zmq PUBhandler could not be used in __init__() method - python

I have a class MyLogger for sending messages to log server by using PUBhandler.
An exception gets raised when MyLogger is instanced in LogWorker.init() method (like version 1), however, it is ok if MyLogger is instanced in LogWorker.log_worker() method (version 2).
Any suggestions would be appreciated.
import logging
from multiprocessing import Process
import os
import random
import sys
import time
import zmq
from zmq.log.handlers import PUBHandler
class MyLogger(object):
''''''
def __init__(self, port, handler=None):
self.port = port
self.handler = handler or self._construct_sock_handler()
self.logger = logging.getLogger()
self.logger.setLevel(logging.INFO)
if not self.logger.handlers:
self.logger.addHandler(self.handler)
def _construct_sock_handler(self):
context = zmq.Context()
log_sock = context.socket(zmq.PUB)
log_sock.connect("tcp://127.0.0.1:%i" % self.port)
time.sleep(0.1)
handler = PUBHandler(log_sock)
return handler
def get_logger(self):
return self.logger
def sub_logger(port, level=logging.DEBUG):
ctx = zmq.Context()
sub = ctx.socket(zmq.SUB)
sub.bind('tcp://127.0.0.1:%i' % port)
sub.setsockopt(zmq.SUBSCRIBE, "")
logging.basicConfig(level=level)
while True:
level, message = sub.recv_multipart()
if message.endswith('\n'):
# trim trailing newline, which will get appended again
message = message[:-1]
log = getattr(logging, level.lower())
log(message)
class LogWorker(object):
def __init__(self):
- pass # version 1
+ self.logger = MyLogger(port).get_logger() # version 2
def log_worker(self, port):
- self.logger = MyLogger(port).get_logger() # version 1
print "starting logger at %i with level=%s" % (os.getpid(), logging.DEBUG)
while True:
level = logging.INFO
self.logger.log(level, "Hello from %i!" % os.getpid())
time.sleep(1)
if __name__ == '__main__':
if len(sys.argv) > 1:
n = int(sys.argv[1])
else:
n = 2
port = 5555
workers = [Process(target=LogWorker().log_worker, args=(port,)) for _ in range(n)]
[w.start() for w in workers]
try:
sub_logger(port)
except KeyboardInterrupt:
pass
finally:
[ w.terminate() for w in workers ]

answer from pyzmq owner minrk:
You cannot pass zmq contexts or sockets across the fork boundary that happens when you instantiate a subprocess with multiprocessing. You have to make sure that you create your Context after you are in the subprocess.
solution:
def work():
worker = LogWorker(port)
worker.log_worker()
workers = [ Process(target=work) for _ in range(n) ]

