Draft minutes of Parallel SCSI WG - March 6, 2001

John Lohmeyer lohmeyer at t10.org
Thu Mar 8 13:20:19 PST 2001


* From the T10 Reflector (t10 at t10.org), posted by:
* John Lohmeyer <lohmeyer at t10.org>
*
These minutes are available in PDF format at: 
ftp:ftp.t10.org/t10/document.01/01-089r0.pdf

Accredited Standards Committee*
National Committee for Information Technology Standards (NCITS)

                                                       Doc. No.: T10/01-089r0
                                                           Date: March 8, 2001
                                                       Reply to: John Lohmeyer
To:        T10 Membership
From:      Ralph Weber & John Lohmeyer
Subject:   Parallel SCSI Working Group Meeting -- March 6, 2001
            Dallas, TX

Agenda
1.     Opening Remarks
2.     Approval of Agenda
3.     Attendance and Membership
4.     SPI-4 Topics
4.1      SPI-4 Physical Topics
4.1.1      Proposal for Ultra320 AAF receiver input signal specification for
SPI-4 (00-400 & 00-408) [Brown]
4.1.2      Receiver Response Requirements (00-332) [Ham]
4.1.3      Periodic structures on SCSI buses (00-352) [Barnes]
4.1.4      Minimum drive levels (01-094) [Bridgewater]
4.2      SPI-4 Protocol Topics
4.2.1      Proposed changes to SPI IU exception handling (00-384) [Srinivasan]
4.2.2      SPI-4: SCC Subpages for SPI initiator negotiated settings (01-066)
[Elliott]
4.2.3      Paced Timing Protocol Clarification (e-mail)
4.2.4      Streaming Clarification (e-mail)
4.2.5      QAS Question (e-mail)
4.2.6      Corrections to SPI-4 Driving and Asserting SCSI Signals (01-096)
[Moore]
4.2.7      Packetized CRC Intervals (01-097) [Moore]
4.3      SPI-4 working draft review [Penokie]
5.     New Business
6.     Meeting Schedule
7.     Adjournment



Results of Meeting

1.     Opening Remarks

John Lohmeyer, the T10 Chair, called the meeting to order at 9:00 a.m.,
Tuesday, March 6, 2001.  He thanked Paul Aloisi of Texas Instruments for
hosting the meeting.

As is customary, the people attending introduced themselves and a copy of the
attendance list was circulated.


2.     Approval of Agenda

The draft agenda was approved with the following changes:

4.2.3      Paced Timing Protocol Clarification (e-mail)
4.2.4      Streaming Clarification (e-mail)
4.2.5      QAS Question (e-mail)
4.2.6      Corrections to SPI-4 Driving and Asserting SCSI Signals (01-096r0)
[Moore]
4.2.7      Packetized CRC Intervals (01-097r0) [Moore]

No items were added/revised during the course of the meeting.


3.     Attendance and Membership

Attendance at working group meetings does not count toward minimum attendance
requirements for T10 membership.  Working group meetings are open to any
person or organization directly and materially affected by T10's scope of
work.  The following people attended the meeting:

          Name          S        Organization         Electronic Mail Address
---------------------- -- ------------------------- -------------------------
Mr. Ron Roberts        P  Adaptec, Inc.             Ron_Roberts at adaptec.com
Mr. Charles Brill      P  AMP / Tyco Electronics    cebrill at ix.netcom.com
Mr. Bill Mable         P  Amphenol Interconnect     mableaipc at aol.com
Mr. Vince Bastiani     V  Bass Technology           bass.tech at gte.net
                           Consulting
Mr. Robert C. Elliott  P  Compaq Computer Corp.     Robert.Elliott at compaq.com
Dr. William Ham        A  Compaq Computer Corp.     bill_ham at ix.netcom.com
Mr. Wayne Bellamy      V  Compaq Computer Corp.     wayne.bellamy at compaq.com
Mr. Neil Wanamaker     P  Crossroads Systems, Inc.  ntw at crossroads.com
Mr. John Tyndall       A  Crossroads Systems, Inc.  jtyndall at crossroads.com
Mr. Gary S. Robinson   P  EMC                       robinson_gary at emc.com
Mr. Ralph O. Weber     P  ENDL Texas                roweber at acm.org
Mr. Eugene Lew         P  Fujitsu                   elew at fcpa.fujitsu.com
Mr. Nathan Hastad      P  General Dynamics          nathan.j.hastad at gd-is.com
Mr. George O. Penokie  P  IBM / Tivoli Systems      gpenokie at tivoli.com
Mr. Dennis Moore       P  KnowledgeTek, Inc.        dmoore at ix.netcom.com
Mr. John Lohmeyer      P  LSI Logic Corp.           lohmeyer at t10.org
Mr. William Petty      A  LSI Logic Corp.           william.petty at lsil.com
Mr. Brian Day          V  LSI Logic Corp.           brian.day at lsil.com
Mr. Richard Moore      A# QLogic Corp.              r_moore at qlc.com
Mr. Dean Wallace       A  QLogic Corp.              d_wallace at qlc.com
Mr. Ting Li Chan       V  QLogic Corp.              t_chan at qlc.com
Mr. Richard L.         V  QLogic Corp.              r_romaniec at qlc.com
Romaniec
Mr. Mark Evans         P  Quantum Corp.             mark.evans at quantum.com
Mr. Bruce Leshay       V  Quantum Corp.             bleshay at tdh.qntm.com
Mr. Gerald Houlder     P  Seagate Technology        gerry_houlder at seagate.com
Mr. Paul D. Aloisi     P  Texas Instruments         Paul_Aloisi at ti.com
Mr. Mike Kosco         V  Texas Instruments         mike at chipcraft.com
Mr. Ron Mathews        AV UNISYS Corporation        ronald.mathews at unisys.com

