Develop Reference

processing very large text files in parallel using multiprocessing and threading

I have found several other questions that touch on this topic but none that are quite like my situation.
I have several very large text files (3+ gigabytes in size).
I would like to process them (say 2 documents) in parallel using multiprocessing. As part of my processing (within a single process) I need to make an API call and because of this would like to have each process have it's own threads to run asynchronously.
I have came up with a simplified example ( I have commented the code to try to explain what I think it should be doing):
import multiprocessing
from threading import Thread
import threading
from queue import Queue
import time
def process_huge_file(*, file_, batch_size=250, num_threads=4):
# create APICaller instance for each process that has it's own Queue
api_call = APICaller()
batch = []
# create threads that will run asynchronously to make API calls
# I expect these to immediately block since there is nothing in the Queue (which is was
# the api_call.run depends on to make a call
threads = []
for i in range(num_threads):
thread = Thread(target=api_call.run)
threads.append(thread)
thread.start()
for thread in threads:
thread.join()
####
# start processing the file line by line
for line in file_:
# if we are at our batch size, add the batch to the api_call to to let the threads do
# their api calling
if i % batch_size == 0:
api_call.queue.put(batch)
else:
# add fake line to batch
batch.append(fake_line)
class APICaller:
def __init__(self):
# thread safe queue to feed the threads which point at instances
of these APICaller objects
self.queue = Queue()
def run(self):
print("waiting for something to do")
self.queue.get()
print("processing item in queue")
time.sleep(0.1)
print("finished processing item in queue")
if __name__ == "__main__":
# fake docs
fake_line = "this is a fake line of some text"
# two fake docs with line length == 1000
fake_docs = [[fake_line] * 1000 for i in range(2)]
####
num_processes = 2
procs = []
for idx, doc in enumerate(fake_docs):
proc = multiprocessing.Process(target=process_huge_file, kwargs=dict(file_=doc))
proc.start()
procs.append(proc)
for proc in procs:
proc.join()
As the code is now, "waiting for something to do" prints 8 times (makes sense 4 threads per process) and then it stops or "deadlocks" which is not what I expect - I expect it to start sharing time with the threads as soon as I start putting items in the Queue but the code does not appear to make it this far. I ordinarily would step through to find a hang up but I still don't have a solid understanding of how to best debug using Threads (another topic for another day).
In the meantime, can someone help me figure out why my code is not doing what it should be doing?

I have made a few adjustments and additions and the code appears to do what it is supposed to now. The main adjustments are: adding a CloseableQueue class (from Brett Slatkins Effective Python Item 55), and ensuring that I call close and join on the queue so that the threads properly exit. Full code with these changes below:
import multiprocessing
from threading import Thread
import threading
from queue import Queue
import time
from concurrency_utils import CloseableQueue
def sync_process_huge_file(*, file_, batch_size=250):
batch = []
for idx, line in enumerate(file_):
# do processing on the text
if idx % batch_size == 0:
time.sleep(0.1)
batch = []
# api_call.queue.put(batch)
else:
computation = 0
for i in range(100000):
computation += i
batch.append(line)
def process_huge_file(*, file_, batch_size=250, num_threads=4):
api_call = APICaller()
batch = []
# api call threads
threads = []
for i in range(num_threads):
thread = Thread(target=api_call.run)
threads.append(thread)
thread.start()
for idx, line in enumerate(file_):
# do processing on the text
if idx % batch_size == 0:
api_call.queue.put(batch)
else:
computation = 0
for i in range(100000):
computation += i
batch.append(line)
for _ in threads:
api_call.queue.close()
api_call.queue.join()
for thread in threads:
thread.join()
class APICaller:
def __init__(self):
self.queue = CloseableQueue()
def run(self):
for item in self.queue:
print("waiting for something to do")
pass
print("processing item in queue")
time.sleep(0.1)
print("finished processing item in queue")
print("exiting run")
if __name__ == "__main__":
# fake docs
fake_line = "this is a fake line of some text"
# two fake docs with line length == 1000
fake_docs = [[fake_line] * 10000 for i in range(2)]
####
time_s = time.time()
num_processes = 2
procs = []
for idx, doc in enumerate(fake_docs):
proc = multiprocessing.Process(target=process_huge_file, kwargs=dict(file_=doc))
proc.start()
procs.append(proc)
for proc in procs:
proc.join()
time_e = time.time()
print(f"took {time_e-time_s} ")
class CloseableQueue(Queue):
SENTINEL = object()
def __init__(self, **kwargs):
super().__init__(**kwargs)
def close(self):
self.put(self.SENTINEL)
def __iter__(self):
while True:
item = self.get()
try:
if item is self.SENTINEL:
return # exit thread
yield item
finally:
self.task_done()
As expected this is a great speedup from running synchronously - 120 seconds vs 50 seconds.

