[英]How do I profile memory usage in Python?
我最近對算法產生了興趣,並開始通過編寫一個簡單的實現然后以各種方式對其進行優化來探索它們。
我已經熟悉用於分析運行時的標准 Python 模塊(對於大多數情況,我發現 IPython 中的 timeit 魔術函數就足夠了),但我也對內存使用感興趣,因此我也可以探索這些權衡(例如,緩存先前計算值的表與根據需要重新計算它們的成本)。 是否有一個模塊可以為我分析給定函數的內存使用情況?
已經在這里回答了這個問題: Python memory profiler
基本上你做這樣的事情(從Guppy-PE引用):
>>> from guppy import hpy; h=hpy()
>>> h.heap()
Partition of a set of 48477 objects. Total size = 3265516 bytes.
Index Count % Size % Cumulative % Kind (class / dict of class)
0 25773 53 1612820 49 1612820 49 str
1 11699 24 483960 15 2096780 64 tuple
2 174 0 241584 7 2338364 72 dict of module
3 3478 7 222592 7 2560956 78 types.CodeType
4 3296 7 184576 6 2745532 84 function
5 401 1 175112 5 2920644 89 dict of class
6 108 0 81888 3 3002532 92 dict (no owner)
7 114 0 79632 2 3082164 94 dict of type
8 117 0 51336 2 3133500 96 type
9 667 1 24012 1 3157512 97 __builtin__.wrapper_descriptor
<76 more rows. Type e.g. '_.more' to view.>
>>> h.iso(1,[],{})
Partition of a set of 3 objects. Total size = 176 bytes.
Index Count % Size % Cumulative % Kind (class / dict of class)
0 1 33 136 77 136 77 dict (no owner)
1 1 33 28 16 164 93 list
2 1 33 12 7 176 100 int
>>> x=[]
>>> h.iso(x).sp
0: h.Root.i0_modules['__main__'].__dict__['x']
>>>
Python 3.4 包含一個新模塊: tracemalloc
。 它提供了有關分配最多內存的代碼的詳細統計信息。 下面的示例顯示了分配內存的前三行。
from collections import Counter
import linecache
import os
import tracemalloc
def display_top(snapshot, key_type='lineno', limit=3):
snapshot = snapshot.filter_traces((
tracemalloc.Filter(False, "<frozen importlib._bootstrap>"),
tracemalloc.Filter(False, "<unknown>"),
))
top_stats = snapshot.statistics(key_type)
print("Top %s lines" % limit)
for index, stat in enumerate(top_stats[:limit], 1):
frame = stat.traceback[0]
# replace "/path/to/module/file.py" with "module/file.py"
filename = os.sep.join(frame.filename.split(os.sep)[-2:])
print("#%s: %s:%s: %.1f KiB"
% (index, filename, frame.lineno, stat.size / 1024))
line = linecache.getline(frame.filename, frame.lineno).strip()
if line:
print(' %s' % line)
other = top_stats[limit:]
if other:
size = sum(stat.size for stat in other)
print("%s other: %.1f KiB" % (len(other), size / 1024))
total = sum(stat.size for stat in top_stats)
print("Total allocated size: %.1f KiB" % (total / 1024))
tracemalloc.start()
counts = Counter()
fname = '/usr/share/dict/american-english'
with open(fname) as words:
words = list(words)
for word in words:
prefix = word[:3]
counts[prefix] += 1
print('Top prefixes:', counts.most_common(3))
snapshot = tracemalloc.take_snapshot()
display_top(snapshot)
結果如下:
Top prefixes: [('con', 1220), ('dis', 1002), ('pro', 809)]
Top 3 lines
#1: scratches/memory_test.py:37: 6527.1 KiB
words = list(words)
#2: scratches/memory_test.py:39: 247.7 KiB
prefix = word[:3]
#3: scratches/memory_test.py:40: 193.0 KiB
counts[prefix] += 1
4 other: 4.3 KiB
Total allocated size: 6972.1 KiB
當內存在計算結束時仍然被占用時,這個例子很好,但有時你的代碼會分配大量內存然后釋放所有內存。 從技術上講,這不是內存泄漏,但它使用的內存比您想象的要多。 當它全部被釋放時,你如何跟蹤內存使用情況? 如果是您的代碼,您可能可以添加一些調試代碼來在它運行時拍攝快照。 如果沒有,您可以在主線程運行時啟動一個后台線程來監視內存使用情況。
這是前面的示例,其中代碼已全部移動到count_prefixes()
函數中。 當該函數返回時,所有內存都被釋放。 我還添加了一些sleep()
調用來模擬長時間運行的計算。
from collections import Counter
import linecache
import os
import tracemalloc
from time import sleep
def count_prefixes():
sleep(2) # Start up time.
