Support for auto Statefulsets

applications/samples/api/openapi.yaml

@@ -43,6 +43,42 @@ paths:
       operationId: ping
       summary: test the application is up
       x-openapi-router-controller: samples.controllers.test_controller
+
+  /write-file:
+    post:
+      tags:
+        - test
+      requestBody:
+        description: Optional content of the file to write.
+        required: false
+        content:
+          application/json:
+            schema:
+              type: object
+              properties:
+                content:
+                  type: string
+      responses:
+        "200":
+          content:
+            application/json:
+              schema:
+                type: object
+                properties:
+                  filename:
+                    type: string
+                  path:
+                    type: string
+                  hostname:
+                    type: string
+          description: The file was written on the application volume
+      operationId: write_file
+      summary: writes a file on the application volume
+      description: >-
+        Writes a timestamped file on the application volume and returns the name of the pod
+        that handled the request. On a statefulset deployment, route this endpoint to the
+        leader service to have all writes land on pod 0.
+      x-openapi-router-controller: samples.controllers.test_controller
   /valid:
     get:
       tags:

applications/samples/backend/samples/controllers/test_controller.py

@@ -29,5 +29,43 @@ def ping():  # noqa: E501
     return time.time()
 
 
+def write_file(body=None):  # noqa: E501
+    """writes a file on the application volume
+
+     # noqa: E501
+
+    :param body: Optional content of the file to write.
+    :type body: dict | bytes
+
+    :rtype: dict
+    """
+    import os
+    import socket
+    import time
+
+    from flask import has_request_context, request
+
+    if body is None and has_request_context() and request.is_json:
+        body = request.get_json()
+
+    try:
+        from cloudharness.applications import get_current_configuration
+        mountpath = get_current_configuration().harness.deployment.volume.mountpath
+    except Exception:
+        # not running inside a cloudharness deployment (e.g. unit tests)
+        mountpath = "/tmp/myvolume"
+
+    hostname = socket.gethostname()
+    filename = f"{time.strftime('%Y%m%d-%H%M%S')}-{hostname}.txt"
+    path = os.path.join(mountpath, filename)
+    content = (body or {}).get("content") or f"written by {hostname}"
+
+    os.makedirs(mountpath, exist_ok=True)
+    with open(path, "w") as f:
+        f.write(content)
+
+    return {"filename": filename, "path": path, "hostname": hostname}
+
+
 def serialization():
     return User(last_name="Last", first_name="First")

applications/samples/backend/samples/test/test_sample.py

@@ -1,2 +1,20 @@
 def test_sample():
     assert True
+
+
+def test_write_file():
+    import socket
+
+    from samples.controllers import test_controller
+
+    # outside a deployment the controller falls back to writing under /tmp/myvolume
+    result = test_controller.write_file({"content": "hello"})
+
+    assert result["hostname"] == socket.gethostname()
+    assert result["hostname"] in result["filename"]
+    with open(result["path"]) as f:
+        assert f.read() == "hello"
+
+    result = test_controller.write_file()
+    with open(result["path"]) as f:
+        assert socket.gethostname() in f.read()

applications/samples/deploy/values-statefulset.yaml

@@ -0,0 +1,4 @@
+harness:
+  deployment:
+    statefulset: true
+    replicas: 2

applications/samples/deploy/values.yaml

@@ -12,6 +12,8 @@ harness:
   use_services:
     - name: common
   deployment:
+    replicas: 2
+    statefulset: true
     volume:
       name: my-shared-volume
       mountpath: /tmp/myvolume
@@ -48,6 +50,9 @@ harness:
       white-listed: true
     - uri: /api/ping
       white-listed: true
+    - uri: /api/write-file
+      methods: [POST]
+      white-listed: true
     - uri: /api/openapi.json
       white-listed: true
     - uri: /icon.png

