ARROW-17451: [CI][Java] Use manylinux2014 image for JNI (apache#13920)

Because our official .jar packages are built in manylinux2014 image. Authored-by: Sutou Kouhei <[email protected]> Signed-off-by: Sutou Kouhei <[email protected]>
zagto · Oct 7, 2022 · bd02afa · bd02afa
1 parent 42943ab
commit bd02afa
Show file tree

Hide file tree

Showing 9 changed files with 87 additions and 63 deletions.
diff --git a/.github/workflows/java_jni.yml b/.github/workflows/java_jni.yml
@@ -47,7 +47,7 @@ env:
 jobs:
 
   docker:
-    name: AMD64 Debian 9 Java JNI (Gandiva, Plasma, ORC, Dataset)
+    name: AMD64 manylinux2014 Java JNI
     runs-on: ubuntu-latest
     if: ${{ !contains(github.event.pull_request.title, 'WIP') }}
     timeout-minutes: 90
@@ -61,23 +61,23 @@ jobs:
         uses: actions/cache@v2
         with:
           path: .docker
-          key: maven-${{ hashFiles('java/**') }}
-          restore-keys: maven-
+          key: java-jni-manylinux-2014-${{ hashFiles('cpp/**', 'java/**') }}
+          restore-keys: java-jni-manylinux-2014-
       - name: Setup Python
         uses: actions/setup-python@v4
         with:
           python-version: 3.8
       - name: Setup Archery
         run: pip install -e dev/archery[docker]
       - name: Execute Docker Build
-        run: archery docker run debian-java-jni
+        run: archery docker run java-jni-manylinux-2014
       - name: Docker Push
         if: success() && github.event_name == 'push' && github.repository == 'apache/arrow'
         continue-on-error: true
-        run: archery docker push debian-java-jni
+        run: archery docker push java-jni-manylinux-2014
 
   docker_integration_python:
-    name: AMD64 Debian 9 Java C Data Interface Integration
+    name: AMD64 Conda Java C Data Interface Integration
     runs-on: ubuntu-latest
     if: ${{ !contains(github.event.pull_request.title, 'WIP') }}
     timeout-minutes: 90

diff --git a/ci/docker/java-jni-manylinux-201x.dockerfile b/ci/docker/java-jni-manylinux-201x.dockerfile
@@ -33,5 +33,13 @@ RUN vcpkg install \
 
 # Install Java
 ARG java=1.8.0
-RUN yum install -y java-$java-openjdk-devel && yum clean all
+RUN yum install -y java-$java-openjdk-devel rh-maven35 && yum clean all
 ENV JAVA_HOME=/usr/lib/jvm/java-$java-openjdk/
+
+# For ci/scripts/java_*.sh
+ENV ARROW_GANDIVA_JAVA=ON \
+    ARROW_HOME=/tmp/local \
+    ARROW_JAVA_CDATA=ON \
+    ARROW_JNI=ON \
+    ARROW_PLASMA=ON \
+    ARROW_USE_CCACHE=ON
diff --git a/ci/scripts/java_build.sh b/ci/scripts/java_build.sh
@@ -18,10 +18,13 @@
 
 set -ex
 
+if [[ "${ARROW_JAVA_BUILD:-ON}" != "ON" ]]; then
+  exit
+fi
+
 arrow_dir=${1}
 source_dir=${1}/java
 build_dir=${2}
-cpp_build_dir=${build_dir}/cpp/${ARROW_BUILD_TYPE:-debug}
 java_jni_dist_dir=${3}
 
