ClickHouse/docker/packager/packager

#!/usr/bin/env python3
#-*- coding: utf-8 -*-
import subprocess
import os
import argparse
import logging
import sys

SCRIPT_PATH = os.path.realpath(__file__)

IMAGE_MAP = {
    "deb": "clickhouse/deb-builder",
    "binary": "clickhouse/binary-builder",
    "unbundled": "clickhouse/unbundled-builder"
}

def check_image_exists_locally(image_name):
    try:
        output = subprocess.check_output("docker images -q {} 2> /dev/null".format(image_name), shell=True)
        return output != ""
    except subprocess.CalledProcessError as ex:
        return False

def pull_image(image_name):
    try:
        subprocess.check_call("docker pull {}".format(image_name), shell=True)
        return True
    except subprocess.CalledProcessError as ex:
        logging.info("Cannot pull image {}".format(image_name))
        return False

def build_image(image_name, filepath):
    subprocess.check_call("docker build --network=host -t {} -f {} .".format(image_name, filepath), shell=True)

def run_docker_image_with_env(image_name, output, env_variables, ch_root, ccache_dir, docker_image_version):
    env_part = " -e ".join(env_variables)
    if env_part:
        env_part = " -e " + env_part

    if sys.stdout.isatty():
        interactive = "-it"
    else:
        interactive = ""

    cmd = "docker run --network=host --rm --volume={output_path}:/output --volume={ch_root}:/build --volume={ccache_dir}:/ccache {env} {interactive} {img_name}".format(
        output_path=output,
        ch_root=ch_root,
        ccache_dir=ccache_dir,
        env=env_part,
        img_name=image_name + ":" + docker_image_version,
        interactive=interactive
    )

    logging.info("Will build ClickHouse pkg with cmd: '{}'".format(cmd))

    subprocess.check_call(cmd, shell=True)

def parse_env_variables(build_type, compiler, sanitizer, package_type, image_type, cache, distcc_hosts, unbundled, split_binary, clang_tidy, version, author, official, alien_pkgs, with_coverage, with_binaries):
    CLANG_PREFIX = "clang"
    DARWIN_SUFFIX = "-darwin"
    DARWIN_ARM_SUFFIX = "-darwin-aarch64"
    ARM_SUFFIX = "-aarch64"
    FREEBSD_SUFFIX = "-freebsd"
    PPC_SUFFIX = '-ppc64le'

    result = []
    cmake_flags = ['$CMAKE_FLAGS', '-DADD_GDB_INDEX_FOR_GOLD=1']

    is_clang = compiler.startswith(CLANG_PREFIX)
    is_cross_darwin = compiler.endswith(DARWIN_SUFFIX)
    is_cross_darwin_arm = compiler.endswith(DARWIN_ARM_SUFFIX)
    is_cross_arm = compiler.endswith(ARM_SUFFIX)
    is_cross_ppc = compiler.endswith(PPC_SUFFIX)
    is_cross_freebsd = compiler.endswith(FREEBSD_SUFFIX)
    is_cross_compile = is_cross_darwin or is_cross_darwin_arm or is_cross_arm or is_cross_freebsd or is_cross_ppc

    # Explicitly use LLD with Clang by default.
    # Don't force linker for cross-compilation.
    if is_clang and not is_cross_compile:
        cmake_flags.append("-DLINKER_NAME=ld.lld")

    if is_cross_darwin:
        cc = compiler[:-len(DARWIN_SUFFIX)]
        cmake_flags.append("-DCMAKE_AR:FILEPATH=/cctools/bin/x86_64-apple-darwin-ar")
        cmake_flags.append("-DCMAKE_INSTALL_NAME_TOOL=/cctools/bin/x86_64-apple-darwin-install_name_tool")
        cmake_flags.append("-DCMAKE_RANLIB:FILEPATH=/cctools/bin/x86_64-apple-darwin-ranlib")
        cmake_flags.append("-DLINKER_NAME=/cctools/bin/x86_64-apple-darwin-ld")
        cmake_flags.append("-DCMAKE_TOOLCHAIN_FILE=/build/cmake/darwin/toolchain-x86_64.cmake")
    elif is_cross_darwin_arm:
        cc = compiler[:-len(DARWIN_ARM_SUFFIX)]
        cmake_flags.append("-DCMAKE_AR:FILEPATH=/cctools/bin/aarch64-apple-darwin-ar")
        cmake_flags.append("-DCMAKE_INSTALL_NAME_TOOL=/cctools/bin/aarch64-apple-darwin-install_name_tool")
        cmake_flags.append("-DCMAKE_RANLIB:FILEPATH=/cctools/bin/aarch64-apple-darwin-ranlib")
        cmake_flags.append("-DLINKER_NAME=/cctools/bin/aarch64-apple-darwin-ld")
        cmake_flags.append("-DCMAKE_TOOLCHAIN_FILE=/build/cmake/darwin/toolchain-aarch64.cmake")
    elif is_cross_arm:
        cc = compiler[:-len(ARM_SUFFIX)]
        cmake_flags.append("-DCMAKE_TOOLCHAIN_FILE=/build/cmake/linux/toolchain-aarch64.cmake")
    elif is_cross_freebsd:
        cc = compiler[:-len(FREEBSD_SUFFIX)]
        cmake_flags.append("-DCMAKE_TOOLCHAIN_FILE=/build/cmake/freebsd/toolchain-x86_64.cmake")
    elif is_cross_ppc:
        cc = compiler[:-len(PPC_SUFFIX)]
        cmake_flags.append("-DCMAKE_TOOLCHAIN_FILE=/build/cmake/linux/toolchain-ppc64le.cmake")
    else:
        cc = compiler

