postgresql/.cirrus.yml
Andres Freund b507a7a19b ci: macos: Reduce test concurrency
Test performance regresses noticably when using all cores. This is more
pronounced with meson than with autoconf, presumably because meson will
schedule the "full number" of tests more consistently.  8 seems to work
OK.

Discussion: https://postgr.es/m/20220927040208.l3shfcidovpzqxfh@awork3.anarazel.de
Backpatch: 15-, where CI was introduced
2022-10-01 16:56:15 -07:00

618 lines
18 KiB
YAML

# CI configuration file for CI utilizing cirrus-ci.org
#
# For instructions on how to enable the CI integration in a repository and
# further details, see src/tools/ci/README
env:
# Source of images / containers
GCP_PROJECT: pg-ci-images
IMAGE_PROJECT: $GCP_PROJECT
CONTAINER_REPO: us-docker.pkg.dev/${GCP_PROJECT}/ci
# The lower depth accelerates git clone. Use a bit of depth so that
# concurrent tasks and retrying older jobs has a chance of working.
CIRRUS_CLONE_DEPTH: 500
# Useful to be able to analyse what in a script takes long
CIRRUS_LOG_TIMESTAMP: true
CCACHE_MAXSIZE: "250M"
# target to test, for all but windows
CHECK: check-world PROVE_FLAGS=$PROVE_FLAGS
CHECKFLAGS: -Otarget
PROVE_FLAGS: --timer
PGCTLTIMEOUT: 120 # avoids spurious failures during parallel tests
TEMP_CONFIG: ${CIRRUS_WORKING_DIR}/src/tools/ci/pg_ci_base.conf
PG_TEST_EXTRA: kerberos ldap ssl
# What files to preserve in case tests fail
on_failure: &on_failure
log_artifacts:
paths:
- "**/*.log"
- "**/*.diffs"
- "**/regress_log_*"
type: text/plain
task:
name: FreeBSD - 13
env:
# FreeBSD on GCP is slow when running with larger number of CPUS /
# jobs. Using one more job than cpus seems to work best.
CPUS: 2
BUILD_JOBS: 3
TEST_JOBS: 3
CCACHE_DIR: /tmp/ccache_dir
only_if: $CIRRUS_CHANGE_MESSAGE !=~ '.*\nci-os-only:.*' || $CIRRUS_CHANGE_MESSAGE =~ '.*\nci-os-only:[^\n]*freebsd.*'
compute_engine_instance:
image_project: $IMAGE_PROJECT
image: family/pg-ci-freebsd-13
platform: freebsd
cpu: $CPUS
memory: 4G
disk: 50
sysinfo_script: |
id
uname -a
ulimit -a -H && ulimit -a -S
export
ccache_cache:
folder: $CCACHE_DIR
# Workaround around performance issues due to 32KB block size
repartition_script: src/tools/ci/gcp_freebsd_repartition.sh
create_user_script: |
pw useradd postgres
chown -R postgres:postgres .
mkdir -p ${CCACHE_DIR}
chown -R postgres:postgres ${CCACHE_DIR}
setup_core_files_script: |
mkdir -m 770 /tmp/cores
chown root:postgres /tmp/cores
sysctl kern.corefile='/tmp/cores/%N.%P.core'
setup_additional_packages_script: |
#pkg install -y ...
# NB: Intentionally build without --with-llvm. The freebsd image size is
# already large enough to make VM startup slow, and even without llvm
# freebsd already takes longer than other platforms except for windows.
configure_script: |
su postgres <<-EOF
./configure \
--enable-cassert --enable-debug --enable-tap-tests \
--enable-nls \
\
--with-gssapi \
--with-icu \
--with-ldap \
--with-libxml \
--with-libxslt \
--with-lz4 \
--with-pam \
--with-perl \
--with-python \
--with-ssl=openssl \
--with-tcl --with-tclconfig=/usr/local/lib/tcl8.6/ \
--with-uuid=bsd \
--with-zstd \
\
--with-includes=/usr/local/include \
--with-libs=/usr/local/lib \
\
CC="ccache cc" \
CXX="ccache c++" \
CFLAGS="-Og -ggdb"
EOF
build_script: su postgres -c "gmake -s -j${BUILD_JOBS} world-bin"
