[openib-general] Re: user_mad: large rmpp length problem

[Michael S. Tsirkin]

Quoting r. Sean Hefty <mshefty at ichips.intel.com>:
> Subject: Re: user_mad: large rmpp length problem
> 
> Hal Rosenstock wrote:
> >>This may work.  I think that there may be issues with respect to providing 
> >>proper synchronization and handling retries, but without looking at an 
> >>implementation, I can't be sure.
> > 
> > Possibly timeouts too. I would prefer to take this a step at a time. I
> > think that allocating some number of page sized chunks is likely to work
> > and IMO we should first go down this direction. If this proves
> > problematic, we can then adjust the strategy.
> 
> Even if the copy to the kernel were deferred on the send side, the receive side 
> will still fully reassemble the MAD before giving it to a client.  The receive 
> MAD will consume multiple data buffers, rather than a single buffer.  But it 
> will still result in consuming kernel memory, and more than that required on the 
> send side because of duplicated headers.
> 
> - Sean
> 

Right, that would have to be handled too, at least at some point.

-- 
MST