Confusing on subprocess.Popen - python

This problem makes me confused
I just want to run 1 command on 18 different input file so I've wrote it like
while filenames or running:
while filenames and len(running) < N_CORES:
filename = filenames.pop(0)
print 'Submiting process for %s' % filename
cmd = COMMAND % dict(filename=filename, localdir=localdir)
p = subprocess.Popen(cmd, shell=True)
print 'running:', cmd
running.append((cmd, p))
i = 0
while i < len(running):
(cmd, p) = running[i]
ret = p.poll()
if ret is not None:
rep = open('Crux.report.%d' % (report_number), 'w')
rep.write('Command: %s' % cmd)
print localdir
print 'done!'
report_number += 1
running.remove((cmd, p))
else:
i += 1
time.sleep(1)
But when I've run it after 3 hours all of the process going to Sleep mode.
But if I call the command from terminal manually (for all of the different files), all of them have been Ok.
Any help would be appreciate.

I assume you want to run 18 processes (one process per file) with no more than N_CORES processes in parallel.
The simplest way could be to use multiprocessing.Pool here:
import multiprocessing as mp
import subprocess
def process_file(filename):
try:
return filename, subprocess.call([cmd, filename], cwd=localdir)
except OSError:
return filename, None # failed to start subprocess
if __name__ == "__main__":
pool = mp.Pool()
for result in pool.imap_unordered(process_file, filenames):
# report result here

Whithout knowing what your subprocesses are supposed to do and how long they are supposed to be running it's hard to give an accurate answer here.
Some problems I see with your program:
you check for i < len(running), while incrementing i and removing from running.
Either use a counter or check if the list still contains elements, but don't do both at the same time. This way you will break out of the loop halfway.
you increment i each time a process has not finished, you probably want to increment if a process has finished.

Related

Display Popen.communicate() in real time [duplicate]

