Skip to content

feat: Enable grafana dashboards by default #324

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 18 commits into from
Nov 24, 2025
Merged

feat: Enable grafana dashboards by default #324

Show file tree
Hide file tree
Changes from 9 commits
Commits
Show all changes
18 commits
Select commit Hold shift + click to select a range
06f0ecc
feat: Add grafana folders by app and env
alldoami Nov 19, 2025
b624240
update env name
alldoami Nov 19, 2025
6efd565
use locals
alldoami Nov 19, 2025
2341215
Merge branch 'main' into CCIE-5548-grafana-folders
alldoami Nov 20, 2025
e2b03cb
central-grafana
alldoami Nov 20, 2025
9664789
name
alldoami Nov 20, 2025
b00246e
folderRef
hspitzley-czi Nov 20, 2025
a48e39b
allowCrossNamespaceImport, shorter resyncPeriod, update naming to avo…
hspitzley-czi Nov 20, 2025
d4a0f2a
amp
hspitzley-czi Nov 20, 2025
83b333b
sync waves
alldoami Nov 21, 2025
6b2accf
fix serviceFailureRate metrics query
hspitzley-czi Nov 21, 2025
467a4d7
folder uids
hspitzley-czi Nov 24, 2025
d0f4afb
configurable instanceSelector
hspitzley-czi Nov 24, 2025
ab4686e
chore: Update README/Schema for changed charts
hspitzley-czi Nov 24, 2025
ae70688
configurable prometheus uid
hspitzley-czi Nov 24, 2025
78fd32c
chore: Update README/Schema for changed charts
hspitzley-czi Nov 24, 2025
afdb395
Merge branch 'main' into CCIE-5548-grafana-folders
hspitzley-czi Nov 24, 2025
9942b01
enable by default
hspitzley-czi Nov 24, 2025
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
30 changes: 15 additions & 15 deletions stack/templates/_helpers.tpl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -355,7 +355,7 @@ Expects a dict with keys: global, service
{{- $service := .service -}}
{{- $metricsQuery := printf "sum(rate(nginx_ingress_controller_requests{namespace=\"%s\", service=\"%s\", status=~\"2..\"}[5m]))\n/\nsum(rate(nginx_ingress_controller_requests{namespace=\"%s\", service=\"%s\"}[5m])) * 100" $global.Values.global.argoBuildEnv.appNamespace (include "service.fullname" $service) $global.Values.global.argoBuildEnv.appNamespace (include "service.fullname" $service) -}}
{{- $panelDict := dict
"datasource" (dict "type" "prometheus" "uid" "prometheus")
"datasource" (dict "type" "prometheus" "uid" "amp")
"gridPos" (dict "h" 8 "w" 12)
"options" (dict
"legend" (dict
Expand All @@ -373,7 +373,7 @@ Expects a dict with keys: global, service
"pluginVersion" "12.1.0"
"targets" (list
(dict
"datasource" (dict "type" "prometheus" "uid" "prometheus")
"datasource" (dict "type" "prometheus" "uid" "amp")
"editorMode" "code"
"expr" $metricsQuery
"legendFormat" "__auto"
Expand All @@ -396,7 +396,7 @@ Expects a dict with keys: global, service
{{- $service := .service -}}
{{- $metricsQuery := printf "sum(rate(nginx_ingress_controller_requests{namespace=\"%s\", service=\"%s\", status!~\"2..\"}[5m])) by (status)" $global.Values.global.argoBuildEnv.appNamespace (include "service.fullname" $service) -}}
{{- $panelDict := dict
"datasource" (dict "type" "prometheus" "uid" "prometheus")
"datasource" (dict "type" "prometheus" "uid" "amp")
"gridPos" (dict "h" 8 "w" 12)
"options" (dict
"legend" (dict
Expand All @@ -414,7 +414,7 @@ Expects a dict with keys: global, service
"pluginVersion" "12.1.0"
"targets" (list
(dict
"datasource" (dict "type" "prometheus" "uid" "prometheus")
"datasource" (dict "type" "prometheus" "uid" "amp")
"editorMode" "code"
"expr" $metricsQuery