upload_caches: ccache
# The use of script avoids make -Otarget complaints about fcntl() on
# platforms without support for locking pipes. See also
# https://savannah.gnu.org/bugs/?60774
# script uses pseudo-ttys, which do support locking.
test_world_script:
- su postgres -c "time script test.log gmake -s -j${TEST_JOBS} ${CHECK} ${CHECKFLAGS}"
on_failure:
<<: *on_failure
cores_script: src/tools/ci/cores_backtrace.sh freebsd /tmp/cores
# configure feature flags, shared between the task running the linux tests and
# the CompilerWarnings task
LINUX_CONFIGURE_FEATURES: &LINUX_CONFIGURE_FEATURES >-
--with-gssapi
--with-icu
--with-ldap
--with-libxml
--with-libxslt
--with-llvm
--with-lz4
--with-pam
--with-perl
--with-python
--with-selinux
--with-ssl=openssl
--with-systemd
--with-tcl --with-tclconfig=/usr/lib/tcl8.6/
--with-uuid=ossp
--with-zstd
task:
name: Linux - Debian Bullseye
env:
CPUS: 4
BUILD_JOBS: 4
TEST_JOBS: 8 # experimentally derived to be a decent choice
CCACHE_DIR: /tmp/ccache_dir
DEBUGINFOD_URLS: "https://debuginfod.debian.net"
LINUX_CONFIGURE_FEATURES: *LINUX_CONFIGURE_FEATURES
only_if: $CIRRUS_CHANGE_MESSAGE !=~ '.*\nci-os-only:.*' || $CIRRUS_CHANGE_MESSAGE =~ '.*\nci-os-only:[^\n]*linux.*'
compute_engine_instance:
image_project: $IMAGE_PROJECT
image: family/pg-ci-bullseye
platform: linux
cpu: $CPUS
memory: 4G
ccache_cache:
folder: ${CCACHE_DIR}
sysinfo_script: |
id
uname -a
cat /proc/cmdline
ulimit -a -H && ulimit -a -S
export
create_user_script: |
useradd -m postgres
chown -R postgres:postgres .
mkdir -p ${CCACHE_DIR}
chown -R postgres:postgres ${CCACHE_DIR}
echo '* - memlock 134217728' > /etc/security/limits.d/postgres.conf
su postgres -c "ulimit -l -H && ulimit -l -S"
setup_core_files_script: |
mkdir -m 770 /tmp/cores
chown root:postgres /tmp/cores
sysctl kernel.core_pattern='/tmp/cores/%e-%s-%p.core'
setup_additional_packages_script: |
#apt-get update
#DEBIAN_FRONTEND=noninteractive apt-get -y install ...
configure_script: |
su postgres <<-EOF
./configure \
--enable-cassert --enable-debug --enable-tap-tests \
--enable-nls \
\
${LINUX_CONFIGURE_FEATURES} \
\
CC="ccache gcc" \
CXX="ccache g++" \
CLANG="ccache clang" \
CFLAGS="-Og -ggdb" \
CXXFLAGS="-Og -ggdb"
EOF
build_script: su postgres -c "make -s -j${BUILD_JOBS} world-bin"
upload_caches: ccache
test_world_script: |
su postgres <<-EOF
ulimit -c unlimited # default is 0
make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
EOF
on_failure:
<<: *on_failure
cores_script: src/tools/ci/cores_backtrace.sh linux /tmp/cores
task:
name: macOS - Monterey
env:
CPUS: 12 # always get that much for cirrusci macOS instances
BUILD_JOBS: $CPUS
# Test performance regresses noticably when using all cores. 8 seems to
# work OK. See
# https://postgr.es/m/20220927040208.l3shfcidovpzqxfh%40awork3.anarazel.de
TEST_JOBS: 8
CIRRUS_WORKING_DIR: ${HOME}/pgsql/
CCACHE_DIR: ${HOME}/ccache
HOMEBREW_CACHE: ${HOME}/homebrew-cache
PERL5LIB: ${HOME}/perl5/lib/perl5
only_if: $CIRRUS_CHANGE_MESSAGE !=~ '.*\nci-os-only:.*' || $CIRRUS_CHANGE_MESSAGE =~ '.*\nci-os-only:[^\n]*(macos|darwin|osx).*'
osx_instance:
image: monterey-base
sysinfo_script: |
id
uname -a
ulimit -a -H && ulimit -a -S
export
setup_core_files_script:
- mkdir ${HOME}/cores
- sudo sysctl kern.corefile="${HOME}/cores/core.%P"
perl_cache:
folder: ~/perl5
cpan_install_script:
