"Python多线程脚本优化 - 内存占用巨大"

Question

我有一个脚本（Django管理命令），有超过800行代码。 这应该从外部Web服务导入数据，操作某物并将其写入Postgres数据库。在

我使用多线程，因为从webservice获取数据不是很快。在

有一个线程用于通过bulk命令获取数据，以获取64个数据集，并将每个数据集写入队列中。在

同时，在一开始有一个工作线程，它处理数据并将其写入数据库。 在main（handle）类中，有一个while循环，每5秒查找队列中的元素数量和正在运行的工作线程的数量。 如果队列中的元素超过500个，而工作线程少于5个，则会启动一个新的工作线程。在

所有工作线程从队列中获取一个项目，操作某物，将数据集写入数据库，并将一个字符串（最多14个字符）附加到另一个队列（#2）。在

队列#2必须在导入结束时将所有导入的对象标记为新的，分别从数据库中删除当前未导入的所有其他项。在

对于数量不超过20.000个数据集的数据库，一切正常。 但是，如果有一个数据库有1.000.000个数据集，那么在处理hole脚本的过程中，内存消耗会增加到8gb的RAM。在

有没有方法可以监视线程和/或队列的内存消耗？ 有没有方法可以在每次while循环后“清理”内存？在

# -*- coding: utf-8 -*-

import os
import threading
import Queue
import time

from optparse import OptionParser, make_option
from decimal import Decimal
from datetime import datetime

from django.core.management import call_command
from django.core.management.base import BaseCommand
from django.conf import settings


def is_someone_alive(thread_list):
    so_alive = False
    for t in thread_list:
        if t.is_alive():
            so_alive = True
    return so_alive


class insert_item(threading.Thread):
    VarLock2 = threading.Lock()

    def __init__(self, queue1, item_still_exist2, name, *args, **options):
        threading.Thread.__init__(self)
        self.options = options
        self.name = name
        self.queue1 = queue1
        self.item_still_exist2 = item_still_exist2

    def run(self):

        while not self.queue1.empty() or getItemBulkThread.isrunning:

            item = self.queue1.get()
            artikelobj, created = Artikel.objects.get_or_create(artikelnr=item['Nr'])

            """
            manipulate data
            """

            self.item_still_exist2.put(artikelobj.artikelnr)

            artikelobj.save()

            self.queue1.task_done()


class getItemBulkThread(threading.Thread):
    isrunning = True
    VarLock = threading.Lock()

    def __init__(self, queue1, name, *args, **options):
        threading.Thread.__init__(self)
        self.options = options
        if self.options['nrStart'] != '':
            self.nrab = self.options['nrStart']
        else:
            self.nrab = ''
        self.name = name
        #self.nrab = '701307'
        self.queue1 = queue1
        self.anz_artikel = 64
        self.max_artikel = 64
        self.skipped = 0
        self.max_skip = 20

    def run(self):

        count_sleep = 0
        while True:

            while self.queue1.qsize() > 5000:
                time.sleep(5)
                count_sleep += 1

            if count_sleep > 0:
                print "~ Artikel-Import %(csleep)sx für 5s pausiert, da Queue-Size > 5000" % {'csleep': count_sleep}
                count_sleep = 0

            try:
                items = getItemBulk()  # from external service

            except Exception as exc1:
                if ('"normal" abort-condition' in str(exc1)):
                    getItemBulkThread.VarLock.acquire()
                    getItemBulkThread.isrunning = False
                    getItemBulkThread.VarLock.release()
                    break
                elif self.anz_artikel > 1:
                    self.anz_artikel /= 2
                    continue
                elif self.skipped <= self.max_skip:
                    self.nrab += 1
                    self.skipped += 1
                    time.sleep(5)
                    continue
                elif self.skipped > self.max_skip:
                    raise Exception("[EXCEPTION] Fehler im Thread: too much items skipped")
                else:
                    getItemBulkThread.VarLock.acquire()
                    getItemBulkThread.isrunning = False
                    getItemBulkThread.VarLock.release()
                    raise

            last_item = len(items) - 1
            self.nrab = items[last_item]['Nr']

            for artikel in items:
                artikel['katItem'] = False
                self.queue1.put(artikel)

            if self.anz_artikel < self.max_artikel:
                self.anz_artikel *= 2
                self.skipped = 0


class Command(BaseCommand):
    """
      Django-mgm-command
    """
    help = u'Import'

