##// END OF EJS Templates
xdiff: add a preprocessing step that trims files...
xdiff: add a preprocessing step that trims files xdiff has a `xdl_trim_ends` step that removes common lines, unmatchable lines. That is in theory good, but happens too late - after splitting, hashing, and adjusting the hash values so they are unique. Those splitting, hashing and adjusting hash values steps could have noticeable overhead. Diffing two large files with minor (one-line-ish) changes are not uncommon. In that case, the raw performance of those preparation steps seriously matter. Even allocating an O(N) array and storing line offsets to it is expensive. Therefore my previous attempts [1] [2] cannot be good enough since they do not remove the O(N) array assignment. This patch adds a preprocessing step - `xdl_trim_files` that runs before other preprocessing steps. It counts common prefix and suffix and lines in them (needed for displaying line number), without doing anything else. Testing with a crafted large (169MB) file, with minor change: ``` open('a','w').write(''.join('%s\n' % (i % 100000) for i in xrange(30000000) if i != 6000000)) open('b','w').write(''.join('%s\n' % (i % 100000) for i in xrange(30000000) if i != 6003000)) ``` Running xdiff by a simple binary [3], this patch improves the xdiff perf by more than 10x for the above case: ``` # xdiff before this patch 2.41s user 1.13s system 98% cpu 3.592 total # xdiff after this patch 0.14s user 0.16s system 98% cpu 0.309 total # gnu diffutils 0.12s user 0.15s system 98% cpu 0.272 total # (best of 20 runs) ``` It's still slightly slower than GNU diffutils. But it's pretty close now. Testing with real repo data: For the whole repo, this patch makes xdiff 25% faster: ``` # hg perfbdiff --count 100 --alldata -c d334afc585e2 --blocks [--xdiff] # xdiff, after ! wall 0.058861 comb 0.050000 user 0.050000 sys 0.000000 (best of 100) # xdiff, before ! wall 0.077816 comb 0.080000 user 0.080000 sys 0.000000 (best of 91) # bdiff ! wall 0.117473 comb 0.120000 user 0.120000 sys 0.000000 (best of 67) ``` For files that are long (ex. commands.py), the speedup is more than 3x, very significant: ``` # hg perfbdiff --count 3000 --blocks commands.py.i 1 [--xdiff] # xdiff, after ! wall 0.690583 comb 0.690000 user 0.690000 sys 0.000000 (best of 12) # xdiff, before ! wall 2.240361 comb 2.210000 user 2.210000 sys 0.000000 (best of 4) # bdiff ! wall 2.469852 comb 2.440000 user 2.440000 sys 0.000000 (best of 4) ``` [1]: https://phab.mercurial-scm.org/D2631 [2]: https://phab.mercurial-scm.org/D2634 [3]: ``` // Code to run xdiff from command line. No proper error handling. #include <stdlib.h> #include <unistd.h> #include <sys/types.h> #include <sys/stat.h> #include <fcntl.h> #include "mercurial/thirdparty/xdiff/xdiff.h" #define ensure(x) if (!(x)) exit(255); mmfile_t readfile(const char *path) { struct stat st; int fd = open(path, O_RDONLY); fstat(fd, &st); mmfile_t file = { malloc(st.st_size), st.st_size }; ensure(read(fd, file.ptr, st.st_size) == st.st_size); close(fd); return file; } int main(int argc, char const *argv[]) { mmfile_t a = readfile(argv[1]), b = readfile(argv[2]); xpparam_t xpp = {0}; xdemitconf_t xecfg = {0}; xdemitcb_t ecb = {0}; xdl_diff(&a, &b, &xpp, &xecfg, &ecb); return 0; } ``` Differential Revision: https://phab.mercurial-scm.org/D2686

File last commit:

r36717:d77c3b02 default
r36838:f33a87cf default
Show More
lock.py
389 lines | 12.8 KiB | text/x-python | PythonLexer
# lock.py - simple advisory locking scheme for mercurial
#
# Copyright 2005, 2006 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 __future__ import absolute_import
import contextlib
import errno
import os
import signal
import socket
import time
import warnings
from .i18n import _
from . import (
encoding,
error,
pycompat,
util,
)
def _getlockprefix():
"""Return a string which is used to differentiate pid namespaces
It's useful to detect "dead" processes and remove stale locks with
confidence. Typically it's just hostname. On modern linux, we include an
extra Linux-specific pid namespace identifier.
