I create 3 processes and want the function wirte1 to write value 'A,B,C' to queue1 ,and function read1 read value from queue1 and put it to queue2 ,in the same time, function read2 read value from queue2, but value B,C can't read from queue2 in time and the process finished.
from multiprocessing import Process, Queue,Manager,Pool,Lock
import os, time, random
#向队列1写数据
def write1(q1,lock):
lock.acquire()
for value in ['A', 'B', 'C']:
print ('Put %s to queue111...%s' % (value,str(os.getpid())))
q1.put(value)
time.sleep(1)
lock.release()
#从队列1读取数据并写入队列2
def read1(q1,q2,lock):
lock.acquire()
while True:
time.sleep(1)
value=q1.get()
# if value is None:break
print('Get %s from queue111.%s' % (value,str(os.getpid())))
q2.put(value)
print('Put %s to queue222...%s' % (value,str(os.getpid())))
lock.release()
def read2(q2,lock):
lock.acquire()
while True:
# if not q2.empty() or not q1.empty():
time.sleep(2)
value=q2.get(True)
print('Get %s from queue222.%s' % (value,os.getpid()))
lock.release()
if __name__=='__main__':
manager = Manager()
# 父进程创建Queue，并传给各个子进程：
q1 = manager.Queue()
q2 = manager.Queue()
lock1 = manager.Lock()
lock2 = manager.Lock()
lock3 = manager.Lock()
start=time.time()
p = Pool()
# pw = p.apply_async(write1, args=(q1,lock1,))
pw = Process(target=write1,args=(q1,lock1,))
# time.sleep(0.5)
# pr = p.apply_async(read1, args=(q1,q2,lock2,))
# pr2 = p.apply_async(read2, args=(q2,lock3))
pr=Process(target=read1,args=(q1,q2,lock2,))
pr2 = Process(target=read2,args=(q2,lock3,))
pw.start()
pr.start()
pr2.start()
# p.close()
# p.join()
pw.join()
pr.terminate()
pr2.terminate()
end=time.time()
# print
print('finished!!')
print(end-start)
the output is:
Put A to queue111...77678 Put B to queue111...77678 Get A from queue111.77680 Put A to queue222...77680 Put C to queue111...77678 Get A from queue222.77681 Get B from queue111.77680 Put B to queue222...77680 Get C from queue111.77680 Put C to queue222...77680 finished!! 3.025238275527954
You can’t use terminate to control a system like this: it races with completing the actual work. Instead, make your loops not be infinite, probably by using a sentinel value in each Queue (as in one commented-out line).
Inside a worker thread I am generating a data frame . Trying to put this into the queue passed to the worker thread is failing. In fact trying to put any values into the queue is failing.
The part of the code that is failing inside the worker thread task1() is given below:
df = pd.DataFrame([[1,2,3,4],[3,4,5,6]])
qmdlvalues.put(df)
mdltiming = time.time() - start
qmdlparams.put(paramval)
qtiming.put(mdltiming)
Complete code
import threading
import queue
from sklearn.manifold import TSNE
import os
import time
def write_tsne_op(opdata,fname,header):
with open(fname, 'w') as outfile:
outfile.write(header)
for data_slice in opdata:
np.savetxt(outfile, data_slice,delimiter=",")
def task1(qmdlvalues,qmdlparams,qtiming,paramval):
start = time.time()
#tmpmdl1 = TSNE(perplexity=100,early_exaggeration=1, n_components=2,random_state=0,verbose=1)
#qmdlvalues.put(tmpmdl1.fit_transform(dense_mx))
df = pd.DataFrame([[1,2,3,4],[3,4,5,6]])
qmdlvalues.put(df)
mdltiming = time.time() - start
qmdlparams.put(paramval)
qtiming.put(mdltiming)
print(df)
print(str(mdltiming))
print(paramval)
def task2(qmdlvalues,qmdlparams,qtiming,paramval):
start = time.time()
#tmpmdl2 = TSNE(perplexity=100,early_exaggeration=10, n_components=2,random_state=0,verbose=1)
#qmdlvalues.put(tmpmdl2.fit_transform(dense_mx2))
qmdlvalues.put(pd.DataFrame([[1,2,3,4],[3,4,5,6]]))
qmdlparams.put(paramval)
mdltiming = time.time() - start
qtiming.put(mdltiming)
if __name__ == "__main__":
dense_mx2 = dense_mx
dense_mx3 = dense_mx
qmdlvl = queue.Queue()
qmdlch = queue.Queue()
qtme = queue.Queue()
mdlvalues = pd.DataFrame()
t1 = threading.Thread(target=task1,args=(qmdlvl,qmdlch,qtme,"#perplex: 100 early exag: 1 timing:$_plex100_exag1.csv"), name='t1')
t2 = threading.Thread(target=task2,args=(qmdlvl,qmdlch,qtme,"#perplex: 100 early exag: 10 timing:$_plex100_exag10.cv"), name='t2')
# starting threads
t1.start()
t2.start()
while True:
if qmdlvl.empty():
print("Queue closed. Exiting thread.")