    cxx = cc.replace('gcc', 'g++').replace('clang', 'clang++')

    if image_type == "deb" or image_type == "unbundled":
        result.append("DEB_CC={}".format(cc))
        result.append("DEB_CXX={}".format(cxx))
        # For building fuzzers
        result.append("CC={}".format(cc))
        result.append("CXX={}".format(cxx))
    elif image_type == "binary":
        result.append("CC={}".format(cc))
        result.append("CXX={}".format(cxx))
        cmake_flags.append('-DCMAKE_C_COMPILER=`which {}`'.format(cc))
        cmake_flags.append('-DCMAKE_CXX_COMPILER=`which {}`'.format(cxx))

    # Create combined output archive for split build and for performance tests.
    if package_type == "performance":
        result.append("COMBINED_OUTPUT=performance")
        cmake_flags.append("-DENABLE_TESTS=0")
    elif split_binary:
        result.append("COMBINED_OUTPUT=shared_build")

    if sanitizer:
        result.append("SANITIZER={}".format(sanitizer))
    if build_type:
        result.append("BUILD_TYPE={}".format(build_type))

    if cache == 'distcc':
        result.append("CCACHE_PREFIX={}".format(cache))

    if cache:
        result.append("CCACHE_DIR=/ccache")
        result.append("CCACHE_BASEDIR=/build")
        result.append("CCACHE_NOHASHDIR=true")
        result.append("CCACHE_COMPILERCHECK=content")
        result.append("CCACHE_MAXSIZE=15G")
        # result.append("CCACHE_UMASK=777")

    if distcc_hosts:
        hosts_with_params = ["{}/24,lzo".format(host) for host in distcc_hosts] + ["localhost/`nproc`"]
        result.append('DISTCC_HOSTS="{}"'.format(" ".join(hosts_with_params)))
    elif cache == "distcc":
        result.append('DISTCC_HOSTS="{}"'.format("localhost/`nproc`"))

    if alien_pkgs:
        result.append("ALIEN_PKGS='" + ' '.join(['--' + pkg for pkg in alien_pkgs]) + "'")

    if with_binaries == "programs":
        result.append('BINARY_OUTPUT=programs')
    elif with_binaries == "tests":
        result.append('ENABLE_TESTS=1')
        result.append('BINARY_OUTPUT=tests')
        cmake_flags.append('-DENABLE_TESTS=1')
        cmake_flags.append('-DUSE_GTEST=1')

    # "Unbundled" build is not suitable for any production usage.
    # But it is occasionally used by some developers.
    # The whole idea of using unknown version of libraries from the OS distribution is deeply flawed.
    # We wish these developers good luck.
    if unbundled:
        # We also disable all CPU features except basic x86_64.
        # It is only slightly related to "unbundled" build, but it is a good place to test if code compiles without these instruction sets.
        cmake_flags.append('-DUNBUNDLED=1 -DUSE_INTERNAL_RDKAFKA_LIBRARY=1 -DENABLE_ARROW=0 -DENABLE_AVRO=0 -DENABLE_ORC=0 -DENABLE_PARQUET=0 -DENABLE_SSSE3=0 -DENABLE_SSE41=0 -DENABLE_SSE42=0 -DENABLE_PCLMULQDQ=0 -DENABLE_POPCNT=0 -DENABLE_AVX=0 -DENABLE_AVX2=0')

    if split_binary:
        cmake_flags.append('-DUSE_STATIC_LIBRARIES=0 -DSPLIT_SHARED_LIBRARIES=1 -DCLICKHOUSE_SPLIT_BINARY=1')
        # We can't always build utils because it requires too much space, but
        # we have to build them at least in some way in CI. The split build is
        # probably the least heavy disk-wise.
        cmake_flags.append('-DENABLE_UTILS=1')