deployment-configuration/helm/templates/auto-database.yaml

@@ -17,32 +17,55 @@ spec:
 {{- if and (eq .app.harness.database.type "postgres") (dig "postgres" "operator" false .app.harness.database) }}
 {{- include "deploy_utils.database.postgres.operator" . }}
 {{- else }}
+{{- $isStatefulSet := .app.harness.database.statefulset | default false }}
+{{- /* A statefulset database owns its volume through volumeClaimTemplates. A PVC named after the
+      database is the leftover of a previous Deployment: it is kept (never deleted by helm) and
+      its data is copied into the statefulset volume by a migration job (see
+      auto-volume-migration.yaml). Delete the legacy PVC once migrated. */}}
+{{- $legacyClaim := false }}
+{{- if $isStatefulSet }}
+{{- if lookup "v1" "PersistentVolumeClaim" .root.Values.namespace .app.harness.database.name }}
+{{- $legacyClaim = true }}
+{{- end }}
+{{- end }}
+{{- if or (not $isStatefulSet) $legacyClaim }}
 ---
 kind: PersistentVolumeClaim
 apiVersion: v1
 metadata:
   name: {{ .app.harness.database.name | quote }}
   namespace: {{ .root.Values.namespace }}
+  {{- if $legacyClaim }}
+  annotations:
+    helm.sh/resource-policy: keep
+  {{- end }}
 spec:
   accessModes:
     - ReadWriteOnce
   resources:
     requests:
       storage: {{ .app.harness.database.size }}
+{{- end }}
 ---
 apiVersion: apps/v1
-kind: Deployment
+kind: {{ ternary "StatefulSet" "Deployment" $isStatefulSet }}
 metadata:
   name: {{ .app.harness.database.name | quote }}
   namespace: {{ .root.Values.namespace }}
   labels:
     usesvolume: {{ .app.harness.database.name }}-{{ .root.Values.namespace }}
 spec:
+  {{- if $isStatefulSet }}
+  # StatefulSet updates terminate the old pod before creating its replacement, so no
+  # Recreate strategy or node pinning is needed.
+  serviceName: {{ .app.harness.database.name | quote }}
+  {{- else }}
   # The database's ReadWriteOnce volume attaches to a single node and the pod is
   # pinned to it via podAffinity. Recreate terminates the old pod before starting
   # the new one, avoiding an unschedulable pod when the node can't fit both.
   strategy:
     type: Recreate
+  {{- end }}
   replicas: 1
   selector:
     matchLabels:
@@ -54,6 +77,7 @@ spec:
         service: db
         usesvolume: {{ .app.harness.database.name }}-{{ .root.Values.namespace }}
     spec:
+      {{- if not $isStatefulSet }}
       affinity:
         podAffinity:
           requiredDuringSchedulingIgnoredDuringExecution:
@@ -65,6 +89,18 @@ spec:
                       - {{ .app.harness.database.name }}-{{ .root.Values.namespace }}
                       - {{ .app.harness.database.name }} # Obsolete, kept for backwards compatability, to be removed at a later date
               topologyKey: "kubernetes.io/hostname"
+      {{- end }}
+      {{- if $legacyClaim }}
+      initContainers:
+      # Holds the pod until the volume-migration job has copied the legacy volume data into
+      # the statefulset volume. Delete the legacy PVC after verifying the migration.
+      - name: volume-migration
+        image: busybox:1.36
+        command: ['sh', '-c', 'until [ -f /migration/target/.cloudharness-volume-migrated ]; do echo "waiting for the volume migration job"; sleep 5; done']
+        volumeMounts:
+          - name: {{ .app.harness.database.name | quote }}
+            mountPath: /migration/target
+      {{- end }}
       containers:
       - name: {{ .app.harness.database.name | quote }}
         imagePullPolicy: IfNotPresent
@@ -82,15 +118,33 @@ spec:
           - mountPath: /dev/shm
             name: dshm  
           {{- end }}  
+      {{- if or (not $isStatefulSet) (eq .app.harness.database.type "postgres") }}
       volumes:
+      {{- if not $isStatefulSet }}
       - name: {{ .app.harness.database.name | quote }}
         persistentVolumeClaim:
           claimName: {{ .app.harness.database.name | quote }}
+      {{- end }}
       {{- if eq .app.harness.database.type "postgres" }}
       - emptyDir:
           medium: Memory
-        name: dshm     
-      {{- end }}     
+        name: dshm
+      {{- end }}
+      {{- end }}
+  {{- if $isStatefulSet }}
+  volumeClaimTemplates:
+    - metadata:
+        name: {{ .app.harness.database.name | quote }}
+      spec:
+        accessModes:
+          - ReadWriteOnce
+        resources:
+          requests:
+            storage: {{ .app.harness.database.size }}
+  {{- end }}
+  {{- if $legacyClaim }}
+  {{- include "deploy_utils.volumeMigration" (dict "root" .root "name" .app.harness.database.name "pvc" .app.harness.database.name) }}
+  {{- end }}
 ---
 {{- if and .root.Values.backup.active (ne .app.harness.database.type "neo4j") }}
 {{- include (print "deploy_utils.database." .app.harness.database.type ".backup") . }}

