Improve dependency install and build (facebookincubator#10920)

Summary: https://github.com/facebookincubator/velox/pull/10422/files added additional packages to be installed via brew. When the package versions are updated via brew, it can cause a build failure. See facebookincubator#10886 We must install or bundle fixed/supported versions to avoid this. Allow installed package headers to be picked up before brew/system package headers Add support for DEPENDENCY_DIR and INSTALL_PREFIX. Pull Request resolved: facebookincubator#10920 Reviewed By: kgpai Differential Revision: D62989022 Pulled By: Yuhta fbshipit-source-id: a10faa3212c32d6f9c0e301921a750e3b7142220
spershin · Sep 19, 2024 · 66b5b0d · 66b5b0d
1 parent a8a21a4
commit 66b5b0d
Show file tree

Hide file tree

Showing 10 changed files with 191 additions and 124 deletions.
diff --git a/.github/workflows/macos.yml b/.github/workflows/macos.yml
@@ -54,6 +54,7 @@ jobs:
       CCACHE_DIR: '${{ github.workspace }}/.ccache'
       # The arm runners have only 7GB RAM
       BUILD_TYPE: "${{ matrix.os ==  'macos-14' && 'Release' || 'Debug' }}"
+      INSTALL_PREFIX: "/tmp/deps-install"
     steps:
       - name: Checkout
         uses: actions/checkout@v4
@@ -66,6 +67,7 @@ jobs:
           source scripts/setup-macos.sh
           install_build_prerequisites
           install_velox_deps_from_brew
+          install_double_conversion
 
           echo "NJOBS=`sysctl -n hw.ncpu`" >> $GITHUB_ENV
           brew unlink protobuf || echo "protobuf not installed"

diff --git a/.gitignore b/.gitignore
@@ -49,6 +49,8 @@ projects/*
 !projects/*.*
 !projects/Makefile
 .venv
+deps-install
+deps-download
 
 #==============================================================================#
 # Autotools artifacts

diff --git a/CMakeLists.txt b/CMakeLists.txt
@@ -45,6 +45,14 @@ if(DEFINED ENV{CONDA_PREFIX})
   endif()
 endif()
 
+if(DEFINED ENV{INSTALL_PREFIX})
+  message(STATUS "Dependency install directory set to: $ENV{INSTALL_PREFIX}")
+  list(APPEND CMAKE_PREFIX_PATH "$ENV{INSTALL_PREFIX}")
+  # Allow installed package headers to be picked up before brew/system package
+  # headers
+  include_directories(BEFORE "$ENV{INSTALL_PREFIX}/include")
+endif()
+
 list(PREPEND CMAKE_MODULE_PATH "${PROJECT_SOURCE_DIR}/CMake"
      "${PROJECT_SOURCE_DIR}/CMake/third-party")
 

diff --git a/README.md b/README.md
@@ -85,19 +85,27 @@ dependencies for a given platform.
 ### Setting up dependencies
 
 The following setup scripts use the `DEPENDENCY_DIR` environment variable to set the
-location of the build packages. If you do not set this variable, it will default to
-the current working directory.
+location to download and build packages. This defaults to `deps-download` in the current
+working directory.
 
-```shell
-$ export DEPENDENCY_DIR=/path/to/your/dependencies
-```
+Use `INSTALL_PREFIX` to set the install directory of the packages. This defaults to
+`deps-install` in the current working directory on macOS and to the default install
+location (eg. `/usr/local`) on linux.
+Using the default install location `/usr/local` on macOS is discouraged since this
+location is used by certain Homebrew versions.
+
+Manually add the `INSTALL_PREFIX` value in the IDE or bash environment,
+say `export INSTALL_PREFIX=/Users/$USERNAME/velox/deps-install` to `~/.zshrc` so that
+subsequent Velox builds can use the installed packages.
+
+*You can reuse `DEPENDENCY_INSTALL` and `INSTALL_PREFIX` for Velox clients such as Prestissimo
+by specifying a common shared directory.`*
 
