ViewVC Help
View File | Revision Log | Show Annotations | Download File
/cvs/IO-AIO/Changes
(Generate patch)

Comparing IO-AIO/Changes (file contents):
Revision 1.197 by root, Wed Jun 17 06:33:07 2009 UTC vs.
Revision 1.231 by root, Wed Aug 4 14:02:58 2010 UTC

4TODO: aio_cptree/mvtree 4TODO: aio_cptree/mvtree
5TODO: reduce condvar fairness: schedule hot-cache-threads first? 5TODO: reduce condvar fairness: schedule hot-cache-threads first?
6TODO: splice/tee/vmsplice? (http://kerneltrap.org/node/6505 http://lwn.net/Articles/178199/) 6TODO: splice/tee/vmsplice? (http://kerneltrap.org/node/6505 http://lwn.net/Articles/178199/)
7TODO: aio_fcntl, at least for file-locking 7TODO: aio_fcntl, at least for file-locking
8TODO: fallocate, if it wouldn't be so useless. 8TODO: fallocate, if it wouldn't be so useless.
9TODO: aio_mincore?
10TODO: posix_madvise.
11TODO: add? also linux-specific stuff?
12O_EXEC
13O_SEARCH
14O_CLOEXEC
15O_DIRECTORY
16O_DSYNC
17O_NOCTTY
18O_NOFOLLOW
19O_NONBLOCK
20O_RSYNC
21O_SYNC
22O_TTY_INIT
9 23
103.25 24 - do not leak memory in IO::AIO::mmap when the scalar already
25 had string-data.
26 - add O_RDWR, O_APPEND and O_EXCL symbols and semi-documented
27 them.
28 - cache the result IV, for a minor speedup in the common case.
29 - croak when an mmapped-scalar changes location, to detect
30 user-errors better.
31
323.65 Wed Mar 31 02:45:05 CEST 2010
33 - actually use PATH_MAX instead of NAME_MAX for readlink, as to not
34 cut off long pathnames in aio_readlink (based on patch by
35 Rasmus Andersson).
36 - a double fork partially killed the event pipe (great testcase
37 by dormando). affects IO::AIO, BDB and Async::Interrupt.
38 - suck steve's dick and rename our symbols to avoid colliding
39 with nonstandard identifier spam on the broken os x pseudo-os.
40 affects IO::AIO and BDB.
41
423.6 Mon Jan 11 00:43:39 CET 2010
43 - (libeio) more fixes for the freebsd/apple sendfile - broken by
44 manpage standards, but apparently correct accoridng to actual
45 kernel sources.
46 - add IO::AIO::mmap/munmap support.
47 - add IO::AIO::m(un)lockall support.
48 - clean up manpage.
49
503.5 Thu Jan 7 21:25:04 CET 2010
51 - (liebio) fix freebsd sendfile (Vanilla Hsu).
52 - (libeio) also fix darwin sendfile that suffered from a similar bug.
53 - add aio_statvfs as interface to statvfs/fstatvfs.
54 - work around buggy symlink() on cygwin in the testsuite.
55 - wtf. freebsd-8.0 actually passes the testsuite! I knew
56 they could implement fork and semaphores one day! cheers!
57
583.4 Sat Jan 2 15:13:04 CET 2010
59 - (libeio) max_poll_time was not properly converted to ticks.
60 - clarify cancel_subs description.
61 - IO::AIO::sendfile did not actually return the return value
62 from the sendfile call.
63 - implement aio_msync, aio_mtouch.
64 - (libeio) tentatively support darwin in sendfile.
65
663.31 Thu Nov 12 02:14:29 CET 2009
67 - fix result status documentation of aio_copy, aio_move.
68 - speed up object creation considerably by avoiding
69 hash lookups.
70
713.3 Wed Aug 5 13:52:58 CEST 2009
72 - use common::sense.
73 - use common schmorp.h header.
74 - allow integers (file descriptors) in addition to file handles.
75 - take advantage of linux' eventfd (but it seems slower on smp?).
76 - use poll not select on posix platforms.
77
783.261 Wed Jul 1 10:11:51 CEST 2009
79 - more 0S X workarounds (patch by Tokuhiro Matsuno).
80
813.26 Tue Jun 30 09:33:26 CEST 2009
82 - 0S X of course claims to be posix 2008 but lacks posix_fadvise.
83 try to work around this horribly broken OS in a somewhat hackish
84 way. might help other os's too.
85
863.25 Sat Jun 27 05:18:26 CEST 2009
11 - added IO::AIO::fadvise and IO::AIO::sendfile. 87 - added IO::AIO::fadvise and IO::AIO::sendfile.
12 - (libeio) replaced quicksort+insertion sort by a tuned radix 88 - (libeio) replaced quicksort+insertion sort by a tuned radix
13 sort + insertion sort, resulting in comparable runtime (usually 89 sort + insertion sort, resulting in comparable runtime (usually
14 faster) to the old version, but without any ill side effects on 90 faster) to the old version, but without any ill side effects on
15 degenerated (for quicksort) data. 91 degenerated (for quicksort) data.

Diff Legend

Removed lines
+ Added lines
< Changed lines
> Changed lines