarTemplateValues - context to be used in template for sidecarContainers
# Example:
# sidecarTemplateValues: *your-custom-globals
# sidecarContainers:
# webserver: |-
# {{ include "webserver-container-template" . }}
# Template for `webserver-container-template` might looks like this:
# image: "{{ .Values.server.sidecarTemplateValues.repository }}:{{ .Values.server.sidecarTemplateValues.tag }}"
# ...
#
sidecarTemplateValues: {}
## Prometheus server container image
##
image:
repository: quay.io/prometheus/prometheus
# if not set appVersion field from Chart.yaml is used
tag: ""
# When digest is set to a non-empty value, images will be pulled by digest (regardless of tag value).
digest: ""
pullPolicy: IfNotPresent
## Prometheus server command
##
command: []
## prometheus server priorityClassName
##
priorityClassName: ""
## EnableServiceLinks indicates whether information about services should be injected
## into pod's environment variables, matching the syntax of Docker links.
## WARNING: the field is unsupported and will be skipped in K8s prior to v1.13.0.
##
enableServiceLinks: true
## The URL prefix at which the container can be accessed. Useful in the case the '-web.external-url' includes a slug
## so that the various internal URLs are still able to access as they are in the default case.
## (Optional)
prefixURL: ""
## External URL which can access prometheus
## Maybe same with Ingress host name
baseURL: ""
## Additional server container environment variables
##
## You specify this manually like you would a raw deployment manifest.
## This means you can bind in environment variables from secrets.
##
## e.g. static environment variable:
## - name: DEMO_GREETING
## value: "Hello from the environment"
##
## e.g. secret environment variable:
## - name: USERNAME
## valueFrom:
## secretKeyRef:
## name: mysecret
## key: username
env: []
# List of flags to override default parameters, e.g:
# - --enable-feature=agent
# - --storage.agent.retention.max-time=30m
# - --config.file=/etc/config/prometheus.yml
defaultFlagsOverride: []
extraFlags:
- web.enable-lifecycle
## web.enable-admin-api flag controls access to the administrative HTTP API which includes functionality such as
## deleting time series. This is disabled by default.
# - web.enable-admin-api
##
## storage.tsdb.no-lockfile flag controls BD locking
# - storage.tsdb.no-lockfile
##
## storage.tsdb.wal-compression flag enables compression of the write-ahead log (WAL)
# - storage.tsdb.wal-compression
## Path to a configuration file on prometheus server container FS
configPath: /etc/config/prometheus.yml
### The data directory used by prometheus to set --storage.tsdb.path
### When empty server.persistentVolume.mountPath is used instead
storagePath: ""
global:
## How frequently to scrape targets by default
##
scrape_interval: 15s
## How long until a scrape request times out
##
scrape_timeout: 10s
## How frequently to evaluate rules
##
evaluation_interval: 1m
## https://prometheus.io/docs/prometheus/latest/configuration/configuration/#remote_write
##
remoteWrite: []
## https://prometheus.io/docs/prometheus/latest/configuration/configuration/#remote_read
##
remoteRead: []
## https://prometheus.io/docs/prometheus/latest/configuration/configuration/#tsdb
##
tsdb: {}
# out_of_order_time_window: 0s
## https://prometheus.io/docs/prometheus/latest/configuration/configuration/#exemplars
## Must be enabled via --enable-feature=exemplar-storage
##
exemplars: {}
# max_exemplars: 100000
## Custom HTTP headers for Liveness/Readiness/Startup Probe
##
## Useful for providing HTTP Basic Auth to healthchecks
probeHeaders: []
# - name: "Authorization"
# value: "Bearer ABCDEabcde12345"
## Additional Prometheus server container arguments
## Set to null for argumentless flags
##
extraArgs: {}
# web.enable-remote-write-receiver: null
## Additional InitContainers to initialize the pod
##
extraInitContainers: []
## Additional Prometheus server Volume mounts
##
extraVolumeMounts: []
## Additional Prometheus server Volumes
##
extraVolumes: []
## Additional Prometheus server hostPath mounts
##
extraHostPathMounts: []
# - name: certs-dir
# mountPath: /etc/kubernetes/certs
# subPath: ""
# hostPath: /etc/kubernetes/certs
# readOnly: true
extraConfigmapMounts: []
