##// END OF EJS Templates
compression: introduce a `storage.revlog.zlib.level` configuration...
compression: introduce a `storage.revlog.zlib.level` configuration This option control the zlib compression level used when compression revlog chunk. This is also a good excuse to pave the way for a similar configuration option for the zstd compression engine. Having a dedicated option for each compression algorithm is useful because they don't support the same range of values. Using a higher zlib compression impact CPU consumption at compression time, but does not directly affected decompression time. However dealing with small compressed chunk can directly help decompression and indirectly help other revlog logic. I ran some basic test on repositories using different level. I am using the mercurial, pypy, netbeans and mozilla-central clone from our benchmark suite. All tested repository use sparse-revlog and got all their delta recomputed. The different compression level has a small effect on the repository size (about 10% variation in the total range). My quick analysis is that revlog mostly store small delta, that are not affected by the compression level much. So the variation probably mostly comes from better compression of the snapshots revisions, and snapshot revision only represent a small portion of the repository content. I also made some basic timings measurements. The "read" timings are gathered using simple run of `hg perfrevlogrevisions`, the "write" timings using `hg perfrevlogwrite` (restricted to the last 5000 revisions for netbeans and mozilla central). The timings are gathered on a generic machine, (not one of our performance locked machine), so small variation might not be meaningful. However large trend remains relevant. Keep in mind that these numbers are not pure compression/decompression time. They also involve the full revlog logic. In particular the difference in chunk size has an impact on the delta chain structure, affecting performance when writing or reading them. On read/write performance, the compression level has a bigger impact. Counter-intuitively, the higher compression levels improve "write" performance for the large repositories in our tested setting. Maybe because the last 5000 delta chain end up having a very different shape in this specific spot? Or maybe because of a more general trend of better delta chains thanks to the smaller chunk and snapshot. This series does not intend to change the default compression level. However, these result call for a deeper analysis of this performance difference in the future. Full data ========= repo level .hg/store size 00manifest.d read write ---------------------------------------------------------------- mercurial 1 49,402,813 5,963,475 0.170159 53.250304 mercurial 6 47,197,397 5,875,730 0.182820 56.264320 mercurial 9 47,121,596 5,849,781 0.189219 56.293612 pypy 1 370,830,572 28,462,425 2.679217 460.721984 pypy 6 340,112,317 27,648,747 2.768691 467.537158 pypy 9 338,360,736 27,639,003 2.763495 476.589918 netbeans 1 1,281,847,810 165,495,457 122.477027 520.560316 netbeans 6 1,205,284,353 159,161,207 139.876147 715.930400 netbeans 9 1,197,135,671 155,034,586 141.620281 678.297064 mozilla 1 2,775,497,186 298,527,987 147.867662 751.263721 mozilla 6 2,596,856,420 286,597,671 170.572118 987.056093 mozilla 9 2,587,542,494 287,018,264 163.622338 739.803002

File last commit:

r41673:bd3f03d8 default
r42210:1fac9b93 default
Show More
blackbox.py
197 lines | 5.7 KiB | text/x-python | PythonLexer
# blackbox.py - log repository events to a file for post-mortem debugging
#
# 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.
"""log repository events to a blackbox for debugging
Logs event information to .hg/blackbox.log to help debug and diagnose problems.
The events that get logged can be configured via the blackbox.track config key.
Examples::
[blackbox]
track = *
# dirty is *EXPENSIVE* (slow);
# each log entry indicates `+` if the repository is dirty, like :hg:`id`.
dirty = True
# record the source of log messages
logsource = True
[blackbox]
track = command, commandfinish, commandexception, exthook, pythonhook
[blackbox]
track = incoming
[blackbox]
# limit the size of a log file
maxsize = 1.5 MB
# rotate up to N log files when the current one gets too big
maxfiles = 3
[blackbox]
# Include nanoseconds in log entries with %f (see Python function
# datetime.datetime.strftime)
date-format = '%Y-%m-%d @ %H:%M:%S.%f'
"""
from __future__ import absolute_import
import re
from mercurial.i18n import _
from mercurial.node import hex
from mercurial import (
encoding,
loggingutil,
registrar,
)
from mercurial.utils import (
dateutil,
procutil,
)
# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
# extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
# be specifying the version(s) of Mercurial they are tested with, or
# leave the attribute unspecified.
testedwith = 'ships-with-hg-core'
cmdtable = {}
command = registrar.command(cmdtable)
configtable = {}
configitem = registrar.configitem(configtable)
configitem('blackbox', 'dirty',
default=False,
)
configitem('blackbox', 'maxsize',
default='1 MB',
)
configitem('blackbox', 'logsource',
default=False,
)
configitem('blackbox', 'maxfiles',
default=7,
)
configitem('blackbox', 'track',
default=lambda: ['*'],
)
configitem('blackbox', 'date-format',
default='%Y/%m/%d %H:%M:%S',
)
_lastlogger = loggingutil.proxylogger()
class blackboxlogger(object):
def __init__(self, ui, repo):
self._repo = repo
self._trackedevents = set(ui.configlist('blackbox', 'track'))
self._maxfiles = ui.configint('blackbox', 'maxfiles')
self._maxsize = ui.configbytes('blackbox', 'maxsize')
self._inlog = False
def tracked(self, event):
return b'*' in self._trackedevents or event in self._trackedevents
def log(self, ui, event, msg, opts):
# self._log() -> ctx.dirty() may create new subrepo instance, which
# ui is derived from baseui. So the recursion guard in ui.log()
# doesn't work as it's local to the ui instance.
if self._inlog:
return
self._inlog = True
try:
self._log(ui, event, msg, opts)
finally:
self._inlog = False
def _log(self, ui, event, msg, opts):
default = ui.configdate('devel', 'default-date')
date = dateutil.datestr(default, ui.config('blackbox', 'date-format'))
user = procutil.getuser()
pid = '%d' % procutil.getpid()
changed = ''
ctx = self._repo[None]
parents = ctx.parents()
rev = ('+'.join([hex(p.node()) for p in parents]))
if (ui.configbool('blackbox', 'dirty') and
ctx.dirty(missing=True, merge=False, branch=False)):
changed = '+'
if ui.configbool('blackbox', 'logsource'):
src = ' [%s]' % event
else:
src = ''
try:
fmt = '%s %s @%s%s (%s)%s> %s'
args = (date, user, rev, changed, pid, src, msg)
with loggingutil.openlogfile(
ui, self._repo.vfs, name='blackbox.log',
maxfiles=self._maxfiles, maxsize=self._maxsize) as fp:
fp.write(fmt % args)
except (IOError, OSError) as err:
# deactivate this to avoid failed logging again
self._trackedevents.clear()
ui.debug('warning: cannot write to blackbox.log: %s\n' %
encoding.strtolocal(err.strerror))
return
_lastlogger.logger = self
def uipopulate(ui):
ui.setlogger(b'blackbox', _lastlogger)
def reposetup(ui, repo):
# During 'hg pull' a httppeer repo is created to represent the remote repo.
# It doesn't have a .hg directory to put a blackbox in, so we don't do
# the blackbox setup for it.
if not repo.local():
return
# Since blackbox.log is stored in the repo directory, the logger should be
# instantiated per repository.
logger = blackboxlogger(ui, repo)
ui.setlogger(b'blackbox', logger)
# Set _lastlogger even if ui.log is not called. This gives blackbox a
# fallback place to log
if _lastlogger.logger is None:
_lastlogger.logger = logger
repo._wlockfreeprefix.add('blackbox.log')
@command('blackbox',
[('l', 'limit', 10, _('the number of events to show')),
],
_('hg blackbox [OPTION]...'),
helpcategory=command.CATEGORY_MAINTENANCE,
helpbasic=True)
def blackbox(ui, repo, *revs, **opts):
'''view the recent repository events
'''
if not repo.vfs.exists('blackbox.log'):
return
limit = opts.get(r'limit')
fp = repo.vfs('blackbox.log', 'r')
lines = fp.read().split('\n')
count = 0
output = []
for line in reversed(lines):
if count >= limit:
break
# count the commands by matching lines like: 2013/01/23 19:13:36 root>
if re.match(br'^\d{4}/\d{2}/\d{2} \d{2}:\d{2}:\d{2} .*> .*', line):
count += 1
output.append(line)
ui.status('\n'.join(reversed(output)))