Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
{{`
{{- $Values := (.helm).Values | default .Values }}
graphTooltip: 1
panels:
- collapsed: false
Expand Down Expand Up @@ -82,7 +82,7 @@ panels:
sum(alertmanager_alerts{namespace=~"$namespace",service=~"$service"})
by (namespace,service,instance)
intervalFactor: 2
legendFormat: '{{instance}}'
legendFormat: '{{`{{instance}}`}}'
refId: A
title: Alerts
type: timeseries
Expand Down Expand Up @@ -156,7 +156,7 @@ panels:
sum(rate(alertmanager_alerts_received_total{namespace=~"$namespace",service=~"$service"}[$__rate_interval]))
by (namespace,service,instance)
intervalFactor: 2
legendFormat: '{{instance}} Received'
legendFormat: '{{`{{instance}}`}} Received'
refId: A
- datasource:
type: prometheus
Expand All @@ -165,7 +165,7 @@ panels:
sum(rate(alertmanager_alerts_invalid_total{namespace=~"$namespace",service=~"$service"}[$__rate_interval]))
by (namespace,service,instance)
intervalFactor: 2
legendFormat: '{{instance}} Invalid'
legendFormat: '{{`{{instance}}`}} Invalid'
refId: B
title: Alerts receive rate
type: timeseries
Expand Down Expand Up @@ -252,7 +252,7 @@ panels:
integration="$integration"}[$__rate_interval])) by
(integration,namespace,service,instance)
intervalFactor: 2
legendFormat: '{{instance}} Total'
legendFormat: '{{`{{instance}}`}} Total'
refId: A
- datasource:
type: prometheus
Expand All @@ -262,7 +262,7 @@ panels:
integration="$integration"}[$__rate_interval])) by
(integration,namespace,service,instance)
intervalFactor: 2
legendFormat: '{{instance}} Failed'
legendFormat: '{{`{{instance}}`}} Failed'
refId: B
title: '$integration: Notifications Send Rate'
type: timeseries
Expand Down Expand Up @@ -338,7 +338,7 @@ panels:
sum(rate(alertmanager_notification_latency_seconds_bucket{namespace=~"$namespace",service=~"$service", integration="$integration"}[$__rate_interval])) by (le,namespace,service,instance)
)
intervalFactor: 2
legendFormat: '{{instance}} 99th Percentile'
legendFormat: '{{`{{instance}}`}} 99th Percentile'
refId: A
- datasource:
type: prometheus
Expand All @@ -348,7 +348,7 @@ panels:
sum(rate(alertmanager_notification_latency_seconds_bucket{namespace=~"$namespace",service=~"$service", integration="$integration"}[$__rate_interval])) by (le,namespace,service,instance)
)
intervalFactor: 2
legendFormat: '{{instance}} Median'
legendFormat: '{{`{{instance}}`}} Median'
refId: B
- datasource:
type: prometheus
Expand All @@ -364,7 +364,7 @@ panels:
integration="$integration"}[$__rate_interval])) by
(namespace,service,instance)
intervalFactor: 2
legendFormat: '{{instance}} Average'
legendFormat: '{{`{{instance}}`}} Average'
refId: C
title: '$integration: Notification Duration'
type: timeseries
Expand All @@ -373,15 +373,13 @@ tags:
- alertmanager-mixin
templating:
list:
- current:
selected: false
text: Prometheus
value: Prometheus
- current: {}
Comment thread
AndrejsPon00 marked this conversation as resolved.