# - name: certs-configmap
# mountPath: /prometheus
# subPath: ""
# configMap: certs-configmap
# readOnly: true
## Additional Prometheus server Secret mounts
# Defines additional mounts with secrets. Secrets must be manually created in the namespace.
extraSecretMounts: []
# - name: secret-files
# mountPath: /etc/secrets
# subPath: ""
# secretName: prom-secret-files
# readOnly: true
## ConfigMap override where fullname is {{.Release.Name}}-{{.Values.server.configMapOverrideName}}
## Defining configMapOverrideName will cause templates/server-configmap.yaml
## to NOT generate a ConfigMap resource
##
configMapOverrideName: ""
## Extra labels for Prometheus server ConfigMap (ConfigMap that holds serverFiles)
extraConfigmapLabels: {}
## Override the prometheus.server.fullname for all objects related to the Prometheus server
fullnameOverride: ""
ingress:
## If true, Prometheus server Ingress will be created
##
enabled: false
# For Kubernetes >= 1.18 you should specify the ingress-controller via the field ingressClassName
# See https://kubernetes.io/blog/2020/04/02/improvements-to-the-ingress-api-in-kubernetes-1.18/#specifying-the-class-of-an-ingress
# ingressClassName: nginx
## Prometheus server Ingress annotations
##
annotations: {}
# kubernetes.io/ingress.class: nginx
# kubernetes.io/tls-acme: 'true'
## Prometheus server Ingress additional labels
##
extraLabels: {}
## Redirect ingress to an additional defined port on the service
# servicePort: 8081
## Prometheus server Ingress hostnames with optional path
## Must be provided if Ingress is enabled
##
hosts: []
# - prometheus.domain.com
# - domain.com/prometheus
path: /
# pathType is only for k8s >= 1.18
pathType: Prefix
## Extra paths to prepend to every host configuration. This is useful when working with annotation based services.
extraPaths: []
# - path: /*
# backend:
# serviceName: ssl-redirect
# servicePort: use-annotation
## Prometheus server Ingress TLS configuration
## Secrets must be manually created in the namespace
##
tls: []
# - secretName: prometheus-server-tls
# hosts:
# - prometheus.domain.com
## Server Deployment Strategy type
strategy:
type: Recreate
## hostAliases allows adding entries to /etc/hosts inside the containers
hostAliases: []
# - ip: "127.0.0.1"
# hostnames:
# - "example.com"
## Node tolerations for server scheduling to nodes with taints
## Ref: https://kubernetes.io/docs/concepts/scheduling-eviction/taint-and-toleration/
##
tolerations: []
# - key: "key"
# operator: "Equal|Exists"
# value: "value"
# effect: "NoSchedule|PreferNoSchedule|NoExecute(1.6 only)"
## Node labels for Prometheus server pod assignment
## Ref: https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/
##
nodeSelector: {}
## Pod affinity
##
affinity: {}
## Pod anti-affinity can prevent the scheduler from placing Prometheus server replicas on the same node.
## The value "soft" means that the scheduler should *prefer* to not schedule two replica pods onto the same node but no guarantee is provided.
## The value "hard" means that the scheduler is *required* to not schedule two replica pods onto the same node.
## The default value "" will disable pod anti-affinity so that no anti-affinity rules will be configured (unless set in `server.affinity`).
##
podAntiAffinity: ""
## If anti-affinity is enabled sets the topologyKey to use for anti-affinity.
## This can be changed to, for example, failure-domain.beta.kubernetes.io/zone
##
podAntiAffinityTopologyKey: kubernetes.io/hostname
## Pod topology spread constraints
## ref. https://kubernetes.io/docs/concepts/scheduling-eviction/topology-spread-constraints/
topologySpreadConstraints: []
## PodDisruptionBudget settings
## ref: https://kubernetes.io/docs/concepts/workloads/pods/disruptions/
##
podDisruptionBudget:
