Fokko commented on PR #8015:
URL: https://github.com/apache/iceberg/pull/8015#issuecomment-1634317651
Just out curiosity, where are you able to run multi-processing?
```
export PYICEBERG_CONCURRENCY_MODE=process
➜ docker-spark-iceberg git:(main) time python3 /tmp/vo.py
Traceback (most recent call last):
File "<string>", line 1, in <module>
File
"/Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.9/lib/python3.9/multiprocessing/spawn.py",
line 116, in spawn_main
exitcode = _main(fd, parent_sentinel)
File
"/Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.9/lib/python3.9/multiprocessing/spawn.py",
line 125, in _main
prepare(preparation_data)
File
"/Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.9/lib/python3.9/multiprocessing/spawn.py",
line 236, in prepare
_fixup_main_from_path(data['init_main_from_path'])
File
"/Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.9/lib/python3.9/multiprocessing/spawn.py",
line 287, in _fixup_main_from_path
main_content = runpy.run_path(main_path,
File
"/Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.9/lib/python3.9/runpy.py",
line 268, in run_path
return _run_module_code(code, init_globals, run_name,
File
"/Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.9/lib/python3.9/runpy.py",
line 97, in _run_module_code
_run_code(code, mod_globals, init_globals,
File
"/Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.9/lib/python3.9/runpy.py",
line 87, in _run_code
exec(code, run_globals)
File "/tmp/vo.py", line 11, in <module>
df = table.scan().to_arrow()
File
"/Users/fokkodriesprong/Desktop/iceberg/python/pyiceberg/table/__init__.py",
line 825, in to_arrow
self.plan_files(),
File
"/Users/fokkodriesprong/Desktop/iceberg/python/pyiceberg/table/__init__.py",
line 784, in plan_files
*executor.map(
File
"/Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.9/lib/python3.9/concurrent/futures/process.py",
line 726, in map
results = super().map(partial(_process_chunk, fn),
File
"/Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.9/lib/python3.9/concurrent/futures/_base.py",
line 597, in map
fs = [self.submit(fn, *args) for args in zip(*iterables)]
File
"/Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.9/lib/python3.9/concurrent/futures/_base.py",
line 597, in <listcomp>
fs = [self.submit(fn, *args) for args in zip(*iterables)]
File
"/Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.9/lib/python3.9/concurrent/futures/process.py",
line 697, in submit
self._adjust_process_count()
File
"/Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.9/lib/python3.9/concurrent/futures/process.py",
line 675, in _adjust_process_count
p.start()
File
"/Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.9/lib/python3.9/multiprocessing/process.py",
line 121, in start
self._popen = self._Popen(self)
File
"/Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.9/lib/python3.9/multiprocessing/context.py",
line 284, in _Popen
return Popen(process_obj)
File
"/Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.9/lib/python3.9/multiprocessing/popen_spawn_posix.py",
line 32, in __init__
super().__init__(process_obj)
File
"/Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.9/lib/python3.9/multiprocessing/popen_fork.py",
line 19, in __init__
self._launch(process_obj)
File
"/Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.9/lib/python3.9/multiprocessing/popen_spawn_posix.py",
line 42, in _launch
prep_data = spawn.get_preparation_data(process_obj._name)
File
"/Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.9/lib/python3.9/multiprocessing/spawn.py",
line 154, in get_preparation_data
_check_not_importing_main()
File
"/Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.9/lib/python3.9/multiprocessing/spawn.py",
line 134, in _check_not_importing_main
raise RuntimeError('''
RuntimeError:
An attempt has been made to start a new process before the
current process has finished its bootstrapping phase.
This probably means that you are not using fork to start your
child processes and you have forgotten to use the proper idiom
in the main module:
if __name__ == '__main__':
freeze_support()
...
The "freeze_support()" line can be omitted if the program
is not going to be frozen to produce an executable.
```
Where:
```python
from pyiceberg.catalog import load_catalog
catalog = load_catalog('local')
table = catalog.load_table('nyc.taxis')
expected_rows = 15885533
for _ in range(10):
df = table.scan().to_arrow()
assert len(df) == expected_rows, f"Got {len(df)} rows, instead of
{expected_rows}"
```
And local points to my local
[docker-spark-iceberg](https://github.com/tabular-io/docker-spark-iceberg/tree/main/spark)
setup, so I don't have S3 latency.
--
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]
