easylinux/kube-prometheus
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update component versions in docs and jsonnets

Browse Source
This commit is contained in:
Julius Volz
2019-02-04 15:45:52 +01:00
parent 19dc4088a6
commit a09da4faf5
8 changed files with 94 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
README.md
View File

@@ -260,13 +260,13 @@ These are the available fields with their respective default values:
namespace: "default", namespace: "default",
versions+:: { versions+:: {
alertmanager: "v0.15.3", alertmanager: "v0.16.0",
nodeExporter: "v0.16.0", nodeExporter: "v0.17.0",
kubeStateMetrics: "v1.3.1", kubeStateMetrics: "v1.5.0",
kubeRbacProxy: "v0.3.1", kubeRbacProxy: "v0.4.1",
addonResizer: "1.0", addonResizer: "1.0",
prometheusOperator: "v0.24.0", prometheusOperator: "v0.28.0",
prometheus: "v2.4.3", prometheus: "v2.5.0",
}, },
imageRepos+:: { imageRepos+:: {

2
jsonnet/kube-prometheus/jsonnetfile.json
View File

@@ -38,7 +38,7 @@
"subdir": "jsonnet/prometheus-operator" "subdir": "jsonnet/prometheus-operator"
} }
}, },
"version": "v0.27.0" "version": "v0.28.0"
}, },
{ {
"name": "etcd-mixin", "name": "etcd-mixin",

10
jsonnetfile.lock.json
View File

@@ -8,7 +8,7 @@
"subdir": "contrib/kube-prometheus/jsonnet/kube-prometheus" "subdir": "contrib/kube-prometheus/jsonnet/kube-prometheus"
} }
}, },
"version": "d5f758dc5d07b214cd5cdf639847ab0197f42f76" "version": "9c1ad1e863ddae4ec43f58e260077ec91ea2ae37"
}, },
{ {
"name": "ksonnet", "name": "ksonnet",
@@ -28,7 +28,7 @@
"subdir": "" "subdir": ""
} }
}, },
"version": "3b031fd4bb5c3027ab5e76a342758c203b535db0" "version": "668950e4af13f0153fa1d7b58ebe7023b33f2217"
}, },
{ {
"name": "grafonnet", "name": "grafonnet",
@@ -48,7 +48,7 @@
"subdir": "grafana-builder" "subdir": "grafana-builder"
} }
}, },
"version": "eb4d2218cefc621cd31041d46c3dbf328325d68f" "version": "ec3d4f943df01f517a083305666cd1c87bcc7e94"
}, },
{ {
"name": "grafana", "name": "grafana",
@@ -68,7 +68,7 @@
"subdir": "jsonnet/prometheus-operator" "subdir": "jsonnet/prometheus-operator"
} }
}, },
"version": "174c9bf17bec78b055e8e63c6ae3a3dc9bb0a3a8" "version": "338addbabc8a29b46840df0bb0355c12b96a6f21"
}, },
{ {
"name": "etcd-mixin", "name": "etcd-mixin",
@@ -78,7 +78,7 @@
"subdir": "Documentation/etcd-mixin" "subdir": "Documentation/etcd-mixin"
} }
}, },
"version": "fa521f4e00fedfb6d98449d92a6408d0b3b0d922" "version": "1fe6f109c87c4fa47775426a6a60c3b954ed5c33"
} }
] ]
} }

61
manifests/0prometheus-operator-0prometheusCustomResourceDefinition.yaml
View File