deployment-configuration/helm/templates/auto-deployments.yaml

@@ -1,6 +1,34 @@
 {{- define "deploy_utils.deployment" }}
+{{- $isStatefulSet := .app.harness.deployment.statefulset | default false }}
+{{- $volume := .app.harness.deployment.volume }}
+{{- /* $rwoVolume: a ReadWriteOnce (non-nfs) volume pins the pod to a single node — it drives both
+      the Recreate strategy and the podAffinity. $ownVolume additionally requires the PVC to be
+      managed here (auto), which a statefulset turns into a volumeClaimTemplate. The checks are
+      nested so hasKey/index never runs on a nil volume: helm < 3.10 (go < 1.18) does not
+      short-circuit 'and'/'or', so a flat expression would fail for volume-less apps. */}}
+{{- $rwoVolume := false }}
+{{- $ownVolume := false }}
+{{- if $volume }}
+{{- if or (not (hasKey $volume "usenfs")) (not $volume.usenfs) }}
+{{- $rwoVolume = true }}
+{{- if or (not (hasKey $volume "auto")) $volume.auto }}
+{{- $ownVolume = true }}
+{{- end }}
+{{- end }}
+{{- end }}
+{{- $useClaimTemplate := and $isStatefulSet $ownVolume }}
+{{- /* A PVC named after the volume is the leftover of a previous Deployment: a migration job
+      (see auto-volume-migration.yaml) copies its data into each statefulset volume, and an init
+      container holds each pod until its volume has been migrated. Delete the legacy PVC once
+      migrated to end the migration. */}}
+{{- $legacyClaim := false }}
+{{- if $useClaimTemplate }}
+{{- if lookup "v1" "PersistentVolumeClaim" .root.Values.namespace $volume.name }}
+{{- $legacyClaim = true }}
+{{- end }}
+{{- end }}
 apiVersion: apps/v1
-kind: Deployment
+kind: {{ ternary "StatefulSet" "Deployment" $isStatefulSet }}
 metadata:
   name: {{ .app.harness.deployment.name| quote }}
   namespace: {{ .root.Values.namespace }}
@@ -11,18 +39,18 @@ metadata:
     {{- end }}
 {{- include "deploy_utils.labels" .root | indent 4 }}
 spec:
-  {{- if .app.harness.deployment.volume }}
-  {{- if or (not (hasKey .app.harness.deployment.volume "usenfs")) (not .app.harness.deployment.volume.usenfs) }}
+  {{- if $isStatefulSet }}
+  # StatefulSet updates terminate the old pod before creating its replacement, so no
+  # Recreate strategy or node pinning is needed even for ReadWriteOnce volumes.
+  serviceName: {{ .app.harness.service.name | quote }}
+  {{- else if $rwoVolume }}
   # A ReadWriteOnce volume attaches to a single node and the pod is pinned to the
   # volume's node via podAffinity (see below). Recreate terminates the old pod
   # before starting the new one, avoiding an unschedulable pod when the node can't
   # fit both. NFS (ReadWriteMany) volumes have no pinning and can roll normally.
-  # Nested ifs (not a flat 'and'): helm < 3.10 (go < 1.18) does not short-circuit,
-  # so hasKey must not run on a nil volume.
   strategy:
     type: Recreate
   {{- end }}
-  {{- end }}
   replicas: {{ .app.harness.deployment.replicas | default 1 }}
   selector:
     matchLabels:
@@ -47,8 +75,7 @@ spec:
       - name: {{ .root.Values.registry.secret.name }}
       {{- end }}
       {{- end }}
-      {{- if and .app.harness.deployment.volume }}
