Re: iSCSI: DataRN

[Santosh Rao <santoshr@cup.hp.com>]

Santosh Rao wrote:

> julian_satran@il.ibm.com wrote:
>
> >
> > The above is correct if the digest error or connection failure occurred on
> > delivery of the command. If a digest error were to be detected by an
> > initiator on the response PDU (by which time the target has already
> > completed the operation and the TCP layer at the initiator has already
> > sent the ACK), then, the command is complete from the device perspective
> > and should not be retried.
> >
> > <js> how would that happen ? </js>
>
> Julian,
>
> If the initiator detected a digest error on the Response PDU[and the target
> has completed all or part of the data phase], such an operation cannot be
> retried without a prior rewind command, in the case of sequential media.
>
> The iSCSI layer cannot retry commands destined to sequential media when there
> is a possibility that some or all of the data phase is complete.
>
> Regards,
> Santosh

Before anybody points out StatSN and the fact that a target need not re-do the
operation but just send the Status, based on the un-acknowledged StatSN, do take
note of the fact that status recovery is optional. The initiator does NOT know
if the target does support status recovery and is not guaranteed that the target
will not re-do the operation.

In the absence of such a guarantee, the initiator cannot retry the command.

- Santosh
begin:vcard 
n:Rao;Santosh 
tel;work:408-447-3751
x-mozilla-html:FALSE
org:Hewlett Packard, Cupertino.;SISL
adr:;;19420, Homestead Road, M\S 43LN,	;Cupertino.;CA.;95014.;USA.
version:2.1
email;internet:santoshr@cup.hp.com
title:Software Design Engineer
x-mozilla-cpt:;21088
fn:Santosh Rao
end:vcard