ClickHouse/docker/test/stateless/run.sh

289 lines
13 KiB
Bash
Raw Normal View History

2020-07-08 08:41:39 +00:00
#!/bin/bash
2023-08-16 20:53:51 +00:00
# shellcheck disable=SC1091
source /setup_export_logs.sh
2020-10-21 20:11:35 +00:00
# fail on errors, verbose and export all env variables
set -e -x -a
2020-07-08 08:41:39 +00:00
# Choose random timezone for this test run.
#
# NOTE: that clickhouse-test will randomize session_timezone by itself as well
# (it will choose between default server timezone and something specific).
2023-01-01 19:53:06 +00:00
TZ="$(rg -v '#' /usr/share/zoneinfo/zone.tab | awk '{print $3}' | shuf | head -n1)"
echo "Choosen random timezone $TZ"
2021-01-06 04:20:33 +00:00
ln -snf "/usr/share/zoneinfo/$TZ" /etc/localtime && echo "$TZ" > /etc/timezone
2020-07-08 08:41:39 +00:00
dpkg -i package_folder/clickhouse-common-static_*.deb
dpkg -i package_folder/clickhouse-common-static-dbg_*.deb
dpkg -i package_folder/clickhouse-server_*.deb
dpkg -i package_folder/clickhouse-client_*.deb
2022-02-15 12:03:51 +00:00
ln -s /usr/share/clickhouse-test/clickhouse-test /usr/bin/clickhouse-test
2020-07-08 08:41:39 +00:00
2023-06-06 10:23:00 +00:00
# shellcheck disable=SC1091
source /attach_gdb.lib
2023-06-05 18:21:40 +00:00
2023-06-30 14:41:27 +00:00
# shellcheck disable=SC1091
source /utils.lib
2023-06-30 14:41:27 +00:00
2020-09-24 08:18:36 +00:00
# install test configs
/usr/share/clickhouse-test/config/install.sh
2020-07-08 08:41:39 +00:00
2022-08-15 22:58:09 +00:00
if [[ -n "$USE_DATABASE_REPLICATED" ]] && [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]; then
echo "Azure is disabled"
else
azurite-blob --blobHost 0.0.0.0 --blobPort 10000 --debug /azurite_log &
fi
2022-08-05 12:00:45 +00:00
./setup_minio.sh stateless
./setup_hdfs_minicluster.sh
2021-08-26 13:12:42 +00:00
2023-08-16 20:53:51 +00:00
config_logs_export_cluster /etc/clickhouse-server/config.d/system_logs_export.yaml
2023-08-06 02:38:04 +00:00
# For flaky check we also enable thread fuzzer
if [ "$NUM_TRIES" -gt "1" ]; then
export THREAD_FUZZER_CPU_TIME_PERIOD_US=1000
export THREAD_FUZZER_SLEEP_PROBABILITY=0.1
export THREAD_FUZZER_SLEEP_TIME_US=100000
2020-12-21 20:24:16 +00:00
export THREAD_FUZZER_pthread_mutex_lock_BEFORE_MIGRATE_PROBABILITY=1
export THREAD_FUZZER_pthread_mutex_lock_AFTER_MIGRATE_PROBABILITY=1
export THREAD_FUZZER_pthread_mutex_unlock_BEFORE_MIGRATE_PROBABILITY=1
export THREAD_FUZZER_pthread_mutex_unlock_AFTER_MIGRATE_PROBABILITY=1
export THREAD_FUZZER_pthread_mutex_lock_BEFORE_SLEEP_PROBABILITY=0.001
export THREAD_FUZZER_pthread_mutex_lock_AFTER_SLEEP_PROBABILITY=0.001
export THREAD_FUZZER_pthread_mutex_unlock_BEFORE_SLEEP_PROBABILITY=0.001
export THREAD_FUZZER_pthread_mutex_unlock_AFTER_SLEEP_PROBABILITY=0.001
export THREAD_FUZZER_pthread_mutex_lock_BEFORE_SLEEP_TIME_US=10000
export THREAD_FUZZER_pthread_mutex_lock_AFTER_SLEEP_TIME_US=10000
export THREAD_FUZZER_pthread_mutex_unlock_BEFORE_SLEEP_TIME_US=10000
export THREAD_FUZZER_pthread_mutex_unlock_AFTER_SLEEP_TIME_US=10000
mkdir -p /var/run/clickhouse-server
# simpliest way to forward env variables to server
sudo -E -u clickhouse /usr/bin/clickhouse-server --config /etc/clickhouse-server/config.xml --daemon --pid-file /var/run/clickhouse-server/clickhouse-server.pid
