Enable ccache for interactive builds (#229)

Reattempting reverted #225 This PR enables `ccache` in build-in-docker script by default, closes #222. A repeated no-change build with the native build dir cleaned is ~90 seconds A repeated no-change build without removing the native build dir is ~30 seconds The PR proposes to change the default to not skipping the clean of libcudf build unless CCACHE_DISABLE=1 is set. Manual override of `libcudf.clean.skip` is honored. Signed-off-by: Gera Shegalov <[email protected]>
NVIDIA · May 11, 2022 · da09bad · da09bad
1 parent a0e0657
commit da09bad
Show file tree

Hide file tree

Showing 3 changed files with 55 additions and 8 deletions.
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
@@ -49,9 +49,12 @@ so it should be invoked as one would invoke Maven, e.g.: `build/build-in-docker
 ### cudf Submodule and Build
 
 [RAPIDS cuDF](https://github.com/rapidsai/cudf) is being used as a submodule in this project.
-Due to the lengthy build of libcudf, it is **not cleaned** during a normal Maven clean phase.
-Use `-Dlibcudf.clean.skip=true` to clean the libcudf build area in addition to the normal clean
-of `target/` directories.
+Due to the lengthy build of libcudf, it is **not cleaned** during a normal Maven clean phase
+unless built using `build/build-in-docker`. `build/build-in-docker` uses `ccache` by default
+unless CCACHE_DISABLE=1 is set in the environment.
+
+`-Dlibcudf.clean.skip=false` can also be specified on the Maven command-line to force
+libcudf to be cleaned during the Maven clean phase.
 
 Currently libcudf is only configured once and the build relies on cmake to re-configure as needed.
 This is because libcudf currently is rebuilding almost entirely when it is configured with the same

diff --git a/build/build-in-docker b/build/build-in-docker
@@ -27,33 +27,57 @@ REPODIR=$SCRIPTDIR/..
 CMAKE_GENERATOR=${CMAKE_GENERATOR:-Ninja}
 CUDA_VERSION=${CUDA_VERSION:-11.5.0}
 DOCKER_CMD=${DOCKER_CMD:-nvidia-docker}
+LOCAL_CCACHE_DIR=${LOCAL_CCACHE_DIR:-"$HOME/.ccache"}
 LOCAL_MAVEN_REPO=${LOCAL_MAVEN_REPO:-"$HOME/.m2/repository"}
 PER_THREAD_DEFAULT_STREAM=${PER_THREAD_DEFAULT_STREAM:-ON}
 USE_GDS=${USE_GDS:-ON}
 
 SPARK_IMAGE_NAME="spark-rapids-jni-build:${CUDA_VERSION}-devel-centos7"
 WORKSPACE_DIR=/rapids
 WORKSPACE_REPODIR="$WORKSPACE_DIR/spark-rapids-jni"
+WORKSPACE_CCACHE_REPODIR="$WORKSPACE_DIR/.ccache"
 WORKSPACE_MAVEN_REPODIR="$WORKSPACE_DIR/.m2/repository"
 
 if (( $# == 0 )); then
   echo "Usage: $0 <Maven build arguments>"
   exit 1
 fi
 
+# ensure directories exist
+mkdir -p "$LOCAL_CCACHE_DIR" "$LOCAL_MAVEN_REPO"
+
 $DOCKER_CMD build -f $REPODIR/ci/Dockerfile \
   --build-arg CUDA_VERSION=$CUDA_VERSION \
   -t $SPARK_IMAGE_NAME \
   $REPODIR/build
 
