Re: ORBS Elevator...

From: Andre Hedrick (andre@linux-ide.org)
Date: Sat Jul 29 2000 - 11:28:35 EST


It is one platter and a pair of heads.
I will know the discrete track/sector arrangements.
This is the first case where the "elevator" an be used as a strong boost.

Cheers,

On Sat, 29 Jul 2000, Andi Kleen wrote:

> On Sat, Jul 29, 2000 at 04:39:45PM +0200, Andrea Arcangeli wrote:
> > It's not obvious to me that the additional information will help
> > performance significantly, but I'll be glad to give it a try and to run
> > some benchmark to see if it helps significantly.
>
> It would certainly be useful for speeding up fsck, if you could teach it
> to run parallel on all spindles of the disk (e2fsck only knows how to
> run parallel on multiple disks, and even that breaks with raid/lvm)
> A generic interface to give user space information about on what parts
> of a blockdevice they can run in parallel without too much seek overhead
> would be very nice (I believe XFS is trying to do something similar to
> optimize its IO performance)
>
>
> -Andi
>

Andre Hedrick
The Linux ATA/IDE guy

-
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/



This archive was generated by hypermail 2b29 : Mon Jul 31 2000 - 21:00:30 EST