else
2021-07-03 23:13:32 +00:00
sudo clickhouse start
fi
2020-07-08 08:41:39 +00:00
if [[ -n "$USE_DATABASE_REPLICATED" ]] && [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]; then
sudo cat /etc/clickhouse-server1/config.d/filesystem_caches_path.xml \
| sed "s|<filesystem_caches_path>/var/lib/clickhouse/filesystem_caches/</filesystem_caches_path>|<filesystem_caches_path>/var/lib/clickhouse/filesystem_caches_1/</filesystem_caches_path>|" \
> /etc/clickhouse-server1/config.d/filesystem_caches_path.xml.tmp
mv /etc/clickhouse-server1/config.d/filesystem_caches_path.xml.tmp /etc/clickhouse-server1/config.d/filesystem_caches_path.xml
sudo cat /etc/clickhouse-server2/config.d/filesystem_caches_path.xml \
2023-09-27 23:05:35 +00:00
| sed "s|<filesystem_caches_path>/var/lib/clickhouse/filesystem_caches/</filesystem_caches_path>|<filesystem_caches_path>/var/lib/clickhouse/filesystem_caches_2/</filesystem_caches_path>|" \
> /etc/clickhouse-server2/config.d/filesystem_caches_path.xml.tmp
mv /etc/clickhouse-server2/config.d/filesystem_caches_path.xml.tmp /etc/clickhouse-server2/config.d/filesystem_caches_path.xml
mkdir -p /var/run/clickhouse-server1
sudo chown clickhouse:clickhouse /var/run/clickhouse-server1
2021-03-18 12:49:31 +00:00
sudo -E -u clickhouse /usr/bin/clickhouse server --config /etc/clickhouse-server1/config.xml --daemon \
--pid-file /var/run/clickhouse-server1/clickhouse-server.pid \
2021-03-18 12:49:31 +00:00
-- --path /var/lib/clickhouse1/ --logger.stderr /var/log/clickhouse-server/stderr1.log \
--logger.log /var/log/clickhouse-server/clickhouse-server1.log --logger.errorlog /var/log/clickhouse-server/clickhouse-server1.err.log \
--tcp_port 19000 --tcp_port_secure 19440 --http_port 18123 --https_port 18443 --interserver_http_port 19009 --tcp_with_proxy_port 19010 \
2021-04-12 18:40:34 +00:00
--mysql_port 19004 --postgresql_port 19005 \
2021-03-29 20:04:50 +00:00
--keeper_server.tcp_port 19181 --keeper_server.server_id 2 \
--prometheus.port 19988 \
--macros.replica r2 # It doesn't work :(
2021-03-13 10:22:48 +00:00
mkdir -p /var/run/clickhouse-server2
sudo chown clickhouse:clickhouse /var/run/clickhouse-server2
2021-03-18 12:49:31 +00:00
sudo -E -u clickhouse /usr/bin/clickhouse server --config /etc/clickhouse-server2/config.xml --daemon \
--pid-file /var/run/clickhouse-server2/clickhouse-server.pid \
2021-03-18 12:49:31 +00:00
-- --path /var/lib/clickhouse2/ --logger.stderr /var/log/clickhouse-server/stderr2.log \
--logger.log /var/log/clickhouse-server/clickhouse-server2.log --logger.errorlog /var/log/clickhouse-server/clickhouse-server2.err.log \
2021-03-13 10:22:48 +00:00
--tcp_port 29000 --tcp_port_secure 29440 --http_port 28123 --https_port 28443 --interserver_http_port 29009 --tcp_with_proxy_port 29010 \
2021-04-12 18:40:34 +00:00
--mysql_port 29004 --postgresql_port 29005 \
2021-03-29 20:04:50 +00:00
--keeper_server.tcp_port 29181 --keeper_server.server_id 3 \
--prometheus.port 29988 \
2021-03-13 10:22:48 +00:00
--macros.shard s2 # It doesn't work :(
2021-03-16 16:39:31 +00:00
MAX_RUN_TIME=$((MAX_RUN_TIME < 9000 ? MAX_RUN_TIME : 9000)) # min(MAX_RUN_TIME, 2.5 hours)
MAX_RUN_TIME=$((MAX_RUN_TIME != 0 ? MAX_RUN_TIME : 9000)) # set to 2.5 hours if 0 (unlimited)
