mercurial/cffi/mpatch.py

bundle2: inline changegroup.readexactly()

Profiling reveals this loop is pretty tight. Literally any
function call elimination can make a big difference.

This commit inlines the relatively trivial changegroup.readexactly()
method inside the loop.

The results with `hg perfbundleread` on a bundle of the Firefox repo
speak for themselves:

! read(8k)
! wall 0.679730 comb 0.680000 user 0.140000 sys 0.540000 (best of 15)
! read(16k)
! wall 0.577228 comb 0.570000 user 0.080000 sys 0.490000 (best of 17)
! read(32k)
! wall 0.516060 comb 0.520000 user 0.040000 sys 0.480000 (best of 20)
! read(128k)
! wall 0.496378 comb 0.490000 user 0.010000 sys 0.480000 (best of 20)
! bundle2 iterparts()
! wall 3.460903 comb 3.460000 user 2.760000 sys 0.700000 (best of 3)
! wall 3.056811 comb 3.050000 user 2.340000 sys 0.710000 (best of 4)
! bundle2 iterparts() seekable
! wall 4.312722 comb 4.310000 user 3.480000 sys 0.830000 (best of 3)
! wall 4.007676 comb 4.000000 user 3.170000 sys 0.830000 (best of 3)
! bundle2 part seek()
! wall 6.754764 comb 6.740000 user 3.970000 sys 2.770000 (best of 3)
! wall 6.267110 comb 6.250000 user 3.480000 sys 2.770000 (best of 3)
! bundle2 part read(8k)
! wall 3.668004 comb 3.660000 user 2.960000 sys 0.700000 (best of 3)
! wall 3.404164 comb 3.400000 user 2.650000 sys 0.750000 (best of 3)
! bundle2 part read(16k)
! wall 3.489196 comb 3.480000 user 2.750000 sys 0.730000 (best of 3)
! wall 3.197972 comb 3.200000 user 2.490000 sys 0.710000 (best of 4)
! bundle2 part read(32k)
! wall 3.388569 comb 3.380000 user 2.640000 sys 0.740000 (best of 3)
! wall 3.060557 comb 3.060000 user 2.340000 sys 0.720000 (best of 4)
! bundle2 part read(128k)
! wall 3.276415 comb 3.270000 user 2.560000 sys 0.710000 (best of 4)
! wall 2.952209 comb 2.950000 user 2.230000 sys 0.720000 (best of 4)

Differential Revision: https://phab.mercurial-scm.org/D1392

# mpatch.py - CFFI implementation of mpatch.c
#
# Copyright 2016 Maciej Fijalkowski <[e-mail]>
#
# 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

from ..pure.mpatch import *
from ..pure.mpatch import mpatchError  # silence pyflakes
from . import _mpatch

ffi = _mpatch.ffi
lib = _mpatch.lib

@ffi.def_extern()
def cffi_get_next_item(arg, pos):
    all, bins = ffi.from_handle(arg)
    container = ffi.new("struct mpatch_flist*[1]")
    to_pass = ffi.new("char[]", str(bins[pos]))
    all.append(to_pass)
    r = lib.mpatch_decode(to_pass, len(to_pass) - 1, container)
    if r < 0:
        return ffi.NULL
    return container[0]

def patches(text, bins):
    lgt = len(bins)
    all = []
    if not lgt:
        return text
    arg = (all, bins)
    patch = lib.mpatch_fold(ffi.new_handle(arg),
                            lib.cffi_get_next_item, 0, lgt)
    if not patch:
        raise mpatchError("cannot decode chunk")
    outlen = lib.mpatch_calcsize(len(text), patch)
    if outlen < 0:
        lib.mpatch_lfree(patch)
        raise mpatchError("inconsistency detected")
    buf = ffi.new("char[]", outlen)
    if lib.mpatch_apply(buf, text, len(text), patch) < 0:
        lib.mpatch_lfree(patch)
        raise mpatchError("error applying patches")
    res = ffi.buffer(buf, outlen)[:]
    lib.mpatch_lfree(patch)
    return res