创建数据库连接并维护多个进程（多处理）

Question

类似于我发表的另一篇文章，该文章回答了该问题并提出了一个新问题。

回顾：我需要更新空间数据库中的每条记录，在该数据库中，我有一个点数据集覆盖了多边形数据集。对于每个点要素，我想分配一个关键点以使其与其所在的多边形要素相关联。因此，如果我的点“纽约市”位于美国多边形内，并且对于美国的多边形“
GID = 1”，我将为我的点纽约市分配“ gid_fkey = 1”。

好的，这已经通过多处理来实现。我注意到使用此工具可以将速度提高150％，因此可以正常工作。但是我认为这会带来很多不必要的开销，因为每条记录都需要一个数据库连接。

所以这是代码：

import multiprocessing, time, psycopg2

class Consumer(multiprocessing.Process):

    def __init__(self, task_queue, result_queue):
        multiprocessing.Process.__init__(self)
        self.task_queue = task_queue
        self.result_queue = result_queue

    def run(self):
        proc_name = self.name
        while True:
            next_task = self.task_queue.get()
            if next_task is None:
                print 'Tasks Complete'
                self.task_queue.task_done()
                break            
            answer = next_task()
            self.task_queue.task_done()
            self.result_queue.put(answer)
        return


class Task(object):
    def __init__(self, a):
        self.a = a

    def __call__(self):        
        pyConn = psycopg2.connect("dbname='geobase_1' host = 'localhost'")
        pyConn.set_isolation_level(0)
        pyCursor1 = pyConn.cursor()

        procQuery = 'UPDATE city SET gid_fkey = gid FROM country  WHERE ST_within((SELECT the_geom FROM city WHERE city_id = %s), country.the_geom) AND city_id = %s' % (self.a, self.a)

        pyCursor1.execute(procQuery)
        print 'What is self?'
        print self.a

        return self.a

    def __str__(self):
        return 'ARC'
    def run(self):
        print 'IN'

if __name__ == '__main__':
    tasks = multiprocessing.JoinableQueue()
    results = multiprocessing.Queue()

    num_consumers = multiprocessing.cpu_count() * 2
    consumers = [Consumer(tasks, results) for i in xrange(num_consumers)]
    for w in consumers:
        w.start()

    pyConnX = psycopg2.connect("dbname='geobase_1' host = 'localhost'")
    pyConnX.set_isolation_level(0)
    pyCursorX = pyConnX.cursor()

    pyCursorX.execute('SELECT count(*) FROM cities WHERE gid_fkey IS NULL')    
    temp = pyCursorX.fetchall()    
    num_job = temp[0]
    num_jobs = num_job[0]

    pyCursorX.execute('SELECT city_id FROM city WHERE gid_fkey IS NULL')    
    cityIdListTuple = pyCursorX.fetchall()

    cityIdListList = []

    for x in cityIdListTuple:
        cityIdList.append(x[0])


    for i in xrange(num_jobs):
        tasks.put(Task(cityIdList[i - 1]))

    for i in xrange(num_consumers):
        tasks.put(None)

    while num_jobs:
        result = results.get()
        print result
        num_jobs -= 1

就像我用“时间”模块测量的那样，每次连接看起来在0.3到1.5秒之间。

有没有一种方法可以使每个进程建立数据库连接，然后仅使用city_id
info作为变量，就可以在此打开操作中将其输入到游标查询中？这样，我说了四个进程，每个进程都有一个数据库连接，然后以某种方式删除了city_id。

Answer 1

尝试在Consumer构造函数中隔离连接的创建，然后将其交给执行的Task：

import multiprocessing, time, psycopg2

class Consumer(multiprocessing.Process):

    def __init__(self, task_queue, result_queue):
        multiprocessing.Process.__init__(self)
        self.task_queue = task_queue
        self.result_queue = result_queue
        self.pyConn = psycopg2.connect("dbname='geobase_1' host = 'localhost'")
        self.pyConn.set_isolation_level(0)


    def run(self):
        proc_name = self.name
        while True:
            next_task = self.task_queue.get()
            if next_task is None:
                print 'Tasks Complete'
                self.task_queue.task_done()
                break            
            answer = next_task(connection=self.pyConn)
            self.task_queue.task_done()
            self.result_queue.put(answer)
        return


class Task(object):
    def __init__(self, a):
        self.a = a

    def __call__(self, connection=None):        
        pyConn = connection
        pyCursor1 = pyConn.cursor()

        procQuery = 'UPDATE city SET gid_fkey = gid FROM country  WHERE ST_within((SELECT the_geom FROM city WHERE city_id = %s), country.the_geom) AND city_id = %s' % (self.a, self.a)

        pyCursor1.execute(procQuery)
        print 'What is self?'
        print self.a

        return self.a

    def __str__(self):
        return 'ARC'
    def run(self):
        print 'IN'