Date: Fri, 5 Jan 2007 10:06:13 -0800 From: "pete wright" <nomadlogic@gmail.com> To: "Eugene Grosbein" <eugen@kuzbass.ru> Cc: stable@freebsd.org, performance@freebsd.org Subject: Re: benchmark Message-ID: <57d710000701051006n278c44b4x9da019f3d8d8275c@mail.gmail.com> In-Reply-To: <20070105180003.GA23331@svzserv.kemerovo.su> References: <20070105174350.GA21615@svzserv.kemerovo.su> <57d710000701050956j36433495v72b62a9404a25a5d@mail.gmail.com> <20070105180003.GA23331@svzserv.kemerovo.su>
next in thread | previous in thread | raw e-mail | index | archive | help
On 1/5/07, Eugene Grosbein <eugen@kuzbass.ru> wrote: > On Fri, Jan 05, 2007 at 09:56:31AM -0800, pete wright wrote: > > > >Tried to use iperf from ports in UDP mode with 64 byte payload, > > >but it calls gettimeofday() after each write and gives me about 80Kpps only > > >for Pentium D 2.8Ghz. > > > > > >What alternative should I use? May be, a netgraph node? > > > > I've done some benchmarking/testing of 10gig-e NIC's using a combo of > > iperf/netgraph and ttcp with good results. all are available in > > ports. > > What pps numbers had you obtained? What CPU had you used? > I don't like iperf for gettimeofday() overhead. > yea that was an issue, hence us using multiple benchmarks to get a better picture of performance. sorry can't really get into the specifics on the hardware/stat's of the benchmark. used 10gig-e as example to illustrate that all these utilities functioned well under heavy tcp and udp loads. -pete -- ~~o0OO0o~~ Pete Wright www.nycbug.org NYC's *BSD User Group
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?57d710000701051006n278c44b4x9da019f3d8d8275c>