@@ -1538,6 +1538,14 @@ spec:
required: required:
- name - name
type: array type: array
enableAdminAPI:
description: 'Enable access to prometheus web admin API. Defaults to
the value of `false`. WARNING: Enabling the admin APIs enables mutating
endpoints, to delete data, shutdown Prometheus, and more. Enabling
this should be done with care and the user is advised to add additional
authentication authorization via a proxy to ensure only clients authorized
to perform these actions can do so. For more information see https://prometheus.io/docs/prometheus/latest/querying/api/#tsdb-admin-apis'
type: boolean
evaluationInterval: evaluationInterval:
description: Interval between consecutive evaluations. description: Interval between consecutive evaluations.
type: string type: string
@@ -1572,6 +1580,9 @@ spec:
description: ListenLocal makes the Prometheus server listen on loopback, description: ListenLocal makes the Prometheus server listen on loopback,
so that it does not bind against the Pod IP. so that it does not bind against the Pod IP.
type: boolean type: boolean
logFormat:
description: Log format for Prometheus to be configured with.
type: string
logLevel: logLevel:
description: Log level for Prometheus to be configured with. description: Log level for Prometheus to be configured with.
type: string type: string
@@ -2059,6 +2070,11 @@ spec:
description: MinBackoff is the initial retry delay. Gets doubled description: MinBackoff is the initial retry delay. Gets doubled
for every retry. for every retry.
type: string type: string
minShards:
description: MinShards is the minimum number of shards, i.e.
amount of concurrency.
format: int32
type: integer
remoteTimeout: remoteTimeout:
description: Timeout for requests to the remote write endpoint. description: Timeout for requests to the remote write endpoint.
type: string type: string
@@ -2243,6 +2259,25 @@ spec:
"In", and the values array contains only "value". The requirements "In", and the values array contains only "value". The requirements
are ANDed. are ANDed.
type: object type: object
rules:
description: /--rules.*/ command-line arguments
properties:
alert:
description: /--rules.alert.*/ command-line arguments
properties:
forGracePeriod:
description: Minimum duration between alert and restored 'for'
state. This is maintained only for alerts with configured
'for' time greater than grace period.
type: string
forOutageTolerance:
description: Max time to tolerate prometheus outage for restoring
'for' state of alert.
type: string
resendDelay:
description: Minimum amount of time to wait before resending
an alert to Alertmanager.
type: string
scrapeInterval: scrapeInterval:
description: Interval between consecutive scrapes. description: Interval between consecutive scrapes.
type: string type: string
@@ -2941,8 +2976,9 @@ spec:
description: Thanos base image if other than default. description: Thanos base image if other than default.
type: string type: string
gcs: gcs:
description: ThanosGCSSpec defines parameters for use of Google description: 'Deprecated: ThanosGCSSpec should be configured with
Cloud Storage (GCS) with Thanos. an ObjectStorageConfig secret starting with Thanos v0.2.0. ThanosGCSSpec
will be removed.'
properties: properties:
bucket: bucket:
description: Google Cloud Storage bucket name for stored blocks. description: Google Cloud Storage bucket name for stored blocks.
@@ -2970,6 +3006,22 @@ spec:
to ensure the Prometheus Operator knows what version of Thanos to ensure the Prometheus Operator knows what version of Thanos
is being configured. is being configured.
type: string type: string
objectStorageConfig:
description: SecretKeySelector selects a key of a Secret.
properties:
key:
description: The key of the secret to select from. Must be
a valid secret key.
type: string
name:
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names'
type: string
optional:
description: Specify whether the Secret or it's key must be
defined
type: boolean
required:
- key
peers: peers:
description: Peers is a DNS name for Thanos to discover peers through. description: Peers is a DNS name for Thanos to discover peers through.
type: string type: string
@@ -2988,8 +3040,9 @@ spec:
to an implementation-defined value. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/' to an implementation-defined value. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/'
type: object type: object
s3: s3:
description: ThanosS3Spec defines parameters for of AWS Simple Storage description: 'Deprecated: ThanosS3Spec should be configured with
Service (S3) with Thanos. (S3 compatible services apply as well) an ObjectStorageConfig secret starting with Thanos v0.2.0. ThanosS3Spec
will be removed.'
properties: properties:
accessKey: accessKey:
description: SecretKeySelector selects a key of a Secret. description: SecretKeySelector selects a key of a Secret.

