Re: iSCSI : Bridging missing CmdSNs and Abort I/O Error recovery

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

Matt,

Surely, an active task at a target involves some resources allocated by
the iSCSI layer firmware on the target !

Are you saying that target firmware at the SCSI Transport protocol
layer (FC, pSCSI, iSCSI) do NOT allocate ANY resources
(like in per-task data structures ) to execute a  task, and thereby,
have no clean up to perform ??

- Santosh

Matt Wakeley wrote:

> No, that would require iSCSI to interpret iSCSI commands.  There is nothing at
> the target iSCSI to clean up (except the "hole" in the command stream).
>
> The target iSCSI receives iSCSI commands and sends them to the SCSI layer,
> what is there to clean up?
>
> -Matt
>
> Santosh Rao wrote:
> >
> > Matt Wakeley wrote:
> >
> > > The target iSCSI is the only entity that has knowledge of CmdSN.  When it
> > > receives a commands, it delivers them to the SCSI layer in CmdSN order (with
> > > the CmdSN stripped off).  iSCSI does not handle the abort commands.
> >
> > The Abort Task should also involve some functionality in the iSCSI layer, which
> > is to invalidate and clean up the iSCSI resources for that task (?)
> >
> > - 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