##// END OF EJS Templates
discovery: slowly increase sampling size...
discovery: slowly increase sampling size Some pathological discovery runs can requires many roundtrip. When this happens things can get very slow. To make the algorithm more resilience again such pathological case. We slowly increase the sample size with each roundtrip (+5%). This will have a negligible impact on "normal" discovery with few roundtrips, but a large positive impact of case with many roundtrips. Asking more question per roundtrip helps to reduce the undecided set faster. Instead of reducing the undecided set a linear speed (in the worst case), we reduce it as a guaranteed (small) exponential rate. The data below show this slow ramp up in sample size: round trip | 1 | 5 | 10 | 20 | 50 | 100 | 130 | sample size | 200 | 254 | 321 | 517 | 2 199 | 25 123 | 108 549 | covered nodes | 200 | 1 357 | 2 821 | 7 031 | 42 658 | 524 530 | 2 276 755 | To be a bit more concrete, lets take a very pathological case as an example. We are doing discovery from a copy of Mozilla-try to a more recent version of mozilla-unified. Mozilla-unified heads are unknown to the mozilla-try repo and there are over 1 million "missing" changesets. (the discovery is "local" to avoid network interference) Without this change, the discovery: - last 1858 seconds (31 minutes), - does 1700 round trip, - asking about 340 000 nodes. With this change, the discovery: - last 218 seconds (3 minutes, 38 seconds a -88% improvement), - does 94 round trip (-94%), - asking about 344 211 nodes (+1%). Of course, this is an extreme case (and 3 minutes is still slow). However this give a good example of how this sample size increase act as a safety net catching any bad situations. We could image a steeper increase than 5%. For example 10% would give the following number: round trip | 1 | 5 | 10 | 20 | 50 | 75 | 100 | sample size | 200 | 321 | 514 | 1 326 | 23 060 | 249 812 | 2 706 594 | covered nodes | 200 | 1 541 | 3 690 | 12 671 | 251 871 | 2 746 254 | 29 770 966 | In parallel, it is useful to understand these pathological cases and improve them. However the current change provides a general purpose safety net to smooth the impact of pathological cases. To avoid issue with older http server, the increase in sample size only occurs if the protocol has not limit on command argument size.

File last commit:

r40859:82210d88 default
r42546:dbd0fcca default
Show More
server.py
212 lines | 6.9 KiB | text/x-python | PythonLexer
# server.py - utility and factory of server
#
# Copyright 2005-2007 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 os
from .i18n import _
from . import (
chgserver,
cmdutil,
commandserver,
error,
hgweb,
pycompat,
util,
)
from .utils import (
procutil,
)
def runservice(opts, parentfn=None, initfn=None, runfn=None, logfile=None,
runargs=None, appendpid=False):
'''Run a command as a service.'''
postexecargs = {}
if opts['daemon_postexec']:
for inst in opts['daemon_postexec']:
if inst.startswith('unlink:'):
postexecargs['unlink'] = inst[7:]
elif inst.startswith('chdir:'):
postexecargs['chdir'] = inst[6:]
elif inst != 'none':
raise error.Abort(_('invalid value for --daemon-postexec: %s')
% inst)
# When daemonized on Windows, redirect stdout/stderr to the lockfile (which
# gets cleaned up after the child is up and running), so that the parent can
# read and print the error if this child dies early. See 594dd384803c. On
# other platforms, the child can write to the parent's stdio directly, until
# it is redirected prior to runfn().
if pycompat.iswindows and opts['daemon_postexec']:
if 'unlink' in postexecargs and os.path.exists(postexecargs['unlink']):
procutil.stdout.flush()
procutil.stderr.flush()
fd = os.open(postexecargs['unlink'],
os.O_WRONLY | os.O_APPEND | os.O_BINARY)
try:
os.dup2(fd, procutil.stdout.fileno())
os.dup2(fd, procutil.stderr.fileno())
finally:
os.close(fd)
def writepid(pid):
if opts['pid_file']:
if appendpid:
mode = 'ab'
else:
mode = 'wb'
fp = open(opts['pid_file'], mode)
fp.write('%d\n' % pid)
fp.close()
if opts['daemon'] and not opts['daemon_postexec']:
# Signal child process startup with file removal
lockfd, lockpath = pycompat.mkstemp(prefix='hg-service-')
os.close(lockfd)
try:
if not runargs:
runargs = procutil.hgcmd() + pycompat.sysargv[1:]
runargs.append('--daemon-postexec=unlink:%s' % lockpath)