I have a python subprocess that I'm trying to read output and error streams from. Currently I have it working, but I'm only able to read from stderr after I've finished reading from stdout. Here's what it looks like:
process = subprocess.Popen(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
stdout_iterator = iter(process.stdout.readline, b"")
stderr_iterator = iter(process.stderr.readline, b"")
for line in stdout_iterator:
# Do stuff with line
print line
for line in stderr_iterator:
# Do stuff with line
print line
As you can see, the stderr for loop can't start until the stdout loop completes. How can I modify this to be able to read from both in the correct order the lines come in?
To clarify: I still need to be able to tell whether a line came from stdout or stderr because they will be treated differently in my code.
The code in your question may deadlock if the child process produces enough output on stderr (~100KB on my Linux machine).
There is a communicate() method that allows to read from both stdout and stderr separately:
from subprocess import Popen, PIPE
process = Popen(command, stdout=PIPE, stderr=PIPE)
output, err = process.communicate()
If you need to read the streams while the child process is still running then the portable solution is to use threads (not tested):
from subprocess import Popen, PIPE
from threading import Thread
from Queue import Queue # Python 2
def reader(pipe, queue):
try:
with pipe:
for line in iter(pipe.readline, b''):
queue.put((pipe, line))
finally:
queue.put(None)
process = Popen(command, stdout=PIPE, stderr=PIPE, bufsize=1)
q = Queue()
Thread(target=reader, args=[process.stdout, q]).start()
Thread(target=reader, args=[process.stderr, q]).start()
for _ in range(2):
for source, line in iter(q.get, None):
print "%s: %s" % (source, line),
See:
Python: read streaming input from subprocess.communicate()
Non-blocking read on a subprocess.PIPE in python
Python subprocess get children's output to file and terminal?
Here's a solution based on selectors, but one that preserves order, and streams variable-length characters (even single chars).
The trick is to use read1(), instead of read().
import selectors
import subprocess
import sys
p = subprocess.Popen(
["python", "random_out.py"], stdout=subprocess.PIPE, stderr=subprocess.PIPE
)
sel = selectors.DefaultSelector()
sel.register(p.stdout, selectors.EVENT_READ)
sel.register(p.stderr, selectors.EVENT_READ)
while True:
for key, _ in sel.select():
data = key.fileobj.read1().decode()
if not data:
exit()
if key.fileobj is p.stdout:
print(data, end="")
else:
print(data, end="", file=sys.stderr)
If you want a test program, use this.
import sys
from time import sleep
for i in range(10):
print(f" x{i} ", file=sys.stderr, end="")
sleep(0.1)
print(f" y{i} ", end="")
sleep(0.1)
The order in which a process writes data to different pipes is lost after write.
There is no way you can tell if stdout has been written before stderr.
You can try to read data simultaneously from multiple file descriptors in a non-blocking way
as soon as data is available, but this would only minimize the probability that the order is incorrect.
This program should demonstrate this:
#!/usr/bin/env python
# -*- coding: utf-8 -*-
import os
import select
import subprocess
testapps={
'slow': '''
import os
import time
os.write(1, 'aaa')
time.sleep(0.01)
os.write(2, 'bbb')
time.sleep(0.01)
os.write(1, 'ccc')
''',
'fast': '''
import os
os.write(1, 'aaa')
os.write(2, 'bbb')
os.write(1, 'ccc')
''',
'fast2': '''
import os
os.write(1, 'aaa')
os.write(2, 'bbbbbbbbbbbbbbb')
os.write(1, 'ccc')
'''
}
def readfds(fds, maxread):
while True:
fdsin, _, _ = select.select(fds,[],[])
for fd in fdsin:
s = os.read(fd, maxread)
if len(s) == 0:
fds.remove(fd)
continue
yield fd, s
if fds == []:
break
def readfromapp(app, rounds=10, maxread=1024):
f=open('testapp.py', 'w')
f.write(testapps[app])
f.close()
results={}
for i in range(0, rounds):
p = subprocess.Popen(['python', 'testapp.py'], stdout=subprocess.PIPE
, stderr=subprocess.PIPE)
data=''
for (fd, s) in readfds([p.stdout.fileno(), p.stderr.fileno()], maxread):
data = data + s
results[data] = results[data] + 1 if data in results else 1
print 'running %i rounds %s with maxread=%i' % (rounds, app, maxread)
results = sorted(results.items(), key=lambda (k,v): k, reverse=False)
for data, count in results:
print '%03i x %s' % (count, data)
print
print "=> if output is produced slowly this should work as whished"
print " and should return: aaabbbccc"
readfromapp('slow', rounds=100, maxread=1024)
print
print "=> now mostly aaacccbbb is returnd, not as it should be"
readfromapp('fast', rounds=100, maxread=1024)
print
