From owner-freebsd-questions Mon Jul 16 7:27:23 2001 Delivered-To: freebsd-questions@freebsd.org Received: from dan.emsphone.com (dan.emsphone.com [199.67.51.101]) by hub.freebsd.org (Postfix) with ESMTP id 6FA8B37B406 for ; Mon, 16 Jul 2001 07:27:09 -0700 (PDT) (envelope-from dan@dan.emsphone.com) Received: (from dan@localhost) by dan.emsphone.com (8.11.4/8.11.4) id f6GER5n03619; Mon, 16 Jul 2001 09:27:05 -0500 (CDT) (envelope-from dan) Date: Mon, 16 Jul 2001 09:27:05 -0500 From: Dan Nelson To: Arun Sharma Cc: questions@FreeBSD.ORG Subject: Re: NFS mount Linux Mandrake 8.0 -> FreeBSD 4.3-STABLE hang Message-ID: <20010716092705.B5696@dan.emsphone.com> References: <20010715200102.A19948@sharmas.dhs.org> <20010715220415.A3289@dan.emsphone.com> <20010715214538.A20260@sharmas.dhs.org> <20010715215513.A20380@sharmas.dhs.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20010715215513.A20380@sharmas.dhs.org> User-Agent: Mutt/1.3.19i X-OS: FreeBSD 5.0-CURRENT Sender: owner-freebsd-questions@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.ORG In the last episode (Jul 15), Arun Sharma said: > On Sun, Jul 15, 2001 at 09:45:38PM -0700, Arun Sharma wrote: > > > > Actually, I figured out that the cp doesn't hang, but takes a *long* > > time - longer than it takes to transfer the file via scp over the > > same interface. > > > > tcpdump shows that NFS is using 8kb block size, but packets get > > fragmented because I'm on a wireless network with a MTU < 2k. > > > > -Arun > > Another clue: the writes are 100x faster than reads, when tested > using dd with the same block size. Just as a test, try dropping your NFS blocksize down to 1k (mount -o -r1024,-w1024) or using a TCP mount (mount -o -T) and see waht happens. -- Dan Nelson dnelson@emsphone.com To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-questions" in the body of the message