delta/python-packages/gitdb.git/gitdb, branch 0.5.4

bumped version to 0.5.4

2011-07-05T15:00:31+00:00

wrote change log for next release.

2011-07-05T14:45:39+00:00

Choosing memory manager type based on the actual python version for best efficiency

Optimized test_pack_streaming not to cache the objects anymore. Instead an iterator is provided which does the job. Previously it would easily use 750 MB of ram to keep all the associated objects, more than 350k. Still a lot of memory for just 350k objects, but its python after all

2011-07-05T14:40:54+00:00

pack: updated to use its cursor properly, which will be required if huge packs should be handled. This reduces performance as each access requires the windows to be checked/adjusted, but that is how it is. This should be circumvented using other backends, like the one of the gitcmd or libgit2.

2011-07-05T14:39:45+00:00

Default is now the sliding memory map manager

Fixed up docs for upcoming release. Bumped version to 0.5.3

2011-06-13T21:49:42+00:00

Merge branch 'smmap'

2011-06-13T13:05:31+00:00

Added changelog information

2011-06-10T20:05:36+00:00

Switched git db to the non-sliding version of the memory manager which is a good tradeoff between performance loss and resource handling

2011-06-10T19:59:22+00:00

Added smmap as submodule, assured the sys path makes it available

2011-06-10T12:26:46+00:00

Fixed _perf module, which built, but didn't link dynamically. All the time, I think it never successfully imported, but its hard to believe this slipped by.

2011-03-31T21:40:10+00:00

Added performance test for pack-writing, which isn't really showing what I want as it currently read data from a densly compressed pack which takes most of the time in the nearly pure python implementation. Compared to c++, all the measured performance is just below anything I'd want to use. But we shouldn't forget this is just a test implementation, writing packs is quite simple actually, if you leave out the delta compression part and the delta logic