Thread Links Date Links
Thread Prev Thread Next Thread Index Date Prev Date Next Date Index

Re: [RPRWG] MSC study groups: memory channel and RPR on the backplane



David,

Please forward this to bob.davis and the MSC reflector.

I am not sure that I will be able to attend especially
given the delta from east to west coast time.

I strongly object to any concept of MSC doing an RPR
in the datacenter project.

I personally believe that RPRontheBackplane is not
within the scope of LMSC, whereas a networking
standard which is the basis of the datacenter
design does fall within our scope.

The RPRWG extended a courtesy to you and by extension
the MSC to investigate RPRontheBackplane. My personal
concern is confusion in the marketplace between
RPR networking standards and other RPR-derived standards.
RPR in the datacenter is in my opinion a networking
standard.

cheers,

mike

David V James wrote:
> To:  MSC
> Cc:  P802.17 WG
>      Bob Grow
> FYI: sync-e
>
> All,
>
> Please forward this to whomever you deem appropriate. These topics are
> intended to be open to all, but I hate to flood uninterested mailboxes.
>
> As background, the MSC is similar to the LMSC, in that MSC sponsors
> standard projects. Most noteable are IEEE 754 Floating Point
> and IEEE 1394, and other microprocessor standards. More information
> is available at: http://grouper.ieee.org/groups/msc/.
>
> Bob David (MSC Chair) and myself have scheduled a teleconference, to
> discuss the following, in preparation for the following MSC meeting,
> which occurs on 2004Apr12.
>
>   14:30 -- 1) Memory channel interface PAR
>   15:30 -- 2) RPR on the backplane PAR
>   16:30 -- 3) Discussion of OUIs: uniqueness and MSC assignments
>
> From a formality perspective, topics (1) and (2) are study group
> meetings; topic (3) is an adhoc meeting of (potentially) interested
> parties.
>
> For those that wish to come in person:
>   1001 Bayhill drive, #180 San Bruno, CA 90466
>   Host: 650-624-4715, leonard.tsai@xxxxxxxxxx
>   Near the El Camino exit off Hwy 380, directions come later.
>
> Conference facilities through freeconference.com:
>   Date: Friday, April 02, 2004
>   Start Time: 2:30 p.m. Pacific Std Time
>   End Time: 5:25 p.m. Pacific Std Time
>   Participants: 25
>   Type of Conference: Web-Scheduled Standard
>   Dial-in Number: 1-702-835-5000  (Las Vegas, Nevada)
>   Participant Access Code: 159617
>
> On topic (1), Bob Davis will be providing material for discussion.
>
> On topic (2), some rough ideas for the PAR include the following:
>
>   Based on the PRP draft, which includes:
>     resilience, spatial reuse, some plug&play, some service classes
>   Extensions that are needed:
>     clarity of rate-counts and fairness
>     elimination of burdensome options
>     complete plug&play, complete bandwidth guarantees
>   New facilities mandated by the environment:
>     low latency (pre-emption, perhaps)
>     synchronous services (compatible with sync-ethernet)
>     destination-asserted reverse flow control
>     backplane PHYs (perhaps leveraged from 802.xx)
>     low-overhead shared memory primitives
>   With the existing RPR PHYs, and the existing/enhanced RPR services,
>     this should also meet the needs of RPR in-the-data-center.
>
> More details and document will be provided.
> RSVPs requested, so sufficient seats and phone-ports will be
> available.
>
> DVJ
> MSC Secretary &
> RPR on the backplane study group chair
>
>
> David V. James
> 3180 South Ct
> Palo Alto, CA 94306
> Home: +1.650.494.0926
>       +1.650.856.9801
> Cell: +1.650.954.6906
> Fax:  +1.360.242.5508
> Base: dvj@xxxxxxxxxxxx


--
Michael Takefman              tak@xxxxxxxxx
Distinguished Engineer,       Cisco Systems
Chair IEEE 802.17 Stds WG
3000 Innovation Dr, Ottawa, Canada, K2K 3E8
voice: 613-254-3399       cell:613-220-6991