feat: 🎸 add backfill cronjob

chart/Chart.yaml

@@ -18,7 +18,7 @@ type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: 1.11.0
+version: 1.12.0
 
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to

chart/env/dev.yaml

@@ -109,6 +109,9 @@ cacheMaintenance:
       cpu: 1
 
 # --- cron jobs  ---
+backfill:
+  enabled: false
+
 metricsCollector:
   action: "collect-metrics"
   schedule: "*/5 * * * *"

chart/env/prod.yaml

@@ -123,6 +123,20 @@ cacheMaintenance:
       memory: "8Gi"
 
 # --- cron jobs  ---
+backfill:
+  enabled: true
+  action: "backfill"
+  schedule: "0 * * * *"
+  # every hour
+  nodeSelector: {}
+  resources:
+    requests:
+      cpu: 1
+    limits:
+      cpu: 1
+      memory: "512Mi"
+  tolerations: []
+
 metricsCollector:
   action: "collect-metrics"
   schedule: "*/2 * * * *"

chart/templates/_helpers.tpl

@@ -83,6 +83,11 @@ app.kubernetes.io/component: "{{ include "name" . }}-cache-maintenance"
 app.kubernetes.io/component: "{{ include "name" . }}-metrics-collector"
 {{- end -}}
 
+{{- define "labels.backfill" -}}
+{{ include "hf.labels.commons" . }}
+app.kubernetes.io/component: "{{ include "name" . }}-backfill"
+{{- end -}}
+
 {{- define "labels.admin" -}}
 {{ include "hf.labels.commons" . }}
 app.kubernetes.io/component: "{{ include "name" . }}-admin"

chart/templates/cron-jobs/backfill/_container.tpl

@@ -0,0 +1,19 @@
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2022 The HuggingFace Authors.
+
+{{- define "containerBackfill" -}}
+- name: "{{ include "name" . }}-backfill"
+  image: {{ include "jobs.cacheMaintenance.image" . }}
+  imagePullPolicy: {{ .Values.images.pullPolicy }}
+  securityContext:
+    allowPrivilegeEscalation: false
+  resources: {{ toYaml .Values.backfill.resources | nindent 4 }}
+  env:
+    {{ include "envLog" . | nindent 2 }}
+    {{ include "envCache" . | nindent 2 }}
+    {{ include "envQueue" . | nindent 2 }}
+    {{ include "envCommon" . | nindent 2 }}
+    {{ include "envMetrics" . | nindent 2 }}
+  - name: CACHE_MAINTENANCE_ACTION
+    value: {{ .Values.backfill.action | quote }}
+{{- end -}}

chart/templates/cron-jobs/backfill/job.yaml

@@ -0,0 +1,24 @@
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2022 The HuggingFace Authors.
+
+{{- if and .Values.images.jobs.cacheMaintenance .Values.backfill.enabled }}
+apiVersion: batch/v1
+kind: CronJob
+metadata:
+  labels: {{ include "labels.backfill" . | nindent 4 }}
+  name: "{{ include "name" . }}-job-backfill"
+  namespace: {{ .Release.Namespace }}
+spec:
+  schedule: {{ .Values.backfill.schedule | quote }}
+  jobTemplate:
+    spec:
+      ttlSecondsAfterFinished: 3600
+      template:
+        spec:
+          restartPolicy: OnFailure
+          {{- include "image.imagePullSecrets" . | nindent 6 }}
+          nodeSelector: {{ toYaml .Values.backfill.nodeSelector | nindent 12 }}
+          tolerations: {{ toYaml .Values.backfill.tolerations | nindent 12 }}
+          containers: {{ include "containerBackfill" . | nindent 12 }}
+          securityContext: {{ include "securityContext" . | nindent 12 }}
+{{- end}}

chart/values.yaml

@@ -232,6 +232,20 @@ cacheMaintenance:
   tolerations: []
 
 # --- cron jobs  ---
+backfill:
+  enabled: false
+  action: "backfill"
+  schedule: "0 */3 * * *"
+  # every 3 hours
+  nodeSelector: {}
+  resources:
+    requests:
+      cpu: 0
+    limits:
+      cpu: 0
+  tolerations: []
+
+
 metricsCollector:
   action: "collect-metrics"
   schedule: "*/5 * * * *"