-      {{- if or (not (hasKey .app.harness.deployment.volume "usenfs")) (not .app.harness.deployment.volume.usenfs) }}
+      {{- if and $rwoVolume (not $isStatefulSet) }}
       affinity:
         podAffinity:
           requiredDuringSchedulingIgnoredDuringExecution:
@@ -61,23 +88,30 @@ spec:
                       - {{ .app.harness.deployment.volume.name }} # Obsolete, kept for backwards compatability, to be removed at a later date
               topologyKey: "kubernetes.io/hostname"
       {{- end }}
-      {{- end }}
-      {{- if .app.harness.deployment.extraContainers }}
-      {{- $hasInit := false }}
+      {{- $hasInit := $legacyClaim }}
       {{- range $name, $container := .app.harness.deployment.extraContainers }}
       {{- if and $container.auto $container.initContainer }}
       {{- $hasInit = true }}
       {{- end }}
       {{- end }}
       {{- if $hasInit }}
       initContainers:
+      {{- if $legacyClaim }}
+      # Holds the pod until the volume-migration job has copied the legacy volume data into
+      # this pod's volume. Delete the legacy PVC after verifying the migration to drop this gate.
+      - name: volume-migration
+        image: busybox:1.36
+        command: ['sh', '-c', 'until [ -f /migration/target/.cloudharness-volume-migrated ]; do echo "waiting for the volume migration job"; sleep 5; done']
+        volumeMounts:
+          - name: {{ $volume.name }}
+            mountPath: /migration/target
+      {{- end }}
       {{- range $name, $container := .app.harness.deployment.extraContainers }}
       {{- if and $container.auto $container.initContainer }}
       {{- include "deploy_utils.extraContainerSpec" (dict "name" $name "container" $container "app" $.app "root" $.root) | nindent 6 }}
       {{- end }}
       {{- end }}
       {{- end }}
-      {{- end }}
       containers:
       - name: {{ .app.harness.deployment.name| default "cloudharness-docs" | quote }}
         image: {{ .app.harness.deployment.image }}
@@ -150,7 +184,7 @@ spec:
         {{- include "deploy_utils.secretsVolume" (dict "root" $root "app" $depApp "name" (printf "cloudharness-%s" $dep) "secretName" $dep) | nindent 8 }}
         {{- end }}
         {{- end }}
-        {{- if .app.harness.deployment.volume }}
+        {{- if and .app.harness.deployment.volume (not $useClaimTemplate) }}
         - name: {{ .app.harness.deployment.volume.name }}
           persistentVolumeClaim:
             claimName: {{ .app.harness.deployment.volume.name }}
@@ -171,6 +205,21 @@ spec:
             secretName: {{ printf "%s-db" .app.harness.deployment.name }}
           {{- end }}
         {{- end }}
+  {{- if $useClaimTemplate }}
+  volumeClaimTemplates:
+    - metadata:
+        name: {{ $volume.name }}
+      spec:
+        accessModes:
+          - ReadWriteOnce
+        storageClassName: standard
+        resources:
+          requests:
+            storage: {{ $volume.size }}
+  {{- end }}
+  {{- if $legacyClaim }}
+  {{- include "deploy_utils.volumeMigration" (dict "root" .root "name" .app.harness.deployment.name "pvc" $volume.name) }}
+  {{- end }}
 ---
 {{- end }}