stackabletech · adwk67 · Jun 5, 2025 · Jun 5, 2025 · Jun 5, 2025 · Jun 5, 2025
diff --git a/.github/workflows/dev_jupyterhub-keycloak-spark.yaml b/.github/workflows/dev_jupyterhub-keycloak-spark.yaml
@@ -0,0 +1,29 @@
+---
+name: Build and publish Spark for jupyterhub-keycloak demo
+
+on:
+  workflow_dispatch:
+  push:
+    branches:
+      - main
+      # TODO (@NickLarsenNZ): Also build on release branches, but with a stackable0.0.0-dev or stackableYY.M.X tag.
+      # The current problem is that we don't know the patch level, so do we always build for `.0`, or just drop that
+      # (eg: stackableYY.M), but then do we do the same for main (eg: 0.0-dev)?
+      # - release-*
+    paths:
+      - demos/jupyterhub-keycloak/Dockerfile
+      - .github/workflows/dev_jupyterhub-keycloak-spark.yaml
+
+jobs:
+  build_image:
+    name: Reusable Workflow
+    uses: ./.github/workflows/reusable_build_image.yaml
+    secrets:
+      harbor-robot-secret: ${{ secrets.HARBOR_ROBOT_DEMOS_GITHUB_ACTION_BUILD_SECRET }}
+      slack-token: ${{ secrets.SLACK_CONTAINER_IMAGE_TOKEN }}
+    with:
+      image-name: spark
+      # TODO (@NickLarsenNZ): Use a versioned image with stackable0.0.0-dev or stackableXX.X.X so that
+      # the demo is reproducable for the release and it will be automatically replaced for the release branch.
+      image-version: 3.5.2-python311
+      containerfile-path: demos/jupyterhub-keycloak/Dockerfile
diff --git a/stacks/jupyterhub-keycloak/Dockerfile → demos/jupyterhub-keycloak/Dockerfile b/stacks/jupyterhub-keycloak/Dockerfile → demos/jupyterhub-keycloak/Dockerfile
@@ -1,9 +1,9 @@
-# docker build -t oci.stackable.tech/sandbox/spark:3.5.5-python311 -f Dockerfile .
-# kind load docker-image oci.stackable.tech/sandbox/spark:3.5.5-python311 -n stackable-data-platform
+# docker build -t oci.stackable.tech/demos/spark:3.5.2-python311 -f Dockerfile .
+# kind load docker-image oci.stackable.tech/demos/spark:3.5.2-python311 -n stackable-data-platform
 # or:
-# docker push oci.stackable.tech/sandbox/spark:3.5.5-python311
+# docker push oci.stackable.tech/demos/spark:3.5.2-python311
 
-FROM spark:3.5.5-scala2.12-java17-ubuntu
+FROM spark:3.5.2-scala2.12-java17-ubuntu
 
 USER root
 

diff --git a/docs/modules/demos/images/jupyterhub-keycloak/load-nb.png b/docs/modules/demos/images/jupyterhub-keycloak/load-nb.png
diff --git a/docs/modules/demos/pages/jupyterhub-keycloak.adoc b/docs/modules/demos/pages/jupyterhub-keycloak.adoc
@@ -103,7 +103,7 @@ This setup is ideal for interactive data processing.
 
 === Spark Configuration
 
-* **Executor Image**: Uses a custom image `oci.stackable.tech/sandbox/spark:3.5.5-python311` (built on the standard Spark image) for the executors, matching the Python version of the notebook.
+* **Executor Image**: Uses a custom image `oci.stackable.tech/demos/spark:3.5.2-python311` (built on the standard Spark image) for the executors, matching the Python version of the notebook.
 * **Resource Allocation**: Configures Spark executor instances, memory, and cores through settings defined in the notebook.
 * **Hadoop and AWS Libraries**: Includes necessary Hadoop and AWS libraries for S3 operations, matching the notebook image version.
 

diff --git a/stacks/jupyterhub-keycloak/jupyterhub.yaml b/stacks/jupyterhub-keycloak/jupyterhub.yaml
@@ -209,7 +209,7 @@ options:
           image:
             display_name: Image
             choices:
-{% for image in ["quay.io/jupyter/pyspark-notebook:python-3.11.9", "quay.io/jupyter/pyspark-notebook:spark-3.5.5"] %}
+{% for image in ["quay.io/jupyter/pyspark-notebook:python-3.11.9", "quay.io/jupyter/pyspark-notebook:spark-3.5.2"] %}
               "{{image}}":
                 display_name: "{{image}}"
                 kubespawner_override:

diff --git a/stacks/jupyterhub-keycloak/process-s3.ipynb b/stacks/jupyterhub-keycloak/process-s3.ipynb
@@ -49,8 +49,8 @@
     "acts as the driver. It is important that the versions of spark and python match across the driver (running in the juypyterhub image)\n",
     "and the executor(s) (running in a separate image, specified below with the `spark.kubernetes.container.image` setting).\n",
     "\n",
-    "The jupyterhub image `quay.io/jupyter/pyspark-notebook:spark-3.5.5` uses a base ubuntu image (like the spark images).\n",
-    "The versions of java match exactly. Python versions can differ at patch level, and the image used below `oci.stackable.tech/sandbox/spark:3.5.5-python311` is built from a `spark:3.5.2-scala2.12-java17-ubuntu` base image with python 3.11 (the same major/minor version as the notebook) installed.\n",
+    "The jupyterhub image `quay.io/jupyter/pyspark-notebook:spark-3.5.2` uses a base ubuntu image (like the spark images).\n",
+    "The versions of java match exactly. Python versions can differ at patch level, and the image used below `oci.stackable.tech/demos/spark:3.5.2-python311` is built from a `spark:3.5.2-scala2.12-java17-ubuntu` base image with python 3.11 (the same major/minor version as the notebook) installed.\n",
     "\n",
     "## S3\n",
     "As we will be reading data from an S3 bucket, we need to add the necessary `hadoop` and `aws` libraries in the same hadoop version as the\n",
@@ -69,7 +69,7 @@
     "NAMESPACE = os.environ.get(\"NAMESPACE\", \"default\")\n",
     "POD_NAME = os.environ.get(\"HOSTNAME\", f\"jupyter-{os.environ.get('USER', 'default')}-{NAMESPACE}\")\n",
     "\n",
-    "EXECUTOR_IMAGE = \"oci.stackable.tech/sandbox/spark:3.5.5-python311\" \n",
+    "EXECUTOR_IMAGE = \"oci.stackable.tech/demos/spark:3.5.2-python311\" \n",
     "\n",
     "spark = (\n",
     "    SparkSession.builder\n",