counts = Counter()
fname = '/usr/share/dict/american-english'
with open(fname) as words:
words = list(words)
for word in words:
prefix = word[:3]
counts[prefix] += 1
sleep(0.0001)
most_common = counts.most_common(3)
sleep(3) # Shut down time.
return most_common
def main():
tracemalloc.start()
most_common = count_prefixes()
print('Top prefixes:', most_common)
snapshot = tracemalloc.take_snapshot()
display_top(snapshot)
def display_top(snapshot, key_type='lineno', limit=3):
snapshot = snapshot.filter_traces((
tracemalloc.Filter(False, "<frozen importlib._bootstrap>"),
tracemalloc.Filter(False, "<unknown>"),
))
top_stats = snapshot.statistics(key_type)
print("Top %s lines" % limit)
for index, stat in enumerate(top_stats[:limit], 1):
frame = stat.traceback[0]
# replace "/path/to/module/file.py" with "module/file.py"
filename = os.sep.join(frame.filename.split(os.sep)[-2:])
print("#%s: %s:%s: %.1f KiB"
% (index, filename, frame.lineno, stat.size / 1024))
line = linecache.getline(frame.filename, frame.lineno).strip()
if line:
print(' %s' % line)
other = top_stats[limit:]
if other:
size = sum(stat.size for stat in other)
print("%s other: %.1f KiB" % (len(other), size / 1024))
total = sum(stat.size for stat in top_stats)
print("Total allocated size: %.1f KiB" % (total / 1024))
main()
當我運行那個版本時,內存使用量從 6MB 減少到 4KB,因為該函數在完成時釋放了所有內存。
Top prefixes: [('con', 1220), ('dis', 1002), ('pro', 809)]
Top 3 lines
#1: collections/__init__.py:537: 0.7 KiB
self.update(*args, **kwds)
#2: collections/__init__.py:555: 0.6 KiB
return _heapq.nlargest(n, self.items(), key=_itemgetter(1))
#3: python3.6/heapq.py:569: 0.5 KiB
result = [(key(elem), i, elem) for i, elem in zip(range(0, -n, -1), it)]
10 other: 2.2 KiB
Total allocated size: 4.0 KiB
現在這是一個受另一個答案啟發的版本,它啟動第二個線程來監視內存使用情況。
from collections import Counter
import linecache
import os
import tracemalloc
from datetime import datetime
from queue import Queue, Empty
from resource import getrusage, RUSAGE_SELF
from threading import Thread
from time import sleep
def memory_monitor(command_queue: Queue, poll_interval=1):
tracemalloc.start()
old_max = 0
snapshot = None
while True:
try:
command_queue.get(timeout=poll_interval)
if snapshot is not None:
print(datetime.now())
display_top(snapshot)
return
except Empty:
max_rss = getrusage(RUSAGE_SELF).ru_maxrss
if max_rss > old_max:
old_max = max_rss
snapshot = tracemalloc.take_snapshot()
print(datetime.now(), 'max RSS', max_rss)
def count_prefixes():
sleep(2) # Start up time.
counts = Counter()
fname = '/usr/share/dict/american-english'
with open(fname) as words:
words = list(words)
for word in words:
prefix = word[:3]
counts[prefix] += 1
sleep(0.0001)
most_common = counts.most_common(3)
sleep(3) # Shut down time.
