feat: added stackdriver support for gcp metrics (#141)

Co-authored-by: Aditya Choudhari <aditya.choudhari@wandb.com>

charts/operator-wandb/Chart.lock

@@ -32,5 +32,8 @@ dependencies:
 - name: nginx
   repository: file://charts/nginx
   version: 0.1.0
-digest: sha256:c6f5bb38d125207b54902f5638451b55807074ea700ff8eea4ea0af2dc19e346
-generated: "2024-05-17T16:55:33.068309+05:30"
+- name: stackdriver
+  repository: file://charts/stackdriver
+  version: 0.1.0
+digest: sha256:9a6c69506deb6969686d5b220a0692b53cfa29642e059bdf27c440c5d7086bdb
+generated: "2024-06-05T11:04:02.508473-07:00"

charts/operator-wandb/Chart.yaml

@@ -2,7 +2,7 @@ apiVersion: v2
 name: operator-wandb
 description: A Helm chart for deploying W&B to Kubernetes
 type: application
-version: 0.13.9
+version: 0.13.10
 appVersion: 1.0.0
 icon: https://wandb.ai/logo.svg
 
@@ -56,3 +56,7 @@ dependencies:
     version: "*.*.*"
     repository: file://charts/nginx
     condition: nginx.install
+  - name: stackdriver
+    version: "*.*.*"
+    repository: file://charts/stackdriver
+    condition: stackdriver.install

charts/operator-wandb/charts/stackdriver/.helmignore

@@ -0,0 +1,23 @@
+# Patterns to ignore when building packages.
+# This supports shell glob matching, relative path matching, and
+# negation (prefixed with !). Only one pattern per line.
+.DS_Store
+# Common VCS dirs
+.git/
+.gitignore
+.bzr/
+.bzrignore
+.hg/
+.hgignore
+.svn/
+# Common backup files
+*.swp
+*.bak
+*.tmp
+*.orig
+*~
+# Various IDEs
+.project
+.idea/
+*.tmproj
+.vscode/

charts/operator-wandb/charts/stackdriver/Chart.yaml

@@ -0,0 +1,5 @@
+apiVersion: v2
+name: stackdriver
+description: A Helm chart for Kubernetes
+version: 0.1.0
+appVersion: "0.15.0"

charts/operator-wandb/charts/stackdriver/templates/_helpers.tpl

@@ -0,0 +1,101 @@
+{{/* vim: set filetype=mustache: */}}
+
+{{/*
+Expand the name of the chart.
+*/}}
+{{- define "stackdriver.name" -}}
+{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Create a default fully qualified app name.
+We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec).
+If release name contains chart name it will be used as a full name.
+*/}}
+{{- define "stackdriver.fullname" -}}
+{{- if .Values.fullnameOverride }}
+{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" }}
+{{- else }}
+{{- $name := default .Chart.Name .Values.nameOverride }}
+{{- if contains $name .Release.Name }}
+{{- .Release.Name | trunc 63 | trimSuffix "-" }}
+{{- else }}
+{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" }}
+{{- end }}
+{{- end }}
+{{- end }}
+
+{{/*
+Create chart name and version as used by the chart label.
+*/}}
+{{- define "stackdriver.chart" -}}
+{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Common labels
+*/}}
+{{- define "stackdriver.labels" -}}
+helm.sh/chart: {{ include "stackdriver.chart" . }}
+{{ include "stackdriver.selectorLabels" . }}
+{{- if .Chart.AppVersion }}
+app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
+{{- end }}
+wandb.com/app-name: {{ include "stackdriver.chart" . }}
+app.kubernetes.io/managed-by: {{ .Release.Service }}
+{{- end }}
+
+{{/*
+Selector labels
+*/}}
+{{- define "stackdriver.selectorLabels" -}}
+app.kubernetes.io/name: {{ include "stackdriver.name" . }}
+app.kubernetes.io/instance: {{ .Release.Name }}
+{{- end }}
+
+{{/*
+Create the name of the service account to use
+*/}}
+{{- define "stackdriver.serviceAccountName" -}}
+{{- if .Values.serviceAccount.create }}
+{{- default (include "stackdriver.fullname" .) .Values.serviceAccount.name }}
+{{- else }}
+{{- default "default" .Values.serviceAccount.name }}
+{{- end }}
+{{- end }}
+
+{{/*
+Returns the extraEnv keys and values to inject into containers.
+
+Global values will override any chart-specific values.
+*/}}
+{{- define "stackdriver.extraEnv" -}}
+{{- $allExtraEnv := merge (default (dict) .local.extraEnv) .global.extraEnv -}}
+{{- range $key, $value := $allExtraEnv }}
+- name: {{ $key }}
+  value: {{ $value | quote }}
+{{- end -}}
+{{- end -}}
+
+{{/*
+Returns a list of _common_ labels to be shared across all
+app deployments and other shared objects.
+*/}}
+{{- define "stackdriver.commonLabels" -}}
+{{- $commonLabels := default (dict) .Values.common.labels -}}
+{{- if $commonLabels }}
+{{-   range $key, $value := $commonLabels }}
+{{ $key }}: {{ $value | quote }}
+{{-   end }}
+{{- end -}}
+{{- end -}}
+
+{{/*
+Returns a list of _pod_ labels to be shared across all
+app deployments.
+*/}}
+{{- define "stackdriver.podLabels" -}}
+{{- range $key, $value := .Values.pod.labels }}
+{{ $key }}: {{ $value | quote }}
+{{- end }}
+{{- end -}}

