Question on Target initiated negotiations...

Skip Jones sk_jones at qlc.com
Thu Jun 1 10:51:19 PDT 1995


Rick,

I believe you have a valid assumption that wide HA's are smart enough to handle
Target Initiated Negotiations.  At least from my camp it's a safe assumption.

Skip Jones
QLogic
_______________________________________________________________________________
From: Rick Roche, 508-770-6351 on Wed, May 31, 1995 9:45 PM
Subject: Question on Target initiated negotiations...
To: "SCSI at wichitaks.ncr.com"@SHRDNS.enet.qntm.com
Cc: STEPH at shrdns.tdh.qntm.com; KEVIN at shrdns.tdh.qntm.com;
MATT at shrdns.tdh.qntm.com; DJ at shrdns.tdh.qntm.com; ROCHE at shrdns.tdh.qntm.com


    Hi,

    We are revisiting the initiate negotiation question on our disk
    products and we wanted to query the reflector audience for their
    input.

    Currently, we DO NOT initiate synchronous negotiation since some
    early host adapters didn't respond very well to the behavior.  One
    concern with this behavior is an adapter which doesn't re-negotiate on
    check conditions status may result in a sync host with and Async target.
    We do allow for target initiated negotiations to be enabled through
    a mode page control bit, but it's defaulted off.

    One proposal is to turn initiate on for wide negotiations based on
    the argument that most (all?) wide adapters must be more advanced
    and probably handle target initiated negotiations fine.  Is this
    a reasonable assumption?  Do people know of drives which do initiate
    negotiations by default?

    Comments?

                                                        Thanks,
                                                        Rick





More information about the T10 mailing list