##// END OF EJS Templates
manifest: avoid corruption by dropping removed files with pure (issue5801)...
manifest: avoid corruption by dropping removed files with pure (issue5801) Previously, removed files would simply be marked by overwriting the first byte with NUL and dropping their entry in `self.position`. But no effort was made to ignore them when compacting the dictionary into text form. This allowed them to slip into the manifest revision, since the code seems to be trying to minimize the string operations by copying as large a chunk as possible. As part of this, compact() walks the existing text based on entries in the `positions` list, and consumed everything up to the next position entry. This typically resulted in a ValueError complaining about unsorted manifest entries. Sometimes it seems that files do get dropped in large repos- it seems to correspond to there being a new entry that would take the same slot. A much more trivial problem is that if the only changes were removals, `_compact()` didn't even run because `__delitem__` doesn't add anything to `self.extradata`. Now there's an explicit variable to flag this, both to allow `_compact()` to run, and to avoid searching the manifest in cases where there are no removals. In practice, this behavior was mostly obscured by the check in fastdelta() which takes a different path that explicitly drops removed files if there are fewer than 1000 changes. However, timeless has a repo where after rebasing tens of commits, a totally different path[1] is taken that bypasses the change count check and hits this problem. [1] https://www.mercurial-scm.org/repo/hg/file/2338bdea4474/mercurial/manifest.py#l1511

File last commit:

r34648:dacfcdd8 default
r42569:0546ead3 stable
Show More
osutil.py
102 lines | 3.5 KiB | text/x-python | PythonLexer
# osutil.py - CFFI version of osutil.c
#
# Copyright 2016 Maciej Fijalkowski <fijall@gmail.com>
#
# 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
import os
import stat as statmod
from ..pure.osutil import *
from .. import (
pycompat,
)
if pycompat.isdarwin:
from . import _osutil
ffi = _osutil.ffi
lib = _osutil.lib
listdir_batch_size = 4096
# tweakable number, only affects performance, which chunks
# of bytes do we get back from getattrlistbulk
attrkinds = [None] * 20 # we need the max no for enum VXXX, 20 is plenty
attrkinds[lib.VREG] = statmod.S_IFREG
attrkinds[lib.VDIR] = statmod.S_IFDIR
attrkinds[lib.VLNK] = statmod.S_IFLNK
attrkinds[lib.VBLK] = statmod.S_IFBLK
attrkinds[lib.VCHR] = statmod.S_IFCHR
attrkinds[lib.VFIFO] = statmod.S_IFIFO
attrkinds[lib.VSOCK] = statmod.S_IFSOCK
class stat_res(object):
def __init__(self, st_mode, st_mtime, st_size):
self.st_mode = st_mode
self.st_mtime = st_mtime
self.st_size = st_size
tv_sec_ofs = ffi.offsetof("struct timespec", "tv_sec")
buf = ffi.new("char[]", listdir_batch_size)
def listdirinternal(dfd, req, stat, skip):
ret = []
while True:
r = lib.getattrlistbulk(dfd, req, buf, listdir_batch_size, 0)
if r == 0:
break
if r == -1:
raise OSError(ffi.errno, os.strerror(ffi.errno))
cur = ffi.cast("val_attrs_t*", buf)
for i in range(r):
lgt = cur.length
assert lgt == ffi.cast('uint32_t*', cur)[0]
ofs = cur.name_info.attr_dataoffset
str_lgt = cur.name_info.attr_length
base_ofs = ffi.offsetof('val_attrs_t', 'name_info')
name = str(ffi.buffer(ffi.cast("char*", cur) + base_ofs + ofs,
str_lgt - 1))
tp = attrkinds[cur.obj_type]
if name == "." or name == "..":
continue
if skip == name and tp == statmod.S_ISDIR:
return []
if stat:
mtime = cur.mtime.tv_sec
mode = (cur.accessmask & ~lib.S_IFMT)| tp
ret.append((name, tp, stat_res(st_mode=mode, st_mtime=mtime,
st_size=cur.datalength)))
else:
ret.append((name, tp))
cur = ffi.cast("val_attrs_t*", int(ffi.cast("intptr_t", cur))
+ lgt)
return ret
def listdir(path, stat=False, skip=None):
req = ffi.new("struct attrlist*")
req.bitmapcount = lib.ATTR_BIT_MAP_COUNT
req.commonattr = (lib.ATTR_CMN_RETURNED_ATTRS |
lib.ATTR_CMN_NAME |
lib.ATTR_CMN_OBJTYPE |
lib.ATTR_CMN_ACCESSMASK |
lib.ATTR_CMN_MODTIME)
req.fileattr = lib.ATTR_FILE_DATALENGTH
dfd = lib.open(path, lib.O_RDONLY, 0)
if dfd == -1:
raise OSError(ffi.errno, os.strerror(ffi.errno))
try:
ret = listdirinternal(dfd, req, stat, skip)
finally:
try:
lib.close(dfd)
except BaseException:
pass # we ignore all the errors from closing, not
# much we can do about that
return ret