view tests/test-atomictempfile.py @ 47343:9f798c1b0d89 stable

cext: fix memory leak in phases computation

Without this a buffer whose size in bytes is the number of
changesets in the repository is leaked each time the repository is
opened and changeset phases are computed.

Impact: the current code in hgwebdir creates a new `localrepository`
instance for each HTTP request. Since any pull or push is made of several
requests, a team of 100 people can easily produce thousands of such
requests per day.

Being a low-level malloc, this leak can't be seen with the gc module and
tools relying on that, but was spotted by valgrind immediately.

Reproduction
------------

  for i in range(cl_args.iterations):
      repo = hg.repository(baseui, repo_path)
      rev = repo.revs(rev).first()
      ctx = repo[rev]

  del ctx
  del repo
  # avoid any pollution by other type of leak
  # (that should be fixed in 5.8)
  repoview._filteredrepotypes.clear()

  gc.collect()

Measurements
------------

Resident Set Size (RSS), taken on a clone of
mozilla-central for performance analysis (440 000
changesets).

before:
  5.8+hg19.5ac0f2a8ba72  1000 iterations: 1606MB
  5.8+hg19.5ac0f2a8ba72 10000 iterations: 5723MB
after:
  5.8+hg20.e2084d39e145  1000 iterations:  555MB
  5.8+hg20.e2084d39e145 10000 iterations:  555MB
         (double checked, not a copy/paste error)

(e2084d39e14 is the present changeset, before amendment
of the message to add the measurements)

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__)