Re: storage-device QoS [was: IPS Draft Charter update]

[john wilkes <wilkes@hplajw.hpl.hp.com>]

Mark,

Like you, I believe that defining - and controlling - the QoS
specification for a storage device is indeed an interestingly
different problem than doing the same thing for network traffic.
Indeed, we've been researching this topic for some time now :-).  (See
<http://www.hpl.hp.com/SSP> for a little more data.)

However, I'd suggest that storage device QoS specification seems to be
outside the immediate scope of the IPS work.  This seems clearly
focussed on achieving transport of existing block storage protocols
(such as SCSI) across an IP-based network.

Expressing - and controlling - storage device QoS seems to be
something that might better be pursued in the T10 forum, where it
would probably show up as extensions to the SCSI device mode pages.
Given that changing SCSI itself is expressly outside the scope of the
IPS WG charter, this seems to place this issue outside it's scope too.

  john