view tests/test-atomictempfile.py @ 44363:f7459da77f23

nodemap: introduce an option to use mmap to read the nodemap mapping

The performance and memory benefit is much greater if we don't have to copy all
the data in memory for each information. So we introduce an option (on by
default) to read the data using mmap.

This changeset is the last one definition the API for index support nodemap
data. (they have to be able to use the mmaping).

Below are some benchmark comparing the best we currently have in 5.3 with the
final step of this series (using the persistent nodemap implementation in
Rust). The benchmark run `hg perfindex` with various revset and the following
variants:

Before:

 * do not use the persistent nodemap
 * use the CPython implementation of the index for nodemap
 * use mmapping of the changelog index

After:

 * use the MixedIndex Rust code, with the NodeTree object for nodemap access
   (still in review)
 * use the persistent nodemap data from disk
 * access the persistent nodemap data through mmap
 * use mmapping of the changelog index

The persistent nodemap greatly speed up  most operation on very large
repositories. Some of the previously very fast lookup end up a bit slower because
the persistent nodemap has to be setup. However the absolute slowdown is very
small and won't matters in the big picture.

Here are some numbers (in seconds) for the reference copy of mozilla-try:

Revset            Before   After     abs-change speedup

-10000:           0.004622 0.005532   0.000910  ×   0.83
-10:              0.000050 0.000132   0.000082  ×   0.37
tip               0.000052 0.000085   0.000033  ×   0.61
0 + (-10000:)     0.028222 0.005337  -0.022885  ×   5.29
0                 0.023521 0.000084  -0.023437  × 280.01
(-10000:) + 0     0.235539 0.005308  -0.230231  ×  44.37
(-10:) + :9       0.232883 0.000180  -0.232703  ×1293.79
(-10000:) + (:99) 0.238735 0.005358  -0.233377  ×  44.55
:99 + (-10000:)   0.317942 0.005593  -0.312349  ×  56.84
:9 + (-10:)       0.313372 0.000179  -0.313193  ×1750.68
:9                0.316450 0.000143  -0.316307  ×2212.93


On smaller repositories, the cost of nodemap related operation is not as big, so
the win is much more modest. Yet it helps shaving a handful of millisecond here
and there.

Here are some numbers (in seconds) for the reference copy of mercurial:

Revset            Before   After     abs-change speedup
-10:              0.000065 0.000097   0.000032  × 0.67
tip               0.000063 0.000078   0.000015  × 0.80
0                 0.000561 0.000079  -0.000482  × 7.10
-10000:           0.004609 0.003648  -0.000961  × 1.26
0 + (-10000:)     0.005023 0.003715  -0.001307  × 1.35
(-10:) + :9       0.002187 0.000108  -0.002079  ×20.25
(-10000:) + 0     0.006252 0.003716  -0.002536  × 1.68
(-10000:) + (:99) 0.006367 0.003707  -0.002660  × 1.71
:9 + (-10:)       0.003846 0.000110  -0.003736  ×34.96
:9                0.003854 0.000099  -0.003755  ×38.92
:99 + (-10000:)   0.007644 0.003778  -0.003866  × 2.02

Differential Revision: https://phab.mercurial-scm.org/D7894

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__)