From owner-freebsd-questions Sat Jul 1 00:40:55 1995 Return-Path: questions-owner Received: (from majordom@localhost) by freefall.cdrom.com (8.6.10/8.6.6) id AAA05110 for questions-outgoing; Sat, 1 Jul 1995 00:40:55 -0700 Received: from silver.sms.fi (silver.sms.fi [194.111.122.1]) by freefall.cdrom.com (8.6.10/8.6.6) with ESMTP id AAA05104 for ; Sat, 1 Jul 1995 00:40:52 -0700 Received: (from pete@localhost) by silver.sms.fi (8.6.11/8.6.9) id KAA17554; Sat, 1 Jul 1995 10:40:44 +0300 Date: Sat, 1 Jul 1995 10:40:44 +0300 Message-Id: <199507010740.KAA17554@silver.sms.fi> From: Petri Helenius To: Jim Leppek Cc: freebsd-questions@freefall.cdrom.com Subject: tcpblast In-Reply-To: <199506251815.OAA00556@cyclops> References: <199506251815.OAA00556@cyclops> Sender: questions-owner@FreeBSD.org Precedence: bulk Jim Leppek writes: > I was running the following: > > tcpblast 127.0.0.1 > > 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