"""
result = encoding.strtolocal(socket.gethostname())
if pycompat.sysplatform.startswith('linux'):
try:
result += '/%x' % os.stat('/proc/self/ns/pid').st_ino
except OSError as ex:
if ex.errno not in (errno.ENOENT, errno.EACCES, errno.ENOTDIR):
raise
return result
@contextlib.contextmanager
def _delayedinterrupt():
"""Block signal interrupt while doing something critical
This makes sure that the code block wrapped by this context manager won't
be interrupted.
For Windows developers: It appears not possible to guard time.sleep()
from CTRL_C_EVENT, so please don't use time.sleep() to test if this is
working.
"""
assertedsigs = []
blocked = False
orighandlers = {}
def raiseinterrupt(num):
if (num == getattr(signal, 'SIGINT', None) or
num == getattr(signal, 'CTRL_C_EVENT', None)):
raise KeyboardInterrupt
else:
raise error.SignalInterrupt
def catchterm(num, frame):
if blocked:
assertedsigs.append(num)
else:
raiseinterrupt(num)
try:
# save handlers first so they can be restored even if a setup is
# interrupted between signal.signal() and orighandlers[] =.
for name in ['CTRL_C_EVENT', 'SIGINT', 'SIGBREAK', 'SIGHUP', 'SIGTERM']:
num = getattr(signal, name, None)
if num and num not in orighandlers:
orighandlers[num] = signal.getsignal(num)
try:
for num in orighandlers:
signal.signal(num, catchterm)
except ValueError:
pass # in a thread? no luck
blocked = True
yield
finally:
# no simple way to reliably restore all signal handlers because
# any loops, recursive function calls, except blocks, etc. can be
# interrupted. so instead, make catchterm() raise interrupt.
blocked = False
try:
for num, handler in orighandlers.items():
signal.signal(num, handler)
except ValueError:
pass # in a thread?
# re-raise interrupt exception if any, which may be shadowed by a new
# interrupt occurred while re-raising the first one
if assertedsigs:
raiseinterrupt(assertedsigs[0])
def trylock(ui, vfs, lockname, timeout, warntimeout, *args, **kwargs):
"""return an acquired lock or raise an a LockHeld exception
This function is responsible to issue warnings and or debug messages about
the held lock while trying to acquires it."""
def printwarning(printer, locker):
"""issue the usual "waiting on lock" message through any channel"""
# show more details for new-style locks
if ':' in locker:
host, pid = locker.split(":", 1)
msg = (_("waiting for lock on %s held by process %r on host %r\n")
% (pycompat.bytestr(l.desc), pycompat.bytestr(pid),
pycompat.bytestr(host)))
else:
msg = (_("waiting for lock on %s held by %r\n")
% (l.desc, pycompat.bytestr(locker)))
printer(msg)
l = lock(vfs, lockname, 0, *args, dolock=False, **kwargs)
debugidx = 0 if (warntimeout and timeout) else -1
warningidx = 0
if not timeout:
warningidx = -1
elif warntimeout:
warningidx = warntimeout
delay = 0
while True:
try:
l._trylock()
break
except error.LockHeld as inst:
if delay == debugidx:
printwarning(ui.debug, inst.locker)
if delay == warningidx:
printwarning(ui.warn, inst.locker)
if timeout <= delay:
raise error.LockHeld(errno.ETIMEDOUT, inst.filename,
l.desc, inst.locker)
time.sleep(1)
delay += 1
l.delay = delay
if l.delay:
if 0 <= warningidx <= l.delay:
ui.warn(_("got lock after %d seconds\n") % l.delay)
else:
ui.debug("got lock after %d seconds\n" % l.delay)
if l.acquirefn:
l.acquirefn()
return l
class lock(object):
'''An advisory lock held by one process to control access to a set
of files. Non-cooperating processes or incorrectly written scripts
can ignore Mercurial's locking scheme and stomp all over the
repository, so don't do that.
Typically used via localrepository.lock() to lock the repository
store (.hg/store/) or localrepository.wlock() to lock everything
else under .hg/.'''
