Shared memory in multiprocessing

Because this is still a very high result on google and no one else has mentioned it yet, I thought I would mention the new possibility of ‘true’ shared memory which was introduced in python version 3.8.0: https://docs.python.org/3/library/multiprocessing.shared_memory.html

I have here included a small contrived example (tested on linux) where numpy arrays are used, which is likely a very common use case:

# one dimension of the 2d array which is shared
dim = 5000

import numpy as np
from multiprocessing import shared_memory, Process, Lock
from multiprocessing import cpu_count, current_process
import time

lock = Lock()

def add_one(shr_name):

    existing_shm = shared_memory.SharedMemory(name=shr_name)
    np_array = np.ndarray((dim, dim,), dtype=np.int64, buffer=existing_shm.buf)
    lock.acquire()
    np_array[:] = np_array[0] + 1
    lock.release()
    time.sleep(10) # pause, to see the memory usage in top
    print('added one')
    existing_shm.close()

def create_shared_block():

    a = np.ones(shape=(dim, dim), dtype=np.int64)  # Start with an existing NumPy array

    shm = shared_memory.SharedMemory(create=True, size=a.nbytes)
    # # Now create a NumPy array backed by shared memory
    np_array = np.ndarray(a.shape, dtype=np.int64, buffer=shm.buf)
    np_array[:] = a[:]  # Copy the original data into shared memory
    return shm, np_array

if current_process().name == "MainProcess":
    print("creating shared block")
    shr, np_array = create_shared_block()

    processes = []
    for i in range(cpu_count()):
        _process = Process(target=add_one, args=(shr.name,))
        processes.append(_process)
        _process.start()

    for _process in processes:
        _process.join()

    print("Final array")
    print(np_array[:10])
    print(np_array[10:])

    shr.close()
    shr.unlink()

Note that because of the 64 bit ints this code can take about 1gb of ram to run, so make sure that you won’t freeze your system using it. ^_^