enabled: false
maxUnavailable: 1
# minAvailable: 1
## unhealthyPodEvictionPolicy is available since 1.27.0 (beta)
## https://kubernetes.io/docs/tasks/run-application/configure-pdb/#unhealthy-pod-eviction-policy
# unhealthyPodEvictionPolicy: IfHealthyBudget
## Use an alternate scheduler, e.g. "stork".
## ref: https://kubernetes.io/docs/tasks/administer-cluster/configure-multiple-schedulers/
##
# schedulerName:
persistentVolume:
## If true, Prometheus server will create/use a Persistent Volume Claim
## If false, use emptyDir
##
enabled: true
## If set it will override the name of the created persistent volume claim
## generated by the stateful set.
##
statefulSetNameOverride: ""
## Prometheus server data Persistent Volume access modes
## Must match those of existing PV or dynamic provisioner
## Ref: http://kubernetes.io/docs/user-guide/persistent-volumes/
##
accessModes:
- ReadWriteOnce
## Prometheus server data Persistent Volume labels
##
labels: {}
## Prometheus server data Persistent Volume annotations
##
annotations: {}
## Prometheus server data Persistent Volume existing claim name
## Requires server.persistentVolume.enabled: true
## If defined, PVC must be created manually before volume will be bound
existingClaim: ""
## Prometheus server data Persistent Volume mount root path
##
mountPath: /data
## Prometheus server data Persistent Volume size
##
size: 8Gi
## Prometheus server data Persistent Volume Storage Class
## If defined, storageClassName: <storageClass>
## If set to "-", storageClassName: "", which disables dynamic provisioning
## If undefined (the default) or set to null, no storageClassName spec is
## set, choosing the default provisioner. (gp2 on AWS, standard on
## GKE, AWS & OpenStack)
##
# storageClass: "-"
## Prometheus server data Persistent Volume Binding Mode
## If defined, volumeBindingMode: <volumeBindingMode>
## If undefined (the default) or set to null, no volumeBindingMode spec is
## set, choosing the default mode.
##
# volumeBindingMode: ""
## Subdirectory of Prometheus server data Persistent Volume to mount
## Useful if the volume's root directory is not empty
##
subPath: ""
## Persistent Volume Claim Selector
## Useful if Persistent Volumes have been provisioned in advance
## Ref: https://kubernetes.io/docs/concepts/storage/persistent-volumes/#selector
##
# selector:
# matchLabels:
# release: "stable"
# matchExpressions:
# - { key: environment, operator: In, values: [ dev ] }
## Persistent Volume Name
## Useful if Persistent Volumes have been provisioned in advance and you want to use a specific one
##
# volumeName: ""
emptyDir:
## Prometheus server emptyDir volume size limit
##
sizeLimit: ""
## Annotations to be added to Prometheus server pods
##
podAnnotations: {}
# iam.amazonaws.com/role: prometheus
## Labels to be added to Prometheus server pods
##
podLabels: {}
## Prometheus AlertManager configuration
##
alertmanagers: []
## Specify if a Pod Security Policy for node-exporter must be created
## Ref: https://kubernetes.io/docs/concepts/policy/pod-security-policy/
##
podSecurityPolicy:
annotations: {}
## Specify pod annotations
## Ref: https://kubernetes.io/docs/concepts/policy/pod-security-policy/#apparmor
## Ref: https://kubernetes.io/docs/concepts/policy/pod-security-policy/#seccomp
## Ref: https://kubernetes.io/docs/concepts/policy/pod-security-policy/#sysctl
##
# seccomp.security.alpha.kubernetes.io/allowedProfileNames: '*'
# seccomp.security.alpha.kubernetes.io/defaultProfileName: 'docker/default'
# apparmor.security.beta.kubernetes.io/defaultProfileName: 'runtime/default'
## Use a StatefulSet if replicaCount needs to be greater than 1 (see below)
##
replicaCount: 1
## Number of old history to retain to allow rollback
## Default Kubernetes value is set to 10
##
revisionHistoryLimit: 10
## Annotations to be added to ConfigMap
##
configMapAnnotations: {}
## Annotations to be added to deployment
##
deploymentAnnotations: {}
statefulSet:
