| Age | Commit message (Collapse) | Author |
|
Signed-off-by: David Lamparter <equinox@opensourcerouting.org>
|
|
When we have no contention on the seqlock, we shouldn't incur the cost
of syscalls.
Signed-off-by: David Lamparter <equinox@opensourcerouting.org>
|
|
This is mostly relevant for Solaris, where config.h sets up some #define
that affect overall header behaviour, so it needs to be before anything
else.
Signed-off-by: David Lamparter <equinox@diac24.net>
|
|
Manually tested rather extensively in addition to included unit tests,
should work as intended.
NB: The OpenBSD futex() code is "future"; it's not actually in OpenBSD
(yet?) and thus untested.
Signed-off-by: David Lamparter <equinox@opensourcerouting.org>
|