 ### Setting up on macOS
 
-On a MacOS machine (either Intel or Apple silicon) you can setup and then build like so:
+On a macOS machine (either Intel or Apple silicon) you can setup and then build like so:
 
 ```shell
-$ export INSTALL_PREFIX=/Users/$USERNAME/velox/velox_dependency_install
 $ ./scripts/setup-macos.sh
 $ make
 ```
@@ -136,7 +144,7 @@ $ ./scripts/setup-adapters.sh
 $ make
 ```
 
-Note that `setup-adapters.sh` supports MacOS and Ubuntu 20.04 or later.
+Note that `setup-adapters.sh` supports macOS and Ubuntu 20.04 or later.
 
 ### Using Clang on Linux
 

diff --git a/scripts/adapters.dockerfile b/scripts/adapters.dockerfile
@@ -15,6 +15,7 @@
 ARG image=ghcr.io/facebookincubator/velox-dev:centos9
 FROM $image
 
+COPY scripts/setup-helper-functions.sh /
 COPY scripts/setup-adapters.sh /
 RUN mkdir build && ( cd build &&  source /opt/rh/gcc-toolset-12/enable && \
     bash /setup-adapters.sh ) && rm -rf build && dnf remove -y conda && dnf clean all

diff --git a/scripts/setup-adapters.sh b/scripts/setup-adapters.sh
@@ -21,10 +21,14 @@ set -eufx -o pipefail
 
 SCRIPTDIR=$(dirname "${BASH_SOURCE[0]}")
 source $SCRIPTDIR/setup-helper-functions.sh
-DEPENDENCY_DIR=${DEPENDENCY_DIR:-$(pwd)}
+DEPENDENCY_DIR=${DEPENDENCY_DIR:-$(pwd)/deps-download}
 CMAKE_BUILD_TYPE="${BUILD_TYPE:-Release}"
 MACHINE=$(uname -m)
 
+if [[ "$OSTYPE" == darwin* ]]; then
+  export INSTALL_PREFIX=${INSTALL_PREFIX:-"$(pwd)/deps-install"}
+fi
+
 function install_aws_deps {
   local AWS_REPO_NAME="aws/aws-sdk-cpp"
   local AWS_SDK_VERSION="1.11.321"
@@ -40,14 +44,16 @@ function install_aws_deps {
     MINIO_ARCH="amd64"
   fi
   local MINIO_BINARY="minio-2022-05-26"
-  local MINIO_OS="linux"
-  if [[ "$OSTYPE" == darwin* ]]; then
-    # minio will have to approved under the Privacy & Security on MacOS on first use.
-    MINIO_OS="darwin"
+  if [[! -f /usr/local/bin/${MINIO_BINARY} ]]; then
+    local MINIO_OS="linux"
+    if [[ "$OSTYPE" == darwin* ]]; then
+      # minio will have to approved under the Privacy & Security on MacOS on first use.
+      MINIO_OS="darwin"
+    fi
+    wget https://dl.min.io/server/minio/release/${MINIO_OS}-${MINIO_ARCH}/archive/minio.RELEASE.2022-05-26T05-48-41Z -O ${MINIO_BINARY}
+    chmod +x ./${MINIO_BINARY}
+    mv ./${MINIO_BINARY} /usr/local/bin/
   fi
-  wget https://dl.min.io/server/minio/release/${MINIO_OS}-${MINIO_ARCH}/archive/minio.RELEASE.2022-05-26T05-48-41Z -O ${MINIO_BINARY}
-  chmod +x ./${MINIO_BINARY}
-  mv ./${MINIO_BINARY} /usr/local/bin/
 }
 
 function install_gcs-sdk-cpp {
@@ -117,41 +123,51 @@ function install_azure-storage-sdk-cpp {
     sed -i "s/\"version-string\"/\"builtin-baseline\": \"$vcpkg_commit_id\",\"version-string\"/" $azure_core_dir/vcpkg.json
     sed -i "s/\"version-string\"/\"overrides\": [{ \"name\": \"openssl\", \"version-string\": \"$openssl_version\" }],\"version-string\"/" $azure_core_dir/vcpkg.json
   fi
-  cmake_install $azure_core_dir -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE} -DBUILD_SHARED_LIBS=OFF
-
+  (
+    cd $azure_core_dir 
