##// END OF EJS Templates
repair: migrate revlogs during upgrade...
repair: migrate revlogs during upgrade Our next step for in-place upgrade is to migrate store data. Revlogs are the biggest source of data within the store and a store is useless without them, so we implement their migration first. Our strategy for migrating revlogs is to walk the store and call `revlog.clone()` on each revlog. There are some minor complications. Because revlogs have different storage options (e.g. changelog has generaldelta and delta chains disabled), we need to obtain the correct class of revlog so inserted data is encoded properly for its type. Various attempts at implementing progress indicators that didn't lead to frustration from false "it's almost done" indicators were made. I initially used a single progress bar based on number of revlogs. However, this quickly churned through all filelogs, got to 99% then effectively froze at 99.99% when it got to the manifest. So I converted the progress bar to total revision count. This was a little bit better. But the manifest was still significantly slower than filelogs and it took forever to process the last few percent. I then tried both revision/chunk bytes and raw bytes as the denominator. This had the opposite effect: because so much data is in manifests, it would churn through filelogs without showing much progress. When it got to manifests, it would fill in 90+% of the progress bar. I finally gave up having a unified progress bar and instead implemented 3 progress bars: 1 for filelog revisions, 1 for manifest revisions, and 1 for changelog revisions. I added extra messages indicating the total number of revisions of each so users know there are more progress bars coming. I also added extra messages before and after each stage to give extra details about what is happening. Strictly speaking, this isn't necessary. But the numbers are impressive. For example, when converting a non-generaldelta mozilla-central repository, the messages you see are: migrating 2475593 total revisions (1833043 in filelogs, 321156 in manifests, 321394 in changelog) migrating 1.67 GB in store; 2508 GB tracked data migrating 267868 filelogs containing 1833043 revisions (1.09 GB in store; 57.3 GB tracked data) finished migrating 1833043 filelog revisions across 267868 filelogs; change in size: -415776 bytes migrating 1 manifests containing 321156 revisions (518 MB in store; 2451 GB tracked data) That "2508 GB" figure really blew me away. I had no clue that the raw tracked data in mozilla-central was that large. Granted, 2451 GB is in the manifest and "only" 57.3 GB is in filelogs. But still. It's worth noting that gratuitous loading of source revlogs in order to display numbers and progress bars does serve a purpose: it ensures we can open all source revlogs. We don't want to spend several minutes copying revlogs only to encounter a permissions error or similar later. As part of this commit, we also add swapping of the store directory to the upgrade function. After revlogs are converted, we move the old store into the backup directory then move the temporary repo's store into the old store's location. On well-behaved systems, this should be 2 atomic operations and the window of inconsistency show be very narrow. There are still a few improvements to be made to store copying and upgrading. But this commit gets the bulk of the work out of the way.

File last commit:

r30636:f1c9fafc default
r30779:38aa1ca9 default
Show More
windows.py
479 lines | 14.3 KiB | text/x-python | PythonLexer
# windows.py - Windows utility function implementations for Mercurial
#
# Copyright 2005-2009 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 __future__ import absolute_import
import errno
import msvcrt
import os
import re
import stat
import sys
from .i18n import _
from . import (
encoding,
osutil,
pycompat,
win32,
)
try:
import _winreg as winreg
winreg.CloseKey
except ImportError:
import winreg
executablepath = win32.executablepath
getuser = win32.getuser
hidewindow = win32.hidewindow
makedir = win32.makedir
nlinks = win32.nlinks
oslink = win32.oslink
samedevice = win32.samedevice
samefile = win32.samefile
setsignalhandler = win32.setsignalhandler
spawndetached = win32.spawndetached
split = os.path.split
testpid = win32.testpid
unlink = win32.unlink
umask = 0o022
class mixedfilemodewrapper(object):
"""Wraps a file handle when it is opened in read/write mode.
fopen() and fdopen() on Windows have a specific-to-Windows requirement
that files opened with mode r+, w+, or a+ make a call to a file positioning
function when switching between reads and writes. Without this extra call,
Python will raise a not very intuitive "IOError: [Errno 0] Error."
