view mercurial/worker.py @ 23845:0a7fd54d4e60

revset: introduce "_parsealiasdecl" to parse alias declarations strictly

This patch introduces "_parsealiasdecl" to parse alias declarations
strictly. For example, "_parsealiasdecl" can detect problems below,
which current implementation can't.

  - un-closed parenthesis causes being treated as "alias symbol"

    because all of declarations not in "func(....)" style are
    recognized as "alias symbol".

    for example, "foo($1, $2" is treated as the alias symbol.

  - alias symbol/function names aren't examined whether they are valid
    as symbol or not

    for example, "foo bar" can be treated as the alias symbol, but of
    course such invalid symbol can't be referred in revset.

  - just splitting argument list by "," causes overlooking syntax
    problems in the declaration

    for example, all of invalid declarations below are overlooked:

    - foo("bar")     => taking one argument named as '"bar"'
    - foo("unclosed) => taking one argument named as '"unclosed'
    - foo(bar::baz)  => taking one argument named as 'bar::baz'
    - foo(bar($1))   => taking one argument named as 'bar($1)'

To decrease complication of patch, current implementation for alias
declarations is replaced by "_parsealiasdecl" in the subsequent
patch. This patch just introduces it.

This patch defines "_parsealiasdecl" not as a method of "revsetalias"
class but as a one of "revset" module, because of ease of testing by
doctest.

This patch factors some helper functions for "tree" out, because:

  - direct accessing like "if tree[0] == 'func' and len(tree) > 1"
    decreases readability

  - subsequent patch (and also existing code paths, in the future) can
    use them for readability

This patch also factors "_tokenizealias" out, because it can be used
also for parsing alias definitions strictly.

# 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]