Mercurial > hg
view mercurial/lock.py @ 30451:94ca0e13d1fc
perf: add command for measuring revlog chunk operations
Upcoming commits will teach revlogs to leverage the new compression
engine API so that new compression formats can more easily be
leveraged in revlogs. We want to be sure this refactoring doesn't
regress performance. So this commit introduces "perfrevchunks" to
explicitly test performance of reading, decompressing, and
recompressing revlog chunks.
Here is output when run on the mozilla-unified repo:
$ hg perfrevlogchunks -c
! read
! wall 0.346603 comb 0.350000 user 0.340000 sys 0.010000 (best of 28)
! read w/ reused fd
! wall 0.337707 comb 0.340000 user 0.320000 sys 0.020000 (best of 30)
! read batch
! wall 0.013206 comb 0.020000 user 0.000000 sys 0.020000 (best of 221)
! read batch w/ reused fd
! wall 0.013259 comb 0.030000 user 0.010000 sys 0.020000 (best of 222)
! chunk
! wall 1.909939 comb 1.910000 user 1.900000 sys 0.010000 (best of 6)
! chunk batch
! wall 1.750677 comb 1.760000 user 1.740000 sys 0.020000 (best of 6)
! compress
! wall 5.668004 comb 5.670000 user 5.670000 sys 0.000000 (best of 3)
$ hg perfrevlogchunks -m
! read
! wall 0.365834 comb 0.370000 user 0.350000 sys 0.020000 (best of 26)
! read w/ reused fd
! wall 0.350160 comb 0.350000 user 0.320000 sys 0.030000 (best of 28)
! read batch
! wall 0.024777 comb 0.020000 user 0.000000 sys 0.020000 (best of 119)
! read batch w/ reused fd
! wall 0.024895 comb 0.030000 user 0.000000 sys 0.030000 (best of 118)
! chunk
! wall 2.514061 comb 2.520000 user 2.480000 sys 0.040000 (best of 4)
! chunk batch
! wall 2.380788 comb 2.380000 user 2.360000 sys 0.020000 (best of 5)
! compress
! wall 9.815297 comb 9.820000 user 9.820000 sys 0.000000 (best of 3)
We already see some interesting data, such as how much slower
non-batched chunk reading is and that zlib compression appears to be
>2x slower than decompression.
I didn't have the data when I wrote this commit message, but I ran this
on Mozilla's NFS-based Mercurial server and the time for reading with a
reused file descriptor was faster. So I think it is worth testing both
with and without file descriptor reuse so we can make informed
decisions about recycling file descriptors.
author | Gregory Szorc <gregory.szorc@gmail.com> |
---|---|
date | Thu, 17 Nov 2016 20:17:51 -0800 |
parents | 518c3e392f75 |
children | dc9f086c7691 |
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. from __future__ import absolute_import import contextlib import errno import socket import time import warnings from . import ( error, util, ) 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): 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() 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 = socket.gethostname() lockname = '%s:%s' % (lock._host, self.pid) retry = 5 while not self.held and retry: retry -= 1 try: self.vfs.makelock(lockname, self.f) self.held = 1 except (OSError, IOError) as why: if why.errno == errno.EEXIST: locker = self._readlock() # 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) 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()