/
values.yaml
473 lines (387 loc) · 16.2 KB
/
values.yaml
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
global:
# The OpenStack region.
region:
# The TLD as used in the URL.
domain:
# Type of the cluster to which the Prometheus is deployed.
# Choose between: controlplane, kubernikus-controlplane, kubernikus-scaleout.
clusterType: controlplane
# Optional name of the cluster to which the Prometheus is deployed.
# Defaults to region if not set.
# cluster:
# Optional tier for Prometheus alerts.
# tier: k8s
# Optional targets to create Prometheus names.
# targets:
linkerd_requested: false
# The image for the Prometheus server. The tag equals the .Chart.appVersion.
image:
repository: keppel.eu-de-1.cloud.sap/ccloud-dockerhub-mirror/prom/prometheus
# Mandatory name for a single Prometheus. To setup multiple, define a list of .Values.names or .Values.global.targets.
# The name is used to find relevant aggregation and alerting rules.
# Examples: kubernetes, openstack, infrastructure, maia, vmware etc.
name:
# A list to deploy multiple Prometheis with the same configuration but different names.
# names:
# Defines how long data is stored. Format: `[0-9]+(ms|s|m|h|d|w|y)`
retentionTime: 7d
# Reference a secret containing additional Prometheus scrape configurations.
# Injecting an invalid configuration might break the Prometheus server instance.
additionalScrapeConfigs: {}
# Name of the secret.
# name:
# Key in the secret.
# key:
# Specify whether the Secret is optional.
# Setting `optional: false` causes an error when the secret does not exist.
# optional: true
# Interval between consecutive scrapes.
scrapeInterval: "60s"
# List of configmaps in the same namespace as the Prometheus that should be mounted to /etc/prometheus/configmaps/<configmap-name>.
# Can be used to add targets found by a custom service discovery.
configMaps: []
# - < name of configmap >
# List of secrets in the same namespace as the Prometheus that should be mounted to /etc/prometheus/secrets/<secret-name>.
secrets: []
# - < name of secret >
# Alertmanager configuration.
alertmanagers:
# Configuration if the Alertmanager has client certificate authentication enabled.
authentication:
enabled: false
# The certificate used for authentication with the Alertmanager..
ssoCert:
# The key used for authentication with the Alertmanager.
ssoKey:
# List of Alertmanagers (AM) to send alerts to.
# If multiple AMs are used in an HA setup, alerts must be send to every AM.
hosts: []
# - alertmanager1.tld
# - alertmanager2.tld
# Configuration for the Service created for this Prometheus.
service:
annotations: {}
# Will explicitly set ingressClassName to nginx. If the cluster has traefik deployed only, this needs to be set to true
traefik:
enabled: false
# Optional ingress for this Prometheus.
ingress:
enabled: false
# List of hostnames for this Prometheus server. If empty, the FQDN will be generated using the pattern prometheus-<name>.<region>.<domain> otherwise <host>.<region>.<domain>.
# The first host is used to generate the external URL for the Prometheus. Remaining hosts will be used as SANs.
# If the ingress is enabled, it's also used for the ingress host.
hosts: []
# List of fully qualified host names to be used for this Prometheus server. Mutually exclusive with hosts.
# The first host is used to generate the external URL for the Prometheus. Remaining hosts will be used as SANs.
# If the ingress is enabled, it's also used for the ingress host.
hostsFQDN: []
# Client certificate authentication on ingress level.
authentication:
oauth:
enabled: false
# The URL to the authentication service.
authURL:
# Optional URL to specify the location of the error page.
authSignInURL:
sso:
enabled: true
# The key (<namespace>/<name>) of the secret containing the CA certificate (`ca.crt`) that is enabled to authenticate against this Ingress.
authTLSSecret: kube-system/ingress-cacrt
# The validation depth between the provided client certificate and the certification authority chain.
authTLSVerifyDepth: 3
# Enables verification of client certificates.
authTLSVerifyClient: on
# Additional annotations for the ingress.
annotations:
cloud.sap/no-http-keep-alive-monitor: "true"
# Optional additional ingress for this Prometheus.
internalIngress:
enabled: false
# List of hostnames for this Prometheus server. If empty, the FQDN will be generated using the pattern prometheus-<name>-internal.<region>.<domain> otherwise <host>.<region>.<domain>.
