##// END OF EJS Templates
xdiff: add a preprocessing step that trims files...
xdiff: add a preprocessing step that trims files xdiff has a `xdl_trim_ends` step that removes common lines, unmatchable lines. That is in theory good, but happens too late - after splitting, hashing, and adjusting the hash values so they are unique. Those splitting, hashing and adjusting hash values steps could have noticeable overhead. Diffing two large files with minor (one-line-ish) changes are not uncommon. In that case, the raw performance of those preparation steps seriously matter. Even allocating an O(N) array and storing line offsets to it is expensive. Therefore my previous attempts [1] [2] cannot be good enough since they do not remove the O(N) array assignment. This patch adds a preprocessing step - `xdl_trim_files` that runs before other preprocessing steps. It counts common prefix and suffix and lines in them (needed for displaying line number), without doing anything else. Testing with a crafted large (169MB) file, with minor change: ``` open('a','w').write(''.join('%s\n' % (i % 100000) for i in xrange(30000000) if i != 6000000)) open('b','w').write(''.join('%s\n' % (i % 100000) for i in xrange(30000000) if i != 6003000)) ``` Running xdiff by a simple binary [3], this patch improves the xdiff perf by more than 10x for the above case: ``` # xdiff before this patch 2.41s user 1.13s system 98% cpu 3.592 total # xdiff after this patch 0.14s user 0.16s system 98% cpu 0.309 total # gnu diffutils 0.12s user 0.15s system 98% cpu 0.272 total # (best of 20 runs) ``` It's still slightly slower than GNU diffutils. But it's pretty close now. Testing with real repo data: For the whole repo, this patch makes xdiff 25% faster: ``` # hg perfbdiff --count 100 --alldata -c d334afc585e2 --blocks [--xdiff] # xdiff, after ! wall 0.058861 comb 0.050000 user 0.050000 sys 0.000000 (best of 100) # xdiff, before ! wall 0.077816 comb 0.080000 user 0.080000 sys 0.000000 (best of 91) # bdiff ! wall 0.117473 comb 0.120000 user 0.120000 sys 0.000000 (best of 67) ``` For files that are long (ex. commands.py), the speedup is more than 3x, very significant: ``` # hg perfbdiff --count 3000 --blocks commands.py.i 1 [--xdiff] # xdiff, after ! wall 0.690583 comb 0.690000 user 0.690000 sys 0.000000 (best of 12) # xdiff, before ! wall 2.240361 comb 2.210000 user 2.210000 sys 0.000000 (best of 4) # bdiff ! wall 2.469852 comb 2.440000 user 2.440000 sys 0.000000 (best of 4) ``` [1]: https://phab.mercurial-scm.org/D2631 [2]: https://phab.mercurial-scm.org/D2634 [3]: ``` // Code to run xdiff from command line. No proper error handling. #include <stdlib.h> #include <unistd.h> #include <sys/types.h> #include <sys/stat.h> #include <fcntl.h> #include "mercurial/thirdparty/xdiff/xdiff.h" #define ensure(x) if (!(x)) exit(255); mmfile_t readfile(const char *path) { struct stat st; int fd = open(path, O_RDONLY); fstat(fd, &st); mmfile_t file = { malloc(st.st_size), st.st_size }; ensure(read(fd, file.ptr, st.st_size) == st.st_size); close(fd); return file; } int main(int argc, char const *argv[]) { mmfile_t a = readfile(argv[1]), b = readfile(argv[2]); xpparam_t xpp = {0}; xdemitconf_t xecfg = {0}; xdemitcb_t ecb = {0}; xdl_diff(&a, &b, &xpp, &xecfg, &ecb); return 0; } ``` Differential Revision: https://phab.mercurial-scm.org/D2686

File last commit:

r36701:e39953fd default
r36838:f33a87cf default
Show More
profiling.py
250 lines | 7.9 KiB | text/x-python | PythonLexer
# profiling.py - profiling functions
#
# Copyright 2016 Gregory Szorc <gregory.szorc@gmail.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, print_function
import contextlib
from .i18n import _
from . import (
encoding,
error,
extensions,
pycompat,
util,
)
def _loadprofiler(ui, profiler):
"""load profiler extension. return profile method, or None on failure"""
extname = profiler
extensions.loadall(ui, whitelist=[extname])
try:
mod = extensions.find(extname)
except KeyError:
return None
else:
return getattr(mod, 'profile', None)
@contextlib.contextmanager
def lsprofile(ui, fp):
format = ui.config('profiling', 'format')
field = ui.config('profiling', 'sort')
limit = ui.configint('profiling', 'limit')
climit = ui.configint('profiling', 'nested')
if format not in ['text', 'kcachegrind']:
ui.warn(_("unrecognized profiling format '%s'"
" - Ignored\n") % format)
format = 'text'
try:
from . import lsprof
except ImportError:
raise error.Abort(_(
'lsprof not available - install from '
'http://codespeak.net/svn/user/arigo/hack/misc/lsprof/'))
p = lsprof.Profiler()
p.enable(subcalls=True)
try:
yield
finally:
p.disable()
if format == 'kcachegrind':
from . import lsprofcalltree
calltree = lsprofcalltree.KCacheGrind(p)
calltree.output(fp)
else:
# format == 'text'
stats = lsprof.Stats(p.getstats())
stats.sort(field)
stats.pprint(limit=limit, file=fp, climit=climit)
@contextlib.contextmanager
def flameprofile(ui, fp):
try:
from flamegraph import flamegraph
except ImportError:
raise error.Abort(_(
'flamegraph not available - install from '
'https://github.com/evanhempel/python-flamegraph'))
# developer config: profiling.freq
freq = ui.configint('profiling', 'freq')
filter_ = None
collapse_recursion = True
thread = flamegraph.ProfileThread(fp, 1.0 / freq,
filter_, collapse_recursion)
start_time = util.timer()
try:
thread.start()
yield
finally:
thread.stop()
thread.join()
print('Collected %d stack frames (%d unique) in %2.2f seconds.' % (
util.timer() - start_time, thread.num_frames(),
thread.num_frames(unique=True)))
@contextlib.contextmanager
def statprofile(ui, fp):
from . import statprof
freq = ui.configint('profiling', 'freq')
if freq > 0:
# Cannot reset when profiler is already active. So silently no-op.
if statprof.state.profile_level == 0:
statprof.reset(freq)
else:
ui.warn(_("invalid sampling frequency '%s' - ignoring\n") % freq)
statprof.start(mechanism='thread')
try:
yield
finally:
data = statprof.stop()
profformat = ui.config('profiling', 'statformat')
formats = {
'byline': statprof.DisplayFormats.ByLine,
'bymethod': statprof.DisplayFormats.ByMethod,
'hotpath': statprof.DisplayFormats.Hotpath,
'json': statprof.DisplayFormats.Json,
'chrome': statprof.DisplayFormats.Chrome,
}
if profformat in formats:
displayformat = formats[profformat]
else:
ui.warn(_('unknown profiler output format: %s\n') % profformat)
displayformat = statprof.DisplayFormats.Hotpath
kwargs = {}
def fraction(s):
if isinstance(s, (float, int)):
return float(s)
if s.endswith('%'):
v = float(s[:-1]) / 100
else:
v = float(s)
if 0 <= v <= 1:
return v
raise ValueError(s)
if profformat == 'chrome':
showmin = ui.configwith(fraction, 'profiling', 'showmin', 0.005)
showmax = ui.configwith(fraction, 'profiling', 'showmax')
kwargs.update(minthreshold=showmin, maxthreshold=showmax)
elif profformat == 'hotpath':
# inconsistent config: profiling.showmin
limit = ui.configwith(fraction, 'profiling', 'showmin', 0.05)
kwargs[r'limit'] = limit
statprof.display(fp, data=data, format=displayformat, **kwargs)
class profile(object):
"""Start profiling.
Profiling is active when the context manager is active. When the context
manager exits, profiling results will be written to the configured output.
"""
def __init__(self, ui, enabled=True):
self._ui = ui
self._output = None
self._fp = None
self._fpdoclose = True
self._profiler = None
self._enabled = enabled
self._entered = False
self._started = False
def __enter__(self):
self._entered = True
if self._enabled:
self.start()
return self
def start(self):
"""Start profiling.
The profiling will stop at the context exit.
If the profiler was already started, this has no effect."""
if not self._entered:
raise error.ProgrammingError()
if self._started:
return
self._started = True
profiler = encoding.environ.get('HGPROF')
proffn = None
if profiler is None:
profiler = self._ui.config('profiling', 'type')
if profiler not in ('ls', 'stat', 'flame'):
# try load profiler from extension with the same name
proffn = _loadprofiler(self._ui, profiler)
if proffn is None:
self._ui.warn(_("unrecognized profiler '%s' - ignored\n")
% profiler)
profiler = 'stat'
self._output = self._ui.config('profiling', 'output')
try:
if self._output == 'blackbox':
self._fp = util.stringio()
elif self._output:
path = self._ui.expandpath(self._output)
self._fp = open(path, 'wb')
elif pycompat.iswindows:
# parse escape sequence by win32print()
class uifp(object):
def __init__(self, ui):
self._ui = ui
def write(self, data):
self._ui.write_err(data)
def flush(self):
self._ui.flush()
self._fpdoclose = False
self._fp = uifp(self._ui)
else:
self._fpdoclose = False
self._fp = self._ui.ferr
if proffn is not None:
pass
elif profiler == 'ls':
proffn = lsprofile
elif profiler == 'flame':
proffn = flameprofile
else:
proffn = statprofile
self._profiler = proffn(self._ui, self._fp)
self._profiler.__enter__()
except: # re-raises
self._closefp()
raise
def __exit__(self, exception_type, exception_value, traceback):
propagate = None
if self._profiler is not None:
propagate = self._profiler.__exit__(exception_type, exception_value,
traceback)
if self._output == 'blackbox':
val = 'Profile:\n%s' % self._fp.getvalue()
# ui.log treats the input as a format string,
# so we need to escape any % signs.
val = val.replace('%', '%%')
self._ui.log('profile', val)
self._closefp()
return propagate
def _closefp(self):
if self._fpdoclose and self._fp is not None:
self._fp.close()