## If true, use a statefulset instead of a deployment for pod management.
## This allows to scale replicas to more than 1 pod
##
enabled: false
annotations: {}
labels: {}
podManagementPolicy: OrderedReady
## Alertmanager headless service to use for the statefulset
##
headless:
annotations: {}
labels: {}
servicePort: 80
## Enable gRPC port on service to allow auto discovery with thanos-querier
gRPC:
enabled: false
servicePort: 10901
# nodePort: 10901
## Statefulset's persistent volume claim retention policy
## pvcDeleteOnStsDelete and pvcDeleteOnStsScale determine whether
## statefulset's PVCs are deleted (true) or retained (false) on scaling down
## and deleting statefulset, respectively. Requires 1.27.0+.
## Ref: https://kubernetes.io/docs/concepts/workloads/controllers/statefulset/#persistentvolumeclaim-retention
##
pvcDeleteOnStsDelete: false
pvcDeleteOnStsScale: false
## Prometheus server readiness and liveness probe initial delay and timeout
## Ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-startup-probes/
##
tcpSocketProbeEnabled: false
probeScheme: HTTP
readinessProbeInitialDelay: 30
readinessProbePeriodSeconds: 5
readinessProbeTimeout: 4
readinessProbeFailureThreshold: 3
readinessProbeSuccessThreshold: 1
livenessProbeInitialDelay: 30
livenessProbePeriodSeconds: 15
livenessProbeTimeout: 10
livenessProbeFailureThreshold: 3
livenessProbeSuccessThreshold: 1
startupProbe:
enabled: false
periodSeconds: 5
failureThreshold: 30
timeoutSeconds: 10
## Prometheus server resource requests and limits
## Ref: http://kubernetes.io/docs/user-guide/compute-resources/
##
resources: {}
# limits:
# cpu: 500m
# memory: 512Mi
# requests:
# cpu: 500m
# memory: 512Mi
# Required for use in managed kubernetes clusters (such as AWS EKS) with custom CNI (such as calico),
# because control-plane managed by AWS cannot communicate with pods' IP CIDR and admission webhooks are not working
##
hostNetwork: false
# When hostNetwork is enabled, this will set to ClusterFirstWithHostNet automatically
dnsPolicy: ClusterFirst
# Use hostPort
# hostPort: 9090
# Use portName
portName: ""
## Vertical Pod Autoscaler config
## Ref: https://github.com/kubernetes/autoscaler/tree/master/vertical-pod-autoscaler
verticalAutoscaler:
## If true a VPA object will be created for the controller (either StatefulSet or Deployemnt, based on above configs)
enabled: false
# updateMode: "Auto"
# containerPolicies:
# - containerName: 'prometheus-server'
# Custom DNS configuration to be added to prometheus server pods
dnsConfig: {}
# nameservers:
# - 1.2.3.4
# searches:
# - ns1.svc.cluster-domain.example
# - my.dns.search.suffix
# options:
# - name: ndots
# value: "2"
# - name: edns0
## Security context to be added to server pods
##
securityContext:
runAsUser: 65534
runAsNonRoot: true
runAsGroup: 65534
fsGroup: 65534
## Security context to be added to server container
##
containerSecurityContext: {}
service:
## If false, no Service will be created for the Prometheus server
##
enabled: true
annotations: {}
labels: {}
clusterIP: ""
## List of IP addresses at which the Prometheus server service is available
## Ref: https://kubernetes.io/docs/concepts/services-networking/service/#external-ips
##
externalIPs: []
loadBalancerIP: ""
loadBalancerSourceRanges: []
servicePort: 80
sessionAffinity: None
type: ClusterIP
## Enable gRPC port on service to allow auto discovery with thanos-querier
gRPC:
enabled: false
servicePort: 10901
# nodePort: 10901
## If using a statefulSet (statefulSet.enabled=true), configure the
## service to connect to a specific replica to have a consistent view
## of the data.
statefulsetReplica:
enabled: false
replica: 0
## Additional port to define in the Service
additionalPorts: []
# additionalPorts:
# - name: authenticated
# port: 8081
# targetPort: 8081
## Prometheus server pod termination grace period
##
terminationGracePeriodSeconds: 300
## Prometheus data retention period (default if not specified is 15 days)
##
retention: "15d"
