feat(build): spark 3.5.2

.github/workflows/ci.yml

@@ -135,10 +135,82 @@ jobs:
           scala:        "2.13"
           with_hive:    "true"
           with_pyspark: "true"
+        - spark:        "3.5.1"
+          java:         "8"
+          hadoop:       "3.3.4"
+          scala:        "2.12"
+          with_hive:    "true"
+          with_pyspark: "true"
+        - spark:        "3.5.1"
+          java:         "8"
+          hadoop:       "3.3.4"
+          scala:        "2.13"
+          with_hive:    "true"
+          with_pyspark: "true"
+        - spark:        "3.5.1"
+          java:         "8"
+          hadoop:       "3.3.6"
+          scala:        "2.12"
+          with_hive:    "true"
+          with_pyspark: "true"
+        - spark:        "3.5.1"
+          java:         "8"
+          hadoop:       "3.3.6"
+          scala:        "2.13"
+          with_hive:    "true"
+          with_pyspark: "true"
+        - spark:        "3.5.1"
+          java:         "11"
+          hadoop:       "3.3.4"
+          scala:        "2.12"
+          with_hive:    "true"
+          with_pyspark: "true"
+        - spark:        "3.5.1"
+          java:         "11"
+          hadoop:       "3.3.4"
+          scala:        "2.13"
+          with_hive:    "true"
+          with_pyspark: "true"
+        - spark:        "3.5.1"
+          java:         "11"
+          hadoop:       "3.3.6"
+          scala:        "2.12"
+          with_hive:    "true"
+          with_pyspark: "true"
+        - spark:        "3.5.1"
+          java:         "11"
+          hadoop:       "3.3.6"
+          scala:        "2.13"
+          with_hive:    "true"
+          with_pyspark: "true"
+        - spark:        "3.5.1"
+          java:         "17"
+          hadoop:       "3.3.4"
+          scala:        "2.12"
+          with_hive:    "true"
+          with_pyspark: "true"
+        - spark:        "3.5.1"
+          java:         "17"
+          hadoop:       "3.3.4"
+          scala:        "2.13"
+          with_hive:    "true"
+          with_pyspark: "true"
+        - spark:        "3.5.1"
+          java:         "17"
+          hadoop:       "3.3.6"
+          scala:        "2.12"
+          with_hive:    "true"
+          with_pyspark: "true"
+        - spark:        "3.5.1"
+          java:         "17"
+          hadoop:       "3.3.6"
+          scala:        "2.13"
+          with_hive:    "true"
+          with_pyspark: "true"
     runs-on: ubuntu-20.04
     env:
       IMAGE_NAME: "spark-k8s"
-      SELF_VERSION: "v3"
+      SELF_VERSION: "v4"
       SPARK_VERSION: "${{ matrix.version.spark }}"
       HADOOP_VERSION: "${{ matrix.version.hadoop }}"
       SCALA_VERSION: "${{ matrix.version.scala }}"

CHANGELOG.md

@@ -1,5 +1,13 @@
 # CHANGELOG
 
+## v4
+- Drop support for all Spark version less than 2.y.z
+- Add Spark 3.5.1
+- Add Hadoop 3.3.6
+- Add support for Java 17 for Spark 3.5.1
+- Fix Ubuntu-based images to use `jre-focal` variant instead of `jre` which was recently upgraded to Ubuntu Jammy to v22.y.z and causing system level python package installation to fail due to [PEP 668](https://issues.apache.org/jira/browse/SPARK-49068)
+- Remove docker tags without self version
+
 ## v3
 
 - (Temporarily drop support for R due to keyserver issues)

README.md

@@ -13,20 +13,21 @@ Debian:
 - `3.2.2`
 - `3.1.3`
 - `3.4.1`
+- `3.5.1`
 
-## Note
+## Notes
 
 (R builds are temporarily suspended due to keyserver issues at current time.)
 
-Build image for Spark 3.4.1 is Ubuntu based because openjdk is deprecated and
-going forward the official Spark repository uses `eclipse-temurin:<java>-jre`
+Build image for Spark 3.4.1/3.5.1 is Ubuntu based because openjdk is deprecated and
+going forward the official Spark repository uses `eclipse-temurin:<java>-jre-focal`
 where slim variants of jre images are not available at the moment.
 
 All the build images with Spark before v3.4.0 are Debian based as the official 
 Spark repository now uses `openjdk:<java>-jre-slim-buster` as the base image 
 for Kubernetes build. Because currently the official Dockerfiles do not pin 
 the Debian distribution, they are incorrectly using the latest Debian `bullseye`,
-which does not have support for Python 2, and its Python 3.9 do not work well 
+which does not have support for Python 2, and its Python 3.9 do not work well
 with PySpark.
 
