Files
wehub-resource-sync 498b235461
Build and test / Build and test AMD64 Ubuntu 22.04 (push) Failing after 0s
Publish Builder / amazonlinux2023 (push) Failing after 1s
Build and test / UT for Go (push) Has been skipped
Publish KRTE Images / KRTE (push) Failing after 1s
Build and test / Integration Test (push) Has been skipped
Build and test / Upload Code Coverage (push) Has been skipped
Publish Builder / rockylinux9 (push) Failing after 1s
Publish Builder / ubuntu22.04 (push) Failing after 0s
Publish Builder / ubuntu24.04 (push) Failing after 0s
Publish Gpu Builder / publish-gpu-builder (push) Failing after 1s
Publish Test Images / PyTest (push) Failing after 0s
Build and test / UT for Cpp (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 12:31:17 +08:00

138 lines
5.1 KiB
Python

import glob
import os
import threading
import time
import pytest
from chaos import constants
from utils.util_log import test_log as log
from yaml import full_load
def check_config(chaos_config):
if not chaos_config.get("kind", None):
raise Exception("kind must be specified")
if not chaos_config.get("spec", None):
raise Exception("spec must be specified")
if "action" not in chaos_config.get("spec", None):
raise Exception("action must be specified in spec")
if "selector" not in chaos_config.get("spec", None):
raise Exception("selector must be specified in spec")
return True
def reset_counting(checkers={}):
"""reset checker counts for all checker threads"""
for ch in checkers.values():
ch.reset()
def gen_experiment_config(yaml):
"""load the yaml file of chaos experiment"""
with open(yaml) as f:
_config = full_load(f)
f.close()
return _config
def start_monitor_threads(checkers={}):
"""start the threads by checkers"""
tasks = []
for k, ch in checkers.items():
ch._keep_running = True
t = threading.Thread(target=ch.keep_running, args=(), name=k, daemon=True)
t.start()
tasks.append(t)
return tasks
def check_thread_status(tasks):
"""check the status of all threads"""
for t in tasks:
if t.is_alive():
log.info(f"thread {t.name} is still running")
else:
log.info(f"thread {t.name} is not running")
def get_env_variable_by_name(name):
"""get env variable by name"""
try:
env_var = os.environ[name]
log.debug(f"env_variable: {env_var}")
return str(env_var)
except Exception as e:
log.debug(f"fail to get env variables, error: {str(e)}")
return None
def get_chaos_yamls():
"""get chaos yaml file(s) from configured environment path"""
chaos_env = get_env_variable_by_name(constants.CHAOS_CONFIG_ENV)
if chaos_env is not None:
if os.path.isdir(chaos_env):
log.debug(f"chaos_env is a dir: {chaos_env}")
return glob.glob(chaos_env + "chaos_*.yaml")
elif os.path.isfile(chaos_env):
log.debug(f"chaos_env is a file: {chaos_env}")
return [chaos_env]
else:
# not a valid directory, return default
pass
log.debug("not a valid directory or file, return default chaos config path")
return glob.glob(constants.TESTS_CONFIG_LOCATION + constants.ALL_CHAOS_YAMLS)
def reconnect(connections, alias="default", timeout=360):
"""trying to connect by connection alias"""
is_connected = False
start = time.time()
end = time.time()
while not is_connected or end - start < timeout:
try:
connections.connect(alias)
is_connected = True
except Exception as e:
log.debug(f"fail to connect, error: {str(e)}")
time.sleep(10)
end = time.time()
else:
log.info(f"failed to reconnect after {timeout} seconds")
return connections.connect(alias)
def assert_statistic(checkers, expectations={}, succ_rate_threshold=0.95, fail_rate_threshold=0.49):
for k in checkers.keys():
# expect succ if no expectations
succ_rate = checkers[k].succ_rate()
total = checkers[k].total()
average_time = checkers[k].average_time
error_messages = getattr(checkers[k], "error_messages", set())
if expectations.get(k, "") == constants.FAIL:
log.info(f"Expect Fail: {str(k)} succ rate {succ_rate}, total: {total}, average time: {average_time:.4f}")
pytest.assume(
succ_rate < fail_rate_threshold or total < 2,
f"Expect Fail: {str(k)} succ rate {succ_rate}, total: {total}, average time: {average_time:.4f}",
)
else:
log.info(f"Expect Succ: {str(k)} succ rate {succ_rate}, total: {total}, average time: {average_time:.4f}")
# Build assertion message with error details
assert_msg = (
f"Expect Succ: {str(k)} succ rate {succ_rate}, total: {total}, average time: {average_time:.4f}"
)
if error_messages:
error_details = "; ".join(error_messages)
assert_msg += f", unique errors({len(error_messages)}): [{error_details}]"
if total == 0:
# Checker never completed any operation. This indicates either the checker
# thread failed to start or the service was completely unavailable. Treat
# it as a real failure rather than silently skipping.
pytest.assume(False, f"{str(k)} never completed any operation (total=0)")
else:
# total >= 1: at least one operation completed, succ_rate is meaningful.
# We no longer require total > 2 because low-frequency checkers (e.g.
# AddFieldChecker, AddVectorFieldChecker) legitimately complete only a few
# operations within a 10-minute window, and succ_rate=1.0 with total=2 is
# a valid passing result.
pytest.assume(succ_rate >= succ_rate_threshold, assert_msg)