Mercurial > hg-stable
view tests/test-filecache.py @ 26379:39d643252b9f
revlog: use existing file handle when reading during _addrevision
_addrevision() may need to read from revlogs as part of computing
deltas. Previously, we would flush existing file handles and open
a new, short-lived file handle to perform the reading.
If we have an existing file handle, it seems logical to reuse it
for reading instead of opening a new file handle. This patch
makes that the new behavior.
After this patch, revlog files are only reopened when adding
revisions if the revlog is switched from inline to non-inline.
On Linux when unbundling a bundle of the mozilla-central repo, this
patch has the following impact on system call counts:
Call Before After Delta
write 827,639 673,390 -154,249
open 700,103 684,089 -16,014
read 74,489 74,489 0
fstat 493,924 461,896 -32,028
close 249,131 233,117 -16,014
stat 242,001 242,001 0
lstat 18,676 18,676 0
lseek 20,268 20,268 0
ioctl 14,652 13,173 -1,479
TOTAL 3,180,758 2,930,679 -250,079
It's worth noting that many of the open() calls fail due to missing
files. That's why there are many more open() calls than close().
Despite the significant system call reduction, this change does not
seem to have a significant performance impact on Linux.
On Windows 10 (not a VM, on a SSD), this patch appears to reduce
unbundle time for mozilla-central from ~960s to ~920s. This isn't
as significant as I was hoping. But a decrease it is nonetheless.
Still, Windows unbundle performance is still >2x slower than Linux.
Despite the lack of significant gains, fewer system calls is fewer
system calls. If nothing else, this will narrow the focus of potential
areas to optimize in the future.
author | Gregory Szorc <gregory.szorc@gmail.com> |
---|---|
date | Sun, 27 Sep 2015 16:08:18 -0700 |
parents | ce26928cbe41 |
children | fc5f548393bf |
line wrap: on
line source
import sys, os, subprocess if subprocess.call(['python', '%s/hghave' % os.environ['TESTDIR'], 'cacheable']): sys.exit(80) from mercurial import util, scmutil, extensions, hg, ui filecache = scmutil.filecache class fakerepo(object): def __init__(self): self._filecache = {} def join(self, p): return p def sjoin(self, p): return p @filecache('x', 'y') def cached(self): print 'creating' return 'string from function' def invalidate(self): for k in self._filecache: try: delattr(self, k) except AttributeError: pass def basic(repo): print "* neither file exists" # calls function repo.cached repo.invalidate() print "* neither file still exists" # uses cache repo.cached # create empty file f = open('x', 'w') f.close() repo.invalidate() print "* empty file x created" # should recreate the object repo.cached f = open('x', 'w') f.write('a') f.close() repo.invalidate() print "* file x changed size" # should recreate the object repo.cached repo.invalidate() print "* nothing changed with either file" # stats file again, reuses object repo.cached # atomic replace file, size doesn't change # hopefully st_mtime doesn't change as well so this doesn't use the cache # because of inode change f = scmutil.opener('.')('x', 'w', atomictemp=True) f.write('b') f.close() repo.invalidate() print "* file x changed inode" repo.cached # create empty file y f = open('y', 'w') f.close() repo.invalidate() print "* empty file y created" # should recreate the object repo.cached f = open('y', 'w') f.write('A') f.close() repo.invalidate() print "* file y changed size" # should recreate the object repo.cached f = scmutil.opener('.')('y', 'w', atomictemp=True) f.write('B') f.close() repo.invalidate() print "* file y changed inode" repo.cached f = scmutil.opener('.')('x', 'w', atomictemp=True) f.write('c') f.close() f = scmutil.opener('.')('y', 'w', atomictemp=True) f.write('C') f.close() repo.invalidate() print "* both files changed inode" repo.cached def fakeuncacheable(): def wrapcacheable(orig, *args, **kwargs): return False def wrapinit(orig, *args, **kwargs): pass originit = extensions.wrapfunction(util.cachestat, '__init__', wrapinit) origcacheable = extensions.wrapfunction(util.cachestat, 'cacheable', wrapcacheable) for fn in ['x', 'y']: try: os.remove(fn) except OSError: pass basic(fakerepo()) util.cachestat.cacheable = origcacheable util.cachestat.__init__ = originit def test_filecache_synced(): # test old behavior that caused filecached properties to go out of sync os.system('hg init && echo a >> a && hg ci -qAm.') repo = hg.repository(ui.ui()) # first rollback clears the filecache, but changelog to stays in __dict__ repo.rollback() repo.commit('.') # second rollback comes along and touches the changelog externally # (file is moved) repo.rollback() # but since changelog isn't under the filecache control anymore, we don't # see that it changed, and return the old changelog without reconstructing # it repo.commit('.') def setbeforeget(repo): os.remove('x') os.remove('y') repo.cached = 'string set externally' repo.invalidate() print "* neither file exists" print repo.cached repo.invalidate() f = open('x', 'w') f.write('a') f.close() print "* file x created" print repo.cached repo.cached = 'string 2 set externally' repo.invalidate() print "* string set externally again" print repo.cached repo.invalidate() f = open('y', 'w') f.write('b') f.close() print "* file y created" print repo.cached print 'basic:' print basic(fakerepo()) print print 'fakeuncacheable:' print fakeuncacheable() test_filecache_synced() print print 'setbeforeget:' print setbeforeget(fakerepo())