I see a lot of tutorials on how to use queues, but they always show them implemented in the same file. I'm trying to organize my code files well from the beginning because I anticipate the project to become very large. How do I get the queue that I initialize in my main file to import into the other function files?
Here is my main file:
import multiprocessing
import queue
from data_handler import data_handler
from get_info import get_memory_info
from get_info import get_cpu_info
if __name__ == '__main__':
q = queue.Queue()
getDataHandlerProcess = multiprocessing.Process(target=data_handler(q))
getMemoryInfoProcess = multiprocessing.Process(target=get_memory_info(q))
getCPUInfoProcess = multiprocessing.Process(target=get_cpu_info(q))
getDataHandlerProcess.start()
getMemoryInfoProcess.start()
getCPUInfoProcess.start()
print("DEBUG: All tasks successfully started.")
Here is my producer:
import psutil
import struct
import time
from data_frame import build_frame
def get_cpu_info(q):
while True:
cpu_string_data = bytes('', 'utf-8')
cpu_times = psutil.cpu_percent(interval=0.0, percpu=True)
for item in cpu_times:
cpu_string_data = cpu_string_data + struct.pack('<d',item)
cpu_frame = build_frame(cpu_string_data, 0, 0, -1, -1)
q.put(cpu_frame)
print(cpu_frame)
time.sleep(1.000)
def get_memory_info(q):
while True:
memory_string_data = bytes('', 'utf-8')
virtual_memory = psutil.virtual_memory()
swap_memory = psutil.swap_memory()
memory_info = list(virtual_memory+swap_memory)
for item in memory_info:
memory_string_data = memory_string_data + struct.pack('<d',item)
memory_frame = build_frame(memory_string_data, 0, 1, -1, -1)
q.put(memory_frame)
print(memory_frame)
time.sleep(1.000)
def get_disk_info(q):
while True:
disk_usage = psutil.disk_usage("/")
disk_io_counters = psutil.disk_io_counters()
time.sleep(1.000)
print(disk_usage)
print(disk_io_counters)
def get_network_info(q):
while True:
net_io_counters = psutil.net_io_counters()
time.sleep(1.000)
print(net_io_counters)
And here is my consumer:
def data_handler(q):
while True:
next_element = q.get()
print(next_element)
print('Item received at data handler queue.')
It is not entirely clear to me what do you mean by " How do I get the queue that I initialize in my main file to import into the other function files?".
Normally you pass a queue as and argument to a function and use it within a function scope regardless of the file structure. Or perform any other variable sharing techniques used for any other data type.
Your code seems to have a few errors however. Firstly, you shouldn't be using queue.Queue with multiprocessing. It has it's own version of that class.
q = multiprocessing.Queue()
It is slower than the queue.Queue, but it works for sharing the data across processes.
Secondly, the proper way to create process objects is:
getDataHandlerProcess = multiprocessing.Process(target=data_handler, args = (q,))
Otherwise you are actually calling data_handler(q) the main thread and trying to assign its return value to the target argument of multiprocessing.Process. Your data_handler function never returns, so the program probably gets into an infinite a deadlock at this point before multiprocessing even begins. Edit: actually it probably goes into infinite wait trying to get an element from an empty queue which will never be filled.
Related
Goal:
Accelerate the random walk generation by using multiple processes.
