RE: iSCSI: Flow Control

[Michael Krause <krause@cup.hp.com>]

At 08:22 PM 10/2/00 -0700, Jim McGrath wrote:
>I agree with Peter.
>
>We should allow immediate data, but only up to a limit previously set by the
>target (so we have a chance that it is received).  But the target has to be
>given the ability to dynamically change (in Peter's terms, advertise) the
>resources available, and be able to do it selectively (i.e. to one initiator
>and not another).  This inability to change the resources deployed for this
>purpose over time is why current schemes are not implemented (no target
>wants to get "caught" and so drastically underadvertizes the actual
>resources it has available).

Agree as well.  The question is does one only do this at connection set-up 
time or does one define a iSCSI operation that performs session option 
negotiation at any time within a session's lifetime.  Also if multiple 
connections are supported, is this negotiation per TCP 
connection?  Recommend doing this per connection within a session and 
allowing resources per connection and resource to vary even between the 
same endnode pair.

Mike