chore(spark-operator): update versions for 25.11.0 release

CHANGELOG.md

@@ -8,14 +8,20 @@ All notable changes to this project will be documented in this file.
 
 - Add experimental support for Spark 4 ([#589])
 - Helm: Allow Pod `priorityClassName` to be configured ([#608]).
+- Support for Spark 3.5.7 ([#610]).
 
 ### Fixed
 
 - SparkConnectServer: The `imagePullSecret` is now correctly passed to Spark executor pods ([#603]).
 
+### Removed
+
+- Support for Spark versions 3.5.5 has been dropped ([#610]).
+
 [#589]: https://github.com/stackabletech/spark-k8s-operator/pull/589
 [#603]: https://github.com/stackabletech/spark-k8s-operator/pull/603
 [#608]: https://github.com/stackabletech/spark-k8s-operator/pull/608
+[#610]: https://github.com/stackabletech/spark-k8s-operator/pull/610
 
 ## [25.7.0] - 2025-07-23
 

docs/modules/spark-k8s/examples/example-history-app.yaml

@@ -5,7 +5,7 @@ metadata:
   name: spark-pi-s3-1
 spec:
   sparkImage:
-    productVersion: 4.0.0
+    productVersion: 3.5.7
     pullPolicy: IfNotPresent
   mode: cluster
   mainClass: org.apache.spark.examples.SparkPi

docs/modules/spark-k8s/examples/example-history-server.yaml

@@ -5,11 +5,11 @@ metadata:
   name: spark-history
 spec:
   image:
-    productVersion: 4.0.0
-  logFileDirectory:  # <1>
+    productVersion: 3.5.7
+  logFileDirectory: # <1>
     s3:
-      prefix: eventlogs/  # <2>
-      bucket:  # <3>
+      prefix: eventlogs/ # <2>
+      bucket: # <3>
         inline:
           bucketName: spark-logs
           connection:
@@ -19,10 +19,10 @@ spec:
               accessStyle: Path
               credentials:
                 secretClass: history-credentials-class
-  sparkConf:  # <4>
+  sparkConf: # <4>
   nodes:
     roleGroups:
       default:
-        replicas: 1  # <5>
+        replicas: 1 # <5>
         config:
           cleaner: true # <6>

docs/modules/spark-k8s/examples/example-spark-connect.yaml

@@ -5,7 +5,7 @@ metadata:
   name: spark-connect # <1>
 spec:
   image:
-    productVersion: "3.5.6" # <2>
+    productVersion: "3.5.7" # <2>
     pullPolicy: IfNotPresent
   args:
     - "--package org.apache.iceberg:iceberg-spark-runtime-3.5_2.12:1.8.1" # <3>
@@ -22,7 +22,7 @@ spec:
         - -Dmy.custom.jvm.arg=customValue # <5>
     config:
       logging:
-        enableVectorAgent: False
+        enableVectorAgent: false
         containers:
           spark:
             custom:
@@ -37,7 +37,7 @@ spec:
         spark.executor.instances: "3"
     config:
       logging:
-        enableVectorAgent: False
+        enableVectorAgent: false
         containers:
           spark:
             custom:

docs/modules/spark-k8s/examples/example-sparkapp-configmap.yaml

@@ -6,7 +6,7 @@ metadata:
   namespace: default
 spec:
   sparkImage:
-    productVersion: 4.0.0
+    productVersion: 3.5.7
   mode: cluster
   mainApplicationFile: s3a://stackable-spark-k8s-jars/jobs/ny-tlc-report-1.1.0.jar # <3>
   mainClass: tech.stackable.demo.spark.NYTLCReport
@@ -22,7 +22,7 @@ spec:
     config:
       volumeMounts:
         - name: cm-job-arguments # <6>
-          mountPath: /arguments  # <7>
+          mountPath: /arguments # <7>
   executor:
     replicas: 3
     config:

