lkml.org 
[lkml]   [2000]   [Mar]   [10]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: new IRQ scalability changes in 2.3.48
> >> The current default for dp264 should be ok at lest for 2-way and maybe ok
> >> for 4-way too (max number of CPU supported by dp264).
> >
> >Eh. It still seems sloppy.
>
> 2-way is fine here. 4-way I don't know yet :)
>
I have to agree with Richard here. From what I've been told, it's
fairly "expensive" for an Alpha to "jump" for an IRQ interrupt and
not get it - i.e. wasted time. If the code exists to support it, the
"default setup" at init time could be to assign IRQs rotating
through the list of CPUs. This way no IRQ would be sent to more than
one CPU (if I'm understanding correctly how all this works)
therefore incurring no wasted cycles.

larry




______________________________________________________________________
Larry Sendlosky ATS
larry@scrugs.lkg.dec.com (978) 506-6640 Compaq
----------------------------------------------------------------------

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/

\
 
 \ /
  Last update: 2005-03-22 13:57    [W:5.832 / U:0.232 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site