##// END OF EJS Templates
branchmap-v3: filter topo heads using node for performance reason...
branchmap-v3: filter topo heads using node for performance reason The branchmap currently contains heads as nodeid. If we build a set of revnum with the topological heads, we need to turn the nodeid in the branchmap to revnum to be able to check if they are topo-heads. That nodeid → revnum lookup is "expensive" and adds up to something noticeable if you do it hundreds of thousand of time. Instead we turn all the topo-heads revnums into nodes and build a set. So we can directly test membership of the nodeids stored in the branchmap. That is much faster. Ideally we would have revnum in the branchmap and could directly test revnum against a revnum set and that would be even faster. However that's an adventure for another time. Without this change, the branchmap format "v3" was significantly slower than the "v2" format. With this changes, some of that gap is recovered With rust + persistent nodemap, this overhead was smaller because the extra lookup did not had to to build the nodemap from scratch. In addition the mozilla-unified repository is able to use the "pure_top" mode of branchmap v3, so it was not really affected by this. Future changeset will work of the remaining of the performance gap. ### benchmark.name = hg.command.unbundle # bin-env-vars.hg.py-re2-module = default # benchmark.variants.issue6528 = disabled # benchmark.variants.resource-usage = default # benchmark.variants.reuse-external-delta-parent = yes # benchmark.variants.revs = any-1-extra-rev # benchmark.variants.source = unbundle # benchmark.variants.validate = default # benchmark.variants.verbosity = quiet ## data-env-vars.name = netbeans-2018-08-01-zstd-sparse-revlog # bin-env-vars.hg.flavor = default branch-v2: 0.233711 ~~~~~ branch-v3 before: 0.380994 (+63.02%, +0.15) branch-v3 after: 0.368769 (+57.79%, +0.14) # bin-env-vars.hg.flavor = rust branch-v2: 0.235230 ~~~~~ branch-v3 before: 0.385060 (+63.70%, +0.15) branch-v3 after: 0.372460 (+58.34%, +0.14) ## data-env-vars.name = netbeans-2018-08-01-ds2-pnm # bin-env-vars.hg.flavor = rust branch-v2: 0.255586 ~~~~~ branch-v3 before: 0.317524 (+24.23%, +0.06) branch-v3 after: 0.318907 (+24.78%, +0.06) ## data-env-vars.name = mozilla-central-2024-03-22-zstd-sparse-revlog # bin-env-vars.hg.flavor = default branch-v2: 0.339010 ~~~~~ branch-v3 before: 0.410007 (+20.94%, +0.07) branch-v3 after: 0.349752 (+3.17%, +0.01) # bin-env-vars.hg.flavor = rust branch-v2: 0.346525 ~~~~~ branch-v3 before: 0.410428 (+18.44%, +0.06) branch-v3 after: 0.354300 (+2.24%, +0.01) ## data-env-vars.name = mozilla-central-2024-03-22-ds2-pnm # bin-env-vars.hg.flavor = rust branch-v2: 0.380202 ~~~~~ branch-v3 before: 0.393871 (+3.60%, +0.01) branch-v3 after: 0.396293 (+4.23%, +0.02) ## data-env-vars.name = mozilla-unified-2024-03-22-zstd-sparse-revlog # bin-env-vars.hg.flavor = default branch-v2: 0.412165 ~~~~~ branch-v3 before: 0.438105 (+6.29%, +0.03) branch-v3 after: 0.424769 (+3.06%, +0.01) # bin-env-vars.hg.flavor = rust branch-v2: 0.412397 ~~~~~ branch-v3 before: 0.438405 (+6.31%, +0.03) branch-v3 after: 0.421796 (+2.28%, +0.01) ## data-env-vars.name = mozilla-unified-2024-03-22-ds2-pnm # bin-env-vars.hg.flavor = rust branch-v2: 0.429501 ~~~~~ branch-v3 before: 0.452692 (+5.40%, +0.02) branch-v3 after: 0.443849 (+3.34%, +0.01) ## data-env-vars.name = mozilla-try-2024-03-26-zstd-sparse-revlog # bin-env-vars.hg.flavor = default branch-v2: 3.403171 ~~~~~ branch-v3 before: 6.562345 (+92.83%, +3.16) branch-v3 after: 6.234055 (+83.18%, +2.83) # bin-env-vars.hg.flavor = rust branch-v2: 3.454876 ~~~~~ branch-v3 before: 6.160248 (+78.31%, +2.71) branch-v3 after: 6.307813 (+82.58%, +2.85) ## data-env-vars.name = mozilla-try-2024-03-26-ds2-pnm # bin-env-vars.hg.flavor = rust branch-v2: 3.465435 ~~~~~ branch-v3 before: 5.381648 (+55.30%, +1.92) branch-v3 after: 5.176076 (+49.36%, +1.71)

