Comments on 01-316r0 - Removal of IMMED bit in Progress Indicator in SSC-2

Kevin D Butt kdbutt at us.ibm.com
Tue Oct 30 12:40:33 PST 2001


* From the T10 Reflector (t10 at t10.org), posted by:
* "Kevin D Butt" <kdbutt at us.ibm.com>
*
One thing that we need to look at related to this is the race condition
introduced with Queueing.  If an initiator sends a command like a REW and
immediately starts polling for the Progress Indication, this command may be
queued and not dequeued for execution until some time after the polling
begins.  Also, there may be multiple progress indication eligible commands
queued.  Which command does the progress indication belong to?  This race
condition needs addressed before we can resolve this proposal.

Kevin Butt
IBM Tape

*
* 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