SPI Packets
Leshay, Bruce
Bruce_Leshay at maxtor.com
Fri Sep 20 08:29:09 PDT 2002
* From the T10 Reflector (t10 at t10.org), posted by:
* "Leshay, Bruce" <Bruce_Leshay at maxtor.com>
*
So Bill, then are you asking if you can follow a write stream LQ with a
status LQ and then data, with no data at all following the write stream LQ?
I guess that question expands to whether it is ever legal to send a write
stream LQ and then not allow the host to send any of the data just
requested. According to the flow charts in chapter 14 of SPI4, you must
follow a SPI_LQ with the appropriate SPI_DATA, unless the host asserted ATN
during the SPI_LQ, in which case the target goes to MSG_OUT phase.
Bruce Leshay
Maxtor Corporation
-----Original Message-----
From: Bill Galloway [mailto:BillG at breatech.com]
Sent: Friday, September 20, 2002 10:53 AM
To: gop at us.ibm.com
Cc: owner-t10 at t10.org; t10 at t10.org
Subject: RE: SPI Packets
* From the T10 Reflector (t10 at t10.org), posted by:
* "Bill Galloway" <BillG at breatech.com>
*
George,
The write stream data packet is from initiator to target but the write
stream LQ is from target to initiator just like the status LQ.
Bill Galloway
BREA Technologies, Inc.
P: (281) 530-3063
F: (281) 988-0358
BillG at breatech.com
-----Original Message-----
From: owner-t10 at t10.org [mailto:owner-t10 at t10.org] On Behalf Of George
Penokie
Sent: Friday, September 20, 2002 8:21 AM
To: BillG at breatech.com
Cc: owner-t10 at t10.org; T10 Reflector
Subject: Re: SPI Packets
* From the T10 Reflector (t10 at t10.org), posted by:
* George Penokie <gop at us.ibm.com>
*
Bill,
To go from write streaming to an LQ that indicates a status type does
require a phase change. Write streaming is initiator to target. LQ
packets are always from target to initiator. Did I miss something in
your question or description??
Bye for now,
George Penokie
Dept 2C6 114-2 N212
E-Mail: gop at us.ibm.com
Internal: 553-5208
External: 507-253-5208 FAX: 507-253-2880
"Bill Galloway"
<BillG at breatech.c To: "T10 Reflector"
<t10 at t10.org>
om> cc:
Sent by: Subject: SPI Packets
owner-t10 at t10.org
09/19/02 09:08 PM
Please respond to
BillG
* From the T10 Reflector (t10 at t10.org), posted by:
* "Bill Galloway" <BillG at breatech.com>
*
I have a question about write streaming in packetized protocol.
After a reselection on a write command the drive sends a LQ packet with
the IU type set to stream. The data length is set to 512. The stream
ends when the drive changes phase or goes bus free.
>From 14.3.4 in SPI-4:
During write streaming the sequence of SPI data stream information units
shall end with any change to the C/D, I/O, or MSG signals on a SPI data
stream information unit boundary.
If during a sequence of SPI data stream information units a SCSI
initiator port detects any change to the C/D, I/O, or MSG signals after
transmitting or receiving the last iuCRC for a SPI data stream
information unit that SCSI initiator port shall consider the current I/O
process to be logically disconnected or in the case of detecting a BUS
FREE phase or a MESSAGE IN phase to be physically disconnected.
Is it legal for the drive to NOT change phase after the stream LQ and go
straight to a status LQ? Both are DT DATA IN so the drive never changes
phase.
Bill Galloway
BREA Technologies, Inc.
P: (281) 530-3063
F: (281) 988-0358
BillG at breatech.com
*
* For T10 Reflector information, send a message with
* 'info t10' (no quotes) in the message body to majordomo at t10.org
*
* For T10 Reflector information, send a message with
* 'info t10' (no quotes) in the message body to majordomo at t10.org
*
* For T10 Reflector information, send a message with
* 'info t10' (no quotes) in the message body to majordomo at t10.org
*
* 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