在K8S中使用helm chart部署Prometheus

近期部署Prometheus的时候,发现网上竟然很难找到比较好的基于k8s部署的教程,甚至就连helm chart官方repo的教程也很不友好,对于很多参数没有详细的解释,也缺少示例。

推荐两个我觉得还不错的资料地址。

  1. https://prometheus.wang/
    这个资料号称自己是prometheus中文文档。
    内容不是非常多,但是很全面的介绍了prometheus及其周边的使用教程,从部署安装到实际使用示例都有,一天应该就能 按照里面的内容全部走一遍,个人觉得是一个很不错的入门教程,他不能让你精通prometheus,但是足够入门,并且是中文的,对我们很友好

  2. https://prometheus.io/docs/introduction/overview/
    这是官网教程地址,建议先把上面的中文教程全部过一遍,然后再官网教程中按需阅读,不要一上来就想着通读文档,既浪费时间,难度也很大(英文的,而且在没有实战经验的情况下读文档很多地方是不能真正理解的)

  3. https://github.com/prometheus-community/helm-charts
    这个是prometheus helm chart的官方repo, 虽然内容很少,但还是推荐一下,毕竟是官方对的,希望以后他们能在文档上多花点时间吧

部署步骤:
首先你要有一个k8s集群,并且已经可以正常使用helm,其他步骤如下

1
2
3
4
5
6
7
8
# 添加helm chart库
helm repo add prometheus-community https://prometheus-community.github.io/helm-charts

# 导出可配置部分的配置文件,这个文件需要修改成符合自己需要的参数
helm show values prometheus-community/prometheus >> values.yaml

# 修改values.yaml中的默认配置文件后就可以部署了
helm install prometheus --namespace prometheus -f values.yaml prometheus-community/prometheus

前面之所以说官方repo的文档差,就是因为他们对于可配置的values.yaml没有很详细的说明和示例配置(也就是开箱即用)

我把自己使用的配置放在了下面,仅供参考

以下几点是需要注意的:

  1. storageclass
    建议直接提供storageclass,然后让helm自己创建PVC,而不是自己创建PVC,这样方便一些,而且在创建storageclass的时候注意加上allowVolumeExpansion: true这个参数,不然PVC不能修改容量,等到以后PVC期初创建的容量的用完之后就麻烦了,因为不能扩容
    在AWS里面其实可以使用EFS作为storageclass的后端存储,因为EFS是无限容量的,这样就不用考虑扩容问题

  2. configmaps(配置文件)
    使用helm chart部署prometheus的时候,prometheus server和alertmanager的配置文件是通过configmap挂载到pod上的,所以在values.yaml中的server和alertmanager部分有一个参数是“configMapOverrideName”,可以让你配置自己configmap,如果不配置这个参数的话那么他就会自己生成一个。

我建议将这个参数置空,让helm chart自己生成,然后利用kubectl将生成的configmap导出自己修改配置后再apply即可,这样对于新手比较容易

1
2
3
4
# 导出configmap并修改
kubectl get configmaps -n prometheus <configmap-name> -o yaml > configmap.yaml
# 应用修改的configmap
kubectl apply -f configmap.yaml

下面就是我实际使用的values.yaml参数

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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
rbac:
create: true

podSecurityPolicy:
enabled: false

imagePullSecrets:
# - name: "image-pull-secret"

## Define serviceAccount names for components. Defaults to component's fully qualified name.
##
serviceAccounts:
alertmanager:
create: true
name:
annotations: {}
nodeExporter:
create: true
name:
annotations: {}
pushgateway:
create: true
name:
annotations: {}
server:
create: true
name:
annotations: {}

alertmanager:
## If false, alertmanager will not be installed
##
enabled: true

## Use a ClusterRole (and ClusterRoleBinding)
## - If set to false - we define a Role and RoleBinding in the defined namespaces ONLY
## This makes alertmanager work - for users who do not have ClusterAdmin privs, but wants alertmanager to operate on their own namespaces, instead of clusterwide.
useClusterRole: true