+_CUDF_CLEAN_SKIP=""
+# if ccache is enabled and libcudf.clean.skip not provided
+# by the user remove the cpp build directory
+#
+if [[ "$CCACHE_DISABLE" != "1" ]]; then
+  if [[ ! "$*" =~ " -Dlibcudf.clean.skip=" ]]; then
+    # Don't skip clean if ccache is enabled
+    # unless the user overrides
+    _CUDF_CLEAN_SKIP="-Dlibcudf.clean.skip=false"
+  fi
+fi
+
 $DOCKER_CMD run -it -u $(id -u):$(id -g) --rm \
   -v "/etc/group:/etc/group:ro" \
   -v "/etc/passwd:/etc/passwd:ro" \
   -v "/etc/shadow:/etc/shadow:ro" \
   -v "/etc/sudoers.d:/etc/sudoers.d:ro" \
   -v "$REPODIR:$WORKSPACE_REPODIR:rw" \
+  -v "$LOCAL_CCACHE_DIR:$WORKSPACE_CCACHE_REPODIR:rw" \
   -v "$LOCAL_MAVEN_REPO:$WORKSPACE_MAVEN_REPODIR:rw" \
   --workdir "$WORKSPACE_REPODIR" \
+  -e CCACHE_DISABLE \
+  -e CCACHE_DIR="$WORKSPACE_CCACHE_REPODIR" \
+  -e CMAKE_C_COMPILER_LAUNCHER="ccache" \
+  -e CMAKE_CXX_COMPILER_LAUNCHER="ccache" \
+  -e CMAKE_CUDA_COMPILER_LAUNCHER="ccache" \
+  -e CMAKE_CXX_LINKER_LAUNCHER="ccache" \
   -e CMAKE_GENERATOR="$CMAKE_GENERATOR" \
   -e CUDA_VISIBLE_DEVICES \
   -e PARALLEL_LEVEL \
@@ -63,4 +87,5 @@ $DOCKER_CMD run -it -u $(id -u):$(id -g) --rm \
     -Dmaven.repo.local=$WORKSPACE_MAVEN_REPODIR \
     -DPER_THREAD_DEFAULT_STREAM=$PER_THREAD_DEFAULT_STREAM \
     -DUSE_GDS=$USE_GDS \
+    $_CUDF_CLEAN_SKIP \
     $*"
diff --git a/ci/Dockerfile b/ci/Dockerfile
@@ -22,10 +22,10 @@
 ###
 ARG CUDA_VERSION=11.5.0
 FROM gpuci/cuda:$CUDA_VERSION-devel-centos7
-
+ARG DEVTOOLSET_VERSION=9
 ### Install basic requirements
 RUN yum install -y centos-release-scl
-RUN yum install -y devtoolset-9 rh-python38 epel-release
+RUN yum install -y devtoolset-${DEVTOOLSET_VERSION} rh-python38 epel-release
 RUN yum install -y zlib-devel maven tar wget patch ninja-build
 # require git 2.18+ to keep consistent submodule operations
 RUN yum -y install https://packages.endpointdev.com/rhel/7/os/x86_64/endpoint-repo.x86_64.rpm && yum install -y git
@@ -34,14 +34,33 @@ RUN scl enable rh-python38 "pip install requests"
 ## pre-create the CMAKE_INSTALL_PREFIX folder, set writable by any user for Jenkins
 RUN mkdir /usr/local/rapids && mkdir /rapids && chmod 777 /usr/local/rapids && chmod 777 /rapids
 
-ARG CMAKE_VERSION=3.20.5
-RUN cd /usr/local/ && wget --quiet https://github.com/Kitware/CMake/releases/download/v${CMAKE_VERSION}/cmake-${CMAKE_VERSION}-linux-x86_64.tar.gz && \
+# 3.22.3: CUDA architecture 'native' support + flexible CMAKE_<LANG>_*_LAUNCHER for ccache
+ARG CMAKE_VERSION=3.22.3
+
+RUN cd /usr/local && wget --quiet https://github.com/Kitware/CMake/releases/download/v${CMAKE_VERSION}/cmake-${CMAKE_VERSION}-linux-x86_64.tar.gz && \
    tar zxf cmake-${CMAKE_VERSION}-linux-x86_64.tar.gz && \
    rm cmake-${CMAKE_VERSION}-linux-x86_64.tar.gz
 ENV PATH /usr/local/cmake-${CMAKE_VERSION}-linux-x86_64/bin:$PATH
 
+# ccache for interactive builds
+ARG CCACHE_VERSION=4.6
+RUN cd /tmp && wget --quiet https://github.com/ccache/ccache/releases/download/v${CCACHE_VERSION}/ccache-${CCACHE_VERSION}.tar.gz && \
+   tar zxf ccache-${CCACHE_VERSION}.tar.gz && \
+   rm ccache-${CCACHE_VERSION}.tar.gz && \
+   cd ccache-${CCACHE_VERSION} && \
+   mkdir build && \
+   cd build && \
+   scl enable devtoolset-${DEVTOOLSET_VERSION} \
+      "cmake .. \
+         -DCMAKE_BUILD_TYPE=Release \
+         -DZSTD_FROM_INTERNET=ON \
+         -DREDIS_STORAGE_BACKEND=OFF && \
+      cmake --build . --parallel ${PARALLEL_LEVEL} --target install" && \
+   cd ../.. && \
+   rm -rf ccache-${CCACHE_VERSION}
+
 ## install a version of boost that is needed for arrow/parquet to work
-RUN cd /usr/local && wget https://boostorg.jfrog.io/artifactory/main/release/1.79.0/source/boost_1_79_0.tar.gz && \
+RUN cd /usr/local && wget --quiet https://boostorg.jfrog.io/artifactory/main/release/1.79.0/source/boost_1_79_0.tar.gz && \
   tar -xzf boost_1_79_0.tar.gz && \
   rm boost_1_79_0.tar.gz && \
   cd boost_1_79_0 && \