##// END OF EJS Templates
util: teach lrucachedict to enforce a max total cost...
util: teach lrucachedict to enforce a max total cost Now that lrucachedict entries can have a numeric cost associated with them and we can easily pop the oldest item in the cache, it now becomes relatively trivial to implement support for enforcing a high water mark on the total cost of items in the cache. This commit teaches lrucachedict instances to have a max cost associated with them. When items are inserted, we pop old items until enough "cost" frees up to make room for the new item. This feature is close to zero cost when not used (modulo the insertion regressed introduced by the previous commit): $ ./hg perflrucachedict --size 4 --gets 1000000 --sets 1000000 --mixed 1000000 ! gets ! wall 0.607444 comb 0.610000 user 0.610000 sys 0.000000 (best of 17) ! wall 0.601653 comb 0.600000 user 0.600000 sys 0.000000 (best of 17) ! inserts ! wall 0.678261 comb 0.680000 user 0.680000 sys 0.000000 (best of 14) ! wall 0.685042 comb 0.680000 user 0.680000 sys 0.000000 (best of 15) ! sets ! wall 0.808770 comb 0.800000 user 0.800000 sys 0.000000 (best of 13) ! wall 0.834241 comb 0.830000 user 0.830000 sys 0.000000 (best of 12) ! mixed ! wall 0.782441 comb 0.780000 user 0.780000 sys 0.000000 (best of 13) ! wall 0.803804 comb 0.800000 user 0.800000 sys 0.000000 (best of 13) $ hg perflrucachedict --size 1000 --gets 1000000 --sets 1000000 --mixed 1000000 ! init ! wall 0.006952 comb 0.010000 user 0.010000 sys 0.000000 (best of 418) ! gets ! wall 0.613350 comb 0.610000 user 0.610000 sys 0.000000 (best of 17) ! wall 0.617415 comb 0.620000 user 0.620000 sys 0.000000 (best of 17) ! inserts ! wall 0.701270 comb 0.700000 user 0.700000 sys 0.000000 (best of 15) ! wall 0.700516 comb 0.700000 user 0.700000 sys 0.000000 (best of 15) ! sets ! wall 0.825720 comb 0.830000 user 0.830000 sys 0.000000 (best of 13) ! wall 0.837946 comb 0.840000 user 0.830000 sys 0.010000 (best of 12) ! mixed ! wall 0.821644 comb 0.820000 user 0.820000 sys 0.000000 (best of 13) ! wall 0.850559 comb 0.850000 user 0.850000 sys 0.000000 (best of 12) I reckon the slight slowdown on insert is due to added if checks. For caches with total cost limiting enabled: $ hg perflrucachedict --size 4 --gets 1000000 --sets 1000000 --mixed 1000000 --costlimit 100 ! gets w/ cost limit ! wall 0.598737 comb 0.590000 user 0.590000 sys 0.000000 (best of 17) ! inserts w/ cost limit ! wall 1.694282 comb 1.700000 user 1.700000 sys 0.000000 (best of 6) ! mixed w/ cost limit ! wall 1.157655 comb 1.150000 user 1.150000 sys 0.000000 (best of 9) $ hg perflrucachedict --size 1000 --gets 1000000 --sets 1000000 --mixed 1000000 --costlimit 10000 ! gets w/ cost limit ! wall 0.598526 comb 0.600000 user 0.600000 sys 0.000000 (best of 17) ! inserts w/ cost limit ! wall 37.838315 comb 37.840000 user 37.840000 sys 0.000000 (best of 3) ! mixed w/ cost limit ! wall 18.060198 comb 18.060000 user 18.060000 sys 0.000000 (best of 3) $ hg perflrucachedict --size 1000 --gets 1000000 --sets 1000000 --mixed 1000000 --costlimit 10000 --mixedgetfreq 90 ! gets w/ cost limit ! wall 0.600024 comb 0.600000 user 0.600000 sys 0.000000 (best of 17) ! inserts w/ cost limit ! wall 37.154547 comb 37.120000 user 37.120000 sys 0.000000 (best of 3) ! mixed w/ cost limit ! wall 4.381602 comb 4.380000 user 4.370000 sys 0.010000 (best of 3) The functions we're benchmarking are slightly different, which could move numbers by a few milliseconds. But the slowdown on insert is too great to be explained by that. The slowness is due to insert heavy operations needing to call popoldest() repeatedly when the cache is at capacity. The next commit will address this. Differential Revision: https://phab.mercurial-scm.org/D4503

File last commit:

r38001:bbdc1bc5 default
r39604:842cd0bd default
Show More
logexchange.py
152 lines | 4.6 KiB | text/x-python | PythonLexer
