Re: current multi-task abort model in RFC 3720

-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

On Feb 18, 2006, at 10:16 PM, T.Krishnanand wrote:

> Folks,
>
> I'm aware that a new multi-task model is being discussed on the mlist
> these days. But the following questions are based on the CURRENT
> RFC3720 model...and what initiators support TODAY.
>
> Consider a scenario where multiple iSCSI initiators are sharing a
> READ-ONLY (no SCSI reservations) access to a common LUN which has
> advertized TAS=1 control mode page setting.
>
> If LUN-reset from init-A and init-B happen on same lun then is it  
> OK if
> LUN-reset response to init-B TM cmd is sent AFTER "task aborted" scsi
> status is sent to init-B for tasks aborted becoz of init-A's
> LUN-reset.
>
> IMHO after receiving the TM response wont init-B think that ALL
> outstanding tasks are aborted and hence MAY be surprised to recv scsi
> status for tasks which were outstanding when the LUN-reset was issued
> from init-B.

I'm not fully clear what the issue is, but I think that you are  
describing an initiator that does not understand TAS=1. With TAS=1,  
tasks don't silently disappear. So you will get abort status on all  
of them, regardless of which initiator triggered the abort.

> IMHO think this scenario should be handled as follows, plz confirm if
> my understanding is correct.
>
> 1)  start processing LUN-reset from init-A
> 2)  send TM response to init-A AFTER sending out "task aborted" scsi
> status for tasks of init-B that were outstanding.
> 3) start processing LUN-reset from init-B. (At this time all init-B
> tasks aborted by init-A's LUN-reset have been notified to the init-B).

I think that is what targets will do today.

One major aspect of the discussion is what exactly is meant by,  
"sending out," in your step 2. Does it mean that we have assigned  
status to the task and we have passed a SCSI Command Response to the  
tcp stack, or does it mean that we have done that and further that we  
know the initiator has responded it has received the status?

On a data-center SAN with working initiators, it doesn't make much  
difference. Add the public internet and/or ill initiators and it  
becomes problematic.

Take care,

Bill
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.1 (Darwin)

iD8DBQFD+2wVDJT2Egh26K0RAtLdAJ4zxQUjmXYC4+ewW1fiAI7Xy+KwtwCdEjtP
vC+p34JTdPPt3SQG65mAYEw=
=FFyo
-----END PGP SIGNATURE-----

_______________________________________________
Ips mailing list
[email protected]
https://www1.ietf.org/mailman/listinfo/ips