Hi Richard, > -----Original Message----- > From: Richard Cochran [mailto:richardcochran@xxxxxxxxx] > Sent: Tuesday, June 5, 2018 9:58 PM > To: Y.b. Lu <yangbo.lu@xxxxxxx> > Cc: netdev@xxxxxxxxxxxxxxx; Madalin-cristian Bucur > <madalin.bucur@xxxxxxx>; Rob Herring <robh+dt@xxxxxxxxxx>; Shawn Guo > <shawnguo@xxxxxxxxxx>; David S . Miller <davem@xxxxxxxxxxxxx>; > devicetree@xxxxxxxxxxxxxxx; linuxppc-dev@xxxxxxxxxxxxxxxx; > linux-arm-kernel@xxxxxxxxxxxxxxxxxxx; linux-kernel@xxxxxxxxxxxxxxx > Subject: Re: [PATCH 09/10] dpaa_eth: add support for hardware timestamping > > On Tue, Jun 05, 2018 at 03:35:28AM +0000, Y.b. Lu wrote: > > [Y.b. Lu] Actually these timestamping codes affected DPAA networking > performance in our previous performance test. > > That's why we used ifdef for it. > > How much does time stamping hurt performance? > > If the time stamping is compiled in but not enabled at run time, does it still > affect performace? [Y.b. Lu] I can't remember and find the old data since it had been a long time. I just did the iperf test today between two 10G ports. I didn’t see any performance changes with timestamping code 😊 So, let's me remove the ifdef in next version. Thanks a lot. > > Thanks, > Richard ��.n��������+%������w��{.n����z�{��ܨ}���Ơz�j:+v�����w����ޙ��&�)ߡ�a����z�ޗ���ݢj��w�f
