Merge pull request #20 from bytewax/pvc

Adding VPC resource for recovery
bytewax · Jun 6, 2023 · 5a9d7df · 5a9d7df
2 parents e381cc3 + 9d9803a
commit 5a9d7df
Show file tree

Hide file tree

Showing 7 changed files with 125 additions and 8 deletions.
diff --git a/README.md b/README.md
@@ -46,7 +46,7 @@ The command removes all the Kubernetes components associated with the chart and
 | Parameter                                 | Description                                   | Default                                                 |
 |-------------------------------------------|-----------------------------------------------|---------------------------------------------------------|
 | `image.repository`                        | Image repository                              | `bytewax.docker.scarf.sh/bytewax/bytewax`                                       |
-| `image.tag`                               | Image tag                                     | `0.16.1-python3.9`                                      |
+| `image.tag`                               | Image tag                                     | `0.16.2-python3.9`                                      |
 | `image.pullPolicy`                        | Image pull policy                             | `Always`                                                |
 | `imagePullSecrets`                        | Image pull secrets                            | `[]`                                                    |
 | `serviceAccount.create`                   | Create service account                        | `true`                                                  |
@@ -72,7 +72,7 @@ The command removes all the Kubernetes components associated with the chart and
 | `envRenderSecret`                         | Sensible environment variables passed to pods and stored as secret | `{}`                               |
 | `extraSecretMounts`                       | Secret mounts to get secrets from files instead of env vars | `[]`                                      |
 | `extraVolumeMounts`                       | Additional volume mounts                      | `[]`                                                    |
-| `configuration.pythonFileName`            | Path of the python file to run                | `basic.py`                                              |
+| `configuration.pythonFileName`            | Path of the python file to run                | `simple.py`                                             |
 | `configuration.processesCount`            | Number of concurrent processes to run         | `1`                                                     |
 | `configuration.workersPerProcess`         | Number of workers per process                 | `1`                                                     |
 | `configuration.jobMode`                   | Create a kubernetes Job resource instead of a Statefulset (use this for batch processing) - Kubernetes version required: 1.24 or superior | `false` |
@@ -81,6 +81,13 @@ The command removes all the Kubernetes components associated with the chart and
 | `configuration.configMap.customName`      | Configmap which has python file(s) created manually | ``                                                |
 | `configuration.configMap.files.pattern`   | Files to store in the ConfigMap to be created | `examples/*`                                            |
 | `configuration.configMap.files.tarName`   | Tar file to store in the ConfigMap to be created | ``                                                   |
+| `configuration.recovery.enabled`          | Enable Recovery                               | `false`                                                 |
+| `configuration.recovery.persistence.accessModes` | Persistence access modes               | `[ReadWriteOnce]`                                       |
+| `configuration.recovery.persistence.size` | Size of persistent volume claim               | `10Gi`                                                  |
+| `configuration.recovery.persistence.annotations` | PersistentVolumeClaim annotations      | `{}`                                                    |
+| `configuration.recovery.persistence.finalizers` | PersistentVolumeClaim finalizers        | `[ "kubernetes.io/pvc-protection" ]`                    |
+| `configuration.recovery.persistence.extraPvcLabels` | Extra labels to apply to the PVC    | `{}`                                                    |
+| `configuration.recovery.persistence.storageClassName` | Type of persistent volume claim   | `nil`                                                   |
 | `customOtlpUrl`                           | OTLP Endpoint URL                             | ``                                                      |
 | `opentelemetry-collector.enabled`         | Install OpenTelemetry Collector Helm Chart    | `false`                                                 |
 | `jaeger.enabled`                          | Install Jaeger Helm Chart                     | `false`                                                 |

diff --git a/charts/bytewax/Chart.yaml b/charts/bytewax/Chart.yaml
@@ -2,8 +2,8 @@ apiVersion: v2
 name: bytewax
 description: A Helm chart for Bytewax
 type: application
-version: 0.6.0
-appVersion: "0.16.1"
+version: 0.6.1
+appVersion: "0.16.2"
 icon: https://bytewax.io/assets/img/favicon.png
 dependencies:
 - condition: opentelemetry-collector.enabled