Get the list of vertices ids from which I want random walks to be generated in an input queue
Start as much processes as possible with the correct parameters
Make them put the random walks into an output queue
Wait for completion
Read the output queue
What I am doing:
# Libraries imports
from multiprocessing import cpu_count, Process, Queue
import queue
import configparser
from gremlin_python.driver.driver_remote_connection import DriverRemoteConnection
from gremlin_python.process.anonymous_traversal import AnonymousTraversalSource, traversal
from gremlin_python.process.graph_traversal import __
# Function the processes are supposed to execute
def job(proc_id:int, siq:Queue, rwq:Queue, g:AnonymousTraversalSource, length:int):
while True:
try:
# Get next element in ids queue
start_id = siq.get_nowait()
except queue.Empty:
# If the ids queue is empty, then terminate
break
else:
# Do a random walk of length <length> from the vertex with id <start_id>
random_walk = g.V(start_id).repeat(
__.local(__.both().sample(1))
).times(length).path().next()
print(f"{proc_id}: rw obtained")
# Transform the list of vertices into a comma-separated string of ids
rwq.put(",".join(
[str(v.id) for v in random_walk]
))
print(f"{proc_id}: rw handled")
if __name__ == "__main__":
# Get the parameters from the <config.ini> configuration file
config = configparser.RawConfigParser()
config.read("config.ini")
jg_uri = config["JANUSGRAPH"]["URI"]
file_random_walks = config["FILES"]["RANDOM_WALKS"]
walks_nb_per_node = int(config["WALKS"]["NB_PER_NODE"])
walks_length = int(config["WALKS"]["LENGTH"])
# Connect to Janus Graph
connection = DriverRemoteConnection(jg_uri, "g")
g_main = traversal().withRemote(connection)
# Instantiate the queues and populate the ids one
start_ids_queue = Queue()
random_walks_queue = Queue()
for vertex in g_main.V().has("vertex_label", "<label>").fold().next():
start_ids_queue.put(vertex.id)
# Create and start the processes
nb_processes = cpu_count()
processes = []
for i in range(nb_processes):
p = Process(target=job, args=(
i,
start_ids_queue,
random_walks_queue,
g_main,
walks_length
))
processes.append(p)
p.start()
for p in processes:
p.join()
# Once the processes are terminated, read the random walks queue
random_walks = []
while not random_walks_queue.empty():
random_walks.append(random_walks_queue.get())
# Do something with the random walks
...
Issue:
Once the processes are started, nothing seems to happen. I never get the X: rw obtained/X: rw handled messages. With a bit more logging, I can see that the queries have been sent yet isn't finishing.
In the logs, when performing the first g_main.V().has("vertex_label", "<label>").fold().next() in the main process (when I populate the ids queue), I have the following message:
DEBUG:gremlinpython:submit with bytecode '[['V'], ['has', 'vertex_label', 'movie'], ['fold']]'
DEBUG:gremlinpython:message '[['V'], ['has', 'vertex_label', '<label>'], ['fold']]'
DEBUG:gremlinpython:processor='traversal', op='bytecode', args='{'gremlin': [['V'], ['has', 'vertex_label', '<label>'], ['fold']], 'aliases': {'g': 'g'}}'
DEBUG:asyncio:Using selector: EpollSelector
When the other processes send their queries, I have similar logs:
DEBUG:gremlinpython:submit with bytecode '[['V', 16456], ['repeat', [['local', [['both'], ['sample', 1]]]]], ['times', 10], ['path']]'
DEBUG:gremlinpython:message '[['V', 16456], ['repeat', [['local', [['both'], ['sample', 1]]]]], ['times', 10], ['path']]'
DEBUG:gremlinpython:processor='traversal', op='bytecode', args='{'gremlin': [['V', 16456], ['repeat', [['local', [['both'], ['sample', 1]]]]], ['times', 10], ['path']], 'aliases': {'g': 'g'}}'
DEBUG:asyncio:Using selector: EpollSelector
The issue seems not to reside in the query sent, but instead in the indefinite wait that ensues.
If you know of an issue with gremlinpython and multiprocessing, if there is a problem in my multi-processing code, or if you have any explanation that I may have overlooked, please explain to me! Thanks a lot to everyone reading this!
