Mercurial > hgsubversion
view tests/test_push_renames.py @ 931:e1dbd9646d6a
svnwrap: use custom StringIO class in get_file()
The wrappers were calling ra.get_file() with a cStringIO object.
Empirically, svn 1.7.5 is writing 16kB blocks to the stream object, and
cStringIO reallocates its internal buffer and doubles its size whenever
it is filled. With large committed files this requires two large
memory blocks at the same time.
SimpleStringIO implements the mimimum StringIO interface used by
ra.get_file() but instead stores all the blocks and "join" them at the
end. It means more fragmentation but requires only one large block,
without overallocation. Also, 16kB blocks should be friendly to most
allocators.
In practice, this simple change let me convert a revision containing
multiple moderately large files, the largest being around 450MB, with a
32-bits Windows setup, python 2.7, swig svn 1.7.5, in stupid mode, while
it was previously aborting with "not enough memory". The same revision
still fails in replay mode.
author | Patrick Mezard <patrick@mezard.eu> |
---|---|
date | Sun, 16 Sep 2012 19:31:49 +0200 |
parents | a279b5838aaf |
children | d741f536f23a |
line wrap: on
line source
import test_util import sys import unittest class TestPushRenames(test_util.TestBase): def setUp(self): test_util.TestBase.setUp(self) self.repo_path = self.load_and_fetch('pushrenames.svndump', stupid=True)[1] def _debug_print_copies(self, ctx): w = sys.stderr.write for f in ctx.files(): if f not in ctx: w('R %s\n' % f) else: w('U %s %r\n' % (f, ctx[f].data())) if ctx[f].renamed(): w('%s copied from %s\n' % (f, ctx[f].renamed()[0])) def test_push_renames(self): repo = self.repo changes = [ # Regular copy of a single file ('a', 'a2', None), # Copy and update of target ('a', 'a3', 'aa\n'), # Regular move of a single file ('b', 'b2', None), ('b', None, None), # Regular move and update of target ('c', 'c2', 'c\nc\n'), ('c', None, None), # Copy and update of source and targets ('d', 'd2', 'd\nd2\n'), ('d', 'd', 'd\nd\n'), # Double copy and removal (aka copy and move) ('e', 'e2', 'e\ne2\n'), ('e', 'e3', 'e\ne3\n'), ('e', None, None), ] self.commitchanges(changes) self.pushrevisions() tip = self.repo['tip'] # self._debug_print_copies(tip) self.assertchanges(changes, tip) def test_push_rename_with_space(self): changes = [ ('random/dir with space/file with space', 'random/dir with space/file with space', 'file contents'), ] self.commitchanges(changes) changes = [ ('random/dir with space/file with space', 'random2/dir with space/file with space', None), ('random/dir with space/file with space', None, None), ] self.commitchanges(changes) self.pushrevisions() self.assertEqual(self.repo['tip'].manifest().keys(), ['a', 'c', 'b', 'e', 'd', 'random2/dir with space/file with space']) def test_push_rename_tree(self): repo = self.repo changes = [ ('geek/alpha', 'geek/alpha', 'content',), ('geek/beta', 'geek/beta', 'content',), ('geek/delta', 'geek/delta', 'content',), ('geek/gamma', 'geek/gamma', 'content',), ('geek/later/pi', 'geek/later/pi', 'content geek/later/pi',), ('geek/later/rho', 'geek/later/rho', 'content geek/later/rho',), ('geek/other/blah', 'geek/other/blah', 'content geek/other/blah',), ('geek/other/another/layer', 'geek/other/another/layer', 'content deep file',), ] self.commitchanges(changes) self.pushrevisions() self.assertchanges(changes, self.repo['tip']) changes = [ # rename (copy + remove) all of geek to greek ('geek/alpha', 'greek/alpha', None,), ('geek/beta', 'greek/beta', None,), ('geek/delta', 'greek/delta', None,), ('geek/gamma', 'greek/gamma', None,), ('geek/later/pi', 'greek/later/pi', None,), ('geek/later/rho', 'greek/later/rho', None,), ('geek/other/blah', 'greek/other/blah', None,), ('geek/other/another/layer', 'greek/other/another/layer', None,), ('geek/alpha', None, None,), ('geek/beta', None, None,), ('geek/delta', None, None,), ('geek/gamma', None, None,), ('geek/later/pi', None, None,), ('geek/later/rho', None, None,), ('geek/other/blah', None, None,), ('geek/other/another/layer', None, None,), ] self.commitchanges(changes) self.pushrevisions() assert reduce(lambda x, y: x and y, ('geek' not in f for f in test_util.svnls(self.repo_path, 'trunk'))), ( 'This failure means rename of an entire tree is broken.' ' There is a print on the preceding line commented out ' 'that should help you.') def suite(): all_tests = [unittest.TestLoader().loadTestsFromTestCase(TestPushRenames), ] return unittest.TestSuite(all_tests)