view mercurial/fancyopts.py @ 29861:2f6d5c60f6fc stable

annotate: pre-calculate the "needed" dictionary (issue5360)

The "needed" dict is used as a reference counter to free items in the giant
"hist" dict. However, currently it is not very accurate and can lead to
dropping "hist" items unnecessarily, for example, with the following DAG,

       -3-
      /   \
  0--1--2--4--

The current algorithm will visit and calculate rev 1 twice, undesired. And
it tries to be smart by clearing rev 1's parents: "pcache[1] = []" at the
time hist[1] being accessed (note: hist[1] needs to be used twice, by rev 2
and rev 3). It can result in incorrect results if p1 of rev 4 deletes chunks
belonging to rev 0.

However, simply removing "needed" is not okay, because it will consume 10x
memory:

  # without any change
  % HGRCPATH= lrun ./hg annotate mercurial/commands.py -r d130a38 3>&2 [1]
  MEMORY   49074176
  CPUTIME  9.213
  REALTIME 9.270

  # with "needed" removed
  MEMORY   637673472
  CPUTIME  8.164
  REALTIME 8.249

This patch moves "needed" (and "pcache") calculation to a separate DFS to
address the issue. It improves perf and fixes issue5360 by correctly reusing
hist, while maintaining low memory usage. Some additional attempt has been
made to further reduce memory usage, like changing "pcache[f] = []" to "del
pcache[f]". Therefore the result can be both faster and lower memory usage:

  # with this patch applied
  MEMORY   47575040
  CPUTIME  7.870
  REALTIME 7.926

[1]: lrun is a lightweight sandbox built on Linux cgroup and namespace. It's
     used to measure CPU and memory usage here. Source code is available at
     github.com/quark-zju/lrun.

# fancyopts.py - better command line parsing
#
#  Copyright 2005-2009 Matt Mackall <[e-mail]> and others
#
# 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 getopt

from .i18n import _
from . import error

def gnugetopt(args, options, longoptions):
    """Parse options mostly like getopt.gnu_getopt.

    This is different from getopt.gnu_getopt in that an argument of - will
    become an argument of - instead of vanishing completely.
    """
    extraargs = []
    if '--' in args:
        stopindex = args.index('--')
        extraargs = args[stopindex + 1:]
        args = args[:stopindex]
    opts, parseargs = getopt.getopt(args, options, longoptions)
    args = []
    while parseargs:
        arg = parseargs.pop(0)
        if arg and arg[0] == '-' and len(arg) > 1:
            parseargs.insert(0, arg)
            topts, newparseargs = getopt.getopt(parseargs, options, longoptions)
            opts = opts + topts
            parseargs = newparseargs
        else:
            args.append(arg)
    args.extend(extraargs)
    return opts, args


def fancyopts(args, options, state, gnu=False):
    """
    read args, parse options, and store options in state

    each option is a tuple of:

      short option or ''
      long option
      default value
      description
      option value label(optional)

    option types include:

      boolean or none - option sets variable in state to true
      string - parameter string is stored in state
      list - parameter string is added to a list
      integer - parameter strings is stored as int
      function - call function with parameter

    non-option args are returned
    """
    namelist = []
    shortlist = ''
    argmap = {}
    defmap = {}

    for option in options:
        if len(option) == 5:
            short, name, default, comment, dummy = option
        else:
            short, name, default, comment = option
        # convert opts to getopt format
        oname = name
        name = name.replace('-', '_')

        argmap['-' + short] = argmap['--' + oname] = name
        defmap[name] = default

        # copy defaults to state
        if isinstance(default, list):
            state[name] = default[:]
        elif callable(default):
            state[name] = None
        else:
            state[name] = default

        # does it take a parameter?
        if not (default is None or default is True or default is False):
            if short:
                short += ':'
            if oname:
                oname += '='
        if short:
            shortlist += short
        if name:
            namelist.append(oname)

    # parse arguments
    if gnu:
        parse = gnugetopt
    else:
        parse = getopt.getopt
    opts, args = parse(args, shortlist, namelist)

    # transfer result to state
    for opt, val in opts:
        name = argmap[opt]
        obj = defmap[name]
        t = type(obj)
        if callable(obj):
            state[name] = defmap[name](val)
        elif t is type(1):
            try:
                state[name] = int(val)
            except ValueError:
                raise error.Abort(_('invalid value %r for option %s, '
                                   'expected int') % (val, opt))
        elif t is type(''):
            state[name] = val
        elif t is type([]):
            state[name].append(val)
        elif t is type(None) or t is type(False):
            state[name] = True

    # return unparsed args
    return args