Solutions:
The first partial solution that I found is to use multi-threading instead of multiprocessing:
import configparser
from gremlin_python.driver.driver_remote_connection import DriverRemoteConnection
from gremlin_python.process.anonymous_traversal import AnonymousTraversalSource, traversal
from gremlin_python.process.graph_traversal import __
import threading
class myThread(threading.Thread):
def __init__(self, thread_id, g, length):
threading.Thread.__init__(self)
self.thread_id = thread_id
self.thread_count = 0
self.gtraversal = g
self.walk_length = length
self.nb_walks = nb_walks
def run(self):
while True:
start_ids_list_lock.acquire()
try:
start_id = start_ids_list.pop(0)
start_ids_list_lock.release()
except IndexError:
start_ids_list_lock.release()
break
else:
self.thread_count += 1
random_walk = job(
vertex_id=start_id,
g=self.gtraversal,
length=self.walk_length,
nb_walks=self.nb_walks
)
random_walks_list_lock.acquire()
random_walks_list.append(random_walk)
random_walks_list_lock.release()
logging.info(f"Thread {self.thread_id}: {self.thread_count} done")
def job(vertex_id:int, g:AnonymousTraversalSource, length:int) -> str:
random_walk = g.V(vertex_id).repeat(
__.local(__.both().sample(1))
).times(length).path().next()
return ",".join(random_walk)
config = configparser.RawConfigParser()
config.read("config.ini")
jg_uri = config["JANUSGRAPH"]["URI"]
file_random_walks = config["FILES"]["RANDOM_WALKS"]
walks_length = int(config["WALKS"]["LENGTH"])
connection = DriverRemoteConnection(jg_uri, "g")
g_main = traversal().withRemote(connection)
threads = []
start_ids_list = []
random_walks_list = []
random_walks_list_lock = threading.Lock()
start_ids_list_lock = threading.Lock()
start_ids_list = [vertex.id for vertex in g_main.V().has("vertex_label", "<label>").fold().next()]
nb_vertices = len(start_ids_list)
nb_threads = 6
for i in range(nb_threads):
thread = myThread(
thread_id=i,
g=g_main,
length=walks_length
)
thread.start()
threads.append(thread)
for t in threads:
t.join()
# Do something with the random walks
...
This solution is effectively working and improves the execution time of the program. This isn't a full answer though, as it doesn't explain why the multiprocessing is not performing as I expected.
I use python multiprocessing to compute some sort of scores on DNA sequences from a large file.
For that I write and use the script below.
I use a Linux machine with 48 cpu in python 3.8 environment.
Th code work fine, and terminate the work correctly and print the processing time at the end.
Problem: when I use the htop command, I find that all 48 processes are still alive.
I don't know why, and I don't know what to add to my script to avoid this.
import csv
import sys
import concurrent.futures
from itertools import combinations
import psutil
import time
nb_cpu = psutil.cpu_count(logical=False)
def fun_job(seq_1, seq_2): # seq_i : (id, string)
start = time.time()
score_dist = compute_score_dist(seq_1[1], seq_2[1])
end = time.time()
return seq_1[0], seq_2[0], score_dist, end - start # id seq1, id seq2, score, time
def help_fun_job(nested_pair):
return fun_job(nested_pair[0], nested_pair[1])
def compute_using_multi_processing(list_comb_ids, dict_ids_seqs):
start = time.perf_counter()
with concurrent.futures.ProcessPoolExecutor(max_workers=nb_cpu) as executor:
results = executor.map(help_fun_job,
[((pair_ids[0], dict_ids_seqs[pair_ids[0]]), (pair_ids[1], dict_ids_seqs[pair_ids[1]]))
for pair_ids in list_comb_ids])
save_results_to_csv(results)
finish = time.perf_counter()
proccessing_time = str(datetime.timedelta(seconds=round(finish - start, 2)))
print(f' Processing time Finished in {proccessing_time} hh:mm:ss')
def main():
print("nb_cpu in this machine : ", nb_cpu)
file_path = sys.argv[1]
dict_ids_seqs = get_dict_ids_seqs(file_path)
list_ids = list(dict_ids_seqs) # This will convert the dict_keys to a list
list_combined_ids = list(combinations(list_ids, 2))
compute_using_multi_processing(list_combined_ids, dict_ids_seqs)
if __name__ == '__main__':
main()
Thank you for your help.
Edit : add the complete code for fun_job (after #Booboo answer)
from Bio import Align
def fun_job(seq_1, seq_2): # seq_i : (id, string)
start = time.time()
aligner = Align.PairwiseAligner()
aligner.mode = 'global'
score_dist = aligner.score(seq_1[1],seq_2[1])
end = time.time()
return seq_1[0], seq_2[0], score_dist, end - start # id seq1, id seq2, score, time
When the with ... as executor: block exits, there is an implicit call to executor.shutdown(wait=True). This will wait for all pending futures to to be done executing "and the resources associated with the executor have been freed", which presumably includes terminating the processes in the pool (if possible?). Why your program terminates (or does it?) or at least you say all the futures have completed executing, while the processes have not terminated is a bit of a mystery. But you haven't provided the code for fun_job, so who can say why this is so?