## Set to a rolename to use existing role - skipping role creating - but still doing serviceaccount and rolebinding to the rolename set here.
useExistingRole: false

## alertmanager container name
##
name: alertmanager

## alertmanager container image
##
image:
repository: quay.io/prometheus/alertmanager
tag: v0.21.0
pullPolicy: IfNotPresent

## alertmanager priorityClassName
##
priorityClassName: ""

## Additional alertmanager container arguments
##
extraArgs: {}

## Additional InitContainers to initialize the pod
##
extraInitContainers: []

## 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 alertmanager
baseURL: "http://localhost:9093"

## Additional alertmanager container environment variable
## For instance to add a http_proxy
##
extraEnv: {}

## Additional alertmanager Secret mounts
# Defines additional mounts with secrets. Secrets must be manually created in the namespace.
extraSecretMounts: []
# - name: secret-files
# mountPath: /etc/secrets
# subPath: ""
# secretName: alertmanager-secret-files
# readOnly: true

## ConfigMap override where fullname is {{.Release.Name}}-{{.Values.alertmanager.configMapOverrideName}}
## Defining configMapOverrideName will cause templates/alertmanager-configmap.yaml
## to NOT generate a ConfigMap resource
##
configMapOverrideName: ""

## The name of a secret in the same kubernetes namespace which contains the Alertmanager config
## Defining configFromSecret will cause templates/alertmanager-configmap.yaml
## to NOT generate a ConfigMap resource
##
configFromSecret: ""

## The configuration file name to be loaded to alertmanager
## Must match the key within configuration loaded from ConfigMap/Secret
##
configFileName: alertmanager.yml

ingress:
## If true, alertmanager Ingress will be created
##
enabled: true

## alertmanager Ingress annotations
##
annotations:
kubernetes.io/ingress.class: nginx
nginx.ingress.kubernetes.io/affinity-mode: "persistent"
nginx.ingress.kubernetes.io/session-cookie-name: "route"
# kubernetes.io/tls-acme: 'true'

## alertmanager Ingress additional labels
##
extraLabels: {}

## alertmanager Ingress hostnames with optional path
## Must be provided if Ingress is enabled
##
hosts:
- alertmanager-stg.example.com
# - domain.com/alertmanager

## 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

## alertmanager Ingress TLS configuration
## Secrets must be manually created in the namespace
##
tls: []
# - secretName: prometheus-alerts-tls
# hosts:
# - alertmanager.domain.com

## Alertmanager Deployment Strategy type
# strategy:
# type: Recreate

## Node tolerations for alertmanager 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)"

## Node labels for alertmanager pod assignment
## Ref: https://kubernetes.io/docs/user-guide/node-selection/
##
nodeSelector: {}

## Pod affinity
##
affinity: {}

## PodDisruptionBudget settings
## ref: https://kubernetes.io/docs/concepts/workloads/pods/disruptions/
##
podDisruptionBudget:
enabled: false
maxUnavailable: 1

## Use an alternate scheduler, e.g. "stork".
## ref: https://kubernetes.io/docs/tasks/administer-cluster/configure-multiple-schedulers/
##
# schedulerName:

persistentVolume:
## If true, alertmanager will create/use a Persistent Volume Claim
## If false, use emptyDir
##
enabled: true

## alertmanager data Persistent Volume access modes
## Must match those of existing PV or dynamic provisioner
## Ref: http://kubernetes.io/docs/user-guide/persistent-volumes/
##
accessModes:
# - ReadWriteOnce
- ReadWriteOnce

## alertmanager data Persistent Volume Claim annotations
##
annotations: {}

## alertmanager data Persistent Volume existing claim name
## Requires alertmanager.persistentVolume.enabled: true
## If defined, PVC must be created manually before volume will be bound
existingClaim: ""

