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

manifests: Regenerate

Browse Source
This commit is contained in:
Lili Cosic
2020-04-16 22:03:16 +02:00
parent fd67733729
commit 926337feac
9 changed files with 49 additions and 63 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
manifests/grafana-dashboardDefinitions.yaml
View File

@@ -283,7 +283,7 @@ items:
"tableColumn": "", "tableColumn": "",
"targets": [ "targets": [
{ {
"expr": "apiserver_request:availability7d{verb=\"read\"}", "expr": "apiserver_request:availability30d{verb=\"read\"}",
"format": "time_series", "format": "time_series",
"intervalFactor": 2, "intervalFactor": 2,
"legendFormat": "", "legendFormat": "",
@@ -654,7 +654,7 @@ items:
"tableColumn": "", "tableColumn": "",
"targets": [ "targets": [
{ {
"expr": "apiserver_request:availability7d{verb=\"write\"}", "expr": "apiserver_request:availability30d{verb=\"write\"}",
"format": "time_series", "format": "time_series",
"intervalFactor": 2, "intervalFactor": 2,
"legendFormat": "", "legendFormat": "",
@@ -27084,10 +27084,10 @@ items:
"steppedLine": false, "steppedLine": false,
"targets": [ "targets": [
{ {
"expr": "(\n prometheus_remote_storage_highest_timestamp_in_seconds{cluster=~\"$cluster\", instance=~\"$instance\"} \n- \n ignoring(queue) group_right(instance) prometheus_remote_storage_queue_highest_sent_timestamp_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}\n)\n", "expr": "(\n prometheus_remote_storage_highest_timestamp_in_seconds{cluster=~\"$cluster\", instance=~\"$instance\"} \n- \n ignoring(remote_name, url) group_right(instance) prometheus_remote_storage_queue_highest_sent_timestamp_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}\n)\n",
"format": "time_series", "format": "time_series",
"intervalFactor": 2, "intervalFactor": 2,
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}", "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
"refId": "A" "refId": "A"
} }
], ],
@@ -27175,10 +27175,10 @@ items:
"steppedLine": false, "steppedLine": false,
"targets": [ "targets": [
{ {
"expr": "(\n rate(prometheus_remote_storage_highest_timestamp_in_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) \n- \n ignoring (queue) group_right(instance) rate(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])\n)\n", "expr": "(\n rate(prometheus_remote_storage_highest_timestamp_in_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) \n- \n ignoring (remote_name, url) group_right(instance) rate(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])\n)\n",
"format": "time_series", "format": "time_series",
"intervalFactor": 2, "intervalFactor": 2,
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}", "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
"refId": "A" "refId": "A"
} }
], ],
@@ -27279,10 +27279,10 @@ items:
"steppedLine": false, "steppedLine": false,
"targets": [ "targets": [
{ {
"expr": "rate(\n prometheus_remote_storage_samples_in_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])\n- \n ignoring(queue) group_right(instance) rate(prometheus_remote_storage_succeeded_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) \n- \n rate(prometheus_remote_storage_dropped_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])\n", "expr": "rate(\n prometheus_remote_storage_samples_in_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])\n- \n ignoring(remote_name, url) group_right(instance) rate(prometheus_remote_storage_succeeded_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])\n- \n rate(prometheus_remote_storage_dropped_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])\n",
"format": "time_series", "format": "time_series",
"intervalFactor": 2, "intervalFactor": 2,
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}", "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
"refId": "A" "refId": "A"
} }
], ],
@@ -27387,7 +27387,7 @@ items:
"expr": "prometheus_remote_storage_shards{cluster=~\"$cluster\", instance=~\"$instance\"}", "expr": "prometheus_remote_storage_shards{cluster=~\"$cluster\", instance=~\"$instance\"}",
"format": "time_series", "format": "time_series",
"intervalFactor": 2, "intervalFactor": 2,
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}", "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
"refId": "A" "refId": "A"
} }
], ],
@@ -27478,7 +27478,7 @@ items:
"expr": "prometheus_remote_storage_shards_max{cluster=~\"$cluster\", instance=~\"$instance\"}", "expr": "prometheus_remote_storage_shards_max{cluster=~\"$cluster\", instance=~\"$instance\"}",
"format": "time_series", "format": "time_series",
"intervalFactor": 2, "intervalFactor": 2,
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}", "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
"refId": "A" "refId": "A"
} }
], ],
