##// END OF EJS Templates
nodemap: also use persistent nodemap for manifest...
nodemap: also use persistent nodemap for manifest The manifest as a different usage pattern than the changelog. First, while the lookup in changelog are not garanteed to match, the lookup in the manifest nodemap come from changelog and will exist in the manifest. In addition, looking up a manifest almost always result in unpacking a manifest an operation that rarely come cheap. Nevertheless, using a persistent nodemap provide a significant gain for some operations. For our measurementw, we use `hg cat --rev REV FILE` on the our reference mozilla-try. On this repository the persistent nodemap cache is about 29 MB in side for a total store side of 11,988 MB File with large history (file: b2g/config/gaia.json, revision: 195a1146daa0) no optimisation: 0.358s using mmap for index: 0.297s (-0.061s) persistent nodemap for changelog only: 0.275s (-0.024s) persistent nodemap for manifest too: 0.258s (-0.017s) File with small history (file: .hgignore, revision: 195a1146daa0) no optimisation: 0.377s using mmap for index: 0.296s (-0.061s) persistent nodemap for changelog only: 0.274s (-0.022s) persistent nodemap for manifest too: 0.257s (-0.017s) Same file but using a revision (8ba995b74e18) with a smaller manifest (3944829 bytes vs 10 bytes) no optimisation: 0.192s (-0.185s) using mmap for index: 0.131s (-0.061s) persistent nodemap for changelog only: 0.106s (-0.025s) persistent nodemap for manifest too: 0.087s (-0.019s) Differential Revision: https://phab.mercurial-scm.org/D8410

File last commit:

r43872:10f53873 default
r45290:640d5b3b default
Show More
unionrepo.py
286 lines | 8.9 KiB | text/x-python | PythonLexer
# unionrepo.py - repository class for viewing union of repository changesets
#
# Derived from bundlerepo.py
# Copyright 2006, 2007 Benoit Boissinot <bboissin@gmail.com>
# Copyright 2013 Unity Technologies, Mads Kiilerich <madski@unity3d.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
"""Repository class for "in-memory pull" of one local repository to another,
allowing operations like diff and log with revsets.
"""
from __future__ import absolute_import
from .i18n import _
from .pycompat import getattr
from . import (
changelog,
cmdutil,
encoding,
error,
filelog,
localrepo,
manifest,
mdiff,
pathutil,
revlog,
util,
vfs as vfsmod,
)
class unionrevlog(revlog.revlog):
def __init__(self, opener, indexfile, revlog2, linkmapper):
# How it works:
# To retrieve a revision, we just need to know the node id so we can
# look it up in revlog2.
#
# To differentiate a rev in the second revlog from a rev in the revlog,
# we check revision against repotiprev.
opener = vfsmod.readonlyvfs(opener)
revlog.revlog.__init__(self, opener, indexfile)
self.revlog2 = revlog2
n = len(self)
self.repotiprev = n - 1
self.bundlerevs = set() # used by 'bundle()' revset expression
for rev2 in self.revlog2:
rev = self.revlog2.index[rev2]
# rev numbers - in revlog2, very different from self.rev
_start, _csize, rsize, base, linkrev, p1rev, p2rev, node = rev
flags = _start & 0xFFFF
if linkmapper is None: # link is to same revlog
assert linkrev == rev2 # we never link back
link = n
else: # rev must be mapped from repo2 cl to unified cl by linkmapper
link = linkmapper(linkrev)
if linkmapper is not None: # link is to same revlog
base = linkmapper(base)
this_rev = self.index.get_rev(node)
if this_rev is not None:
# this happens for the common revlog revisions
self.bundlerevs.add(this_rev)
continue
p1node = self.revlog2.node(p1rev)
p2node = self.revlog2.node(p2rev)
