view tests/test-atomictempfile.py @ 32200:4d504e541d3d

rebase: use matcher to optimize manifestmerge The old merge code would call manifestmerge and calculate the complete diff between the source to the destination. In many cases, like rebase, the vast majority of differences between the source and destination are irrelevant because they are differences between the destination and the common ancestor only, and therefore don't affect the merge. Since most actions are 'keep', all the effort to compute them is wasted. Instead, let's compute the difference between the source and the common ancestor and only perform the diff of those files against the merge destination. When using treemanifest, this lets us avoid loading almost the entire tree when rebasing from a very old ancestor. This speeds up rebase of an old stack of 27 commits by 20x. In mozilla-central, without treemanifest, when rebasing a commit from default~100000 to default, this speeds up the manifestmerge step from 2.6s to 1.2s. However, the additional diff adds an overhead to all manifestmerge calls, especially for flat manifests. When rebasing a commit from default~1 to default it appears to add 100ms in mozilla-central. While we could put this optimization behind a flag, I think the fact that it makes merge O(number of changes being applied) instead of O(number of changes between X and Y) justifies it.
author Durham Goode <durham@fb.com>
date Wed, 03 May 2017 10:43:59 -0700
parents 318a24b52eeb
children 68c43a416585
line wrap: on
line source

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__)