hide: 0
label: Data Source
name: datasource
query: prometheus
type: datasource
regex: {{ $Values.grafana.dashboard.datasource.regex | default "" }}
- current:
selected: false
text: ""
Expand Down Expand Up @@ -433,4 +431,3 @@ timepicker:
timezone: utc
title: KPS / Alertmanager / Overview
uid: alertmanager-overview
`}}
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
{{`
{{- $Values := (.helm).Values | default .Values }}
editable: true
links:
- asDropdown: true
Expand Down Expand Up @@ -253,7 +253,7 @@ panels:
expr: >-
sum(rate(workqueue_adds_total{job="apiserver", instance=~"$instance",
cluster="$cluster"}[$__rate_interval])) by (instance, name)
legendFormat: '{{instance}} {{name}}'
legendFormat: '{{`{{instance}}`}} {{`{{name}}`}}'
refId: A
title: Work Queue Add Rate
type: timeseries
Expand Down Expand Up @@ -331,7 +331,7 @@ panels:
sum(rate(workqueue_queue_duration_seconds_bucket{job="apiserver",
instance=~"$instance", cluster="$cluster"}[$__rate_interval])) by
(instance, name, le))
legendFormat: '{{instance}} {{name}}'
legendFormat: '{{`{{instance}}`}} {{`{{name}}`}}'
refId: A
title: Work Queue Latency
type: timeseries
Expand Down Expand Up @@ -406,7 +406,7 @@ panels:
expr: >-
sum(rate(workqueue_depth{job="apiserver", instance=~"$instance",
cluster="$cluster"}[$__rate_interval])) by (instance, name)
legendFormat: '{{instance}} {{name}}'
legendFormat: '{{`{{instance}}`}} {{`{{name}}`}}'
refId: A
title: Work Queue Depth
type: timeseries
Expand Down Expand Up @@ -480,7 +480,7 @@ panels:
expr: >-
process_resident_memory_bytes{job="apiserver",instance=~"$instance",
cluster="$cluster"}
legendFormat: '{{instance}}'
legendFormat: '{{`{{instance}}`}}'
refId: A
title: Memory
type: timeseries
Expand Down Expand Up @@ -555,7 +555,7 @@ panels:
expr: >-
rate(process_cpu_seconds_total{job="apiserver",instance=~"$instance",
cluster="$cluster"}[$__rate_interval])
legendFormat: '{{instance}}'
legendFormat: '{{`{{instance}}`}}'
refId: A
title: CPU usage
type: timeseries
Expand Down Expand Up @@ -629,7 +629,7 @@ panels:
expr: >-
go_goroutines{job="apiserver",instance=~"$instance",
cluster="$cluster"}
legendFormat: '{{instance}}'
legendFormat: '{{`{{instance}}`}}'
refId: A
title: Goroutines
type: timeseries
Expand Down Expand Up @@ -809,7 +809,7 @@ panels:
sum by (code)
(code_resource:apiserver_request_total:rate5m{verb="read",
cluster="$cluster"})
legendFormat: '{{ code }}'
legendFormat: '{{`{{ code }}`}}'
refId: A
title: Read SLI - Requests
type: timeseries
Expand Down Expand Up @@ -911,7 +911,7 @@ panels:
sum by (code)
(code_resource:apiserver_request_total:rate5m{verb="write",
cluster="$cluster"})
legendFormat: '{{ code }}'
legendFormat: '{{`{{ code }}`}}'
refId: A
title: Write SLI - Requests
type: timeseries
Expand Down Expand Up @@ -992,7 +992,7 @@ panels:
cluster="$cluster"}) / sum by (resource)
(code_resource:apiserver_request_total:rate5m{verb="read",
cluster="$cluster"})
legendFormat: '{{ resource }}'
legendFormat: '{{`{{ resource }}`}}'
refId: A
title: Read SLI - Errors
type: timeseries
Expand Down Expand Up @@ -1073,7 +1073,7 @@ panels:
cluster="$cluster"}) / sum by (resource)
(code_resource:apiserver_request_total:rate5m{verb="write",
cluster="$cluster"})
legendFormat: '{{ resource }}'
legendFormat: '{{`{{ resource }}`}}'
refId: A
title: Write SLI - Errors
type: timeseries
Expand Down Expand Up @@ -1150,7 +1150,7 @@ panels:
expr: >-
cluster_quantile:apiserver_request_sli_duration_seconds:histogram_quantile{verb="read",
cluster="$cluster"}
legendFormat: '{{ resource }}'
legendFormat: '{{`{{ resource }}`}}'
refId: A
title: Read SLI - Duration
type: timeseries
Expand Down Expand Up @@ -1227,7 +1227,7 @@ panels:
expr: >-
cluster_quantile:apiserver_request_sli_duration_seconds:histogram_quantile{verb="write",
cluster="$cluster"}
legendFormat: '{{ resource }}'
legendFormat: '{{`{{ resource }}`}}'
refId: A
title: Write SLI - Duration
type: timeseries