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

kill threads later a time in python

I have a python code with threads, and i need that if in for example 1 hour the threads are not finished, finish all threads and finish the script, and if the hour are not complete wait that all my threads finish.
I try with a daemon thread, and with a sleep of the hour, and if the hour is complete use a: sys.exit() but it not works to me, because always wait to my sleep threadh, then my script wait until the thread finished and the sys.exit() does not work.
import socket, threading, time, sys
from sys import argv
import os
acc_time=0
transactions_ps=5
ins = open(sys.argv[1],'r')
msisdn_list = []
for line in ins:
msisdn_list.append (line.strip('\n'))
# print line
ins.close()
def worker(msisdn_list):
semaphore.acquire()
global transactions_ps
print " ***** ", threading.currentThread().getName(), "Lanzado"
count=1
acc_time=0
print "len: ",len(msisdn_list)
for i in msisdn_list:
try:
init=time.time()
time.sleep(2)
print "sleeping...",i
time.sleep(4)
final=time.time()
acc_time = acc_time+final-init
print acc_time
except IOError:
print "Connection failed",sys.exc_info()[0]
print "Deteniendo ",threading.currentThread().getName()
semaphore.release()
def kill_process(secs_to_die):
time.sleep(secs_to_die)
sys.exit()
seconds_to_die=3600
thread_kill = threading.Thread(target = kill_process, args=(seconds_to_die,))
thread_kill.start()
max_con=5
semaphore = threading.BoundedSemaphore(max_con)
for i in range(0,28,transactions_ps):
w = threading.Thread(target=worker, args=(msisdn_list[i:i+transactions_ps-1],))
w.setDaemon(True)
w.start()
How can to do it

A minimal change to your code that would fix the issue is threading.Barrier:
barrier = Barrier(number_of_threads, timeout=3600)
# create (number_of_threads - 1) threads, pass them barrier
# each thread calls barrier.wait() on exit
barrier.wait() # after number_of_threads .wait() calls or on timeout it returns
A simpler alternative is to use multiprocessing.dummy.Pool that creates daemon threads:
from multiprocessing.dummy import Pool # use threads
start = timer()
endtime = start + 3600
for result in pool.imap_unordered(work, args):
if timer() > endtime:
exit("timeout")
The code doesn't timeout until a work item is done i.e., it expects that processing a single item from the list doesn't take long.
Complete example:
#!/usr/bin/env python3
import logging
import multiprocessing as mp
from multiprocessing.dummy import Pool
from time import monotonic as timer, sleep
info = mp.get_logger().info
def work(i):
info("start %d", i)
sleep(1)
info("end %d", i)
seconds_to_die = 3600
max_con = 5
mp.log_to_stderr().setLevel(logging.INFO) # enable logging
pool = Pool(max_con) # no more than max_con at a time
start = timer()
endtime = start + seconds_to_die
for _ in pool.imap_unordered(work, range(10000)):
if timer() > endtime:
exit("timeout")