- perl -mIPC::Run -e 1 || cpan -T IPC::Run
- perl -mIO::Pty -e 1 || cpan -T IO::Pty
upload_caches: perl
# XXX: Could we instead install homebrew into a cached directory? The
# homebrew installation takes a good bit of time every time, even if the
# packages do not need to be downloaded.
homebrew_cache:
folder: $HOMEBREW_CACHE
setup_additional_packages_script: |
brew install \
ccache \
icu4c \
krb5 \
llvm \
lz4 \
make \
openldap \
openssl \
python \
tcl-tk \
zstd
brew cleanup -s # to reduce cache size
upload_caches: homebrew
ccache_cache:
folder: $CCACHE_DIR
configure_script: |
brewpath="/usr/local"
INCLUDES="${brewpath}/include:${INCLUDES}"
LIBS="${brewpath}/lib:${LIBS}"
for pkg in icu4c krb5 openldap openssl zstd ; do
pkgpath="${brewpath}/opt/${pkg}"
INCLUDES="${pkgpath}/include:${INCLUDES}"
LIBS="${pkgpath}/lib:${LIBS}"
PKG_CONFIG_PATH="${pkgpath}/lib/pkgconfig:${PKG_CONFIG_PATH}"
done
export PKG_CONFIG_PATH
./configure \
--enable-cassert --enable-debug --enable-tap-tests \
--enable-nls \
\
--with-bonjour \
--with-gssapi \
--with-icu \
--with-ldap \
--with-libxml \
--with-libxslt \
--with-lz4 \
--with-perl \
--with-python \
--with-ssl=openssl \
--with-tcl --with-tclconfig=${brewpath}/opt/tcl-tk/lib/ \
--with-uuid=e2fs \
--with-zstd \
\
--prefix=${HOME}/install \
--with-includes="${INCLUDES}" \
--with-libs="${LIBS}" \
\
CC="ccache cc" \
CXX="ccache c++" \
CLANG="ccache ${brewpath}/llvm/bin/ccache" \
CFLAGS="-Og -ggdb" \
CXXFLAGS="-Og -ggdb" \
\
LLVM_CONFIG=${brewpath}/llvm/bin/llvm-config \
PYTHON=python3
build_script: gmake -s -j${BUILD_JOBS} world-bin
upload_caches: ccache
test_world_script: |
ulimit -c unlimited # default is 0
ulimit -n 1024 # default is 256, pretty low
# See freebsd use of script for explanation
script test.log gmake -s -j${TEST_JOBS} ${CHECK} ${CHECKFLAGS}
on_failure:
<<: *on_failure
cores_script: src/tools/ci/cores_backtrace.sh macos "${HOME}/cores"
task:
name: Windows - Server 2019, VS 2019
env:
# Half the allowed per-user CPU cores
CPUS: 4
# Our windows infrastructure doesn't have test concurrency above the level
# of a single vcregress test target. Due to that, it's useful to run prove
# with multiple jobs. For the other tasks it isn't, because two sources
# (make and prove) of concurrency can overload machines.
#
# The concrete choice of 10 is based on a small bit of experimentation and
# likely can be improved upon further.
PROVE_FLAGS: -j10 --timer
# The default cirrus working dir is in a directory msbuild complains about
CIRRUS_WORKING_DIR: "c:/cirrus"
# Avoid re-installing over and over
NO_TEMP_INSTALL: 1
# git's tar doesn't deal with drive letters, see
# https://postgr.es/m/b6782dc3-a7b0-ed56-175f-f8f54cb08d67%40dunslane.net
TAR: "c:/windows/system32/tar.exe"
# Avoids port conflicts between concurrent tap test runs
PG_TEST_USE_UNIX_SOCKETS: 1
PG_REGRESS_SOCK_DIR: "c:/cirrus/"
# -m enables parallelism
# verbosity:minimal + Summary reduce verbosity, while keeping a summary of
# errors/warnings
# ForceNoAlign prevents msbuild from introducing line-breaks for long lines
# disable file tracker, we're never going to rebuild, and it slows down the
# build
MSBFLAGS: -m -verbosity:minimal "-consoleLoggerParameters:Summary;ForceNoAlign" /p:TrackFileAccess=false -nologo
