Date: Sat, 1 Jul 95 21:11:49 EDT From: jleppek@suw2k.ess.harris.com (James Leppek) To: freebsd-questions@freefall.cdrom.com Subject: Re: tcpblast Message-ID: <9507020111.AA00633@borg.ess.harris.com>
next in thread | raw e-mail | index | archive | help
Pete, You may have something there. if I leave the mtu at 16384 I get a thruput of 2.1 Mbytes/s but it drops to .1 after a few test. If I change the mtu to 1500 a get a thruput of 1.3Mbytes/s but no stalls. Would it be better to change the default mtu for lo0 to a smaller value as a default?? If I use an mtu of 6000 the thruput is at 2Mbytes/s with no stalls. Hmmm is this thread starting to belong in hackers :-) Jim > From pete@silver.sms.fi Sat Jul 1 13:45:34 1995 > Date: Sat, 1 Jul 1995 10:40:44 +0300 > From: Petri Helenius <pete@sms.fi> > To: Jim Leppek <jleppek@harris.com> > Cc: freebsd-questions@freefall.cdrom.com > Subject: tcpblast > > Jim Leppek writes: > > I was running the following: > > > > tcpblast 127.0.0.1 <some blocks> > > > > and got some strange results would anyone care to explain them? > > this is on a DX4/100 16Meg, X is running with three idle xterms. > > the system is a 2.0.5R, only the test is active, no build worlds > > or anything :-) > > > > (the use of my hostname, localhost, or 127.0.0.1 makes no difference) > > > > these tests were run in a row, I just "up arrowed" and changed > > the number of blocks. > > > > The thruput varies greatly, is this normal? > > Would it be possible that because of the large MTU of the loopback- > interface you are experiencing TCP deadlock? > > Pete >
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?9507020111.AA00633>