leitner
|
c4b0dd6b81
|
move cleanup after check that all events are handled
|
4 years ago |
|
leitner
|
15f004df55
|
prevent infinite loop in cleanup code for
io_close-with-outstanding-events-queued race prevention
|
4 years ago |
|
leitner
|
69c9d1454d
|
port the epoll optimizations to kqueue, hopefully repairing it in the process
|
5 years ago |
|
leitner
|
9d51f000ef
|
silence another compiler warning
|
5 years ago |
|
leitner
|
bbaf63c7fd
|
remove compiler warnings in ent
try to fix io_waituntil2 on freebsd
|
5 years ago |
|
leitner
|
2a0bcc2fb6
|
implement deferred closing
|
8 years ago |
|
leitner
|
a1f1986247
|
include <foo> -> include "foo"
|
9 years ago |
|
leitner
|
967e3ce019
|
revert edge triggering epoll; it had reliability and fairness issues and
was also not actually faster
|
10 years ago |
|
leitner
|
d9cbb3940c
|
it turns out you don't need -1/EGAIN to know edge triggering told you
there is no more data, it's enough to read/write less than you asked for
|
11 years ago |
|
leitner
|
a544abc39c
|
switch io_fds from array to newly implemented (hopefully thread-safe) iarray
switch epoll from level triggering to edge triggering
|
11 years ago |
|
leitner
|
ff3a3410ec
|
hopefully this fixes the looping gatling processes
|
11 years ago |
|
leitner
|
e175800a8c
|
add io_fd_canwrite (like io_fd but assume the fd is writable)
save a few syscalls here and there
|
13 years ago |
|
leitner
|
1fcfcd268a
|
hups
|
16 years ago |
|
leitner
|
83c1186870
|
fix for NetBSD 3.0 (they broke their sys/types.h)
remove support for ip6.int reverse lookup in DNS routines (the domain is
no longer delegated)
|
19 years ago |
|
leitner
|
c1c50c7dbd
|
further Windoze support (test/io5.c works, gatling still doesn't)
This is just to get gatling to work, I may remove it again after
that.
|
19 years ago |
|
leitner
|
b1e8f341ba
|
no debug
|
20 years ago |
|
leitner
|
12caccfd48
|
don't shrink in array_allocate
|
20 years ago |
|
leitner
|
e1e80badf0
|
add some debug stuff
|
20 years ago |
|
leitner
|
6fb76c3cd9
|
<io.h> -> <iob.h>
|
21 years ago |
|
leitner
|
adcb7aee21
|
handle POLLNVAL (can't happen errors)
|
21 years ago |
|
sanjiyan
|
a58d400d5c
|
fixing the poll call in io_waituntil2
|
21 years ago |
|
leitner
|
a4cf7a8a8b
|
fix Solaris /dev/poll
|
21 years ago |
|
leitner
|
65adb024f5
|
bug fixing time
|
21 years ago |
|
leitner
|
82a4ae868d
|
broken lose32 port using mingw (don't use!!!)
initial Solaris /dev/poll port
|
21 years ago |
|
leitner
|
b81e8bcd27
|
typo
|
21 years ago |
|
leitner
|
17f3955f84
|
handle BSD errors
|
21 years ago |
|
leitner
|
361872ffa4
|
handle errors properly
|
21 years ago |
|
leitner
|
96be549818
|
handle errors signalled by epoll
|
21 years ago |
|
leitner
|
963fa817de
|
guard against one descriptor being flagged twice
|
21 years ago |
|
leitner
|
eaa4dea67b
|
correctly initialize records before reusing them in io_fd
do something about unexpected epoll events
|
21 years ago |
|
leitner
|
29ae01d54f
|
glibc compatibility ;)
|
21 years ago |
|
leitner
|
3dd2a0344b
|
damn!
|
21 years ago |
|
leitner
|
c64f721daf
|
oops, typo
|
21 years ago |
|
leitner
|
519b512cc3
|
kqueue does not like timeout==-1 but wants a NULL pointer to wait
indefinitely
|
21 years ago |
|
leitner
|
2a2e1ddc75
|
add sigio support
extend code to cope with edge triggered event notification
add io_eagain() so that you can notify io_wait if accept() returned EAGAIN
|
22 years ago |
|
leitner
|
dc09a17215
|
fix
|
22 years ago |
|
leitner
|
b1a8110926
|
epoll now works enough for test/io5
|
22 years ago |
|
leitner
|
325a6176ca
|
write a small socket server with io_wait integration and add and debug
io framework enough to support the test program
|
22 years ago |
|
leitner
|
8cd9323a1b
|
add waituntil and waituntil2 (internal)
|
22 years ago |