Re: Command Queue Depth (was asymmetric/Symmetric)

[csapuntz@cisco.com]

Jim McGrath <Jim.McGrath@quantum.com> writes:

> The path I'd recommend is to allow people to oversubscribe a target's
> resources, and then to do a graceful recovery when that gets you into
> trouble.
> 
> Note that drive designers do this all of the time - we tend to optimize for
> common cases, and then worry about how to handle outlyers using other
> mechanisms.  While a more complicated model, it gets you the best overall
> resource utilization.  We use read on arrival, ECC on the Fly, Retrys, auto
> reallocation, all in attempts to handle the common path quickly and the rare
> path more slowly, where the differences are error rates.  
> 
> In this case I would allow initiators to send down data immediately  - when
> that works (like when ECC on the Fly works) you get a benefit.  If packets
> are dropped you can rely on existing mechanisms to recover, or you can put
> in a new, improved, and perhaps more friendly process.  In either case I
> think the result would probably be better than a tight credit based model
> where a lot of delays would be introduced and a lot of (historically
> unresolved) allocation policy issues arise.

For oversubscribing command queues, is the TASK SET FULL error condition
sufficient?

For oversubscribing unsolicited data sent with WRITES, the current spec
allows the target to drop such immediate data and issue RTTs.

-Costa