##// 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
repocache.py
140 lines | 4.5 KiB | text/x-python | PythonLexer
# repocache.py - in-memory repository cache for long-running services
#
# Copyright 2018 Yuya Nishihara <yuya@tcha.org>
#
# 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
import gc
import threading
from . import (
error,
hg,
obsolete,
scmutil,
util,
)
class repoloader:
"""Load repositories in background thread
This is designed for a forking server. A cached repo cannot be obtained
until the server fork()s a worker and the loader thread stops.
"""
def __init__(self, ui, maxlen):
self._ui = ui.copy()
self._cache = util.lrucachedict(max=maxlen)
# use deque and Event instead of Queue since deque can discard
# old items to keep at most maxlen items.
self._inqueue = collections.deque(maxlen=maxlen)
self._accepting = False
self._newentry = threading.Event()
self._thread = None
def start(self):
assert not self._thread
if self._inqueue.maxlen == 0:
# no need to spawn loader thread as the cache is disabled
return
self._accepting = True
self._thread = threading.Thread(target=self._mainloop)
self._thread.start()
def stop(self):
if not self._thread:
return
self._accepting = False
self._newentry.set()
self._thread.join()
self._thread = None
self._cache.clear()
self._inqueue.clear()
def load(self, path):
"""Request to load the specified repository in background"""
self._inqueue.append(path)
self._newentry.set()
def get(self, path):
"""Return a cached repo if available
This function must be called after fork(), where the loader thread
is stopped. Otherwise, the returned repo might be updated by the
loader thread.
"""
if self._thread and self._thread.is_alive():
raise error.ProgrammingError(
b'cannot obtain cached repo while loader is active'
)
return self._cache.peek(path, None)
def _mainloop(self):
while self._accepting:
# Avoid heavy GC after fork(), which would cancel the benefit of
# COW. We assume that GIL is acquired while GC is underway in the
# loader thread. If that isn't true, we might have to move
# gc.collect() to the main thread so that fork() would never stop
# the thread where GC is in progress.
gc.collect()
self._newentry.wait()
while self._accepting:
self._newentry.clear()
try:
path = self._inqueue.popleft()
except IndexError:
break
scmutil.callcatch(self._ui, lambda: self._load(path))
def _load(self, path):
start = util.timer()
# TODO: repo should be recreated if storage configuration changed
try:
# pop before loading so inconsistent state wouldn't be exposed
repo = self._cache.pop(path)
except KeyError:
repo = hg.repository(self._ui, path).unfiltered()
_warmupcache(repo)
repo.ui.log(
b'repocache',
b'loaded repo into cache: %s (in %.3fs)\n',
path,
util.timer() - start,
)
self._cache.insert(path, repo)
# TODO: think about proper API of preloading cache
def _warmupcache(repo):
repo.invalidateall()
repo.changelog
repo.obsstore._all
repo.obsstore.successors
repo.obsstore.predecessors
repo.obsstore.children
for name in obsolete.cachefuncs:
obsolete.getrevs(repo, name)
# ensure the phase cache is fully initialized
repo._phasecache.phase(repo, repo.changelog.tiprev())
# TODO: think about proper API of attaching preloaded attributes
def copycache(srcrepo, destrepo):
"""Copy cached attributes from srcrepo to destrepo"""
destfilecache = destrepo._filecache
srcfilecache = srcrepo._filecache
if b'changelog' in srcfilecache:
destfilecache[b'changelog'] = ce = srcfilecache[b'changelog']
ce.obj.opener = ce.obj._inner.opener = destrepo.svfs
if b'obsstore' in srcfilecache:
destfilecache[b'obsstore'] = ce = srcfilecache[b'obsstore']
ce.obj.svfs = destrepo.svfs
if b'_phasecache' in srcfilecache:
destfilecache[b'_phasecache'] = ce = srcfilecache[b'_phasecache']
ce.obj.opener = destrepo.svfs