print "=> you could try to read data one by one, and return"
print " e.g. a whole line only when LF is read"
print " (b's should be finished before c's)"
readfromapp('fast', rounds=100, maxread=1)
print
print "=> but even this won't work ..."
readfromapp('fast2', rounds=100, maxread=1)
and outputs something like this:
=> if output is produced slowly this should work as whished
and should return: aaabbbccc
running 100 rounds slow with maxread=1024
100 x aaabbbccc
=> now mostly aaacccbbb is returnd, not as it should be
running 100 rounds fast with maxread=1024
006 x aaabbbccc
094 x aaacccbbb
=> you could try to read data one by one, and return
e.g. a whole line only when LF is read
(b's should be finished before c's)
running 100 rounds fast with maxread=1
003 x aaabbbccc
003 x aababcbcc
094 x abababccc
=> but even this won't work ...
running 100 rounds fast2 with maxread=1
003 x aaabbbbbbbbbbbbbbbccc
001 x aaacbcbcbbbbbbbbbbbbb
008 x aababcbcbcbbbbbbbbbbb
088 x abababcbcbcbbbbbbbbbb
This works for Python3 (3.6):
p = subprocess.Popen(cmd, stdout=subprocess.PIPE,
stderr=subprocess.PIPE, universal_newlines=True)
# Read both stdout and stderr simultaneously
sel = selectors.DefaultSelector()
sel.register(p.stdout, selectors.EVENT_READ)
sel.register(p.stderr, selectors.EVENT_READ)
ok = True
while ok:
for key, val1 in sel.select():
line = key.fileobj.readline()
if not line:
ok = False
break
if key.fileobj is p.stdout:
print(f"STDOUT: {line}", end="")
else:
print(f"STDERR: {line}", end="", file=sys.stderr)
from https://docs.python.org/3/library/subprocess.html#using-the-subprocess-module
If you wish to capture and combine both streams into one, use
stdout=PIPE and stderr=STDOUT instead of capture_output.
so the easiest solution would be:
process = subprocess.Popen(command, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
stdout_iterator = iter(process.stdout.readline, b"")
for line in stdout_iterator:
# Do stuff with line
print line
I know this question is very old, but this answer may help others who stumble upon this page in researching a solution for a similar situation, so I'm posting it anyway.
I've built a simple python snippet that will merge any number of pipes into a single one. Of course, as stated above, the order cannot be guaranteed, but this is as close as I think you can get in Python.
It spawns a thread for each of the pipes, reads them line by line and puts them into a Queue (which is FIFO). The main thread loops through the queue, yielding each line.
import threading, queue
def merge_pipes(**named_pipes):
r'''
Merges multiple pipes from subprocess.Popen (maybe other sources as well).
The keyword argument keys will be used in the output to identify the source
of the line.
Example:
p = subprocess.Popen(['some', 'call'],
stdin=subprocess.PIPE,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE)
outputs = {'out': log.info, 'err': log.warn}
for name, line in merge_pipes(out=p.stdout, err=p.stderr):
outputs[name](line)
This will output stdout to the info logger, and stderr to the warning logger
'''
# Constants. Could also be placed outside of the method. I just put them here
# so the method is fully self-contained
PIPE_OPENED=1
PIPE_OUTPUT=2
PIPE_CLOSED=3
# Create a queue where the pipes will be read into
output = queue.Queue()
# This method is the run body for the threads that are instatiated below
# This could be easily rewritten to be outside of the merge_pipes method,
# but to make it fully self-contained I put it here
def pipe_reader(name, pipe):
r"""
reads a single pipe into the queue
"""
output.put( ( PIPE_OPENED, name, ) )
try:
for line in iter(pipe.readline,''):
output.put( ( PIPE_OUTPUT, name, line.rstrip(), ) )
finally:
output.put( ( PIPE_CLOSED, name, ) )
# Start a reader for each pipe
for name, pipe in named_pipes.items():
t=threading.Thread(target=pipe_reader, args=(name, pipe, ))
t.daemon = True
t.start()
# Use a counter to determine how many pipes are left open.
# If all are closed, we can return
pipe_count = 0
# Read the queue in order, blocking if there's no data
for data in iter(output.get,''):
code=data[0]
if code == PIPE_OPENED:
pipe_count += 1
elif code == PIPE_CLOSED:
pipe_count -= 1
elif code == PIPE_OUTPUT:
yield data[1:]
if pipe_count == 0:
return
This works for me (on windows):
https://github.com/waszil/subpiper
from subpiper import subpiper
def my_stdout_callback(line: str):
print(f'STDOUT: {line}')
def my_stderr_callback(line: str):
print(f'STDERR: {line}')
my_additional_path_list = [r'c:\important_location']
retcode = subpiper(cmd='echo magic',
stdout_callback=my_stdout_callback,
stderr_callback=my_stderr_callback,
add_path_list=my_additional_path_list)

