Re: Btree runtime recovery. Stuck spins.

On Fri, Feb 09, 2001 at 01:23:35PM -0500, Tom Lane wrote:
> Bruce Momjian <pgman(at)candle(dot)pha(dot)pa(dot)us> writes:
> > Our spinlocks don't go into an infinite test loop, right? They back off
> > and retest at random intervals.
>
> Not very random --- either 0 or 10 milliseconds. (I think there was
> some discussion of changing that, but it died off without agreeing on
> anything.) ...

I think we agreed that 0 was just wrong, but nobody changed it.
Changing it to 1 microsecond would be the smallest reasonable
change. As it is, it just does a bunch of no-op syscalls each time it
wakes up after a 10ms sleep, without yielding the CPU.

Nathan Myers
ncm(at)zembu(dot)com