##// 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:

r40856:96be0eca default
r42546:dbd0fcca default
Show More
loggingutil.py
121 lines | 3.7 KiB | text/x-python | PythonLexer
# loggingutil.py - utility for logging events
#
# Copyright 2010 Nicolas Dumazet
# Copyright 2013 Facebook, Inc.
#
# 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 errno
from . import (
pycompat,
)
from .utils import (
dateutil,
procutil,
stringutil,
)
def openlogfile(ui, vfs, name, maxfiles=0, maxsize=0):
"""Open log file in append mode, with optional rotation
If maxsize > 0, the log file will be rotated up to maxfiles.
"""
def rotate(oldpath, newpath):
try:
vfs.unlink(newpath)
except OSError as err:
if err.errno != errno.ENOENT:
ui.debug("warning: cannot remove '%s': %s\n" %
(newpath, err.strerror))
try:
if newpath:
vfs.rename(oldpath, newpath)
except OSError as err:
if err.errno != errno.ENOENT:
ui.debug("warning: cannot rename '%s' to '%s': %s\n" %
(newpath, oldpath, err.strerror))
if maxsize > 0:
try:
st = vfs.stat(name)
except OSError:
pass
else:
if st.st_size >= maxsize:
path = vfs.join(name)
for i in pycompat.xrange(maxfiles - 1, 1, -1):
rotate(oldpath='%s.%d' % (path, i - 1),
newpath='%s.%d' % (path, i))
rotate(oldpath=path,
newpath=maxfiles > 0 and path + '.1')
return vfs(name, 'a', makeparentdirs=False)
def _formatlogline(msg):
date = dateutil.datestr(format=b'%Y/%m/%d %H:%M:%S')
pid = procutil.getpid()
return b'%s (%d)> %s' % (date, pid, msg)
def _matchevent(event, tracked):
return b'*' in tracked or event in tracked
class filelogger(object):
"""Basic logger backed by physical file with optional rotation"""
def __init__(self, vfs, name, tracked, maxfiles=0, maxsize=0):
self._vfs = vfs
self._name = name
self._trackedevents = set(tracked)
self._maxfiles = maxfiles
self._maxsize = maxsize
def tracked(self, event):
return _matchevent(event, self._trackedevents)
def log(self, ui, event, msg, opts):
line = _formatlogline(msg)
try:
with openlogfile(ui, self._vfs, self._name,
maxfiles=self._maxfiles,
maxsize=self._maxsize) as fp:
fp.write(line)
except IOError as err:
ui.debug(b'cannot write to %s: %s\n'
% (self._name, stringutil.forcebytestr(err)))
class fileobjectlogger(object):
"""Basic logger backed by file-like object"""
def __init__(self, fp, tracked):
self._fp = fp
self._trackedevents = set(tracked)
def tracked(self, event):
return _matchevent(event, self._trackedevents)
def log(self, ui, event, msg, opts):
line = _formatlogline(msg)
try:
self._fp.write(line)
self._fp.flush()
except IOError as err:
ui.debug(b'cannot write to %s: %s\n'
% (stringutil.forcebytestr(self._fp.name),
stringutil.forcebytestr(err)))
class proxylogger(object):
"""Forward log events to another logger to be set later"""
def __init__(self):
self.logger = None
def tracked(self, event):
return self.logger is not None and self.logger.tracked(event)
def log(self, ui, event, msg, opts):
assert self.logger is not None
self.logger.log(ui, event, msg, opts)