[openib-general] putting in dead wood for DAPL and similar abomination

James Lentini jlentini at netapp.com
Wed Mar 2 08:11:35 PST 2005



hch> Please don't put in things like the address translation service or
hch> memory windows for DAPL folks.  The IB code in the kernel already
hch> has far too much unused stuff and adding more will not go past reviews
hch> for kernel inclusions - as will DAPL itself exactly because of such
hch> utter stupidities.  Similar hint to the NFS over RDMA folks at CITI -
hch> if you want your stuff to go in use the openib helper directly below
hch> the transport switch - differnet RDMA transports are too diverse to
hch> be sanely abstracted out and DAPL does a horrible job at that.  

DAPL has been efficiently supported on top of InfiniBand, iWARP, the 
Virtual Interface Architecture, Quadrics, and Myrinet.

hch> If we need to consolidate code for differnt transports we can put 
hch> it into a library later on.



More information about the general mailing list