One thing you might try is to switch to using the multiprocessing.pool.Pool class from the multiprocessing module. It supports a terminate method, which is implicitly called when its context manager with block exits, that explicitly attempts to terminate all processes in the pool:
#import concurrent.futures
import multiprocessing
... # etc.
def compute_using_multi_processing(list_comb_ids, dict_ids_seqs):
start = time.perf_counter()
with multiprocessing.Pool(processes=nb_cpu) as executor:
results = executor.map(help_fun_job,
[((pair_ids[0], dict_ids_seqs[pair_ids[0]]), (pair_ids[1], dict_ids_seqs[pair_ids[1]]))
for pair_ids in list_comb_ids])
save_results_to_csv(results)
finish = time.perf_counter()
proccessing_time = str(datetime.timedelta(seconds=round(finish - start, 2)))
print(f' Processing time Finished in {proccessing_time} hh:mm:ss')
I store QuertyText within a pandas dataframe. Once I've loaded all the queries into I want to conduct an analysis again each query. Currently, I have ~50k to evaluate. So, doing it one by one, will take a long time.
So, I wanted to implement concurrent.futures. How do I take the individual QueryText stored within fullAnalysis as pass it to concurrent.futures and return the output as a variable?
Here is my entire code:
import pandas as pd
import time
import gensim
import sys
import warnings
from concurrent.futures import ThreadPoolExecutor
from concurrent.futures import as_completed
fullAnalysis = pd.DataFrame()
def fetch_data(jFile = 'ProcessingDetails.json'):
print("Fetching data...please wait")
#read JSON file for latest dictionary file name
baselineDictionaryFileName = 'Dictionary/Dictionary_05-03-2020.json'
#copy data to pandas dataframe
labelled_data = pd.read_json(baselineDictionaryFileName)
#Add two more columns to get the most similar text and score
labelled_data['SimilarText'] = ''
labelled_data['SimilarityScore'] = float()
print("Data fetched from " + baselineDictionaryFileName + " and there are " + str(labelled_data.shape[0]) + " rows to be evalauted")
return labelled_data
def calculateScore(inputFunc):
warnings.filterwarnings("ignore", category=DeprecationWarning)
model = gensim.models.Word2Vec.load('w2v_model_bigdata')
inp = inputFunc
print(inp)
out = dict()
strEvaluation = inp.split("most_similar ",1)[1]
#while inp != 'quit':
split_inp = inp.split()
try:
if split_inp[0] == 'help':
pass
elif split_inp[0] == 'similarity' and len(split_inp) >= 3:
pass
elif split_inp[0] == 'most_similar' and len(split_inp) >= 2:
for pair in model.most_similar(positive=[split_inp[1]]):
out.update({pair[0]: pair[1]})
except KeyError as ke:
#print(str(ke) + "\n")
inp = input()
return out
def main():
with ThreadPoolExecutor(max_workers=5) as executor:
for i in range(len(fullAnalysis)):
text = fullAnalysis['QueryText'][i]
arg = 'most_similar'+ ' ' + text
#for item in executor.map(calculateScore, arg):
output = executor.map(calculateScore, arg)
return output
if __name__ == "__main__":
fullAnalysis = fetch_data()
results = main()
print(f'results: {results}')
The Python Global Interpreter Lock or GIL allows only one thread to hold control of the Python interpreter. Since your function calculateScore might be cpu-bound and requires the interpreter to execute its byte code, you may be gaining little by using threading. If, on the other hand, it were doing mostly I/O operations, it would be giving up the GIL for most of its running time allowing other threads to run. But that does not seem to be the case here. You probably should be using the ProcessPoolExecutor from concurrent.futures (try it both ways and see):
def main():
with ProcessPoolExecutor(max_workers=None) as executor:
the_futures = {}
for i in range(len(fullAnalysis)):
text = fullAnalysis['QueryText'][i]
arg = 'most_similar'+ ' ' + text
future = executor.submit(calculateScore, arg)
the_futures[future] = i # map future to request
for future in as_completed(the_futures): # results as they become available not necessarily the order of submission
i = the_futures[future] # the original index
result = future.result() # the result
If you omit the max_workers parameter (or specify a value of None) from the ProcessPoolExecutor constructor, the default will be the number of processors you have on your machine (not a bad default). There is no point in specifying a value larger than the number of processors you have.