# Don't pass --cwd to the child process, because we've already
# changed directory.
for i in pycompat.xrange(1, len(runargs)):
if runargs[i].startswith('--cwd='):
del runargs[i]
break
elif runargs[i].startswith('--cwd'):
del runargs[i:i + 2]
break
def condfn():
return not os.path.exists(lockpath)
pid = procutil.rundetached(runargs, condfn)
if pid < 0:
# If the daemonized process managed to write out an error msg,
# report it.
if pycompat.iswindows and os.path.exists(lockpath):
with open(lockpath, 'rb') as log:
for line in log:
procutil.stderr.write(line)
raise error.Abort(_('child process failed to start'))
writepid(pid)
finally:
util.tryunlink(lockpath)
if parentfn:
return parentfn(pid)
else:
return
if initfn:
initfn()
if not opts['daemon']:
writepid(procutil.getpid())
if opts['daemon_postexec']:
try:
os.setsid()
except AttributeError:
pass
if 'chdir' in postexecargs:
os.chdir(postexecargs['chdir'])
procutil.hidewindow()
procutil.stdout.flush()
procutil.stderr.flush()
nullfd = os.open(os.devnull, os.O_RDWR)
logfilefd = nullfd
if logfile:
logfilefd = os.open(logfile, os.O_RDWR | os.O_CREAT | os.O_APPEND,
0o666)
os.dup2(nullfd, procutil.stdin.fileno())
os.dup2(logfilefd, procutil.stdout.fileno())
os.dup2(logfilefd, procutil.stderr.fileno())
stdio = (procutil.stdin.fileno(), procutil.stdout.fileno(),
procutil.stderr.fileno())
if nullfd not in stdio:
os.close(nullfd)
if logfile and logfilefd not in stdio:
os.close(logfilefd)
# Only unlink after redirecting stdout/stderr, so Windows doesn't
# complain about a sharing violation.
if 'unlink' in postexecargs:
os.unlink(postexecargs['unlink'])
if runfn:
return runfn()
_cmdservicemap = {
'chgunix': chgserver.chgunixservice,
'pipe': commandserver.pipeservice,
'unix': commandserver.unixforkingservice,
}
def _createcmdservice(ui, repo, opts):
mode = opts['cmdserver']
try:
servicefn = _cmdservicemap[mode]
except KeyError:
raise error.Abort(_('unknown mode %s') % mode)
commandserver.setuplogging(ui, repo)
return servicefn(ui, repo, opts)
def _createhgwebservice(ui, repo, opts):
# this way we can check if something was given in the command-line
if opts.get('port'):
opts['port'] = util.getport(opts.get('port'))
alluis = {ui}
if repo:
baseui = repo.baseui
alluis.update([repo.baseui, repo.ui])
else:
baseui = ui
webconf = opts.get('web_conf') or opts.get('webdir_conf')
if webconf:
if opts.get('subrepos'):
raise error.Abort(_('--web-conf cannot be used with --subrepos'))
# load server settings (e.g. web.port) to "copied" ui, which allows
# hgwebdir to reload webconf cleanly
servui = ui.copy()
servui.readconfig(webconf, sections=['web'])
alluis.add(servui)
elif opts.get('subrepos'):
servui = ui
# If repo is None, hgweb.createapp() already raises a proper abort
# message as long as webconf is None.
if repo:
webconf = dict()
cmdutil.addwebdirpath(repo, "", webconf)
else:
servui = ui
optlist = ("name templates style address port prefix ipv6"
" accesslog errorlog certificate encoding")
for o in optlist.split():
val = opts.get(o, '')
if val in (None, ''): # should check against default options instead
continue
for u in alluis:
u.setconfig("web", o, val, 'serve')
app = hgweb.createapp(baseui, repo, webconf)
return hgweb.httpservice(servui, app, opts)
def createservice(ui, repo, opts):
if opts["cmdserver"]:
return _createcmdservice(ui, repo, opts)
else:
return _createhgwebservice(ui, repo, opts)