[BLOCKING][CI] Upgrade to Spark 2.4.3 (#4414)

* [CI] Upgrade to Spark 2.4.2

* Pass Spark version to build script

* Allow multiple --build-arg in ci_build.sh

* Fix syntax

* Fix container name

* Update pom.xml

* Fix container name

* Update Jenkinsfile

* Update pom.xml

* Update Dockerfile.jvm_cross

Jenkinsfile

@@ -58,7 +58,7 @@ pipeline {
             'build-gpu-cuda8.0': { BuildCUDA(cuda_version: '8.0') },
             'build-gpu-cuda9.2': { BuildCUDA(cuda_version: '9.2') },
             'build-gpu-cuda10.0': { BuildCUDA(cuda_version: '10.0') },
-            'build-jvm-packages': { BuildJVMPackages(spark_version: '2.4.1') },
+            'build-jvm-packages': { BuildJVMPackages(spark_version: '2.4.3') },
             'build-jvm-doc': { BuildJVMDoc() }
           ])
         }
@@ -77,7 +77,7 @@ pipeline {
             'test-python-mgpu-cuda10.0': { TestPythonGPU(cuda_version: '10.0', multi_gpu: true) },
             'test-cpp-gpu': { TestCppGPU(cuda_version: '10.0') },
             'test-cpp-mgpu': { TestCppGPU(cuda_version: '10.0', multi_gpu: true) },
-            'test-jvm-jdk8': { CrossTestJVMwithJDK(jdk_version: '8') },
+            'test-jvm-jdk8': { CrossTestJVMwithJDK(jdk_version: '8', spark_version: '2.4.3') },
             'test-jvm-jdk11': { CrossTestJVMwithJDK(jdk_version: '11') },
             'test-jvm-jdk12': { CrossTestJVMwithJDK(jdk_version: '12') },
             'test-r-3.4.4': { TestR(use_r35: false) },
@@ -213,7 +213,7 @@ def BuildJVMPackages(args) {
     // Use only 4 CPU cores
     def docker_extra_params = "CI_DOCKER_EXTRA_PARAMS_INIT='--cpuset-cpus 0-3'"
     sh """
-    ${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_jvm_packages.sh
+    ${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/build_jvm_packages.sh ${args.spark_version}
     """
     echo 'Stashing XGBoost4J JAR...'
     stash name: 'xgboost4j_jar', includes: 'jvm-packages/xgboost4j/target/*.jar,jvm-packages/xgboost4j-spark/target/*.jar,jvm-packages/xgboost4j-example/target/*.jar'
@@ -299,12 +299,17 @@ def CrossTestJVMwithJDK(args) {
   node('linux && cpu') {
     unstash name: 'xgboost4j_jar'
     unstash name: 'srcs'
-    echo "Test XGBoost4J on a machine with JDK ${args.jdk_version}"
+    if (args.spark_version != null) {
+      echo "Test XGBoost4J on a machine with JDK ${args.jdk_version}, Spark ${args.spark_version}"
+    } else {
+      echo "Test XGBoost4J on a machine with JDK ${args.jdk_version}"
+    }
     def container_type = "jvm_cross"
     def docker_binary = "docker"
-    def docker_args = "--build-arg JDK_VERSION=${args.jdk_version}"
+    def spark_arg = (args.spark_version != null) ? "--build-arg SPARK_VERSION=${args.spark_version}" : ""
-    // Only run integration tests for JDK 8, as Spark doesn't support later JDKs yet
+    def docker_args = "--build-arg JDK_VERSION=${args.jdk_version} ${spark_arg}"
-    def docker_extra_params = (args.jdk_version == '8') ? "CI_DOCKER_EXTRA_PARAMS_INIT='-e RUN_INTEGRATION_TEST=1'" : ""
+    // Run integration tests only when spark_version is given
+    def docker_extra_params = (args.spark_version != null) ? "CI_DOCKER_EXTRA_PARAMS_INIT='-e RUN_INTEGRATION_TEST=1'" : ""
     sh """
     ${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/test_jvm_cross.sh
     """

jvm-packages/pom.xml

@@ -34,7 +34,7 @@
         <maven.compiler.source>1.7</maven.compiler.source>
         <maven.compiler.target>1.7</maven.compiler.target>
         <flink.version>1.5.0</flink.version>
-        <spark.version>2.4.1</spark.version>
+        <spark.version>2.4.3</spark.version>
         <scala.version>2.11.12</scala.version>
         <scala.binary.version>2.11</scala.binary.version>
     </properties>

tests/ci_build/Dockerfile.jvm_cross

@@ -1,5 +1,6 @@
 FROM ubuntu:19.04
 ARG JDK_VERSION=8
+ARG SPARK_VERSION=2.4.3
 
 # Environment
 ENV DEBIAN_FRONTEND noninteractive
@@ -19,9 +20,9 @@ RUN \
     tar xvf apache-maven-3.6.1-bin.tar.gz -C /opt && \
     ln -s /opt/apache-maven-3.6.1/ /opt/maven && \
     # Spark
-    wget https://archive.apache.org/dist/spark/spark-2.4.1/spark-2.4.1-bin-hadoop2.7.tgz && \
+    wget https://archive.apache.org/dist/spark/spark-$SPARK_VERSION/spark-$SPARK_VERSION-bin-hadoop2.7.tgz && \
-    tar xvf spark-2.4.1-bin-hadoop2.7.tgz -C /opt && \
+    tar xvf spark-$SPARK_VERSION-bin-hadoop2.7.tgz -C /opt && \
-    ln -s /opt/spark-2.4.1-bin-hadoop2.7 /opt/spark
+    ln -s /opt/spark-$SPARK_VERSION-bin-hadoop2.7 /opt/spark
 
 ENV PATH=/opt/python/bin:/opt/spark/bin:/opt/maven/bin:$PATH
 

tests/ci_build/build_jvm_packages.sh

@@ -3,13 +3,20 @@
 set -e
 set -x
 
+if [ $# -ne 1 ]; then
+  echo "Usage: $0 [spark version]"
+  exit 1
+fi
+
+spark_version=$1
+
 # Initialize local Maven repository
 ./tests/ci_build/initialize_maven.sh
 
 rm -rf build/
 cd jvm-packages
 
-mvn --no-transfer-progress package
+mvn --no-transfer-progress package -Dspark.version=${spark_version}
 
 set +x
 set +e

tests/ci_build/ci_build.sh

@@ -51,11 +51,11 @@ if [[ "$1" == "-it" ]]; then
     shift 1
 fi
 
-if [[ "$1" == "--build-arg" ]]; then
+while [[ "$1" == "--build-arg" ]]; do
-    CI_DOCKER_BUILD_ARG+="$1"
+    CI_DOCKER_BUILD_ARG+=" $1"
     CI_DOCKER_BUILD_ARG+=" $2"
     shift 2
-fi
+done
 
 if [[ ! -f "${DOCKERFILE_PATH}" ]]; then
     echo "Invalid Dockerfile path: \"${DOCKERFILE_PATH}\""