@@ -27569,7 +27569,7 @@ items:
"expr": "prometheus_remote_storage_shards_min{cluster=~\"$cluster\", instance=~\"$instance\"}", "expr": "prometheus_remote_storage_shards_min{cluster=~\"$cluster\", instance=~\"$instance\"}",
"format": "time_series", "format": "time_series",
"intervalFactor": 2, "intervalFactor": 2,
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}", "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
"refId": "A" "refId": "A"
} }
], ],
@@ -27660,7 +27660,7 @@ items:
"expr": "prometheus_remote_storage_shards_desired{cluster=~\"$cluster\", instance=~\"$instance\"}", "expr": "prometheus_remote_storage_shards_desired{cluster=~\"$cluster\", instance=~\"$instance\"}",
"format": "time_series", "format": "time_series",
"intervalFactor": 2, "intervalFactor": 2,
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}", "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
"refId": "A" "refId": "A"
} }
], ],
@@ -27764,7 +27764,7 @@ items:
"expr": "prometheus_remote_storage_shard_capacity{cluster=~\"$cluster\", instance=~\"$instance\"}", "expr": "prometheus_remote_storage_shard_capacity{cluster=~\"$cluster\", instance=~\"$instance\"}",
"format": "time_series", "format": "time_series",
"intervalFactor": 2, "intervalFactor": 2,
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}", "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
"refId": "A" "refId": "A"
} }
], ],
@@ -27855,7 +27855,7 @@ items:
"expr": "prometheus_remote_storage_pending_samples{cluster=~\"$cluster\", instance=~\"$instance\"}", "expr": "prometheus_remote_storage_pending_samples{cluster=~\"$cluster\", instance=~\"$instance\"}",
"format": "time_series", "format": "time_series",
"intervalFactor": 2, "intervalFactor": 2,
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}", "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
"refId": "A" "refId": "A"
} }
], ],
@@ -28050,7 +28050,7 @@ items:
"expr": "prometheus_wal_watcher_current_segment{cluster=~\"$cluster\", instance=~\"$instance\"}", "expr": "prometheus_wal_watcher_current_segment{cluster=~\"$cluster\", instance=~\"$instance\"}",
"format": "time_series", "format": "time_series",
"intervalFactor": 2, "intervalFactor": 2,
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}", "legendFormat": "{{cluster}}:{{instance}} {{consumer}}",
"refId": "A" "refId": "A"
} }
], ],
@@ -28154,7 +28154,7 @@ items:
"expr": "rate(prometheus_remote_storage_dropped_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])", "expr": "rate(prometheus_remote_storage_dropped_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])",
"format": "time_series", "format": "time_series",
"intervalFactor": 2, "intervalFactor": 2,
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}", "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
"refId": "A" "refId": "A"
} }
], ],
@@ -28245,7 +28245,7 @@ items:
"expr": "rate(prometheus_remote_storage_failed_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])", "expr": "rate(prometheus_remote_storage_failed_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])",
"format": "time_series", "format": "time_series",
"intervalFactor": 2, "intervalFactor": 2,
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}", "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
"refId": "A" "refId": "A"
} }
], ],
@@ -28336,7 +28336,7 @@ items:
"expr": "rate(prometheus_remote_storage_retried_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])", "expr": "rate(prometheus_remote_storage_retried_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])",
"format": "time_series", "format": "time_series",
"intervalFactor": 2, "intervalFactor": 2,
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}", "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
"refId": "A" "refId": "A"
} }
], ],
@@ -28427,7 +28427,7 @@ items:
"expr": "rate(prometheus_remote_storage_enqueue_retries_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])", "expr": "rate(prometheus_remote_storage_enqueue_retries_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])",
"format": "time_series", "format": "time_series",
"intervalFactor": 2, "intervalFactor": 2,
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}", "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
"refId": "A" "refId": "A"
} }
], ],
@@ -28580,11 +28580,11 @@ items:
"includeAll": true, "includeAll": true,
"label": null, "label": null,
"multi": false, "multi": false,
"name": "queue", "name": "url",
"options": [ "options": [
], ],
"query": "label_values(prometheus_remote_storage_shards{cluster=~\"$cluster\", instance=~\"$instance\"}, queue)", "query": "label_values(prometheus_remote_storage_shards{cluster=~\"$cluster\", instance=~\"$instance\"}, url)",
"refresh": 2, "refresh": 2,
"regex": "", "regex": "",
"sort": 0, "sort": 0,

