thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-11-10 01:25:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #30729 from ClickHouse/trying_actions

Browse Source 
Add functional tests to github actions
This commit is contained in:
alesapin 2021-10-29 09:49:31 +03:00 committed by GitHub
commit ddac7a51e2
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
10 changed files with 411 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

86
.github/workflows/main.yml vendored
View File

@ -47,9 +47,16 @@ jobs:
- name: Check out repository code
uses: actions/checkout@v2
- name: Style Check
env:
TEMP_PATH: ${{ runner.temp }}/style_check
run: |
cd $GITHUB_WORKSPACE/tests/ci
python3 style_check.py
- name: Cleanup
if: always()
run: |
docker kill $(docker ps -q) ||:
sudo rm -fr $TEMP_PATH
BuilderDebDebug:
needs: DockerHubPush
runs-on: [self-hosted, builder]
@ -58,14 +65,16 @@ jobs:
uses: actions/download-artifact@v2
with:
name: changed_images
path: ${{ runner.temp }}/build_check
path: ${{ runner.temp }}/images_path
- name: Check out repository code
uses: actions/checkout@v2
with:
submodules: 'recursive'
fetch-depth: 0 # otherwise we will have no info about contributors
- name: Build
env:
TEMP_PATH: ${{runner.temp}}/build_check
IMAGES_PATH: ${{runner.temp}}/images_path
REPO_COPY: ${{runner.temp}}/build_check/ClickHouse
CACHES_PATH: ${{runner.temp}}/../ccaches
CHECK_NAME: 'ClickHouse build check (actions)'
@ -80,6 +89,11 @@ jobs:
with:
name: ${{ env.BUILD_NAME }}
path: ${{ runner.temp }}/build_check/${{ env.BUILD_NAME }}.json
- name: Cleanup
if: always()
run: |
docker kill $(docker ps -q) ||:
sudo rm -fr $TEMP_PATH
BuilderReport:
needs: [BuilderDebDebug]
runs-on: [self-hosted, style-checker]
@ -100,6 +114,69 @@ jobs:
mkdir -p $TEMP_PATH
cd $GITHUB_WORKSPACE/tests/ci
python3 build_report_check.py "$CHECK_NAME"
- name: Cleanup
if: always()
run: |
docker kill $(docker ps -q) ||:
sudo rm -fr $TEMP_PATH
FunctionalStatelessTestDebug:
needs: [BuilderDebDebug]
runs-on: [self-hosted, func-tester]
steps:
- name: Download json reports
uses: actions/download-artifact@v2
with:
path: ${{runner.temp}}/reports_dir
- name: Check out repository code
uses: actions/checkout@v2
- name: Functional test
env:
TEMP_PATH: ${{runner.temp}}/stateless_debug
REPORTS_PATH: ${{runner.temp}}/reports_dir
CHECK_NAME: 'Stateless tests (debug, actions)'
REPO_COPY: ${{runner.temp}}/stateless_debug/ClickHouse
REQUIRED_BUILD_NUMBER: 7
KILL_TIMEOUT: 10800
run: |
sudo rm -fr $TEMP_PATH
mkdir -p $TEMP_PATH
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci
python3 functional_test_check.py "$CHECK_NAME" $REQUIRED_BUILD_NUMBER $KILL_TIMEOUT
- name: Cleanup
if: always()
run: |
docker kill $(docker ps -q) ||:
sudo rm -fr $TEMP_PATH
FunctionalStatefulTestDebug:
needs: [BuilderDebDebug]
runs-on: [self-hosted, func-tester]
steps:
- name: Download json reports
uses: actions/download-artifact@v2
with:
path: ${{runner.temp}}/reports_dir
- name: Check out repository code
uses: actions/checkout@v2
- name: Functional test
env:
TEMP_PATH: ${{runner.temp}}/stateful_debug
REPORTS_PATH: ${{runner.temp}}/reports_dir
CHECK_NAME: 'Stateful tests (debug, actions)'
REPO_COPY: ${{runner.temp}}/stateful_debug/ClickHouse
REQUIRED_BUILD_NUMBER: 7
KILL_TIMEOUT: 3600
run: |
sudo rm -fr $TEMP_PATH
mkdir -p $TEMP_PATH
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci
python3 functional_test_check.py "$CHECK_NAME" $REQUIRED_BUILD_NUMBER $KILL_TIMEOUT
- name: Cleanup
if: always()
run: |
docker kill $(docker ps -q) ||:
sudo rm -fr $TEMP_PATH
FastTest:
needs: DockerHubPush
runs-on: [self-hosted, builder]
@ -116,8 +193,13 @@ jobs:
mkdir -p $TEMP_PATH
cp -r $GITHUB_WORKSPACE $TEMP_PATH
cd $REPO_COPY/tests/ci && python3 fast_test_check.py
- name: Cleanup
if: always()
run: |
docker kill $(docker ps -q) ||:
sudo rm -fr $TEMP_PATH
FinishCheck:
needs: [StyleCheck, DockerHubPush, CheckLabels, BuilderReport, FastTest]
needs: [StyleCheck, DockerHubPush, CheckLabels, BuilderReport, FastTest, FunctionalStatelessTestDebug, FunctionalStatefulTestDebug]
runs-on: [self-hosted, style-checker]
steps:
- name: Check out repository code