Expand All @@ -1246,7 +1246,7 @@ templating:
label: Data source
name: datasource
query: prometheus
regex: ""
regex: {{ $Values.grafana.dashboard.datasource.regex | default "" }}
type: datasource
- datasource:
type: prometheus
Expand Down Expand Up @@ -1275,4 +1275,3 @@ time:
timezone: utc
title: KPS / Kubernetes / API server
uid: 09ec8aa1e996d6ffcd6817bbaff4db1b
`}}
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
{{`
{{- $Values := (.helm).Values | default .Values }}
editable: true
links:
- asDropdown: true
Expand Down Expand Up @@ -696,7 +696,7 @@ templating:
label: Data source
name: datasource
query: prometheus
regex: ""
regex: {{ $Values.grafana.dashboard.datasource.regex | default "" }}
type: datasource
- datasource:
type: prometheus
Expand All @@ -715,4 +715,3 @@ time:
timezone: utc
title: KPS / Kubernetes / Networking / Cluster
uid: ff635a025bcfea7bc3dd4f508990a3e9
`}}
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
{{`
{{- $Values := (.helm).Values | default .Values }}
editable: true
links:
- asDropdown: true
Expand Down Expand Up @@ -127,7 +127,7 @@ panels:
job="kube-controller-manager",
instance=~"$instance"}[$__rate_interval])) by (cluster, instance,
name)
legendFormat: '{{cluster}} {{instance}} {{name}}'
legendFormat: '{{`{{cluster}}`}} {{`{{instance}}`}} {{`{{name}}`}}'
refId: A
title: Work Queue Add Rate
type: timeseries
Expand Down Expand Up @@ -203,7 +203,7 @@ panels:
job="kube-controller-manager",
instance=~"$instance"}[$__rate_interval])) by (cluster, instance,
name)
legendFormat: '{{cluster}} {{instance}} {{name}}'
legendFormat: '{{`{{cluster}}`}} {{`{{instance}}`}} {{`{{name}}`}}'
refId: A
title: Work Queue Depth
type: timeseries
Expand Down Expand Up @@ -280,7 +280,7 @@ panels:
job="kube-controller-manager",
instance=~"$instance"}[$__rate_interval])) by (cluster, instance,
name, le))
legendFormat: '{{cluster}} {{instance}} {{name}}'
legendFormat: '{{`{{cluster}}`}} {{`{{instance}}`}} {{`{{name}}`}}'
refId: A
title: Work Queue Latency
type: timeseries
Expand Down Expand Up @@ -454,7 +454,7 @@ panels:
sum(rate(rest_client_request_duration_seconds_bucket{cluster="$cluster",
job="kube-controller-manager", instance=~"$instance",
verb="POST"}[$__rate_interval])) by (verb, le))
legendFormat: '{{verb}}'
legendFormat: '{{`{{verb}}`}}'
refId: A
title: Post Request Latency 99th Quantile
type: timeseries
Expand Down Expand Up @@ -530,7 +530,7 @@ panels:
sum(rate(rest_client_request_duration_seconds_bucket{cluster="$cluster",
job="kube-controller-manager", instance=~"$instance",
verb="GET"}[$__rate_interval])) by (verb, le))
legendFormat: '{{verb}}'
legendFormat: '{{`{{verb}}`}}'
refId: A
title: Get Request Latency 99th Quantile
type: timeseries
Expand Down Expand Up @@ -604,7 +604,7 @@ panels:
expr: >-
process_resident_memory_bytes{cluster="$cluster",
job="kube-controller-manager",instance=~"$instance"}
legendFormat: '{{instance}}'
legendFormat: '{{`{{instance}}`}}'
refId: A
title: Memory
type: timeseries
Expand Down Expand Up @@ -678,7 +678,7 @@ panels:
expr: >-
rate(process_cpu_seconds_total{cluster="$cluster",
job="kube-controller-manager",instance=~"$instance"}[$__rate_interval])
legendFormat: '{{instance}}'
legendFormat: '{{`{{instance}}`}}'
refId: A
title: CPU usage
type: timeseries
Expand Down Expand Up @@ -752,7 +752,7 @@ panels:
expr: >-
go_goroutines{cluster="$cluster",
job="kube-controller-manager",instance=~"$instance"}
legendFormat: '{{instance}}'
legendFormat: '{{`{{instance}}`}}'
refId: A
title: Goroutines
type: timeseries
Expand All @@ -770,7 +770,7 @@ templating:
label: Data source
name: datasource
query: prometheus
regex: ""
regex: {{ $Values.grafana.dashboard.datasource.regex | default "" }}
type: datasource
- datasource:
type: prometheus
Expand Down Expand Up @@ -800,4 +800,3 @@ time:
timezone: utc
title: KPS / Kubernetes / Controller Manager
uid: 72e0e05bef5099e5f049b05fdc429ed4
`}}
Loading
Loading