# If tests hang forever, cirrus eventually times out. In that case log
# output etc is not uploaded, making the problem hard to debug. Of course
# tests internally should have shorter timeouts, but that's proven to not
# be sufficient. 15min currently is fast enough to finish individual test
# "suites".
T_C: "\"C:/Program Files/Git/usr/bin/timeout.exe\" -v -k60s 15m"
# startcreate_script starts a postgres instance that we don't want to get
# killed at the end of that script (it's stopped in stop_script). Can't
# trivially use background_scripts because a) need pg_ctl's dropping of
# permissions b) need to wait for startup to have finished, and we don't
# currently have a tool for that...
CIRRUS_ESCAPING_PROCESSES: 1
# Cirrus defaults to SetErrorMode(SEM_NOGPFAULTERRORBOX | ...). That
# prevents crash reporting from working unless binaries do SetErrorMode()
# themselves. Furthermore, it appears that either python or, more likely,
# the C runtime has a bug where SEM_NOGPFAULTERRORBOX can very
# occasionally *trigger* a crash on process exit - which is hard to debug,
# given that it explicitly prevents crash dumps from working...
# 0x8001 is SEM_FAILCRITICALERRORS | SEM_NOOPENFILEERRORBOX
CIRRUS_WINDOWS_ERROR_MODE: 0x8001
only_if: $CIRRUS_CHANGE_MESSAGE !=~ '.*\nci-os-only:.*' || $CIRRUS_CHANGE_MESSAGE =~ '.*\nci-os-only:[^\n]*windows.*'
windows_container:
image: $CONTAINER_REPO/windows_ci_vs_2019:latest
cpu: $CPUS
memory: 4G
sysinfo_script: |
chcp
systeminfo
powershell -Command get-psdrive -psprovider filesystem
set
setup_additional_packages_script: |
REM choco install -y --no-progress ...
configure_script:
# copy errors out when using forward slashes
- copy src\tools\ci\windows_build_config.pl src\tools\msvc\config.pl
- vcvarsall x64
- perl src/tools/msvc/mkvcbuild.pl
build_script:
- vcvarsall x64
- msbuild %MSBFLAGS% pgsql.sln
tempinstall_script:
# Installation on windows currently only completely works from src/tools/msvc
- cd src/tools/msvc && perl install.pl %CIRRUS_WORKING_DIR%/tmp_install
test_regress_parallel_script: |
%T_C% perl src/tools/msvc/vcregress.pl check parallel
startcreate_script: |
rem paths to binaries need backslashes
tmp_install\bin\pg_ctl.exe initdb -D tmp_check/db -l tmp_check/initdb.log --options=--no-sync
echo include '%TEMP_CONFIG%' >> tmp_check/db/postgresql.conf
tmp_install\bin\pg_ctl.exe start -D tmp_check/db -l tmp_check/postmaster.log
test_pl_script: |
%T_C% perl src/tools/msvc/vcregress.pl plcheck
test_isolation_script: |
%T_C% perl src/tools/msvc/vcregress.pl isolationcheck
test_modules_script: |
%T_C% perl src/tools/msvc/vcregress.pl modulescheck
test_contrib_script: |
%T_C% perl src/tools/msvc/vcregress.pl contribcheck
stop_script: |
tmp_install\bin\pg_ctl.exe stop -D tmp_check/db -l tmp_check/postmaster.log
test_ssl_script: |
set with_ssl=openssl
%T_C% perl src/tools/msvc/vcregress.pl taptest ./src/test/ssl/
test_subscription_script: |
%T_C% perl src/tools/msvc/vcregress.pl taptest ./src/test/subscription/
test_authentication_script: |
%T_C% perl src/tools/msvc/vcregress.pl taptest ./src/test/authentication/
test_recovery_script: |
%T_C% perl src/tools/msvc/vcregress.pl recoverycheck
test_bin_script: |
%T_C% perl src/tools/msvc/vcregress.pl bincheck
test_ecpg_script: |
rem tries to build additional stuff
vcvarsall x64
rem References ecpg_regression.proj in the current dir
cd src/tools/msvc
%T_C% perl vcregress.pl ecpgcheck
on_failure:
<<: *on_failure
crashlog_artifacts:
path: "crashlog-*.txt"
type: text/plain
task:
name: CompilerWarnings
# To limit unnecessary work only run this once the normal linux test succeeds
depends_on:
- Linux - Debian Bullseye
env:
CPUS: 4
BUILD_JOBS: 4
# Use larger ccache cache, as this task compiles with multiple compilers /
# flag combinations
CCACHE_MAXSIZE: "1GB"
CCACHE_DIR: "/tmp/ccache_dir"
