SAS letter ballot comment resolution teleconference Thursday 2pm Central

Sheffield, Robert L robert.l.sheffield at intel.com
Tue Mar 18 13:25:06 PST 2003


* From the T10 Reflector (t10 at t10.org), posted by:
* "Sheffield, Robert L" <robert.l.sheffield at intel.com>
*
Yes, this is required in SAS-1 as it provides further resolution to Microsoft's LB comment:

Author: MSFT
Page: 259
Sequence number: 13
Date: 3/5/2003 4:33:22 PM
Type: Note
ACCEPT - DONE (Bill Galloway's proposal added "An affiliation established when the command is transmitted should be kept until all frames for the command have been delivered. This avoids confusing the SATA device, which only knows about one SATA host. STP initiator ports may keep affiliations for longer tenures, but this is discouraged." which should help).

.3.2 SATA tunneling for multiple initiator ports
The affiliation mechanism creates a policy that encourages initiators to fight over resources. The policy that multiple initiators shouldn't be actively connecting to an STP target shouldn't be enforced by hardware. It should be a usage convention.
[key concern is resources coming and going as seen by an OS]

Bob Sheffield
Intel Corporation - CH6-333
Storage Components Division (SCD)
5000 W. Chandler Blvd
Chandler, AZ 85226-3699
Phone: 480-554-8597
Fax: 480-554-6617


> -----Original Message-----
> From: Elliott, Robert (Server Storage) [mailto:Elliott at hp.com]
> Sent: Tuesday, March 18, 2003 10:30 AM
> To: t10 at t10.org
> Subject: SAS letter ballot comment resolution teleconference Thursday
> 2pm Central
> 
> 
> 03-131r0 STP affiliation usage model   (Bob Sheffield)
> ====================================
> Is this explanatory text desired in SAS-1?
> 
*
* 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