--- Bernard Metzler, PhD Tech. Leader High Performance I/O, Principal Research Staff IBM Zurich Research Laboratory Saeumerstrasse 4 CH-8803 Rueschlikon, Switzerland +41 44 724 8605 -----"Leon Romanovsky" <leon@xxxxxxxxxx> wrote: ----- >To: "Bernard Metzler" <bmt@xxxxxxxxxxxxxx> >From: "Leon Romanovsky" <leon@xxxxxxxxxx> >Date: 04/28/2019 06:56PM >Cc: linux-rdma@xxxxxxxxxxxxxxx, "Bernard Metzler" ><bmt@xxxxxxxxxxxxxxxxxxx> >Subject: Re: [PATCH v8 09/12] SIW receive path > >On Fri, Apr 26, 2019 at 03:18:49PM +0200, Bernard Metzler wrote: >> From: Bernard Metzler <bmt@xxxxxxxxxxxxxxxxxxx> >> >> Signed-off-by: Bernard Metzler <bmt@xxxxxxxxxxxxxx> >> --- >> drivers/infiniband/sw/siw/siw_qp_rx.c | 1520 >+++++++++++++++++++++++++ >> 1 file changed, 1520 insertions(+) >> create mode 100644 drivers/infiniband/sw/siw/siw_qp_rx.c >> > >Are you sure that likely/unlikely annotations almost in every line >better than correctly written functions with success oriented flows? > >I would be glad to see any performance proof for such extensive >usage. That's almost impossible, but I can give it a try ;) I think, unlikely() statements around protocol failure checks is rather common in networking code. But let me check if I have overdone it... > >Thanks > >
