mercurial/pure/mpatch.py

stream-clone: avoid opening a revlog in case we do not need it

Opening an revlog has a cost, especially if it is inline as we have to scan the
file and construct an index.

To prevent the associated slowdown, we just do a minimal scan to check that an
inline file is still inline, and simply stream the file without creating a
revlog when we can.

This provides a big boost compared to the previous changeset, even if the full
generation is still penalized by the initial gathering of information.

All benchmarks are run on linux with Python 3.10.7.
# benchmark.name             = hg.exchange.stream.generate
# benchmark.variants.version = v2

### Compared to the previous changesets

We get a large win all across the board!

# mercurial-2018-08-01-zstd-sparse-revlog
before:  0.250694 seconds
after:   0.105986 seconds  (-57.72%)
# pypy-2018-08-01-zstd-sparse-revlog
before:  3.885657 seconds
after:   1.709748 seconds  (-56.00%)
# netbeans-2018-08-01-zstd-sparse-revlog
before: 16.679371 seconds
after:   7.687469 seconds  (-53.91%)
# mozilla-central-2018-08-01-zstd-sparse-revlog
before: 38.575482 seconds
after:  17.520316 seconds  (-54.58%)
# mozilla-try-2019-02-18-zstd-sparse-revlog
before: 81.160994 seconds
after:  37.073753 seconds  (-54.32%)



### Compared to 6.4.3

We are still significantly slower than 6.4.3, the extra time is usually twice
slower than the extra time we observe on the locked section, which is a quite
interesting information.

Except for mercurial-central that is much faster. That discrepancy is not really
explained yet.

# mercurial-2018-08-01-zstd-sparse-revlog
6.4.3:  0.072560 seconds
after:  0.105986 seconds  (+46.07%) (- 0.03 seconds)
# pypy-2018-08-01-zstd-sparse-revlog
6.4.3:  1.211193 seconds
after:  1.709748 seconds  (+41.16%) (-0.45 seconds)
# netbeans-2018-08-01-zstd-sparse-revlog
6.4.3:  4.932843 seconds
after:  7.687469 seconds  (+55.84%) (-2.75 seconds)
# mozilla-central-2018-08-01-zstd-sparse-revlog
6.4.3: 34.012226 seconds
after: 17.520316 seconds  (-48.49%) (-16.49 seconds)
# mozilla-try-2019-02-18-zstd-sparse-revlog
6.4.3: 23.850555 seconds
after: 37.073753 seconds  (+55.44%) (+13.22 seconds)

# mpatch.py - Python implementation of mpatch.c
#
# Copyright 2009 Olivia 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.


import io
import struct

from typing import (
    List,
    Tuple,
)


stringio = io.BytesIO


class mpatchError(Exception):
    """error raised when a delta cannot be decoded"""


# This attempts to apply a series of patches in time proportional to
# the total size of the patches, rather than patches * len(text). This
# means rather than shuffling strings around, we shuffle around
# pointers to fragments with fragment lists.
#
# When the fragment lists get too long, we collapse them. To do this
# efficiently, we do all our operations inside a buffer created by
# mmap and simply use memmove. This avoids creating a bunch of large
# temporary string buffers.


def _pull(
    dst: List[Tuple[int, int]], src: List[Tuple[int, int]], l: int
) -> None:  # pull l bytes from src
    while l:
        f = src.pop()
        if f[0] > l:  # do we need to split?
            src.append((f[0] - l, f[1] + l))
            dst.append((l, f[1]))
            return
        dst.append(f)
        l -= f[0]


def _move(m: stringio, dest: int, src: int, count: int) -> None:
    """move count bytes from src to dest

    The file pointer is left at the end of dest.
    """
    m.seek(src)
    buf = m.read(count)
    m.seek(dest)
    m.write(buf)


def _collect(
    m: stringio, buf: int, list: List[Tuple[int, int]]
) -> Tuple[int, int]:
    start = buf
    for l, p in reversed(list):
        _move(m, buf, p, l)
        buf += l
    return (buf - start, start)


def patches(a: bytes, bins: List[bytes]) -> bytes:
    if not bins:
        return a

    plens = [len(x) for x in bins]
    pl = sum(plens)
    bl = len(a) + pl
    tl = bl + bl + pl  # enough for the patches and two working texts
    b1, b2 = 0, bl

    if not tl:
        return a

    m = stringio()

    # load our original text
    m.write(a)
    frags = [(len(a), b1)]

    # copy all the patches into our segment so we can memmove from them
    pos = b2 + bl
    m.seek(pos)
    for p in bins:
        m.write(p)

    for plen in plens:
        # if our list gets too long, execute it
        if len(frags) > 128:
            b2, b1 = b1, b2
            frags = [_collect(m, b1, frags)]

        new = []
        end = pos + plen
        last = 0
        while pos < end:
            m.seek(pos)
            try:
                p1, p2, l = struct.unpack(b">lll", m.read(12))
            except struct.error:
                raise mpatchError(b"patch cannot be decoded")
            _pull(new, frags, p1 - last)  # what didn't change
            _pull([], frags, p2 - p1)  # what got deleted
            new.append((l, pos + 12))  # what got added
            pos += l + 12
            last = p2
        frags.extend(reversed(new))  # what was left at the end

    t = _collect(m, b2, frags)

    m.seek(t[1])
    return m.read(t[0])


def patchedsize(orig: int, delta: bytes) -> int:
    outlen, last, bin = 0, 0, 0
    binend = len(delta)
    data = 12

    while data <= binend:
        decode = delta[bin : bin + 12]
        start, end, length = struct.unpack(b">lll", decode)
        if start > end:
            break
        bin = data + length
        data = bin + 12
        outlen += start - last
        last = end
        outlen += length

    if bin != binend:
        raise mpatchError(b"patch cannot be decoded")

    outlen += orig - last
    return outlen