+    cmake_install -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE} -DBUILD_SHARED_LIBS=OFF
+  )
   # install azure-storage-common
-  cmake_install sdk/storage/azure-storage-common -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE} -DBUILD_SHARED_LIBS=OFF
+  (
+    cd sdk/storage/azure-storage-common
+    cmake_install -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE} -DBUILD_SHARED_LIBS=OFF
+  )
 
   # install azure-storage-blobs
-  cmake_install sdk/storage/azure-storage-blobs -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE} -DBUILD_SHARED_LIBS=OFF
-
+  (
+    cd sdk/storage/azure-storage-blobs
+    cmake_install -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE} -DBUILD_SHARED_LIBS=OFF
+  )
   # install azure-storage-files-datalake
-  cmake_install sdk/storage/azure-storage-files-datalake -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE} -DBUILD_SHARED_LIBS=OFF
+  (
+    cd sdk/storage/azure-storage-files-datalake
+    cmake_install -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE} -DBUILD_SHARED_LIBS=OFF
+  )
 }
 
 function install_hdfs_deps {
   github_checkout apache/hawq master
-  libhdfs3_dir=$DEPENDENCY_DIR/hawq/depends/libhdfs3
+  libhdfs3_dir=hawq/depends/libhdfs3
   if [[ "$OSTYPE" == darwin* ]]; then
-     sed -i '' -e "/FIND_PACKAGE(GoogleTest REQUIRED)/d" $libhdfs3_dir/CMakeLists.txt
-     sed -i '' -e "s/dumpversion/dumpfullversion/" $libhdfs3_dir/CMakeLists.txt
+     sed -i '' -e "/FIND_PACKAGE(GoogleTest REQUIRED)/d" $DEPENDENCY_DIR/$libhdfs3_dir/CMakeLists.txt
+     sed -i '' -e "s/dumpversion/dumpfullversion/" $DEPENDENCY_DIR/$libhdfs3_dir/CMakeLists.txt
   fi
 
   if [[ "$OSTYPE" == linux-gnu* ]]; then
-    sed -i "/FIND_PACKAGE(GoogleTest REQUIRED)/d" $libhdfs3_dir/CMakeLists.txt
-    sed -i "s/dumpversion/dumpfullversion/" $libhdfs3_dir/CMake/Platform.cmake
+    sed -i "/FIND_PACKAGE(GoogleTest REQUIRED)/d" $DEPENDENCY_DIR/$libhdfs3_dir/CMakeLists.txt
+    sed -i "s/dumpversion/dumpfullversion/" $DEPENDENCY_DIR/$libhdfs3_dir/CMake/Platform.cmake
     # Dependencies for Hadoop testing
     wget_and_untar https://archive.apache.org/dist/hadoop/common/hadoop-3.3.0/hadoop-3.3.0.tar.gz hadoop
-    cp -a hadoop /usr/local/
+    cp -a ${DEPENDENCY_DIR}/hadoop /usr/local/
     wget -P /usr/local/hadoop/share/hadoop/common/lib/ https://repo1.maven.org/maven2/junit/junit/4.11/junit-4.11.jar
 
     yum install -y java-1.8.0-openjdk-devel
 
   fi
-  cmake_install $libhdfs3_dir
+  cmake_install_dir $libhdfs3_dir
 }
 
-cd "${DEPENDENCY_DIR}" || exit
+(mkdir -p "${DEPENDENCY_DIR}") || exit
 # aws-sdk-cpp missing dependencies
 
 if [[ "$OSTYPE" == "linux-gnu"* ]]; then

diff --git a/scripts/setup-centos9.sh b/scripts/setup-centos9.sh
@@ -36,6 +36,8 @@ export CFLAGS=${CXXFLAGS//"-std=c++17"/} # Used by LZO.
 CMAKE_BUILD_TYPE="${BUILD_TYPE:-Release}"
 BUILD_DUCKDB="${BUILD_DUCKDB:-true}"
 USE_CLANG="${USE_CLANG:-false}"
+export INSTALL_PREFIX=${INSTALL_PREFIX:-"/usr/local"}
+DEPENDENCY_DIR=${DEPENDENCY_DIR:-$(pwd)/deps-download}
 
 FB_OS_VERSION="v2024.05.20.00"