If you do not need to tie the future back to the original request, then the_futures can just be a list to which But simplest yest in not even to bother to use the as_completed method:
def main():
with ProcessPoolExecutor(max_workers=5) as executor:
the_futures = []
for i in range(len(fullAnalysis)):
text = fullAnalysis['QueryText'][i]
arg = 'most_similar'+ ' ' + text
future = executor.submit(calculateScore, arg)
the_futures.append(future)
# wait for the completion of all the results and return them all:
results = [f.result() for f in the_futures()] # results in creation order
return results
It should be mentioned that code that launches the ProcessPoolExecutor functions should be in a block governed by a if __name__ = '__main__':. If it isn't you will get into a recursive loop with each subprocess launching the ProcessPoolExecutor. But that seems to be the case here. Perhaps you meant to use the ProcessPoolExecutor all along?
Also:
I don't know what the line ...
model = gensim.models.Word2Vec.load('w2v_model_bigdata')
... in function calculateStore does. It may be the one i/o-bound statement. But this appears to be something that does not vary from call to call. If that is the case and model is not being modified in the function, shouldn't this statement be moved out of the function and computed just once? Then this function would clearly run faster (and be clearly cpu-bound).
Also:
The exception block ...
except KeyError as ke:
#print(str(ke) + "\n")
inp = input()
... is puzzling. You are inputting a value that will never be used right before returning. If this is to pause execution, there is no error message being output.
With Booboo assistance, I was able to update code to include ProcessPoolExecutor. Here is my updated code. Overall, processing has been speed up by more than 60%.
I did run into a processing issue and found this topic BrokenPoolProcess that addresses the issue.
output = {}
thePool = {}
def main(labelled_data, dictionaryRevised):
args = sys.argv[1:]
with ProcessPoolExecutor(max_workers=None) as executor:
for i in range(len(labelled_data)):
text = labelled_data['QueryText'][i]
arg = 'most_similar'+ ' '+ text
output = winprocess.submit(
executor, calculateScore, arg
)
thePool[output] = i #original index for future to request
for output in as_completed(thePool): # results as they become available not necessarily the order of submission
i = thePool[output] # the original index
text = labelled_data['QueryText'][i]
result = output.result() # the result
maximumKey = max(result.items(), key=operator.itemgetter(1))[0]
maximumValue = result.get(maximumKey)
labelled_data['SimilarText'][i] = maximumKey
labelled_data['SimilarityScore'][i] = maximumValue
return labelled_data, dictionaryRevised
if __name__ == "__main__":
start = time.perf_counter()
print("Starting to evaluate Query Text for labelling...")
output_Labelled_Data, output_dictionary_revised = preProcessor()
output,dictionary = main(output_Labelled_Data, output_dictionary_revised)
finish = time.perf_counter()
print(f'Finished in {round(finish-start, 2)} second(s)')
I'm working on a Raspberry Pi (3 B+) making a data collection device and I'm
trying to spawn a process to record the data coming in and write it to a file. I have a function for the writing that works fine when I call it directly.
When I call it using the multiprocess approach however, nothing seems to happen. I can see in task monitors in Linux that the process does in fact get spawned but no file gets written, and when I try to pass a flag to it to shut down it doesn't work, meaning I end up terminating the process and nothing seems to have happened.
I've been over this every which way and can't see what I'm doing wrong; does anyone else? In case it's relevant, these are functions inside a parent class, and one of the functions is meant to spawn another as a thread.