docs/modules/spark-k8s/examples/example-sparkapp-image.yaml

@@ -7,7 +7,7 @@ metadata:
 spec:
   image: oci.stackable.tech/stackable/ny-tlc-report:0.2.0 # <1>
   sparkImage:
-    productVersion: 4.0.0
+    productVersion: 3.5.7
   mode: cluster
   mainApplicationFile: local:///stackable/spark/jobs/ny_tlc_report.py # <2>
   args:

docs/modules/spark-k8s/examples/example-sparkapp-pvc.yaml

@@ -6,7 +6,7 @@ metadata:
   namespace: default
 spec:
   sparkImage:
-    productVersion: 4.0.0
+    productVersion: 3.5.7
   mode: cluster
   mainApplicationFile: s3a://my-bucket/app.jar # <1>
   mainClass: org.example.App # <2>

docs/modules/spark-k8s/examples/example-sparkapp-s3-private.yaml

@@ -5,7 +5,7 @@ metadata:
   name: example-sparkapp-s3-private
 spec:
   sparkImage:
-    productVersion: 4.0.0
+    productVersion: 3.5.7
   mode: cluster
   mainApplicationFile: s3a://my-bucket/spark-examples.jar # <1>
   mainClass: org.apache.spark.examples.SparkPi # <2>

docs/modules/spark-k8s/examples/example-sparkapp-streaming.yaml

@@ -6,7 +6,7 @@ metadata:
   namespace: default
 spec:
   sparkImage:
-    productVersion: 4.0.0
+    productVersion: 3.5.7
   mode: cluster
   mainApplicationFile: local:///stackable/spark/examples/src/main/python/streaming/hdfs_wordcount.py
   args:

docs/modules/spark-k8s/examples/getting_started/getting_started.sh

@@ -56,7 +56,7 @@ metadata:
   namespace: default
 spec:
   sparkImage:
-    productVersion: 4.0.0
+    productVersion: 3.5.7
   mode: cluster
   mainApplicationFile: local:///stackable/spark/examples/src/main/python/pi.py
   driver:

docs/modules/spark-k8s/examples/getting_started/getting_started.sh.j2

@@ -56,7 +56,7 @@ metadata:
   namespace: default
 spec:
   sparkImage:
-    productVersion: 4.0.0
+    productVersion: 3.5.7
   mode: cluster
   mainApplicationFile: local:///stackable/spark/examples/src/main/python/pi.py
   driver:

docs/modules/spark-k8s/pages/usage-guide/job-dependencies.adoc

@@ -29,7 +29,7 @@ Below is an example of a custom image that includes a JDBC driver:
 
 [source, Dockerfile]
 ----
-FROM oci.stackable.tech/sdp/spark-k8s:4.0.0-stackable0.0.0-dev # <1>
+FROM oci.stackable.tech/sdp/spark-k8s:3.5.7-stackable0.0.0-dev # <1>
 
 RUN curl --fail -o /stackable/spark/jars/postgresql-42.6.0.jar "https://jdbc.postgresql.org/download/postgresql-42.6.0.jar" # <2>
 ----
@@ -41,8 +41,8 @@ Build your custom image and push it to your container registry.
 
 [source, bash]
 ----
-docker build -t my-registry/spark-k8s:4.0.0-psql .
-docker push my-registry/spark-k8s:4.0.0-psql
+docker build -t my-registry/spark-k8s:3.5.7-psql .
+docker push my-registry/spark-k8s:3.5.7-psql
 ----
 
 And the following snippet showcases an application that uses the custom image:
@@ -55,8 +55,8 @@ metadata:
   name: spark-jdbc
 spec:
   sparkImage:
-    custom: "my-registry/spark-k8s:4.0.0-psql" # <1>
-    productVersion: "4.0.0" # <2>
+    custom: "my-registry/spark-k8s:3.5.7-psql" # <1>
+    productVersion: "3.5.7" # <2>
 ...
 ----
 

docs/modules/spark-k8s/partials/supported-versions.adoc

@@ -3,12 +3,11 @@
 // Stackable Platform documentation.
 // Please sort the versions in descending order (newest first)
 