break
try:
item = qmdlvl.get(timeout=.5)
except:
continue
print("Got item:", item)
# wait until all threads finish
t1.join()
t2.join()
Below is the actual output I am getting from the code in the main
while True:
if qmdlvl.empty():
print("Queue closed. Exiting thread.")
break
try:
item = qmdlvl.get(timeout=.5)
except:
continue
print("Got item:", item)
ID of process running main program: 6456
Main thread name: MainThread
Queue closed. Exiting thread.
I want to able to put the data frame into a queue inside the worker thread and access the same data frame in the main thread.
There are parameter mis-matches in my earlier code those have been corrected an a full working code presented below.
I stored the output of t-SNE directly into the queue and retrieved the same in the main thread. The next progression would be convert this to thread pool and sub-classing.
import threading
import queue
from sklearn.manifold import TSNE
import os
import time
def write_tsne_op(opdata,fname,header):
with open(fname, 'w') as outfile:
outfile.write(header)
for data_slice in opdata:
np.savetxt(outfile, data_slice,delimiter=",")
def task1(ip_matrix,qmdlvalues,qmdlparam,plex,exag,qmdltime,qmdlhrfn,hderfname):
string=""
start=0
end=0
mdltiming=0
start = time.time()
tmpmdl1 = TSNE(perplexity=plex,early_exaggeration=exag, n_components=2,random_state=0,verbose=1)
qmdlvalues.put(tmpmdl1.fit_transform(ip_matrix))
string = str(plex)+ "$" + str(exag)
qmdlparam.put(string)
qmdlhrfn.put(hderfname)
end = time.time()
mdltimig = end - start
print(str(mdltiming)+"time")
qmdltime.put(mdltiming)
def task2(ip_matrix,qmdlvalues,qmdlparam,plex,exag,qmdltime,qmdlhrfn,hderfname):
string=""
start=0
end=0
mdltiming=0
start = time.time()
tmpmdl2 = TSNE(perplexity=plex,early_exaggeration=exag, n_components=2,random_state=0,verbose=1)
qmdlvalues.put(tmpmdl2.fit_transform(ip_matrix))
string = str(plex)+ "$" + str(exag)
qmdlparam.put(string)
qmdlhrfn.put(hderfname)
end = time.time()
mdltimig = end - start
qmdltime.put(mdltiming)
def task3(ip_matrix,qmdlvalues,qmdlparam,plex,exag,qmdltime,qmdlhrfn,hderfname):
string=""
start=0
end=0
mdltiming=0
start = time.time()
tmpmdl3 = TSNE(perplexity=plex,early_exaggeration=exag, n_components=2,random_state=0,verbose=1)
qmdlvalues.put(tmpmdl3.fit_transform(ip_matrix))
string = str(plex)+ "$" + str(exag)
qmdlparam.put(string)
qmdlhrfn.put(hderfname)
end = time.time()
mdltimig = end - start
qmdltime.put(mdltiming)
def task4(ip_matrix,qmdlvalues,qmdlparam,plex,exag,qmdltime,qmdlhrfn,hderfname):
string=""
start=0
end=0
mdltiming=0
start = time.time()
tmpmdl4 = TSNE(perplexity=plex,early_exaggeration=exag, n_components=2,random_state=0,verbose=1)
qmdlvalues.put(tmpmdl4.fit_transform(ip_matrix))
string = str(plex)+ "$" + str(exag)
qmdlparam.put(string)
qmdlhrfn.put(hderfname)
end = time.time()
mdltimig = end - start
qmdltime.put(mdltiming)
if __name__ == "__main__":
# print ID of current process
print("ID of process running main program: {}".format(os.getpid()))
# print name of main thread
print("Main thread name: {}".format(threading.main_thread().name))
dense_mx2 = dense_mx
dense_mx3 = dense_mx
dense_mx4 = dense_mx
qmdlvl = queue.Queue()
qmdlch = queue.Queue()
qmdltme = queue.Queue()
qmdlhdrfname = queue.Queue()
perplex = 200
# creating threads
exag=10
t1 = threading.Thread(target=task1,args=(dense_mx,qmdlvl,qmdlch,perplex,exag,qmdltme,qmdlhdrfname,"#perplex: 200 early exag: 10 timing:$_plex200_exag10.csv"), name='t1')
exag=30
t2 = threading.Thread(target=task2,args=(dense_mx2,qmdlvl,qmdlch,perplex,exag,qmdltme,qmdlhdrfname,"#perplex: 200 early exag: 30 timing:$_plex200_exag30.cv"), name='t2')
exag=50