Related

Python Multithreading with requests

i have one scraper which initiate the "requestes" session and fetch some data, using a IPV6, i have now 10000 ip list, I have prepared it using threading, but its giving error.
Need support to find out the issue.
import requests, queue,threading, urllib3,jso,pandas as pd, os, time, datetime,inspect
num_threads = 2
root = os.path.dirname(os.path.abspath(inspect.getfile(inspect.currentframe())))
with open (root+ "/ip_list.txt") as ips:
device_ip = list(ips)
class Writer_Worker(threading.Thread):
def __init__(self, queue, df, *args, **kwargs):
if not queue:
print("Device Queue not specified")
exit(1)
self.out_q = queue
self.df = df
super().__init__(*args, **kwargs)
def run(self):
while True:
try:
device_details = self.out_q.get(timeout=3)
except queue.Empty:
return
self.df[device_details[0]] = device_details
self.out_q.task_done()
class Worker(threading.Thread):
def __init__(self, queue, out_queue, device_password, *args, **kwargs):
if not queue:
print("Device Queue not specified")
exit(1)
self.queue = queue
self.pas = device_password
self.out_q = out_queue
super().__init__(*args, **kwargs)
def run(self):
while True:
try:
device_ip = self.queue.get(timeout=3)
except queue.Empty:
return
self.connect_to_device_and_process(device_ip)
self.queue.task_done()
def connect_to_device_and_process(self, device_ip):
st = str("Online")
try:
r = requests.post("https://["+device_ip+"]/?q=index.login&mimosa_ajax=1", {"username":"configure", "password":self.pas}, verify=False)
except requests.exceptions.ConnectionError:
st = str("Offline")
self.out_q.put([device_ip,st,"","","","","","","","","","","","","","","","","",""])
return
finally:
if 'Online' in st:
r = requests.get("https://["+device_ip+"]/cgi/dashboard.php", cookies=r.cookies, verify=False)
if "Response [401]" in str(r):
st2 = str("Password Error")
self.out_q.put([device_ip,st2,"","","","","","","","","","","","","","","","","",""])
else:
data = json.loads(r.content.decode())
output5 = data ['config'] ['Spectrum_Power']
self.out_q.put([device_ip,st,output5['Auto_Power'].replace('2', 'Max Power').replace('1', 'Min Power').replace('0', 'off'),output5['AutoConfig']])
def main():
start = time.time()
urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
pas = input("Enter Device Password:")
df =pd.DataFrame(columns = ["IP","Status","Auto_Power","AutoChannel"])
q = queue.Queue(len(device_ip))
for ip in device_ip:
q.put_nowait(ip)
out_q = queue.Queue(len(device_ip))
Writer_Worker(out_q, df).start()
for _ in range(num_threads):
Worker(q, out_q, pas).start()
q.join()
print(df)
df.to_excel('iBridge_C5x_Audit_Report.xlsx', sheet_name='Detail', index = False)
if __name__ == "__main__":
main()
below is the error while running the script, seeps I am unable to login to this device.
Any help is appreciable.
You should use a thread pool that distributes the work between a fixed number of threads. This is a core feature of Python since version 3.2.
from concurrent.futures import ThreadPoolExecutor
Define a function perform(ip) that performs the request for one ip
Set variable numThreads to the number of desired threads
Run the thread-pool executor:
print(f'Using {numThreads} threads')
with ThreadPoolExecutor(max_workers=numThreads) as pool:
success = all(pool.map(perform, ips))
Source: https://docs.python.org/3/library/concurrent.futures.html
On that page you find an example even better tailored to your application: https://docs.python.org/3/library/concurrent.futures.html#threadpoolexecutor-example
from threading import Thread
th = Thread(target=self.fill_imdb, args=(movies_info_part, "thread " + str(count)))
th.start()
fill_imdb is my method

