SAS HARD_RESET

Elliott, Robert (Server Storage) elliott at hp.com
Thu Feb 10 13:55:01 PST 2005


* From the T10 Reflector (t10 at t10.org), posted by:
* "Elliott, Robert (Server Storage)" <elliott at hp.com>
*
There is no way to instruct a target to send HARD_RESET.  In table 57
(in sas1r08) notice that T is not listed as a possible source of the
HARD_RESET primitive - only I and E are listed.  So, if an initiator is
attached to a target, there's no way to generate it.

If an initiator is attached to an expander, you can use SMP to have the
expander send HARD_RESET to that initiator.  

It's vendor-specific how an application instructs its initiator to
behave as if it received a HARD_RESET.  The SAS wire protocol need not
be involved; this is all internal to the initiator device.

--
Rob Elliott, elliott at hp.com
Hewlett-Packard Industry Standard Server Storage Advanced Technology
https://ecardfile.com/id/RobElliott


 

> -----Original Message-----
> From: sungwon_ha at agilent.com [mailto:sungwon_ha at agilent.com] 
> Sent: Thursday, February 10, 2005 12:57 PM
> To: Elliott, Robert (Server Storage); t10 at t10.org
> Subject: RE: SAS HARD_RESET
> 
> Thanks for the great answer. 
> I have follow-up question. Can targets send HARD_RESET 
> primitive when requested by a software? In other words, 
> HARD_RESET primitive can be used whenever SCSI software wants 
> to invoke a SCSI "hard reset" condition in an SSP initiator? 
> SAM-3 in 6.3.2 specifies that "The hard reset condition 
> applies to both SCSI initiator devices and SCSI target devices."
> Thanks.
> 
> 
> 
> 
> -----Original Message-----
> From: owner-t10 at t10.org [mailto:owner-t10 at t10.org]On Behalf 
> Of Elliott,
> Robert (Server Storage)
> Sent: Thursday, February 10, 2005 7:21 AM
> To: t10 at t10.org
> Subject: RE: SAS HARD_RESET
> 
> 
> * From the T10 Reflector (t10 at t10.org), posted by:
> * "Elliott, Robert (Server Storage)" <elliott at hp.com>
> *
> > * From the T10 Reflector (t10 at t10.org), posted by:
> > * <sungwon_ha at agilent.com>
> >
> > I have a question regarding Serial Attached SCSI - 
> > 1.1(SAS-1.1) draft. 
> > In the draft, HARD_RESET primitive is defined and actions 
> > triggered by arrival of the HARD_RESET primitive are well-defined. 
> > My question is on what conditions, HARD_RESET primitive is 
> > sent. One condition can be the arrival of SMP PHY CONTROL 
> > request which specifies HARD RESET PHY OPERATION. Other than 
> > that condition, the draft does not mention when and why 
> > HARD_RESET primitive is sent. 
> > Thanks.
> 
> Expanders only send it when instructed with SMP (sent by initiator as
> requested by software).  Initiators only send it when requested by
> software.
> 
> It can be used whenever SCSI software wants to invoke a SCSI "hard
> reset" condition (as defined in SAM-3) in an SSP target device.
> 
> It can also be used when ATA software wants to clear an STP 
> affiliation
> held by another STP initiator (e.g. it keeps getting OPEN_REJECT (STP
> RESOURCES BUSY), and the STP initiator port holding the 
> affiliation (as
> reported by REPORT PHY SATA) is no longer in the SAS domain (as
> determined by the discover process).
> 
> --
> Rob Elliott, elliott at hp.com
> Hewlett-Packard Industry Standard Server Storage Advanced Technology
> https://ecardfile.com/id/RobElliott
>  
> *
> * For T10 Reflector information, send a message with
> * 'info t10' (no quotes) in the message body to majordomo at t10.org
> 
*
* 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