Date: Thu, 28 Apr 2011 08:41:21 -0700 From: Jack Vogel <jfvogel@gmail.com> To: Adam Stylinski <kungfujesus06@gmail.com> Cc: freebsd-net@freebsd.org, Mike Tancsa <mike@sentex.net> Subject: Re: em0 performance subpar Message-ID: <BANLkTikTb0xqHFyvpJ5cvQjUP7T4Hg1aiA@mail.gmail.com> In-Reply-To: <20110428153539.GC19362@ossumpossum.geop.uc.edu> References: <20110428072946.GA11391@zephyr.adamsnet> <4DB965D8.7090906@sentex.net> <20110428132922.GC2800@ossumpossum.geop.uc.edu> <4DB96DDD.4070801@sentex.net> <20110428141500.GE2800@ossumpossum.geop.uc.edu> <4DB97A07.2020606@sentex.net> <20110428150110.GG2800@ossumpossum.geop.uc.edu> <4DB985FC.4000704@sentex.net> <20110428153539.GC19362@ossumpossum.geop.uc.edu>
next in thread | previous in thread | raw e-mail | index | archive | help
Just in case anyone did not notice, this adapter is actually using the legacy subdevice, ie lem, there has been little focus on that code, things that are not even PCI Express are becoming pretty elderly. Let me look this thread over in a bit more detail after I get into the office in a bit... Jack On Thu, Apr 28, 2011 at 8:35 AM, Adam Stylinski <kungfujesus06@gmail.com>wrote: > On Thu, Apr 28, 2011 at 11:21:32AM -0400, Mike Tancsa wrote: > > On 4/28/2011 11:01 AM, Adam Stylinski wrote: > > > > > > ./netblast 192.168.0.121 5001 32768 30 > > > > > > start: 1304002549.184689025 > > > finish: 1304002579.187555311 > > > send calls: 2163162 > > > send errors: 2095950 > > > approx send rate: 2240 > > > approx error rate: 0 > > > > > > ? This output is a bit cryptic but from what I think I understand from > the source code it's the number of successful sends of the payload size in > 30 seconds. > > > > > > So to do the math: > > > (32768*2210)/(1024*1024) > > > 69.06250000000000000000MB/sec? This is still only saturating about > half the link speed. > > > > Just to be clear, you have something listening on the other side on port > > 5001 right ? ie on 192.168.0.121, you did a ./netreceive 5001... And > > the payload is.... 32768 ?!? Try something that does not need > > fragmentation and is within your max MTU. e.g. 500 byte frames should > > saturate a gigabit link. > > > > Watch it in real time with something like ifstat > > > > ./netblast 192.168.0.121 5001 500 5 > > > > ---Mike > > > > > > > > > > -- > > ------------------- > > Mike Tancsa, tel +1 519 651 3400 > > Sentex Communications, mike@sentex.net > > Providing Internet services since 1994 www.sentex.net > > Cambridge, Ontario Canada http://www.tancsa.com/ > > k so during the transmission ifstat reported: > > 0.53 44266.87 > 0.23 62788.56 > 0.06 62774.17 > 0.00 62774.26 > 0.00 62774.95 > 0.40 19482.25 > > And the rate output of netblast (using as suggested the parameters above): > 119091 > > This is about 454mbps. Still way slower than it ought to be. > > -- > Adam Stylinski > PGP Key: http://pohl.ececs.uc.edu/~adam/publickey.pub > Blog: http://technicallyliving.blogspot.com >
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?BANLkTikTb0xqHFyvpJ5cvQjUP7T4Hg1aiA>