Multiprocessing Queue.get() hangs

I'm trying to implement basic multiprocessing and I've run into an issue. The python script is attached below.
import time, sys, random, threading
from multiprocessing import Process
from Queue import Queue
from FrequencyAnalysis import FrequencyStore, AnalyzeFrequency
append_queue = Queue(10)
database = FrequencyStore()
def add_to_append_queue(_list):
append_queue.put(_list)
def process_append_queue():
while True:
item = append_queue.get()
database.append(item)
print("Appended to database in %.4f seconds" % database.append_time)
append_queue.task_done()
return
def main():
database.load_db()
print("Database loaded in %.4f seconds" % database.load_time)
append_queue_process = Process(target=process_append_queue)
append_queue_process.daemon = True
append_queue_process.start()
#t = threading.Thread(target=process_append_queue)
#t.daemon = True
#t.start()
while True:
path = raw_input("file: ")
if path == "exit":
break
a = AnalyzeFrequency(path)
a.analyze()
print("Analyzed file in %.4f seconds" % a._time)
add_to_append_queue(a.get_results())
append_queue.join()
#append_queue_process.join()
database.save_db()
print("Database saved in %.4f seconds" % database.save_time)
sys.exit(0)
if __name__=="__main__":
main()
The AnalyzeFrequency analyzes the frequencies of words in a file and get_results() returns a sorted list of said words and frequencies. The list is very large, perhaps 10000 items.
This list is then passed to the add_to_append_queue method which adds it to a queue. The process_append_queue takes the items one by one and adds the frequencies to a "database". This operation takes a bit longer than the actual analysis in main() so I am trying to use a seperate process for this method. When I try and do this with the threading module, everything works perfectly fine, no errors. When I try and use Process, the script hangs at item = append_queue.get().
Could someone please explain what is happening here, and perhaps direct me toward a fix?
All answers appreciated!
UPDATE
The pickle error was my fault, it was just a typo. Now I am using the Queue class within multiprocessing but the append_queue.get() method still hangs.
NEW CODE
import time, sys, random
from multiprocessing import Process, Queue
from FrequencyAnalysis import FrequencyStore, AnalyzeFrequency
append_queue = Queue()
database = FrequencyStore()
def add_to_append_queue(_list):
append_queue.put(_list)
def process_append_queue():
while True:
database.append(append_queue.get())
print("Appended to database in %.4f seconds" % database.append_time)
return
def main():
database.load_db()
print("Database loaded in %.4f seconds" % database.load_time)
append_queue_process = Process(target=process_append_queue)
append_queue_process.daemon = True
append_queue_process.start()
#t = threading.Thread(target=process_append_queue)
#t.daemon = True
#t.start()
while True:
path = raw_input("file: ")
if path == "exit":
break
a = AnalyzeFrequency(path)
a.analyze()
print("Analyzed file in %.4f seconds" % a._time)
add_to_append_queue(a.get_results())
#append_queue.join()
#append_queue_process.join()
print str(append_queue.qsize())
database.save_db()
print("Database saved in %.4f seconds" % database.save_time)
sys.exit(0)
if __name__=="__main__":
main()
UPDATE 2
This is the database code:
