我以这种方式使用多重处理:import multiprocessing as mp
def worker(thread_id, tasks, results):
tmp_dir = 'temp_for_{}'.format(thread_id)
os.makedirs(tmp_dir)
try:
while not tasks.empty():
data = tasks.get()
response = process_pdf(data, tmp_dir)
results.put(response)
except (keyboardInterrupt, SystemExit):
log.info('Interrupt signal received in thread %s.', thread_id)
except Queue.Empty:
pass
except Exception:
log.error("Unexpected error in %s", thread_id, exc_info=True)
finally:
shutil.rmtree(tmp_dir)
log.info("Thread %s exit", thread_id)
if __name__ == "__main__":
tasks, results = mp.Queue(), mp.Queue()
for record in cursor.select(query):
tasks.put(record)
manager = mp.Manager()
workers = [mp.Process(target=worker, args=(i, tasks, results)) for i in xrange(8)]
for worker in workers:
worker.start()
try:
for worker in workers:
worker.join()
except (KeyboardInterrupt, SystemExit):
log.info('Interrupt signal received in main. Cleaning up main')
finally:
log.info('Got %s results. Saving', results.qsize())
while not results.empty():
cursor.update_one('documents', 'id', results.get())
cursor.close()
以下是我运行此代码时的输出:
^{pr2}$
然后我在等待了一段时间后输入^C,并得到以下输出:^C14:37:16 15/10 INFO: Interrupt signal received in main. Cleaning up main
14:37:16 15/10 INFO: Got 16 results. Saving
我得到了所有线程的回溯:Process Process-9:
Traceback (most recent call last):
File "/usr/lib64/python2.7/multiprocessing/process.py", line 261, in _bootstrap
util._exit_function()
File "/usr/lib64/python2.7/multiprocessing/util.py", line 328, in _exit_function
util._exit_function()
File "/usr/lib64/python2.7/multiprocessing/util.py", line 274, in _run_finalizers
finalizer()
File "/usr/lib64/python2.7/multiprocessing/util.py", line 207, in __call__
res = self._callback(*self._args, **self._kwargs)
File "/usr/lib64/python2.7/multiprocessing/queues.py", line 218, in _finalize_join
thread.join()
File "/usr/lib64/python2.7/threading.py", line 952, in join
thread.join()
File "/usr/lib64/python2.7/threading.py", line 340, in wait
waiter.acquire()
KeyboardInterrupt
为什么要绞死?如果重要的话,我可以添加process_pdf()使用subprocess.Popen()运行一些子流程。在