## alertmanager data Persistent Volume mount root path
##
mountPath: /data

## alertmanager data Persistent Volume size
##
size: 50Gi

## alertmanager data Persistent Volume Storage Class
## If defined, storageClassName: <storageClass>
## If set to "-", storageClassName: "", which disables dynamic provisioning
## If undefined (the default) or set to null, no storageClassName spec is
## set, choosing the default provisioner. (gp2 on AWS, standard on
## GKE, AWS & OpenStack)
##
storageClass: "prometheus-storageclass"

## alertmanager 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 alertmanager data Persistent Volume to mount
## Useful if the volume's root directory is not empty
##
subPath: ""

emptyDir:
## alertmanager emptyDir volume size limit
##
sizeLimit: ""

## Annotations to be added to alertmanager pods
##
podAnnotations: {}
## Tell prometheus to use a specific set of alertmanager pods
## instead of all alertmanager pods found in the same namespace
## Useful if you deploy multiple releases within the same namespace
##
## prometheus.io/probe: alertmanager-teamA

## Labels to be added to Prometheus AlertManager pods
##
podLabels: {}

## 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: 2

## 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: true

annotations: {}
labels: {}
podManagementPolicy: OrderedReady

## Alertmanager headless service to use for the statefulset
##
headless:
annotations: {}
labels: {}

## Enabling peer mesh service end points for enabling the HA alert manager
## Ref: https://github.com/prometheus/alertmanager/blob/master/README.md
enableMeshPeer: false

servicePort: 80

## alertmanager resource requests and limits
## Ref: http://kubernetes.io/docs/user-guide/compute-resources/
##
resources:
limits:
cpu: 200m
memory: 1024Mi
requests:
cpu: 20m
memory: 100Mi

# Custom DNS configuration to be added to alertmanager 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 alertmanager pods
##
securityContext:
runAsUser: 65534
runAsNonRoot: true
runAsGroup: 65534
fsGroup: 65534

service:
annotations: {}
labels: {}
clusterIP: ""

## Enabling peer mesh service end points for enabling the HA alert manager
## Ref: https://github.com/prometheus/alertmanager/blob/master/README.md
# enableMeshPeer : true

## List of IP addresses at which the alertmanager service is available
## Ref: https://kubernetes.io/docs/user-guide/services/#external-ips
##
externalIPs: []

loadBalancerIP: ""
loadBalancerSourceRanges: []
servicePort: 80
# nodePort: 30000
sessionAffinity: None
type: ClusterIP

## Monitors ConfigMap changes and POSTs to a URL
## Ref: https://github.com/jimmidyson/configmap-reload
##
configmapReload:
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: jimmidyson/configmap-reload
tag: v0.5.0
pullPolicy: IfNotPresent

## Additional configmap-reload container arguments
##
extraArgs: {}
## Additional configmap-reload volume directories
##
extraVolumeDirs: []


## Additional configmap-reload mounts
##
extraConfigmapMounts: []
# - name: prometheus-alerts
# mountPath: /etc/alerts.d
# subPath: ""
# configMap: prometheus-alerts
# readOnly: true


## configmap-reload resource requests and limits
## Ref: http://kubernetes.io/docs/user-guide/compute-resources/
##
resources: {}
alertmanager:
## 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: jimmidyson/configmap-reload
tag: v0.5.0
pullPolicy: IfNotPresent

## Additional configmap-reload container arguments
##
extraArgs: {}
## Additional configmap-reload volume directories
##
extraVolumeDirs: []


## Additional configmap-reload mounts
##
extraConfigmapMounts: []
# - name: prometheus-alerts
# mountPath: /etc/alerts.d
# subPath: ""
# configMap: prometheus-alerts
# readOnly: true


## configmap-reload resource requests and limits
## Ref: http://kubernetes.io/docs/user-guide/compute-resources/
##
resources: {}

kubeStateMetrics:
## If false, kube-state-metrics sub-chart will not be installed
##
enabled: true

