| … | |
… | |
| 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/sync_file_range? (http://kerneltrap.org/node/6505 http://lwn.net/Articles/178199/) |
6 | TODO: splice/tee/vmsplice/sync_file_range? (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 | - use a separate configure script for IO::AIO (not the libeio one). |
|
|
10 | |
|
|
11 | 3.0 Sun May 11 00:57:14 CEST 2008 |
|
|
12 | - added bin/treescan to the distribution. |
|
|
13 | - switched to using libeio. |
|
|
14 | - LOTS OF INCOMPATIBLE CHANGES: |
|
|
15 | - remove signal functionality, it is not worth the effort. |
|
|
16 | - max_outstanding no longer returns the previous number of requests. |
|
|
17 | - poll_cb no longer returns number of requests. |
|
|
18 | |
|
|
19 | 2.62 Sat Apr 26 13:59:33 CEST 2008 |
|
|
20 | - port to solaris perls configured for old posix |
|
|
21 | (analysed by Jost Krieger). |
|
|
22 | - keep a reference to the perl filehandle object in aio_close, |
|
|
23 | so it doesn't get closed prematurely, leading to ugly races. |
|
|
24 | |
|
|
25 | 2.61 Wed Apr 16 18:45:02 CEST 2008 |
| 9 | - fix treescan output duplication and improve output ordering. |
26 | - fix treescan output duplication and improve output ordering. |
| 10 | also display files given on the commandline. |
27 | also display files given on the commandline. |
|
|
28 | - use a different algorithm for aio_close that is faster |
|
|
29 | and probably has even lower chances of blocking. |
| 11 | - do our own stack memory management for threads - linux |
30 | - do our own stack memory management for threads - linux |
| 12 | allocates outrageous amounts of VM (not so bad unless you |
31 | allocates outrageous amounts of VM (not so bad unless you |
| 13 | use mlockall...), which severely limits the number of threads |
32 | use mlockall...), which severely limits the number of threads |
| 14 | on 32-bit arches: stack size is the larger of PTHREAD_STACK_MIN |
33 | on 32-bit arches: stack size is the larger of PTHREAD_STACK_MIN |
| 15 | and 4096 * sizeof (long) (usually this is 16..64k). |
34 | and 4096 * sizeof (long) (usually this is 16..64k). |