File last commit:

r52756:f4733654 default
r52869:41b8892a default
Show More
treediscovery.py
207 lines | 7.0 KiB | text/x-python | PythonLexer
# discovery.py - protocol changeset discovery functions
#
# Copyright 2010 Olivia Mackall <olivia@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 annotations
import collections
from .i18n import _
from .node import short
from . import (
error,
)
def findcommonincoming(repo, remote, heads=None, force=False, audit=None):
"""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:
with remote.commandexecutor() as e:
heads = e.callcommand(b'heads', {}).result()
if audit is not None:
audit[b'total-roundtrips'] = 1
audit[b'total-roundtrips-heads'] = 1
audit[b'total-roundtrips-branches'] = 0
audit[b'total-roundtrips-between'] = 0
audit[b'total-queries'] = 0
audit[b'total-queries-branches'] = 0
audit[b'total-queries-between'] = 0
if repo.changelog.tip() == repo.nullid:
base.add(repo.nullid)
if heads != [repo.nullid]:
return [repo.nullid], [repo.nullid], list(heads)
return [repo.nullid], [], heads
# assume we're closer to the tip than the root
# and start by examining the heads
repo.ui.status(_(b"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
progress = repo.ui.makeprogress(_(b'searching'), unit=_(b'queries'))
# 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)
with remote.commandexecutor() as e:
if audit is not None:
audit[b'total-queries'] += len(unknown)
audit[b'total-queries-branches'] += len(unknown)
audit[b'total-roundtrips'] += 1
audit[b'total-roundtrips-branches'] += 1
branches = e.callcommand(b'branches', {b'nodes': unknown}).result()
unknown = collections.deque(branches)
while unknown:
r = []
while unknown:
n = unknown.popleft()
if n[0] in seen:
continue
repo.ui.debug(b"examining %s:%s\n" % (short(n[0]), short(n[1])))
if n[0] == repo.nullid: # found the end of the branch
pass
elif n in seenbranch:
repo.ui.debug(b"branch already found\n")
continue
elif n[1] and knownnode(n[1]): # do we know the base?
repo.ui.debug(
b"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(b"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:
for p in range(0, len(r), 10):
reqcnt += 1
progress.increment()
if repo.ui.debugflag:
msg = b"request %d: %s\n"
msg %= (reqcnt, b" ".join(map(short, r)))
repo.ui.debug(msg)
with remote.commandexecutor() as e:
subset = r[p : p + 10]
if audit is not None:
audit[b'total-queries'] += len(subset)
audit[b'total-queries-branches'] += len(subset)
audit[b'total-roundtrips'] += 1
audit[b'total-roundtrips-branches'] += 1
branches = e.callcommand(
b'branches',
{
b'nodes': subset,
},
).result()
for b in branches:
repo.ui.debug(
b"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
progress.increment()
with remote.commandexecutor() as e:
if audit is not None:
audit[b'total-queries'] += len(search)
audit[b'total-queries-between'] += len(search)
audit[b'total-roundtrips'] += 1
audit[b'total-roundtrips-between'] += 1
between = e.callcommand(b'between', {b'pairs': search}).result()
for n, l in zip(search, between):
l.append(n[1])
p = n[0]
f = 1
for i in l:
repo.ui.debug(b"narrowing %d:%d %s\n" % (f, len(l), short(i)))
if knownnode(i):
if f <= 2:
repo.ui.debug(
b"found new branch changeset %s\n" % short(p)
)
fetch.add(p)
base.add(i)
else:
repo.ui.debug(
b"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(_(b"already have changeset ") + short(f[:4]))
base = list(base)
if base == [repo.nullid]:
if force:
repo.ui.warn(_(b"warning: repository is unrelated\n"))
else:
raise error.Abort(_(b"repository is unrelated"))
repo.ui.debug(
b"found new changesets starting at "
+ b" ".join([short(f) for f in fetch])
+ b"\n"
)
progress.complete()
repo.ui.debug(b"%d total queries\n" % reqcnt)
return base, list(fetch), heads