## kube-state-metrics sub-chart configurable values
## Please see https://github.com/kubernetes/kube-state-metrics/tree/master/charts/kube-state-metrics
##
# kube-state-metrics:

nodeExporter:
## If false, node-exporter will not be installed
##
enabled: true

## If true, node-exporter pods share the host network namespace
##
hostNetwork: true

## If true, node-exporter pods share the host PID namespace
##
hostPID: true

## If true, node-exporter pods mounts host / at /host/root
##
hostRootfs: true

## node-exporter container name
##
name: node-exporter

## node-exporter container image
##
image:
repository: quay.io/prometheus/node-exporter
tag: v1.1.2
pullPolicy: IfNotPresent

## 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'

## node-exporter priorityClassName
##
priorityClassName: ""

## Custom Update Strategy
##
updateStrategy:
type: RollingUpdate

## Additional node-exporter container arguments
##
extraArgs: {}

## Additional InitContainers to initialize the pod
##
extraInitContainers: []

## Additional node-exporter hostPath mounts
##
extraHostPathMounts: []
# - name: textfile-dir
# mountPath: /srv/txt_collector
# hostPath: /var/lib/node-exporter
# readOnly: true
# mountPropagation: HostToContainer

extraConfigmapMounts: []
# - name: certs-configmap
# mountPath: /prometheus
# configMap: certs-configmap
# readOnly: true

## Node tolerations for node-exporter 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)"

## Node labels for node-exporter pod assignment
## Ref: https://kubernetes.io/docs/user-guide/node-selection/
##
nodeSelector: {}

## Annotations to be added to node-exporter pods
##
podAnnotations: {}

## Labels to be added to node-exporter pods
##
pod:
labels: {}

## PodDisruptionBudget settings
## ref: https://kubernetes.io/docs/concepts/workloads/pods/disruptions/
##
podDisruptionBudget:
enabled: false
maxUnavailable: 1

## node-exporter resource limits & requests
## Ref: https://kubernetes.io/docs/user-guide/compute-resources/
##
resources: {}
# limits:
# cpu: 200m
# memory: 50Mi
# requests:
# cpu: 100m
# memory: 30Mi

# Custom DNS configuration to be added to node-exporter 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 node-exporter pods
##
securityContext:
fsGroup: 65534
runAsGroup: 65534
runAsNonRoot: true
runAsUser: 65534

service:
annotations:
prometheus.io/scrape: "true"
labels: {}

# Exposed as a headless service:
# https://kubernetes.io/docs/concepts/services-networking/service/#headless-services
clusterIP: None

## List of IP addresses at which the node-exporter service is available
## Ref: https://kubernetes.io/docs/user-guide/services/#external-ips
##
externalIPs: []

hostPort: 9100
loadBalancerIP: ""
loadBalancerSourceRanges: []
servicePort: 9100
type: ClusterIP

server:
## Prometheus server container name
##
enabled: true

## 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

## namespaces to monitor (instead of monitoring all - clusterwide). Needed if you want to run without Cluster-admin privileges.
# namespaces:
# - yournamespace

name: server

# sidecarContainers - add more containers to prometheus server
# Key/Value where Key is the sidecar `- name: <Key>`
# Example:
# sidecarContainers:
# webserver:
# image: nginx
sidecarContainers: {}

## Prometheus server container image
##
image:
repository: quay.io/prometheus/prometheus
tag: v2.26.0
pullPolicy: IfNotPresent

## 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: []

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: 1m
## 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: []

## Additional Prometheus server container arguments
##
extraArgs: {}

## 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: ""

ingress:
## If true, Prometheus server Ingress will be created
##
enabled: true

## Prometheus server Ingress annotations
##
annotations:
kubernetes.io/ingress.class: nginx
nginx.ingress.kubernetes.io/affinity: "cookie"
nginx.ingress.kubernetes.io/affinity-mode: "persistent"
nginx.ingress.kubernetes.io/session-cookie-name: "route"
# kubernetes.io/tls-acme: 'true'