This class wraps posixfile instances when the file is opened in read/write
mode and automatically adds checks or inserts appropriate file positioning
calls when necessary.
"""
OPNONE = 0
OPREAD = 1
OPWRITE = 2
def __init__(self, fp):
object.__setattr__(self, '_fp', fp)
object.__setattr__(self, '_lastop', 0)
def __getattr__(self, name):
return getattr(self._fp, name)
def __setattr__(self, name, value):
return self._fp.__setattr__(name, value)
def _noopseek(self):
self._fp.seek(0, os.SEEK_CUR)
def seek(self, *args, **kwargs):
object.__setattr__(self, '_lastop', self.OPNONE)
return self._fp.seek(*args, **kwargs)
def write(self, d):
if self._lastop == self.OPREAD:
self._noopseek()
object.__setattr__(self, '_lastop', self.OPWRITE)
return self._fp.write(d)
def writelines(self, *args, **kwargs):
if self._lastop == self.OPREAD:
self._noopeseek()
object.__setattr__(self, '_lastop', self.OPWRITE)
return self._fp.writelines(*args, **kwargs)
def read(self, *args, **kwargs):
if self._lastop == self.OPWRITE:
self._noopseek()
object.__setattr__(self, '_lastop', self.OPREAD)
return self._fp.read(*args, **kwargs)
def readline(self, *args, **kwargs):
if self._lastop == self.OPWRITE:
self._noopseek()
object.__setattr__(self, '_lastop', self.OPREAD)
return self._fp.readline(*args, **kwargs)
def readlines(self, *args, **kwargs):
if self._lastop == self.OPWRITE:
self._noopseek()
object.__setattr__(self, '_lastop', self.OPREAD)
return self._fp.readlines(*args, **kwargs)
def posixfile(name, mode='r', buffering=-1):
'''Open a file with even more POSIX-like semantics'''
try:
fp = osutil.posixfile(name, mode, buffering) # may raise WindowsError
# The position when opening in append mode is implementation defined, so
# make it consistent with other platforms, which position at EOF.
if 'a' in mode:
fp.seek(0, os.SEEK_END)
if '+' in mode:
return mixedfilemodewrapper(fp)
return fp
except WindowsError as err:
# convert to a friendlier exception
raise IOError(err.errno, '%s: %s' % (name, err.strerror))
class winstdout(object):
'''stdout on windows misbehaves if sent through a pipe'''
def __init__(self, fp):
self.fp = fp
def __getattr__(self, key):
return getattr(self.fp, key)
def close(self):
try:
self.fp.close()
except IOError:
pass
def write(self, s):
try:
# This is workaround for "Not enough space" error on
# writing large size of data to console.
limit = 16000
l = len(s)
start = 0
self.softspace = 0
while start < l:
end = start + limit
self.fp.write(s[start:end])
start = end
except IOError as inst:
if inst.errno != 0:
raise
self.close()
raise IOError(errno.EPIPE, 'Broken pipe')
def flush(self):
try:
return self.fp.flush()
except IOError as inst:
if inst.errno != errno.EINVAL:
raise
self.close()
raise IOError(errno.EPIPE, 'Broken pipe')
def _is_win_9x():
'''return true if run on windows 95, 98 or me.'''
try:
return sys.getwindowsversion()[3] == 1
except AttributeError:
return 'command' in encoding.environ.get('comspec', '')
def openhardlinks():
return not _is_win_9x()
def parsepatchoutput(output_line):
"""parses the output produced by patch and returns the filename"""
pf = output_line[14:]
if pf[0] == '`':
pf = pf[1:-1] # Remove the quotes
return pf
def sshargs(sshcmd, host, user, port):
'''Build argument list for ssh or Plink'''
pflag = 'plink' in sshcmd.lower() and '-P' or '-p'
args = user and ("%s@%s" % (user, host)) or host
return port and ("%s %s %s" % (args, pflag, port)) or args
def setflags(f, l, x):
pass
def copymode(src, dst, mode=None):
pass
def checkexec(path):
return False
def checklink(path):
return False
def setbinary(fd):