# The first host is used to generate the external URL for the Prometheus. Remaining hosts will be used as SANs.
# If the ingress is enabled, it's also used for the ingress host.
hosts: []
# List of fully qualified host names to be used for this Prometheus server. Mutually exclusive with hosts.
# The first host is used to generate the external URL for the Prometheus. Remaining hosts will be used as SANs.
# If the ingress is enabled, it's also used for the ingress host.
hostsFQDN: []
# Client certificate authentication on ingress level.
authentication:
oauth:
enabled: false
# The URL to the authentication service.
authURL:
# Optional URL to specify the location of the error page.
authSignInURL:
sso:
enabled: true
# The key (<namespace>/<name>) of the secret containing the CA certificate (`ca.crt`) that is enabled to authenticate against this Ingress.
authTLSSecret: kube-system/ingress-cacrt
# The validation depth between the provided client certificate and the certification authority chain.
authTLSVerifyDepth: 3
# Enables verification of client certificates.
authTLSVerifyClient: on
# Additional annotations for the ingress.
annotations:
cloud.sap/no-http-keep-alive-monitor: "true"
# Enable persistent storage.
# If disabled, data will be stored in memory.
persistence:
enabled: false
# Optional name of the PVC. Default: < .Values.name >
# name:
# Access mode of the PVC.
accessMode: ReadWriteOnce
# Size of the PVC.
size: 100Gi
# Label selector to be be applied to the PVC.
selector: {}
# Create RBAC resources.
rbac:
create: true
# ServiceAccount to use for the Prometheus server.
# Note that a ServiceAccount with name `default` cannot be created.
# Instead the generated name will be used.
serviceAccount:
create: true
# Optional name of the service account.
# If not provided one will be generated in the format: prometheus-<name>.
name: ""
# Thanos configuration.
thanos:
# Enables Prometheus sidecar. This is now the default setting for global monitoring integration.
# Only disable this, if you don't want to have your Prometheus being queried by global Thanos.
# Important: needed thanos swift seed configuration is provided by system/thanos-seeds and specified with thanosSeeds below
enabled: true
objectStorageConfig:
# set false to only add thanos-sidecar gRPC store API. Usually you now do want sidecarDiscovery to be set, see below.
enabled: true
# Note:
# The name of the secret specified below will be prefixed with `prometheus-<name>`
# to avoid multiple configurations with the same name.
name: thanos-storage-config
key: thanos.yaml
optional: true
# When there is no store activated (objectStorageConfig.enabled = false) you can have this sidecar detected by the operator
# using a StoreEndpoint. You need to specify which thanos should pick up the sidecar. This Thanos needs to run QueryDiscovery.
# domain defaults to cluster.local and only needs to be set if it differs
# thanosNamespace needs to be set, if the thanos specified with thanosName resides in a Sidecar disjunct namespace.
sidecarDiscovery:
- thanosName:
# thanosNamespace:
namespace:
# domain:
# Specification for Thanos sidecar to Prometheus server.
# See https://github.com/coreos/prometheus-operator/blob/master/Documentation/api.md#thanosspec .
spec:
baseImage: keppel.eu-de-1.cloud.sap/ccloud-quay-mirror/thanos/thanos
version: v0.31.0
# Being one of debug, info, warn, error. Defaults to warn.
# logLevel: info
thanosSeeds:
seed:
# If disabled the user and container need to exist, or you are in another cluster but metal. In this case leverage the dedicated system/thanos-seeds chart instead of this default, prometheus-bundled seed.
enabled: true
# List of required OpenstackSeeds that need to be resolved before.
# Warning: This list is rather specific to SAP Converged Cloud.
requires:
- swift/swift-seed
- monsoon3/domain-ccadmin-seed
- monsoon3/domain-default-seed
# optional cluster type appended to container name to prevent same names for different prometheus
clusterType:
# Configuration for OpenStack Swift Thanos storage backend.
# Deploy an OpenstackSeed custom resource triggering creation of an Openstack user and Swift container used to persist Prometheus metrics.
# See: https://github.com/sapcc/kubernetes-operators/tree/master/openstack-seeder
swiftStorageConfig:
authURL:
userDomainName:
password:
domainName:
projectName:
projectDomainName:
# all settings below are not mandatory and auto-generated
userName:
containerName:
# Currently not supported are:
# tenantID:
# domainID:
# userID:
# needs to be enabled for vmware-monitoring only
vmware: false
# The labels to add to any time series or alerts when communicating with
# external systems (federation, remote storage, Alertmanager).
externalLabels: {}
# labelName: labelValue
# The log level of the Prometheus. Defaults to warn.
# logLevel: info
# Kubernetes resource requests and limits for this Prometheus.
# See: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container .
resources:
requests:
cpu: "1"
memory: 8Gi
ephemeral-storage: 200M
# specifying container specific maximal values.
vpaResources:
# if prometheus needs more than 10Gi memory, this needs to be increased otherwise the VPA will not set it accordingly
prometheus:
containerName: "prometheus"
maxAllowed:
cpu: "3"
memory: "10Gi"
configReloader:
containerName: "config-reloader"
maxAllowed:
cpu: "100"
memory: "200Mi"
thanosSidecar:
containerName: "thanos-sidecar"
maxAllowed:
cpu: "1"
memory: "3Gi"
# If set to Auto, make sure to enable alerts.thanos.enabled and alerts.thanos.name if you are in any Prometheus but kubernetes and kubernikus. This will deploy needed alerts to Thanos Ruler.
vpaUpdateMode: "Off"
# A security context defines privilege and access control settings for a Pod or Container.
# See: https://kubernetes.io/docs/tasks/configure-pod-container/security-context .
securityContext:
fsGroup: 0
runAsUser: 0
# Enabled default Prometheus Service Discoveries (SD).
# 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/targets`: List of target Prometheis by which the metrics should be scraped.