LINUX_CONFIGURE_FEATURES: *LINUX_CONFIGURE_FEATURES
# task that did not run, count as a success, so we need to recheck Linux'
# condition here ...
only_if: $CIRRUS_CHANGE_MESSAGE !=~ '.*\nci-os-only:.*' || $CIRRUS_CHANGE_MESSAGE =~ '.*\nci-os-only:[^\n]*linux.*'
container:
image: $CONTAINER_REPO/linux_debian_bullseye_ci:latest
cpu: $CPUS
sysinfo_script: |
id
uname -a
cat /proc/cmdline
ulimit -a -H && ulimit -a -S
gcc -v
clang -v
export
ccache_cache:
folder: $CCACHE_DIR
setup_additional_packages_script: |
#apt-get update
#DEBIAN_FRONTEND=noninteractive apt-get -y install ...
###
# Test that code can be built with gcc/clang without warnings
###
setup_script: echo "COPT=-Werror" > src/Makefile.custom
# Trace probes have a history of getting accidentally broken. Use the
# different compilers to build with different combinations of dtrace on/off
# and cassert on/off.
# gcc, cassert off, dtrace on
always:
gcc_warning_script: |
time ./configure \
--cache gcc.cache \
--enable-dtrace \
${LINUX_CONFIGURE_FEATURES} \
CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
make -s -j${BUILD_JOBS} clean
time make -s -j${BUILD_JOBS} world-bin
# gcc, cassert on, dtrace off
always:
gcc_a_warning_script: |
time ./configure \
--cache gcc.cache \
--enable-cassert \
${LINUX_CONFIGURE_FEATURES} \
CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
make -s -j${BUILD_JOBS} clean
time make -s -j${BUILD_JOBS} world-bin
# clang, cassert off, dtrace off
always:
clang_warning_script: |
time ./configure \
--cache clang.cache \
${LINUX_CONFIGURE_FEATURES} \
CC="ccache clang" CXX="ccache clang++" CLANG="ccache clang"
make -s -j${BUILD_JOBS} clean
time make -s -j${BUILD_JOBS} world-bin
# clang, cassert on, dtrace on
always:
clang_a_warning_script: |
time ./configure \
--cache clang.cache \
--enable-cassert \
--enable-dtrace \
${LINUX_CONFIGURE_FEATURES} \
CC="ccache clang" CXX="ccache clang++" CLANG="ccache clang"
make -s -j${BUILD_JOBS} clean
time make -s -j${BUILD_JOBS} world-bin
# cross-compile to windows
always:
mingw_cross_warning_script: |
time ./configure \
--host=x86_64-w64-mingw32 \
--enable-cassert \
CC="ccache x86_64-w64-mingw32-gcc" \
CXX="ccache x86_64-w64-mingw32-g++"
make -s -j${BUILD_JOBS} clean
time make -s -j${BUILD_JOBS} world-bin
###
# Verify docs can be built
###
# XXX: Only do this if there have been changes in doc/ since last build
always:
docs_build_script: |
time ./configure \
--cache gcc.cache \
CC="ccache gcc" \
CXX="ccache g++" \
CLANG="ccache clang"
make -s -j${BUILD_JOBS} clean
time make -s -j${BUILD_JOBS} -C doc
###
# Verify headerscheck / cpluspluscheck succeed
#
# - Don't use ccache, the files are uncacheable, polluting ccache's
# cache
# - Use -fmax-errors, as particularly cpluspluscheck can be very verbose
# - XXX have to disable ICU to avoid errors:
# https://postgr.es/m/20220323002024.f2g6tivduzrktgfa%40alap3.anarazel.de
# - XXX: the -Wno-register avoids verbose warnings:
# https://postgr.es/m/20220308181837.aun3tdtdvao4vb7o%40alap3.anarazel.de
###
always:
headers_headerscheck_script: |
time ./configure \
${LINUX_CONFIGURE_FEATURES} \
--without-icu \
--quiet \
CC="gcc" CXX"=g++" CLANG="clang"
make -s -j${BUILD_JOBS} clean
time make -s headerscheck EXTRAFLAGS='-fmax-errors=10'
headers_cpluspluscheck_script: |
time make -s cpluspluscheck EXTRAFLAGS='-Wno-register -fmax-errors=10'
always:
upload_caches: ccache