What do people think about adaptive polling?

Victor Balada Diaz victor at bsdes.net
Mon Dec 11 02:38:55 PST 2006


On Sun, Dec 10, 2006 at 09:48:24PM -0800, Matthew Dillon wrote:
>     This isn't something I'm working on, but I'd like people's opinions
>     on the idea.
> 
>     Our biggest problem with new hardware is with interrupt routing. 
>     While I do want DragonFly to be able to route interrupts properly,
>     I think we need something in the OS that deals with interrupt routing
>     failures.
> 
>     The idea is to be able to do an end-run around systems with broken
>     interrupt routing by instituting adaptive polling.  Basically all
>     devices that can produce events are polled at some reasonable minimum
>     rate, say 50hz.  When polled, the device returns an indication as to
>     whether it processed any new events or not.  A TRUE indication increases
>     the poll rate for that device, up to some reasonable maximum, and a
>     FALSE indication decreases the poll rate, down to some reasonable
>     minimum.

It's a good idea but i think that it could be improved:

For devices with working interrupts if a device starts generating
too many interrupts, just switch to polling mode.

This would be very useful for things like network cards which
could switch from interrupt to polling mode on the fly and get
better performance with higher load.

-- 
La prueba más fehaciente de que existe vida inteligente en otros
planetas, es que no han intentado contactar con nosotros. 





More information about the Kernel mailing list