Code I'm using:
from datetime import datetime, timedelta
import csv
from drivers.IMU_SEN0 import IMU_SEN0
import multiprocessing, os
class IMU_data_logger:
_output_filename = ''
_csv_headers = []
_accelerometer_headers = ['Accelerometer X','Accelerometer Y','Accelerometer Z']
_gyroscope_headers = ['Gyroscope X','Gyroscope Y','Gyroscope Z']
_magnetometer_headers = ['Bearing']
_log_accelerometer = False
_log_gyroscope= False
_log_magnetometer = False
IMU = None
_writer=[]
_run_underway = False
_process=[]
_stop_value = 0
def __init__(self,output_filename='/home/pi/blah.csv',log_accelerometer = True,log_gyroscope= True,log_magnetometer = True):
"""data logging device
NOTE! Multiple instances of this class should not use the same IMU devices simultaneously!"""
self._output_filename = output_filename
self._log_accelerometer = log_accelerometer
self._log_gyroscope = log_gyroscope
self._log_magnetometer = log_magnetometer
def __del__(self):
# TODO Update this
if self._run_underway: # If there's still a run underway, end it first
self.end_recording()
def _set_up(self):
self.IMU = IMU_SEN0(self._log_accelerometer,self._log_gyroscope,self._log_magnetometer)
self._set_up_headers()
def _set_up_headers(self):
"""Set up the headers of the CSV file based on the header substrings at top and the input flags on what will be measured"""
self._csv_headers = []
if self._log_accelerometer is not None:
self._csv_headers+= self._accelerometer_headers
if self._log_gyroscope is not None:
self._csv_headers+= self._gyroscope_headers
if self._log_magnetometer is not None:
self._csv_headers+= self._magnetometer_headers
def _record_data(self,frequency,stop_value):
self._set_up() #Run setup in thread
"""Record data function, which takes a recording frequency, in herz, as an input"""
previous_read_time=datetime.now()-timedelta(1,0,0)
self._run_underway = True # Note that a run is now going
Period = 1/frequency # Period, in seconds, of a recording based on the input frequency
print("Writing output data to",self._output_filename)
with open(self._output_filename,'w',newline='') as outcsv:
self._writer = csv.writer(outcsv)
self._writer.writerow(self._csv_headers) # Write headers to file
while stop_value.value==0: # While a run continues
if datetime.now()-previous_read_time>=timedelta(0,1,0): # If we've waited a period, collect the data; otherwise keep looping
print("run underway value",self._run_underway)
if datetime.now()-previous_read_time>=timedelta(0,Period,0): # If we've waited a period, collect the data; otherwise keep looping
previous_read_time = datetime.now() # Update previous readtime
next_row = []
if self._log_accelerometer:
# Get values in m/s^2
axes = self.IMU.read_accelerometer_values()
next_row += [axes['x'],axes['y'],axes['z']]
if self._log_gyroscope:
# Read gyro values
gyro = self.IMU.read_gyroscope_values()
next_row += [gyro['x'],gyro['y'],gyro['z']]
if self._log_magnetometer:
# Read magnetometer value
b= self.IMU.read_magnetometer_bearing()
next_row += b
self._writer.writerow(next_row)
# Close the csv when done
outcsv.close()
def start_recording(self,frequency_in_hz):
# Create recording process
self._stop_value = multiprocessing.Value('i',0)
self._process = multiprocessing.Process(target=self._record_data,args=(frequency_in_hz,self._stop_value))
# Start recording process
self._process.start()
print(datetime.now().strftime("%H:%M:%S.%f"),"Data logging process spawned")
print("Logging Accelerometer:",self._log_accelerometer)
print("Logging Gyroscope:",self._log_gyroscope)
print("Logging Magnetometer:",self._log_magnetometer)
print("ID of data logging process: {}".format(self._process.pid))
def end_recording(self,terminate_wait = 2):
"""Function to end the recording multithread that's been spawned.
Args: terminate_wait: This is the time, in seconds, to wait after attempting to shut down the process before terminating it."""