    if clang_tidy:
        cmake_flags.append('-DENABLE_CLANG_TIDY=1')
        cmake_flags.append('-DENABLE_UTILS=1')
        cmake_flags.append('-DUSE_GTEST=1')
        cmake_flags.append('-DENABLE_TESTS=1')
        cmake_flags.append('-DENABLE_EXAMPLES=1')
        # Don't stop on first error to find more clang-tidy errors in one run.
        result.append('NINJA_FLAGS=-k0')

    if with_coverage:
        cmake_flags.append('-DWITH_COVERAGE=1')

    if version:
        result.append("VERSION_STRING='{}'".format(version))

    if author:
        result.append("AUTHOR='{}'".format(author))

    if official:
        cmake_flags.append('-DYANDEX_OFFICIAL_BUILD=1')

    result.append('CMAKE_FLAGS="' + ' '.join(cmake_flags) + '"')

    return result

if __name__ == "__main__":
    logging.basicConfig(level=logging.INFO, format='%(asctime)s %(message)s')
    parser = argparse.ArgumentParser(description="ClickHouse building script using prebuilt Docker image")
    # 'performance' creates a combined .tgz with server and configs to be used for performance test.
    parser.add_argument("--package-type", choices=['deb', 'binary', 'performance'], required=True)
    parser.add_argument("--clickhouse-repo-path", default=os.path.join(os.path.dirname(os.path.abspath(__file__)), os.pardir, os.pardir))
    parser.add_argument("--output-dir", required=True)
    parser.add_argument("--build-type", choices=("debug", ""), default="")
    parser.add_argument("--compiler", choices=("clang-11", "clang-11-darwin", "clang-11-darwin-aarch64", "clang-11-aarch64",
                                               "clang-12", "clang-12-darwin", "clang-12-darwin-aarch64", "clang-12-aarch64",
                                               "clang-13", "clang-13-darwin", "clang-13-darwin-aarch64", "clang-13-aarch64", "clang-13-ppc64le",
                                               "clang-11-freebsd", "clang-12-freebsd", "clang-13-freebsd", "gcc-11"), default="clang-13")
    parser.add_argument("--sanitizer", choices=("address", "thread", "memory", "undefined", ""), default="")
    parser.add_argument("--unbundled", action="store_true")
    parser.add_argument("--split-binary", action="store_true")
    parser.add_argument("--clang-tidy", action="store_true")
    parser.add_argument("--cache", choices=("", "ccache", "distcc"), default="")
    parser.add_argument("--ccache_dir", default= os.getenv("HOME", "") + '/.ccache')
    parser.add_argument("--distcc-hosts", nargs="+")
    parser.add_argument("--force-build-image", action="store_true")
    parser.add_argument("--version")
    parser.add_argument("--author", default="clickhouse")
    parser.add_argument("--official", action="store_true")
    parser.add_argument("--alien-pkgs", nargs='+', default=[])
    parser.add_argument("--with-coverage", action="store_true")
    parser.add_argument("--with-binaries", choices=("programs", "tests", ""), default="")
    parser.add_argument("--docker-image-version", default="latest")

    args = parser.parse_args()
    if not os.path.isabs(args.output_dir):
        args.output_dir = os.path.abspath(os.path.join(os.getcwd(), args.output_dir))

    image_type = 'binary' if args.package_type == 'performance' else 'unbundled' if args.unbundled else args.package_type
    image_name = IMAGE_MAP[image_type]

    if not os.path.isabs(args.clickhouse_repo_path):
        ch_root = os.path.abspath(os.path.join(os.getcwd(), args.clickhouse_repo_path))
    else:
        ch_root = args.clickhouse_repo_path

    if args.alien_pkgs and not image_type == "deb":
        raise Exception("Can add alien packages only in deb build")

    if args.with_binaries != "" and not image_type == "deb":
        raise Exception("Can add additional binaries only in deb build")

    if args.with_binaries != "" and image_type == "deb":
        logging.info("Should place {} to output".format(args.with_binaries))

    dockerfile = os.path.join(ch_root, "docker/packager", image_type, "Dockerfile")
    image_with_version = image_name + ":" + args.docker_image_version
    if image_type != "freebsd" and not check_image_exists_locally(image_name) or args.force_build_image:
        if not pull_image(image_with_version) or args.force_build_image:
            build_image(image_with_version, dockerfile)
    env_prepared = parse_env_variables(
        args.build_type, args.compiler, args.sanitizer, args.package_type, image_type,
        args.cache, args.distcc_hosts, args.unbundled, args.split_binary, args.clang_tidy,
        args.version, args.author, args.official, args.alien_pkgs, args.with_coverage, args.with_binaries)

    run_docker_image_with_env(image_name, args.output_dir, env_prepared, ch_root, args.ccache_dir, args.docker_image_version)
    logging.info("Output placed into {}".format(args.output_dir))