Jal*_*eks 9 python memory multiprocessing python-3.x
使用 Python 的 multiprocessing 时Pool.map()，我没有找回我的记忆。超过1GB的内存仍然被占用，虽然Pool退出了带有 的函数，但一切都关闭了，我什至尝试删除 的变量Pool并显式调用垃圾收集器。
当，在下面显示的代码中，取消注释pool.map()（并注释该pool.map()行）上方的两行时，一切看起来都不错，但是一旦使用multiprocessing内存，似乎在离开函数后不会再次被释放。
因为在现实世界的代码multiprocessing中调用了其他几个使用的函数，这甚至会堆积起来，消耗所有内存。
（不幸的是，我无法为次要的第二种情况生成一个最小的例子，堆积内存，但是一旦主要问题解决了，第二个也应该消失。）
这是 Linux 上的 Python 3.7.3，非常欢迎任何至少解释甚至解决此问题的帮助。
最小示例代码：
import gc
from time import sleep
from memory_profiler import profile
import numpy as np
def waitat(where, t):
# print and wait, gives chance to see live memory usage in some task manager program
print(where)
sleep(t)
@profile
def parallel_convert_all_to_hsv(imgs: np.ndarray) -> np.ndarray:
from skimage.color import rgb2hsv
import multiprocessing as mp
print("going parallel")
pool = mp.Pool()
try:
# images_converted = [] # there is no memory problem when using commented lines below, instead of pool.map(…) line
# for img in imgs:
# images_converted.append(rgb2hsv(img))
images_converted = pool.map(rgb2hsv, imgs)
except KeyboardInterrupt:
pool.terminate()
waitat("after pool.map",5)
pool.close()
pool.join()
waitat("before del pool",5)
pool = None
del pool # memory should now be freed here?
mp = None
rgb2hsv = None
waitat("after del pool",5)
print("copying over")
res = np.array(images_converted)
waitat("before del image_hsv in function",5)
images_converted = None
del images_converted
return res
@profile
def doit():
print("create random images")
max_images = 700
images = np.random.rand(max_images, 300, 300,3)
waitat("before going parallel",5)
images_converted = parallel_convert_all_to_hsv(images)
print("images_converted has %i bytes" % images_converted.nbytes)
# how to clean up Pool's memory at latest here?
waitat("before deleting original images",5)
images = None
del images
waitat("memory should be as before going parallel + %i bytes" % images_converted.nbytes ,10)
images_converted = None
del images_converted
waitat("nearly end, memory should be as before" ,15)
gc.collect(2)
waitat("end, memory should be as before" ,15)
doit()
使用Memory Profiler输出，显示问题：
import gc
from time import sleep
from memory_profiler import profile
import numpy as np
def waitat(where, t):
# print and wait, gives chance to see live memory usage in some task manager program
print(where)
sleep(t)
@profile
def parallel_convert_all_to_hsv(imgs: np.ndarray) -> np.ndarray:
from skimage.color import rgb2hsv
import multiprocessing as mp
print("going parallel")
pool = mp.Pool()
try:
# images_converted = [] # there is no memory problem when using commented lines below, instead of pool.map(…) line
# for img in imgs:
# images_converted.append(rgb2hsv(img))
images_converted = pool.map(rgb2hsv, imgs)
except KeyboardInterrupt:
pool.terminate()
waitat("after pool.map",5)
pool.close()
pool.join()
waitat("before del pool",5)
pool = None
del pool # memory should now be freed here?