return most_common
def main():
queue = Queue()
poll_interval = 0.1
monitor_thread = Thread(target=memory_monitor, args=(queue, poll_interval))
monitor_thread.start()
try:
most_common = count_prefixes()
print('Top prefixes:', most_common)
finally:
queue.put('stop')
monitor_thread.join()
def display_top(snapshot, key_type='lineno', limit=3):
snapshot = snapshot.filter_traces((
tracemalloc.Filter(False, "<frozen importlib._bootstrap>"),
tracemalloc.Filter(False, "<unknown>"),
))
top_stats = snapshot.statistics(key_type)
print("Top %s lines" % limit)
for index, stat in enumerate(top_stats[:limit], 1):
frame = stat.traceback[0]
# replace "/path/to/module/file.py" with "module/file.py"
filename = os.sep.join(frame.filename.split(os.sep)[-2:])
print("#%s: %s:%s: %.1f KiB"
% (index, filename, frame.lineno, stat.size / 1024))
line = linecache.getline(frame.filename, frame.lineno).strip()
if line:
print(' %s' % line)
other = top_stats[limit:]
if other:
size = sum(stat.size for stat in other)
print("%s other: %.1f KiB" % (len(other), size / 1024))
total = sum(stat.size for stat in top_stats)
print("Total allocated size: %.1f KiB" % (total / 1024))
main()
resource
模塊可讓您檢查當前的內存使用情況,並保存峰值內存使用情況的快照。 隊列讓主線程告訴內存監視器線程何時打印其報告並關閉。 當它運行時,它會顯示list()
調用正在使用的內存:
2018-05-29 10:34:34.441334 max RSS 10188
2018-05-29 10:34:36.475707 max RSS 23588
2018-05-29 10:34:36.616524 max RSS 38104
2018-05-29 10:34:36.772978 max RSS 45924
2018-05-29 10:34:36.929688 max RSS 46824
2018-05-29 10:34:37.087554 max RSS 46852
Top prefixes: [('con', 1220), ('dis', 1002), ('pro', 809)]
2018-05-29 10:34:56.281262
Top 3 lines
#1: scratches/scratch.py:36: 6527.0 KiB
words = list(words)
#2: scratches/scratch.py:38: 16.4 KiB
prefix = word[:3]
#3: scratches/scratch.py:39: 10.1 KiB
counts[prefix] += 1
19 other: 10.8 KiB
Total allocated size: 6564.3 KiB
如果您使用的是 Linux,您可能會發現/proc/self/statm
比resource
模塊更有用。
如果您只想查看對象的內存使用情況,(回答其他問題)
有一個名為Pympler的模塊,其中包含
asizeof
模塊。使用方法如下:
from pympler import asizeof asizeof.asizeof(my_object)
與
sys.getsizeof
不同,它適用於您自己創建的對象。>>> asizeof.asizeof(tuple('bcd')) 200 >>> asizeof.asizeof({'foo': 'bar', 'baz': 'bar'}) 400 >>> asizeof.asizeof({}) 280 >>> asizeof.asizeof({'foo':'bar'}) 360 >>> asizeof.asizeof('foo') 40 >>> asizeof.asizeof(Bar()) 352 >>> asizeof.asizeof(Bar().__dict__) 280
>>> help(asizeof.asizeof)
Help on function asizeof in module pympler.asizeof:
asizeof(*objs, **opts)
Return the combined size in bytes of all objects passed as positional arguments.
披露:
但很好,因為它很簡單:
import resource
def using(point=""):
usage=resource.getrusage(resource.RUSAGE_SELF)
return '''%s: usertime=%s systime=%s mem=%s mb
'''%(point,usage[0],usage[1],
usage[2]/1024.0 )
只需將using("Label")
插入您想要查看發生了什么的位置。 例如
print(using("before"))
wrk = ["wasting mem"] * 1000000
print(using("after"))
>>> before: usertime=2.117053 systime=1.703466 mem=53.97265625 mb
>>> after: usertime=2.12023 systime=1.70708 mem=60.8828125 mb
下面是一個簡單的函數裝飾器,它允許跟蹤進程在函數調用之前、函數調用之后消耗了多少內存,以及有什么區別:
import time
import os
import psutil
def elapsed_since(start):
return time.strftime("%H:%M:%S", time.gmtime(time.time() - start))
def get_process_memory():
process = psutil.Process(os.getpid())
mem_info = process.memory_info()
return mem_info.rss
def profile(func):
def wrapper(*args, **kwargs):
mem_before = get_process_memory()
start = time.time()
result = func(*args, **kwargs)
elapsed_time = elapsed_since(start)
mem_after = get_process_memory()
print("{}: memory before: {:,}, after: {:,}, consumed: {:,}; exec time: {}".format(
func.__name__,
mem_before, mem_after, mem_after - mem_before,
