我最近对算法产生了兴趣，并开始通过编写一个简单的实现然后以各种方式对其进行优化来探索它们。

我已经熟悉用于分析运行时的标准 Python 模块(对于大多数事情，我发现 IPython 中的 timeit 魔术函数就足够了)，但我也对内存使用感兴趣，因此我可以探索这些权衡以及(例如，缓存先前计算值的表与根据需要重新计算它们的成本)。是否有一个模块可以为我分析给定函数的内存使用情况？

最佳答案

Python 3.4 包含一个新模块:tracemalloc .它提供了有关哪些代码分配了最多内存的详细统计信息。这是一个显示分配内存的前三行的示例。

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)

结果如下:

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

什么时候内存泄漏不是泄漏？

当内存在计算结束时仍被占用时，该示例非常棒，但有时您的代码会分配大量内存，然后将其全部释放。从技术上讲，这不是内存泄漏，但它使用的内存比您想象的要多。当所有内存都被释放时，如何跟踪内存使用情况？如果是您的代码，您可能可以添加一些调试代码以在其运行时拍摄快照。如果没有，您可以在主线程运行时启动一个后台线程来监控内存使用情况。

这是前面的示例，其中代码已全部移入 count_prefixes() 函数。当该函数返回时，所有内存都被释放。我还添加了一些 sleep() 调用来模拟长时间运行的计算。

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()

当我运行那个版本时，内存使用量从 6MB 下降到了 4KB，因为函数在完成时释放了所有内存。

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

现在这是一个受 another answer 启发的版本这会启动第二个线程来监控内存使用情况。

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 模块可让您检查当前内存使用情况，并保存峰值内存使用情况的快照。队列让主线程告诉内存监视器线程何时打印其报告并关闭。当它运行时，它会显示 list() 调用正在使用的内存:

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，您可能会发现 /proc/self/statm比 resource 模块更有用。

关于python - 如何在 Python 中分析内存使用情况？，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/552744/