"legendFormat" "{{status}}"
Expand All @@ -437,7 +437,7 @@ Expects a dict with keys: global, service
{{- $service := .service -}}
{{- $metricsQuery := printf "increase(kube_pod_container_status_restarts_total{namespace=\"%s\", pod=~\"%s-.*\"}[5m])" $global.Values.global.argoBuildEnv.appNamespace (include "service.fullname" $service) -}}
{{- $panelDict := dict
"datasource" (dict "type" "prometheus" "uid" "prometheus")
"datasource" (dict "type" "prometheus" "uid" "amp")
"gridPos" (dict "h" 8 "w" 12)
"options" (dict
"legend" (dict
Expand All @@ -455,7 +455,7 @@ Expects a dict with keys: global, service
"pluginVersion" "12.1.0"
"targets" (list
(dict
"datasource" (dict "type" "prometheus" "uid" "prometheus")
"datasource" (dict "type" "prometheus" "uid" "amp")
"editorMode" "code"
"expr" $metricsQuery
"legendFormat" "{{pod}}"
Expand All @@ -478,7 +478,7 @@ Expects a dict with keys: global, service
{{- $service := .service -}}
{{- $metricsQuery := printf "sum(rate(nginx_ingress_controller_request_duration_seconds_sum{namespace=\"%s\", status=\"200\", service=\"%s\"}[5m]))\n/\nsum(rate(nginx_ingress_controller_request_duration_seconds_count{namespace=\"%s\", status=\"200\", service=\"%s\"}[5m]))" $global.Values.global.argoBuildEnv.appNamespace (include "service.fullname" $service) $global.Values.global.argoBuildEnv.appNamespace (include "service.fullname" $service) -}}
{{- $panelDict := dict
"datasource" (dict "type" "prometheus" "uid" "prometheus")
"datasource" (dict "type" "prometheus" "uid" "amp")
"gridPos" (dict "h" 8 "w" 12)
"options" (dict
"legend" (dict
Expand All @@ -496,7 +496,7 @@ Expects a dict with keys: global, service
"pluginVersion" "12.1.0"
"targets" (list
(dict
"datasource" (dict "type" "prometheus" "uid" "prometheus")
"datasource" (dict "type" "prometheus" "uid" "amp")
"editorMode" "code"
"expr" $metricsQuery
"legendFormat" "__auto"
Expand All @@ -522,7 +522,7 @@ Expects a dict with keys: global, cronJob
{{- $successQuery := printf "count((kube_job_status_succeeded{namespace=\"%s\", job_name=~\"%s-.*\"} UNLESS kube_job_status_succeeded{namespace=\"%s\", job_name=~\"%s-.*\"} offset $__interval) == 1)" $namespace $cronJobFullname $namespace $cronJobFullname -}}
{{- $failureQuery := printf "count((kube_job_status_failed{namespace=\"%s\", job_name=~\"%s-.*\"} UNLESS kube_job_status_failed{namespace=\"%s\", job_name=~\"%s-.*\"} offset $__interval) == 1)" $namespace $cronJobFullname $namespace $cronJobFullname -}}
{{- $panelDict := dict
"datasource" (dict "type" "prometheus" "uid" "prometheus")
"datasource" (dict "type" "prometheus" "uid" "amp")
"gridPos" (dict "h" 8 "w" 12)
"options" (dict
"legend" (dict
Expand All @@ -549,15 +549,15 @@ Expects a dict with keys: global, cronJob
"pluginVersion" "12.1.0"
"targets" (list
(dict
"datasource" (dict "type" "prometheus" "uid" "prometheus")
"datasource" (dict "type" "prometheus" "uid" "amp")
"editorMode" "code"
"expr" $successQuery
"legendFormat" "Success"
"range" true
"refId" "A"
)
(dict
"datasource" (dict "type" "prometheus" "uid" "prometheus")
"datasource" (dict "type" "prometheus" "uid" "amp")
"editorMode" "code"
"expr" $failureQuery
"legendFormat" "Failure"
Expand Down Expand Up @@ -646,7 +646,7 @@ Expects a dict with keys: global, cronJob
{{- $namespace := $global.Values.global.argoBuildEnv.appNamespace -}}
{{- $lastSuccessQuery := printf "max(kube_job_status_completion_time{namespace=\"%s\", job_name=~\"%s-.*\"} > 0) * 1000" $namespace $cronJobFullname -}}
