Interrupt latency problems

[Paul Richards]

On Sat, 2003-05-10 at 18:01, Poul-Henning Kamp wrote:
> In message <1052585648.27195.19.camel at cf.freebsd-services.com>, Paul Richards w
> rites:
> 
> >I'm not sure it's as simple as Giant though. We have a great big Giant
> >in 4.X and I don't see the same problem there.
> 
> It is Giant.
> 
> The Giant we have in 4.X is mitigated by SPL levels in the kernel.
> -current has Giant and no SPL levels.
> 
> And I know this is a tall request for you Paul, but anyway: Please don't
> argue if you don't have facts.

I'm a little tired of your attitude towards people who are just trying
to hold discussions so they can better understand the problems, even if
they don't fully understand them initially.

If you can't be bothered to take the time to do that then just don't
reply at all instead of trying to put people down all the time.

It seemed to me a reasonable question to ask why Giant in current
doesn't degrade to the big lock we had before but your explanation does
little to help me understand that. Fortunately, Bosko was willing to
take the time to provide an explanation so now I understand better.

-- 
Paul Richards