view mercurial/pure/parsers.py @ 26117:4dc5b51f38fe

revlog: change generaldelta delta parent heuristic The old generaldelta heuristic was "if p1 (or p2) was closer than the last full text, use it, otherwise use prev". This was problematic when a repo contained multiple branches that were very different. If commits to branch A were pushed, and the last full text was branch B, it would generate a fulltext. Then if branch B was pushed, it would generate another fulltext. The problem is that the last fulltext (and delta'ing against `prev` in general) has no correlation with the contents of the incoming revision, and therefore will always have degenerate cases. According to the blame, that algorithm was chosen to minimize the chain length. Since there is already code that protects against that (the delta-vs-fulltext code), and since it has been improved since the original generaldelta algorithm went in (2011), I believe the chain length criteria will still be preserved. The new algorithm always diffs against p1 (or p2 if it's closer), unless the resulting delta will fail the delta-vs-fulltext check, in which case we delta against prev. Some before and after stats on manifest.d size. internal large repo old heuristic - 2.0 GB new heuristic - 1.2 GB mozilla-central old heuristic - 242 MB new heuristic - 261 MB The regression in mozilla central is due to the new heuristic choosing p2r as the delta when it's closer to the tip. Switching the algorithm to always prefer p1r brings the size back down (242 MB). This is result of the way in which mozilla does merges and pushes, and the result could easily swing the other direction in other repos (depending on if they merge X into Y or Y into X), but will never be as degenerate as before. I future patch will address the regression by introducing an optional, even more aggressive delta heuristic which will knock the mozilla manifest size down dramatically.
author Durham Goode <durham@fb.com>
date Sun, 30 Aug 2015 13:58:11 -0700
parents 4ece2847cf4c
children 6ab8c6511a6a
line wrap: on
line source

# parsers.py - Python implementation of parsers.c
#
# Copyright 2009 Matt Mackall <mpm@selenic.com> 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 mercurial.node import nullid
import struct, zlib, cStringIO

_pack = struct.pack
_unpack = struct.unpack
_compress = zlib.compress
_decompress = zlib.decompress

# Some code below makes tuples directly because it's more convenient. However,
# code outside this module should always use dirstatetuple.
def dirstatetuple(*x):
    # x is a tuple
    return x

def parse_index2(data, inline):
    def gettype(q):
        return int(q & 0xFFFF)

    def offset_type(offset, type):
        return long(long(offset) << 16 | type)

    indexformatng = ">Qiiiiii20s12x"

    s = struct.calcsize(indexformatng)
    index = []
    cache = None
    off = 0

    l = len(data) - s
    append = index.append
    if inline:
        cache = (0, data)
        while off <= l:
            e = _unpack(indexformatng, data[off:off + s])
            append(e)
            if e[1] < 0:
                break
            off += e[1] + s
    else:
        while off <= l:
            e = _unpack(indexformatng, data[off:off + s])
            append(e)
            off += s

    if off != len(data):
        raise ValueError('corrupt index file')

    if index:
        e = list(index[0])
        type = gettype(e[0])
        e[0] = offset_type(0, type)
        index[0] = tuple(e)

    # add the magic null revision at -1
    index.append((0, 0, 0, -1, -1, -1, -1, nullid))

    return index, cache

def parse_dirstate(dmap, copymap, st):
    parents = [st[:20], st[20: 40]]
    # dereference fields so they will be local in loop
    format = ">cllll"
    e_size = struct.calcsize(format)
    pos1 = 40
    l = len(st)

    # the inner loop
    while pos1 < l:
        pos2 = pos1 + e_size
        e = _unpack(">cllll", st[pos1:pos2]) # a literal here is faster
        pos1 = pos2 + e[4]
        f = st[pos2:pos1]
        if '\0' in f:
            f, c = f.split('\0')
            copymap[f] = c
        dmap[f] = e[:4]
    return parents

def pack_dirstate(dmap, copymap, pl, now):
    now = int(now)
    cs = cStringIO.StringIO()
    write = cs.write
    write("".join(pl))
    for f, e in dmap.iteritems():
        if e[0] == 'n' and e[3] == now:
            # The file was last modified "simultaneously" with the current
            # write to dirstate (i.e. within the same second for file-
            # systems with a granularity of 1 sec). This commonly happens
            # for at least a couple of files on 'update'.
            # The user could change the file without changing its size
            # within the same second. Invalidate the file's mtime in
            # dirstate, forcing future 'status' calls to compare the
            # contents of the file if the size is the same. This prevents
            # mistakenly treating such files as clean.
            e = dirstatetuple(e[0], e[1], e[2], -1)
            dmap[f] = e

        if f in copymap:
            f = "%s\0%s" % (f, copymap[f])
        e = _pack(">cllll", e[0], e[1], e[2], e[3], len(f))
        write(e)
        write(f)
    return cs.getvalue()