4
manifests/prometheus-operator-serviceMonitor.yaml
View File

@@ -4,7 +4,7 @@ metadata:
labels: labels:
app.kubernetes.io/component: controller app.kubernetes.io/component: controller
app.kubernetes.io/name: prometheus-operator app.kubernetes.io/name: prometheus-operator
app.kubernetes.io/version: v0.38.0 app.kubernetes.io/version: v0.38.1
name: prometheus-operator name: prometheus-operator
namespace: monitoring namespace: monitoring
spec: spec:
@@ -19,4 +19,4 @@ spec:
matchLabels: matchLabels:
app.kubernetes.io/component: controller app.kubernetes.io/component: controller
app.kubernetes.io/name: prometheus-operator app.kubernetes.io/name: prometheus-operator
app.kubernetes.io/version: v0.38.0 app.kubernetes.io/version: v0.38.1

45
manifests/prometheus-rules.yaml
View File

@@ -389,12 +389,15 @@ spec:
verb: write verb: write
record: apiserver_request:availability30d record: apiserver_request:availability30d
- expr: | - expr: |
sum by (code) (increase(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[30d])) sum by (code, verb) (increase(apiserver_request_total{job="apiserver"}[30d]))
record: code_verb:apiserver_request_total:increase30d
- expr: |
sum by (code) (code_verb:apiserver_request_total:increase30d{verb=~"LIST|GET"})
labels: labels:
verb: read verb: read
record: code:apiserver_request_total:increase30d record: code:apiserver_request_total:increase30d
- expr: | - expr: |
sum by (code) (increase(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[30d])) sum by (code) (code_verb:apiserver_request_total:increase30d{verb=~"POST|PUT|PATCH|DELETE"})
labels: labels:
verb: write verb: write
record: code:apiserver_request_total:increase30d record: code:apiserver_request_total:increase30d
@@ -1311,29 +1314,6 @@ spec:
for: 5m for: 5m
labels: labels:
severity: warning severity: warning
- alert: KubeAPILatencyHigh
annotations:
message: The API server has a 99th percentile latency of {{ $value }} seconds
for {{ $labels.verb }} {{ $labels.resource }}.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapilatencyhigh
expr: |
cluster_quantile:apiserver_request_duration_seconds:histogram_quantile{job="apiserver",quantile="0.99"} > 4
for: 10m
labels:
severity: critical
- alert: KubeAPIErrorsHigh
annotations:
message: API server is returning errors for {{ $value | humanizePercentage
}} of requests for {{ $labels.verb }} {{ $labels.resource }} {{ $labels.subresource
}}.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorshigh
expr: |
sum(rate(apiserver_request_total{job="apiserver",code=~"5.."}[5m])) by (resource,subresource,verb)
/
sum(rate(apiserver_request_total{job="apiserver"}[5m])) by (resource,subresource,verb) > 0.10
for: 10m
labels:
severity: critical
- alert: KubeAPIErrorsHigh - alert: KubeAPIErrorsHigh
annotations: annotations:
message: API server is returning errors for {{ $value | humanizePercentage message: API server is returning errors for {{ $value | humanizePercentage
@@ -1451,7 +1431,7 @@ spec:
