1 | Revision history for IO::AIO |
1 | Revision history for IO::AIO |
2 | |
2 | |
3 | TODO: aio_cptree/mvtree |
3 | TODO: aio_cptree/mvtree |
4 | TODO: reduce condvar fairness: schedule hot-cache-threads first? |
4 | TODO: reduce condvar fairness: schedule hot-cache-threads first? |
5 | TODO: splice/tee/vmsplice? (http://kerneltrap.org/node/6505 http://lwn.net/Articles/178199/) |
5 | TODO: vmsplice? (http://kerneltrap.org/node/6505 http://lwn.net/Articles/178199/) |
6 | TODO: aio_fcntl, at least for file-locking |
6 | TODO: aio_fcntl, at least for file-locking |
7 | TODO: aio_mincore? |
7 | TODO: aio_mincore? |
8 | TODO: getxattr etc.? |
8 | TODO: getxattr etc.? |
9 | TODO: F_DUPFD_CLOEXEC |
9 | TODO: F_DUPFD_CLOEXEC |
10 | TODO: SEEK_HOLE, SEEK_DATA? |
10 | TODO: emulation for splice? |
|
|
11 | TODO: eio_mmap|mlock|munmap|splice... |
11 | |
12 | |
|
|
13 | - fix a crash in aio_fiemap, when used on ranges without any |
|
|
14 | extents. |
|
|
15 | - work around linux kernel bug (at least in 3.2): kernel might |
|
|
16 | trash fiemap input arguments. |
|
|
17 | - work around linux kernel bug (at least in 3.2): kernel does not |
|
|
18 | set FIEMAP_EXTENT_LAST on last segment. |
|
|
19 | - work around linux kernel bug (at least in 3.2): kernel silently |
|
|
20 | truncates segment count if a file. |
|
|
21 | - make fh argument of IO::AIO::mmap optional, also add mmap/munmap |
|
|
22 | to quick overview. |
|
|
23 | - splice can corrupt data. |
|
|
24 | - (libeio) remove pread/pwrite emulation. |
|
|
25 | - do not grow mmaped scalars in aio_read. |
|
|
26 | - add FALLOC_FL_PUNCH_HOLE and document fallocate. |
|
|
27 | |
|
|
28 | 4.15 Tue Apr 10 06:59:00 CEST 2012 |
|
|
29 | - always include linux/types.h for fiemap, for compatibility to |
|
|
30 | ancient systems (Paul Howarth). |
|
|
31 | - experimental support for IO::AIO::splice and ::tee (no aio_...). |
|
|
32 | - provide SEEK_HOLE and SEEK_DATA, if available. |
|
|
33 | - work around (again!) an immensely stupid bug in RHEL, defining |
|
|
34 | autoconf macros in linux system headers (analysed by Paul Howarth). |
|
|
35 | |
|
|
36 | 4.14 Sat Apr 7 02:45:18 CEST 2012 |
|
|
37 | - fix stat structure usage on windows, which caused bogus stat results. |
|
|
38 | - (libeio) make readahead emulation behave more like actual readahead by never failing. |
12 | - new request aio_seek. |
39 | - new request aio_seek. |
13 | - new request aio_fiemap. |
40 | - new request aio_fiemap. |
14 | - fix stat structure usage on windows, which caused bogus stat results. |
|
|
15 | - (libeio) make readahead emulation behave more like actual readahead by never failing. |
|
|
16 | - autogenerate the #ifdef/#define 0 blocks for symbols we export. |
41 | - autogenerate the #ifdef/#define 0 blocks for symbols we export. |
17 | |
42 | |
18 | 4.12 Fri Dec 30 08:51:25 CET 2011 |
43 | 4.12 Fri Dec 30 08:51:25 CET 2011 |
19 | - realpath would return a random value if the name was too long, |
44 | - realpath would return a random value if the name was too long, |
20 | instead of -1. |
45 | instead of -1. |