Callback function does not see correct values in instance

I'm having a strange phenomena in Python with callback functions and handlers.
I use ZMQ to handle my communication and use a stream for the socket. I have the base class:
import multiprocessing
import zmq
from concurrent.futures import ThreadPoolExecutor
from zmq.eventloop import ioloop, zmqstream
from zmq.utils import jsonapi as json
# Types of messages
TYPE_A = 'type_a'
TYPE_B = 'type_b'
class ZmqProcess(multiprocessing.Process):
def __init__(self):
super(ZmqProcess, self).__init__()
self.context = None
self.loop = None
self.handle_stream = None
def setup(self):
self.context = zmq.Context()
self.loop = ioloop.IOLoop.instance()
def send(self, msg_type, msg, host, port):
sock = zmq.Context().socket(zmq.PAIR)
sock.connect('tcp://%s:%s' % (host, port))
sock.send_json([msg_type, msg])
def stream(self, sock_type, addr):
sock = self.context.socket(sock_type)
if isinstance(addr, str):
addr = addr.split(':')
host, port = addr if len(addr) == 2 else (addr[0], None)
if port:
sock.bind('tcp://%s:%s' % (host, port))
else:
port = sock.bind_to_random_port('tcp://%s' % host)
stream = zmqstream.ZMQStream(sock, self.loop)
return stream, int(port)
class MessageHandler(object):
def __init__(self, json_load=-1):
self._json_load = json_load
self.pool = ThreadPoolExecutor(max_workers=10)
def __call__(self, msg):
i = self._json_load
msg_type, data = json.loads(msg[i])
msg[i] = data
if msg_type.startswith('_'):
raise AttributeError('%s starts with an "_"' % msg_type)
getattr(self, msg_type)(*msg)
And I have a class that inherits from it:
import zmq
import zmq_base
class ZmqServerMeta(zmq_base.ZmqProcess):
def __init__(self, bind_addr, handlers):
super(ZmqServerMeta, self).__init__()
self.bind_addr = bind_addr
self.handlers = handlers
def setup(self):
super(ZmqServerMeta, self).setup()
self.handle_stream, _ = self.stream(zmq.PAIR, self.bind_addr)
self.handle_stream.on_recv(StreamHandler(self.handle_stream, self.stop,
self.handlers))
def run(self):
self.setup()
self.loop.start()
def stop(self):
self.loop.stop()
class StreamHandler(zmq_base.MessageHandler):
def __init__(self, handle_stream, stop, handlers):
super(StreamHandler, self).__init__()
self._handle_stream = handle_stream
self._stop = stop
self._handlers = handlers
def type_a(self, data):
if zmq_base.TYPE_A in self._handlers:
if self._handlers[zmq_base.TYPE_A]:
for handle in self._handlers[zmq_base.TYPE_A]:
self.pool.submit(handle, data)
else:
pass
else:
pass
def type_b(self, data):
if zmq_base.TYPE_B in self._handlers:
if self._handlers[zmq_base.TYPE_B]:
for handle in self._handlers[zmq_base.TYPE_B]:
self.pool.submit(handle, data)
else:
pass
else:
pass
def endit(self):
self._stop()
Additionally, I have a class that I want to use as storage. And here is where the trouble starts:
import threading
import zmq_server_meta as server
import zmq_base as base
class Storage:
def __init__(self):
self.list = []
self.list_lock = threading.RLock()
self.zmq_server = None
self.host = '127.0.0.1'
self.port = 5432
self.bind_addr = (self.host, self.port)
def setup(self):
handlers = {base.TYPE_A: [self. remove]}
self.zmq_server = server.ZmqServerMeta(handlers=handlers, bind_addr=self.bind_addr)
self.zmq_server.start()
def add(self, data):
with self.list_lock:
try:
self.list.append(data)
except:
print "Didn't work"
def remove(self, msg):
with self.list_lock:
try:
self.list.remove(msg)
except:
print "Didn't work"
The idea is that that class stores some global information that it receives.
It is all started in a file to test:
import sys
import time
import storage
import zmq_base as base
import zmq_server_meta as server
def printMsg(msg):
print msg
store = storage.Storage()
store.setup()
handlers = {base.TYPE_B: [printMsg]}
client = server.ZmqServerMeta(handlers=handlers, bind_addr=('127.0.0.1', 5431))
client.start()
message = "Test"
store.add(message)
client.send(base.TYPE_A, message, '127.0.0.1', 5432)
I simplified it to reduce clutter. Instead of just adding it, it is usually send and then a response comes back. The response, the client sending, should be processed by the correct callback, remove(), and it should remove something out of the list. The problem that occurs is, that the remove() function sees an empty list, although there should be an element in the list. If I check from the testing file, I can see the element after it was added, and if I call remove() from there, I see a non-empty list and can remove it. My question is, why does the callback sees an empty list and how can I make sure it does see the correct elements in the list?
Kind regards
Patrick
I believe the problem lays in the fact that the ZmqProcess class inherits from multiprocessing.Process. Multiprocessing does not allow to share objects among different processes, except by using a shared memory map using Value or Array ( as can be seen in the documentation: https://docs.python.org/3/library/multiprocessing.html#sharing-state-between-processes )
If you want to use your custom object, you can use a Server process / proxy object, which can be found in on the same page of the documentation.
So you can, for instance, define a manager in the init function of the Storage class like: self.manager = Manager() Afterwards you put self.list = self.manager.list(). This should do the trick.