2
manifests/0prometheus-operator-clusterRole.yaml
View File

@@ -44,11 +44,13 @@ rules:
- "" - ""
resources: resources:
- services - services
- services/finalizers
- endpoints - endpoints
verbs: verbs:
- get - get
- create - create
- update - update
- delete
- apiGroups: - apiGroups:
- "" - ""
resources: resources:

4
manifests/0prometheus-operator-deployment.yaml
View File

@@ -20,8 +20,8 @@ spec:
- --kubelet-service=kube-system/kubelet - --kubelet-service=kube-system/kubelet
- --logtostderr=true - --logtostderr=true
- --config-reloader-image=quay.io/coreos/configmap-reload:v0.0.1 - --config-reloader-image=quay.io/coreos/configmap-reload:v0.0.1
- --prometheus-config-reloader=quay.io/coreos/prometheus-config-reloader:v0.27.0 - --prometheus-config-reloader=quay.io/coreos/prometheus-config-reloader:v0.28.0
image: quay.io/coreos/prometheus-operator:v0.27.0 image: quay.io/coreos/prometheus-operator:v0.28.0
name: prometheus-operator name: prometheus-operator
ports: ports:
- containerPort: 8080 - containerPort: 8080

38
manifests/prometheus-rules.yaml
View File

@@ -314,7 +314,7 @@ spec:
message: Alertmanager has disappeared from Prometheus target discovery. message: Alertmanager has disappeared from Prometheus target discovery.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-alertmanagerdown runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-alertmanagerdown
expr: | expr: |
absent(up{job="alertmanager-main"} == 1) absent(up{job="alertmanager-main",namespace="monitoring"} == 1)
for: 15m for: 15m
labels: labels:
severity: critical severity: critical
@@ -386,7 +386,7 @@ spec:
message: Prometheus has disappeared from Prometheus target discovery. message: Prometheus has disappeared from Prometheus target discovery.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-prometheusdown runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-prometheusdown
expr: | expr: |
absent(up{job="prometheus-k8s"} == 1) absent(up{job="prometheus-k8s",namespace="monitoring"} == 1)
for: 15m for: 15m
labels: labels:
severity: critical severity: critical
@@ -395,7 +395,7 @@ spec:
message: PrometheusOperator has disappeared from Prometheus target discovery. message: PrometheusOperator has disappeared from Prometheus target discovery.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-prometheusoperatordown runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-prometheusoperatordown
expr: | expr: |
absent(up{job="prometheus-operator"} == 1) absent(up{job="prometheus-operator",namespace="monitoring"} == 1)
for: 15m for: 15m
labels: labels:
severity: critical severity: critical
@@ -799,7 +799,7 @@ spec:
message: The configuration of the instances of the Alertmanager cluster `{{$labels.service}}` message: The configuration of the instances of the Alertmanager cluster `{{$labels.service}}`
are out of sync. are out of sync.
expr: | expr: |
count_values("config_hash", alertmanager_config_hash{job="alertmanager-main"}) BY (service) / ON(service) GROUP_LEFT() label_replace(prometheus_operator_spec_replicas{job="prometheus-operator",controller="alertmanager"}, "service", "alertmanager-$1", "name", "(.*)") != 1 count_values("config_hash", alertmanager_config_hash{job="alertmanager-main",namespace="monitoring"}) BY (service) / ON(service) GROUP_LEFT() label_replace(prometheus_operator_spec_replicas{job="prometheus-operator",namespace="monitoring",controller="alertmanager"}, "service", "alertmanager-$1", "name", "(.*)") != 1
for: 5m for: 5m
labels: labels:
severity: critical severity: critical
@@ -808,7 +808,7 @@ spec:
message: Reloading Alertmanager's configuration has failed for {{ $labels.namespace message: Reloading Alertmanager's configuration has failed for {{ $labels.namespace