# Get process id
id = self._process.pid
# Set stop event for process
self._stop_value.value = 1
self._process.join(terminate_wait) # Wait two seconds for the process to terminate
if self._process.is_alive(): # If it's still alive after waiting
self._process.terminate()
print(datetime.now().strftime("%H:%M:%S.%f"),"Process",id,"needed to be terminated.")
else:
print(datetime.now().strftime("%H:%M:%S.%f"),"Process",id,"successfully ended itself.")
====================================================================
ANSWER: For anyone following up here, it turns out the problem was my use of the VS Code debugger which apparently doesn't work with multiprocessing and was somehow preventing the success of the spawned process. Many thanks to Tomasz Swider below for helping me work through issues and, eventually, find my idiocy. The help was very deeply appreciated!!
I can see few thing wrong in your code:
First thing
stop_value == 0 will not work as the multiprocess.Value('i', 0) != 0, change that line to
while stop_value.value == 0
Second, you never update previous_read_time so it will write the readings as fast as it can, you will run out of disk quick
Third, try use time.sleep() the thing you are doing is called busy looping and it is bad, it is wasting CPU cycles needlessly.
Four, terminating with self._stop_value = 1 probably will not work there must be other way to set that value maybe self._stop_value.value = 1.
Well here is a pice of example code based on the code that you have provided that is working just fine:
import csv
import multiprocessing
import time
from datetime import datetime, timedelta
from random import randint
class IMU(object):
#staticmethod
def read_accelerometer_values():
return dict(x=randint(0, 100), y=randint(0, 100), z=randint(0, 10))
class Foo(object):
def __init__(self, output_filename):
self._output_filename = output_filename
self._csv_headers = ['xxxx','y','z']
self._log_accelerometer = True
self.IMU = IMU()
def _record_data(self, frequency, stop_value):
#self._set_up() # Run setup functions for the data collection device and store it in the self.IMU variable
"""Record data function, which takes a recording frequency, in herz, as an input"""
previous_read_time = datetime.now() - timedelta(1, 0, 0)
self._run_underway = True # Note that a run is now going
Period = 1 / frequency # Period, in seconds, of a recording based on the input frequency
print("Writing output data to", self._output_filename)
with open(self._output_filename, 'w', newline='') as outcsv:
self._writer = csv.writer(outcsv)
self._writer.writerow(self._csv_headers) # Write headers to file
while stop_value.value == 0: # While a run continues
if datetime.now() - previous_read_time >= timedelta(0, 1,
0): # If we've waited a period, collect the data; otherwise keep looping
print("run underway value", self._run_underway)
if datetime.now() - previous_read_time >= timedelta(0, Period,
0): # If we've waited a period, collect the data; otherwise keep looping
next_row = []
if self._log_accelerometer:
# Get values in m/s^2
axes = self.IMU.read_accelerometer_values()
next_row += [axes['x'], axes['y'], axes['z']]
previous_read_time = datetime.now()
self._writer.writerow(next_row)
# Close the csv when done
outcsv.close()
def start_recording(self, frequency_in_hz):
# Create recording process
self._stop_value = multiprocessing.Value('i', 0)
self._process = multiprocessing.Process(target=self._record_data, args=(frequency_in_hz, self._stop_value))
# Start recording process
self._process.start()
print(datetime.now().strftime("%H:%M:%S.%f"), "Data logging process spawned")
print("ID of data logging process: {}".format(self._process.pid))
def end_recording(self, terminate_wait=2):
"""Function to end the recording multithread that's been spawned.
Args: terminate_wait: This is the time, in seconds, to wait after attempting to shut down the process before terminating it."""
# Get process id
id = self._process.pid
# Set stop event for process
self._stop_value.value = 1
self._process.join(terminate_wait) # Wait two seconds for the process to terminate
if self._process.is_alive(): # If it's still alive after waiting
self._process.terminate()
print(datetime.now().strftime("%H:%M:%S.%f"), "Process", id, "needed to be terminated.")
else:
print(datetime.now().strftime("%H:%M:%S.%f"), "Process", id, "successfully ended itself.")