class FrequencyStore:
def __init__(self):
self.sorter = Sorter()
self.db = {}
self.load_time = -1
self.save_time = -1
self.append_time = -1
self.sort_time = -1
def load_db(self):
start_time = time.time()
try:
file = open("results.txt", 'r')
except:
raise IOError
self.db = {}
for line in file:
word, count = line.strip("\n").split("=")
self.db[word] = int(count)
file.close()
self.load_time = time.time() - start_time
def save_db(self):
start_time = time.time()
_db = []
for key in self.db:
_db.append([key, self.db[key]])
_db = self.sort(_db)
try:
file = open("results.txt", 'w')
except:
raise IOError
file.truncate(0)
for x in _db:
file.write(x[0] + "=" + str(x[1]) + "\n")
file.close()
self.save_time = time.time() - start_time
def create_sorted_db(self):
_temp_db = []
for key in self.db:
_temp_db.append([key, self.db[key]])
_temp_db = self.sort(_temp_db)
_temp_db.reverse()
return _temp_db
def get_db(self):
return self.db
def sort(self, _list):
start_time = time.time()
_list = self.sorter.mergesort(_list)
_list.reverse()
self.sort_time = time.time() - start_time
return _list
def append(self, _list):
start_time = time.time()
for x in _list:
if x[0] not in self.db:
self.db[x[0]] = x[1]
else:
self.db[x[0]] += x[1]
self.append_time = time.time() - start_time
Comments suggest you're trying to run this on Windows. As I said in a comment,
If you're running this on Windows, it can't work - Windows doesn't
have fork(), so each process gets its own Queue and they have nothing
to do with each other. The entire module is imported "from scratch" by
each process on Windows. You'll need to create the Queue in main(),
and pass it as an argument to the worker function.
Here's fleshing out what you need to do to make it portable, although I removed all the database stuff because it's irrelevant to the problems you've described so far. I also removed the daemon fiddling, because that's usually just a lazy way to avoid shutting down things cleanly, and often as not will come back to bite you later:
def process_append_queue(append_queue):
while True:
x = append_queue.get()
if x is None:
break
print("processed %d" % x)
print("worker done")
def main():
import multiprocessing as mp
append_queue = mp.Queue(10)
append_queue_process = mp.Process(target=process_append_queue, args=(append_queue,))
append_queue_process.start()
for i in range(100):
append_queue.put(i)
append_queue.put(None) # tell worker we're done
append_queue_process.join()
if __name__=="__main__":
main()
The output is the "obvious" stuff:
processed 0
processed 1
processed 2
processed 3
processed 4
...
processed 96
processed 97
processed 98
processed 99
worker done
Note: because Windows doesn't (can't) fork(), it's impossible for worker processes to inherit any Python object on Windows. Each process runs the entire program from its start. That's why your original program couldn't work: each process created its own Queue, wholly unrelated to the Queue in the other process. In the approach shown above, only the main process creates a Queue, and the main process passes it (as an argument) to the worker process.
queue.Queue is thread-safe, but doesn't work across processes. This is quite easy to fix, though. Instead of:
from multiprocessing import Process
from Queue import Queue
You want:
from multiprocessing import Process, Queue