## Prometheus server Ingress additional labels
##
extraLabels: {}

## Prometheus server Ingress hostnames with optional path
## Must be provided if Ingress is enabled
##
hosts:
- prometheus-stg.example.com
# - domain.com/prometheus

## 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/configuration/assign-pod-node/
##
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/user-guide/node-selection/
##
nodeSelector: {}

## Pod affinity
##
affinity: {}

## PodDisruptionBudget settings
## ref: https://kubernetes.io/docs/concepts/workloads/pods/disruptions/
##
podDisruptionBudget:
enabled: false
maxUnavailable: 1

## 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

## 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 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: 200Gi

## 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-storageclass-gp2"

## 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: ""

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: 2

## 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: true

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

## Prometheus server readiness and liveness probe initial delay and timeout
## Ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-startup-probes/
##
readinessProbeInitialDelay: 30
readinessProbePeriodSeconds: 5
readinessProbeTimeout: 4
readinessProbeFailureThreshold: 3
readinessProbeSuccessThreshold: 1
livenessProbeInitialDelay: 30
livenessProbePeriodSeconds: 15
livenessProbeTimeout: 10
livenessProbeFailureThreshold: 3
livenessProbeSuccessThreshold: 1

## 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, you probably want to set this to ClusterFirstWithHostNet
dnsPolicy: ClusterFirst

## 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

service:
annotations: {}
labels: {}
clusterIP: ""

## List of IP addresses at which the Prometheus server service is available
## Ref: https://kubernetes.io/docs/user-guide/services/#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

## Prometheus server pod termination grace period
##
terminationGracePeriodSeconds: 300

## Prometheus data retention period (default if not specified is 15 days)
##
retention: "180d"

pushgateway:
## If false, pushgateway will not be installed
##
enabled: true

## Use an alternate scheduler, e.g. "stork".
## ref: https://kubernetes.io/docs/tasks/administer-cluster/configure-multiple-schedulers/
##
# schedulerName:

## pushgateway container name
##
name: pushgateway

## pushgateway container image
##
image:
repository: prom/pushgateway
tag: v1.3.1
pullPolicy: IfNotPresent

## pushgateway priorityClassName
##
priorityClassName: ""

## Additional pushgateway container arguments
##
## for example: persistence.file: /data/pushgateway.data
extraArgs: {}

## Additional InitContainers to initialize the pod
##
extraInitContainers: []

ingress:
## If true, pushgateway Ingress will be created
##
enabled: true

## pushgateway Ingress annotations
##
annotations:
kubernetes.io/ingress.class: nginx
nginx.ingress.kubernetes.io/affinity: "cookie"
nginx.ingress.kubernetes.io/affinity-mode: "persistent"
nginx.ingress.kubernetes.io/session-cookie-name: "route"
# kubernetes.io/tls-acme: 'true'

## pushgateway Ingress hostnames with optional path
## Must be provided if Ingress is enabled
##
hosts:
- pushgateway-stg.example.com
# - domain.com/pushgateway

## 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

## pushgateway Ingress TLS configuration
## Secrets must be manually created in the namespace
##
tls: []
# - secretName: prometheus-alerts-tls
# hosts:
# - pushgateway.domain.com

## Node tolerations for pushgateway 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)"

## Node labels for pushgateway pod assignment
## Ref: https://kubernetes.io/docs/user-guide/node-selection/
##
nodeSelector: {}

## Annotations to be added to pushgateway pods
##
podAnnotations: {}

## Labels to be added to pushgateway pods
##
podLabels: {}

## 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'

replicaCount: 1

## Annotations to be added to deployment
##
deploymentAnnotations: {}

## PodDisruptionBudget settings
## ref: https://kubernetes.io/docs/concepts/workloads/pods/disruptions/
##
podDisruptionBudget:
enabled: false
maxUnavailable: 1

