adriangb commented on PR #16491:
URL: https://github.com/apache/datafusion/pull/16491#issuecomment-2993585382
I think with these fixes to `Display<ScalarValue>` the tests will pass
consistently.
I used this script to test:
```python
#!/usr/bin/env python3
import argparse
import subprocess
from concurrent.futures import ThreadPoolExecutor, as_completed
from threading import Event
def run_test(command, run_num, total_runs, stop_event):
"""Run a single test and return result"""
if stop_event.is_set():
return run_num, "SKIPPED", None
try:
result = subprocess.run(command, shell=True, capture_output=True,
text=True)
status = "PASS" if result.returncode == 0 else "FAIL"
print(f"Run {run_num}/{total_runs}: {status}")
return run_num, status, result
except Exception as e:
print(f"Run {run_num}/{total_runs}: ERROR - {e}")
return run_num, "ERROR", None
def main():
parser = argparse.ArgumentParser(description="Run a command multiple
times and report failure rate")
parser.add_argument("-P", "--parallel", type=int, default=1,
help="Number of parallel jobs (default: 1)")
parser.add_argument("-n", "--runs", type=int, default=100, help="Number
of runs (default: 100)")
parser.add_argument("-x", "--stop-on-failure", action="store_true",
help="Stop at first failure")
parser.add_argument("command", nargs=argparse.REMAINDER, help="Command
to run")
args = parser.parse_args()
command = " ".join(args.command)
print(f"Running command {args.runs} times with {args.parallel} parallel
jobs...")
print(f"Command: {command}")
print("----------------------------------------")
stop_event = Event()
failures = 0
completed_runs = 0
failure_outputs = []
with ThreadPoolExecutor(max_workers=args.parallel) as executor:
# Submit all jobs
futures = []
for i in range(1, args.runs + 1):
future = executor.submit(run_test, command, i, args.runs,
stop_event)
futures.append(future)
# Process results as they complete
for future in as_completed(futures):
run_num, status, result = future.result()
completed_runs += 1
if status == "FAIL" or status == "ERROR":
failures += 1
if result and (result.stdout or result.stderr):
failure_outputs.append((run_num, result.stdout,
result.stderr))
if args.stop_on_failure:
print(f"Stopping at first failure (run {run_num})")
stop_event.set()
# Cancel remaining futures
for f in futures:
f.cancel()
break
print("----------------------------------------")
print("Results:")
print(f"Total runs: {completed_runs}")
print(f"Failures: {failures}")
print(f"Passes: {completed_runs - failures}")
if completed_runs > 0:
failure_rate = (failures * 100) / completed_runs
print(f"Failure rate: {failure_rate:.2f}%")
else:
print("Failure rate: 0%")
# Print failure outputs
if failure_outputs:
print("\n" + "="*50)
print("FAILURE OUTPUTS:")
print("="*50)
for run_num, stdout, stderr in failure_outputs:
print(f"\n--- Run {run_num} ---")
if stdout:
print("STDOUT:")
print(stdout)
if stderr:
print("STDERR:")
print(stderr)
if __name__ == "__main__":
main()
```
And was able to run with no errors:
```bash
./run-test.py -P 10 -n 600 -x cargo test --package datafusion --test fuzz --
fuzz_cases::sort_query_fuzz::sort_query_fuzzer_runner --exact --show-output
```
I'm running a 1200 run to confirm now.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