## Prometheus' data retention size. Supported units: B, KB, MB, GB, TB, PB, EB.
##
retentionSize: ""
## Prometheus server ConfigMap entries for rule files (allow prometheus labels interpolation)
ruleFiles: {}
## Prometheus server ConfigMap entries for scrape_config_files
## (allows scrape configs defined in additional files)
##
scrapeConfigFiles: []
## Prometheus server ConfigMap entries
##
serverFiles:
## Alerts configuration
## Ref: https://prometheus.io/docs/prometheus/latest/configuration/alerting_rules/
alerting_rules.yml: {}
# groups:
# - name: Instances
# rules:
# - alert: InstanceDown
# expr: up == 0
# for: 5m
# labels:
# severity: page
# annotations:
# description: '{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 5 minutes.'
# summary: 'Instance {{ $labels.instance }} down'
## DEPRECATED DEFAULT VALUE, unless explicitly naming your files, please use alerting_rules.yml
alerts: {}
## Records configuration
## Ref: https://prometheus.io/docs/prometheus/latest/configuration/recording_rules/
recording_rules.yml: {}
## DEPRECATED DEFAULT VALUE, unless explicitly naming your files, please use recording_rules.yml
rules: {}
prometheus.yml:
rule_files:
- /etc/config/recording_rules.yml
- /etc/config/alerting_rules.yml
## Below two files are DEPRECATED will be removed from this default values file
- /etc/config/rules
- /etc/config/alerts
scrape_configs:
- job_name: 'api'
static_configs:
- targets: ['api.default.svc.cluster.local:5000']
- job_name: 'url-shortener'
static_configs:
- targets: ['url-shortener.default.svc.cluster.local:5001']
- job_name: 'qr-code-generator'
static_configs:
- targets: ['qr-code-generator.default.svc.cluster.local:5002']
- job_name: 'analytics'
static_configs:
- targets: ['analytics.default.svc.cluster.local:5003']
- job_name: prometheus
static_configs:
- targets:
- localhost:9090
# A scrape configuration for running Prometheus on a Kubernetes cluster.
# This uses separate scrape configs for cluster components (i.e. API server, node)
# and services to allow each to use different authentication configs.
#
# Kubernetes labels will be added as Prometheus labels on metrics via the
# `labelmap` relabeling action.
# Scrape config for API servers.
#
# Kubernetes exposes API servers as endpoints to the default/kubernetes
# service so this uses `endpoints` role and uses relabelling to only keep
# the endpoints associated with the default/kubernetes service using the
# default named port `https`. This works for single API server deployments as
# well as HA API server deployments.
- job_name: 'kubernetes-apiservers'
kubernetes_sd_configs:
- role: endpoints
# Default to scraping over https. If required, just disable this or change to
# `http`.
scheme: https
# This TLS & bearer token file config is used to connect to the actual scrape
# endpoints for cluster components. This is separate to discovery auth
# configuration because discovery & scraping are two separate concerns in
# Prometheus. The discovery auth config is automatic if Prometheus runs inside
# the cluster. Otherwise, more config options have to be provided within the
# <kubernetes_sd_config>.
tls_config:
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
# If your node certificates are self-signed or use a different CA to the
# master CA, then disable certificate verification below. Note that
# certificate verification is an integral part of a secure infrastructure
# so this should only be disabled in a controlled environment. You can
# disable certificate verification by uncommenting the line below.
#
insecure_skip_verify: true
bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
# Keep only the default/kubernetes service endpoints for the https port. This
# will add targets for each API server which Kubernetes adds an endpoint to
# the default/kubernetes service.
relabel_configs:
- source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]
action: keep
regex: default;kubernetes;https
- job_name: 'kubernetes-nodes'
# Default to scraping over https. If required, just disable this or change to
# `http`.
scheme: https
# This TLS & bearer token file config is used to connect to the actual scrape
# endpoints for cluster components. This is separate to discovery auth
# configuration because discovery & scraping are two separate concerns in
# Prometheus. The discovery auth config is automatic if Prometheus runs inside
# the cluster. Otherwise, more config options have to be provided within the
# <kubernetes_sd_config>.
tls_config:
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
# If your node certificates are self-signed or use a different CA to the
# master CA, then disable certificate verification below. Note that
# certificate verification is an integral part of a secure infrastructure
# so this should only be disabled in a controlled environment. You can
# disable certificate verification by uncommenting the line below.
#
insecure_skip_verify: true
bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
kubernetes_sd_configs:
- role: node
relabel_configs:
- action: labelmap
regex: __meta_kubernetes_node_label_(.+)
- target_label: __address__
replacement: kubernetes.default.svc:443
- source_labels: [__meta_kubernetes_node_name]
regex: (.+)
target_label: __metrics_path__
replacement: /api/v1/nodes/$1/proxy/metrics
- job_name: 'kubernetes-nodes-cadvisor'
# Default to scraping over https. If required, just disable this or change to
# `http`.
scheme: https
# This TLS & bearer token file config is used to connect to the actual scrape
# endpoints for cluster components. This is separate to discovery auth
# configuration because discovery & scraping are two separate concerns in
# Prometheus. The discovery auth config is automatic if Prometheus runs inside
# the cluster. Otherwise, more config options have to be provided within the
# <kubernetes_sd_config>.
tls_config:
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
# If your node certificates are self-signed or use a different CA to the
# master CA, then disable certificate verification below. Note that
# certificate verification is an integral part of a secure infrastructure
# so this should only be disabled in a controlled environment. You can
# disable certificate verification by uncommenting the line below.
#
insecure_skip_verify: true
bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
kubernetes_sd_configs:
- role: node
# This configuration will work only on kubelet 1.7.3+
# As the scrape endpoints for cAdvisor have changed
# if you are using older version you need to change the replacement to
# replacement: /api/v1/nodes/$1:4194/proxy/metrics
# more info here https://github.com/coreos/prometheus-operator/issues/633
relabel_configs:
- action: labelmap
regex: __meta_kubernetes_node_label_(.+)
- target_label: __address__
replacement: kubernetes.default.svc:443
- source_labels: [__meta_kubernetes_node_name]
regex: (.+)
target_label: __metrics_path__
replacement: /api/v1/nodes/$1/proxy/metrics/cadvisor
# Metric relabel configs to apply to samples before ingestion.
# [Metric Relabeling](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs)
# metric_relabel_configs:
# - action: labeldrop
# regex: (kubernetes_io_hostname|failure_domain_beta_kubernetes_io_region|beta_kubernetes_io_os|beta_kubernetes_io_arch|beta_kubernetes_io_instance_type|failure_domain_beta_kubernetes_io_zone)
# Scrape config for service endpoints.
#
# The relabeling allows the actual service scrape endpoint to be configured
# via the following annotations:
#
# * `prometheus.io/scrape`: Only scrape services that have a value of
# `true`, except if `prometheus.io/scrape-slow` is set to `true` as well.
# * `prometheus.io/scheme`: If the metrics endpoint is secured then you will need
# to set this to `https` & most likely set the `tls_config` of the scrape config.
# * `prometheus.io/path`: If the metrics path is not `/metrics` override this.
# * `prometheus.io/port`: If the metrics are exposed on a different port to the
# service then set this appropriately.
# * `prometheus.io/param_<parameter>`: If the metrics endpoint uses parameters
# then you can set any parameter
- job_name: 'kubernetes-service-endpoints'
honor_labels: true
kubernetes_sd_configs:
- role: endpoints
relabel_configs:
- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape]
action: keep
regex: true
- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape_slow]
action: drop
regex: true
- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scheme]
action: replace
target_label: __scheme__
regex: (https?)
- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path]
action: replace
target_label: __metrics_path__
regex: (.+)
- source_labels: [__address__, __meta_kubernetes_service_annotation_prometheus_io_port]
action: replace
target_label: __address__
regex: (.+?)(?::\d+)?;(\d+)
replacement: $1:$2
- action: labelmap
regex: __meta_kubernetes_service_annotation_prometheus_io_param_(.+)
replacement: __param_$1
- action: labelmap
regex: __meta_kubernetes_service_label_(.+)
- source_labels: [__meta_kubernetes_namespace]
action: replace
target_label: namespace
- source_labels: [__meta_kubernetes_service_name]
action: replace