# lock is symlink on platforms that support it, file on others.
# symlink is used because create of directory entry and contents
# are atomic even over nfs.
# old-style lock: symlink to pid
# new-style lock: symlink to hostname:pid
_host = None
def __init__(self, vfs, file, timeout=-1, releasefn=None, acquirefn=None,
desc=None, inheritchecker=None, parentlock=None,
dolock=True):
self.vfs = vfs
self.f = file
self.held = 0
self.timeout = timeout
self.releasefn = releasefn
self.acquirefn = acquirefn
self.desc = desc
self._inheritchecker = inheritchecker
self.parentlock = parentlock
self._parentheld = False
self._inherited = False
self.postrelease = []
self.pid = self._getpid()
if dolock:
self.delay = self.lock()
if self.acquirefn:
self.acquirefn()
def __enter__(self):
return self
def __exit__(self, exc_type, exc_value, exc_tb):
self.release()
def __del__(self):
if self.held:
warnings.warn("use lock.release instead of del lock",
category=DeprecationWarning,
stacklevel=2)
# ensure the lock will be removed
# even if recursive locking did occur
self.held = 1
self.release()
def _getpid(self):
# wrapper around util.getpid() to make testing easier
return util.getpid()
def lock(self):
timeout = self.timeout
while True:
try:
self._trylock()
return self.timeout - timeout
except error.LockHeld as inst:
if timeout != 0:
time.sleep(1)
if timeout > 0:
timeout -= 1
continue
raise error.LockHeld(errno.ETIMEDOUT, inst.filename, self.desc,
inst.locker)
def _trylock(self):
if self.held:
self.held += 1
return
if lock._host is None:
lock._host = _getlockprefix()
lockname = '%s:%d' % (lock._host, self.pid)
retry = 5
while not self.held and retry:
retry -= 1
try:
with _delayedinterrupt():
self.vfs.makelock(lockname, self.f)
self.held = 1
except (OSError, IOError) as why:
if why.errno == errno.EEXIST:
locker = self._readlock()
if locker is None:
continue
# special case where a parent process holds the lock -- this
# is different from the pid being different because we do
# want the unlock and postrelease functions to be called,
# but the lockfile to not be removed.
if locker == self.parentlock:
self._parentheld = True
self.held = 1
return
locker = self._testlock(locker)
if locker is not None:
raise error.LockHeld(errno.EAGAIN,
self.vfs.join(self.f), self.desc,
locker)
else:
raise error.LockUnavailable(why.errno, why.strerror,
why.filename, self.desc)
if not self.held:
# use empty locker to mean "busy for frequent lock/unlock
# by many processes"
raise error.LockHeld(errno.EAGAIN,
self.vfs.join(self.f), self.desc, "")
def _readlock(self):
"""read lock and return its value
Returns None if no lock exists, pid for old-style locks, and host:pid
for new-style locks.
"""
try:
return self.vfs.readlock(self.f)
except (OSError, IOError) as why:
if why.errno == errno.ENOENT:
return None
raise
def _testlock(self, locker):
if locker is None:
return None
try:
host, pid = locker.split(":", 1)
except ValueError:
return locker
if host != lock._host:
return locker
try:
pid = int(pid)
except ValueError:
return locker
if util.testpid(pid):
return locker
# if locker dead, break lock. must do this with another lock
# held, or can race and break valid lock.
try:
l = lock(self.vfs, self.f + '.break', timeout=0)
self.vfs.unlink(self.f)
l.release()
except error.LockError:
return locker
def testlock(self):
"""return id of locker if lock is valid, else None.
If old-style lock, we cannot tell what machine locker is on.
with new-style lock, if locker is on this machine, we can
see if locker is alive. If locker is on this machine but
not alive, we can safely break lock.
The lock file is only deleted when None is returned.
"""
locker = self._readlock()
return self._testlock(locker)
@contextlib.contextmanager
def inherit(self):
"""context for the lock to be inherited by a Mercurial subprocess.
Yields a string that will be recognized by the lock in the subprocess.
Communicating this string to the subprocess needs to be done separately
-- typically by an environment variable.
"""
if not self.held:
raise error.LockInheritanceContractViolation(
'inherit can only be called while lock is held')
if self._inherited:
raise error.LockInheritanceContractViolation(
'inherit cannot be called while lock is already inherited')
if self._inheritchecker is not None:
self._inheritchecker()
if self.releasefn:
self.releasefn()
if self._parentheld:
lockname = self.parentlock
else:
lockname = '%s:%s' % (lock._host, self.pid)
self._inherited = True
try:
yield lockname
finally:
if self.acquirefn:
self.acquirefn()
self._inherited = False
def release(self):
"""release the lock and execute callback function if any
If the lock has been acquired multiple times, the actual release is
delayed to the last release call."""
if self.held > 1:
self.held -= 1
elif self.held == 1:
self.held = 0
if self._getpid() != self.pid:
# we forked, and are not the parent
return
try:
if self.releasefn:
self.releasefn()
finally:
if not self._parentheld:
try:
self.vfs.unlink(self.f)
except OSError:
pass
# The postrelease functions typically assume the lock is not held
# at all.
if not self._parentheld:
for callback in self.postrelease:
callback()
# Prevent double usage and help clear cycles.
self.postrelease = None
def release(*locks):
for lock in locks:
if lock is not None:
lock.release()