Re: 2.1.111: IDE DMA disabled?

Gerard Roudier (groudier@club-internet.fr)
Thu, 30 Jul 1998 19:04:05 +0200 (MET DST)


On Wed, 29 Jul 1998, Doug Ledford wrote:

> 2) Quantum drives are horrible about having firmware that will break when
> pushed to the limit of their queue depth on a regular basis.

How do you want a drive to guarantee a fixed maximum of tagged commands
in multi-initiator environment ?
So, expecting T10 to recommend a fixed maximum tagged command depth is
just dreaming in my opinion.

Donnot know about the cheesy Fireballs, but the Atlases used to return
QUEUE FULL even sometimes with 0 command disconnected when they are
flooded with short IOs and write caching is enabled.
I have done very heavy testing of the Atlases with latest ncr53c8xx driver
and never had had troubles, but just the syslog being flooded with QUEUE
FULL warning messages.
No breakage even with the L912 and LYK8 firmwares.
Am I just lucky or really fortunate ? ;-)

BTW, I like the QUANTUM Atlas firmwares.

Gerard.

-
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.altern.org/andrebalsa/doc/lkml-faq.html