> To be honest I don't have an answer. The thought of this passed my mind but > yet it has an exported API in the kernel - I wonder why. So what do you > think of using vmalloc in this case?
If you're going to use vmap(), then you might as well use vmalloc(). the issue is with consuming address space, which is very limited on 32-bit systems (there is often less than 128 MB of vmalloc available total). However in this case it is probably OK. I guess we don't want to allocate these structures independently and take another pointer deref for every send -- although I would be curious to know if it actually costs much. - R. _______________________________________________ general mailing list [email protected] http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