# TODO: it's probably wrong to set compressed length to None, but
# I have no idea if csize is valid in the base revlog context.
e = (
flags,
None,
rsize,
base,
link,
self.rev(p1node),
self.rev(p2node),
node,
)
self.index.append(e)
self.bundlerevs.add(n)
n += 1
def _chunk(self, rev):
if rev <= self.repotiprev:
return revlog.revlog._chunk(self, rev)
return self.revlog2._chunk(self.node(rev))
def revdiff(self, rev1, rev2):
"""return or calculate a delta between two revisions"""
if rev1 > self.repotiprev and rev2 > self.repotiprev:
return self.revlog2.revdiff(
self.revlog2.rev(self.node(rev1)),
self.revlog2.rev(self.node(rev2)),
)
elif rev1 <= self.repotiprev and rev2 <= self.repotiprev:
return super(unionrevlog, self).revdiff(rev1, rev2)
return mdiff.textdiff(self.rawdata(rev1), self.rawdata(rev2))
def _revisiondata(self, nodeorrev, _df=None, raw=False):
if isinstance(nodeorrev, int):
rev = nodeorrev
node = self.node(rev)
else:
node = nodeorrev
rev = self.rev(node)
if rev > self.repotiprev:
# work around manifestrevlog NOT being a revlog
revlog2 = getattr(self.revlog2, '_revlog', self.revlog2)
func = revlog2._revisiondata
else:
func = super(unionrevlog, self)._revisiondata
return func(node, _df=_df, raw=raw)
def addrevision(self, text, transaction, link, p1=None, p2=None, d=None):
raise NotImplementedError
def addgroup(
self,
deltas,
linkmapper,
transaction,
addrevisioncb=None,
maybemissingparents=False,
):
raise NotImplementedError
def strip(self, minlink, transaction):
raise NotImplementedError
def checksize(self):
raise NotImplementedError
class unionchangelog(unionrevlog, changelog.changelog):
def __init__(self, opener, opener2):
changelog.changelog.__init__(self, opener)
linkmapper = None
changelog2 = changelog.changelog(opener2)
unionrevlog.__init__(
self, opener, self.indexfile, changelog2, linkmapper
)
class unionmanifest(unionrevlog, manifest.manifestrevlog):
def __init__(self, opener, opener2, linkmapper):
manifest.manifestrevlog.__init__(self, opener)
manifest2 = manifest.manifestrevlog(opener2)
unionrevlog.__init__(
self, opener, self.indexfile, manifest2, linkmapper
)
class unionfilelog(filelog.filelog):
def __init__(self, opener, path, opener2, linkmapper, repo):
filelog.filelog.__init__(self, opener, path)
filelog2 = filelog.filelog(opener2, path)
self._revlog = unionrevlog(
opener, self.indexfile, filelog2._revlog, linkmapper
)
self._repo = repo
self.repotiprev = self._revlog.repotiprev
self.revlog2 = self._revlog.revlog2
def iscensored(self, rev):
"""Check if a revision is censored."""
if rev <= self.repotiprev:
return filelog.filelog.iscensored(self, rev)
node = self.node(rev)
return self.revlog2.iscensored(self.revlog2.rev(node))
class unionpeer(localrepo.localpeer):
def canpush(self):
return False
class unionrepository(object):
"""Represents the union of data in 2 repositories.
Instances are not usable if constructed directly. Use ``instance()``
or ``makeunionrepository()`` to create a usable instance.
"""
def __init__(self, repo2, url):
self.repo2 = repo2
self._url = url
self.ui.setconfig(b'phases', b'publish', False, b'unionrepo')
@localrepo.unfilteredpropertycache
def changelog(self):
return unionchangelog(self.svfs, self.repo2.svfs)
@localrepo.unfilteredpropertycache
def manifestlog(self):
rootstore = unionmanifest(
self.svfs, self.repo2.svfs, self.unfiltered()._clrev
)
return manifest.manifestlog(
self.svfs, self, rootstore, self.narrowmatch()
)
def _clrev(self, rev2):
"""map from repo2 changelog rev to temporary rev in self.changelog"""
node = self.repo2.changelog.node(rev2)
return self.changelog.rev(node)
def url(self):
return self._url
def file(self, f):
return unionfilelog(
self.svfs, f, self.repo2.svfs, self.unfiltered()._clrev, self
)
def close(self):
self.repo2.close()
def cancopy(self):
return False
def peer(self):
return unionpeer(self)
def getcwd(self):
return encoding.getcwd() # always outside the repo
def instance(ui, path, create, intents=None, createopts=None):
if create:
raise error.Abort(_(b'cannot create new union repository'))
parentpath = ui.config(b"bundle", b"mainreporoot")
if not parentpath:
# try to find the correct path to the working directory repo
parentpath = cmdutil.findrepo(encoding.getcwd())
if parentpath is None:
parentpath = b''
if parentpath:
# Try to make the full path relative so we get a nice, short URL.
# In particular, we don't want temp dir names in test outputs.
cwd = encoding.getcwd()
if parentpath == cwd:
parentpath = b''
else:
cwd = pathutil.normasprefix(cwd)
if parentpath.startswith(cwd):
parentpath = parentpath[len(cwd) :]
if path.startswith(b'union:'):
s = path.split(b":", 1)[1].split(b"+", 1)
if len(s) == 1:
repopath, repopath2 = parentpath, s[0]
else:
repopath, repopath2 = s
else:
repopath, repopath2 = parentpath, path
return makeunionrepository(ui, repopath, repopath2)
def makeunionrepository(ui, repopath1, repopath2):
"""Make a union repository object from 2 local repo paths."""
repo1 = localrepo.instance(ui, repopath1, create=False)
repo2 = localrepo.instance(ui, repopath2, create=False)
url = b'union:%s+%s' % (
util.expandpath(repopath1),
util.expandpath(repopath2),
)
class derivedunionrepository(unionrepository, repo1.__class__):
pass
repo = repo1
repo.__class__ = derivedunionrepository
unionrepository.__init__(repo1, repo2, url)
return repo