too many file descriptors in select() python in windows

i am trying to receive about 1000 connections to my server but it cannot receive more than 512. What can i do to increase the amount of open connections? I am running windows 8.1
Not: I am very new to this stuff so, thanks for help
Here is my code;
import asyncore
import socket
import uuid
import time
import threading
class statistics(threading.Thread):
def __init__(self):
threading.Thread.__init__(self)
def run(self):
while True:
entry = raw_input("")
zaman = int(time.time())
cmd = receivedCmd
print "calculating.."
time.sleep(1)
if entry == 'istatistik':
print str(receivedCmd-cmd) + " command/second"
print "total received commands: " + str(receivedCmd)
entry = ""
class tcpClient:
def __init__(self):
self.clientid = uuid.uuid1(int(time.time()))
self.buffer = ""
self.buffer_size = 0
self.conn_time = time.time()
self.overflow = 0
#print str(self.clientid) + " assingned"
def recv_msg(self, msg):
global receivedCmd
self.buffer = msg
self.buffer_size = len(self.buffer)
receivedCmd = receivedCmd + 1
if self.buffer_size >= 1024:
self.overflow = 1
def __del__(self):
print str(self.clientid) + " has left."
class TCPHandler(asyncore.dispatcher_with_send):
global clist
def handle_read(self):
data = self.recv(1024)
if data:
if clist[self].overflow:
self.send("overflow")
self.handle_close()
else:
self.send(data)
clist[self].recv_msg(data)
def handle_close(self):
del clist[self]
self.close()
def handle_error(self):
del clist[self]
self.close()
class TCPServer(asyncore.dispatcher):
global clist
def __init__(self, host, port):
asyncore.dispatcher.__init__(self)
self.create_socket(socket.AF_INET, socket.SOCK_STREAM)
self.set_reuse_addr()
self.bind((host, port))
self.listen(5)
def handle_accept(self):
self.clist = clist
pair = self.accept()
if pair is None:
pass
else:
sock, addr = pair
#print 'Connection : %s' % repr(addr)
clist[TCPHandler(sock)] = tcpClient()
if __name__ == '__main__':
clist = {}
receivedCmd = 0
server = TCPServer('', 5000)
server2 = TCPServer('',5001)
StaticsThread = statistics()
StaticsThread.start()
asyncore.loop()
Note: I still cannot receive more than 512 connections with the Twisted Framework, i don't know what to do. There have to be thousands of connected clients. Please help.
The asyncore module relies in the select OS function, which only supports a limited number of file descriptors.
As an alternative use a multi-threading server (I won't recommend this) or, better, the Twisted framework which is event-driven (highly recommended!).
Hope this helps!
Since Twisted's default reactor under Windows is also select-based then you should consider using the IOCP reactor instead.
from twisted.internet import iocpreactor
iocpreactor.install()
from twisted.internet import reactor
But also take into account that Twisted prefers Linux systems (where the default reactor is epoll-based) rather than Windows. Maybe switching to Linux is a better choice.

Python, Call a class function within another class

Can you anyone please help me call the broadcast function from class BroadcastServerFactory in class test, as per attached code
I have tried so many methods of call a function from another class, but no solution
import sys
from twisted.internet import reactor
from twisted.python import log
from twisted.web.server import Site
from twisted.web.static import File
from autobahn.websocket import WebSocketServerFactory, \
WebSocketServerProtocol, \
listenWS
class test():
//call broadcast function from here
class BroadcastServerProtocol(WebSocketServerProtocol):
def onOpen(self):
self.factory.register(self)
def onMessage(self, msg, binary):
if not binary:
self.factory.broadcast("'%s' from %s" % (msg, self.peerstr))
def connectionLost(self, reason):
WebSocketServerProtocol.connectionLost(self, reason)
self.factory.unregister(self)
class BroadcastServerFactory(WebSocketServerFactory):
"""
Simple broadcast server broadcasting any message it receives to all
currently connected clients.
"""
def __init__(self, url, debug = False, debugCodePaths = False):
WebSocketServerFactory.__init__(self, url, debug = debug, debugCodePaths = debugCodePaths)
self.clients = []
self.tickcount = 0
self.tick()
def tick(self):
self.tickcount += 1
self.broadcast("'tick %d' from server" % self.tickcount)
reactor.callLater(1, self.tick)
def register(self, client):
if not client in self.clients:
print "registered client " + client.peerstr
self.clients.append(client)
def unregister(self, client):
if client in self.clients:
print "unregistered client " + client.peerstr
self.clients.remove(client)
def broadcast(self, msg):
print "broadcasting message '%s' .." % msg
for c in self.clients:
c.sendMessage(msg)
print "message sent to " + c.peerstr
if __name__ == '__main__':
if len(sys.argv) > 1 and sys.argv[1] == 'debug':
log.startLogging(sys.stdout)
debug = True
else:
debug = False
ServerFactory = BroadcastServerFactory
#ServerFactory = BroadcastPreparedServerFactory
factory = ServerFactory("ws://localhost:9000",
debug = debug,
debugCodePaths = debug)
factory.protocol = BroadcastServerProtocol
factory.setProtocolOptions(allowHixie76 = True)
listenWS(factory)
webdir = File(".")
web = Site(webdir)
reactor.listenTCP(8080, web)
reactor.run()
class test():
def __init__(self, factory):
factory.broadcast("I don't know what I'm doing!")
Meanwhile, in main...
factory = ServerFactory("ws://localhost:9000",
debug = debug,
debugCodePaths = debug)
test(factory)
This will do what you want, but it seems you're missing some core concepts about classes and instances. For the test class to call anything on another class, there needs to be an instance of it first (bar the case of static methods).

