SPI-3 & Packetized
Bruce.Leshay at quantum.com
Fri Dec 11 05:33:50 PST 1998
* From the T10 Reflector (t10 at symbios.com), posted by:
* Bruce Leshay <Bruce.Leshay at quantum.com>
I don't agree that "DT will fail in many existing backplane designs"
- DT is not restricted
to Fast-40 speeds, it can run at whatever speed you negotiate for. DT at
Fast-10 is not very aggressive
and still has twice the throughput of ST at Fast-10.
I believe the reason for the decision boiled down to the fact that
everybody has to design major
new hardware to do packetized, and they aren't going to design that hardware
and not put in DT
capability. So there should be no device that supports packetized but
doesn't support DT, and you should
always be able to negotiate DT down to some speed at which it works.
> -----Original Message-----
> From: Lawrence J. Lamers [SMTP:ljlamers at ix.netcom.com]
> Sent: Thursday, December 10, 1998 8:46 AM
> To: gop at us.ibm.com; Lawrence J. Lamers
> Cc: t10 at Symbios.COM
> Subject: SPI-3 & Packetized
> * From the T10 Reflector (t10 at symbios.com), posted by:
> * "Lawrence J. Lamers" <ljlamers at ix.netcom.com>
> I was reviewing SPI-3 and suddenly realized that packet protocol is
> restricted to DT DATA phases. I don't remember this decision being made.
> Is there a technical reason for this?
> It is my belief that DT will fail in many existing backplane designs; if
> speed negotiate down to ST or SE we loose any CRC protection. If we
> convince the world to go packetized shouldn't it be available independant
> of the physical layer?
> Lawrence J. Lamers Adaptec, Inc
> email: ljlamers at ieee.org 691 South Milpitas Blvd.
> Phone: (408) 578-1709 Milpitas, CA 95035
> * For T10 Reflector information, send a message with
> * 'info t10' (no quotes) in the message body to majordomo at symbios.com
* For T10 Reflector information, send a message with
* 'info t10' (no quotes) in the message body to majordomo at symbios.com
More information about the T10