Wording issue with SPI-4 rev. 8

Richard Moore richard.moore at qlogic.com
Thu Jan 3 16:04:56 PST 2002


* From the T10 Reflector (t10 at t10.org), posted by:
* "Richard Moore" <richard.moore at qlogic.com>
*
Rob,

I agree with your interpretation.

The SPI-4 wording could do a better job of forcing this interpretation.
The last paragraph in 4.12.4.6.4 is almost, but not quite, clear
enough: "When QAS is enabled, the port may participate in QAS
arbitrations when attempting to connect to a port that has enabled
QAS." The problem I have with this sentence is that "QAS enabled"
is neither a bus-wide state (as might be inferred from the unqualified
"When QAS is enabled"), nor a port-specific state (as might be
inferred from "a port that has enabled QAS"). It is, as you say,
an I_T-specific bit. It would be better to replace the entire
paragraph with:

"When an initiator port and a target port have negotiated with each
other to enable QAS, either of the two ports may participate in QAS
arbitrations when attempting to connect to the other port. When a
target port has set QAS_REQ to zero in a PPR IN message to an initiator
port, both ports shall not participate in QAS arbitrations when
attempting to connect to the other port. When an initiator port and a
target port have negotiated with each other to enable QAS and
information units, that target port may issue a QAS REQUEST message to
that initiator port to release the bus after a DT DATA phase. A target
port shall not send QAS REQUEST messages to an initiator unless it has
negotiated with that initiator to enable both QAS and information
units."

Note that the current wording in 4.12.4.6.4 doesn't say whether
the target is allowed to send QAS REQUEST messages to an initiator
if the two ports have negotiated to enable IUs and disable QAS; the
last line in my paragraph does. I believe this is what the requirement
should be. 16.3.13 sort of says this, but the language there is
descriptive ("is sent") rather than prescriptive ("shall" or "shall
not"). The above change would make it clear that this is a
requirement. This change also makes it clear that a negotiation
result of QAS_REQ = 0 (sent by the target) prohibits QAS participation
by either of the two ports for the purpose of contacting the other;
the existing language doesn't.

 -- Richard Moore
    QLogic Corp.


-----Original Message-----
From: Elliott, Robert [mailto:Robert.Elliott at COMPAQ.com]
Sent: Wednesday, January 02, 2002 11:08 AM
To: t10 at t10.org
Subject: RE: Wording issue with SPI-4 rev. 8

Because the bit is I_T based:

For an initiator port, QAS_REQ=1 means "I can participate in QAS" to 
open connections to this target port.  QAS_REQ=0 means only normal
arbitration will be used for opening connections to this target port.

For a target port, QAS_REQ=1 means "I can participate in QAS" to 
open connections to this initiator port. QAS_REQ=0 means only normal
arbitration will be used for opening connections to this initiator port.

For a target port, IU_REQ=1 and QAS_REQ=1 means "I will generate 
QAS REQUEST messages" after talking to this initiator port.

For a target port, IU_REQ=0 and QAS_REQ=1 means "I will not generate 
QAS REQUEST messages" after talking to this initiator port.

*
* 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