view mercurial/worker.py @ 26375:3686fa2b8eee

windows: insert file positioning call between reads and writes

fopen() and fdopen() have a unique-to-Windows requirement that
transitions between read and write operations in files opened
in modes r+, w+, and a+ perform a file positioning call
(fsetpos, fseek, or rewind) in between. While the MSDN docs don't
say what will happen if this is not done, observations reveal
that Python raises an IOError with errno 0. Furthermore, I
/think/ this behavior isn't deterministic. But I can reproduce
it reliably with subsequent patches applied that open revlogs
in a+ mode and perform both reads and writes.

This patch introduces a proxy class for file handles opened
in r+, w+, and a+ mode on Windows. The class intercepts calls
and audits whether a file positioning function has been called
between read and write operations. If not, a dummy, no-op seek
to the current file position is performed. This appears to be
sufficient to "trick" Windows into allowing transitions between
read and writes without raising errors.

# worker.py - master-slave parallelism support
#
# Copyright 2013 Facebook, Inc.
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from __future__ import absolute_import

import errno
import multiprocessing
import os
import signal
import sys
import threading

from .i18n import _
from . import util

def countcpus():
    '''try to count the number of CPUs on the system'''
    try:
        return multiprocessing.cpu_count()
    except NotImplementedError:
        return 1

def _numworkers(ui):
    s = ui.config('worker', 'numcpus')
    if s:
        try:
            n = int(s)
            if n >= 1:
                return n
        except ValueError:
            raise util.Abort(_('number of cpus must be an integer'))
    return min(max(countcpus(), 4), 32)

if os.name == 'posix':
    _startupcost = 0.01
else:
    _startupcost = 1e30

def worthwhile(ui, costperop, nops):
    '''try to determine whether the benefit of multiple processes can
    outweigh the cost of starting them'''
    linear = costperop * nops
    workers = _numworkers(ui)
    benefit = linear - (_startupcost * workers + linear / workers)
    return benefit >= 0.15

def worker(ui, costperarg, func, staticargs, args):
    '''run a function, possibly in parallel in multiple worker
    processes.

    returns a progress iterator

    costperarg - cost of a single task

    func - function to run

    staticargs - arguments to pass to every invocation of the function

    args - arguments to split into chunks, to pass to individual
    workers
    '''
    if worthwhile(ui, costperarg, len(args)):
        return _platformworker(ui, func, staticargs, args)
    return func(*staticargs + (args,))

def _posixworker(ui, func, staticargs, args):
    rfd, wfd = os.pipe()
    workers = _numworkers(ui)
    oldhandler = signal.getsignal(signal.SIGINT)
    signal.signal(signal.SIGINT, signal.SIG_IGN)
    pids, problem = [], [0]
    for pargs in partition(args, workers):
        pid = os.fork()
        if pid == 0:
            signal.signal(signal.SIGINT, oldhandler)
            try:
                os.close(rfd)
                for i, item in func(*(staticargs + (pargs,))):
                    os.write(wfd, '%d %s\n' % (i, item))
                os._exit(0)
            except KeyboardInterrupt:
                os._exit(255)
                # other exceptions are allowed to propagate, we rely
                # on lock.py's pid checks to avoid release callbacks
        pids.append(pid)
    pids.reverse()
    os.close(wfd)
    fp = os.fdopen(rfd, 'rb', 0)
    def killworkers():
        # if one worker bails, there's no good reason to wait for the rest
        for p in pids:
            try:
                os.kill(p, signal.SIGTERM)
            except OSError as err:
                if err.errno != errno.ESRCH:
                    raise
    def waitforworkers():
        for _pid in pids:
            st = _exitstatus(os.wait()[1])
            if st and not problem[0]:
                problem[0] = st
                killworkers()
    t = threading.Thread(target=waitforworkers)
    t.start()
    def cleanup():
        signal.signal(signal.SIGINT, oldhandler)
        t.join()
        status = problem[0]
        if status:
            if status < 0:
                os.kill(os.getpid(), -status)
            sys.exit(status)
    try:
        for line in fp:
            l = line.split(' ', 1)
            yield int(l[0]), l[1][:-1]
    except: # re-raises
        killworkers()
        cleanup()
        raise
    cleanup()

def _posixexitstatus(code):
    '''convert a posix exit status into the same form returned by
    os.spawnv

    returns None if the process was stopped instead of exiting'''
    if os.WIFEXITED(code):
        return os.WEXITSTATUS(code)
    elif os.WIFSIGNALED(code):
        return -os.WTERMSIG(code)

if os.name != 'nt':
    _platformworker = _posixworker
    _exitstatus = _posixexitstatus

def partition(lst, nslices):
    '''partition a list into N slices of equal size'''
    n = len(lst)
    chunk, slop = n / nslices, n % nslices
    end = 0
    for i in xrange(nslices):
        start = end
        end = start + chunk
        if slop:
            end += 1
            slop -= 1
        yield lst[start:end]