charts/operator-wandb/charts/stackdriver/templates/deployment.yaml

@@ -0,0 +1,123 @@
+{{- if .Values.enabled }}
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: {{ include "stackdriver.fullname" . }}
+  labels:
+    {{- include "wandb.commonLabels" . | nindent 4 }}
+    {{- include "stackdriver.commonLabels" . | nindent 4 }}
+    {{- include "stackdriver.labels" . | nindent 4 }}
+    {{- if .Values.deployment.labels -}}
+    {{-   toYaml .Values.deployment.labels | nindent 4 }}
+    {{- end }}
+  annotations:
+    {{- include "wandb.deploymentAnnotations" $ | nindent 4 }}
+    {{- if .Values.deployment.annotations -}}
+    {{-   toYaml .Values.deployment.annotations | nindent 4 }}
+    {{- end }}
+spec:
+  replicas: {{ .Values.replicaCount }}
+  selector:
+    matchLabels:
+      {{- include "wandb.selectorLabels" $ | nindent 6 }}
+      {{- include "stackdriver.labels" . | nindent 6 }}
+  template:
+    metadata:
+      labels:
+        {{- include "wandb.podLabels" . | nindent 8 }}
+        {{- include "stackdriver.commonLabels" . | nindent 8 }}
+        {{- include "stackdriver.podLabels" . | nindent 8 }}
+        {{- include "stackdriver.labels" . | nindent 8 }}
+      annotations:
+        {{- if .Values.pod.annotations -}}
+        {{-   toYaml .Values.pod.annotations | nindent 8 }}
+        {{- end }}
+    spec:
+      containers:
+        - name: {{ .Chart.Name }}
+          image:  "{{ .Values.image.repository }}:{{ .Values.image.tag }}"
+          command: ["stackdriver_exporter"]
+          volumeMounts:
+          {{- if or .Values.stackdriver.serviceAccountSecret .Values.stackdriver.serviceAccountKey }}
+            - name: stackdriver-service-account
+              mountPath: /etc/secrets/service-account/
+          {{- end}}
+          args:
+            - --google.project-id={{ .Values.stackdriver.projectId }}
+            - --monitoring.metrics-interval={{ .Values.stackdriver.metrics.interval }}
+            - --monitoring.metrics-offset={{ .Values.stackdriver.metrics.offset }}
+            - --monitoring.metrics-type-prefixes={{ .Values.stackdriver.metrics.typePrefixes | replace " " "" }}
+            {{- range .Values.stackdriver.metrics.filters }}
+            - --monitoring.filters={{ . }}
+            {{- end }}
+            - --stackdriver.backoff-jitter={{ .Values.stackdriver.backoffJitter }}
+            - --stackdriver.http-timeout={{ .Values.stackdriver.httpTimeout }}
+            - --stackdriver.max-backoff={{ .Values.stackdriver.maxBackoff }}
+            - --stackdriver.max-retries={{ .Values.stackdriver.maxRetries }}
+            - --stackdriver.retry-statuses={{ .Values.stackdriver.retryStatuses }}
+            - --web.listen-address={{ .Values.web.listenAddress }}
+            - --web.telemetry-path={{ .Values.web.path }}
+          {{- if .Values.stackdriver.dropDelegatedProjects }}
+            - --monitoring.drop-delegated-projects
+          {{- end }}
+          {{- if .Values.stackdriver.metrics.ingestDelay }}
+            - --monitoring.metrics-ingest-delay
+          {{- end }}
+          {{- if .Values.stackdriver.metrics.aggregateDeltas }}
+            - --monitoring.aggregate-deltas
+            - --monitoring.aggregate-deltas-ttl={{ .Values.stackdriver.metrics.aggregateDeltasTTL }}
+          {{- end }}
+          {{- if .Values.extraArgs }}
+          {{- range $key, $value := .Values.extraArgs }}
+            {{- if $value }}
+            - --{{ $key }}={{ $value }}
+            {{- end }}
+          {{- end }}
+          {{- end }}
+          {{- if or .Values.stackdriver.serviceAccountSecret .Values.stackdriver.serviceAccountKey }}
+          env:
+            - name: GOOGLE_APPLICATION_CREDENTIALS
+              value: /etc/secrets/service-account/credentials.json
+          {{- end }}
+          resources:
+            {{- toYaml .Values.resources | nindent 12 }}
+          ports:
+            - containerPort: {{ .Values.service.httpPort }}
+              name: http
+          livenessProbe:
+            httpGet:
+              path: /health
+              port: http
+            initialDelaySeconds: 30
+            timeoutSeconds: 10
+          readinessProbe:
+            httpGet:
+              path: /health
+              port: http
+            initialDelaySeconds: 10
+            timeoutSeconds: 10
+      restartPolicy: {{ .Values.restartPolicy }}
+      serviceAccountName: {{ include "stackdriver.serviceAccountName" . }}
+      {{- if .tolerations }}
+      tolerations:
+        {{- toYaml .tolerations | nindent 8 }}
+      {{- end }}
+      {{- include "wandb.nodeSelector" . | nindent 6 }}
+      {{- include "wandb.priorityClassName" . | nindent 6 }}
+      {{- include "wandb.podSecurityContext" .Values.pod.securityContext | nindent 6 }}
+      volumes:
+      {{- if .Values.stackdriver.serviceAccountSecret }}
+        - name: stackdriver-service-account
+          secret:
+            secretName: {{ .Values.stackdriver.serviceAccountSecret | quote }}
+            {{- if and (.Values.stackdriver.serviceAccountSecret) (.Values.stackdriver.serviceAccountSecretKey) }}
+            items:
+              - key: {{ .Values.stackdriver.serviceAccountSecretKey | quote }}
+                path: credentials.json
+            {{- end }}
+      {{- else if .Values.stackdriver.serviceAccountKey }}
+        - name: stackdriver-service-account
+          secret:
+            secretName: {{ template "stackdriver-exporter.fullname" . }}
+      {{- end}}
+{{- end }}