# When run without console, pipes may expose invalid
# fileno(), usually set to -1.
fno = getattr(fd, 'fileno', None)
if fno is not None and fno() >= 0:
msvcrt.setmode(fno(), os.O_BINARY)
def pconvert(path):
return path.replace(pycompat.ossep, '/')
def localpath(path):
return path.replace('/', '\\')
def normpath(path):
return pconvert(os.path.normpath(path))
def normcase(path):
return encoding.upper(path) # NTFS compares via upper()
# see posix.py for definitions
normcasespec = encoding.normcasespecs.upper
normcasefallback = encoding.upperfallback
def samestat(s1, s2):
return False
# A sequence of backslashes is special iff it precedes a double quote:
# - if there's an even number of backslashes, the double quote is not
# quoted (i.e. it ends the quoted region)
# - if there's an odd number of backslashes, the double quote is quoted
# - in both cases, every pair of backslashes is unquoted into a single
# backslash
# (See http://msdn2.microsoft.com/en-us/library/a1y7w461.aspx )
# So, to quote a string, we must surround it in double quotes, double
# the number of backslashes that precede double quotes and add another
# backslash before every double quote (being careful with the double
# quote we've appended to the end)
_quotere = None
_needsshellquote = None
def shellquote(s):
r"""
>>> shellquote(r'C:\Users\xyz')
'"C:\\Users\\xyz"'
>>> shellquote(r'C:\Users\xyz/mixed')
'"C:\\Users\\xyz/mixed"'
>>> # Would be safe not to quote too, since it is all double backslashes
>>> shellquote(r'C:\\Users\\xyz')
'"C:\\\\Users\\\\xyz"'
>>> # But this must be quoted
>>> shellquote(r'C:\\Users\\xyz/abc')
'"C:\\\\Users\\\\xyz/abc"'
"""
global _quotere
if _quotere is None:
_quotere = re.compile(r'(\\*)("|\\$)')
global _needsshellquote
if _needsshellquote is None:
# ":" is also treated as "safe character", because it is used as a part
# of path name on Windows. "\" is also part of a path name, but isn't
# safe because shlex.split() (kind of) treats it as an escape char and
# drops it. It will leave the next character, even if it is another
# "\".
_needsshellquote = re.compile(r'[^a-zA-Z0-9._:/-]').search
if s and not _needsshellquote(s) and not _quotere.search(s):
# "s" shouldn't have to be quoted
return s
return '"%s"' % _quotere.sub(r'\1\1\\\2', s)
def quotecommand(cmd):
"""Build a command string suitable for os.popen* calls."""
if sys.version_info < (2, 7, 1):
# Python versions since 2.7.1 do this extra quoting themselves
return '"' + cmd + '"'
return cmd
def popen(command, mode='r'):
# Work around "popen spawned process may not write to stdout
# under windows"
# http://bugs.python.org/issue1366
command += " 2> %s" % os.devnull
return os.popen(quotecommand(command), mode)
def explainexit(code):
return _("exited with status %d") % code, code
# if you change this stub into a real check, please try to implement the
# username and groupname functions above, too.
def isowner(st):
return True
def findexe(command):
'''Find executable for command searching like cmd.exe does.
If command is a basename then PATH is searched for command.
PATH isn't searched if command is an absolute or relative path.
An extension from PATHEXT is found and added if not present.
If command isn't found None is returned.'''
pathext = encoding.environ.get('PATHEXT', '.COM;.EXE;.BAT;.CMD')
pathexts = [ext for ext in pathext.lower().split(pycompat.ospathsep)]
if os.path.splitext(command)[1].lower() in pathexts:
pathexts = ['']
def findexisting(pathcommand):
'Will append extension (if needed) and return existing file'
for ext in pathexts:
executable = pathcommand + ext
if os.path.exists(executable):
return executable
return None
if pycompat.ossep in command:
return findexisting(command)
for path in encoding.environ.get('PATH', '').split(pycompat.ospathsep):
executable = findexisting(os.path.join(path, command))
if executable is not None:
return executable
return findexisting(os.path.expanduser(os.path.expandvars(command)))
_wantedkinds = set([stat.S_IFREG, stat.S_IFLNK])
def statfiles(files):
'''Stat each file in files. Yield each stat, or None if a file
does not exist or has a type we don't care about.