-- 4.0.0 (Hadoop 3.4.1, Scala 2.13, Python 3.11, Java 17) (Experimental)
-- 3.5.6 (Hadoop 3.3.4, Scala 2.12, Python 3.11, Java 17) (LTS)
-- 3.5.5 (Hadoop 3.3.4, Scala 2.12, Python 3.11, Java 17) (Deprecated)
+- 4.0.1 (Hadoop 3.4.1, Scala 2.13, Python 3.11, Java 17) (Experimental)
+- 3.5.6 (Hadoop 3.3.4, Scala 2.12, Python 3.11, Java 17) (Deprecated)
+- 3.5.7 (Hadoop 3.3.4, Scala 2.12, Python 3.11, Java 17) (LTS)
 
-Some reasons why Spark 4 is considered experimental (as of August 2025):
+Some reasons why Spark 4 is considered experimental (as of September 2025):
 
 - Missing HBase compatibility (See: https://github.com/apache/hbase-connectors/pull/130)
-- Missing Iceberg compatibility (See: https://github.com/apache/iceberg/issues/13358)
 - Executors fail to load logging libs (maybe related: https://issues.apache.org/jira/browse/SPARK-52585)

examples/README-examples.md

@@ -8,30 +8,30 @@ This note outlines a few things that are needed to run these examples on a local
 
 Create a new local cluster (e.g. with [Kind](https://kind.sigs.k8s.io/docs/user/quick-start/) and the [stackablectl tool](https://github.com/stackabletech/stackablectl)). This creates a cluster named `stackable-data-platform`.
 
-````text
+```text
 kind create cluster --name stackable-data-platform
 stackablectl operator install spark-k8s commons secret
-````
+```
 
 Load the `ny-tlc-report` image to the cluster:
 
-````text
+```text
 kind load docker-image oci.stackable.tech/stackable/ny-tlc-report:0.2.0 --name stackable-data-platform
-````
+```
 
 ## Set up the `PersistentVolumeClaim`
 
 The PVC should contain a few dependencies that Spark needs to access S3:
 
-````text
+```text
 kubectl apply -f kind/kind-pvc.yaml
-````
+```
 
 ## Set up the `minio` object store
 
 Use a local object store to avoid external dependencies:
 
-````text
+```text
 helm install test-minio \
 --version 4.0.15 \
 --set mode=standalone \
@@ -40,26 +40,26 @@ helm install test-minio \
 --set 'buckets[0].name=my-bucket,buckets[0].policy=public' \
 --set resources.requests.memory=1Gi \
 --repo https://charts.min.io/ minio
-````
+```
 
-````text
+```text
 kubectl apply -f kind/minio.yaml
-````
+```
 
 Several resources are needed in this store. These can be loaded like this:
 
-````text
+```text
 kubectl exec minio-mc-0 -- sh -c 'mc alias set test-minio http://test-minio:9000/'
-kubectl cp examples/ny-tlc-report-1.1.0-3.5.6.jar  minio-mc-0:/tmp
+kubectl cp examples/ny-tlc-report-1.1.0-3.5.7.jar  minio-mc-0:/tmp
 kubectl cp apps/ny_tlc_report.py  minio-mc-0:/tmp
 kubectl cp examples/yellow_tripdata_2021-07.csv  minio-mc-0:/tmp
-kubectl exec minio-mc-0 -- mc cp /tmp/ny-tlc-report-1.1.0-3.5.6.jar test-minio/my-bucket
+kubectl exec minio-mc-0 -- mc cp /tmp/ny-tlc-report-1.1.0-3.5.7.jar test-minio/my-bucket
 kubectl exec minio-mc-0 -- mc cp /tmp/ny_tlc_report.py test-minio/my-bucket
 kubectl exec minio-mc-0 -- mc cp /tmp/yellow_tripdata_2021-07.csv test-minio/my-bucket
-````
+```
 
 We now have a local S3-implementation with the bucket populated with the resources we need for the examples, which can be run like this:
 