    def create_parser(self, prog_name, subcommand):
        """
        Create and return the ``OptionParser`` which will be used to
        parse the arguments to this command.
        """
        return OptionParser(prog=prog_name, usage=self.usage(subcommand),
            version=self.get_version(),
            option_list=self.option_list,
            conflict_handler="resolve")

    def handle(self, *args, **options):

        startzeit = datetime.now()
        anzahl_Artikel_vorher = Artikel.objects.all().count()  # Artikel is a model

        self.options = options

        items_vorher = []

        queue1 = Queue.Queue()
        item_still_exists2 = Queue.Queue()

        running_threads = []

        thread = getItemBulkThread(queue1, name="Artikel", *args, **options)
        running_threads.append(thread)
        thread.daemon = True
        thread.start()

        anz_worker_threads = 1
        anz_max_worker_threads = 5

        insert_threads = [insert_item(queue1, item_still_exists2, name="Worker-%(anz)s" % {'anz': i + 1}, *args, **options) for i in range(anz_worker_threads)]
        for thread in insert_threads:
            running_threads.append(thread)
            thread.setDaemon(True)
            thread.start()

        add_seconds = 5
        element_grenze = 500
        lastelemente = 0
        asc_elemente = 0
        anz_abgearbeitet = 0

        while getItemBulkThread.isrunning or not queue1.empty():
            time.sleep(add_seconds)
            elemente = queue1.qsize()
            akt_zeit = datetime.now()
            diff_zeit = akt_zeit - startzeit
            diff = elemente - lastelemente
            anz_abgearbeitet = item_still_exists2.qsize()
            art_speed = (anz_abgearbeitet / timedelta_total_seconds(diff_zeit)) * 60
            ersetz_var = {'anz': elemente, 'zeit': diff_zeit, 'tstamp': akt_zeit.strftime('%Y.%m.%d-%H:%M:%S'), 'anzw': anz_worker_threads, 'diff': diff, 'anza': anz_abgearbeitet, 'art_speed': art_speed}
            print("%(zeit)s vergangen - %(tstamp)s - %(anz)s Elemente in Queue, Veränderung: %(diff)s - Anz Worker: %(anzw)s - Artikel importiert: %(anza)s - Speed: %(art_speed)02d Art/Min" % ersetz_var)

            if diff > 0:
                asc_elemente += 1
            else:
                asc_elemente = 0
            if asc_elemente > 2 and anz_worker_threads < anz_max_worker_threads and elemente > element_grenze:
                ersetz_var = {'maxw': anz_max_worker_threads, 'nr': anz_worker_threads + 1, 'element_grenze': element_grenze}
                print "~~ 2x in Folge mehr Queue-Elemente als vorher, die max. Anzahl an Workern %(maxw)s noch nicht erreicht und mehr als %(element_grenze)s Elemente in der Queue, daher Start eines neuen Workers (Nr %(nr)s)" % ersetz_var
                anz_worker_threads += 1
                thread = insert_item(queue1, item_still_exists2, name="Worker-%(anz)s" % {'anz': anz_worker_threads}, *args, **options)
                running_threads.append(thread)
                thread.setDaemon(True)
                thread.start()
                asc_elemente = 0
            lastelemente = elemente

        queue1.join()

        items_nachher = []
        while not item_still_exists2.empty():
            item = item_still_exists2.get()
            if item in items_vorher:
                items_nachher.append(item)
                items_vorher.remove(item)
            item_still_exists2.task_done()

        item_still_exists2.join()

        if len(items_vorher) > 0:
            Artikel.objects.filter(artikelnr__in=items_vorher).delete()

        anzahl_Artikel_nachher = Artikel.objects.all().count()
        anzahl_Artikel_diff = anzahl_Artikel_nachher - anzahl_Artikel_vorher

        endzeit = datetime.now()
        dauer = endzeit - startzeit

我在某些位置缩写了代码：）

Answer 1

内存消耗过大的一个可能原因是没有为输入队列设置最大大小。见the ^{} parameter。在

在一个相关的注释上，你写下：

In the main (handle) class, there is a while-loop that looks every 5 seconds for the quantity of elements in the queue and the quantity of running worker-threads. If there are more than 500 elements in the queue and there are less then 5 worker-threads, it starts a new worker-thread.

创建新线程并不一定会增加吞吐量。您应该做一些测试来确定最佳线程数，结果可能是1。在