Python multiprocessing RemoteManager under a multiprocessing.Process

I'm trying to start a data queue server under a managing process (so that it can later be turned into a service), and while the data queue server function works fine in the main process, it does not work in a process created using multiprocessing.Process.
The dataQueueServer and dataQueueClient code is based on the code from the multiprocessing module documentation here.
When run on its own, dataQueueServer works well. However, when run using a multiprocessing.Process's start() in mpquueue, it doesn't work (when tested with the client). I am using the dataQueueClient without changes to test both cases.
The code does reach the serve_forever in both cases, so I think the server is working, but something is blocking it from communicating back to the client in the mpqueue case.
I have placed the loop that runs the serve_forever() part under a thread, so that it can be stoppable.
Here is the code:
mpqueue # this is the "manager" process trying to spawn the server in a child process
import time
import multiprocessing
import threading
import dataQueueServer
class Printer():
def __init__(self):
self.lock = threading.Lock()
def tsprint(self, text):
with self.lock:
print text
class QueueServer(multiprocessing.Process):
def __init__(self, name = '', printer = None):
multiprocessing.Process.__init__(self)
self.name = name
self.printer = printer
self.ml = dataQueueServer.MainLoop(name = 'ml', printer = self.printer)
def run(self):
self.printer.tsprint(self.ml)
self.ml.start()
def stop(self):
self.ml.stop()
if __name__ == '__main__':
printer = Printer()
qs = QueueServer(name = 'QueueServer', printer = printer)
printer.tsprint(qs)
printer.tsprint('starting')
qs.start()
printer.tsprint('started.')
printer.tsprint('Press Ctrl-C to quit')
try:
while True:
time.sleep(60)
except KeyboardInterrupt:
printer.tsprint('\nTrying to exit cleanly...')
qs.stop()
printer.tsprint('stopped')
dataQueueServer
import time
import threading
from multiprocessing.managers import BaseManager
from multiprocessing import Queue
HOST = ''
PORT = 50010
AUTHKEY = 'authkey'
## Define some helper functions for use by the main process loop
class Printer():
def __init__(self):
self.lock = threading.Lock()
def tsprint(self, text):
with self.lock:
print text
class QueueManager(BaseManager):
pass
class MainLoop(threading.Thread):
"""A thread based loop manager, allowing termination signals to be sent
to the thread"""
def __init__(self, name = '', printer = None):
threading.Thread.__init__(self)
self._stopEvent = threading.Event()
self.daemon = True
self.name = name
if printer is None:
self.printer = Printer()
else:
self.printer = printer
## create the queue
self.queue = Queue()
## Add a function to the handler to return the queue to clients
self.QM = QueueManager
self.QM.register('get_queue', callable=lambda:self.queue)
self.queue_manager = self.QM(address=(HOST, PORT), authkey=AUTHKEY)
self.queue_server = self.queue_manager.get_server()
def __del__(self):
self.printer.tsprint( 'closing...')
def run(self):
self.printer.tsprint( '{}: started serving'.format(self.name))
self.queue_server.serve_forever()
def stop(self):
self.printer.tsprint ('{}: stopping'.format(self.name))
self._stopEvent.set()
def stopped(self):
return self._stopEvent.isSet()
def start():
printer = Printer()
ml = MainLoop(name = 'ml', printer = printer)
ml.start()
return ml
def stop(ml):
ml.stop()
if __name__ == '__main__':
ml = start()
raw_input("\nhit return to stop")
stop(ml)
And a client:
dataQueueClient
import datetime
from multiprocessing.managers import BaseManager
n = 0
N = 10**n
HOST = ''
PORT = 50010
AUTHKEY = 'authkey'
def now():
return datetime.datetime.now()
