Mercurial > hg
view mercurial/lock.py @ 21809:e250b8300e6e
parsers: inline fields of dirstate values in C version
Previously, while unpacking the dirstate we'd create 3-4 new CPython objects
for most dirstate values:
- the state is a single character string, which is pooled by CPython
- the mode is a new object if it isn't 0 due to being in the lookup set
- the size is a new object if it is greater than 255
- the mtime is a new object if it isn't -1 due to being in the lookup set
- the tuple to contain them all
In some cases such as regular hg status, we actually look at all the objects.
In other cases like hg add, hg status for a subdirectory, or hg status with the
third-party hgwatchman enabled, we look at almost none of the objects.
This patch eliminates most object creation in these cases by defining a custom
C struct that is exposed to Python with an interface similar to a tuple. Only
when tuple elements are actually requested are the respective objects created.
The gains, where they're expected, are significant. The following tests are run
against a working copy with over 270,000 files.
parse_dirstate becomes significantly faster:
$ hg perfdirstate
before: wall 0.186437 comb 0.180000 user 0.160000 sys 0.020000 (best of 35)
after: wall 0.093158 comb 0.100000 user 0.090000 sys 0.010000 (best of 95)
and as a result, several commands benefit:
$ time hg status # with hgwatchman enabled
before: 0.42s user 0.14s system 99% cpu 0.563 total
after: 0.34s user 0.12s system 99% cpu 0.471 total
$ time hg add new-file
before: 0.85s user 0.18s system 99% cpu 1.033 total
after: 0.76s user 0.17s system 99% cpu 0.931 total
There is a slight regression in regular status performance, but this is fixed
in an upcoming patch.
author | Siddharth Agarwal <sid0@fb.com> |
---|---|
date | Tue, 27 May 2014 14:27:41 -0700 |
parents | c697b70f295f |
children | f484be02bd35 |
line wrap: on
line source
# 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. import util, error import errno, os, socket, time import warnings 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, desc=None): self.vfs = vfs self.f = file self.held = 0 self.timeout = timeout self.releasefn = releasefn self.desc = desc self.postrelease = [] self.pid = os.getpid() self.delay = self.lock() 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 lock(self): timeout = self.timeout while True: try: self.trylock() return self.timeout - timeout except error.LockHeld, 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 = socket.gethostname() lockname = '%s:%s' % (lock._host, self.pid) while not self.held: try: self.vfs.makelock(lockname, self.f) self.held = 1 except (OSError, IOError), why: if why.errno == errno.EEXIST: locker = self.testlock() 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) 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. """ try: locker = self.vfs.readlock(self.f) except (OSError, IOError), why: if why.errno == errno.ENOENT: return None raise 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 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 os.getpid() != self.pid: # we forked, and are not the parent return if self.releasefn: self.releasefn() try: self.vfs.unlink(self.f) except OSError: pass for callback in self.postrelease: callback() def release(*locks): for lock in locks: if lock is not None: lock.release()