On Sat, 21 Mar 1998, Bruce Momjian wrote:
> > Secondly, the select() backoff patch I am working on starts out with a zero
> > timeout and backs off incrementally by increasing the timeout value on
> > subsequent iterations. The idea is to break up convoys and avoid big piles of
> > processes pounding on a spinlock. This cannot be done with sched_yield().
>
> Hard to beat the backoff argument. I vote we only use select().
I haven't heard any compelling arguments so far as to why
sched_yield() is better then select(), so I tend to vote the same way...
Marc G. Fournier
Systems Administrator @ hub.org
primary: scrappy@hub.org secondary: scrappy@{freebsd|postgresql}.org