chore: update latest spark version to 3.5.5 (#534)

razvan · maltesander · web-flow · commit 0d6b0f013447 · 2025-03-12T14:27:40.000Z
* chore: update latest spark version to 3.5.5

* update test jars

* update cargo.lock

* update iceberg version

* Update tests/test-definition.yaml

Co-authored-by: Malte Sander &lt;malte.sander.it@gmail.com&gt;

* Update tests/test-definition.yaml

Co-authored-by: Malte Sander &lt;malte.sander.it@gmail.com&gt;

---------

Co-authored-by: Malte Sander &lt;malte.sander.it@gmail.com&gt;
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -16,13 +16,15 @@ All notable changes to this project will be documented in this file.
 ### Changed
 
 - Default to OCI for image metadata and product image selection ([#514]).
+- Update tests and docs to Spark version 3.5.5 ([#534])
 
 [#501]: https://github.com/stackabletech/spark-k8s-operator/pull/501
 [#508]: https://github.com/stackabletech/spark-k8s-operator/pull/508
 [#514]: https://github.com/stackabletech/spark-k8s-operator/pull/514
 [#515]: https://github.com/stackabletech/spark-k8s-operator/pull/515
 [#528]: https://github.com/stackabletech/spark-k8s-operator/pull/528
 [#532]: https://github.com/stackabletech/spark-k8s-operator/pull/532
+[#534]: https://github.com/stackabletech/spark-k8s-operator/pull/534
 
 ## [24.11.1] - 2025-01-10
 
diff --git a/Cargo.lock b/Cargo.lock
diff --git a/docs/modules/spark-k8s/examples/example-history-app.yaml b/docs/modules/spark-k8s/examples/example-history-app.yaml
@@ -5,7 +5,7 @@ metadata:
   name: spark-pi-s3-1
 spec:
   sparkImage:
-    productVersion: 3.5.2
+    productVersion: 3.5.5
     pullPolicy: IfNotPresent
   mode: cluster
   mainClass: org.apache.spark.examples.SparkPi
diff --git a/docs/modules/spark-k8s/examples/example-history-server.yaml b/docs/modules/spark-k8s/examples/example-history-server.yaml
@@ -5,7 +5,7 @@ metadata:
   name: spark-history
 spec:
   image:
-    productVersion: 3.5.2
+    productVersion: 3.5.5
   logFileDirectory:  # <1>
     s3:
       prefix: eventlogs/  # <2>
diff --git a/docs/modules/spark-k8s/examples/example-sparkapp-configmap.yaml b/docs/modules/spark-k8s/examples/example-sparkapp-configmap.yaml
@@ -6,7 +6,7 @@ metadata:
   namespace: default
 spec:
   sparkImage:
-    productVersion: 3.5.2
+    productVersion: 3.5.5
   mode: cluster
   mainApplicationFile: s3a://stackable-spark-k8s-jars/jobs/ny-tlc-report-1.1.0.jar # <3>
   mainClass: tech.stackable.demo.spark.NYTLCReport
diff --git a/docs/modules/spark-k8s/examples/example-sparkapp-image.yaml b/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: 3.5.2
+    productVersion: 3.5.5
   mode: cluster
   mainApplicationFile: local:///stackable/spark/jobs/ny_tlc_report.py # <2>
   args:
diff --git a/docs/modules/spark-k8s/examples/example-sparkapp-pvc.yaml b/docs/modules/spark-k8s/examples/example-sparkapp-pvc.yaml
@@ -6,7 +6,7 @@ metadata:
   namespace: default
 spec:
   sparkImage:
-    productVersion: 3.5.2
+    productVersion: 3.5.5
   mode: cluster
   mainApplicationFile: s3a://stackable-spark-k8s-jars/jobs/ny-tlc-report-1.0-SNAPSHOT.jar # <1>
   mainClass: org.example.App # <2>
diff --git a/docs/modules/spark-k8s/examples/example-sparkapp-s3-private.yaml b/docs/modules/spark-k8s/examples/example-sparkapp-s3-private.yaml
@@ -5,7 +5,7 @@ metadata:
   name: example-sparkapp-s3-private
 spec:
   sparkImage:
-    productVersion: 3.5.2
+    productVersion: 3.5.5
   mode: cluster
   mainApplicationFile: s3a://my-bucket/spark-examples.jar # <1>
   mainClass: org.apache.spark.examples.SparkPi # <2>
diff --git a/docs/modules/spark-k8s/examples/example-sparkapp-streaming.yaml b/docs/modules/spark-k8s/examples/example-sparkapp-streaming.yaml
@@ -6,7 +6,7 @@ metadata:
   namespace: default
 spec:
   sparkImage:
-    productVersion: 3.5.2
+    productVersion: 3.5.5
   mode: cluster
   mainApplicationFile: local:///stackable/spark/examples/src/main/python/streaming/hdfs_wordcount.py
   args:
diff --git a/docs/modules/spark-k8s/examples/getting_started/getting_started.sh b/docs/modules/spark-k8s/examples/getting_started/getting_started.sh
@@ -63,7 +63,7 @@ metadata:
   namespace: default
 spec:
   sparkImage:
-    productVersion: 3.5.2
+    productVersion: 3.5.5
   mode: cluster
   mainApplicationFile: local:///stackable/spark/examples/src/main/python/pi.py
   driver:
diff --git a/docs/modules/spark-k8s/examples/getting_started/getting_started.sh.j2 b/docs/modules/spark-k8s/examples/getting_started/getting_started.sh.j2
@@ -63,7 +63,7 @@ metadata:
   namespace: default
 spec:
   sparkImage:
-    productVersion: 3.5.2
+    productVersion: 3.5.5
   mode: cluster
   mainApplicationFile: local:///stackable/spark/examples/src/main/python/pi.py
   driver:
diff --git a/docs/modules/spark-k8s/pages/usage-guide/job-dependencies.adoc b/docs/modules/spark-k8s/pages/usage-guide/job-dependencies.adoc
@@ -58,7 +58,7 @@ Below is an example of a custom image that includes a JDBC driver:
 