{{- $panelDict := dict
"datasource" (dict "type" "prometheus" "uid" "prometheus")
"datasource" (dict "type" "prometheus" "uid" "amp")
"gridPos" (dict "h" 8 "w" 6)
"options" (dict
"colorMode" "value"
Expand All @@ -664,7 +664,7 @@ Expects a dict with keys: global, cronJob
"pluginVersion" "12.1.0"
"targets" (list
(dict
"datasource" (dict "type" "prometheus" "uid" "prometheus")
"datasource" (dict "type" "prometheus" "uid" "amp")
"editorMode" "code"
"expr" $lastSuccessQuery
"legendFormat" "Last Successful Run"
Expand Down Expand Up @@ -714,7 +714,7 @@ Expects a dict with keys: global, cronJob
{{- $namespace := $global.Values.global.argoBuildEnv.appNamespace -}}
{{- $avgDurationQuery := printf "avg(kube_job_status_completion_time{namespace=\"%s\", job_name=~\"%s-.*\"} - kube_job_status_start_time{namespace=\"%s\", job_name=~\"%s-.*\"})" $namespace $cronJobFullname $namespace $cronJobFullname -}}
{{- $panelDict := dict
"datasource" (dict "type" "prometheus" "uid" "prometheus")
"datasource" (dict "type" "prometheus" "uid" "amp")
"gridPos" (dict "h" 8 "w" 6)
"options" (dict
"colorMode" "value"
Expand All @@ -732,7 +732,7 @@ Expects a dict with keys: global, cronJob
"pluginVersion" "12.1.0"
"targets" (list
(dict
"datasource" (dict "type" "prometheus" "uid" "prometheus")
"datasource" (dict "type" "prometheus" "uid" "amp")
"editorMode" "code"
"expr" $avgDurationQuery
"legendFormat" "Average Duration"
Expand Down
47 changes: 46 additions & 1 deletion stack/templates/dashboard.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,50 @@
{{ $globalValues := dict "Chart" $global.Chart "Release" $global.Release "Capabilities" $global.Capabilities "Values" $global.Values.global }}
{{- with $globalValues }}
{{- if .Values.grafanaDashboard.enabled -}}
{{- $rootFolderName := printf "argus-%s" .Values.argusMetadata.stackName }}
{{- $rootFolderTitle := "Argus" }}
{{- $appFolderName := printf "%s-%s" .Values.argusMetadata.appName .Values.argusMetadata.stackName }}
{{- $appFolderTitle := .Values.argusMetadata.appName -}}
{{- $envFolderName := printf "%s-%s-%s" .Values.argusMetadata.appName .Values.argusMetadata.envName .Values.argusMetadata.stackName }}
{{- $envFolderTitle := .Values.argusMetadata.envName -}}
---
apiVersion: grafana.integreatly.org/v1beta1
kind: GrafanaFolder
metadata:
name: {{ $rootFolderName }}
spec:
allowCrossNamespaceImport: true
resyncPeriod: 30s
instanceSelector:
matchLabels:
name: central-grafana
title: {{ $rootFolderTitle }}
---
apiVersion: grafana.integreatly.org/v1beta1
kind: GrafanaFolder
metadata:
name: {{ $appFolderName }}
spec:
allowCrossNamespaceImport: true
resyncPeriod: 30s
instanceSelector:
matchLabels:
name: central-grafana
title: {{ $appFolderTitle }}
parentFolderRef: {{ $rootFolderName }}
---
apiVersion: grafana.integreatly.org/v1beta1
kind: GrafanaFolder
metadata:
name: {{ $envFolderName }}
spec:
allowCrossNamespaceImport: true
resyncPeriod: 30s
instanceSelector:
matchLabels:
name: central-grafana
title: {{ $envFolderTitle }}
parentFolderRef: {{ $appFolderName }}
---
apiVersion: grafana.integreatly.org/v1beta1
kind: GrafanaDashboard
Expand All @@ -12,7 +56,8 @@ spec:
resyncPeriod: 30s
instanceSelector:
matchLabels:
app: grafana
name: central-grafana
folderRef: {{ $envFolderName }}
json: |
{{- include "stack.grafanaDashboard.json" $global | nindent 4 }}
---
Expand Down
Loading