 FMT_VERSION="10.1.1"
@@ -85,19 +87,19 @@ function install_gflags {
   # Remove an older version if present.
   dnf remove -y gflags
   wget_and_untar https://github.com/gflags/gflags/archive/v2.2.2.tar.gz gflags
-  cmake_install gflags -DBUILD_SHARED_LIBS=ON -DBUILD_STATIC_LIBS=ON -DBUILD_gflags_LIB=ON -DLIB_SUFFIX=64
+  cmake_install_dir gflags -DBUILD_SHARED_LIBS=ON -DBUILD_STATIC_LIBS=ON -DBUILD_gflags_LIB=ON -DLIB_SUFFIX=64
 }
 
 function install_glog {
   wget_and_untar https://github.com/google/glog/archive/v0.6.0.tar.gz glog
-  cmake_install glog -DBUILD_SHARED_LIBS=ON
+  cmake_install_dir glog -DBUILD_SHARED_LIBS=ON
 }
 
 function install_lzo {
   wget_and_untar http://www.oberhumer.com/opensource/lzo/download/lzo-2.10.tar.gz lzo
   (
-    cd lzo
-    ./configure --prefix=/usr --enable-shared --disable-static --docdir=/usr/share/doc/lzo-2.10
+    cd ${DEPENDENCY_DIR}/lzo
+    ./configure --prefix=${INSTALL_PREFIX} --enable-shared --disable-static --docdir=/usr/share/doc/lzo-2.10
     make "-j$(nproc)"
     make install
   )
@@ -106,36 +108,36 @@ function install_lzo {
 function install_boost {
   wget_and_untar https://github.com/boostorg/boost/releases/download/${BOOST_VERSION}/${BOOST_VERSION}.tar.gz boost
   (
-    cd boost
+    cd ${DEPENDENCY_DIR}/boost
     if [[ ${USE_CLANG} != "false" ]]; then
-      ./bootstrap.sh --prefix=/usr/local --with-toolset="clang-15"
+      ./bootstrap.sh --prefix=${INSTALL_PREFIX} --with-toolset="clang-15"
       # Switch the compiler from the clang-15 toolset which doesn't exist (clang-15.jam) to
       # clang of version 15 when toolset clang-15 is used.
       # This reconciles the project-config.jam generation with what the b2 build system allows for customization.
       sed -i 's/using clang-15/using clang : 15/g' project-config.jam
       ${SUDO} ./b2 "-j$(nproc)" -d0 install threading=multi toolset=clang-15 --without-python
     else
-      ./bootstrap.sh --prefix=/usr/local
+      ./bootstrap.sh --prefix=${INSTALL_PREFIX}
       ${SUDO} ./b2 "-j$(nproc)" -d0 install threading=multi --without-python
     fi
   )
 }
 
 function install_snappy {
   wget_and_untar https://github.com/google/snappy/archive/1.1.8.tar.gz snappy
-  cmake_install snappy -DSNAPPY_BUILD_TESTS=OFF
+  cmake_install_dir snappy -DSNAPPY_BUILD_TESTS=OFF
 }
 
 function install_fmt {
   wget_and_untar https://github.com/fmtlib/fmt/archive/${FMT_VERSION}.tar.gz fmt
-  cmake_install fmt -DFMT_TEST=OFF
+  cmake_install_dir fmt -DFMT_TEST=OFF
 }
 
 function install_protobuf {
   wget_and_untar https://github.com/protocolbuffers/protobuf/releases/download/v21.8/protobuf-all-21.8.tar.gz protobuf
   (
-    cd protobuf
-    ./configure --prefix=/usr
+    cd ${DEPENDENCY_DIR}/protobuf
+    ./configure --prefix=${INSTALL_PREFIX}
     make "-j${NPROC}"
     make install
     ldconfig
@@ -144,61 +146,60 @@ function install_protobuf {
 
 function install_fizz {
   wget_and_untar https://github.com/facebookincubator/fizz/archive/refs/tags/${FB_OS_VERSION}.tar.gz fizz
-  cmake_install fizz/fizz -DBUILD_TESTS=OFF