 [source, Dockerfile]
 ----
-FROM oci.stackable.tech/sdp/spark-k8s:3.5.2-stackable24.11.0 # <1>
+FROM oci.stackable.tech/sdp/spark-k8s:3.5.5-stackable25.3.0 # <1>
 
 RUN curl --fail -o /stackable/spark/jars/postgresql-42.6.0.jar "https://jdbc.postgresql.org/download/postgresql-42.6.0.jar"
 ----
@@ -75,8 +75,8 @@ metadata:
   name: spark-jdbc
 spec:
   sparkImage:
-    custom: "oci.stackable.tech/sandbox/spark-k8s:3.5.2-stackable0.0.0-dev" # <1>
-    productVersion: "3.5.2" # <2>
+    custom: "oci.stackable.tech/sandbox/spark-k8s:3.5.5-stackable0.0.0-dev" # <1>
+    productVersion: "3.5.5" # <2>
     pullPolicy: IfNotPresent # <3>
 ...
 ----
@@ -134,7 +134,7 @@ spec:
     spark.sql.catalog.local.warehouse: /tmp/warehouse
   deps:
     packages:
-      - org.apache.iceberg:iceberg-spark-runtime-3.4_2.12:1.3.1 # <1>
+      - org.apache.iceberg:iceberg-spark-runtime-3.5_2.12:1.8.1 # <1>
 ...
 ----
 
diff --git a/docs/modules/spark-k8s/partials/supported-versions.adoc b/docs/modules/spark-k8s/partials/supported-versions.adoc
@@ -3,5 +3,5 @@
 // Stackable Platform documentation.
 // Please sort the versions in descending order (newest first)
 