 : ${BUILD_DOCS_JAVA:=OFF}
@@ -85,7 +88,7 @@ if [ "${ARROW_JAVA_CDATA}" = "ON" ]; then
 fi
 
 if [ "${ARROW_GANDIVA_JAVA}" = "ON" ]; then
-  ${mvn} -Darrow.cpp.build.dir=${cpp_build_dir} -Parrow-jni install
+  ${mvn} -Darrow.cpp.build.dir=${java_jni_dist_dir} -Parrow-jni install
 fi
 
 if [ "${ARROW_PLASMA}" = "ON" ]; then

diff --git a/ci/scripts/java_jni_macos_build.sh b/ci/scripts/java_jni_macos_build.sh
@@ -29,6 +29,7 @@ echo "=== Clear output directories and leftovers ==="
 rm -rf ${build_dir}
 
 echo "=== Building Arrow C++ libraries ==="
+install_dir=${build_dir}/cpp-install
 : ${ARROW_BUILD_TESTS:=OFF}
 : ${ARROW_DATASET:=ON}
 : ${ARROW_FILESYSTEM:=ON}
@@ -40,9 +41,15 @@ echo "=== Building Arrow C++ libraries ==="
 : ${ARROW_PLASMA:=ON}
 : ${ARROW_PYTHON:=OFF}
 : ${ARROW_S3:=ON}
+: ${ARROW_USE_CCACHE:=OFF}
 : ${CMAKE_BUILD_TYPE:=Release}
 : ${CMAKE_UNITY_BUILD:=ON}
 
+if [ "${ARROW_USE_CCACHE}" == "ON" ]; then
+  echo "=== ccache statistics before build ==="
+  ccache -s
+fi
+
 export ARROW_TEST_DATA="${arrow_dir}/testing/data"
 export PARQUET_TEST_DATA="${arrow_dir}/cpp/submodules/parquet-testing/data"
 export AWS_EC2_METADATA_DISABLED=TRUE
@@ -75,12 +82,13 @@ cmake \
   -DARROW_S3=${ARROW_S3} \
   -DARROW_SNAPPY_USE_SHARED=OFF \
   -DARROW_THRIFT_USE_SHARED=OFF \
+  -DARROW_USE_CCACHE=${ARROW_USE_CCACHE} \
   -DARROW_UTF8PROC_USE_SHARED=OFF \
   -DARROW_ZSTD_USE_SHARED=OFF \
   -DAWSSDK_SOURCE=BUNDLED \
   -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE} \
   -DCMAKE_INSTALL_LIBDIR=lib \
-  -DCMAKE_INSTALL_PREFIX=${build_dir}/cpp \
+  -DCMAKE_INSTALL_PREFIX=${install_dir} \
   -DCMAKE_UNITY_BUILD=${CMAKE_UNITY_BUILD} \
   -DPARQUET_BUILD_EXAMPLES=OFF \
   -DPARQUET_BUILD_EXECUTABLES=OFF \
@@ -102,12 +110,17 @@ ${arrow_dir}/ci/scripts/java_jni_build.sh \
   ${build_dir} \
   ${dist_dir}
 
+if [ "${ARROW_USE_CCACHE}" == "ON" ]; then
+  echo "=== ccache statistics after build ==="
+  ccache -s
+fi
 
 echo "=== Copying libraries to the distribution folder ==="
 mkdir -p "${dist_dir}"
-cp -L ${build_dir}/cpp/lib/libgandiva_jni.dylib ${dist_dir}
-cp -L ${build_dir}/cpp/lib/libarrow_dataset_jni.dylib ${dist_dir}
-cp -L ${build_dir}/cpp/lib/libarrow_orc_jni.dylib ${dist_dir}
+cp -L ${install_dir}/lib/libarrow_dataset_jni.dylib ${dist_dir}
+cp -L ${install_dir}/lib/libarrow_orc_jni.dylib ${dist_dir}
+cp -L ${install_dir}/lib/libgandiva_jni.dylib ${dist_dir}
+cp -L ${build_dir}/cpp/*/libplasma_java.dylib ${dist_dir}
 
 echo "=== Checking shared dependencies for libraries ==="
 