You may refer to this implementation of KThread:
http://python.todaysummary.com/q_python_45717.html

the efficiency compare between gevent and thread

Recently,I'm working on a gevent demo and I try to compare the efficiency between gevent and thread. Generally speaking，the gevent code should be more efficient than the thread code. But when I use time command to profile the program, I get the unusual result(my command is time python FILENAME.py 50 1000,the last two parameters means pool number or thread number,so I change the two number in the table below). The result shows that the thread is more efficient than the gevent code,so I want to know why this happen and what's wrong with my program? Thanks.
gevent VS thread
My code is below(The main idea is use thread or gevent to send multi HTTP request):
******This is the thread version code******
# _*_ coding: utf-8 _*_
import sys
reload(sys)
sys.setdefaultencoding("utf8")
import requests
import threading
import time
import urllib2
finished = 0
def GetUrl(pagenum):
url = 'http://opendata.baidu.com/zhaopin/s?p=mini&wd=%B0%D9%B6%C8&pn=' + \
str(pagenum*20) + '&rn=20'
return url
def setUrlSet():
for i in xrange(requestnum):
urlnum = i % 38
urlset.append(GetUrl(urlnum))
def GetResponse(pagenum):
try:
r = requests.get(urlset[pagenum])
except Exception, e:
print e
pass
def DigJobByPagenum(pagenum, requestnum):
init_num = pagenum
print '%d begin' % init_num
while pagenum < requestnum:
GetResponse(pagenum)
pagenum += threadnum
print '%d over' % init_num
def NormalThread(threadnum):
startime = time.time()
print "%s is running..." % threading.current_thread().name
threads = []
global finished, requestnum
for i in xrange(threadnum):
thread = threading.Thread(target=DigJobByPagenum, args=(i, requestnum))
threads.append(thread)
for t in threads:
t.daemon = True
t.start()
for t in threads:
t.join()
finished += 1
endtime = time.time()
print "%s is stop.The total time is %0.2f" % \
(threading.current_thread().name, (endtime - startime))
def GetAvageTime(array):
alltime = 0.0
for i in array:
alltime += i
avageTime = alltime/len(array)
return avageTime
if __name__ == '__main__':
threadnum = int(sys.argv[1])
requestnum = int(sys.argv[2])
print 'threadnum : %s,requestnum %s ' % (threadnum, requestnum)
originStartTime = time.time()
urlset = []
setUrlSet()
NormalThread(threadnum)
******This is the gevent verison code******
# _*_ coding: utf-8 _*_
import sys
reload(sys)
sys.setdefaultencoding("utf8")
from gevent import monkey
monkey.patch_all()
import gevent
from gevent import pool
import requests
import time
finished = 0
def GetUrl(pagenum):
url = 'http://opendata.baidu.com/zhaopin/s?p=mini&wd=%B0%D9%B6%C8&pn=' + \
str(pagenum*20) + '&rn=20'
return url
def setUrlSet():
for i in xrange(requestnum):
urlnum = i % 38
urlset.append(GetUrl(urlnum))
def GetResponse(url):
startime = time.time()
r = requests.get(url)
print url
endtime = time.time()
spendtime = endtime - startime
NormalSpendTime.append(spendtime)
global finished
finished += 1
print finished
def GetAvageTime(array):
alltime = 0.0
for i in array:
alltime += i
avageTime = alltime/len(array)
return avageTime
def RunAsyncJob():
jobpool = pool.Pool(concurrent)
for url in urlset:
jobpool.spawn(GetResponse, url)
jobpool.join()
endtime = time.time()
allSpendTime = endtime - originStartime
print 'Total spend time is %0.3f, total request num is %s within %s \
seconds' % (allSpendTime, finished, timeoutNum)
print 'Each request time is %0.3f' % (GetAvageTime(NormalSpendTime))
if __name__ == '__main__':
concurrent = int(sys.argv[1])
requestnum = int(sys.argv[2])
timeoutNum = 100
NormalSpendTime = []
urlset = []
urlActionList = []
setUrlSet()
originStartime = time.time()
RunAsyncJob()

Try
gevent.monkey.patch_all(httplib=True)
It seems that by default gevent does not patch httplib (have a look at http://www.gevent.org/gevent.monkey.html : httplib=False) so you are actually doing blocking requests and you lose all advantages of the asynchronous framework. Although I'm not sure whether requests uses httplib.
If that doesn't work, then have a look at this lib:
https://github.com/kennethreitz/grequests