}}/{{ $labels.pod}}. }}/{{ $labels.pod}}.
expr: | expr: |
alertmanager_config_last_reload_successful{job="alertmanager-main"} == 0 alertmanager_config_last_reload_successful{job="alertmanager-main",namespace="monitoring"} == 0
for: 10m for: 10m
labels: labels:
severity: warning severity: warning
@@ -816,9 +816,9 @@ spec:
annotations: annotations:
message: Alertmanager has not found all other members of the cluster. message: Alertmanager has not found all other members of the cluster.
expr: | expr: |
alertmanager_cluster_members{job="alertmanager-main"} alertmanager_cluster_members{job="alertmanager-main",namespace="monitoring"}
!= on (service) GROUP_LEFT() != on (service) GROUP_LEFT()
count by (service) (alertmanager_cluster_members{job="alertmanager-main"}) count by (service) (alertmanager_cluster_members{job="alertmanager-main",namespace="monitoring"})
for: 5m for: 5m
labels: labels:
severity: critical severity: critical
@@ -865,7 +865,7 @@ spec:
description: Reloading Prometheus' configuration has failed for {{$labels.namespace}}/{{$labels.pod}} description: Reloading Prometheus' configuration has failed for {{$labels.namespace}}/{{$labels.pod}}
summary: Reloading Prometheus' configuration failed summary: Reloading Prometheus' configuration failed
expr: | expr: |
prometheus_config_last_reload_successful{job="prometheus-k8s"} == 0 prometheus_config_last_reload_successful{job="prometheus-k8s",namespace="monitoring"} == 0
for: 10m for: 10m
labels: labels:
severity: warning severity: warning
@@ -875,7 +875,7 @@ spec:
$labels.pod}} $labels.pod}}
summary: Prometheus' alert notification queue is running full summary: Prometheus' alert notification queue is running full
expr: | expr: |
predict_linear(prometheus_notifications_queue_length{job="prometheus-k8s"}[5m], 60 * 30) > prometheus_notifications_queue_capacity{job="prometheus-k8s"} predict_linear(prometheus_notifications_queue_length{job="prometheus-k8s",namespace="monitoring"}[5m], 60 * 30) > prometheus_notifications_queue_capacity{job="prometheus-k8s",namespace="monitoring"}
for: 10m for: 10m
labels: labels:
severity: warning severity: warning
@@ -885,7 +885,7 @@ spec:
$labels.pod}} to Alertmanager {{$labels.Alertmanager}} $labels.pod}} to Alertmanager {{$labels.Alertmanager}}
summary: Errors while sending alert from Prometheus summary: Errors while sending alert from Prometheus
expr: | expr: |
rate(prometheus_notifications_errors_total{job="prometheus-k8s"}[5m]) / rate(prometheus_notifications_sent_total{job="prometheus-k8s"}[5m]) > 0.01 rate(prometheus_notifications_errors_total{job="prometheus-k8s",namespace="monitoring"}[5m]) / rate(prometheus_notifications_sent_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0.01
for: 10m for: 10m
labels: labels:
severity: warning severity: warning
@@ -895,7 +895,7 @@ spec:
$labels.pod}} to Alertmanager {{$labels.Alertmanager}} $labels.pod}} to Alertmanager {{$labels.Alertmanager}}
summary: Errors while sending alerts from Prometheus summary: Errors while sending alerts from Prometheus
expr: | expr: |
rate(prometheus_notifications_errors_total{job="prometheus-k8s"}[5m]) / rate(prometheus_notifications_sent_total{job="prometheus-k8s"}[5m]) > 0.03 rate(prometheus_notifications_errors_total{job="prometheus-k8s",namespace="monitoring"}[5m]) / rate(prometheus_notifications_sent_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0.03
for: 10m for: 10m
labels: labels:
severity: critical severity: critical
@@ -905,7 +905,7 @@ spec:
to any Alertmanagers to any Alertmanagers