2020-07-08 08:41:39 +00:00
fi
2023-08-06 02:38:04 +00:00
2023-08-10 02:32:39 +00:00
# Wait for the server to start, but not for too long.
for _ in {1..100}
2023-08-06 02:38:04 +00:00
do
clickhouse-client --query "SELECT 1" && break
sleep 1
done
2023-08-16 20:53:51 +00:00
setup_logs_replication
2023-08-06 02:38:04 +00:00
attach_gdb_to_clickhouse || true # FIXME: to not break old builds, clean on 2023-09-01
2023-06-02 15:00:24 +00:00
2023-07-02 09:52:50 +00:00
function fn_exists() {
declare -F "$1" > /dev/null;
}
# FIXME: to not break old builds, clean on 2023-09-01
function try_run_with_retry() {
local total_retries="$1"
shift
if fn_exists run_with_retry; then
run_with_retry "$total_retries" "$@"
else
"$@"
fi
}
function run_tests()
{
2021-03-16 16:39:31 +00:00
set -x
# We can have several additional options so we pass them as array because it is more ideologically correct.
2020-10-22 14:33:23 +00:00
read -ra ADDITIONAL_OPTIONS <<< "${ADDITIONAL_OPTIONS:-}"
HIGH_LEVEL_COVERAGE=YES
# Use random order in flaky check
if [ "$NUM_TRIES" -gt "1" ]; then
2021-03-29 18:24:29 +00:00
ADDITIONAL_OPTIONS+=('--order=random')
HIGH_LEVEL_COVERAGE=NO
fi
if [[ -n "$USE_S3_STORAGE_FOR_MERGE_TREE" ]] && [[ "$USE_S3_STORAGE_FOR_MERGE_TREE" -eq 1 ]]; then
ADDITIONAL_OPTIONS+=('--s3-storage')
fi
2021-02-15 10:26:34 +00:00
if [[ -n "$USE_DATABASE_REPLICATED" ]] && [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]; then
ADDITIONAL_OPTIONS+=('--replicated-database')
ADDITIONAL_OPTIONS+=('--jobs')
ADDITIONAL_OPTIONS+=('2')
else
# Too many tests fail for DatabaseReplicated in parallel. All other
# configurations are OK.
ADDITIONAL_OPTIONS+=('--jobs')
ADDITIONAL_OPTIONS+=('8')
2021-02-15 10:26:34 +00:00
fi
if [[ -n "$RUN_BY_HASH_NUM" ]] && [[ -n "$RUN_BY_HASH_TOTAL" ]]; then
ADDITIONAL_OPTIONS+=('--run-by-hash-num')
ADDITIONAL_OPTIONS+=("$RUN_BY_HASH_NUM")
ADDITIONAL_OPTIONS+=('--run-by-hash-total')
ADDITIONAL_OPTIONS+=("$RUN_BY_HASH_TOTAL")
HIGH_LEVEL_COVERAGE=NO
fi
2022-06-23 07:59:13 +00:00
if [[ -n "$USE_DATABASE_ORDINARY" ]] && [[ "$USE_DATABASE_ORDINARY" -eq 1 ]]; then
ADDITIONAL_OPTIONS+=('--db-engine=Ordinary')
fi
if [[ "${HIGH_LEVEL_COVERAGE}" = "YES" ]]; then
ADDITIONAL_OPTIONS+=('--report-coverage')
fi
2023-01-17 19:04:25 +00:00
ADDITIONAL_OPTIONS+=('--report-logs-stats')
2023-07-02 09:52:50 +00:00
try_run_with_retry 10 clickhouse-client -q "insert into system.zookeeper (name, path, value) values ('auxiliary_zookeeper2', '/test/chroot/', '')"
Add zookeeper name in endpoint id (#49780) * Add zookeeper name in endpoint id When we migrate a replicated table from one zookeeper cluster to another (the reason why we migration is that zookeeper's load is too high), we will create a new table with the same zpath, but it will fail and the old table will be in trouble. Here is some infomation: 1.old table: CREATE TABLE a1 (`id` UInt64) ENGINE = ReplicatedMergeTree('/clickhouse/tables/default/a1/{shard}', '{replica}') ORDER BY (id); 2.new table: CREATE TABLE a2 (`id` UInt64) ENGINE = ReplicatedMergeTree('aux1:/clickhouse/tables/default/a1/{shard}', '{replica}') ORDER BY (id); 3.error info: <Error> executeQuery: Code: 220. DB::Exception: Duplicate interserver IO endpoint: DataPartsExchange:/clickhouse/tables/default/a1/01/replicas/02. (DUPLICATE_INTERSERVER_IO_ENDPOINT) <Error> InterserverIOHTTPHandler: Code: 221. DB::Exception: No interserver IO endpoint named DataPartsExchange:/clickhouse/tables/default/a1/01/replicas/02. (NO_SUCH_INTERSERVER_IO_ENDPOINT) * Revert "Add zookeeper name in endpoint id" This reverts commit 9deb75b249619b7abdd38e3949ca8b3a76c9df8e. * Add zookeeper name in endpoint id When we migrate a replicated table from one zookeeper cluster to another (the reason why we migration is that zookeeper's load is too high), we will create a new table with the same zpath, but it will fail and the old table will be in trouble. * Fix incompatible with a new setting * add a test, fix other issues * Update 02442_auxiliary_zookeeper_endpoint_id.sql * Update 02735_system_zookeeper_connection.reference * Update 02735_system_zookeeper_connection.sql * Update run.sh * Remove the 'no-fasttest' tag * Update 02442_auxiliary_zookeeper_endpoint_id.sql --------- Co-authored-by: Alexander Tokmakov <tavplubix@clickhouse.com> Co-authored-by: Alexander Tokmakov <tavplubix@gmail.com>
2023-05-25 09:50:14 +00:00
set +e
clickhouse-test --testname --shard --zookeeper --check-zookeeper-session --hung-check --print-time \
2023-02-03 13:34:18 +00:00
--test-runs "$NUM_TRIES" "${ADDITIONAL_OPTIONS[@]}" 2>&1 \
| ts '%Y-%m-%d %H:%M:%S' \
| tee -a test_output/test_result.txt
set -e
}
export -f run_tests
if [ "$NUM_TRIES" -gt "1" ]; then
# We don't run tests with Ordinary database in PRs, only in master.
# So run new/changed tests with Ordinary at least once in flaky check.
timeout "$MAX_RUN_TIME" bash -c 'NUM_TRIES=1; USE_DATABASE_ORDINARY=1; run_tests' \
| sed 's/All tests have finished//' | sed 's/No tests were run//' ||:
fi
2020-12-28 11:46:53 +00:00
timeout "$MAX_RUN_TIME" bash -c run_tests ||:
2021-01-14 10:42:51 +00:00
2021-12-10 16:38:20 +00:00
echo "Files in current directory"
ls -la ./
echo "Files in root directory"
ls -la /
/process_functional_tests_result.py || echo -e "failure\tCannot parse results" > /test_output/check_status.tsv
2021-02-20 20:04:24 +00:00
2021-03-30 10:49:43 +00:00
clickhouse-client -q "system flush logs" ||:
2021-03-29 11:47:57 +00:00
# Stop server so we can safely read data with clickhouse-local.
# Why do we read data with clickhouse-local?
# Because it's the simplest way to read it when server has crashed.
sudo clickhouse stop ||:
2022-05-03 22:10:40 +00:00
if [[ -n "$USE_DATABASE_REPLICATED" ]] && [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]; then
sudo clickhouse stop --pid-path /var/run/clickhouse-server1 ||:
sudo clickhouse stop --pid-path /var/run/clickhouse-server2 ||:
2022-05-03 22:10:40 +00:00
fi
2023-02-14 12:12:53 +00:00
rg -Fa "<Fatal>" /var/log/clickhouse-server/clickhouse-server.log ||:
2023-03-23 14:36:17 +00:00
rg -A50 -Fa "============" /var/log/clickhouse-server/stderr.log ||:
2023-01-01 20:17:43 +00:00
zstd --threads=0 < /var/log/clickhouse-server/clickhouse-server.log > /test_output/clickhouse-server.log.zst &
data_path_config="--path=/var/lib/clickhouse/"
if [[ -n "$USE_S3_STORAGE_FOR_MERGE_TREE" ]] && [[ "$USE_S3_STORAGE_FOR_MERGE_TREE" -eq 1 ]]; then
# We need s3 storage configuration (but it's more likely that clickhouse-local will fail for some reason)
data_path_config="--config-file=/etc/clickhouse-server/config.xml"