# * `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.
serviceDiscoveries:
# Targets found via SD are only kept if the `prometheus.io/targets` annotation matches the name of this Prometheus.
# However this can be overridden using the following parameter.
# The result is a regex like `.*$prometheusName.*|.*$additionalTargets[i].*`
# additionalTargets:
# - ...
# Scrape interval for all jobs.
scrapeInterval: 30s
# Scrape timeout for all jobs.
scrapeTimeout: 25s
# SD for Kubernetes services and endpoints.
endpoints:
enabled: true
# Only scrape services and endpoints with annotation prometheus.io/targets: $prometheusName.
# If set to false, all targets are scraped.
limitToPrometheusTargets: true
# Scrape all metrics by default.
forbiddenMetrics: []
# SD for Kubernetes Pods. See https://github.com/coreos/prometheus-operator/issues/38.
pods:
enabled: false
# Only scrape pods with annotation prometheus.io/targets: $prometheusName.
# If set to false, all targets are scraped.
limitToPrometheusTargets: true
# Scrape all metrics by default.
forbiddenMetrics: []
# Custom metric relabelings
# See https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs
# metricRelabelings:
# SD for Kubernetes Probes.
probes:
enabled: false
# SD for kubernetes API server.
kubeAPIServer:
enabled: false
# Full list of APIserver metrics: https://github.com/kubernetes/apiserver/blob/master/pkg/endpoints/metrics/metrics.go .
allowedMetrics:
- apiserver_request_total
- apiserver_longrunning_requests
- apiserver_request_duration_seconds
- apiserver_dropped_requests_total
- apiserver_requested_deprecated_apis
- apiserver_current_inflight_requests
- etcd_request_latency_seconds
- apiserver_object_counts
- process_max_fds
- process_open_fds
- aggregator_unavailable_apiservice
# Scrape cAdvisor metrics.
cAdvisor:
enabled: false
# Full list of cAdvisor metrics: https://github.com/google/cadvisor/blob/master/docs/storage/prometheus.md .
allowedMetrics:
- container_cpu_cfs_periods_total
- container_cpu_cfs_throttled_seconds_total
- container_cpu_cfs_throttled_periods_total
- container_cpu_usage_seconds_total
- container_cpu_user_seconds_total
- container_cpu_system_seconds_total
- container_fs_inodes_total
- container_fs_limit_bytes
- container_fs_usage_bytes
- container_last_seen
- container_memory_usage_bytes
- container_memory_working_set_bytes
- container_network_receive_bytes_total
- container_network_transmit_bytes_total
- container_start_time_seconds
- container_oom_events_total
# Scrape kubelet metrics.
kubelet:
enabled: false
# Full list of kubelet metrics: https://github.com/kubernetes/kubernetes/blob/master/pkg/kubelet/metrics/metrics.go#L33 .
# Scrape all kubelet metrics by default.
allowedMetrics: []
# Scrape kube-dns pods.
kubeDNS:
enabled: false
# Scrape all node exporters.
nodeExporter:
enabled: false
# Scrape kubernikus k8s API component metrics
kubernikus:
enabled: false
namespace: kubernikus
# The pod's tolerations.
# See https://kubernetes.io/docs/concepts/configuration/taint-and-toleration
tolerations: []
# Assign custom affinity rules to the prometheus instance.
# See https://kubernetes.io/docs/concepts/configuration/assign-pod-node
affinity: {}
# Define which Nodes the Pods are scheduled on.
# See https://kubernetes.io/docs/user-guide/node-selection
nodeSelector: {}
# The tier of the alerts.
# If set .Values.global.tier takes precedence.
alerts:
# prometheus name picking up the prometheus self metrics, defaults to prometheus.name
prometheus:
# thanos name that picks up the alerts from Prometheus - mainly used when kube_ metrics needs to be present
thanos:
enabled: false
# name:
# service name routing the alerts, defaults to `metrics`
service:
# support_group routing the alerts, defaults to `observability`
support_group:
multipleTargetScrapes:
enabled: true
# List of exceptions for scrape jobs. This is joined together with a `|`.
exceptions: []
# This alert requires kube state metrics. Disable if not present
multiplePodScrapes:
enabled: true
# If true, a custom Prometheus naming will take place. Only needed for vmware-monitoring.
vmware: false
# Add remoteWrite configurations as a list. It expects a certificate with the specified key. It can be the same secret, if it has both, the cert and the key, it can be different too.
remoteWriteTargets: []
# - name: randomName
# url: some.url.foo.bar.xyz
# tlsConfig:
# cert:
# secret:
# name: certs-spoken-name
# key: cert
# keySecret:
# name: certs-spoken-name
# key: key
# remoteTimeout: 60s #defaults to 30s