t3 = threading.Thread(target=task3,args=(dense_mx3,qmdlvl,qmdlch,perplex,exag,qmdltme,qmdlhdrfname,"#perplex: 200 early exag: 50 timing:$_plex200_exag50.csv"), name='t3')
exag=100
t4 = threading.Thread(target=task4,args=(dense_mx4,qmdlvl,qmdlch,perplex,exag,qmdltme,qmdlhdrfname,"#perplex: 200 early exag: 100 timing:$_plex200_exag100.cv"), name='t4')
# starting threads
t1.start()
t2.start()
t3.start()
t4.start()
# wait until all threads finish
t1.join()
t2.join()
t3.join()
t4.join()
while True:
if qmdlvl.empty():
print("Queue closed. Exiting thread.")
break
try:
item1 = qmdlvl.get(timeout=.5)
item2 = qmdlch.get(timeout=.5)
item3 = qmdltme.get(timeout=.5)
header,fname = qmdlhdrfname.get(timeout=.5).split('$')
except:
continue
write_tsne_op(item1,fname,header)
So Im trying to code a really simple Internet Download Manager Spoof with Python 2.7
It is supposed to query a files HTTP header, get the byte range and spread the download among a no.of threads(I hard-coded 2 for simplicity) according to the byte range and later join the file parts together again.
The problem is my console log tells me that only 1 thread is started.
[EDIT] The problem has been solved. Find the working code below.
Here is my source:
from __future__ import print_function
import threading
import urllib
import urllib2
import time
threads = []
# url to open
url = "http://www.sample-videos.com/video/mp4/720/big_buck_bunny_720p_1mb.mp4"
u = urllib.urlopen(url)
# define file
file_name = "test.mp4"
f = open(file_name, 'wb')
# open url and get header info
def get_file_size(url):
stream_size = u.info()['Content-Length']
end = stream_size
return end
start = 0
#get stream size
end = get_file_size(url)
# specify block size
block_sz = 512
#algo to divide work among 2 threads
def calculate_no_of_bytes_for_thread1():
full_stream_size = end
first_thread = {'start':0, 'end':(int(full_stream_size)/2)}
print(first_thread)
return first_thread
#algo to divide work among 2 threads
def calculate_no_of_bytes_for_thread2():
full_stream_size = end
second_thread= {'start':int(full_stream_size)/2,'end': int(full_stream_size)}
print(second_thread)
return second_thread
# download function
def download_thread(url ,id,start,end):
current_size = int(float(start)/1024)
total_size = int(float(end)/1024)
print ("Start at_"+str(current_size) + "Ends at_" + str(total_size))
# specify request range and init stream
req = urllib2.Request(url)
req.headers['Range'] = 'bytes=%s-%s' % (start, end)
data = urllib2.urlopen(req)
while True:
buffer = u.read(block_sz)
if not buffer:
break
start += len(buffer)
f.write(buffer)
thread_id = id
#percentage = (current_size * 100 / total_size)
status = str(thread_id) + "_" + str(current_size) + "_" +str(total_size)
print (status)
#starts 2 threads
def start_threads():
for i in range(2):
#if first loop, start thread 1
if(i==1):
start = calculate_no_of_bytes_for_thread1().get('start')
end = calculate_no_of_bytes_for_thread1().get('end')
print("Thread 1 started")
t = threading.Thread(target=download_thread, args=(url,i,start,end))
t.start()
threads.append( t)
#if second loop, start thread 1
if(i==2):
start = calculate_no_of_bytes_for_thread2().get('start')
end = calculate_no_of_bytes_for_thread2().get('end')
print("Thread 2 started")
t = threading.Thread(target=download_thread, args=(url,i,start,end))
t.start()
threads.append( t)
# Join threads back (order doesn't matter, you just want them all)
for i in threads:
i.join()
#start benchmarking
start_time = time.clock()
start_threads()
print ("Finito!")
end_time = time.clock()
benchmark = str(end_time - start_time)
print ("Download took_" +benchmark)
f.close()
And the output:
{'start': 0, 'end': 527868}
{'start': 0, 'end': 527868}
Thread 1 started
Start at_0Ends at_515
1_0_515
1_0_515
Finito!