elapsed_time))
return result
return wrapper
由於接受的答案以及下一個最高投票的答案在我看來存在一些問題,因此我想提供一個更多的答案,該答案與 Ihor B. 的答案密切相關,並進行了一些小而重要的修改。
該解決方案可以運行通過包裝函數調用與任紋上profile
,或通過與裝飾你的函數/方法的功能,把它@profile
裝飾。
當您想分析某些第三方代碼而不弄亂其源代碼時,第一種技術很有用,而第二種技術有點“更干凈”,並且在您不介意修改函數/方法的源代碼時效果更好想要簡介。
我還修改了輸出,以便您獲得 RSS、VMS 和共享內存。 我不太關心“之前”和“之后”的值,而只關心增量,所以我刪除了這些(如果您要與 Ihor B. 的答案進行比較)。
# profile.py
import time
import os
import psutil
import inspect
def elapsed_since(start):
#return time.strftime("%H:%M:%S", time.gmtime(time.time() - start))
elapsed = time.time() - start
if elapsed < 1:
return str(round(elapsed*1000,2)) + "ms"
if elapsed < 60:
return str(round(elapsed, 2)) + "s"
if elapsed < 3600:
return str(round(elapsed/60, 2)) + "min"
else:
return str(round(elapsed / 3600, 2)) + "hrs"
def get_process_memory():
process = psutil.Process(os.getpid())
mi = process.memory_info()
return mi.rss, mi.vms, mi.shared
def format_bytes(bytes):
if abs(bytes) < 1000:
return str(bytes)+"B"
elif abs(bytes) < 1e6:
return str(round(bytes/1e3,2)) + "kB"
elif abs(bytes) < 1e9:
return str(round(bytes / 1e6, 2)) + "MB"
else:
return str(round(bytes / 1e9, 2)) + "GB"
def profile(func, *args, **kwargs):
def wrapper(*args, **kwargs):
rss_before, vms_before, shared_before = get_process_memory()
start = time.time()
result = func(*args, **kwargs)
elapsed_time = elapsed_since(start)
rss_after, vms_after, shared_after = get_process_memory()
print("Profiling: {:>20} RSS: {:>8} | VMS: {:>8} | SHR {"
":>8} | time: {:>8}"
.format("<" + func.__name__ + ">",
format_bytes(rss_after - rss_before),
format_bytes(vms_after - vms_before),
format_bytes(shared_after - shared_before),
elapsed_time))
return result
if inspect.isfunction(func):
return wrapper
elif inspect.ismethod(func):
return wrapper(*args,**kwargs)
profile.py
:from profile import profile
from time import sleep
from sklearn import datasets # Just an example of 3rd party function call
# Method 1
run_profiling = profile(datasets.load_digits)
data = run_profiling()
# Method 2
@profile
def my_function():
# do some stuff
a_list = []
for i in range(1,100000):
a_list.append(i)
return a_list
res = my_function()
這應該會產生類似於以下內容的輸出:
Profiling: <load_digits> RSS: 5.07MB | VMS: 4.91MB | SHR 73.73kB | time: 89.99ms
Profiling: <my_function> RSS: 1.06MB | VMS: 1.35MB | SHR 0B | time: 8.43ms
profile(my_function, arg)
來分析my_function(arg)
也許它有幫助:
<見附加>
pip install gprof2dot
sudo apt-get install graphviz
gprof2dot -f pstats profile_for_func1_001 | dot -Tpng -o profile.png
def profileit(name):
"""
@profileit("profile_for_func1_001")
"""
def inner(func):
def wrapper(*args, **kwargs):
prof = cProfile.Profile()
retval = prof.runcall(func, *args, **kwargs)
# Note use of name from outer scope
prof.dump_stats(name)
return retval
return wrapper
return inner
@profileit("profile_for_func1_001")
def func1(...)
使用 memory_profile 計算代碼塊/函數的內存使用情況的簡單示例,同時返回函數的結果:
import memory_profiler as mp
def fun(n):
tmp = []
for i in range(n):
tmp.extend(list(range(i*i)))
return "XXXXX"
在運行代碼之前計算內存使用量,然后計算代碼期間的最大使用量:
start_mem = mp.memory_usage(max_usage=True)
res = mp.memory_usage(proc=(fun, [100]), max_usage=True, retval=True)
print('start mem', start_mem)
print('max mem', res[0][0])
print('used mem', res[0][0]-start_mem)
print('fun output', res[1])
運行函數時計算采樣點的使用情況:
res = mp.memory_usage((fun, [100]), interval=.001, retval=True)
print('min mem', min(res[0]))
print('max mem', max(res[0]))
print('used mem', max(res[0])-min(res[0]))
print('fun output', res[1])
學分:@skeept
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.