On Mon, Jul 13, 2015 at 03:36:44PM -0400, Tom Talpey wrote: > On 7/11/2015 6:25 AM, 'Christoph Hellwig' wrote: > >I think what we need to support for now is FRMR as the primary target, > >and FMR as a secondar[y]. > > FMR is a *very* bad choice, for several reasons. If an API can transparently support FMR, then I think it can also transparently support ib_get_phys_mr as an alternative, they look pretty similar... ? > Personally, I'd recommend ib_get_phys_mr() over FMR. It at least > doesn't suffer from issues 1, 2 and 4. Your comments are right for the rkey case, but for lkey, there is no security concern with using a FMR, or pooling them. It doesn't look like any iwarp drivers supports FMR, so they are certainly safe to use on IB as the lkey. This is why I am becoming more convinced that treating lkey and rkey the same is not helpful. Conversely, it looks like if we could drop ehca and mthca we could ditch FMR entirely.. Jason -- To unsubscribe from this list: send the line "unsubscribe linux-nfs" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html