def gen(n, func, *args, **kwargs):
k = 0
while k < n:
yield func(*args, **kwargs)
k += 1
class QueueManager(BaseManager):
pass
QueueManager.register('get_queue')
m = QueueManager(address=(HOST, PORT), authkey=AUTHKEY)
m.connect()
queue = m.get_queue()
def load(msg, q):
return q.put(msg)
def get(q):
return q.get()
lgen = gen(N, load, msg = 'hello', q = queue)
t0 = now()
while True:
try:
lgen.next()
except StopIteration:
break
t1 = now()
print 'loaded %d items in ' % N, t1-t0
t0 = now()
while queue.qsize() > 0:
queue.get()
t1 = now()
print 'got %d items in ' % N, t1-t0
So it seems like the solution is simple enough: Don't use serve_forever(), and use manager.start() instead.
According to Eli Bendersky, the BaseManager (and it's extended version SyncManager) already spawns the server in a new process (and looking at the multiprocessing.managers code confirms this). The problem I have been experiencing stems from the form used in the example, in which the server is started under the main process.
I still don't understand why the current example doesn't work when run under a child process, but that's no longer an issue.
Here's the working (and much simplified from OP) code to manage multiple queue servers:
Server:
from multiprocessing import Queue
from multiprocessing.managers import SyncManager
HOST = ''
PORT0 = 5011
PORT1 = 5012
PORT2 = 5013
AUTHKEY = 'authkey'
name0 = 'qm0'
name1 = 'qm1'
name2 = 'qm2'
description = 'Queue Server'
def CreateQueueServer(HOST, PORT, AUTHKEY, name = None, description = None):
name = name
description = description
q = Queue()
class QueueManager(SyncManager):
pass
QueueManager.register('get_queue', callable = lambda: q)
QueueManager.register('get_name', callable = name)
QueueManager.register('get_description', callable = description)
manager = QueueManager(address = (HOST, PORT), authkey = AUTHKEY)
manager.start() # This actually starts the server
return manager
# Start three queue servers
qm0 = CreateQueueServer(HOST, PORT0, AUTHKEY, name0, description)
qm1 = CreateQueueServer(HOST, PORT1, AUTHKEY, name1, description)
qm2 = CreateQueueServer(HOST, PORT2, AUTHKEY, name2, description)
raw_input("return to end")
Client:
from multiprocessing.managers import SyncManager
HOST = ''
PORT0 = 5011
PORT1 = 5012
PORT2 = 5013
AUTHKEY = 'authkey'
def QueueServerClient(HOST, PORT, AUTHKEY):
class QueueManager(SyncManager):
pass
QueueManager.register('get_queue')
QueueManager.register('get_name')
QueueManager.register('get_description')
manager = QueueManager(address = (HOST, PORT), authkey = AUTHKEY)
manager.connect() # This starts the connected client
return manager
# create three connected managers
qc0 = QueueServerClient(HOST, PORT0, AUTHKEY)
qc1 = QueueServerClient(HOST, PORT1, AUTHKEY)
qc2 = QueueServerClient(HOST, PORT2, AUTHKEY)
# Get the queue objects from the clients
q0 = qc0.get_queue()
q1 = qc1.get_queue()
q2 = qc2.get_queue()
# put stuff in the queues
q0.put('some stuff')
q1.put('other stuff')
q2.put({1:123, 2:'abc'})
# check their sizes
print 'q0 size', q0.qsize()
print 'q1 size', q1.qsize()
print 'q2 size', q2.qsize()
# pull some stuff and print it
print q0.get()
print q1.get()
print q2.get()
Adding an additional server to share a dictionary with the information of the running queue servers so that consumers can easily tell what's available where is easy enough using that model. One thing to note, though, is that the shared dictionary requires slightly different syntax than a normal dictionary: dictionary[0] = something will not work. You need to use dictionary.update([(key, value), (otherkey, othervalue)]) and dictionary.get(key) syntax, which propagates across to all other clients connected to this dictionary..

Categories