## pushgateway resource requests and limits
## Ref: http://kubernetes.io/docs/user-guide/compute-resources/
##
resources: {}
# limits:
# cpu: 10m
# memory: 32Mi
# requests:
# cpu: 10m
# memory: 32Mi

# Custom DNS configuration to be added to push-gateway 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 push-gateway pods
##
securityContext:
runAsUser: 65534
runAsNonRoot: true

service:
annotations:
prometheus.io/probe: pushgateway
labels: {}
clusterIP: ""

## List of IP addresses at which the pushgateway service is available
## Ref: https://kubernetes.io/docs/user-guide/services/#external-ips
##
externalIPs: []

loadBalancerIP: ""
loadBalancerSourceRanges: []
servicePort: 9091
type: ClusterIP

## pushgateway Deployment Strategy type
# strategy:
# type: Recreate

persistentVolume:
## If true, pushgateway will create/use a Persistent Volume Claim
##
enabled: false

## pushgateway 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

## pushgateway data Persistent Volume Claim annotations
##
annotations: {}

## pushgateway data Persistent Volume existing claim name
## Requires pushgateway.persistentVolume.enabled: true
## If defined, PVC must be created manually before volume will be bound
existingClaim: ""

## pushgateway data Persistent Volume mount root path
##
mountPath: /data

## pushgateway data Persistent Volume size
##
size: 50Gi

## pushgateway 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-storageclass-gp2"

## pushgateway 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 pushgateway data Persistent Volume to mount
## Useful if the volume's root directory is not empty
##
subPath: ""


## alertmanager ConfigMap entries
##
alertmanagerFiles:
alertmanager.yml:
global: {}
# slack_api_url: ''

receivers:
- name: default-receiver
# slack_configs:
# - channel: '@you'
# send_resolved: true

route:
group_wait: 10s
group_interval: 5m
receiver: default-receiver
repeat_interval: 3h

## 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: 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

# 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`
# * `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.
- job_name: 'kubernetes-service-endpoints'

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_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_label_(.+)
- source_labels: [__meta_kubernetes_namespace]
action: replace
target_label: kubernetes_namespace
- source_labels: [__meta_kubernetes_service_name]
action: replace
target_label: kubernetes_name
- source_labels: [__meta_kubernetes_pod_node_name]
action: replace
target_label: kubernetes_node

# Scrape config for slow service endpoints; same as above, but with a larger
# timeout and a larger interval
#
# The relabeling allows the actual service scrape endpoint to be configured
# via the following annotations:
#
# * `prometheus.io/scrape-slow`: Only scrape services that have a value of `true`
# * `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.
- job_name: 'kubernetes-service-endpoints-slow'

scrape_interval: 5m
scrape_timeout: 30s

kubernetes_sd_configs:
- role: endpoints

relabel_configs:
- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape_slow]
action: keep
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_label_(.+)
- source_labels: [__meta_kubernetes_namespace]
action: replace
target_label: kubernetes_namespace
- source_labels: [__meta_kubernetes_service_name]
action: replace
target_label: kubernetes_name
- source_labels: [__meta_kubernetes_pod_node_name]
action: replace
target_label: kubernetes_node

- job_name: 'prometheus-pushgateway'
honor_labels: true

kubernetes_sd_configs:
- role: service

relabel_configs:
- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_probe]
action: keep
regex: pushgateway

# Example scrape config for probing services via the Blackbox Exporter.
#
# The relabeling allows the actual service scrape endpoint to be configured
# via the following annotations:
#
# * `prometheus.io/probe`: Only probe services that have a value of `true`
- job_name: 'kubernetes-services'

metrics_path: /probe
params:
module: [http_2xx]

kubernetes_sd_configs:
- role: service

relabel_configs:
- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_probe]
action: keep
regex: true
- source_labels: [__address__]
target_label: __param_target
- target_label: __address__
replacement: blackbox
- source_labels: [__param_target]
target_label: instance
- action: labelmap
regex: __meta_kubernetes_service_label_(.+)
- source_labels: [__meta_kubernetes_namespace]
target_label: kubernetes_namespace
- source_labels: [__meta_kubernetes_service_name]
target_label: kubernetes_name

