Wording issue with SPI-4 rev. 8

Richard Moore richard.moore at qlogic.com
Mon Jan 7 09:05:55 PST 2002


* From the T10 Reflector (t10 at t10.org), posted by:
* "Richard Moore" <richard.moore at qlogic.com>
*
Right, as I said it's a waste of time if the message is only
going to get rejected. But I think Gerry's point is that it's
possible to design an initiator (likely just a firmware change)
so that it accepts the QAS REQUEST and recognizes this as a
physical disconnect, even if the initiator doesn't implement the
QAS protocol. Unfortunately, there's only one bit available to
convey both bits of information: whether the initiator
supports the full QAS protocol, and whether the initiator
supports the QAS REQUEST message.

As far as I'm concerned, it's a toss-up as to which way
to go in response to Gerry's request. Doing what he asks may
have the effect of hurting performance on mixed (QAS + non-QAS)
buses in the short term, but if initiators upgrade their firmware
to support it, in the long run such buses will benefit.

 -- Richard Moore
    QLogic Corp.


-----Original Message-----
From: Elliott, Robert [mailto:Robert.Elliott at COMPAQ.com]
Sent: Friday, January 04, 2002 4:42 PM
To: t10 at t10.org
Subject: RE: Wording issue with SPI-4 rev. 8


* From the T10 Reflector (t10 at t10.org), posted by:
* "Elliott, Robert" <Robert.Elliott at compaq.com>
*
If the initiator doesn't negotiate QAS_REQ enabled, I'd expect an
attention condition followed by MESSAGE REJECT followed by BUS FREE,
which defeats the purpose of trying to send QAS_REQUEST.

---
Rob Elliott, Compaq Server Storage
Robert.Elliott at compaq.com

*
* For T10 Reflector information, send a message with
* 'info t10' (no quotes) in the message body to majordomo at t10.org




More information about the T10 mailing list