1
docker/test/stateful/Dockerfile
View File

@ -9,6 +9,7 @@ RUN apt-get update -y \
COPY s3downloader /s3downloader
ENV S3_URL="https://clickhouse-datasets.s3.yandex.net"
ENV DATASETS="hits visits"
COPY run.sh /

2
docker/test/stateful/run.sh
View File

@ -56,7 +56,7 @@ function start()
start
# shellcheck disable=SC2086 # No quotes because I want to split it into words.
/s3downloader --dataset-names $DATASETS
/s3downloader --url-prefix "$S3_URL" --dataset-names $DATASETS
chmod 777 -R /var/lib/clickhouse
clickhouse-client --query "SHOW DATABASES"

2
tests/ci/build_check.py
View File

@ -128,7 +128,7 @@ if __name__ == "__main__":
gh = Github(get_best_robot_token())
images_path = os.path.join(temp_path, 'changed_images.json')
images_path = os.path.join(os.getenv("IMAGES_PATH", temp_path), 'changed_images.json')
image_name = get_image_name(build_config)
image_version = 'latest'
if os.path.exists(images_path):

1
tests/ci/build_report_check.py
View File

@ -86,7 +86,6 @@ if __name__ == "__main__":
build_reports = []
for root, dirs, files in os.walk(reports_path):
print(files)
for f in files:
if f.startswith("build_urls_") and f.endswith('.json'):
logging.info("Found build report json %s", f)

2
tests/ci/fast_test_check.py
View File

@ -113,7 +113,7 @@ if __name__ == "__main__":
images = json.load(images_fd)
logging.info("Got images %s", images)
if 'clickhouse/fasttest' in images:
docker_image += ':' + images['clickhouse/pvs-test']
docker_image += ':' + images['clickhouse/fasttest']
logging.info("Got docker image %s", docker_image)
for i in range(10):