28 People Present

Status Key:  P    -  Principal
              A,A# -  Alternate
              AV   -  Advisory Member
              L    -  Liaison
              V    -  Visitor


4.     SPI-4 Topics

4.1    SPI-4 Physical Topics

4.1.1  Proposal for Ultra320 AAF receiver input signal specification for SPI-4
(00-400 & 00-408) [Brown]

Bruce Leshay presented a proposal for signal characterization in Ultra320 when
AAF is used (00-400r1).  The group discussed the relationship between the
several proposed requirements, how the requirements can be observed and
measured, and how the requirements relate to a working filtering receiver.
Bill Ham expressed concerns over issues of skew and jitter.  Phone
consultation was conducted with Russ Brown who was unable to attend the
meeting owing to problems with airline flight cancellations.

Mark Evans moved that 00-400r2 (r0 as revised here) be recommended for
inclusion in SPI-4.  George Penokie seconded the motion.

Bill Ham asked that the proposal be revised to state that the requirements it
states will be used as inputs to the process of developing cable plant
requirements and after a lengthy discussion Mark Evans declined to add such a
statement in the r2 revision.  Concerns were raised about how interconnect
specifications will be derived from the receiver requirements (AAF and/or
precompensation).  It was noted that these issues were raised previously.

To verify the changes, the revision 0 contents were compared line by line with
the revision 2 contents.

The motion passed on a vote of 5:3:4.

4.1.2  Receiver Response Requirements (00-332) [Ham]

Bill Ham noted that 00-332r3 has been available since the January meeting.
Concerns were raised about the pulse width relationship between this
proposal's must reject requirement and the AAF must accept requirement.  The
proposal was revised.

Bill Ham moved that 00-332r4 (r3 as revised) be recommended for inclusion in
SPI-4.  Bruce Leshay seconded the motion.  The motion passed on a vote of
11:1:2.

George Penokie asked where the text is to be added in SPI-4 and on the
recommendation of Paul Aloisi, Bill Ham further revised r3 to state that the
text goes into the receiver section of Annex A.

4.1.3  Periodic structures on SCSI buses (00-352) [Barnes]

John Lohmeyer reported that Larry Barnes asked for discussion of this item to
be deferred to the next meeting.

4.1.4  Minimum drive levels (01-094) [Bridgewater]

Wally Bridgewater presented a proposal to change the minimum drive levels
(01-094r0).  The main request in the proposal was that the minimum drive level
be reduced from 320 mV to 185 mV.  The request was justified based on power
dissipation in protocol chips.  Questions were raised about aspects of the
model used to justify the ability to operate at the lower minimum drive level.
Wally agreed to bring a better-justified proposal to the next meeting.


4.2    SPI-4 Protocol Topics

4.2.1  Proposed changes to SPI IU exception handling (00-384) [Srinivasan]

John Lohmeyer reported that Mr. Srinivasan asked for this topic to be dropped
|from this and future agendas.

4.2.2  SPI-4: SCC Subpages for SPI initiator negotiated settings (01-066)
[Elliott]

Rob Elliott presented a proposal that would allow an initiator communicating
with a RAID controller to determine the negotiated transfer rates used by the
RAID controller to communicate with the disk drives it is using on the
secondary SCSI buses (01-066r0).  Questions were raised about how the proposal
relates to the existing model for SCC devices.  Proposed improvements to the
proposal included use of the well known LUN and/or definition of an ASC/ASCQ
to be reported as a unit attention condition.

Rob agreed to revise the proposal to be included in a future command set
related to well-known LUNs.

4.2.3  Paced Timing Protocol Clarification (e-mail)

George Penokie presented an e-mail message from Brian Day containing two
questions regarding timing specification in training for paced transfers.

