##// 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
hook.py
204 lines | 7.5 KiB | text/x-python | PythonLexer
# hook.py - hook support for mercurial
#
# Copyright 2007 Matt Mackall <mpm@selenic.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 i18n import _
import os, sys, time
import extensions, util, demandimport, error
def _pythonhook(ui, repo, name, hname, funcname, args, throw):
'''call python hook. hook is callable object, looked up as
name in python module. if callable returns "true", hook
fails, else passes. if hook raises exception, treated as
hook failure. exception propagates if throw is "true".
reason for "true" meaning "hook failed" is so that
unmodified commands (e.g. mercurial.commands.update) can
be run as hooks without wrappers to convert return values.'''
if callable(funcname):
obj = funcname
funcname = obj.__module__ + "." + obj.__name__
else:
d = funcname.rfind('.')
if d == -1:
raise util.Abort(_('%s hook is invalid ("%s" not in '
'a module)') % (hname, funcname))
modname = funcname[:d]
oldpaths = sys.path
if util.mainfrozen():
# binary installs require sys.path manipulation
modpath, modfile = os.path.split(modname)
if modpath and modfile:
sys.path = sys.path[:] + [modpath]
modname = modfile
with demandimport.deactivated():
try:
obj = __import__(modname)
except ImportError:
e1 = sys.exc_type, sys.exc_value, sys.exc_traceback
try:
# extensions are loaded with hgext_ prefix
obj = __import__("hgext_%s" % modname)
except ImportError:
e2 = sys.exc_type, sys.exc_value, sys.exc_traceback
if ui.tracebackflag:
ui.warn(_('exception from first failed import '
'attempt:\n'))
ui.traceback(e1)
if ui.tracebackflag:
ui.warn(_('exception from second failed import '
'attempt:\n'))
ui.traceback(e2)
raise util.Abort(_('%s hook is invalid '
'(import of "%s" failed)') %
(hname, modname))
sys.path = oldpaths
try:
for p in funcname.split('.')[1:]:
obj = getattr(obj, p)
except AttributeError:
raise util.Abort(_('%s hook is invalid '
'("%s" is not defined)') %
(hname, funcname))
if not callable(obj):
raise util.Abort(_('%s hook is invalid '
'("%s" is not callable)') %
(hname, funcname))
ui.note(_("calling hook %s: %s\n") % (hname, funcname))
starttime = time.time()
try:
# redirect IO descriptors to the ui descriptors so hooks
# that write directly to these don't mess up the command
# protocol when running through the command server
old = sys.stdout, sys.stderr, sys.stdin
sys.stdout, sys.stderr, sys.stdin = ui.fout, ui.ferr, ui.fin
r = obj(ui=ui, repo=repo, hooktype=name, **args)
except Exception as exc:
if isinstance(exc, util.Abort):
ui.warn(_('error: %s hook failed: %s\n') %
(hname, exc.args[0]))
else:
ui.warn(_('error: %s hook raised an exception: '
'%s\n') % (hname, exc))
if throw:
raise
ui.traceback()
return True
finally:
sys.stdout, sys.stderr, sys.stdin = old
duration = time.time() - starttime
ui.log('pythonhook', 'pythonhook-%s: %s finished in %0.2f seconds\n',
name, funcname, duration)
if r:
if throw:
raise error.HookAbort(_('%s hook failed') % hname)
ui.warn(_('warning: %s hook failed\n') % hname)
return r
def _exthook(ui, repo, name, cmd, args, throw):
ui.note(_("running hook %s: %s\n") % (name, cmd))
starttime = time.time()
env = {}
for k, v in args.iteritems():
if callable(v):
v = v()
if isinstance(v, dict):
# make the dictionary element order stable across Python
# implementations
v = ('{' +
', '.join('%r: %r' % i for i in sorted(v.iteritems())) +
'}')
env['HG_' + k.upper()] = v
if repo:
cwd = repo.root
else:
cwd = os.getcwd()
r = ui.system(cmd, environ=env, cwd=cwd)
duration = time.time() - starttime
ui.log('exthook', 'exthook-%s: %s finished in %0.2f seconds\n',
name, cmd, duration)
if r:
desc, r = util.explainexit(r)
if throw:
raise error.HookAbort(_('%s hook %s') % (name, desc))
ui.warn(_('warning: %s hook %s\n') % (name, desc))
return r
def _allhooks(ui):
hooks = []
for name, cmd in ui.configitems('hooks'):
if not name.startswith('priority'):
priority = ui.configint('hooks', 'priority.%s' % name, 0)
hooks.append((-priority, len(hooks), name, cmd))
return [(k, v) for p, o, k, v in sorted(hooks)]
_redirect = False
def redirect(state):
global _redirect
_redirect = state
def hook(ui, repo, name, throw=False, **args):
if not ui.callhooks:
return False
r = False
oldstdout = -1
try:
for hname, cmd in _allhooks(ui):
if hname.split('.')[0] != name or not cmd:
continue
if oldstdout == -1 and _redirect:
try:
stdoutno = sys.__stdout__.fileno()
stderrno = sys.__stderr__.fileno()
# temporarily redirect stdout to stderr, if possible
if stdoutno >= 0 and stderrno >= 0:
sys.__stdout__.flush()
oldstdout = os.dup(stdoutno)
os.dup2(stderrno, stdoutno)
except (OSError, AttributeError):
# files seem to be bogus, give up on redirecting (WSGI, etc)
pass
if callable(cmd):
r = _pythonhook(ui, repo, name, hname, cmd, args, throw) or r
elif cmd.startswith('python:'):
if cmd.count(':') >= 2:
path, cmd = cmd[7:].rsplit(':', 1)
path = util.expandpath(path)
if repo:
path = os.path.join(repo.root, path)
try:
mod = extensions.loadpath(path, 'hghook.%s' % hname)
except Exception:
ui.write(_("loading %s hook failed:\n") % hname)
raise
hookfn = getattr(mod, cmd)
else:
hookfn = cmd[7:].strip()
r = _pythonhook(ui, repo, name, hname, hookfn, args, throw) or r
else:
r = _exthook(ui, repo, hname, cmd, args, throw) or r
# The stderr is fully buffered on Windows when connected to a pipe.
# A forcible flush is required to make small stderr data in the
# remote side available to the client immediately.
sys.stderr.flush()
finally:
if _redirect and oldstdout >= 0:
os.dup2(oldstdout, stdoutno)
os.close(oldstdout)
return r