# Example scrape config for pods
#
# The relabeling allows the actual pod scrape endpoint to be configured via the
# following annotations:
#
# * `prometheus.io/scrape`: Only scrape pods that have a value of `true`
# * `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`: Scrape the pod on the indicated port instead of the default of `9102`.
- job_name: 'kubernetes-pods'

kubernetes_sd_configs:
- role: pod

relabel_configs:
- source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape]
action: keep
regex: true
- source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scheme]
action: replace
regex: (https?)
target_label: __scheme__
- source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_path]
action: replace
target_label: __metrics_path__
regex: (.+)
- source_labels: [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port]
action: replace
regex: ([^:]+)(?::\d+)?;(\d+)
replacement: $1:$2
target_label: __address__
- action: labelmap
regex: __meta_kubernetes_pod_label_(.+)
- source_labels: [__meta_kubernetes_namespace]
action: replace
target_label: kubernetes_namespace
- source_labels: [__meta_kubernetes_pod_name]
action: replace
target_label: kubernetes_pod_name
- source_labels: [__meta_kubernetes_pod_phase]
regex: Pending|Succeeded|Failed
action: drop

# Example Scrape config for pods which should be scraped slower. An useful example
# would be stackriver-exporter which queries an API on every scrape of the pod
#
# The relabeling allows the actual pod scrape endpoint to be configured via the
# following annotations:
#
# * `prometheus.io/scrape-slow`: Only scrape pods that have a value of `true`
# * `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`: Scrape the pod on the indicated port instead of the default of `9102`.
- job_name: 'kubernetes-pods-slow'

scrape_interval: 5m
scrape_timeout: 30s

kubernetes_sd_configs:
- role: pod

relabel_configs:
- source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape_slow]
action: keep
regex: true
- source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scheme]
action: replace
regex: (https?)
target_label: __scheme__
- source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_path]
action: replace
target_label: __metrics_path__
regex: (.+)
- source_labels: [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port]
action: replace
regex: ([^:]+)(?::\d+)?;(\d+)
replacement: $1:$2
target_label: __address__
- action: labelmap
regex: __meta_kubernetes_pod_label_(.+)
- source_labels: [__meta_kubernetes_namespace]
action: replace
target_label: kubernetes_namespace
- source_labels: [__meta_kubernetes_pod_name]
action: replace
target_label: kubernetes_pod_name
- source_labels: [__meta_kubernetes_pod_phase]
regex: Pending|Succeeded|Failed
action: drop

# adds additional scrape configs to prometheus.yml
# must be a string so you have to add a | after extraScrapeConfigs:
# example adds prometheus-blackbox-exporter scrape config
extraScrapeConfigs:
# - job_name: 'prometheus-blackbox-exporter'
# metrics_path: /probe
# params:
# module: [http_2xx]
# static_configs:
# - targets:
# - https://example.com
# relabel_configs:
# - source_labels: [__address__]
# target_label: __param_target
# - source_labels: [__param_target]
# target_label: instance
# - target_label: __address__
# replacement: prometheus-blackbox-exporter:9115

# Adds option to add alert_relabel_configs to avoid duplicate alerts in alertmanager
# useful in H/A prometheus with different external labels but the same alerts
alertRelabelConfigs:
# alert_relabel_configs:
# - source_labels: [dc]
# regex: (.+)\d+
# target_label: dc

networkPolicy:
## Enable creation of NetworkPolicy resources.
##
enabled: false

# Force namespace of namespaced resources
forceNamespace: null