how to add non blocking stderr capture to threaded popen's

I've got a python 3 script i use to backup and encrypt mysqldump files and im having a particular issues with one database that is 67gb after encryption & compression.
The mysqldump is outputting errorcode 3, so i'd like to catch the actual error message, as this could mean a couple of things.
The random thing is the backup file is the right size, so not sure what the error means. it worked once on this database...
the code looks like the below and i'd really appreciate some help on how to add non-blocking capture of stderr when the return code is anything but 0 for both p1 and p2.
Also, if im doing anything glaringly obvious wrong, please do let me know, as i'd like to make sure this is a reliable process. it has been working fine on my databases under 15gb compressed.
def dbbackup():
while True:
item = q.get()
#build up folder structure, daily, weekly, monthy & project
genfile = config[item]['DBName'] + '-' + dateyymmdd + '-'
genfile += config[item]['PubKey'] + '.sql.gpg'
if os.path.isfile(genfile):
syslog.syslog(item + ' ' + genfile + ' exists, removing')
os.remove(genfile)
syslog.syslog(item + ' will be backed up as ' + genfile)
args = ['mysqldump', '-u', config[item]['UserNm'],
'-p' + config[item]['Passwd'], '-P', config[item]['Portnu'],
'-h', config[item]['Server']]
args.extend(config[item]['MyParm'].split())
args.append(config[item]['DBName'])
p1 = subprocess.Popen(args, stdout=subprocess.PIPE)
p2 = subprocess.Popen(['gpg', '-o', genfile, '-r',
config[item]['PubKey'], '-z', '9', '--encrypt'], stdin=p1.stdout)
p2.wait()
if p2.returncode == 0:
syslog.syslog(item + ' encryption successful')
else:
syslog.syslog(syslog.LOG_CRIT, item + ' encryption failed '+str(p2.returncode))
p1.terminate()
p1.wait()
if p1.returncode == 0:
#does some uploads of the file etc..
else:
syslog.syslog(syslog.LOG_CRIT, item + ' extract failed '+str(p1.returncode))
q.task_done()
def main():
db2backup = []
for settingtest in config:
db2backup.append(settingtest)
if len(db2backup) >= 1:
syslog.syslog('Backups started')
for database in db2backup:
q.put(database)
syslog.syslog(database + ' added to backup queue')
q.join()
syslog.syslog('Backups finished')
q = queue.Queue()
config = configparser.ConfigParser()
config.read('backup.cfg')
backuptype = 'daily'
dateyymmdd = datetime.datetime.now().strftime('%Y%m%d')
for i in range(2):
t = threading.Thread(target=dbbackup)
t.daemon = True
t.start()
if __name__ == '__main__':
main()
Simplify your code:
avoid unnecessary globals, pass parameters to the corresponding functions instead
avoid reimplementing a thread pool (it hurts readability and it misses convience features accumulated over the years).
The simplest way to capture stderr is to use stderr=PIPE and .communicate() (blocking call):
#!/usr/bin/env python3
from configparser import ConfigParser
from datetime import datetime
from multiprocessing.dummy import Pool
from subprocess import Popen, PIPE
def backup_db(item, conf): # config[item] == conf
"""Run `mysqldump ... | gpg ...` command."""
genfile = '{conf[DBName]}-{now:%Y%m%d}-{conf[PubKey]}.sql.gpg'.format(
conf=conf, now=datetime.now())
# ...
args = ['mysqldump', '-u', conf['UserNm'], ...]
with Popen(['gpg', ...], stdin=PIPE) as gpg, \
Popen(args, stdout=gpg.stdin, stderr=PIPE) as db_dump:
gpg.communicate()
error = db_dump.communicate()[1]
if gpg.returncode or db_dump.returncode:
error
def main():
config = ConfigParser()
with open('backup.cfg') as file: # raise exception if config is unavailable
config.read_file(file)
with Pool(2) as pool:
pool.starmap(backup_db, config.items())
if __name__ == "__main__":
main()
NOTE: no need to call db_dump.terminate() if gpg dies prematurely: mysqldump dies when it tries to write something to the closed gpg.stdin.
If there are huge number of items in the config then you could use pool.imap() instead of pool.starmap() (the call should be modified slightly).
For robustness, wrap backup_db() function to catch and log all exceptions.