if __name__ == '__main__':
foo = Foo('/tmp/foometer.csv')
foo.start_recording(20)
time.sleep(5)
print('Ending recording')
foo.end_recording()
After some lookup into google and posts of stackoverflow and other sites, i'm still confused on how i can apply a queue and threading on my code:
import psycopg2
import sys
import re
# for threading and queue
import multiprocessing
from multiprocessing import Queue
# for threading and queue
import time
from datetime import datetime
class Database_connection():
def db_call(self,query,dbHost,dbName,dbUser,dbPass):
try:
con = None
con = psycopg2.connect(host=dbHost,database=dbName,
user=dbUser,password=dbPass)
cur = con.cursor()
cur.execute(query)
data = cur.fetchall()
resultList = []
for data_out in data:
resultList.append(data_out)
return resultList
except psycopg2.DatabaseError, e:
print 'Error %s' % e
sys.exit(1)
finally:
if con:
con.close()
w = Database_connection()
sql = "select stars from galaxy"
startTime = datetime.now()
for result in w.db_call(sql, "x", "x", "x", "x"):
print result[0]
print "Runtime: " + str(datetime.now()-startTime)
lets supose the result will be 100+ values. How can i, put those 100+ results on queue and execute ( print, for example ) then 5 at time using queue and multiprocessing module?
What do you want this code to do?
You get no output from this code because get() returns the next item from the queue (doc). You are putting the letters from the sql response into the queue one letter at a time. the i in for i... is looping over the list returned by w.db_call. Those items are (I assume) strings, which you are then iterating over and adding one at a time to the queue. The next thing you do is to remove the element you just added to the queue from the queue, which leaves the queue unchanged over each pass through the loop. If you put a print statement in the loop it prints out the letter it just got from the queue.
Queues are used to pass information between processes. I think you are trying to set-up a producer/consumer pattern where you have one process add things to the queue and multiple other processes which consume things from the queue. See working example of multiprocessing.Queue and links contained there in (example, main documentation).
Probably the simplest way to get this working, as long as you don't need it to run in an interactive shell, is to use Pool (lifted almost verbatim from the documentation of multiprocess)
from multiprocessing import Pool
p = Pool(5) # sets the number of worker threads you want
def f(res):
# put what ever you want to do with each of the query results in here
return res
result_lst = w.db_call(sql, "x", "x", "x", "x")
proced_results = p.map(f, result_lst)
which apply what ever you want to do to each result (written into the function f) and returns the results of that manipulation as a list. The number of sub-processes to use is set by the argument to Pool.
This is my suggestion...
import Queue
from threading import Thread
class Database_connection:
def db_call(self,query,dbHost,dbName,dbUser,dbPass):
# your code here
return
# in this example each thread will execute this function
def processFtpAddrMt(queue):
# loop will continue until queue containing FTP addresses is empty
while True:
# get an ftp address, a exception will be called when the
# queue is empty and the loop will break
try: ftp_addr = queue.get()
except: break
# put code to process the ftp address here
# let queue know this task is done
queue.task_done()
w = Database_connection()
sql = "select stars from galaxy"
ftp_addresses = w.db_call(sql, "x", "x", "x", "x")
# put each result of the SQL call in a Queue class
ftp_addr_queue = Queue.Queue()
for addr in ftp_addresses:
ftp_addr_queue.put(addr)
# create five threads where each one will run analyzeFtpResult
# pass the queue to the analyzeFtpResult function
for x in range(0,5):
t = Thread(target=processFtpAddrMt,args=(ftp_addr_queue,))
t.setDaemon(True)
t.start()
# blocks further execution of the script until all queue items have been processed
ftp_addr_queue.join()
It uses the Queue class to store your SQL results and then the Thread class to process the queue. Five thread classes are created and each one uses a processFtpAddrMt function which take ftp addresses from the queue until the queue is empty. All you have to do is add the code for processing the ftp address. Hope this helps.
I was able to solve the problem with the following:
def worker():
w = Database_connection()
sql = "select stars from galaxy"
for result in w.db_call(sql, "x", "x", "x", "x"):
if result:
jobs = []
startTime = datetime.now()
for i in range(1):
p = multiprocessing.Process(target=worker)
jobs.append(p)
p.start()
print "Runtime: " + str(datetime.now()-startTime)
I belive it is not the best way to do it, but for now solved my problem :)