bisect: avoid copying ancestor list for non-merge commits
During a bisection, hg needs to compute a list of all ancestors for every
candidate commit. This is accomplished via a bottom-up traversal of the set of
candidates, during which each revision's ancestor list is populated using the
ancestor list of its parent(s). Previously, this involved copying the entire
list, which could be very long in if the bisection range was large.
To help improve this, we can observe that each candidate commit is visited
exactly once, at which point its ancestor list is copied into its children's
lists and then dropped. In the case of non-merge commits, a commit's ancestor
list consists exactly of its parent's list plus itself. This means that we can
trivially reuse the parent's existing list for one of its non-merge children,
which avoids copying entirely if that commit is the parent's only child. This
makes bisections over linear ranges of commits much faster.
During some informal testing in the large publicly-available `mozilla-central`
repository, this noticeably sped up bisections over large ranges of history:
Setup:
$ cd mozilla-central
$ hg bisect --reset
$ hg bisect --good 0
$ hg log -r tip -T '{rev}\n'
628417
Test:
$ time hg bisect --bad tip --noupdate
Before:
real 3m35.927s
user 3m35.553s
sys 0m0.319s
After:
real 1m41.142s
user 1m40.810s
sys 0m0.285s
import glob
import os
import shutil
import stat
import tempfile
import unittest
from mercurial import (
util,
)
atomictempfile = util.atomictempfile
class testatomictempfile(unittest.TestCase):
def setUp(self):
self._testdir = tempfile.mkdtemp(b'atomictempfiletest')
self._filename = os.path.join(self._testdir, b'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, b'.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, b'.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(b'.'))
# if a programmer screws up and passes bad args to atomictempfile, they
# get a plain ordinary TypeError, not infinite recursion
def testoops(self):
with self.assertRaises(TypeError):
atomictempfile()
# checkambig=True avoids ambiguity of timestamp
def testcheckambig(self):
def atomicwrite(checkambig):
f = atomictempfile(self._filename, checkambig=checkambig)
f.write(b'FOO')
f.close()
# try some times, because reproduction of ambiguity depends on
# "filesystem time"
for i in range(5):
atomicwrite(False)
oldstat = os.stat(self._filename)
if oldstat[stat.ST_CTIME] != oldstat[stat.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 range(repetition):
atomicwrite(True)
newstat = os.stat(self._filename)
if oldstat[stat.ST_CTIME] != newstat[stat.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)
oldtime = (oldstat[stat.ST_MTIME] + repetition) & 0x7FFFFFFF
self.assertTrue(newstat[stat.ST_MTIME] == oldtime)
# 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=b'rb')
self.assertTrue(file.read(), b'foobar\n')
file.discard()
def testcontextmanagersuccess(self):
"""When the context closes, the file is closed"""
with atomictempfile(b'foo') as f:
self.assertFalse(os.path.isfile(b'foo'))
f.write(b'argh\n')
self.assertTrue(os.path.isfile(b'foo'))
def testcontextmanagerfailure(self):
"""On exception, the file is discarded"""
try:
with atomictempfile(b'foo') as f:
self.assertFalse(os.path.isfile(b'foo'))
f.write(b'argh\n')
raise ValueError
except ValueError:
pass
self.assertFalse(os.path.isfile(b'foo'))
if __name__ == '__main__':
import silenttestrunner
silenttestrunner.main(__name__)