diff --git a/charts/bytewax/examples/simple.py b/charts/bytewax/examples/simple.py
@@ -0,0 +1,9 @@
+# ./simple.py
+from bytewax.dataflow import Dataflow
+from bytewax.testing import TestingInput
+from bytewax.connectors.stdio import StdOutput
+
+flow = Dataflow()
+flow.input("inp", TestingInput(range(99999999)))
+flow.map(lambda item: item + 1)
+flow.output("out", StdOutput())
diff --git a/charts/bytewax/templates/job.yaml b/charts/bytewax/templates/job.yaml
@@ -125,6 +125,10 @@ spec:
 {{- else }}
           value: "http://{{ .Release.Name }}-opentelemetry-collector:4317"
 {{- end }}
+{{- if .Values.configuration.recovery.enabled }}
+        - name: BYTEWAX_SQLITE_DIRECTORY
+          value: /var/recovery
+{{- end }}
 {{- range $key, $value := .Values.env }}
         - name: "{{ tpl $key $ }}"
           value: "{{ tpl (print $value) $ }}"
@@ -154,6 +158,10 @@ spec:
           mountPath: /etc/bytewax
         - name: working-directory
           mountPath: /var/bytewax/
+{{- if .Values.configuration.recovery.enabled }}
+        - name: recovery
+          mountPath: /var/recovery
+{{- end }}
       volumes:
       - name: hostfile
         emptyDir: {}
@@ -192,4 +200,9 @@ spec:
         emptyDir: {}
         {{- end }}
 {{- end }}
+{{- if .Values.configuration.recovery.enabled }}
+      - name: recovery
+        persistentVolumeClaim:
+          claimName: {{ .Release.Name }}
+{{- end }}
 {{- end }}
diff --git a/charts/bytewax/templates/pvc.yaml b/charts/bytewax/templates/pvc.yaml
@@ -0,0 +1,34 @@
+{{- if and .Values.configuration.jobMode .Values.configuration.recovery.enabled}}
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: {{ .Release.Name }}
+  namespace: {{ .Release.Namespace }}
+  labels:
+    {{- include "bytewax.labels" . | nindent 4 }}
+  annotations:
+    helm.sh/resource-policy: "keep"
+  {{- with .Values.configuration.recovery.persistence.annotations  }}
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+  {{- with .Values.configuration.recovery.persistence.finalizers  }}
+  finalizers:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+spec:
+  accessModes:
+    {{- range .Values.configuration.recovery.persistence.accessModes }}
+    - {{ . | quote }}
+    {{- end }}
+  resources:
+    requests:
+      storage: {{ .Values.configuration.recovery.persistence.size | quote }}
+  {{- with .Values.configuration.recovery.persistence.storageClassName }}
+  storageClassName: {{ . }}
+  {{- end }}
+  {{- with .Values.configuration.recovery.persistence.selectorLabels }}
+  selector:
+    matchLabels:
+    {{- toYaml . | nindent 6 }}
+  {{- end }}
+{{- end }}
diff --git a/charts/bytewax/templates/statefulset.yaml b/charts/bytewax/templates/statefulset.yaml
@@ -8,6 +8,36 @@ metadata:
     {{- include "bytewax.labels" . | nindent 4 }}  
 spec:
   replicas: {{ .Values.configuration.processesCount }}
+{{- if .Values.configuration.recovery.enabled }}
+  volumeClaimTemplates:
+  - metadata:
+      name: recovery
+      annotations:
+        helm.sh/resource-policy: "keep"
+      {{- with .Values.configuration.recovery.persistence.annotations  }}
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- with .Values.configuration.recovery.persistence.finalizers  }}
+      finalizers:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+    spec:
+      accessModes:
+        {{- range .Values.configuration.recovery.persistence.accessModes }}
+        - {{ . | quote }}
+        {{- end }}
+      resources:
+        requests:
+          storage: {{ .Values.configuration.recovery.persistence.size }}
+  {{- with .Values.configuration.recovery.persistence.storageClassName }}
+      storageClassName: {{ . }}
+  {{- end }}
+      {{- with .Values.configuration.recovery.persistence.selectorLabels }}
+      selector:
+        matchLabels:
+        {{- toYaml . | nindent 10 }}
+      {{- end }}
+{{- end }}
   selector:
     matchLabels:
       bytewax.io/dataflow-info: {{ .Release.Name }}
@@ -25,7 +55,7 @@ spec:
         {{- include "bytewax.selectorLabels" . | nindent 8 }}
 {{- with .Values.podLabels }}
 {{ toYaml . | indent 8 }}
-{{- end }}      
+{{- end }}
     spec:
       affinity:
         {{- toYaml .Values.affinity | nindent 8 }}
@@ -146,6 +176,10 @@ spec:
 {{- else }}
           value: "http://{{ .Release.Name }}-opentelemetry-collector:4317"
 {{- end }}
+{{- if .Values.configuration.recovery.enabled }}
+        - name: BYTEWAX_SQLITE_DIRECTORY
+          value: /var/recovery
+{{- end }}
 {{- range $key, $value := .Values.env }}
         - name: "{{ tpl $key $ }}"
           value: "{{ tpl (print $value) $ }}"
@@ -179,6 +213,10 @@ spec:
           mountPath: /etc/bytewax
         - name: working-directory
           mountPath: /var/bytewax/
+{{- if .Values.configuration.recovery.enabled }}
+        - name: recovery
+          mountPath: /var/recovery
+{{- end }}
       volumes:
 {{- if .Values.api.enabled }}
       - name: api-cache

diff --git a/charts/bytewax/values.yaml b/charts/bytewax/values.yaml
@@ -6,7 +6,7 @@ image:
   repository: bytewax.docker.scarf.sh/bytewax/bytewax
   pullPolicy: Always
   # Overrides the image tag whose default is the chart appVersion.
-  tag: "0.16.1-python3.9"
+  tag: "0.16.2-python3.9"
 
 imagePullSecrets: []
 
@@ -116,17 +116,33 @@ extraVolumeMounts: []
   #   hostPath: /usr/shared/
 
 configuration:
-  pythonFileName: "k8s_basic.py"
+  pythonFileName: "simple.py"
   processesCount: 1
   workersPerProcess: 1
   keepAlive: false
   jobMode: false
   configMap:
     create: true
-    customName:  
+    customName:
     files:
       pattern: "examples/*"
       tarName: ""
+  recovery:
+    enabled: false
+    ## Enable recovery using Kubernetes Persistent Volume Claims to store Sqlite files
+    ## ref: http://kubernetes.io/docs/user-guide/persistent-volumes/
+    ##
+    persistence:
+      # storageClassName: default
+      accessModes:
+        - ReadWriteOnce
+      size: 10Gi
+      # annotations: {}
+      finalizers:
+        - kubernetes.io/pvc-protection
+      # selectorLabels: {}
+      ## Extra labels to apply to a PVC.
+      extraPvcLabels: {}
 
 ## Configuration examples ##
 #