summary: Prometheus is not connected to any Alertmanagers summary: Prometheus is not connected to any Alertmanagers
expr: | expr: |
prometheus_notifications_alertmanagers_discovered{job="prometheus-k8s"} < 1 prometheus_notifications_alertmanagers_discovered{job="prometheus-k8s",namespace="monitoring"} < 1
for: 10m for: 10m
labels: labels:
severity: warning severity: warning
@@ -915,7 +915,7 @@ spec:
reload failures over the last four hours.' reload failures over the last four hours.'
summary: Prometheus has issues reloading data blocks from disk summary: Prometheus has issues reloading data blocks from disk
expr: | expr: |
increase(prometheus_tsdb_reloads_failures_total{job="prometheus-k8s"}[2h]) > 0 increase(prometheus_tsdb_reloads_failures_total{job="prometheus-k8s",namespace="monitoring"}[2h]) > 0
for: 12h for: 12h
labels: labels:
severity: warning severity: warning
@@ -925,7 +925,7 @@ spec:
compaction failures over the last four hours.' compaction failures over the last four hours.'
summary: Prometheus has issues compacting sample blocks summary: Prometheus has issues compacting sample blocks
expr: | expr: |
increase(prometheus_tsdb_compactions_failed_total{job="prometheus-k8s"}[2h]) > 0 increase(prometheus_tsdb_compactions_failed_total{job="prometheus-k8s",namespace="monitoring"}[2h]) > 0
for: 12h for: 12h
labels: labels:
severity: warning severity: warning
@@ -935,7 +935,7 @@ spec:
log (WAL).' log (WAL).'
summary: Prometheus write-ahead log is corrupted summary: Prometheus write-ahead log is corrupted
expr: | expr: |
tsdb_wal_corruptions_total{job="prometheus-k8s"} > 0 tsdb_wal_corruptions_total{job="prometheus-k8s",namespace="monitoring"} > 0
for: 4h for: 4h
labels: labels:
severity: warning severity: warning
@@ -945,7 +945,7 @@ spec:
samples. samples.
summary: Prometheus isn't ingesting samples summary: Prometheus isn't ingesting samples
expr: | expr: |
rate(prometheus_tsdb_head_samples_appended_total{job="prometheus-k8s"}[5m]) <= 0 rate(prometheus_tsdb_head_samples_appended_total{job="prometheus-k8s",namespace="monitoring"}[5m]) <= 0
for: 10m for: 10m
labels: labels:
severity: warning severity: warning
@@ -955,7 +955,7 @@ spec:
due to duplicate timestamps but different values' due to duplicate timestamps but different values'
summary: Prometheus has many samples rejected summary: Prometheus has many samples rejected
expr: | expr: |
increase(prometheus_target_scrapes_sample_duplicate_timestamp_total{job="prometheus-k8s"}[5m]) > 0 increase(prometheus_target_scrapes_sample_duplicate_timestamp_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0
for: 10m for: 10m
labels: labels:
severity: warning severity: warning
@@ -966,7 +966,7 @@ spec:
message: Errors while reconciling {{ $labels.controller }} in {{ $labels.namespace message: Errors while reconciling {{ $labels.controller }} in {{ $labels.namespace
}} Namespace. }} Namespace.
expr: | expr: |
rate(prometheus_operator_reconcile_errors_total{job="prometheus-operator"}[5m]) > 0.1 rate(prometheus_operator_reconcile_errors_total{job="prometheus-operator",namespace="monitoring"}[5m]) > 0.1
for: 10m for: 10m
labels: labels:
severity: warning severity: warning
@@ -974,7 +974,7 @@ spec:
annotations: annotations:
message: Errors while reconciling Prometheus in {{ $labels.namespace }} Namespace. message: Errors while reconciling Prometheus in {{ $labels.namespace }} Namespace.
expr: | expr: |
rate(prometheus_operator_node_address_lookup_errors_total{job="prometheus-operator"}[5m]) > 0.1 rate(prometheus_operator_node_address_lookup_errors_total{job="prometheus-operator",namespace="monitoring"}[5m]) > 0.1
for: 10m for: 10m
labels: labels:
severity: warning severity: warning