annotate mercurial/cffi/mpatch.py @ 41978:a56487081109

store: don't read the whole fncache in memory

In large repositories with lot of files, the fncache grows more than 100 MB and
reading that whole thing into memory slows things down. Let's not read the whole
thing into memory.

This patch changes fncache loading code to read 1 MB at once. Loading 1 MB at
once saves ~1 sec on perffncacheload for our internal repository. I tried
various values such as 0.5 MB, 5 MB, 10 MB but best results were produced using
1 MB as the chunksize.

On a narrow clone with fncache around 40 MB, this patch saves ~0.04 seconds on
average on perffncacheload.

To test the code, I have coded an extension in test-fncache.t which set
chunksize to 1 byte, and the test passes with that.

Differential Revision: https://phab.mercurial-scm.org/D5296

# 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