285
tests/ci/functional_test_check.py Normal file
View File

@ -0,0 +1,285 @@
#!/usr/bin/env python3
import csv
import logging
import subprocess
import os
import json
import time
import sys
from github import Github
import requests
from report import create_test_html_report
from s3_helper import S3Helper
from get_robot_token import get_best_robot_token
from pr_info import PRInfo
DOWNLOAD_RETRIES_COUNT = 5
def process_logs(s3_client, additional_logs, s3_path_prefix):
additional_urls = []
for log_path in additional_logs:
if log_path:
additional_urls.append(
s3_client.upload_test_report_to_s3(
log_path,
s3_path_prefix + "/" + os.path.basename(log_path)))
return additional_urls
def upload_results(s3_client, pr_number, commit_sha, test_results, raw_log, additional_files, check_name):
additional_files = [raw_log] + additional_files
s3_path_prefix = f"{pr_number}/{commit_sha}/" + check_name.lower().replace(' ', '_').replace('(', '_').replace(')', '_').replace(',', '_')
additional_urls = process_logs(s3_client, additional_files, s3_path_prefix)
branch_url = "https://github.com/ClickHouse/ClickHouse/commits/master"
branch_name = "master"
if pr_number != 0:
branch_name = f"PR #{pr_number}"
branch_url = f"https://github.com/ClickHouse/ClickHouse/pull/{pr_number}"
commit_url = f"https://github.com/ClickHouse/ClickHouse/commit/{commit_sha}"
task_url = f"https://github.com/ClickHouse/ClickHouse/actions/runs/{os.getenv('GITHUB_RUN_ID')}"
raw_log_url = additional_urls[0]
additional_urls.pop(0)
html_report = create_test_html_report(check_name, test_results, raw_log_url, task_url, branch_url, branch_name, commit_url, additional_urls, True)
with open('report.html', 'w', encoding='utf-8') as f:
f.write(html_report)
url = s3_client.upload_test_report_to_s3('report.html', s3_path_prefix + ".html")
logging.info("Search result in url %s", url)
return url
def get_commit(gh, commit_sha):
repo = gh.get_repo(os.getenv("GITHUB_REPOSITORY", "ClickHouse/ClickHouse"))
commit = repo.get_commit(commit_sha)
return commit
def get_image_name(check_name):
if 'stateless' in check_name.lower():
return 'clickhouse/stateless-test'
if 'stateful' in check_name.lower():
return 'clickhouse/stateful-test'
else:
raise Exception(f"Cannot deduce image name based on check name {check_name}")
def dowload_build_with_progress(url, path):
logging.info("Downloading from %s to temp path %s", url, path)
for i in range(DOWNLOAD_RETRIES_COUNT):
try:
with open(path, 'wb') as f:
response = requests.get(url, stream=True)
response.raise_for_status()
total_length = response.headers.get('content-length')
if total_length is None or int(total_length) == 0:
logging.info("No content-length, will download file without progress")
f.write(response.content)
else:
dl = 0
total_length = int(total_length)
logging.info("Content length is %ld bytes", total_length)
for data in response.iter_content(chunk_size=4096):
dl += len(data)
f.write(data)
if sys.stdout.isatty():
done = int(50 * dl / total_length)
percent = int(100 * float(dl) / total_length)
eq_str = '=' * done
space_str = ' ' * (50 - done)
sys.stdout.write(f"\r[{eq_str}{space_str}] {percent}%")
sys.stdout.flush()
break
except Exception as ex:
sys.stdout.write("\n")
time.sleep(3)
logging.info("Exception while downloading %s, retry %s", ex, i + 1)
if os.path.exists(path):
os.remove(path)
else:
raise Exception(f"Cannot download dataset from {url}, all retries exceeded")
sys.stdout.write("\n")
logging.info("Downloading finished")
def download_builds(result_path, build_urls):
for url in build_urls:
if url.endswith('.deb'):
fname = os.path.basename(url)
logging.info("Will download %s to %s", fname, result_path)
dowload_build_with_progress(url, os.path.join(result_path, fname))
def get_build_config(build_number, repo_path):
ci_config_path = os.path.join(repo_path, "tests/ci/ci_config.json")
with open(ci_config_path, 'r', encoding='utf-8') as ci_config:
config_dict = json.load(ci_config)
return config_dict['build_config'][build_number]
def get_build_urls(build_config_str, reports_path):
for root, _, files in os.walk(reports_path):
for f in files:
if build_config_str in f :
logging.info("Found build report json %s", f)
with open(os.path.join(root, f), 'r', encoding='utf-8') as file_handler:
build_report = json.load(file_handler)
return build_report['build_urls']
return []
def build_config_to_string(build_config):
if build_config["package-type"] == "performance":
return "performance"
return "_".join([
build_config['compiler'],
build_config['build-type'] if build_config['build-type'] else "relwithdebuginfo",
build_config['sanitizer'] if build_config['sanitizer'] else "none",
build_config['bundled'],
build_config['splitted'],
"tidy" if build_config['tidy'] == "enable" else "notidy",
"with_coverage" if build_config['with_coverage'] else "without_coverage",
build_config['package-type'],
])
def get_run_command(builds_path, result_path, server_log_path, kill_timeout, additional_envs, image):
additional_options = ['--hung-check']
