… | |
… | |
4 | TODO: aio_cptree/mvtree |
4 | TODO: aio_cptree/mvtree |
5 | TODO: reduce condvar fairness: schedule hot-cache-threads first? |
5 | TODO: reduce condvar fairness: schedule hot-cache-threads first? |
6 | TODO: splice/tee/vmsplice? (http://kerneltrap.org/node/6505 http://lwn.net/Articles/178199/) |
6 | TODO: splice/tee/vmsplice? (http://kerneltrap.org/node/6505 http://lwn.net/Articles/178199/) |
7 | TODO: aio_fcntl, at least for file-locking |
7 | TODO: aio_fcntl, at least for file-locking |
8 | |
8 | |
9 | - avoid some degenerate sorting cases on systems without d_ino, |
9 | - (libeio) replaced quicksort+insertion sort by a tuned radix |
10 | or when the dentries are mostly sorted by inode already (common |
10 | sort + insertion sort, resulting in comparable runtime (usually |
11 | with freshly unpacked tarfiles for example). |
11 | faster) to the old version, but without any ill side effects on |
|
|
12 | degenerated (for quicksort) data. |
12 | - correctly sort dirs by inodes only if we have perfect type |
13 | - (libeio) correctly sort dirs by inodes if we have perfect type |
13 | knowledge and DIRS_FIRST is used. |
14 | knowledge and DIRS_FIRST is used. |
14 | - speed up directory entry sorting further by some 20%. |
15 | - (libeio) internally the wrong DT_* constants were used, but no |
|
|
16 | known system has differing EIO_DT_*/DT_* values, so not an issue. |
|
|
17 | - removed a (harmless) assert that was left over on the code |
|
|
18 | but should not have been. |
15 | |
19 | |
16 | 3.23 Sat Jun 13 16:57:58 CEST 2009 |
20 | 3.23 Sat Jun 13 16:57:58 CEST 2009 |
17 | - fix off-by-one bug in aio_readdir that was introduced in the |
21 | - fix off-by-one bug in aio_readdir that was introduced in the |
18 | rushed 3.22 release. |
22 | rushed 3.22 release. |
19 | |
23 | |