fi
# Compress tables.
#
# NOTE:
# - that due to tests with s3 storage we cannot use /var/lib/clickhouse/data
# directly
# - even though ci auto-compress some files (but not *.tsv) it does this only
# for files >64MB, we want this files to be compressed explicitly
for table in query_log zookeeper_log trace_log transactions_info_log
do
clickhouse-local "$data_path_config" --only-system-tables -q "select * from system.$table format TSVWithNamesAndTypes" | zstd --threads=0 > /test_output/$table.tsv.zst ||:
if [[ -n "$USE_DATABASE_REPLICATED" ]] && [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]; then
2023-01-01 20:17:43 +00:00
clickhouse-local --path /var/lib/clickhouse1/ --only-system-tables -q "select * from system.$table format TSVWithNamesAndTypes" | zstd --threads=0 > /test_output/$table.1.tsv.zst ||:
clickhouse-local --path /var/lib/clickhouse2/ --only-system-tables -q "select * from system.$table format TSVWithNamesAndTypes" | zstd --threads=0 > /test_output/$table.2.tsv.zst ||:
fi
done
# Also export trace log in flamegraph-friendly format.
for trace_type in CPU Memory Real
do
clickhouse-local "$data_path_config" --only-system-tables -q "
select
arrayStringConcat((arrayMap(x -> concat(splitByChar('/', addressToLine(x))[-1], '#', demangle(addressToSymbol(x)) ), trace)), ';') AS stack,
count(*) AS samples
from system.trace_log
2021-04-23 20:03:53 +00:00
where trace_type = '$trace_type'
group by trace
order by samples desc
settings allow_introspection_functions = 1
format TabSeparated" \
2023-01-01 20:17:43 +00:00
| zstd --threads=0 > "/test_output/trace-log-$trace_type-flamegraph.tsv.zst" ||:
done
2021-03-29 11:47:57 +00:00
# Compressed (FIXME: remove once only github actions will be left)
rm /var/log/clickhouse-server/clickhouse-server.log
2021-02-22 13:53:43 +00:00
mv /var/log/clickhouse-server/stderr.log /test_output/ ||:
if [[ -n "$WITH_COVERAGE" ]] && [[ "$WITH_COVERAGE" -eq 1 ]]; then
2023-01-01 20:17:43 +00:00
tar --zstd -chf /test_output/clickhouse_coverage.tar.zst /profraw ||:
2021-02-22 13:53:43 +00:00
fi
tar -chf /test_output/coordination.tar /var/lib/clickhouse/coordination ||:
if [[ -n "$USE_DATABASE_REPLICATED" ]] && [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]; then
2023-02-14 12:12:53 +00:00
rg -Fa "<Fatal>" /var/log/clickhouse-server/clickhouse-server1.log ||:
rg -Fa "<Fatal>" /var/log/clickhouse-server/clickhouse-server2.log ||:
2023-01-01 20:17:43 +00:00
zstd --threads=0 < /var/log/clickhouse-server/clickhouse-server1.log > /test_output/clickhouse-server1.log.zst ||:
zstd --threads=0 < /var/log/clickhouse-server/clickhouse-server2.log > /test_output/clickhouse-server2.log.zst ||:
# FIXME: remove once only github actions will be left
rm /var/log/clickhouse-server/clickhouse-server1.log
rm /var/log/clickhouse-server/clickhouse-server2.log
2021-03-18 12:49:31 +00:00
mv /var/log/clickhouse-server/stderr1.log /test_output/ ||:
mv /var/log/clickhouse-server/stderr2.log /test_output/ ||:
tar -chf /test_output/coordination1.tar /var/lib/clickhouse1/coordination ||:
tar -chf /test_output/coordination2.tar /var/lib/clickhouse2/coordination ||:
fi