@@ -122,9 +135,11 @@ archery linking check-dependencies \
   --allow libcurl \
   --allow libgandiva_jni \
   --allow libncurses \
+  --allow libplasma_java \
   --allow libz \
   libarrow_cdata_jni.dylib \
   libarrow_dataset_jni.dylib \
   libarrow_orc_jni.dylib \
-  libgandiva_jni.dylib
+  libgandiva_jni.dylib \
+  libplasma_java.dylib
 popd
diff --git a/ci/scripts/java_jni_manylinux_build.sh b/ci/scripts/java_jni_manylinux_build.sh
@@ -32,6 +32,7 @@ echo "=== Building Arrow C++ libraries ==="
 devtoolset_version=$(rpm -qa "devtoolset-*-gcc" --queryformat %{VERSION} | \
                        grep -o "^[0-9]*")
 devtoolset_include_cpp="/opt/rh/devtoolset-${devtoolset_version}/root/usr/include/c++/${devtoolset_version}"
+: ${ARROW_BUILD_TESTS:=OFF}
 : ${ARROW_DATASET:=ON}
 : ${ARROW_GANDIVA:=ON}
 : ${ARROW_GANDIVA_JAVA:=ON}
@@ -44,14 +45,19 @@ devtoolset_include_cpp="/opt/rh/devtoolset-${devtoolset_version}/root/usr/includ
 : ${ARROW_PLASMA_JAVA_CLIENT:=ON}
 : ${ARROW_PYTHON:=OFF}
 : ${ARROW_S3:=ON}
-: ${ARROW_BUILD_TESTS:=OFF}
+: ${ARROW_USE_CCACHE:=OFF}
 : ${CMAKE_BUILD_TYPE:=Release}
 : ${CMAKE_UNITY_BUILD:=ON}
 : ${VCPKG_ROOT:=/opt/vcpkg}
 : ${VCPKG_FEATURE_FLAGS:=-manifests}
 : ${VCPKG_TARGET_TRIPLET:=${VCPKG_DEFAULT_TRIPLET:-x64-linux-static-${CMAKE_BUILD_TYPE}}}
 : ${GANDIVA_CXX_FLAGS:=-isystem;${devtoolset_include_cpp};-isystem;${devtoolset_include_cpp}/x86_64-redhat-linux;-isystem;-lpthread}
 
+if [ "${ARROW_USE_CCACHE}" == "ON" ]; then
+  echo "=== ccache statistics before build ==="
+  ccache -s
+fi
+
 export ARROW_TEST_DATA="${arrow_dir}/testing/data"
 export PARQUET_TEST_DATA="${arrow_dir}/cpp/submodules/parquet-testing/data"
 export AWS_EC2_METADATA_DISABLED=TRUE
@@ -87,11 +93,12 @@ cmake \
   -DARROW_S3=${ARROW_S3} \
   -DARROW_SNAPPY_USE_SHARED=OFF \
   -DARROW_THRIFT_USE_SHARED=OFF \
+  -DARROW_USE_CCACHE=${ARROW_USE_CCACHE} \
   -DARROW_UTF8PROC_USE_SHARED=OFF \
   -DARROW_ZSTD_USE_SHARED=OFF \
   -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE} \
   -DCMAKE_INSTALL_LIBDIR=lib \
-  -DCMAKE_INSTALL_PREFIX=${build_dir}/cpp \
+  -DCMAKE_INSTALL_PREFIX=${ARROW_HOME} \
   -DCMAKE_UNITY_BUILD=${CMAKE_UNITY_BUILD} \
   -DORC_SOURCE=BUNDLED \
   -DORC_PROTOBUF_EXECUTABLE=${VCPKG_ROOT}/installed/${VCPKG_TARGET_TRIPLET}/tools/protobuf/protoc \
@@ -126,11 +133,17 @@ ${arrow_dir}/ci/scripts/java_jni_build.sh \
   ${build_dir} \
   ${dist_dir}
 
+if [ "${ARROW_USE_CCACHE}" == "ON" ]; then
+  echo "=== ccache statistics after build ==="
+  ccache -s
+fi
+
 
 echo "=== Copying libraries to the distribution folder ==="
-cp -L ${build_dir}/cpp/lib/libgandiva_jni.so ${dist_dir}
-cp -L ${build_dir}/cpp/lib/libarrow_dataset_jni.so ${dist_dir}
-cp -L ${build_dir}/cpp/lib/libarrow_orc_jni.so ${dist_dir}
+cp -L ${ARROW_HOME}/lib/libarrow_dataset_jni.so ${dist_dir}
+cp -L ${ARROW_HOME}/lib/libarrow_orc_jni.so ${dist_dir}
+cp -L ${ARROW_HOME}/lib/libgandiva_jni.so ${dist_dir}
+cp -L ${build_dir}/cpp/*/libplasma_java.so ${dist_dir}
 
 echo "=== Checking shared dependencies for libraries ==="
 
