Quoting r. Sean Hefty <[EMAIL PROTECTED]>: > 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 _______________________________________________ openib-general mailing list [email protected] http://openib.org/mailman/listinfo/openib-general To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
