[openib-general] How about ib_send_page() ?

[Vivek Kashyap]

On Thu, 19 May 2005, Roland Dreier wrote:

>     Vivek> The draft does allow for a negotiation per connection for
>     Vivek> the implementations that wish to take advantage of
>     Vivek> it. However, an implementation can by default choose to use
>     Vivek> a 'connected-mode MTU' e.g. 32K always. It can then, for
>     Vivek> every connection choose to, negotiate to this value and if
>     Vivek> it is not workable fall back to the UD mode and deny the
>     Vivek> connection mode. The ARP entries hold the connected mode
>     Vivek> flags thereby keeping track of the mode to use per
>     Vivek> destination.
> 
> But this means that the MTU of the link will be different for UD
> destinations (including multicast) and RC destinations, right?  Or am
> I missing something?
> 
>  - R.
> 

I should say it depends. One can utilise a setup that sets the MTU to 2044 or 
whatever is the UD MTU on the subnet for all modes. The connection will 
advertise the maximum receive MTU as this value. 

Consider a proof of concept implementation:
	1. MUST support IPoIB-UD. Call its MTU UD-MTU.
	2. The connection mode is setup to utilise UD-MTU
	3. The node therefore has only one MTU to send
	4. Since the node advertises UD-MTU as the maximum receive MTU it will
	not receive a connection packet greater than that value.

This is simple enough -- only need to add support for connected mode address 
resolution and connection setup.

Such a solution provides APM and reliable connection if that is chosen but 
not the large MTU. If the large MTU is desired then force there is a split 
between UD and connected mode MTU. 

Vivek