From owner-freebsd-stable Sat Aug 8 13:51:19 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id NAA23203 for freebsd-stable-outgoing; Sat, 8 Aug 1998 13:51:19 -0700 (PDT) (envelope-from owner-freebsd-stable@FreeBSD.ORG) Received: from zed.ludd.luth.se (zed.ludd.luth.se [130.240.16.33]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id NAA23198 for ; Sat, 8 Aug 1998 13:51:16 -0700 (PDT) (envelope-from pantzer@sister.ludd.luth.se) Received: from sister.ludd.luth.se (pantzer@sister.ludd.luth.se [130.240.16.77]) by zed.ludd.luth.se (8.8.5/8.8.5) with SMTP id WAA08160; Sat, 8 Aug 1998 22:50:54 +0200 Message-Id: <199808082050.WAA08160@zed.ludd.luth.se> X-Mailer: exmh version 2.0.2 2/24/98 To: Morgan Davis cc: stable@FreeBSD.ORG Subject: Re: tuning nfs In-reply-to: Your message of "Sat, 08 Aug 1998 11:54:31 PDT." <199808081854.LAA03637@io.cts.com> Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Date: Sat, 08 Aug 1998 22:50:53 +0200 From: Mattias Pantzare Content-Transfer-Encoding: 8bit X-MIME-Autoconverted: from quoted-printable to 8bit by hub.freebsd.org id NAA23199 Sender: owner-freebsd-stable@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG > We have a server that is causing these messages to appear on clients: > > nfs server nsfserv-i2:/data: not responding > nfs server nsfserv-i2:/data: is alive again > nfs server nsfserv-i2:/data: not responding > nfs server nsfserv-i2:/data: is alive again > nfs server nsfserv-i2:/data: not responding > nfs server nsfserv-i2:/data: is alive again > nfs server nsfserv-i2:/data: not responding > nfs server nsfserv-i2:/data: is alive again > nfs server nsfserv-i2:/data: not responding > nfs server nsfserv-i2:/data: is alive again > > The pairs ("not responding" and "is alive again") seem to occur in the > same second, according to timestamps in /var/log/messages. Is this > from having some timeout threshhold set too low, not enough nfsds on > the server, not enough nfsiods on the client, a network problem, or > what? Is it a real problem or just an annoying diagnostic? A network problem or to slow server (or to low timeout). Check the network for lost packets, ping with a big packet size for example. If it is on a local ethernet something is wrong if you lose packets. If it is loosing packets and you can't do anyting about it, try NFS over TCP instead of UDP (not all NFS implementations support that). As to tuning, the only thing that I know of is the number of NFS servers, try a higher number and se if it helps. Check if the CPU or disks are overloaded. The problem is real in the sense that you don't get all the performance, but no data is lost. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-stable" in the body of the message