##// END OF EJS Templates
context: write dirstate out explicitly after marking files as clean...
context: write dirstate out explicitly after marking files as clean To detect change of a file without redundant comparison of file content, dirstate recognizes a file as certainly clean, if: (1) it is already known as "normal", (2) dirstate entry for it has valid (= not "-1") timestamp, and (3) mode, size and timestamp of it on the filesystem are as same as ones expected in dirstate This works as expected in many cases, but doesn't in the corner case that changing a file keeps mode, size and timestamp of it on the filesystem. The timetable below shows steps in one of typical such situations: ---- ----------------------------------- ---------------- timestamp of "f" ---------------- dirstate file- time action mem file system ---- ----------------------------------- ---- ----- ----- N -1 *** - make file "f" clean N - execute 'hg foobar' - instantiate 'dirstate' -1 -1 - 'dirstate.normal("f")' N -1 (e.g. via dirty check) - change "f", but keep size N N+1 - release wlock - 'dirstate.write()' N N - 'hg status' shows "f" as "clean" N N N ---- ----------------------------------- ---- ----- ----- The most important point is that 'dirstate.write()' is executed at N+1 or later. This causes writing dirstate timestamp N of "f" out successfully. If it is executed at N, 'parsers.pack_dirstate()' replaces timestamp N with "-1" before actual writing dirstate out. Occasional test failure for unexpected file status is typical example of this corner case. Batch execution with small working directory is finished in no time, and rarely satisfies condition (2) above. This issue can occur in cases below; - 'hg revert --rev REV' for revisions other than the parent - failure of 'merge.update()' before 'merge.recordupdates()' The root cause of this issue is that files are changed without flushing in-memory dirstate changes via 'repo.commit()' (even though omitting 'dirstate.normallookup()' on changed files also causes this issue). To detect changes of files correctly, this patch writes in-memory dirstate changes out explicitly after marking files as clean in 'workingctx._checklookup()', which is invoked via 'repo.status()'. After this change, timetable is changed as below: ---- ----------------------------------- ---------------- timestamp of "f" ---------------- dirstate file- time action mem file system ---- ----------------------------------- ---- ----- ----- N -1 *** - make file "f" clean N - execute 'hg foobar' - instantiate 'dirstate' -1 -1 - 'dirstate.normal("f")' N -1 (e.g. via dirty check) ----------------------------------- ---- ----- ----- - 'dirsttate.write()' -1 -1 ----------------------------------- ---- ----- ----- - change "f", but keep size N N+1 - release wlock - 'dirstate.write()' -1 -1 - 'hg status' -1 -1 N ---- ----------------------------------- ---- ----- ----- To reproduce this issue in tests certainly, this patch emulates some timing critical actions as below: - timestamp of "f" in '.hg/dirstate' is -1 at the beginning 'hg debugrebuildstate' before command invocation ensures it. - make file "f" clean at N - change "f" at N 'touch -t 200001010000' before and after command invocation changes mtime of "f" to "2000-01-01 00:00" (= N). - invoke 'dirstate.write()' via 'repo.status()' at N 'fakedirstatewritetime.py' forces 'pack_dirstate()' to use "2000-01-01 00:00" as "now", only if 'pack_dirstate()' is invoked via 'workingctx._checklookup()'. - invoke 'dirstate.write()' via releasing wlock at N+1 (or "not at N") 'pack_dirstate()' via releasing wlock uses actual timestamp at runtime as "now", and it should be different from the "2000-01-01 00:00" of "f". BTW, this patch also changes 'test-largefiles-misc.t', because adding 'dirstate.write()' makes recent dirstate changes visible to external process.