-- 3.5.2 (Hadoop 3.3.4, Scala 2.12, Python 3.11, Java 17) (LTS)
-- 3.5.1 (Hadoop 3.3.4, Scala 2.12, Python 3.11, Java 17)
+- 3.5.5 (Hadoop 3.3.4, Scala 2.12, Python 3.11, Java 17) (LTS)
+- 3.5.2 (Hadoop 3.3.4, Scala 2.12, Python 3.11, Java 17)
diff --git a/examples/README-examples.md b/examples/README-examples.md
@@ -50,10 +50,10 @@ Several resources are needed in this store. These can be loaded like this:
 
 ````text
 kubectl exec minio-mc-0 -- sh -c 'mc alias set test-minio http://test-minio:9000/'
-kubectl cp examples/ny-tlc-report-1.1.0-3.5.2.jar  minio-mc-0:/tmp
+kubectl cp examples/ny-tlc-report-1.1.0-3.5.5.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-1.1.0-3.5.2.jar test-minio/my-bucket
+kubectl exec minio-mc-0 -- mc cp /tmp/ny-tlc-report-1.1.0-3.5.5.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
 ````
diff --git a/examples/ny-tlc-report-1.1.0-3.5.5.jar b/examples/ny-tlc-report-1.1.0-3.5.5.jar
diff --git a/examples/ny-tlc-report-external-dependencies.yaml b/examples/ny-tlc-report-external-dependencies.yaml
@@ -6,7 +6,7 @@ metadata:
   namespace: default
 spec:
   sparkImage:
-    productVersion: 3.5.2
+    productVersion: 3.5.5
     pullPolicy: IfNotPresent
   mode: cluster
   mainApplicationFile: s3a://my-bucket/ny_tlc_report.py
diff --git a/examples/ny-tlc-report-image.yaml b/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:3.5.2-stackable0.0.0-dev
+  sparkImage: oci.stackable.tech/sdp/spark-k8s:3.5.5-stackable0.0.0-dev
   sparkImagePullPolicy: IfNotPresent
   mode: cluster
   mainApplicationFile: local:///stackable/spark/jobs/ny_tlc_report.py
diff --git a/examples/ny-tlc-report.yaml b/examples/ny-tlc-report.yaml
@@ -13,9 +13,9 @@ metadata:
   name: spark-ny-cm
 spec:
   sparkImage:
-    productVersion: 3.5.2
+    productVersion: 3.5.5
   mode: cluster
-  mainApplicationFile: s3a://my-bucket/ny-tlc-report-1.1.0-3.5.2.jar
+  mainApplicationFile: s3a://my-bucket/ny-tlc-report-1.1.0-3.5.5.jar
   mainClass: tech.stackable.demo.spark.NYTLCReport
   volumes:
     - name: cm-job-arguments
diff --git a/rust/operator-binary/src/crd/affinity.rs b/rust/operator-binary/src/crd/affinity.rs
@@ -47,7 +47,7 @@ mod test {
           name: spark-history
         spec:
           image:
-            productVersion: 3.5.2
+            productVersion: 3.5.5
           logFileDirectory:
             s3:
               prefix: eventlogs/
diff --git a/rust/operator-binary/src/crd/history.rs b/rust/operator-binary/src/crd/history.rs
@@ -453,7 +453,7 @@ mod test {
           name: spark-history
         spec:
           image:
-            productVersion: 3.5.2
+            productVersion: 3.5.5
           logFileDirectory:
             s3:
               prefix: eventlogs/
diff --git a/rust/operator-binary/src/history/config/jvm.rs b/rust/operator-binary/src/history/config/jvm.rs
@@ -65,7 +65,7 @@ mod tests {
           name: spark-history
         spec:
           image:
-            productVersion: 3.5.2
+            productVersion: 3.5.5
           logFileDirectory:
             s3:
               prefix: eventlogs/
@@ -98,7 +98,7 @@ mod tests {
           name: spark-history
         spec:
           image:
-            productVersion: 3.5.2
+            productVersion: 3.5.5
           logFileDirectory:
             s3:
               prefix: eventlogs/
diff --git a/tests/templates/kuttl/iceberg/10-deploy-spark-app.yaml.j2 b/tests/templates/kuttl/iceberg/10-deploy-spark-app.yaml.j2
@@ -48,7 +48,7 @@ spec:
       #
       # We extract the spark parts from the test scenario value.
       #
-      - org.apache.iceberg:iceberg-spark-runtime-{{ ".".join(test_scenario['values']['spark'].split('.')[:2]) }}_2.12:1.5.2
+      - org.apache.iceberg:iceberg-spark-runtime-{{ ".".join(test_scenario['values']['spark'].split('.')[:2]) }}_2.12:1.8.1
   volumes:
     - name: script
       configMap:
diff --git a/tests/templates/kuttl/spark-ny-public-s3/ny-tlc-report-1.1.0-3.5.5.jar b/tests/templates/kuttl/spark-ny-public-s3/ny-tlc-report-1.1.0-3.5.5.jar
diff --git a/tests/test-definition.yaml b/tests/test-definition.yaml
@@ -5,15 +5,15 @@ dimensions:
       - "false"
   - name: spark
     values:
-      - 3.5.1
       - 3.5.2
+      - 3.5.5
       # Alternatively, if you want to use a custom image, append a comma and the full image name to the product version
       # as in the example below.
-      # - 3.5.1,oci.stackable.tech/sandbox/spark-k8s:3.5.1-stackable0.0.0-dev
+      # - 3.5.5,oci.stackable.tech/sandbox/spark-k8s:3.5.5-stackable0.0.0-dev
   - name: spark-delta-lake
     values:
-      - 3.5.2
-      # - 3.5.1,oci.stackable.tech/sandbox/spark-k8s:3.5.1-stackable0.0.0-dev
+      - 3.5.5
+      # - 3.5.5,oci.stackable.tech/sandbox/spark-k8s:3.5.5-stackable0.0.0-dev
   - name: hbase
     values:
       - 2.6.0