 Hence some Dockerfile overrides are in-place to make sure that Spark 2 builds
@@ -48,11 +49,11 @@ For quick testing of local build, you should do the following commands:
 
 ```bash
 export IMAGE_NAME=spark-k8s
-export SELF_VERSION="v3"
+export SELF_VERSION="v4"
 export SCALA_VERSION="2.12"
-export SPARK_VERSION="3.3.0"
-export HADOOP_VERSION="3.3.2"
-export JAVA_VERSION="11"
+export SPARK_VERSION="3.5.1"
+export HADOOP_VERSION="3.3.6"
+export JAVA_VERSION="17"
 export WITH_HIVE="true"
 export WITH_PYSPARK="true"
 bash make-distribution.sh

build.sh

@@ -1,9 +1,9 @@
 export IMAGE_NAME=spark-k8s
-export SELF_VERSION="v3"
+export SELF_VERSION="v4"
 export SCALA_VERSION="2.12"
-export SPARK_VERSION="3.3.0"
-export HADOOP_VERSION="3.3.2"
-export JAVA_VERSION="11"
+export SPARK_VERSION="3.5.2"
+export HADOOP_VERSION="3.3.6"
+export JAVA_VERSION="8"
 export WITH_HIVE="true"
 export WITH_PYSPARK="true"
 bash make-distribution.sh

make-distribution.sh

@@ -40,57 +40,25 @@ TERM=xterm-color ./dev/make-distribution.sh \
     ${HIVE_INSTALL_FLAG:+"-Phive"} \
     -DskipTests
 
-SPARK_MAJOR_VERSION="$(echo "${SPARK_VERSION}" | cut -d '.' -f1)"
-HADOOP_MAJOR_VERSION="$(echo "${HADOOP_VERSION}" | cut -d '.' -f1)"
-HIVE_HADOOP3_HIVE_EXEC_URL=${HIVE_HADOOP3_HIVE_EXEC_URL:-https://github.com/guangie88/hive-exec-jar/releases/download/1.2.1.spark2-hadoop3/hive-exec-1.2.1.spark2.jar}
-
-# Replace Hive for Hadoop 3 since Hive 1.2.1 does not officially support Hadoop 3 when using Spark 2.y.z
-# Note docker-image-tool.sh takes the jars from assembly/target/scala-2.*/jars
-if [[ "${WITH_HIVE}" = "true" ]] && [[ "${SPARK_MAJOR_VERSION}" -eq 2 ]] && [[ "${HADOOP_MAJOR_VERSION}" -eq 3 ]]; then
-    HIVE_EXEC_JAR_NAME="hive-exec-1.2.1.spark2.jar"
-    TARGET_JAR_PATH="$(find assembly -type f -name "${HIVE_EXEC_JAR_NAME}")"
-    curl -LO "${HIVE_HADOOP3_HIVE_EXEC_URL}" && mv "${HIVE_EXEC_JAR_NAME}" "${TARGET_JAR_PATH}"
-    # Spark <= 2.4 uses ${TARGET_JAR_PATH} for Docker COPY, but Spark >= 3 uses dist/jars/
-    cp "${TARGET_JAR_PATH}" "dist/jars/"
-fi
-
 SPARK_MAJOR_VERSION="$(echo "${SPARK_VERSION}" | cut -d '.' -f1)"
 SPARK_MINOR_VERSION="$(echo "${SPARK_VERSION}" | cut -d '.' -f2)"
+HADOOP_MAJOR_VERSION="$(echo "${HADOOP_VERSION}" | cut -d '.' -f1)"
 
-if [[ ${SPARK_MAJOR_VERSION} -eq 2 && ${SPARK_MINOR_VERSION} -eq 4 ]]; then  # 2.4.z
-    # Same Dockerfiles as Spark v2.4.8, but allow override of base image to use Debian Buster
-    # and not using PYTHONENV and instead copies pyspark out like Spark 3.y.z
-    DOCKERFILE_BASE="../overrides/base/2.4.z/Dockerfile"
-    DOCKERFILE_PY="../overrides/python/2.4.z/Dockerfile"
-else
-    DOCKERFILE_BASE="./resource-managers/kubernetes/docker/src/main/dockerfiles/spark/Dockerfile"
-    DOCKERFILE_PY="./resource-managers/kubernetes/docker/src/main/dockerfiles/spark/bindings/python/Dockerfile"
-fi
+DOCKERFILE_BASE="./resource-managers/kubernetes/docker/src/main/dockerfiles/spark/Dockerfile"
