From owner-freebsd-questions Wed Sep 25 20:03:43 1996 Return-Path: owner-questions Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id UAA00383 for questions-outgoing; Wed, 25 Sep 1996 20:03:43 -0700 (PDT) Received: from alyssa.ai.net ([208.194.40.2]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id UAA00343 for ; Wed, 25 Sep 1996 20:03:38 -0700 (PDT) Received: (from nc@localhost) by alyssa.ai.net (8.6.12/8.6.12) id WAA03369; Wed, 25 Sep 1996 22:44:50 -0400 Date: Wed, 25 Sep 1996 22:44:40 -0400 (EDT) From: Network Coordinator To: questions@freebsd.org Subject: Machines disapearing from the Net? (fwd) Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-questions@freebsd.org X-Loop: FreeBSD.org Precedence: bulk We have two new machines that are moving a fair amount of traffic. Each is doing about 50GB/day in transfers or about 30 request/s under a modified Apache 1.1.1 under FreeBSD 2.1.5 and 2.2-SNAP-08-01-96 One representative machine is configured with 512MB of RAM and a P6-200 processor. It has plenty of MBUF clusters free [is only using about 5660 of 8192] and has 11805 Kbytes (51%) allocated to the network at a low period. One had been running for about 3 weeks and the other only a few days, yet both are disapearing from the net every so often. They return with a simple ifconfig vx0 up [even though the port is never listed as down]. When trying to ping from these machines in the "down" state, they report that "no buffer space is available" which could be a result of the port being considered "down". One is using an Intel Etherpower 10/100Mbit PCI and other [as above is using a 3Com-3C595TX PCI]. We have not seen this problem since 2.0.5-SNAP-02-02-95, so the problem may have a different cause but the same symptom? We have other machines running 2.1.5 with about 4M hits/day that have not shown this problem [yet]. Any ideas? Thanks for your time, John Hubbel American Information Network Networking Power for People, Places and Ideas.