File last commit:

r25660:328739ea default
r25753:fe03f522 default
Show More
config.py
164 lines | 5.9 KiB | text/x-python | PythonLexer
# config.py - configuration parsing for Mercurial
#
# 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 i18n import _
import error, util
import os, errno
class config(object):
def __init__(self, data=None, includepaths=[]):
self._data = {}
self._source = {}
self._unset = []
self._includepaths = includepaths
if data:
for k in data._data:
self._data[k] = data[k].copy()
self._source = data._source.copy()
def copy(self):
return config(self)
def __contains__(self, section):
return section in self._data
def __getitem__(self, section):
return self._data.get(section, {})
def __iter__(self):
for d in self.sections():
yield d
def update(self, src):
for s, n in src._unset:
if s in self and n in self._data[s]:
del self._data[s][n]
del self._source[(s, n)]
for s in src:
if s not in self:
self._data[s] = util.sortdict()
self._data[s].update(src._data[s])
self._source.update(src._source)
def get(self, section, item, default=None):
return self._data.get(section, {}).get(item, default)
def backup(self, section, item):
"""return a tuple allowing restore to reinstall a previous value
The main reason we need it is because it handles the "no data" case.
"""
try:
value = self._data[section][item]
source = self.source(section, item)
return (section, item, value, source)
except KeyError:
return (section, item)
def source(self, section, item):
return self._source.get((section, item), "")
def sections(self):
return sorted(self._data.keys())
def items(self, section):
return self._data.get(section, {}).items()
def set(self, section, item, value, source=""):
if section not in self:
self._data[section] = util.sortdict()
self._data[section][item] = value
if source:
self._source[(section, item)] = source
def restore(self, data):
"""restore data returned by self.backup"""
if len(data) == 4:
# restore old data
section, item, value, source = data
self._data[section][item] = value
self._source[(section, item)] = source
else:
# no data before, remove everything
section, item = data
if section in self._data:
self._data[section].pop(item, None)
self._source.pop((section, item), None)
def parse(self, src, data, sections=None, remap=None, include=None):
sectionre = util.re.compile(r'\[([^\[]+)\]')
itemre = util.re.compile(r'([^=\s][^=]*?)\s*=\s*(.*\S|)')
contre = util.re.compile(r'\s+(\S|\S.*\S)\s*$')
emptyre = util.re.compile(r'(;|#|\s*$)')
commentre = util.re.compile(r'(;|#)')
unsetre = util.re.compile(r'%unset\s+(\S+)')
includere = util.re.compile(r'%include\s+(\S|\S.*\S)\s*$')
section = ""
item = None
line = 0
cont = False
for l in data.splitlines(True):
line += 1
if line == 1 and l.startswith('\xef\xbb\xbf'):
# Someone set us up the BOM
l = l[3:]
if cont:
if commentre.match(l):
continue
m = contre.match(l)
if m:
if sections and section not in sections:
continue
v = self.get(section, item) + "\n" + m.group(1)
self.set(section, item, v, "%s:%d" % (src, line))
continue
item = None
cont = False
m = includere.match(l)
if m and include:
expanded = util.expandpath(m.group(1))
includepaths = [os.path.dirname(src)] + self._includepaths
for base in includepaths:
inc = os.path.normpath(os.path.join(base, expanded))
try:
include(inc, remap=remap, sections=sections)
break
except IOError as inst:
if inst.errno != errno.ENOENT:
raise error.ParseError(_("cannot include %s (%s)")
% (inc, inst.strerror),
"%s:%s" % (src, line))
continue
if emptyre.match(l):
continue
m = sectionre.match(l)
if m:
section = m.group(1)
if remap:
section = remap.get(section, section)
if section not in self:
self._data[section] = util.sortdict()
continue
m = itemre.match(l)
if m:
item = m.group(1)
cont = True
if sections and section not in sections:
continue
self.set(section, item, m.group(2), "%s:%d" % (src, line))
continue
m = unsetre.match(l)
if m:
name = m.group(1)
if sections and section not in sections:
continue
if self.get(section, name) is not None:
del self._data[section][name]
self._unset.append((section, name))
continue
raise error.ParseError(l.rstrip(), ("%s:%s" % (src, line)))
def read(self, path, fp=None, sections=None, remap=None):
if not fp:
fp = util.posixfile(path)
self.parse(path, fp.read(), sections, remap, self.read)