Mercurial > hg
view mercurial/pure/mpatch.py @ 50316:87f0155d68aa stable
revlog: improve the robustness of the splitting process
The previous "in-place" splitting, preserving the splitting on transaction
failure had a couple of issue in case of transaction rollback:
- a race windows that could still lead to a crash and data loss
- it corrupted the `fncache`.
So instead, we use a new approach that we summarized as "we do a backup of the
inline revlog pre-split, and we restore this in case of failure".
To make readers live easier, we don't overwrite the inline index file until
transaction finalization. (once the transaction get into its finalization phase,
it is not expected to rollback, unless some crash happens).
To do so, we write the index of the split index in a temporary file that we use
until transaction finalization. We also keep a backup of the initial inline file
to be able to rollback the split if needed.
As a result, transaction rollback cancel the split and no longer corrupt
fncache. We also no longer have a small inconsistency windows where the
transaction could be unrecoverable.
author | Pierre-Yves David <pierre-yves.david@octobus.net> |
---|---|
date | Mon, 20 Mar 2023 11:52:17 +0100 |
parents | 94a797032fc4 |
children | d748fd2647f8 |
line wrap: on
line source
# mpatch.py - Python implementation of mpatch.c # # Copyright 2009 Olivia Mackall <olivia@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. 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