@@ -149,5 +162,6 @@ archery linking check-dependencies \
   libarrow_cdata_jni.so \
   libarrow_dataset_jni.so \
   libarrow_orc_jni.so \
-  libgandiva_jni.so
+  libgandiva_jni.so \
+  libplasma_java.so
 popd
diff --git a/ci/scripts/java_test.sh b/ci/scripts/java_test.sh
@@ -18,9 +18,12 @@
 
 set -ex
 
+if [[ "${ARROW_JAVA_TEST:-ON}" != "ON" ]]; then
+  exit
+fi
+
 arrow_dir=${1}
 source_dir=${1}/java
-cpp_build_dir=${2}/cpp/${ARROW_BUILD_TYPE:-debug}
 java_jni_dist_dir=${3}
 
 # For JNI and Plasma tests
@@ -36,7 +39,7 @@ pushd ${source_dir}
 ${mvn} test
 
 if [ "${ARROW_JNI}" = "ON" ]; then
-  ${mvn} test -Parrow-jni -pl adapter/orc,gandiva,dataset -Darrow.cpp.build.dir=${cpp_build_dir}
+  ${mvn} test -Parrow-jni -pl adapter/orc,gandiva,dataset -Darrow.cpp.build.dir=${java_jni_dist_dir}
 fi
 
 if [ "${ARROW_JAVA_CDATA}" = "ON" ]; then
@@ -46,7 +49,7 @@ fi
 if [ "${ARROW_PLASMA}" = "ON" ]; then
   pushd ${source_dir}/plasma
   java -cp target/test-classes:target/classes \
-       -Djava.library.path=${cpp_build_dir} \
+       -Djava.library.path=${java_jni_dist_dir} \
        org.apache.arrow.plasma.PlasmaClientTest
   popd
 fi

diff --git a/cpp/src/plasma/CMakeLists.txt b/cpp/src/plasma/CMakeLists.txt
@@ -185,14 +185,14 @@ if(ARROW_PLASMA_JAVA_CLIENT)
 
   if(APPLE)
     target_link_libraries(plasma_java
-                          plasma_shared
-                          ${PLASMA_LINK_LIBS}
+                          plasma_static
+                          ${PLASMA_STATIC_LINK_LIBS}
                           "-undefined dynamic_lookup"
                           ${PTHREAD_LIBRARY})
-  else(APPLE)
-    target_link_libraries(plasma_java plasma_shared ${PLASMA_LINK_LIBS}
+  else()
+    target_link_libraries(plasma_java plasma_static ${PLASMA_STATIC_LINK_LIBS}
                           ${PTHREAD_LIBRARY})
-  endif(APPLE)
+  endif()
 endif()
 #
 # Unit tests

