On Wed, Jun 28, 2017 at 05:48:33PM +0300, Sagi Grimberg wrote: > > > > > I hope that we are done. > > > > https://patchwork.kernel.org/patch/9808615/ > > > > > > You have a bogus empty line change there. > > > > If I remember correctly, It was needed to silence checkpatch. > > So it should not be a part of the patch. > > Also, I think that the statement is _really_ unnecessary: > > "* Setting it to "true" will allow to mimic with IB devices, > * the slow memory registration of iWARP devices." > > And, its simply not true. Its designed to test the rw logic for > sg patterns that would normally not be registered. The fact > that iWARP registers memory for rdma reads is completely orthogonal. > > And this statement is not true either: > > "* This parameter is useful for new ULP bringup > * and/or conversion to this R/W API." > > Its designed to test the code itself, not for ULP > bringup or conversion, although it is useful for that. > > And, I can't say that I 100% agree with not making it > configurable, but since you insist so much, at least > give a proper description. No problem, I'll send updated version. Thanks
Attachment:
signature.asc
Description: PGP signature
