Я использую самую легкую / простую dask многопроцессорную систему, которая является некластерной локальной Client:
from distributed import Client
client = Client()
Даже в этом случае: первый случай вызова dask.bag.compute() приводит к следующему:
Connected to pydev debugger (build 191.7141.48)
Traceback (most recent call last):
File "/Applications/PyCharm.app/Contents/helpers/pydev/_pydevd_bundle/pydevd_comm.py", line 383, in _on_run
r = self.sock.recv(1024)
OSError: [Errno 9] Bad file descriptor
Traceback (most recent call last):
File "/Applications/PyCharm.app/Contents/helpers/pydev/_pydevd_bundle/pydevd_comm.py", line 383, in _on_run
r = self.sock.recv(1024)
OSError: [Errno 9] Bad file descriptor
Traceback (most recent call last):
File "/Applications/PyCharm.app/Contents/helpers/pydev/_pydevd_bundle/pydevd_comm.py", line 383, in _on_run
r = self.sock.recv(1024)
OSError: [Errno 9] Bad file descriptor
В результате вы можете более или менее подбросить монету о том, будет ли выполняться программа или произойдет ошибка с исключением из-за связи.Вот что происходит, когда переворачивается «хвосты»:
Connected to pydev debugger (build 191.7141.48)
Traceback (most recent call last):
File "/Applications/PyCharm.app/Contents/helpers/pydev/_pydevd_bundle/pydevd_comm.py", line 383, in _on_run
r = self.sock.recv(1024)
OSError: [Errno 9] Bad file descriptor
Process ForkServerProcess-3:
Traceback (most recent call last):
File "/usr/local/lib/python3.7/site-packages/distributed/core.py", line 178, in __init__
from .counter import Digest
ImportError: cannot import name 'Digest' from 'distributed.counter' (/usr/local/lib/python3.7/site-packages/distributed/counter.py)
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/usr/local/Cellar/python/3.7.3/Frameworks/Python.framework/Versions/3.7/lib/python3.7/multiprocessing/process.py", line 297, in _bootstrap
self.run()
File "/usr/local/Cellar/python/3.7.3/Frameworks/Python.framework/Versions/3.7/lib/python3.7/multiprocessing/process.py", line 99, in run
self._target(*self._args, **self._kwargs)
File "/usr/local/lib/python3.7/site-packages/distributed/process.py", line 181, in _run
target(*args, **kwargs)
File "/usr/local/lib/python3.7/site-packages/distributed/nanny.py", line 587, in _run
worker = Worker(*worker_args, **worker_kwargs)
File "/usr/local/lib/python3.7/site-packages/distributed/worker.py", line 552, in __init__
**kwargs
File "/usr/local/lib/python3.7/site-packages/distributed/node.py", line 76, in __init__
io_loop=self.io_loop,
File "/usr/local/lib/python3.7/site-packages/distributed/core.py", line 180, in __init__
self.digests = defaultdict(partial(Digest, loop=self.io_loop))
File "/usr/local/Cellar/python/3.7.3/Frameworks/Python.framework/Versions/3.7/lib/python3.7/contextlib.py", line 130, in __exit__
self.gen.throw(type, value, traceback)
File "/usr/local/lib/python3.7/site-packages/distributed/utils.py", line 179, in ignoring
yield
SystemError: error return without exception set
distributed.nanny - WARNING - Worker process 20417 exited with status 1
Traceback (most recent call last):
File "_pydevd_frame_eval/pydevd_frame_evaluator_darwin_37_64.pyx", line 95, in _pydevd_frame_eval.pydevd_frame_evaluator_darwin_37_64.get_bytecode_while_frame_eval
KeyError: '/usr/local/lib/python3.7/site-packages/distributed/bokeh/__init__.py'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/Applications/PyCharm.app/Contents/helpers/pydev/pydevd.py", line 1758, in <module>
main()
File "/Applications/PyCharm.app/Contents/helpers/pydev/pydevd.py", line 1752, in main
globals = debugger.run(setup['file'], None, None, is_module)
File "/Applications/PyCharm.app/Contents/helpers/pydev/pydevd.py", line 1147, in run
pydev_imports.execfile(file, globals, locals) # execute the script
File "/Applications/PyCharm.app/Contents/helpers/pydev/_pydev_imps/_pydev_execfile.py", line 18, in execfile
exec(compile(contents+"\n", file, 'exec'), glob, loc)
File "/git/huddl/python/hamspam/enron.py", line 205, in <module>
client = Client()
File "/usr/local/lib/python3.7/site-packages/distributed/client.py", line 712, in __init__
self.start(timeout=timeout)
File "/usr/local/lib/python3.7/site-packages/distributed/client.py", line 858, in start
sync(self.loop, self._start, **kwargs)
File "/usr/local/lib/python3.7/site-packages/distributed/utils.py", line 331, in sync
six.reraise(*error[0])
File "/usr/local/lib/python3.7/site-packages/six.py", line 693, in reraise
raise value
File "/usr/local/lib/python3.7/site-packages/distributed/utils.py", line 316, in f
result[0] = yield future
File "/usr/local/lib/python3.7/site-packages/tornado/gen.py", line 729, in run
value = future.result()
File "/usr/local/lib/python3.7/site-packages/tornado/gen.py", line 736, in run
yielded = self.gen.throw(*exc_info) # type: ignore
File "/usr/local/lib/python3.7/site-packages/distributed/client.py", line 928, in _start
yield self.cluster
File "/usr/local/lib/python3.7/site-packages/tornado/gen.py", line 729, in run
value = future.result()
File "/usr/local/Cellar/python/3.7.3/Frameworks/Python.framework/Versions/3.7/lib/python3.7/asyncio/tasks.py", line 603, in _wrap_awaitable
return (yield from awaitable.__await__())
File "/usr/local/lib/python3.7/site-packages/tornado/gen.py", line 736, in run
yielded = self.gen.throw(*exc_info) # type: ignore
File "/usr/local/lib/python3.7/site-packages/distributed/deploy/local.py", line 284, in _start
yield [self._start_worker(**self.worker_kwargs) for i in range(n_workers)]
File "/usr/local/lib/python3.7/site-packages/tornado/gen.py", line 729, in run
value = future.result()
File "/usr/local/lib/python3.7/site-packages/tornado/gen.py", line 501, in callback
result_list.append(f.result())
File "/usr/local/lib/python3.7/site-packages/tornado/gen.py", line 742, in run
yielded = self.gen.send(value)
File "/usr/local/lib/python3.7/site-packages/distributed/deploy/local.py", line 316, in _start_worker
raise gen.TimeoutError("Worker failed to start")
tornado.util.TimeoutError: Worker failed to start
Любой совет по этому поводу?
При использовании режима LocalCluster будет еще больше проблем / осложнений.-но это будет сохранено для другого вопроса.