GraalPy silent error on multi-threaded code #543

import threading
import sys
from collections import *

def t0(b1,s,res):
    b1.wait()
    try:
        res.append(s.insert(0, 10))
    except Exception as error:
        res.append(repr(error))
def t1(b1,s,res):
    b1.wait()
    try:
        res.append(s.clear())
    except Exception as error:
        res.append(repr(error))
def t2(b1,s,res):
    b1.wait()
    try:
        res.append(s.insert(0, 10))
    except Exception as error:
        res.append(repr(error))
def t3(b1,s,res):
    b1.wait()
    try:
        res.append(s.__ne__([0, 1, 2, 3, 4, 5, 6, 7, 8, 9]))
    except Exception as error:
        res.append(repr(error))
def Test():
  normal_data_structure = [1, 2, 3]
  possible_results = [([10], ['None', 'None', 'None', 'True']),
                     ([], ['None', 'None', 'None', 'True']),
                     ([10, 10], ['None', 'None', 'None', 'True'])]
  threads=[]
  barrier = threading.Barrier(4)
  res = []
  threads.append(threading.Thread(target= t0, args=(barrier, normal_data_structure,res)))
  threads.append(threading.Thread(target= t1, args=(barrier, normal_data_structure,res)))
  threads.append(threading.Thread(target= t2, args=(barrier, normal_data_structure,res)))
  threads.append(threading.Thread(target= t3, args=(barrier, normal_data_structure,res)))
  for i in range(0, len(threads)):
      threads[i].start()
  for i in range(0, len(threads)):
      threads[i].join()
  for i in range(0, len(res)):
      if isinstance(res[i], set):
          temp = list(map(str,list(res[i])))
          temp.sort()
          res[i]= str(temp)
      else:
          res[i]= str(res[i])
  res.sort()
  if (normal_data_structure, res) not in possible_results:
      print("found bug: " + str((normal_data_structure,res)))
  normal_data_structure = [1, 2, 3]

print("test begin...")
for i in range(0,100):
    threads = []
    print(i)
    # if i % 1000 == 0:
        # print(i)
    for i in range(0,100):
        threads.append(threading.Thread(target= Test))
    for t in threads:
        t.start()
    for t in threads:
        t.join()
print("test Done")

import subprocess
import traceback
​
fail_count = 0
for i in range(100):
    try:
        r = subprocess.run(['graalpy-24.2.2-windows-amd64/bin/graalpy.exe',
                        '--log.python.level=FINE', '--log.engine.level=FINE', '--log.launcher.level=FINE',
                        'test.py'], 
                        capture_output=True, # comment this line if you want to see the live counter from the subprocess
                    check=True,
                    text=True)
        print(f"Done with {i}")
        if r.stderr:
            with open(f'good_output{i}.txt', 'w+') as f:
                f.write(r.stderr)
    except subprocess.CalledProcessError as e:
        fail_count += 1
        print(f"Failcount: {fail_count}")
        print(f"Subprocess Error: [{e}]")
        print("Return code:", e.returncode)
        print('stderr written to error_output.txt')
        if e.stderr:
            with open(f'error_output{i}.txt', 'w+') as f:
                f.write(e.stderr)
    # dead code below
    except Exception:
        print("Something else went wrong")
        traceback.print_exc()
print(f"Subprocess failed {fail_count} times")