How do SAS self-configuring expanders self configure?

Ralph Weber roweber at IEEE.org
Thu Jan 26 21:11:10 PST 2006


* From the T10 Reflector (t10 at t10.org), posted by:
* Ralph Weber <roweber at ieee.org>
*
Rob,

I figured you would know where to find the 4x4. Congratulations.

"... and shall contain a management application client and
SMP initiator port to perform the discover process to configure
its own expander route table."

What discover process? Surely not the "... level-order (i.e.,
breadth-first) traversal of the SAS domain" specified in 4.7.1.
That would seem to be a bit over the top, particularly in the
case of an expander near the bottom of the tree.

Have the performance implications of every expander in a large
configuration doing this been reviewed lately?

All the best,

.Ralph

Elliott, Robert (Server Storage) wrote:

>* From the T10 Reflector (t10 at t10.org), posted by:
>* "Elliott, Robert (Server Storage)" <Elliott at hp.com>
>*
>A self-configuring expander is one that fills in its routing tables on
>its own, and does not expose them through REPORT/CONFIGURE ROUTING
>INFORMATION functions.
>
>4.1.5 describes the two types:
>"Expander devices with expander phys with the table routing attribute
>contain an expander route table. The expander route table may be
>configurable. An expander device with a configurable route table
>depends on a management application client within the SAS domain 
>to use the discover process (see 4.7) to configure the expander 
>route table.
>
>An expander device with expander phys with the table routing
>attribute that does not have a configurable route table shall be 
>self-configuring, and shall contain a management application client
>and SMP initiator port to perform the discover process to configure 
>its own expander route table."
>
>What more does the standard need to say?  
>
>The details of the route table implementation are vendor-specific.
>The addresses it must add (in whatever manner) are defined by 
>the discover process.
>
>One detail lacking is a way for self-configuring expanders to
>report their status with regard to error handling.  We agreed 
>to deal with that in SAS-2.
>
>We briefly discussed adding a generation count to all the
>SMP functions so a management app client would realize that
>configuration started changing since it last checked the
>REPORT GENERAL function CONFIGURING bit, but decided the
>BROADCAST (CHANGE) when configuration stops was adequate
>(it retriggers a new discover process by that app client,
>which will pick up a consistent new set of results).
>
>More than one vendor has implemented self-configuration in
>a real expander, and I haven't heard any complaints about not
>understanding what to do.
>
>--
>Rob Elliott, elliott at hp.com
>Hewlett-Packard Industry Standard Server Storage Advanced Technology
>https://ecardfile.com/id/RobElliott
>
>
> 
>
>  
>
>>-----Original Message-----
>>From: owner-t10 at t10.org [mailto:owner-t10 at t10.org] On Behalf 
>>Of Ralph Weber
>>Sent: Thursday, January 26, 2006 4:10 PM
>>To: T10, Reflector
>>Subject: How do SAS self-configuring expanders self configure?
>>
>>* From the T10 Reflector (t10 at t10.org), posted by:
>>* Ralph Weber <roweber at ieee.org>
>>*
>>I have been told several times that SAS-1.1 (and by inference SAS-2)
>>define how self configuring expanders do their self configuration
>>thing. I have taken a stab at finding this definition:
>>
>>  http://www.t10.org/ftp/t10/document.06/06-087r0.pdf
>>
>>The only 'self-configuring expander devices shall ...' I can find
>>in SAS-2 (give or take a few words) is:
>>
>>  Self-configuring expander devices shall originate a BROADCAST
>>  (CHANGE) when they are done configuring.
>>
>>Anyone with greater insight than I, is welcome to engrave the SAS-2
>>clause number for the location of these mythical self configuration
>>requirements on a 4x4 and beat me about the head and 
>>shoulders with it.
>>
>>On the other hand, the next person who claims that SAS-x defines how
>>self configuring expanders work is advised to arrive with such a 4x4
>>in their hip pocket in order to have any hope of being taken 
>>seriously.
>>
>>All the best,
>>
>>.Ralph
>>
>>
>>*
>>* 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
>
>
>
>  
>

*
* 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