##// END OF EJS Templates
revlog: optionally cache the full text when adding revisions...
revlog: optionally cache the full text when adding revisions revlog instances can cache the full text of a single revision. Typically the most recently read revision is cached. When adding a delta group via addgroup() and _addrevision(), the full text isn't always computed: sometimes only the passed in delta is sufficient for adding a new revision to the revlog. When writing the changelog from a delta group, the just-added full text revision is always read immediately after it is written because the changegroup code needs to extract the set of files from the entry. In other words, revision() is *always* being called and caching the full text of the just-added revision is guaranteed to result in a cache hit, making the cache worthwhile. This patch adds support to _addrevision() for always building and caching the full text. This option is currently only active when processing changelog entries from a changegroup. While the total number of revision() calls is the same, the location matters: buildtext() calls into revision() on the base revision when building the full text of the just-added revision. Since the previous revision's _addrevision() built the full text and the the previous revision is likely the base revision, this means that the base revision's full text is likely cached and can be used to compute the current full text from just a delta. No extra I/O required. The end result is the changelog isn't opened and read after adding every revision from a changegroup. On my 2013 MacBook Pro running OS X 10.10.5 from an SSD and Python 2.7, this patch impacted the time taken to apply ~262,000 changesets from a mozilla-central gzip bundle: before: ~43s after: ~32s ~25% reduction in changelog processing times. Not bad.

File last commit:

r25987:c6d049a5 default
r26243:83629142 default
Show More
treediscovery.py
160 lines | 5.2 KiB | text/x-python | PythonLexer
# discovery.py - protocol changeset discovery functions
#
# Copyright 2010 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 collections
from .i18n import _
from .node import (
nullid,
short,
)
from . import (
error,
util,
)
def findcommonincoming(repo, remote, heads=None, force=False):
"""Return a tuple (common, fetch, heads) used to identify the common
subset of nodes between repo and remote.
"common" is a list of (at least) the heads of the common subset.
"fetch" is a list of roots of the nodes that would be incoming, to be
supplied to changegroupsubset.
"heads" is either the supplied heads, or else the remote's heads.
"""
knownnode = repo.changelog.hasnode
search = []
fetch = set()
seen = set()
seenbranch = set()
base = set()
if not heads:
heads = remote.heads()
if repo.changelog.tip() == nullid:
base.add(nullid)
if heads != [nullid]:
return [nullid], [nullid], list(heads)
return [nullid], [], heads
# assume we're closer to the tip than the root
# and start by examining the heads
repo.ui.status(_("searching for changes\n"))
unknown = []
for h in heads:
if not knownnode(h):
unknown.append(h)
else:
base.add(h)
if not unknown:
return list(base), [], list(heads)
req = set(unknown)
reqcnt = 0
# search through remote branches
# a 'branch' here is a linear segment of history, with four parts:
# head, root, first parent, second parent
# (a branch always has two parents (or none) by definition)
unknown = collections.deque(remote.branches(unknown))
while unknown:
r = []
while unknown:
n = unknown.popleft()
if n[0] in seen:
continue
repo.ui.debug("examining %s:%s\n"
% (short(n[0]), short(n[1])))
if n[0] == nullid: # found the end of the branch
pass
elif n in seenbranch:
repo.ui.debug("branch already found\n")
continue
elif n[1] and knownnode(n[1]): # do we know the base?
repo.ui.debug("found incomplete branch %s:%s\n"
% (short(n[0]), short(n[1])))
search.append(n[0:2]) # schedule branch range for scanning
seenbranch.add(n)
else:
if n[1] not in seen and n[1] not in fetch:
if knownnode(n[2]) and knownnode(n[3]):
repo.ui.debug("found new changeset %s\n" %
short(n[1]))
fetch.add(n[1]) # earliest unknown
for p in n[2:4]:
if knownnode(p):
base.add(p) # latest known
for p in n[2:4]:
if p not in req and not knownnode(p):
r.append(p)
req.add(p)
seen.add(n[0])
if r:
reqcnt += 1
repo.ui.progress(_('searching'), reqcnt, unit=_('queries'))
repo.ui.debug("request %d: %s\n" %
(reqcnt, " ".join(map(short, r))))
for p in xrange(0, len(r), 10):
for b in remote.branches(r[p:p + 10]):
repo.ui.debug("received %s:%s\n" %
(short(b[0]), short(b[1])))
unknown.append(b)
# do binary search on the branches we found
while search:
newsearch = []
reqcnt += 1
repo.ui.progress(_('searching'), reqcnt, unit=_('queries'))
for n, l in zip(search, remote.between(search)):
l.append(n[1])
p = n[0]
f = 1
for i in l:
repo.ui.debug("narrowing %d:%d %s\n" % (f, len(l), short(i)))
if knownnode(i):
if f <= 2:
repo.ui.debug("found new branch changeset %s\n" %
short(p))
fetch.add(p)
base.add(i)
else:
repo.ui.debug("narrowed branch search to %s:%s\n"
% (short(p), short(i)))
newsearch.append((p, i))
break
p, f = i, f * 2
search = newsearch
# sanity check our fetch list
for f in fetch:
if knownnode(f):
raise error.RepoError(_("already have changeset ")
+ short(f[:4]))
base = list(base)
if base == [nullid]:
if force:
repo.ui.warn(_("warning: repository is unrelated\n"))
else:
raise util.Abort(_("repository is unrelated"))
repo.ui.debug("found new changesets starting at " +
" ".join([short(f) for f in fetch]) + "\n")
repo.ui.progress(_('searching'), None)
repo.ui.debug("%d total queries\n" % reqcnt)
return base, list(fetch), heads