# logexchange.py
#
# Copyright 2017 Augie Fackler <raf@durin42.com>
# Copyright 2017 Sean Farley <sean@farley.io>
#
# 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
from .node import hex
from . import (
util,
vfs as vfsmod,
)
# directory name in .hg/ in which remotenames files will be present
remotenamedir = 'logexchange'
def readremotenamefile(repo, filename):
"""
reads a file from .hg/logexchange/ directory and yields it's content
filename: the file to be read
yield a tuple (node, remotepath, name)
"""
vfs = vfsmod.vfs(repo.vfs.join(remotenamedir))
if not vfs.exists(filename):
return
f = vfs(filename)
lineno = 0
for line in f:
line = line.strip()
if not line:
continue
# contains the version number
if lineno == 0:
lineno += 1
try:
node, remote, rname = line.split('\0')
yield node, remote, rname
except ValueError:
pass
f.close()
def readremotenames(repo):
"""
read the details about the remotenames stored in .hg/logexchange/ and
yields a tuple (node, remotepath, name). It does not yields information
about whether an entry yielded is branch or bookmark. To get that
information, call the respective functions.
"""
for bmentry in readremotenamefile(repo, 'bookmarks'):
yield bmentry
for branchentry in readremotenamefile(repo, 'branches'):
yield branchentry
def writeremotenamefile(repo, remotepath, names, nametype):
vfs = vfsmod.vfs(repo.vfs.join(remotenamedir))
f = vfs(nametype, 'w', atomictemp=True)
# write the storage version info on top of file
# version '0' represents the very initial version of the storage format
f.write('0\n\n')
olddata = set(readremotenamefile(repo, nametype))
# re-save the data from a different remote than this one.
for node, oldpath, rname in sorted(olddata):
if oldpath != remotepath:
f.write('%s\0%s\0%s\n' % (node, oldpath, rname))
for name, node in sorted(names.iteritems()):
if nametype == "branches":
for n in node:
f.write('%s\0%s\0%s\n' % (n, remotepath, name))
elif nametype == "bookmarks":
if node:
f.write('%s\0%s\0%s\n' % (node, remotepath, name))
f.close()
def saveremotenames(repo, remotepath, branches=None, bookmarks=None):
"""
save remotenames i.e. remotebookmarks and remotebranches in their
respective files under ".hg/logexchange/" directory.
"""
wlock = repo.wlock()
try:
if bookmarks:
writeremotenamefile(repo, remotepath, bookmarks, 'bookmarks')
if branches:
writeremotenamefile(repo, remotepath, branches, 'branches')
finally:
wlock.release()
def activepath(repo, remote):
"""returns remote path"""
local = None
# is the remote a local peer
local = remote.local()
# determine the remote path from the repo, if possible; else just
# use the string given to us
rpath = remote
if local:
rpath = remote._repo.root
elif not isinstance(remote, bytes):
rpath = remote._url
# represent the remotepath with user defined path name if exists
for path, url in repo.ui.configitems('paths'):
# remove auth info from user defined url
noauthurl = util.removeauth(url)
if url == rpath or noauthurl == rpath:
rpath = path
break
return rpath
def pullremotenames(localrepo, remoterepo):
"""
pulls bookmarks and branches information of the remote repo during a
pull or clone operation.
localrepo is our local repository
remoterepo is the peer instance
"""
remotepath = activepath(localrepo, remoterepo)
with remoterepo.commandexecutor() as e:
bookmarks = e.callcommand('listkeys', {
'namespace': 'bookmarks',
}).result()
# on a push, we don't want to keep obsolete heads since
# they won't show up as heads on the next pull, so we
# remove them here otherwise we would require the user
# to issue a pull to refresh the storage
bmap = {}
repo = localrepo.unfiltered()
with remoterepo.commandexecutor() as e:
branchmap = e.callcommand('branchmap', {}).result()
for branch, nodes in branchmap.iteritems():
bmap[branch] = []
for node in nodes:
if node in repo and not repo[node].obsolete():
bmap[branch].append(hex(node))
saveremotenames(localrepo, remotepath, bmap, bookmarks)