additional_options.append('--print-time')
additional_options_str = '-e ADDITIONAL_OPTIONS="' + ' '.join(additional_options) + '"'
envs = [f'-e MAX_RUN_TIME={int(0.9 * kill_timeout)}', '-e S3_URL="https://clickhouse-datasets.s3.amazonaws.com"']
envs += [f'-e {e}' for e in additional_envs]
env_str = ' '.join(envs)
return f"docker run --volume={builds_path}:/package_folder " \
f"--volume={result_path}:/test_output --volume={server_log_path}:/var/log/clickhouse-server " \
f"--cap-add=SYS_PTRACE {env_str} {additional_options_str} {image}"
def process_results(result_folder, server_log_path):
test_results = []
additional_files = []
# Just upload all files from result_folder.
# If task provides processed results, then it's responsible for content of result_folder.
if os.path.exists(result_folder):
test_files = [f for f in os.listdir(result_folder) if os.path.isfile(os.path.join(result_folder, f))]
additional_files = [os.path.join(result_folder, f) for f in test_files]
if os.path.exists(server_log_path):
server_log_files = [f for f in os.listdir(server_log_path) if os.path.isfile(os.path.join(server_log_path, f))]
additional_files = additional_files + [os.path.join(server_log_path, f) for f in server_log_files]
status_path = os.path.join(result_folder, "check_status.tsv")
logging.info("Found test_results.tsv")
with open(status_path, 'r', encoding='utf-8') as status_file:
status = list(csv.reader(status_file, delimiter='\t'))
if len(status) != 1 or len(status[0]) != 2:
return "error", "Invalid check_status.tsv", test_results, additional_files
state, description = status[0][0], status[0][1]
results_path = os.path.join(result_folder, "test_results.tsv")
with open(results_path, 'r', encoding='utf-8') as results_file:
test_results = list(csv.reader(results_file, delimiter='\t'))
if len(test_results) == 0:
raise Exception("Empty results")
return state, description, test_results, additional_files
if __name__ == "__main__":
logging.basicConfig(level=logging.INFO)
temp_path = os.getenv("TEMP_PATH", os.path.abspath("."))
repo_path = os.getenv("REPO_COPY", os.path.abspath("../../"))
reports_path = os.getenv("REPORTS_PATH", "./reports")
check_name = sys.argv[1]
build_number = int(sys.argv[2])
kill_timeout = int(sys.argv[3])
if not os.path.exists(temp_path):
os.makedirs(temp_path)
with open(os.getenv('GITHUB_EVENT_PATH'), 'r', encoding='utf-8') as event_file:
event = json.load(event_file)
pr_info = PRInfo(event)
gh = Github(get_best_robot_token())
for root, _, files in os.walk(reports_path):
for f in files:
if f == 'changed_images.json':
images_path = os.path.join(root, 'changed_images.json')
break
image_name = get_image_name(check_name)
docker_image = image_name
if images_path and os.path.exists(images_path):
logging.info("Images file exists")
with open(images_path, 'r', encoding='utf-8') as images_fd:
images = json.load(images_fd)
logging.info("Got images %s", images)
if image_name in images:
docker_image += ':' + images[image_name]
else:
logging.info("Images file not found")
for i in range(10):
try:
logging.info("Pulling image %s", docker_image)
subprocess.check_output(f"docker pull {docker_image}", stderr=subprocess.STDOUT, shell=True)
break
except Exception as ex:
time.sleep(i * 3)
logging.info("Got execption pulling docker %s", ex)
else:
raise Exception(f"Cannot pull dockerhub for image docker pull {docker_image}")
build_config = get_build_config(build_number, repo_path)
build_config_str = build_config_to_string(build_config)
urls = get_build_urls(build_config_str, reports_path)
if not urls:
raise Exception("No build URLs found")
packages_path = os.path.join(temp_path, "packages")
if not os.path.exists(packages_path):
os.makedirs(packages_path)
server_log_path = os.path.join(temp_path, "server_log")
if not os.path.exists(server_log_path):
os.makedirs(server_log_path)
result_path = os.path.join(temp_path, "result_path")
if not os.path.exists(result_path):
os.makedirs(result_path)
run_log_path = os.path.join(result_path, "runlog.log")
download_builds(packages_path, urls)
run_command = get_run_command(packages_path, result_path, server_log_path, kill_timeout, [], docker_image)
logging.info("Going to run func tests: %s", run_command)
with open(run_log_path, 'w', encoding='utf-8') as log:
with subprocess.Popen(run_command, shell=True, stderr=log, stdout=log) as process:
retcode = process.wait()
if retcode == 0:
logging.info("Run successfully")
else:
logging.info("Run failed")
subprocess.check_call(f"sudo chown -R ubuntu:ubuntu {temp_path}", shell=True)
s3_helper = S3Helper('https://s3.amazonaws.com')
state, description, test_results, additional_logs = process_results(result_path, server_log_path)
report_url = upload_results(s3_helper, pr_info.number, pr_info.sha, test_results, run_log_path, additional_logs, check_name)
print(f"::notice ::Report url: {report_url}")
commit = get_commit(gh, pr_info.sha)
commit.create_status(context=check_name, description=description, state=state, target_url=report_url)

