Bidirectional transfers in SPI-4

Mark.Heath at seagate.com Mark.Heath at seagate.com
Mon Oct 23 07:04:12 PDT 2000


* From the T10 Reflector (t10 at t10.org), posted by:
* Mark.Heath at seagate.com
*
Bill Galloway wrote:

> I can not find it in spi-4 right now but all commands were supposed to be
> blown away if you change the IU_REQ bit.  If you sent the command out with a
> command IU and drop out of packetized then the target cannot describe the
> 16-bit tag and 64-bit lun on the reconnection.

It certainly makes sense that this is how things ought to work, but I too
am uable to find this "abort all tasks on IU_REQ change" requirement
described in either SPI-3 or SPI-4.  Can someone point me to the correct
place in the standard?

Thanks,

Mark Heath
Seagate Technology

*
* 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