##// END OF EJS Templates
perf: add command for measuring revlog chunk operations...
perf: add command for measuring revlog chunk operations Upcoming commits will teach revlogs to leverage the new compression engine API so that new compression formats can more easily be leveraged in revlogs. We want to be sure this refactoring doesn't regress performance. So this commit introduces "perfrevchunks" to explicitly test performance of reading, decompressing, and recompressing revlog chunks. Here is output when run on the mozilla-unified repo: $ hg perfrevlogchunks -c ! read ! wall 0.346603 comb 0.350000 user 0.340000 sys 0.010000 (best of 28) ! read w/ reused fd ! wall 0.337707 comb 0.340000 user 0.320000 sys 0.020000 (best of 30) ! read batch ! wall 0.013206 comb 0.020000 user 0.000000 sys 0.020000 (best of 221) ! read batch w/ reused fd ! wall 0.013259 comb 0.030000 user 0.010000 sys 0.020000 (best of 222) ! chunk ! wall 1.909939 comb 1.910000 user 1.900000 sys 0.010000 (best of 6) ! chunk batch ! wall 1.750677 comb 1.760000 user 1.740000 sys 0.020000 (best of 6) ! compress ! wall 5.668004 comb 5.670000 user 5.670000 sys 0.000000 (best of 3) $ hg perfrevlogchunks -m ! read ! wall 0.365834 comb 0.370000 user 0.350000 sys 0.020000 (best of 26) ! read w/ reused fd ! wall 0.350160 comb 0.350000 user 0.320000 sys 0.030000 (best of 28) ! read batch ! wall 0.024777 comb 0.020000 user 0.000000 sys 0.020000 (best of 119) ! read batch w/ reused fd ! wall 0.024895 comb 0.030000 user 0.000000 sys 0.030000 (best of 118) ! chunk ! wall 2.514061 comb 2.520000 user 2.480000 sys 0.040000 (best of 4) ! chunk batch ! wall 2.380788 comb 2.380000 user 2.360000 sys 0.020000 (best of 5) ! compress ! wall 9.815297 comb 9.820000 user 9.820000 sys 0.000000 (best of 3) We already see some interesting data, such as how much slower non-batched chunk reading is and that zlib compression appears to be >2x slower than decompression. I didn't have the data when I wrote this commit message, but I ran this on Mozilla's NFS-based Mercurial server and the time for reading with a reused file descriptor was faster. So I think it is worth testing both with and without file descriptor reuse so we can make informed decisions about recycling file descriptors.

File last commit:

r30332:318a24b5 default
r30451:94ca0e13 default
Show More
test-atomictempfile.py
119 lines | 4.1 KiB | text/x-python | PythonLexer
/ tests / test-atomictempfile.py
from __future__ import absolute_import
import glob
import os
import shutil
import tempfile
import unittest
from mercurial import (
util,
)
atomictempfile = util.atomictempfile
class testatomictempfile(unittest.TestCase):
def setUp(self):
self._testdir = tempfile.mkdtemp('atomictempfiletest')
self._filename = os.path.join(self._testdir, 'testfilename')
def tearDown(self):
shutil.rmtree(self._testdir, True)
def testsimple(self):
file = atomictempfile(self._filename)
self.assertFalse(os.path.isfile(self._filename))
tempfilename = file._tempname
self.assertTrue(tempfilename in glob.glob(
os.path.join(self._testdir, '.testfilename-*')))
file.write(b'argh\n')
file.close()
self.assertTrue(os.path.isfile(self._filename))
self.assertTrue(tempfilename not in glob.glob(
os.path.join(self._testdir, '.testfilename-*')))
# discard() removes the temp file without making the write permanent
def testdiscard(self):
file = atomictempfile(self._filename)
(dir, basename) = os.path.split(file._tempname)
file.write(b'yo\n')
file.discard()
self.assertFalse(os.path.isfile(self._filename))
self.assertTrue(basename not in os.listdir('.'))
# if a programmer screws up and passes bad args to atomictempfile, they
# get a plain ordinary TypeError, not infinite recursion
def testoops(self):
self.assertRaises(TypeError, atomictempfile)
# checkambig=True avoids ambiguity of timestamp
def testcheckambig(self):
def atomicwrite(checkambig):
f = atomictempfile(self._filename, checkambig=checkambig)
f.write('FOO')
f.close()
# try some times, because reproduction of ambiguity depends on
# "filesystem time"
for i in xrange(5):
atomicwrite(False)
oldstat = os.stat(self._filename)
if oldstat.st_ctime != oldstat.st_mtime:
# subsequent changing never causes ambiguity
continue
repetition = 3
# repeat atomic write with checkambig=True, to examine
# whether st_mtime is advanced multiple times as expected
for j in xrange(repetition):
atomicwrite(True)
newstat = os.stat(self._filename)
if oldstat.st_ctime != newstat.st_ctime:
# timestamp ambiguity was naturally avoided while repetition
continue
# st_mtime should be advanced "repetition" times, because
# all atomicwrite() occurred at same time (in sec)
self.assertTrue(newstat.st_mtime ==
((oldstat.st_mtime + repetition) & 0x7fffffff))
# no more examination is needed, if assumption above is true
break
else:
# This platform seems too slow to examine anti-ambiguity
# of file timestamp (or test happened to be executed at
# bad timing). Exit silently in this case, because running
# on other faster platforms can detect problems
pass
def testread(self):
with open(self._filename, 'wb') as f:
f.write(b'foobar\n')
file = atomictempfile(self._filename, mode='rb')
self.assertTrue(file.read(), b'foobar\n')
file.discard()
def testcontextmanagersuccess(self):
"""When the context closes, the file is closed"""
with atomictempfile('foo') as f:
self.assertFalse(os.path.isfile('foo'))
f.write(b'argh\n')
self.assertTrue(os.path.isfile('foo'))
def testcontextmanagerfailure(self):
"""On exception, the file is discarded"""
try:
with atomictempfile('foo') as f:
self.assertFalse(os.path.isfile('foo'))
f.write(b'argh\n')
raise ValueError
except ValueError:
pass
self.assertFalse(os.path.isfile('foo'))
if __name__ == '__main__':
import silenttestrunner
silenttestrunner.main(__name__)