Re: stochastic fair queueing in the elevator [Re: [BENCHMARK] 2.4.20-ck3 / aa / rmap with contest]

[Andrea Arcangeli]

On Mon, Feb 10, 2003 at 04:12:45AM -0800, Andrew Morton wrote:
> traffic, etc would be expected.   Could be that sending out a
> request which is larger than a track is saving a rev of the disk
> for some reason.

I'm guessing something on those lines yes, I doubt it's purerely in core
overhead that makes that much difference. Just for completeness, I never
read this in literature or data sheets, this is all out of pratical
experience, so we can't exclude something odd in the scsi layer, but I
very much doubt, the only thing that might explain it is to waste cpu
and we know it's not wasting it.

Andrea