Run python process (using Pool of Multiprocessing ) parallel for batch

See, I need to write a code for ~quarter million input files to run on batch. I saw this post: https://codereview.stackexchange.com/questions/20416/python-parallelization-using-popen
I can't figure it out how to implement this in my code.
What I want
I want to give each process specific number of cores or in other words, specific number of processes only can run at certain time.
If one process is finished another one should takes its place.
My code (using subprocess)
Main.py
import subprocess
import os
import multiprocessing
import time
MAXCPU = multiprocessing.cpu_count()
try:
cp = int(raw_input("Enter Number of CPU's to use (Total %d) = "%MAXCPU))
assert cp <= MAXCPU
except:
print "Bad command taking all %d cores"%MAXCPU
cp =MAXCPU # set MAXCPU as CPU
list_pdb = [i for i in os.listdir(".") if i.endswith(".pdb")] # Input PDB files
assert len(list_pdb) != 0
c = {}
d = {}
t = {}
devnull = file("Devnull","wb")
for each in range(0, len(list_pdb), cp): # Number of cores in Use = 4
for e in range(cp):
if each + e < len(list_pdb):
args = ["sh", "Child.sh", list_pdb[each + e], str(cp)]
p = subprocess.Popen(args, shell=False,
stdout=devnull, stderr=devnull)
c[p.pid] = p
print "Started Process : %s" % list_pdb[each + e]
while c:
print c.keys()
pid, status = os.wait()
if pid in c:
print "Ended Process"
del c[pid]
devnull.close()
Child.sh
#!/bin/sh
sh grand_Child.sh
sh grand_Child.sh
sh grand_Child.sh
sh grand_Child.sh
# Some heavy processes with $1
grand_Child.sh
#!/bin/sh
sleep 5
Output
Here's a version of the code using multiprocessing.Pool. It's a lot simpler, as the module does nearly all the work!
This version also does:
lots of logging, when a proc starts/ends
prints how many files will be processed
lets you process more than numcpus at a time
Often when running multiprocess jobs, it's best to run more processes than CPUs. Different procs will wait on I/O, vs waiting for CPU. Often people run 2n+1, so for a 4 proc system they run 2*4+1 or 9 procs for a job. (I generally hardcode "5" or "10" until there's a reason to change, I'm lazy that way :) )
Enjoy!
source
import glob
import multiprocessing
import os
import subprocess
MAXCPU = multiprocessing.cpu_count()
TEST = False
def do_work(args):
path,numproc = args
curproc = multiprocessing.current_process()
print curproc, "Started Process, args={}".format(args)
devnull = open(os.devnull, 'w')
cmd = ["sh", "Child.sh", path, str(numproc)]
if TEST:
cmd.insert(0, 'echo')
try:
return subprocess.check_output(
cmd, shell=False,
stderr=devnull,
)
finally:
print curproc, "Ended Process"
if TEST:
cp = MAXCPU
list_pdb = glob.glob('t*.py')
else:
cp = int(raw_input("Enter Number of processes to use (%d CPUs) = " % MAXCPU))
list_pdb = glob.glob('*.pdb') # Input PDB files
# assert cp <= MAXCPU
print '{} files, {} procs'.format(len(list_pdb), cp)
assert len(list_pdb) != 0
pool = multiprocessing.Pool(cp)
print pool.map(
do_work, [ (path,cp) for path in list_pdb ],
)
pool.close()
pool.join()
output
27 files, 4 procs
<Process(PoolWorker-2, started daemon)> Started Process, args=('tdownload.py', 4)
<Process(PoolWorker-2, started daemon)> Ended Process
<Process(PoolWorker-2, started daemon)> Started Process, args=('tscapy.py', 4)
<Process(PoolWorker-2, started daemon)> Ended Process

process stop working while queue is not empty

I try to write a script in python to convert url into its corresponding ip. Since the url file is huge (nearly 10GB), so I'm trying to use multiprocessing lib.
I create one process to write output to file and a set of processes to convert url.
Here is my code:
import multiprocessing as mp
import socket
import time
num_processes = mp.cpu_count()
sentinel = None
def url2ip(inqueue, output):
v_url = inqueue.get()
print 'v_url '+v_url
try:
v_ip = socket.gethostbyname(v_url)
output_string = v_url+'|||'+v_ip+'\n'
except:
output_string = v_url+'|||-1'+'\n'
print 'output_string '+output_string
output.put(output_string)
print output.full()
def handle_output(output):
f_ip = open("outputfile", "a")
while True:
output_v = output.get()
if output_v:
print 'output_v '+output_v
f_ip.write(output_v)
else:
break
f_ip.close()
if __name__ == '__main__':
output = mp.Queue()
inqueue = mp.Queue()
jobs = []
proc = mp.Process(target=handle_output, args=(output, ))
proc.start()
print 'run in %d processes' % num_processes
for i in range(num_processes):
p = mp.Process(target=url2ip, args=(inqueue, output))
jobs.append(p)
p.start()
for line in open('inputfile','r'):
print 'ori '+line.strip()
inqueue.put(line.strip())
for i in range(num_processes):
# Send the sentinal to tell Simulation to end
inqueue.put(sentinel)
for p in jobs:
p.join()
output.put(None)
proc.join()
However, it did not work. It did produce several outputs (4 out of 10 urls in the test file) but it just suddenly stops while queues are not empty (I did check queue.empty())
Could anyone suggest what's wrong?Thanks
You're workers exit after processing a single url each, they need to loop internally until they get the sentinel. However, you should probably just look at multiprocessing.pool instead, as that does the bookkeeping for you.

Categories

Resources