##// END OF EJS Templates
bisect: avoid adding irrelevant revisions to bisect state...
bisect: avoid adding irrelevant revisions to bisect state When adding new revisions to the bisect state, it only makes sense to add information about revisions that are under consideration (i.e., those that are topologically between the known good and bad revisions). However, if the user passes in a revset (e.g., '!merge()' to exclude merge commits), hg will resolve the revset first and add all matching revisions to the bisect state (which in this case would likely be the majority of revisions in the repo). To avoid this, revisions should only be added to the bisect state if they are between the good and bad revisions (and therefore relevant to the bisection). -- Here are the results of some performance tests using the `mozilla-central` repo (since it is one of the largest freely-available hg repositories in the wild). These tests compare the performance of a locally-built `hg` before and after application of this series. Note that `--noupdate` is passed to avoid including update time (which should not vary across cases). Setup (run between each test): $ hg bisect --reset $ hg bisect --noupdate --bad 56c3ad4bde5c70714b784ccf15d099e0df0f5bde $ hg bisect --noupdate --good 57426696adaf08298af3027fa77486fee0633b13 Test using a revset that returns a very large number of revisions: $ time hg bisect --noupdate --skip '!merge()' > /dev/null Before: real 0m9.398s user 0m9.233s sys 0m0.120s After: real 0m1.513s user 0m1.425s sys 0m0.052s Test using a revset that is expensive to compute: $ time hg bisect --noupdate --skip 'desc("Bug")' > /dev/null Before: real 0m49.853s user 0m49.580s sys 0m0.243s After: real 0m4.120s user 0m4.036s sys 0m0.048s

File last commit:

r49801:642e31cb default
r50337:81623652 default
Show More
repocache.py
138 lines | 4.4 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.
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)
repo._phasecache.loadphaserevs(repo)
# 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._realopener = 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