mp = None
rgb2hsv = None
waitat("after del pool",5)
print("copying over")
res = np.array(images_converted)
waitat("before del image_hsv in function",5)
images_converted = None
del images_converted
return res
@profile
def doit():
print("create random images")
max_images = 700
images = np.random.rand(max_images, 300, 300,3)
waitat("before going parallel",5)
images_converted = parallel_convert_all_to_hsv(images)
print("images_converted has %i bytes" % images_converted.nbytes)
# how to clean up Pool's memory at latest here?
waitat("before deleting original images",5)
images = None
del images
waitat("memory should be as before going parallel + %i bytes" % images_converted.nbytes ,10)
images_converted = None
del images_converted
waitat("nearly end, memory should be as before" ,15)
gc.collect(2)
waitat("end, memory should be as before" ,15)
doit()
非并行代码的输出（没有出现问题的地方）：
$ python3 -m memory_profiler pool-mem-probs.py
create random images
before going parallel
going parallel
after pool.map
before del pool
after del pool
copying over
before del image_hsv in function
Filename: pool-mem-probs.py
Line # Mem usage Increment Line Contents
================================================
11 1481.2 MiB 1481.2 MiB @profile
12 def parallel_convert_all_to_hsv(imgs: np.ndarray) -> np.ndarray:
13 1487.2 MiB 6.0 MiB from skimage.color import rgb2hsv
14 1487.2 MiB 0.0 MiB import multiprocessing as mp
15 1487.2 MiB 0.0 MiB print("going parallel")
16 1488.6 MiB 1.4 MiB pool = mp.Pool()
17 1488.6 MiB 0.0 MiB try:
18 # images_converted = [] # there is no memory problem when using commented lines below, instead of pool.map(…) line
19 # for img in imgs:
20 # images_converted.append(rgb2hsv(img))
21 2930.9 MiB 1442.3 MiB images_converted = pool.map(rgb2hsv, imgs)
22 except KeyboardInterrupt:
23 pool.terminate()
24 2930.9 MiB 0.0 MiB waitat("after pool.map",5)
25
26 2930.9 MiB 0.0 MiB pool.close()
27 2931.0 MiB 0.1 MiB pool.join()
28
29 2931.0 MiB 0.0 MiB waitat("before del pool",5)
30 2931.0 MiB 0.0 MiB pool = None
31 2931.0 MiB 0.0 MiB del pool # memory should now be freed here?
32 2931.0 MiB 0.0 MiB mp = None
33 2931.0 MiB 0.0 MiB rgb2hsv = None
34
35 2931.0 MiB 0.0 MiB waitat("after del pool",5)
36 2931.0 MiB 0.0 MiB print("copying over")
37 4373.0 MiB 1441.9 MiB res = np.array(images_converted)
38 4373.0 MiB 0.0 MiB waitat("before del image_hsv in function",5)
39 4016.6 MiB 0.0 MiB images_converted = None
40 4016.6 MiB 0.0 MiB del images_converted
41 4016.6 MiB 0.0 MiB return res
images_converted has 1512000000 bytes
before deleting original images
memory should be as before going parallel + 1512000000 bytes
nearly end, memory should be as before
end, memory should be as before
Filename: pool-mem-probs.py
Line # Mem usage Increment Line Contents
================================================
43 39.1 MiB 39.1 MiB @profile
44 def doit():
45 39.1 MiB 0.0 MiB print("create random images")
46 39.1 MiB 0.0 MiB max_images = 700
47 1481.2 MiB 1442.1 MiB images = np.random.rand(max_images, 300, 300,3)
48
49 1481.2 MiB 0.0 MiB waitat("before going parallel",5)
50 4016.6 MiB 2535.4 MiB images_converted = parallel_convert_all_to_hsv(images)
51 4016.6 MiB 0.0 MiB print("images_converted has %i bytes" % images_converted.nbytes)
52 # how to clean up Pool's memory at latest here?
53
54 4016.6 MiB 0.0 MiB waitat("before deleting original images",5)
55 2574.6 MiB 0.0 MiB images = None
56 2574.6 MiB 0.0 MiB del images
57 2574.6 MiB 0.0 MiB waitat("memory should be as before going parallel + %i bytes" % images_converted.nbytes ,10)
58 1132.7 MiB 0.0 MiB images_converted = None
59 1132.7 MiB 0.0 MiB del images_converted
60 1132.7 MiB 0.0 MiB waitat("nearly end, memory should be as before" ,15)
61 1132.7 MiB 0.0 MiB gc.collect(2)
62 1132.7 MiB 0.0 MiB waitat("end, memory should be as before" ,15)