Date: Tue, 29 May 2018 19:42:42 +0200 From: "Muenz, Michael" <m.muenz@spam-fetish.org> To: "Rodney W. Grimes" <freebsd-rwg@pdx.rh.CN85.dnsmgr.net>, Vitalij Satanivskij <satan@ukr.net> Cc: freebsd-net@freebsd.org Subject: Re: GRE/gif/netgraph tunnel speed on 10Gbit channel Message-ID: <debcb6b2-ac1a-24e1-2e74-d8f081b461df@spam-fetish.org> In-Reply-To: <201805291402.w4TE2RMe065517@pdx.rh.CN85.dnsmgr.net> References: <201805291402.w4TE2RMe065517@pdx.rh.CN85.dnsmgr.net>
next in thread | previous in thread | raw e-mail | index | archive | help
Am 29.05.2018 um 16:02 schrieb Rodney W. Grimes: >> Am 29.05.2018 um 13:33 schrieb Vitalij Satanivskij: >> >> MM> Can you try MTU 1400 on GRE0 and MSS of 1300 just for testing? >> MM> With this values I get 4600Mbit sending and 1400Mbit receiving with >> MM> iperf and 10 parallel streams. >> MM> >> >> UUUPSS looks like i have problem with metodology >> >> I'm use iperf3 and even with -P10 or run's in parallel (on diferents ports) it show summary of +-2gbits max > Iperf3 is known not to do Parallel well: > -P, --parallel n > number of parallel client streams to run. Note that iperf3 is > single threaded, so if you are CPU bound, this will not yield > higher throughput. > > I suggest using iperf for -P tests that cause the single thread of > iperf3 to become CPU bound. Oh, this was new to me. With iperf I got consistent 4,6Gbit in both directions.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?debcb6b2-ac1a-24e1-2e74-d8f081b461df>