interrupt coalescing / polling

John Plevyak jplevyak@inktomi.com
Fri Feb 26 02:08:15 1999


I am considering studying the interrupt overhead on the receive side.
I'll keep you informed.

What do you think about under high load avoiding the interrupts 
entirely and running off the timer interrupt?

Is there a configuration variable to turn off receive interrupts?

On Fri, Feb 26, 1999 at 12:36:30AM -0500, Donald Becker wrote:
> On Thu, 25 Feb 1999, John Plevyak wrote:
> 
> > Does the Intel EthreExpress Pro do interrupt coalescing and
> > does the driver support this?
> 
> The "firmware" hidden inside the chip supposedly has a sophisticated
> interrupt optimization for receives, but this is hidden from the driver.
> I've never done cycle-by-cycle timings to confirm this.
> 
> The Tx routine avoids generating interrupts, except when it empties the Tx
> queue.
> 
> Donald Becker					  becker@cesdis.gsfc.nasa.gov
> USRA-CESDIS, Center of Excellence in Space Data and Information Sciences.
> Code 930.5, Goddard Space Flight Center,  Greenbelt, MD.  20771
> 301-286-0882	     http://cesdis.gsfc.nasa.gov/people/becker/whoiam.html
> 

-- 
John Bradley Plevyak,    PhD,    jplevyak@inktomi.com,     PGP KeyID: 051130BD
Inktomi Corporation,  1900 S. Norfolk Street,  Suite 110,  San Mateo, CA 94403
W:(415)653-2830 F:(415)653-2801 P:(888)491-1332/5103192436.4911332@pagenet.net