Mercurial > hgsubversion
view tests/test_updatemeta.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 | 5bacb9c63e3e |
children |
line wrap: on
line source
import test_util import os import pickle import unittest import test_rebuildmeta from mercurial import context from mercurial import extensions from mercurial import hg from mercurial import ui from hgsubversion import svncommands from hgsubversion import svnmeta def _do_case(self, name, stupid, single): subdir = test_util.subdir.get(name, '') layout = 'auto' if single: layout = 'single' repo, repo_path = self.load_and_fetch(name, subdir=subdir, stupid=stupid, layout=layout) assert len(self.repo) > 0 wc2_path = self.wc_path + '_clone' u = ui.ui() src, dest = test_util.hgclone(u, self.wc_path, wc2_path, update=False) src = test_util.getlocalpeer(src) dest = test_util.getlocalpeer(dest) # insert a wrapper that prevents calling changectx.children() def failfn(orig, ctx): self.fail('calling %s is forbidden; it can cause massive slowdowns ' 'when rebuilding large repositories' % orig) origchildren = getattr(context.changectx, 'children') extensions.wrapfunction(context.changectx, 'children', failfn) # test updatemeta on an empty repo try: svncommands.updatemeta(u, dest, args=[test_util.fileurl(repo_path + subdir), ]) finally: # remove the wrapper context.changectx.children = origchildren self._run_assertions(name, stupid, single, src, dest, u) def _run_assertions(self, name, stupid, single, src, dest, u): test_rebuildmeta._run_assertions(self, name, stupid, single, src, dest, u) skip = set([ 'project_root_not_repo_root.svndump', 'corrupt.svndump', ]) attrs = {'_do_case': _do_case, '_run_assertions': _run_assertions, } for case in [f for f in os.listdir(test_util.FIXTURES) if f.endswith('.svndump')]: # this fixture results in an empty repository, don't use it if case in skip: continue bname = 'test_' + case[:-len('.svndump')] attrs[bname] = test_rebuildmeta.buildmethod(case, bname, False, False) name = bname + '_stupid' attrs[name] = test_rebuildmeta.buildmethod(case, name, True, False) name = bname + '_single' attrs[name] = test_rebuildmeta.buildmethod(case, name, False, True) UpdateMetaTests = type('UpdateMetaTests', (test_util.TestBase,), attrs) def suite(): all_tests = [unittest.TestLoader().loadTestsFromTestCase(UpdateMetaTests), ] return unittest.TestSuite(all_tests)