Re: httplib=False
You are already using requests library to make web calls. It has gevent flavour called grequests:
https://github.com/kennethreitz/grequests
Overall I don't immediately see much reason to prefer one style of threading to the other, if your pool is so small. Of course real threads are relatively heavy (start with 8MB stack), but you have to take that into proportion to the size of your job.
My take, try both (done), verify you are doing both right (to do) and let numbers do the talking.

python threads exits immediately

I am new to python.
I am trying out Hbase thrift client using thrift. I got some code on net, which I just modify to work with latest version of thrift but when I run the code , it just exit, no threads are started.
Here is the code.
import json, traceback, sys, datetime, time, logging, threading, random
import logging.handlers
import thrift
sys.path.append('gen-py')
from thrift.transport.TSocket import TSocket
from thrift.transport.TTransport import TBufferedTransport
from thrift.protocol import TBinaryProtocol
from hbase import THBaseService
gWritenItems = 0
gStartT = 0
gEndT = 0
recordsPerBatch = 300 #reports per client per day
columns = 3
#config
concurrent = 10
records = 60000#6000000 #6 million
bytesPerRecord = 1024
mylock = threading.RLock()
class writeThread(threading.Thread):
def __init__(self, threadname, RecordsThreadwillwrite):
threading.Thread.__init__(self, name = threadname)
bytesPerColumn = int(bytesPerRecord/columns) - 11 #suppose 3 columns
self.columnvalue = "value_" + "x"*bytesPerColumn + "_endv"
self.tbwBatch = int (RecordsThreadwillwrite / recordsPerBatch)
self.transport = TBufferedTransport(TSocket('pnq-adongrevm1', 5151), 40960)
self.transport.open()
protocol = TBinaryProtocol.TBinaryProtocol(self.transport)
self.client = THBaseService.Client(protocol)
self.table = "example"
def run(self):
print "+%s start" % (self.getName())
global gEndT
global gWritenItems
threadWritenItem = 0
for loopidx in xrange(0, self.tbwBatch):
self.write_hbase() #write
threadWritenItem += recordsPerBatch
mylock.acquire()
gEndT = time.time()
gWritenItems += threadWritenItem
print "%s done, %s seconds past, %d reocrds saved" % (self.getName(), gEndT-gStartT, gWritenItems)
mylock.release()
self.transport.close()
def write_hbase(self): #write 50 rowkyes, and 3 column families in each rowkey
print self.getName(), "Start write"
batchmutations = []
for i in xrange(0, recordsPerBatch): # write to db, 300 items together
mutations = []
rowkey = "RK_%s_%s" % (random.random(), time.time())
for ii in xrange(0, columns):
mutations.append(THBaseService.TPut(row=rowkey, columnValues=[TColumnValue(family="f1", qualifier="%s"%ii, value=self.columnvalue)]))
self.client.putMultiple(self.table,mutations)
itemsPerThread = int(records / concurrent)
for threadid in xrange(0, concurrent):
gStartT = time.time()
t = writeThread("Thread_%s" % threadid, itemsPerThread)
t.start();
print "%d thread created, each thread will write %d records" % (concurrent, itemsPerThread)
I just get a message 10 thread created, each thread will write 6000 records

Yep, this is because you are not waiting for threads to finish their job, so the main thread just exits. Try this:
itemsPerThread = int(records / concurrent)
threads = []
for threadid in xrange(0, concurrent):
gStartT = time.time()
t = writeThread("Thread_%s" % threadid, itemsPerThread)
t.start();
threads.append(t)
# wait until all finish the job
for t in threads:
t.join()
EDIT Ha, I don't think I'm right here, because you didn't mark your threads as daemons. It should work even without joining. But have a look at this code:
class CustomThread(threading.Thread):
def run(self):
print "test"
for x in xrange(0, 10):
t = CustomThread()
t.start()
It will always reach print "test" line no matter what. So in your code it should always reach print "+%s start" % (self.getName()) no matter what. Are you sure it doesn't work? :)
If it doesn't, then there are only two possibilities:
There is a blocking operation and/or exception in your __init__ method. But then it would not reach final print;
concurrent variable is 0 for some reason (which is not consistent with the final print).