##// END OF EJS Templates
manifest: persist the manifestfulltext cache...
manifest: persist the manifestfulltext cache Reconstructing the manifest from the revlog takes time, so much so that there already is a LRU cache to avoid having to load a manifest multiple times. This patch persists that LRU cache in the .hg/cache directory, so we can re-use this cache across hg commands. Commit benchmark (run on Macos 10.13 on a 2017-model Macbook Pro with Core i7 2.9GHz and flash drive), testing without and with patch run 5 times, baseline is r2a227782e754: * committing to an existing file, against the mozilla-central repository. Baseline real time average 1.9692, with patch 1.3786. A new debugcommand "hg debugmanifestfulltextcache" lets you inspect the cache, clear it, or add specific manifest nodeids to it. When calling repo.updatecaches(), the manifest(s) for the working copy parents are added to the cache. The hg perfmanifest command has an additional --clear-disk switch to clear this cache when testing manifest loading performance. Using this command to test performance on the firefox repository for revision f947d902ed91, whose manifest has a delta chain length of 60540, we see: $ hg perfmanifest f947d902ed91 --clear-disk ! wall 0.972253 comb 0.970000 user 0.850000 sys 0.120000 (best of 10) $ hg debugmanifestfulltextcache -a `hg log --debug -r f947d902ed91 | grep manifest | cut -d: -f3` Cache contains 1 manifest entries, in order of most to least recent: id: 0294517df4aad07c70701db43bc7ff24c3ce7dbc, size 25.6 MB Total cache data size 25.6 MB, on-disk 0 bytes $ hg perfmanifest f947d902ed91 ! wall 0.036748 comb 0.040000 user 0.020000 sys 0.020000 (best of 100) Worst-case scenario: a manifest text loaded from a single delta; in the firefox repository manifest node 9a1246ff762e is the chain base for the manifest attached to revision f947d902ed91. Loading this from a full cache file is just as fast as without the cache; the extra node ids ensure a big full cache: $ for node in 9a1246ff762e 1a1922c14a3e 54a31d11a36a 0294517df4aa; do > hgd debugmanifestfulltextcache -a $node > /dev/null > done $ hgd perfmanifest -m 9a1246ff762e ! wall 0.077513 comb 0.080000 user 0.030000 sys 0.050000 (best of 100) $ hgd perfmanifest -m 9a1246ff762e --clear-disk ! wall 0.078547 comb 0.080000 user 0.070000 sys 0.010000 (best of 100)

File last commit:

r38001:bbdc1bc5 default
r38803:0a57945a 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)