tests/test-atomictempfile.py

setdiscovery: stop limiting the number of local head we initially send

In our testing this limitation provides now real gain and instead triggers
pathological discovery timing for some repository with many heads.

See inline documentation for details.

Some timing below:

Mozilla try repository, (~1M revs, ~35K heads), discovery between 2 clones with
100 head missing on each side

before:
! wall 1.492111 comb 1.490000 user 1.450000 sys 0.040000 (best of 20)
! wall 1.813992 comb 1.820000 user 1.700000 sys 0.120000 (max of 20)
! wall 1.574326 comb 1.573500 user 1.522000 sys 0.051500 (avg of 20)
! wall 1.572583 comb 1.570000 user 1.520000 sys 0.050000 (median of 20)

after:
! wall 1.147834 comb 1.150000 user 1.090000 sys 0.060000 (best of 20)
! wall 1.449144 comb 1.450000 user 1.330000 sys 0.120000 (max of 20)
! wall 1.204618 comb 1.202500 user 1.146500 sys 0.056000 (avg of 20)
! wall 1.194407 comb 1.190000 user 1.140000 sys 0.050000 (median of 20)


pypy (~100 heads, 317 heads) discovery between clones with only 42 common heads

before:
! wall 0.031653 comb 0.030000 user 0.030000 sys 0.000000 (best of 25)
! wall 0.055719 comb 0.050000 user 0.040000 sys 0.010000 (max of 25)
! wall 0.038939 comb 0.039600 user 0.038400 sys 0.001200 (avg of 25)
! wall 0.038660 comb 0.050000 user 0.040000 sys 0.010000 (median of 25)

after:
! wall 0.018754 comb 0.020000 user 0.020000 sys 0.000000 (best of 49)
! wall 0.034505 comb 0.040000 user 0.030000 sys 0.010000 (max of 49)
! wall 0.019631 comb 0.019796 user 0.018367 sys 0.001429 (avg of 49)
! wall 0.019132 comb 0.020000 user 0.020000 sys 0.000000 (median of 49)


Private repository (~1M revs, ~3K heads), discovery from a strip subset, about
100 changesets to be pulled.

before:
! wall 1.837729 comb 1.840000 user 1.790000 sys 0.050000 (best of 20)
! wall 2.203468 comb 2.200000 user 2.100000 sys 0.100000 (max of 20)
! wall 2.049355 comb 2.048500 user 2.002500 sys 0.046000 (avg of 20)
! wall 2.035315 comb 2.040000 user 2.000000 sys 0.040000 (median of 20)

after:
! wall 0.136598 comb 0.130000 user 0.110000 sys 0.020000 (best of 20)
! wall 0.330519 comb 0.330000 user 0.260000 sys 0.070000 (max of 20)
! wall 0.157254 comb 0.155500 user 0.123000 sys 0.032500 (avg of 20)
! wall 0.149870 comb 0.140000 user 0.110000 sys 0.030000 (median of 20)


Same private repo, discovery between two clone with 500 different heads on each
side:

before:
! wall 2.372919 comb 2.370000 user 2.320000 sys 0.050000 (best of 20)
! wall 2.622422 comb 2.610000 user 2.510000 sys 0.100000 (max of 20)
! wall 2.450135 comb 2.450000 user 2.402000 sys 0.048000 (avg of 20)
! wall 2.443896 comb 2.450000 user 2.410000 sys 0.040000 (median of 20)

after:
! wall 0.625497 comb 0.620000 user 0.570000 sys 0.050000 (best of 20)
! wall 0.834723 comb 0.820000 user 0.730000 sys 0.090000 (max of 20)
! wall 0.675725 comb 0.675500 user 0.628000 sys 0.047500 (avg of 20)
! wall 0.671614 comb 0.680000 user 0.640000 sys 0.040000 (median of 20)

from __future__ import absolute_import

import glob
import os
import shutil
import stat
import tempfile
import unittest

from mercurial import (
    pycompat,
    util,
)
atomictempfile = util.atomictempfile

if pycompat.ispy3:
    xrange = range

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 xrange(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 xrange(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__)