bundle2: implement generic part payload decoder
The previous commit extracted _payloadchunks() to a new derived class.
There was still a reference to this method in unbundlepart, making
unbundlepart unusable on its own.
This commit implements a generic version of a bundle2 part payload
decoder, without offset tracking. seekableunbundlepart._payloadchunks()
has been refactored to consume it, adding offset tracking like before.
We also implement unbundlepart._payloadchunks(), which is a thin
wrapper for it. Since we never instantiate unbundlepart directly,
this new method is not used. This will be changed in subsequent
commits.
The new implementation also inlines some simple code from unpackermixin
and adds some local variable to prevent extra function calls and
attribute lookups. `hg perfbundleread` on an uncompressed Firefox
bundle seems to show a minor win:
! bundle2 iterparts()
! wall 12.593258 comb 12.250000 user 8.870000 sys 3.380000 (best of 3)
! wall 10.891305 comb 10.820000 user 7.990000 sys 2.830000 (best of 3)
! bundle2 part seek()
! wall 13.173163 comb 11.100000 user 8.390000 sys 2.710000 (best of 3)
! wall 12.991478 comb 10.390000 user 7.720000 sys 2.670000 (best of 3)
! bundle2 part read(8k)
! wall 9.483612 comb 9.480000 user 8.420000 sys 1.060000 (best of 3)
! wall 8.599892 comb 8.580000 user 7.720000 sys 0.860000 (best of 3)
! bundle2 part read(16k)
! wall 9.159815 comb 9.150000 user 8.220000 sys 0.930000 (best of 3)
! wall 8.265361 comb 8.250000 user 7.360000 sys 0.890000 (best of 3)
! bundle2 part read(32k)
! wall 9.141308 comb 9.130000 user 8.220000 sys 0.910000 (best of 3)
! wall 8.290308 comb 8.280000 user 7.330000 sys 0.950000 (best of 3)
! bundle2 part read(128k)
! wall 8.880587 comb 8.850000 user 7.960000 sys 0.890000 (best of 3)
! wall 8.204900 comb 8.150000 user 7.210000 sys 0.940000 (best of 3)
Function call overhead in Python strikes again!
Of course, bundle2 decoding CPU overhead is likely small compared to
decompression and changegroup application. But every little bit helps.
Differential Revision: https://phab.mercurial-scm.org/D1387
# 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,
)
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 error.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