Mercurial > hgsubversion
view tests/test_push_dirs.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 | db3a651494f9 |
children | d741f536f23a |
line wrap: on
line source
import test_util import unittest class TestPushDirectories(test_util.TestBase): def test_push_dirs(self): repo_path = self.load_and_fetch('emptyrepo.svndump')[1] changes = [ # Single file in single directory ('d1/a', 'd1/a', 'a\n'), # Two files in one directory ('d2/a', 'd2/a', 'a\n'), ('d2/b', 'd2/b', 'a\n'), # Single file in empty directory hierarchy ('d31/d32/d33/d34/a', 'd31/d32/d33/d34/a', 'a\n'), ('d31/d32/a', 'd31/d32/a', 'a\n'), ] self.commitchanges(changes) self.pushrevisions() self.assertEqual(test_util.svnls(repo_path, 'trunk'), ['d1', 'd1/a', 'd2', 'd2/a', 'd2/b', 'd31', 'd31/d32', 'd31/d32/a', 'd31/d32/d33', 'd31/d32/d33/d34', 'd31/d32/d33/d34/a']) # Add one revision with changed files only, no directory addition # or deletion. changes = [ ('d1/a', 'd1/a', 'aa\n'), ('d2/a', 'd2/a', 'aa\n'), ] self.commitchanges(changes) self.pushrevisions() changes = [ # Remove single file in single directory ('d1/a', None, None), # Remove one file out of two ('d2/a', None, None), # Removing this file should remove one empty parent dir too ('d31/d32/d33/d34/a', None, None), ] self.commitchanges(changes) self.pushrevisions() self.assertEqual(test_util.svnls(repo_path, 'trunk'), ['d2', 'd2/b', 'd31', 'd31/d32', 'd31/d32/a', ]) def test_push_new_dir_project_root_not_repo_root(self): repo_path = self.load_and_fetch('fetch_missing_files_subdir.svndump', subdir='foo')[1] changes = [('magic_new/a', 'magic_new/a', 'ohai',), ] self.commitchanges(changes) self.pushrevisions() self.assertEqual(test_util.svnls(repo_path, 'foo/trunk'), ['bar', 'bar/alpha', 'bar/beta', 'bar/delta', 'bar/gamma', 'foo', 'magic_new', 'magic_new/a']) def test_push_new_file_existing_dir_root_not_repo_root(self): repo_path = self.load_and_fetch('empty_dir_in_trunk_not_repo_root.svndump', subdir='project')[1] changes = [('narf/a', 'narf/a', 'ohai',), ] self.commitchanges(changes) self.assertEqual(test_util.svnls(repo_path, 'project/trunk'), ['a', 'narf', ]) self.pushrevisions() self.assertEqual(test_util.svnls(repo_path, 'project/trunk'), ['a', 'narf', 'narf/a']) changes = [('narf/a', None, None,), ] self.commitchanges(changes) self.pushrevisions() self.assertEqual(test_util.svnls(repo_path, 'project/trunk'), ['a']) def test_push_single_dir_change_in_subdir(self): # Tests simple pushing from default branch to a single dir repo # Changes a file in a subdir (regression). repo, repo_path = self.load_and_fetch('branch_from_tag.svndump', stupid=False, layout='single', subdir='tags') changes = [('tag_r3/alpha', 'tag_r3/alpha', 'foo'), ('tag_r3/new', 'tag_r3/new', 'foo'), ('new_dir/new', 'new_dir/new', 'foo'), ] self.commitchanges(changes) self.pushrevisions() self.assertEqual(test_util.svnls(repo_path, 'tags'), ['copied_tag', 'copied_tag/alpha', 'copied_tag/beta', 'new_dir', 'new_dir/new', 'tag_r3', 'tag_r3/alpha', 'tag_r3/beta', 'tag_r3/new']) def suite(): all_tests = [unittest.TestLoader().loadTestsFromTestCase(TestPushDirectories), ] return unittest.TestSuite(all_tests)