asynchronous - 异步写入文件

Question

我一直在尝试创建一个服务器进程，以异步方式从客户端进程接收输入文件路径和输出路径。服务器进行了一些与数据库有关的转换，但是为了简单起见，我们假设它只是将所有内容都转换为大写。这是服务器的一个玩具示例:

import asyncio
import aiofiles as aiof
import logging
import sys


ADDRESS = ("localhost", 10000)

logging.basicConfig(level=logging.DEBUG,
                    format="%(name)s: %(message)s",
                    stream=sys.stderr)

log = logging.getLogger("main")
loop = asyncio.get_event_loop()


async def server(reader, writer):
    log = logging.getLogger("process at {}:{}".format(*ADDRESS))
    paths = await reader.read()
    in_fp, out_fp = paths.splitlines()
    log.debug("connection accepted")
    log.debug("processing file {!r}, writing output to {!r}".format(in_fp, out_fp))
    async with aiof.open(in_fp, loop=loop) as inp, aiof.open(out_fp, "w", loop=loop) as out:
        async for line in inp:
            out.write(line.upper())
        out.flush()
    writer.write(b"done")
    await writer.drain()
    log.debug("closing")
    writer.close()
    return


factory = asyncio.start_server(server, *ADDRESS)
server = loop.run_until_complete(factory)
log.debug("starting up on {} port {}".format(*ADDRESS))

try:
    loop.run_forever()
except KeyboardInterrupt:
    pass
finally:
    log.debug("closing server")
    server.close()
    loop.run_until_complete(server.wait_closed())
    log.debug("closing event loop")
    loop.close()

客户端:

import asyncio
import logging
import sys
import random

ADDRESS = ("localhost", 10000)
MESSAGES = ["/path/to/a/big/file.txt\n", 
            "/output/file_{}.txt\n".format(random.randint(0, 99999))]

logging.basicConfig(level=logging.DEBUG,
                    format="%(name)s: %(message)s",
                    stream=sys.stderr)

log = logging.getLogger("main")
loop = asyncio.get_event_loop()

async def client(address, messages):
    log = logging.getLogger("client")
    log.debug("connecting to {} port {}".format(*address))
    reader, writer = await asyncio.open_connection(*address)
    writer.writelines([bytes(line, "utf8") for line in messages])
    if writer.can_write_eof():
        writer.write_eof()
    await writer.drain()

    log.debug("waiting for response")
    response = await reader.read()
    log.debug("received {!r}".format(response))
    writer.close()
    return


try:
    loop.run_until_complete(client(ADDRESS, MESSAGES))
finally:
    log.debug("closing event loop")
    loop.close()

我一次激活了服务器和几个客户端。服务器的日志:

asyncio: Using selector: KqueueSelector
main: starting up on localhost port 10000
process at localhost:10000: connection accepted
process at localhost:10000: processing file b'/path/to/a/big/file.txt', writing output to b'/output/file_79609.txt'
process at localhost:10000: connection accepted
process at localhost:10000: processing file b'/path/to/a/big/file.txt', writing output to b'/output/file_68917.txt'
process at localhost:10000: connection accepted
process at localhost:10000: processing file b'/path/to/a/big/file.txt', writing output to b'/output/file_2439.txt'
process at localhost:10000: closing
process at localhost:10000: closing
process at localhost:10000: closing

所有客户都打印此:

asyncio: Using selector: KqueueSelector
client: connecting to localhost port 10000
client: waiting for response
client: received b'done'
main: closing event loop

输出文件已创建，但保持为空。我相信他们没有被冲洗。有什么办法可以解决吗？

Answer 1

您在await和out.write()之前缺少out.flush():

import asyncio
from pathlib import Path

import aiofiles as aiof

FILENAME = "foo.txt"


async def bad():
    async with aiof.open(FILENAME, "w") as out:
        out.write("hello world")
        out.flush()
    print("done")


async def good():
    async with aiof.open(FILENAME, "w") as out:
        await out.write("hello world")
        await out.flush()
    print("done")


loop = asyncio.get_event_loop()

server = loop.run_until_complete(bad())
print(Path(FILENAME).stat().st_size)  # prints 0

server = loop.run_until_complete(good())
print(Path(FILENAME).stat().st_size)  # prints 11

但是，我强烈建议您尝试跳过aiofile并使用常规的同步磁盘I/O，并保持asyncio的网络事件:

with open(file, "w"):  # regular file I/O
    async for s in network_request():  # asyncio for slow network work. measure it!
        f.write(s) # should be really quick, measure it!