+DOCKERFILE_PY="./resource-managers/kubernetes/docker/src/main/dockerfiles/spark/bindings/python/Dockerfile"
 
 if [[ ${SPARK_MAJOR_VERSION} -eq 3 && ${SPARK_MINOR_VERSION} -ge 4 ]]; then  # >=3.4
     # From Spark v3.4.0 onwards, openjdk is not the prefered base image source as it i
     # deprecated and taken over by eclipse-temurin. slim-buster variants are not available
     # on eclipse-temurin at the moment.
-    IMAGE_VARIANT="jre"
+    IMAGE_VARIANT="jre-focal"
 else
     IMAGE_VARIANT="jre-slim-buster"
 fi
 
-# Temporarily remove R build due to keyserver issue
-# DOCKERFILE_R="./resource-managers/kubernetes/docker/src/main/dockerfiles/R/Dockerfile"
-
 SPARK_LABEL="${SPARK_VERSION}"
 TAG_NAME="${SELF_VERSION}_${SPARK_LABEL}_hadoop-${HADOOP_VERSION}_scala-${SCALA_VERSION}_java-${JAVA_VERSION}"
 
-# ./bin/docker-image-tool.sh \
-#     -b java_image_tag=${JAVA_VERSION}-jre-slim-buster \
-#     -r "${IMAGE_NAME}" \
-#     -t "${TAG_NAME}" \
-#     -f "${DOCKERFILE_BASE}" \
-#     -p "${DOCKERFILE_PY}" \
-#     -R "${DOCKERFILE_R}" \
-#     build
-
 ./bin/docker-image-tool.sh \
     -b java_image_tag=${JAVA_VERSION}-${IMAGE_VARIANT} \
     -r "${IMAGE_NAME}" \
@@ -101,6 +69,5 @@ TAG_NAME="${SELF_VERSION}_${SPARK_LABEL}_hadoop-${HADOOP_VERSION}_scala-${SCALA_
 
 docker tag "${IMAGE_NAME}/spark:${TAG_NAME}" "${IMAGE_NAME}:${TAG_NAME}"
 docker tag "${IMAGE_NAME}/spark-py:${TAG_NAME}" "${IMAGE_NAME}-py:${TAG_NAME}"
-# docker tag "${IMAGE_NAME}/spark-r:${TAG_NAME}" "${IMAGE_NAME}-r:${TAG_NAME}"
 
 popd >/dev/null

push-images.sh

@@ -11,21 +11,10 @@ else
 fi
 
 TAG_NAME="${SELF_VERSION}_${SPARK_LABEL}_hadoop-${HADOOP_VERSION}_scala-${SCALA_VERSION}_java-${JAVA_VERSION}"
-ALT_TAG_NAME="${SPARK_LABEL}_hadoop-${HADOOP_VERSION}_scala-${SCALA_VERSION}_java-${JAVA_VERSION}"
 
 docker tag "${IMAGE_NAME}:${TAG_NAME}" "${IMAGE_ORG}/${IMAGE_NAME}:${TAG_NAME}"
 docker push "${IMAGE_ORG}/${IMAGE_NAME}:${TAG_NAME}"
-docker tag "${IMAGE_NAME}:${TAG_NAME}" "${IMAGE_ORG}/${IMAGE_NAME}:${ALT_TAG_NAME}"
-docker push "${IMAGE_ORG}/${IMAGE_NAME}:${ALT_TAG_NAME}"
 
 # Python image push
 docker tag "${IMAGE_NAME}-py:${TAG_NAME}" "${IMAGE_ORG}/${IMAGE_NAME}-py:${TAG_NAME}"
 docker push "${IMAGE_ORG}/${IMAGE_NAME}-py:${TAG_NAME}"
-docker tag "${IMAGE_NAME}-py:${TAG_NAME}" "${IMAGE_ORG}/${IMAGE_NAME}-py:${ALT_TAG_NAME}"
-docker push "${IMAGE_ORG}/${IMAGE_NAME}-py:${ALT_TAG_NAME}"
-
-# R image push
-# docker tag "${IMAGE_NAME}-r:${TAG_NAME}" "${IMAGE_ORG}/${IMAGE_NAME}-r:${TAG_NAME}"
-# docker push "${IMAGE_ORG}/${IMAGE_NAME}-r:${TAG_NAME}"
-# docker tag "${IMAGE_NAME}-r:${TAG_NAME}" "${IMAGE_ORG}/${IMAGE_NAME}-r:${ALT_TAG_NAME}"
-# docker push "${IMAGE_ORG}/${IMAGE_NAME}-r:${ALT_TAG_NAME}"

templates/vars.yml

@@ -1,4 +1,4 @@
-self_version: 'v3'
+self_version: 'v4'
 
 versions:
 - spark:  ['3.1.3']
@@ -19,4 +19,9 @@ versions:
 - spark:  ['3.4.1']
   java:   ['8', '11']
   hadoop: ['3.3.4']
+  scala:  ['2.12', '2.13']
+
+- spark:  ['3.5.1']	
+  java:   ['8', '11', '17']	
+  hadoop: ['3.3.4', '3.3.6']	
   scala:  ['2.12', '2.13']