        1.  SEL behavior when starting a training sequence after a reselection.
It's my understanding from section 10.7.2 that the target shall release the
SEL line two system deskews after detecting the assertion of BSY from the
initiator.  In section 10.8.4.2.2, it states that the target shall assert SEL
two system deskews before asserting REQ.  How soon after releasing SEL from
the reselection phase can a target reassert it to prepare for training?
Essentially, is there any minimum deassertion time between those two events?

The group discussed several existing requirements in this area.  Brian Day
moved that after reselection targets must release SEL for a minimum two deskew
delays before asserting SEL as described in SPI-4 subclause 10.8.4.2.2.  Bruce
Leshay seconded the motion.  In the absence of any objections, the motion was
approved unanimously.

        2.  Ending pacing transfers from DT DATA IN
 From section 10.8.4.3.4, the target negates the REQ and P1 lines once the
offset has gone to zero.  Then it states the rules in 10.13 must be followed.
Is there any minimum time restriction on the target from negating the REQ/P1
to changing the phase lines?  If the target is allowed to simultaneously
negate the REQ/P1 and change phase, the initiator may actually see a REQ in
the new phase during that switch if the cable skews the REQ "slower" than the
phase lines... which to the initiator would look like a violation of section
10.13.    I was expecting to find some requirement on the target for that, but
didn't see one.

The group discussed the how best to minimize the timing impact of the needed
change.  Brian agreed that no resolution is needed for this problem.  He's
just going to modify his product to deal with the issue.

4.2.4  Streaming Clarification (e-mail)

Brian Day reviewed an issue raised by Sriram Srinivasan.

Subclause 16.3.12.1 says "A RD_STRM bit of one indicates read streaming shall
be enabled?"   Does "shall be enabled" mean that the target shall use ONLY SPI
L_Qs  with data stream type for read data transfer or choose to use it
sometimes and choose to use data type in the SPI L_Q some other times?   In
other words, can a task, say, a SCSI read command,  be completed by  using a
combination of streaming and non-streaming reads in one or more  connections
with an initiator with whom the target has negotiated a RD_STRM bit of 1?

Sriram's email noted that the same question applies in the write streaming
case.

The group discussed the cited requirement and related requirements and
concluded that a clarification of the current text would be good.  Wording the
clarification proved to be too difficult in the meeting setting so George
Penokie agreed to work offline to write the needed non-substantive
clarification.

4.2.5  QAS Question (e-mail)

George Penokie presented a question about QAS.

What happens if the initiator on the I_T nexus detects a parity error on a QAS
message? And, to make things even more interesting, the device that wants the
bus does not see a parity error on the same QAS message?

The group reviewed the discussion of the issue as it occurred on the
reflector.  It was agreed that if the initiator detects the parity error then
it asserts ATN.  Bruce Leshay's question was, "what next?"  Bruce and George
walked through the issues that follow that question.  The conclusion of the
discussion was that the target should go bus free, with the only remaining
issue being whether it would be an unexpected bus free or not.

Bruce Leshay moved that in 10.5.4 a requirement be added that if ATN is
asserted, then the target shall go to message out, receive all the message
bytes, and the perform an unexpected bus free.  George Penokie seconded the
motion.  In the absence of any objections, the motion passed unanimously.

4.2.6  Corrections to SPI-4 Driving and Asserting SCSI Signals (01-096)
[Moore]

Richard Moore reviewed a proposal to address editor's notes 3 and 6 in SPI-4
revision 3 (01-096r0).  Revisions were requested and agreed by Richard.
Richard Moore moved that 01-096r1 (r0 as modified) be recommended for
inclusion in SPI-4.  Bruce Leshay seconded the motion.  In the absence of any
objections, the motion passed unanimously.

4.2.7  Packetized CRC Intervals (01-097) [Moore]

Richard Moore expressed concerns that the behavior is not well documented when
there are miss matches between the CRC interval and the streaming interval and
proposed changes to improve the definition of the behavior (01-097r0).  The
group discussed how best to clarify the behavior.  George agreed to correct
the first identified omission as an editorial change.

The second part of the proposal to add restrictions on iuCRC intervals met
with opposition.  Richard agreed to work on a revised proposal that would
address the objections.


4.3    SPI-4 working draft review [Penokie]

George Penokie lead a review of the editor's notes in SPI-4 revision 3.


5.     New Business

No new business was brought before the meeting.


6.     Meeting Schedule

The next meeting of the Parallel SCSI Working Group will be Tuesday May 1,
2001 commencing at 9:00 a.m. in Nashua, NH at the Sheraton Hotel
(603-888-9970).


7.     Adjournment

The meeting was adjourned at 6:25 p.m. on Tuesday, March 6, 2001.

--
John Lohmeyer                  Email: lohmeyer at t10.org
LSI Logic Corp.                Voice: +1-719-533-7560
4420 ArrowsWest Dr.              Fax: +1-719-533-7183
Colo Spgs, CO 80907

*
* 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