+  cmake_install_dir fizz/fizz -DBUILD_TESTS=OFF
 }
 
 function install_folly {
   wget_and_untar https://github.com/facebook/folly/archive/refs/tags/${FB_OS_VERSION}.tar.gz folly
-  cmake_install folly -DBUILD_TESTS=OFF -DFOLLY_HAVE_INT128_T=ON
+  cmake_install_dir folly -DBUILD_TESTS=OFF -DFOLLY_HAVE_INT128_T=ON
 }
 
 function install_wangle {
   wget_and_untar https://github.com/facebook/wangle/archive/refs/tags/${FB_OS_VERSION}.tar.gz wangle
-  cmake_install wangle/wangle -DBUILD_TESTS=OFF
+  cmake_install_dir wangle/wangle -DBUILD_TESTS=OFF
 }
 
 function install_fbthrift {
   wget_and_untar https://github.com/facebook/fbthrift/archive/refs/tags/${FB_OS_VERSION}.tar.gz fbthrift
-  cmake_install fbthrift -Denable_tests=OFF -DBUILD_TESTS=OFF -DBUILD_SHARED_LIBS=OFF
+  cmake_install_dir fbthrift -Denable_tests=OFF -DBUILD_TESTS=OFF -DBUILD_SHARED_LIBS=OFF
 }
 
 function install_mvfst {
   wget_and_untar https://github.com/facebook/mvfst/archive/refs/tags/${FB_OS_VERSION}.tar.gz mvfst
-  cmake_install mvfst -DBUILD_TESTS=OFF
+  cmake_install_dir mvfst -DBUILD_TESTS=OFF
 }
 
 function install_duckdb {
   if $BUILD_DUCKDB ; then
     echo 'Building DuckDB'
     wget_and_untar https://github.com/duckdb/duckdb/archive/refs/tags/v0.8.1.tar.gz duckdb
-    cmake_install duckdb -DBUILD_UNITTESTS=OFF -DENABLE_SANITIZER=OFF -DENABLE_UBSAN=OFF -DBUILD_SHELL=OFF -DEXPORT_DLL_SYMBOLS=OFF -DCMAKE_BUILD_TYPE=Release
+    cmake_install_dir duckdb -DBUILD_UNITTESTS=OFF -DENABLE_SANITIZER=OFF -DENABLE_UBSAN=OFF -DBUILD_SHELL=OFF -DEXPORT_DLL_SYMBOLS=OFF -DCMAKE_BUILD_TYPE=Release
   fi
 }
 
 function install_arrow {
   wget_and_untar https://archive.apache.org/dist/arrow/arrow-${ARROW_VERSION}/apache-arrow-${ARROW_VERSION}.tar.gz arrow
-  (
-    cd arrow/cpp
-    cmake_install \
-      -DARROW_PARQUET=OFF \
-      -DARROW_WITH_THRIFT=ON \
-      -DARROW_WITH_LZ4=ON \
-      -DARROW_WITH_SNAPPY=ON \
-      -DARROW_WITH_ZLIB=ON \
-      -DARROW_WITH_ZSTD=ON \
-      -DARROW_JEMALLOC=OFF \
-      -DARROW_SIMD_LEVEL=NONE \
-      -DARROW_RUNTIME_SIMD_LEVEL=NONE \
-      -DARROW_WITH_UTF8PROC=OFF \
-      -DARROW_TESTING=ON \
-      -DCMAKE_INSTALL_PREFIX=/usr/local \
-      -DCMAKE_BUILD_TYPE=Release \
-      -DARROW_BUILD_STATIC=ON \
-      -DThrift_SOURCE=BUNDLED
+  cmake_install_dir arrow/cpp \
+    -DARROW_PARQUET=OFF \
+    -DARROW_WITH_THRIFT=ON \
+    -DARROW_WITH_LZ4=ON \
+    -DARROW_WITH_SNAPPY=ON \
+    -DARROW_WITH_ZLIB=ON \
+    -DARROW_WITH_ZSTD=ON \
+    -DARROW_JEMALLOC=OFF \
+    -DARROW_SIMD_LEVEL=NONE \
+    -DARROW_RUNTIME_SIMD_LEVEL=NONE \
+    -DARROW_WITH_UTF8PROC=OFF \
+    -DARROW_TESTING=ON \
+    -DCMAKE_INSTALL_PREFIX=${INSTALL_PREFIX} \
+    -DCMAKE_BUILD_TYPE=Release \
+    -DARROW_BUILD_STATIC=ON \
+    -DThrift_SOURCE=BUNDLED
 
+  (
     # Install thrift.
-    cd _build/thrift_ep-prefix/src/thrift_ep-build
-    cmake --install ./ --prefix /usr/local/
+    cd ${DEPENDENCY_DIR}/arrow/cpp/_build/thrift_ep-prefix/src/thrift_ep-build
+    cmake --install ./ --prefix ${INSTALL_PREFIX}
   )
 }