Cluster and cache stat per directory to minimize number of OS stat calls.'''
dircache = {} # dirname -> filename -> status | None if file does not exist
getkind = stat.S_IFMT
for nf in files:
nf = normcase(nf)
dir, base = os.path.split(nf)
if not dir:
dir = '.'
cache = dircache.get(dir, None)
if cache is None:
try:
dmap = dict([(normcase(n), s)
for n, k, s in osutil.listdir(dir, True)
if getkind(s.st_mode) in _wantedkinds])
except OSError as err:
# Python >= 2.5 returns ENOENT and adds winerror field
# EINVAL is raised if dir is not a directory.
if err.errno not in (errno.ENOENT, errno.EINVAL,
errno.ENOTDIR):
raise
dmap = {}
cache = dircache.setdefault(dir, dmap)
yield cache.get(base, None)
def username(uid=None):
"""Return the name of the user with the given uid.
If uid is None, return the name of the current user."""
return None
def groupname(gid=None):
"""Return the name of the group with the given gid.
If gid is None, return the name of the current group."""
return None
def removedirs(name):
"""special version of os.removedirs that does not remove symlinked
directories or junction points if they actually contain files"""
if osutil.listdir(name):
return
os.rmdir(name)
head, tail = os.path.split(name)
if not tail:
head, tail = os.path.split(head)
while head and tail:
try:
if osutil.listdir(head):
return
os.rmdir(head)
except (ValueError, OSError):
break
head, tail = os.path.split(head)
def unlinkpath(f, ignoremissing=False):
"""unlink and remove the directory if it is empty"""
try:
unlink(f)
except OSError as e:
if not (ignoremissing and e.errno == errno.ENOENT):
raise
# try removing directories that might now be empty
try:
removedirs(os.path.dirname(f))
except OSError:
pass
def rename(src, dst):
'''atomically rename file src to dst, replacing dst if it exists'''
try:
os.rename(src, dst)
except OSError as e:
if e.errno != errno.EEXIST:
raise
unlink(dst)
os.rename(src, dst)
def gethgcmd():
return [sys.executable] + sys.argv[:1]
def groupmembers(name):
# Don't support groups on Windows for now
raise KeyError
def isexec(f):
return False
class cachestat(object):
def __init__(self, path):
pass
def cacheable(self):
return False
def lookupreg(key, valname=None, scope=None):
''' Look up a key/value name in the Windows registry.
valname: value name. If unspecified, the default value for the key
is used.
scope: optionally specify scope for registry lookup, this can be
a sequence of scopes to look up in order. Default (CURRENT_USER,
LOCAL_MACHINE).
'''
if scope is None:
scope = (winreg.HKEY_CURRENT_USER, winreg.HKEY_LOCAL_MACHINE)
elif not isinstance(scope, (list, tuple)):
scope = (scope,)
for s in scope:
try:
val = winreg.QueryValueEx(winreg.OpenKey(s, key), valname)[0]
# never let a Unicode string escape into the wild
return encoding.tolocal(val.encode('UTF-8'))
except EnvironmentError:
pass
expandglobs = True
def statislink(st):
'''check whether a stat result is a symlink'''
return False
def statisexec(st):
'''check whether a stat result is an executable file'''
return False
def poll(fds):
# see posix.py for description
raise NotImplementedError()
def readpipe(pipe):
"""Read all available data from a pipe."""
chunks = []
while True:
size = win32.peekpipe(pipe)
if not size:
break
s = pipe.read(size)
if not s:
break
chunks.append(s)
return ''.join(chunks)
def bindunixsocket(sock, path):
raise NotImplementedError('unsupported platform')