view tests/test-atomictempfile.py @ 26945:8a256cee72c8 stable

tags: create new sortdict for performance reasons

sortdict internally maintains a list of keys in insertion order. When a
key is replaced via __setitem__, we .remove() from this list. This
involves a linear scan and array adjustment. This is an expensive
operation.

The tags reading code was calling into sortdict.__setitem__ for each tag
in a read .hgtags revision. For repositories with thousands of tags or
thousands of .hgtags revisions, the overhead from list.remove()
noticeable.

This patch creates a new sortdict() so __setitem__ calls don't incur a
list.remove.

This doesn't appear to have any performance impact on my Firefox
repository. But that's only because tags reading doesn't show up in
profiles to begin with. I'm still waiting to hear from a user with over
10,000 tags and hundreds of heads on the impact of this patch.

import os
import glob
import unittest
import silenttestrunner

from mercurial.util import atomictempfile

class testatomictempfile(unittest.TestCase):
    def test1_simple(self):
        if os.path.exists('foo'):
            os.remove('foo')
        file = atomictempfile('foo')
        (dir, basename) = os.path.split(file._tempname)
        self.assertFalse(os.path.isfile('foo'))
        self.assertTrue(basename in glob.glob('.foo-*'))

        file.write('argh\n')
        file.close()

        self.assertTrue(os.path.isfile('foo'))
        self.assertTrue(basename not in glob.glob('.foo-*'))

    # discard() removes the temp file without making the write permanent
    def test2_discard(self):
        if os.path.exists('foo'):
            os.remove('foo')
        file = atomictempfile('foo')
        (dir, basename) = os.path.split(file._tempname)

        file.write('yo\n')
        file.discard()

        self.assertFalse(os.path.isfile('foo'))
        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 test3_oops(self):
        self.assertRaises(TypeError, atomictempfile)

if __name__ == '__main__':
    silenttestrunner.main(__name__)