on node {{ $labels.node }}. on node {{ $labels.node }}.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletpodstartuplatencyhigh runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletpodstartuplatencyhigh
expr: | expr: |
histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{job="kubelet", metrics_path="/metrics"}[5m])) by (instance, le)) * on(instance) group_left(node) kubelet_node_name > 60 histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{job="kubelet", metrics_path="/metrics"}[5m])) by (instance, le)) * on(instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"} > 60
for: 15m for: 15m
labels: labels:
severity: warning severity: warning
@@ -1616,8 +1596,8 @@ spec:
- alert: PrometheusRemoteStorageFailures - alert: PrometheusRemoteStorageFailures
annotations: annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} failed to send description: Prometheus {{$labels.namespace}}/{{$labels.pod}} failed to send
{{ printf "%.1f" $value }}% of the samples to {{ if $labels.queue }}{{ $labels.queue {{ printf "%.1f" $value }}% of the samples to {{ $labels.remote_name}}:{{
}}{{ else }}{{ $labels.url }}{{ end }}. $labels.url }}
summary: Prometheus fails to send samples to remote storage. summary: Prometheus fails to send samples to remote storage.
expr: | expr: |
( (
@@ -1637,8 +1617,8 @@ spec:
- alert: PrometheusRemoteWriteBehind - alert: PrometheusRemoteWriteBehind
annotations: annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} remote write description: Prometheus {{$labels.namespace}}/{{$labels.pod}} remote write
is {{ printf "%.1f" $value }}s behind for {{ if $labels.queue }}{{ $labels.queue is {{ printf "%.1f" $value }}s behind for {{ $labels.remote_name}}:{{ $labels.url
}}{{ else }}{{ $labels.url }}{{ end }}. }}.
summary: Prometheus remote write is behind. summary: Prometheus remote write is behind.
expr: | expr: |
# Without max_over_time, failed scrapes could create false negatives, see # Without max_over_time, failed scrapes could create false negatives, see
@@ -1655,8 +1635,9 @@ spec:
- alert: PrometheusRemoteWriteDesiredShards - alert: PrometheusRemoteWriteDesiredShards
annotations: annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} remote write description: Prometheus {{$labels.namespace}}/{{$labels.pod}} remote write
desired shards calculation wants to run {{ $value }} shards, which is more desired shards calculation wants to run {{ $value }} shards for queue {{
than the max of {{ printf `prometheus_remote_storage_shards_max{instance="%s",job="prometheus-k8s",namespace="monitoring"}` $labels.remote_name}}:{{ $labels.url }}, which is more than the max of {{
printf `prometheus_remote_storage_shards_max{instance="%s",job="prometheus-k8s",namespace="monitoring"}`
$labels.instance | query | first | value }}. $labels.instance | query | first | value }}.
summary: Prometheus remote write desired shards calculation wants to run more summary: Prometheus remote write desired shards calculation wants to run more
than configured max shards. than configured max shards.