-````text
+```text
 kubectl apply -f examples/ny-tlc-report.yaml
-````
+```

examples/ny-tlc-report-external-dependencies.yaml

@@ -6,7 +6,7 @@ metadata:
   namespace: default
 spec:
   sparkImage:
-    productVersion: 3.5.6
+    productVersion: 3.5.7
     pullPolicy: IfNotPresent
   mode: cluster
   mainApplicationFile: s3a://my-bucket/ny_tlc_report.py

examples/ny-tlc-report-image.yaml

@@ -7,7 +7,7 @@ metadata:
 spec:
   # everything under /jobs will be copied to /stackable/spark/jobs
   image: oci.stackable.tech/stackable/ny-tlc-report:0.2.0
-  sparkImage: oci.stackable.tech/sdp/spark-k8s:3.5.6-stackable0.0.0-dev
+  sparkImage: oci.stackable.tech/sdp/spark-k8s:3.5.7-stackable0.0.0-dev
   sparkImagePullPolicy: IfNotPresent
   mode: cluster
   mainApplicationFile: local:///stackable/spark/jobs/ny_tlc_report.py

examples/ny-tlc-report.yaml

@@ -13,9 +13,9 @@ metadata:
   name: spark-ny-cm
 spec:
   sparkImage:
-    productVersion: 3.5.6
+    productVersion: 3.5.7
   mode: cluster
-  mainApplicationFile: s3a://my-bucket/ny-tlc-report-1.1.0-3.5.6.jar
+  mainApplicationFile: s3a://my-bucket/ny-tlc-report-1.1.0-3.5.7.jar
   mainClass: tech.stackable.demo.spark.NYTLCReport
   volumes:
     - name: cm-job-arguments

rust/operator-binary/src/crd/affinity.rs

@@ -47,7 +47,7 @@ mod test {
           name: spark-history
         spec:
           image:
-            productVersion: 3.5.6
+            productVersion: 3.5.7
           logFileDirectory:
             s3:
               prefix: eventlogs/

rust/operator-binary/src/crd/history.rs

@@ -447,7 +447,7 @@ mod test {
           name: spark-history
         spec:
           image:
-            productVersion: 3.5.6
+            productVersion: 3.5.7
           logFileDirectory:
             s3:
               prefix: eventlogs/

rust/operator-binary/src/history/config/jvm.rs

@@ -65,7 +65,7 @@ mod tests {
           name: spark-history
         spec:
           image:
-            productVersion: 3.5.6
+            productVersion: 3.5.7
           logFileDirectory:
             s3:
               prefix: eventlogs/
@@ -98,7 +98,7 @@ mod tests {
           name: spark-history
         spec:
           image:
-            productVersion: 3.5.6
+            productVersion: 3.5.7
           logFileDirectory:
             s3:
               prefix: eventlogs/

tests/templates/kuttl/hbase-connector/04-install-hbase.yaml.j2

@@ -17,13 +17,15 @@ spec:
     config:
       logging:
         enableVectorAgent: {{ lookup('env', 'VECTOR_AGGREGATOR') | length > 0 }}
+      gracefulShutdownTimeout: 30s # speed up tests
     roleGroups:
       default:
         replicas: 2
   regionServers:
     config:
       logging:
         enableVectorAgent: {{ lookup('env', 'VECTOR_AGGREGATOR') | length > 0 }}
+      gracefulShutdownTimeout: 30s # speed up tests
     roleGroups:
       default:
         replicas: 1

tests/templates/kuttl/hbase-connector/10-deploy-spark-app.yaml.j2

@@ -14,8 +14,7 @@ spec:
 {% else %}
     productVersion: "{{ test_scenario['values']['spark-hbase-connector'] }}"
 {% endif %}
-    # pullPolicy: IfNotPresent
-    pullPolicy: Always
+    pullPolicy: IfNotPresent
   mode: cluster
   mainApplicationFile: local:///stackable/spark/jobs/test-hbase.py
   sparkConf: