view mercurial/worker.py @ 22506:6e1fbcb18a75 stable

hgweb: fail if an invalid command was supplied in url path (issue4071)

Traditionally, the way to specify a command for hgweb was to use url query
arguments (e.g. "?cmd=batch"). If the command is unknown to hgweb, it gives an
error (e.g. "400 no such method: badcmd").

But there's also another way to specify a command: as a url path fragment (e.g.
"/graph"). Before, hgweb was made forgiving (looks like it was made in
44c5157474e7) and user could put any unknown command in the url. If hgweb
couldn't understand it, it would just silently fall back to the default
command, which depends on the actual style (e.g. for paper it's shortlog, for
monoblue it's summary). This was inconsistent and was breaking some tools that
rely on http status codes (as noted in the issue4071). So this patch changes
that behavior to the more consistent one, i.e. hgweb will now return "400 no
such method: badcmd".

So if some tool was relying on having an invalid command return http status
code 200 and also have some information, then it will stop working. That is, if
somebody typed foobar when they really meant shortlog (and the user was lucky
enough to choose a style where the default command is shortlog too), that fact
will now be revealed.

Code-wise, the changed if block is only relevant when there's no "?cmd" query
parameter (i.e. only when command is specified as a url path fragment), and
looks like the removed else branch was there only for falling back to default
command. With that removed, the rest of the code works as expected: it looks at
the command, and if it's not known, raises a proper ErrorResponse exception
with an appropriate message.

Evidently, there were no tests that required the old behavior. But, frankly, I
don't know any way to tell if anyone actually exploited such forgiving behavior
in some in-house tool.

# 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 _ 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]