5
manifests/setup/prometheus-operator-0thanosrulerCustomResourceDefinition.yaml
View File

@@ -612,6 +612,11 @@ spec:
items: items:
type: string type: string
type: array type: array
alertQueryUrl:
description: The external Query URL the Thanos Ruler will set in the
'Source' field of all alerts. Maps to the '--alert.query-url' CLI
arg.
type: string
alertmanagersConfig: alertmanagersConfig:
description: Define configuration for connecting to alertmanager. Only description: Define configuration for connecting to alertmanager. Only
available with thanos v0.10.0 and higher. Maps to the `alertmanagers.config` available with thanos v0.10.0 and higher. Maps to the `alertmanagers.config`

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

@@ -4,7 +4,7 @@ metadata:
labels: labels:
app.kubernetes.io/component: controller app.kubernetes.io/component: controller
app.kubernetes.io/name: prometheus-operator app.kubernetes.io/name: prometheus-operator
app.kubernetes.io/version: v0.38.0 app.kubernetes.io/version: v0.38.1
name: prometheus-operator name: prometheus-operator
rules: rules:
- apiGroups: - apiGroups:

2
manifests/setup/prometheus-operator-clusterRoleBinding.yaml
View File

@@ -4,7 +4,7 @@ metadata:
labels: labels:
app.kubernetes.io/component: controller app.kubernetes.io/component: controller
app.kubernetes.io/name: prometheus-operator app.kubernetes.io/name: prometheus-operator
app.kubernetes.io/version: v0.38.0 app.kubernetes.io/version: v0.38.1
name: prometheus-operator name: prometheus-operator
roleRef: roleRef:
apiGroup: rbac.authorization.k8s.io apiGroup: rbac.authorization.k8s.io

8
manifests/setup/prometheus-operator-deployment.yaml
View File

@@ -4,7 +4,7 @@ metadata:
labels: labels:
app.kubernetes.io/component: controller app.kubernetes.io/component: controller
app.kubernetes.io/name: prometheus-operator app.kubernetes.io/name: prometheus-operator
app.kubernetes.io/version: v0.38.0 app.kubernetes.io/version: v0.38.1
name: prometheus-operator name: prometheus-operator
namespace: monitoring namespace: monitoring
spec: spec:
@@ -18,15 +18,15 @@ spec:
labels: labels:
app.kubernetes.io/component: controller app.kubernetes.io/component: controller
app.kubernetes.io/name: prometheus-operator app.kubernetes.io/name: prometheus-operator
app.kubernetes.io/version: v0.38.0 app.kubernetes.io/version: v0.38.1
spec: spec:
containers: containers:
- args: - args:
- --kubelet-service=kube-system/kubelet - --kubelet-service=kube-system/kubelet
- --logtostderr=true - --logtostderr=true
- --config-reloader-image=jimmidyson/configmap-reload:v0.3.0 - --config-reloader-image=jimmidyson/configmap-reload:v0.3.0
- --prometheus-config-reloader=quay.io/coreos/prometheus-config-reloader:v0.38.0 - --prometheus-config-reloader=quay.io/coreos/prometheus-config-reloader:v0.38.1
image: quay.io/coreos/prometheus-operator:v0.38.0 image: quay.io/coreos/prometheus-operator:v0.38.1
name: prometheus-operator name: prometheus-operator
ports: ports:
- containerPort: 8080 - containerPort: 8080

2
manifests/setup/prometheus-operator-service.yaml
View File

@@ -4,7 +4,7 @@ metadata:
labels: labels:
app.kubernetes.io/component: controller app.kubernetes.io/component: controller
app.kubernetes.io/name: prometheus-operator app.kubernetes.io/name: prometheus-operator
app.kubernetes.io/version: v0.38.0 app.kubernetes.io/version: v0.38.1
name: prometheus-operator name: prometheus-operator
namespace: monitoring namespace: monitoring
spec: spec:

2
manifests/setup/prometheus-operator-serviceAccount.yaml
View File

@@ -4,6 +4,6 @@ metadata:
labels: labels:
app.kubernetes.io/component: controller app.kubernetes.io/component: controller
app.kubernetes.io/name: prometheus-operator app.kubernetes.io/name: prometheus-operator
app.kubernetes.io/version: v0.38.0 app.kubernetes.io/version: v0.38.1
name: prometheus-operator name: prometheus-operator
namespace: monitoring namespace: monitoring