On Thu, Apr 28, 2011 at 10:30:31AM -0400, Mike Tancsa wrote: > On 4/28/2011 10:15 AM, Adam Stylinski wrote: > > > > > em0: <Intel(R) PRO/1000 Legacy Network Connection 1.0.3> port 0xe800-0xe83f > > mem 0xfe9e0000-0xfe9fffff,0xfe9c0000-0xfe9dffff irq 20 at device 5.0 on pci7 > > em0: [FILTER] > > I am not sure the newer driver will help performance wise. It might fix > that bug you saw at least. Jack from intel might be able to shed some > light on it. In the mean time, try generating traffic via netblast. > Another tool I find helpful in narrowing down tcp performance > differences is netperf > > ---Mike > > > -- > ------------------- > Mike Tancsa, tel +1 519 651 3400 > Sentex Communications, m...@sentex.net > Providing Internet services since 1994 www.sentex.net > Cambridge, Ontario Canada http://www.tancsa.com/
./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. -- Adam Stylinski PGP Key: http://pohl.ececs.uc.edu/~adam/publickey.pub Blog: http://technicallyliving.blogspot.com
pgpydG9qLVEOn.pgp
Description: PGP signature