Download took_6.97844422658
Working code:
from __future__ import print_function
import threading
import urllib
import urllib2
import time
threads = []
parts = {}
# url to open
url = "http://www.sample-videos.com/audio/mp3/india-national-anthem.mp3"
u = urllib.urlopen(url)
# define file
file_name = "test.mp3"
f = open(file_name, 'wb')
# open url and get header info
def get_file_size(url):
stream_size = u.info()['Content-Length']
file_size = stream_size
return file_size
start = 0
#get stream size
end = get_file_size(url)
# specify block size
block_sz = 512
#algo to divide work among 2 threads
def calculate_no_of_bytes_for_thread1():
full_stream_size = end
first_thread = {'start':0, 'end':(int(full_stream_size)/2)}
print(first_thread)
return first_thread
#algo to divide work among 2 threads
def calculate_no_of_bytes_for_thread2():
full_stream_size = end
second_thread= {'start':int(full_stream_size)/2,'end': int(full_stream_size)}
print(second_thread)
return second_thread
# download function
def download_thread(url ,id,start,end):
current_size = int(float(start)/1024)
total_size = int(float(end)/1024)
print ("Start at_"+str(current_size) + "Ends at_" + str(total_size))
# specify request range and init stream
req = urllib2.Request(url)
req.headers['Range'] = 'bytes=%s-%s' % (start, end)
while True:
buffer = u.read(block_sz)
if not buffer:
break
start += len(buffer)
f.write(buffer)
thread_id = id
status = "Thread ID_" +str(thread_id) + "Downloaded_" + str(int(start/1024)) + "Total_" +str(total_size)
print (status)
#starts 2 threads
def start_threads():
for i in range(2):
#if first loop, start thread 1
if(i==0):
start = calculate_no_of_bytes_for_thread1().get('start')
end = calculate_no_of_bytes_for_thread1().get('end')
print("Thread 1 started")
t = threading.Thread(target=download_thread, args=(url,i,start,end))
t.start()
threads.append( t)
#if second loop, start thread 2
if(i==1):
start = calculate_no_of_bytes_for_thread2().get('start')
end = calculate_no_of_bytes_for_thread2().get('end')
print("Thread 2 started")
t = threading.Thread(target=download_thread, args=(url,i,start,end))
t.start()
threads.append( t)
# Join threads back (order doesn't matter, you just want them all)
for i in threads:
i.join()
# Sort parts and you're done
# result = ''
# for i in range(2):
# result += parts[i*block_sz]
#start benchmarking
start_time = time.clock()
start_threads()
print ("Finito!")
end_time = time.clock()
benchmark = str(end_time - start_time)
print ("Download took_" +benchmark)
f.close()
You have:
for i in range(2):
if(i==1):
...
if(i==2):
...
But range(2) iterates over [0,1] not [1,2].
Save some trouble and just remove those 3 lines. The code to start the two threads can just run serially.
I was trying to execute a multi processed program like this
recQ = eventQ = Queue()
def _getRecords():
files=os.listdir(LOGDIR)
for file in files:
fileHeader = open(os.path.join(LOGDIR,file))
reader = logf.LogfileReader(fileHeader)
data = defaultdict(lambda: defaultdict(int))
for record in fileHeader.readlines():
recQ.put(record)
recQ.put('Done')
def _makeEvents():
while(True):
rec = recQ.get()
if not rec == 'Done':
e = event._getOject(rec)
eventQ.put(e)
else: break
eventQ.put('Done')
def _updateSQL():
while(True):
data = eventQ.get()
if not data == 'Done':
event = eventQ.get()
sql._updateEvent(event)
else: break
def _trigger():
processes = []
processes.append(Process(target = _getRecords(), args = ()))
processes.append(Process(target = _makeEvents(), args = ()))
processes.append(Process(target = _updateSQL(), args = ()))
for process in processes:
process.start()
if __name__ == '__main__':
_trigger()
Now the problem is when i am starting all the process from for loop, they are getting executed one after the other. I ve tried a similar example on some simpler data it is working very fine with it. Can any one tell me whats wrong with my code.
Thanks in advance :)
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.