diff --git a/dev/tasks/java-jars/github.yml b/dev/tasks/java-jars/github.yml
@@ -28,7 +28,11 @@ jobs:
       {{ macros.github_checkout_arrow()|indent }}
       {{ macros.github_install_archery()|indent }}
       - name: Build C++ Libs
-        run: archery docker run java-jni-manylinux-2014
+        run: |
+          archery docker run \
+            -e ARROW_JAVA_BUILD=OFF \
+            -e ARROW_JAVA_TEST=OFF \
+            java-jni-manylinux-2014
       - name: Compress into single artifact to keep directory structure
         run: tar -cvzf arrow-shared-libs-linux.tar.gz arrow/java-dist/
       - name: Upload Artifacts
@@ -61,6 +65,9 @@ jobs:
           # aws-sdk-cpp and bundled aws-sdk-cpp. We uninstall Homebrew's
           # aws-sdk-cpp to ensure using only bundled aws-sdk-cpp.
           brew uninstall aws-sdk-cpp
+      - name: Setup ccache
+        run: |
+          arrow/ci/scripts/ccache_setup.sh
       - name: Build C++ Libs
         run: |
           set -e
@@ -100,11 +107,13 @@ jobs:
           test -f arrow/java-dist/libarrow_cdata_jni.dylib
           test -f arrow/java-dist/libarrow_dataset_jni.dylib
           test -f arrow/java-dist/libgandiva_jni.dylib
+          test -f arrow/java-dist/libplasma_java.dylib
           test -f arrow/java-dist/libarrow_orc_jni.dylib
           test -f arrow/java-dist/libarrow_cdata_jni.so
           test -f arrow/java-dist/libarrow_dataset_jni.so
           test -f arrow/java-dist/libarrow_orc_jni.so
           test -f arrow/java-dist/libgandiva_jni.so
+          test -f arrow/java-dist/libplasma_java.so
       - name: Build Bundled Jar
         run: |
           set -e

diff --git a/docker-compose.yml b/docker-compose.yml
@@ -122,7 +122,6 @@ x-hierarchy:
     - debian-go-cgo
     - debian-go-cgo-python
   - debian-java
-  - debian-java-jni
   - debian-js
   - fedora-cpp:
     - fedora-python
@@ -999,10 +998,14 @@ services:
       <<: *ccache
     volumes:
       - .:/arrow:delegated
+      - ${DOCKER_VOLUME_PREFIX}maven-cache:/root/.m2:delegated
       - ${DOCKER_VOLUME_PREFIX}python-wheel-manylinux2014-ccache:/ccache:delegated
     command:
-      ["pip install -e /arrow/dev/archery &&
-        /arrow/ci/scripts/java_jni_manylinux_build.sh /arrow /build /arrow/java-dist"]
+      ["pip install -e /arrow/dev/archery && \
+        /arrow/ci/scripts/java_jni_manylinux_build.sh /arrow /build /arrow/java-dist && \
+        source /opt/rh/rh-maven35/enable && \
+        /arrow/ci/scripts/java_build.sh /arrow /build /arrow/java-dist && \
+        /arrow/ci/scripts/java_test.sh /arrow /build /arrow/java-dist"]
 
   ##############################  Integration #################################
 
@@ -1541,37 +1544,6 @@ services:
         /arrow/ci/scripts/java_build.sh /arrow /build &&
         /arrow/ci/scripts/java_test.sh /arrow /build"
 
-  debian-java-jni:
-    # Includes plasma test, jni for gandiva and orc, and C data interface.
-    # Usage:
-    #   docker-compose build debian-java
-    #   docker-compose build debian-java-jni
-    #   docker-compose run debian-java-jni
-    image: ${REPO}:${ARCH}-debian-9-java-${JDK}-maven-${MAVEN}-jni
-    build:
-      context: .
-      dockerfile: ci/docker/linux-apt-jni.dockerfile
-      cache_from:
-        - ${REPO}:${ARCH}-debian-9-java-${JDK}-maven-${MAVEN}-jni
-      args:
-        llvm: ${LLVM}
-    shm_size: *shm-size
-    environment:
-      <<: *ccache
-      ARROW_BUILD_TESTS: "OFF"
-      ARROW_S3: "OFF"
-      ARROW_SUBSTRAIT: "OFF"
-    volumes:
-      - .:/arrow:delegated
-      - ${DOCKER_VOLUME_PREFIX}maven-cache:/root/.m2:delegated
-      - ${DOCKER_VOLUME_PREFIX}debian-ccache:/ccache:delegated
-    command:
-      /bin/bash -c "
-        /arrow/ci/scripts/cpp_build.sh /arrow /build &&
-        /arrow/ci/scripts/java_jni_build.sh /arrow /build /tmp/java_dist &&
-        /arrow/ci/scripts/java_build.sh /arrow /build /tmp/java_dist &&
-        /arrow/ci/scripts/java_test.sh /arrow /build /tmp/java_dist"
-
   oracle-java:
     # Usage:
     #   docker-compose build oracle-java