6
tests/ci/metrics_lambda/app.py
View File

@ -70,7 +70,7 @@ def list_runners(access_token):
def group_runners_by_tag(listed_runners):
result = {}
RUNNER_TYPE_LABELS = ['style-checker', 'builder']
RUNNER_TYPE_LABELS = ['style-checker', 'builder', 'func-tester']
for runner in listed_runners:
for tag in runner.tags:
if tag in RUNNER_TYPE_LABELS:
@ -136,7 +136,9 @@ def main(github_secret_key, github_app_id, push_to_cloudwatch):
if push_to_cloudwatch:
push_metrics_to_cloudwatch(group_runners, 'RunnersMetrics/' + group)
else:
print(group, group_runners)
print(group)
for runner in group_runners:
print('\t', runner)
if __name__ == "__main__":

38
tests/queries/0_stateless/00646_url_engine.python
View File

@ -12,8 +12,20 @@ import subprocess
from io import StringIO
from http.server import BaseHTTPRequestHandler, HTTPServer
def get_local_port(host):
with socket.socket() as fd:
def is_ipv6(host):
try:
socket.inet_aton(host)
return False
except:
return True
def get_local_port(host, ipv6):
if ipv6:
family = socket.AF_INET6
else:
family = socket.AF_INET
with socket.socket(family) as fd:
fd.bind((host, 0))
return fd.getsockname()[1]
@ -28,14 +40,23 @@ CLICKHOUSE_PORT_HTTP = os.environ.get('CLICKHOUSE_PORT_HTTP', '8123')
# IP-address of this host accessible from the outside world. Get the first one
HTTP_SERVER_HOST = subprocess.check_output(['hostname', '-i']).decode('utf-8').strip().split()[0]
HTTP_SERVER_PORT = get_local_port(HTTP_SERVER_HOST)
IS_IPV6 = is_ipv6(HTTP_SERVER_HOST)
HTTP_SERVER_PORT = get_local_port(HTTP_SERVER_HOST, IS_IPV6)
# IP address and port of the HTTP server started from this script.
HTTP_SERVER_ADDRESS = (HTTP_SERVER_HOST, HTTP_SERVER_PORT)
HTTP_SERVER_URL_STR = 'http://' + ':'.join(str(s) for s in HTTP_SERVER_ADDRESS) + "/"
if IS_IPV6:
HTTP_SERVER_URL_STR = 'http://' + f'[{str(HTTP_SERVER_ADDRESS[0])}]:{str(HTTP_SERVER_ADDRESS[1])}' + "/"
else:
HTTP_SERVER_URL_STR = 'http://' + f'{str(HTTP_SERVER_ADDRESS[0])}:{str(HTTP_SERVER_ADDRESS[1])}' + "/"
CSV_DATA = os.path.join(tempfile._get_default_tempdir(), next(tempfile._get_candidate_names()))
def get_ch_answer(query):
host = CLICKHOUSE_HOST
if IS_IPV6:
host = f'[{host}]'
url = os.environ.get('CLICKHOUSE_URL', 'http://{host}:{port}'.format(host=CLICKHOUSE_HOST, port=CLICKHOUSE_PORT_HTTP))
return urllib.request.urlopen(url, data=query.encode()).read().decode()
@ -95,8 +116,15 @@ class CSVHTTPServer(BaseHTTPRequestHandler):
def log_message(self, format, *args):
return
class HTTPServerV6(HTTPServer):
address_family = socket.AF_INET6
def start_server(requests_amount):
httpd = HTTPServer(HTTP_SERVER_ADDRESS, CSVHTTPServer)
if IS_IPV6:
httpd = HTTPServerV6(HTTP_SERVER_ADDRESS, CSVHTTPServer)
else:
httpd = HTTPServer(HTTP_SERVER_ADDRESS, CSVHTTPServer)
def real_func():
for i in range(requests_amount):

2
tests/queries/0_stateless/01598_memory_limit_zeros.sql
View File

@ -1,4 +1,4 @@
-- Tags: no-parallel, no-fasttest
SET max_memory_usage = 1, max_untracked_memory = 1000000;
SET max_memory_usage = 1, max_untracked_memory = 1000000, max_threads=40;
select 'test', count(*) from zeros_mt(1000000) where not ignore(zero); -- { serverError 241 }