Date: Mon, 13 Oct 2014 18:42:11 +0200 From: =?ISO-8859-1?Q?Olivier_Cochard=2DLabb=E9?= <olivier@cochard.me> To: "George V. Neville-Neil" <gnn@freebsd.org> Cc: svn-src-head <svn-src-head@freebsd.org>, svn-src-all <svn-src-all@freebsd.org>, src-committers <src-committers@freebsd.org> Subject: Re: svn commit: r272906 - in head/sys: conf libkern netpfil/pf sys Message-ID: <CA%2Bq%2BTcpt0zEbgu_LndZb4dzh=xykHvppeykuiG6P9cTJgDGeWw@mail.gmail.com> In-Reply-To: <201410101926.s9AJQRY1049602@svn.freebsd.org> References: <201410101926.s9AJQRY1049602@svn.freebsd.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On Fri, Oct 10, 2014 at 9:26 PM, George V. Neville-Neil <gnn@freebsd.org> wrote: > Author: gnn > Date: Fri Oct 10 19:26:26 2014 > New Revision: 272906 > URL: https://svnweb.freebsd.org/changeset/base/272906 > > Log: > Change the PF hash from Jenkins to Murmur3. In forwarding tests > this showed a conservative 3% incrase in PPS. > > It's not easy to measure 3% of difference ;-) My benchs didn't reach to measure it (about 2000 flows of minimum packet-size, result displayed in packet-per-second): In state-full: x 272685.pf-statefull + 273009.pf-statefull +----------------------------------------------------------------------+ |x x + + xx x ++ +| | |__________________A_________M_______| | | |____________A_M___________| | +----------------------------------------------------------------------+ N Min Max Median Avg Stddev x 5 1297273 1332110 1329176 1321089.2 14527.702 + 5 1324108 1351078 1336257 1335044.2 10562.448 No difference proven at 95.0% confidence Neither in stateless: x 272685.pf-stateless + 273009.pf-stateless +----------------------------------------------------------------------+ |x x + x+ x x + + +| | |_______________M_A________________| | | |__________________________A_________________________| | +----------------------------------------------------------------------+ N Min Max Median Avg Stddev x 5 1311342 1316466 1313645 1313898.6 2378.5845 + 5 1312893 1320772 1316878 1316927.4 3607.1013 No difference proven at 95.0% confidence Regards, Olivier
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?CA%2Bq%2BTcpt0zEbgu_LndZb4dzh=xykHvppeykuiG6P9cTJgDGeWw>