From owner-freebsd-stable@FreeBSD.ORG Tue Jun 24 14:14:30 2014 Return-Path: Delivered-To: freebsd-stable@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1 with cipher ADH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id DE11659C for ; Tue, 24 Jun 2014 14:14:30 +0000 (UTC) Received: from smarthost1.sentex.ca (smarthost1.sentex.ca [IPv6:2607:f3e0:0:1::12]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client CN "smarthost.sentex.ca", Issuer "smarthost.sentex.ca" (not verified)) by mx1.freebsd.org (Postfix) with ESMTPS id A76752E36 for ; Tue, 24 Jun 2014 14:14:30 +0000 (UTC) Received: from [IPv6:2607:f3e0:0:4:f025:8813:7603:7e4a] (saphire3.sentex.ca [IPv6:2607:f3e0:0:4:f025:8813:7603:7e4a]) by smarthost1.sentex.ca (8.14.9/8.14.9) with ESMTP id s5OEEPt7021546; Tue, 24 Jun 2014 10:14:25 -0400 (EDT) (envelope-from mike@sentex.net) Message-ID: <53A987AE.8060708@sentex.net> Date: Tue, 24 Jun 2014 10:14:06 -0400 From: Mike Tancsa Organization: Sentex Communications User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:24.0) Gecko/20100101 Thunderbird/24.6.0 MIME-Version: 1.0 To: Rick Macklem Subject: Re: nfs slowdown (RELENG_8) References: <2091718059.2982836.1403563319620.JavaMail.root@uoguelph.ca> <53A978D1.2000207@sentex.net> In-Reply-To: <53A978D1.2000207@sentex.net> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Scanned-By: MIMEDefang 2.74 Cc: FreeBSD-STABLE Mailing List X-BeenThere: freebsd-stable@freebsd.org X-Mailman-Version: 2.1.18 Precedence: list List-Id: Production branch of FreeBSD source code List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 24 Jun 2014 14:14:30 -0000 On 6/24/2014 9:10 AM, Mike Tancsa wrote: > On 6/23/2014 6:41 PM, Rick Macklem wrote: >>> >> I suggest you try disabling TSO on the nics (or setting wsize=32786 >> on all mounts). Usually such slowdowns are related to the underlying >> network fabric and there are known TSO issues for nics/drivers that >> only handle 32 transmit buffers when 64K writes are being used. > > Thanks Rick, > I tried that. Both doing ifconfig em1 -tso and set net.inet.tcp.tso > to 0. No impact on these particular boxes. Mount is done > > > /sbin/mount_nfs -o tcp,rsize=32768,wsize=32768,async > > I looked at the tcpdump between the working and non working servers and > they look identical. Tried changing switch ports and the problem does > not follow the port, only the server. I also just tried with an igb nic and the same issue. These are i386 boxes. I wonder if its something to do with that. (non PAE kernel) ---Mike -- ------------------- Mike Tancsa, tel +1 519 651 3400 Sentex Communications, mike@sentex.net Providing Internet services since 1994 www.sentex.net Cambridge, Ontario Canada http://www.tancsa.com/