Re: pthread_rwlock starvation

[Sad Clouds <cryintothebluesky%googlemail.com@localhost>]

On Sat, 17 Apr 2010 15:11:42 -0400
Matthew Mondor <mm_lists%pulsar-zone.net@localhost> wrote:

> However, I seem unable to reproduce the problem on a uniprocessor
> netbsd-5 (i686 optimized on 32-bit hardware) using the test case you
> posted.
> -- 
> Matt

Yes you probably need to run it on SMP machine. Sometimes it takes
several minutes before it hits the corner case and one of the CPUs sits
idle for many seconds.