view tests/test-rust-revlog.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 unittest

try:
    from mercurial import rustext

    rustext.__name__  # trigger immediate actual import
except ImportError:
    rustext = None
else:
    from mercurial.rustext import revlog

    # this would fail already without appropriate ancestor.__package__
    from mercurial.rustext.ancestor import LazyAncestors

from mercurial.testing import revlog as revlogtesting


@unittest.skipIf(
    rustext is None,
    "rustext module revlog relies on is not available",
)
class RustRevlogIndexTest(revlogtesting.RevlogBasedTestBase):
    def test_heads(self):
        idx = self.parseindex()
        rustidx = revlog.MixedIndex(idx)
        self.assertEqual(rustidx.headrevs(), idx.headrevs())

    def test_get_cindex(self):
        # drop me once we no longer need the method for shortest node
        idx = self.parseindex()
        rustidx = revlog.MixedIndex(idx)
        cidx = rustidx.get_cindex()
        self.assertTrue(idx is cidx)

    def test_len(self):
        idx = self.parseindex()
        rustidx = revlog.MixedIndex(idx)
        self.assertEqual(len(rustidx), len(idx))

    def test_ancestors(self):
        idx = self.parseindex()
        rustidx = revlog.MixedIndex(idx)
        lazy = LazyAncestors(rustidx, [3], 0, True)
        # we have two more references to the index:
        # - in its inner iterator for __contains__ and __bool__
        # - in the LazyAncestors instance itself (to spawn new iterators)
        self.assertTrue(2 in lazy)
        self.assertTrue(bool(lazy))
        self.assertEqual(list(lazy), [3, 2, 1, 0])
        # a second time to validate that we spawn new iterators
        self.assertEqual(list(lazy), [3, 2, 1, 0])

        # let's check bool for an empty one
        self.assertFalse(LazyAncestors(idx, [0], 0, False))


if __name__ == '__main__':
    import silenttestrunner

    silenttestrunner.main(__name__)