charts/operator-wandb/charts/stackdriver/templates/service.yaml

@@ -0,0 +1,23 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: {{ include "stackdriver.fullname" . }}
+  labels:
+    {{- include "wandb.commonLabels" . | nindent 4 }}
+    {{- include "stackdriver.labels" . | nindent 4 }}
+    {{- include "stackdriver.commonLabels" . | nindent 4 }}
+    {{- if .Values.service.labels -}}
+    {{-   toYaml .Values.service.labels | nindent 4 }}
+    {{- end }}
+  annotations:
+    {{- if .Values.service.annotations -}}
+    {{-   toYaml .Values.service.annotations | nindent 4 }}
+    {{- end }}
+spec:
+  type: {{ .Values.service.type }}
+  ports:
+    - port: 9255
+      protocol: TCP
+      name: stackdriver
+  selector:
+    {{- include "stackdriver.labels" . | nindent 4 }}

charts/operator-wandb/charts/stackdriver/templates/serviceaccount.yaml

@@ -0,0 +1,15 @@
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: {{ include "stackdriver.serviceAccountName" . }}
+  labels:
+    {{- include "wandb.commonLabels" . | nindent 4 }}
+    {{- include "stackdriver.commonLabels" . | nindent 4 }}
+    {{- include "stackdriver.labels" . | nindent 4 }}
+    {{- if .Values.serviceAccount.labels -}}
+    {{-   toYaml .Values.serviceAccount.labels | nindent 4 }}
+    {{- end }}
+  annotations:
+    {{- if .Values.serviceAccount.annotations -}}
+    {{-   toYaml .Values.serviceAccount.annotations | nindent 4 }}
+    {{- end }}