mercurial/worker.py

revset: lower weight for _intlist function

The histedit command uses a revset like:

(_intlist('1234\x001235')) and merge()

Previously the optimizer gave a weight of 1.5 to the _intlist side (1 for the
function, 0.5 for the string) which caused it to process the merge() side first.
This caused it to evaluate merge against every commit in the repo, which took
2.5 seconds on a large repo.

I changed the weight of _intlist to 0, since it's a trivial calculation, which
makes it process intlist first, which makes merge apply only to the revs in the
list. Which makes the revset take 0.15 seconds now. Cutting off 2.4 seconds off
our histedit performance.

>From the revset benchmark:
revset #25: (_intlist('20000\x0020001')) and merge()
0) obsolete feature not enabled but 54243 markers found!
! wall 0.036767 comb 0.040000 user 0.040000 sys 0.000000 (best of 100)
1) obsolete feature not enabled but 54243 markers found!
! wall 0.000198 comb 0.000000 user 0.000000 sys 0.000000 (best of 9084)

# 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 i18n import _
import errno, os, signal, sys, threading
import util

def countcpus():
    '''try to count the number of CPUs on the system'''

    # posix
    try:
        n = int(os.sysconf('SC_NPROCESSORS_ONLN'))
        if n > 0:
            return n
    except (AttributeError, ValueError):
        pass

    # windows
    try:
        n = int(os.environ['NUMBER_OF_PROCESSORS'])
        if n > 0:
            return n
    except (KeyError, ValueError):
        pass

    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, 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]