From owner-freebsd-net@freebsd.org Fri Jun 26 23:58:45 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id E26FC98D404 for ; Fri, 26 Jun 2015 23:58:44 +0000 (UTC) (envelope-from rmacklem@uoguelph.ca) Received: from esa-annu.net.uoguelph.ca (esa-annu.mail.uoguelph.ca [131.104.91.36]) by mx1.freebsd.org (Postfix) with ESMTP id A25B01D10 for ; Fri, 26 Jun 2015 23:58:44 +0000 (UTC) (envelope-from rmacklem@uoguelph.ca) X-IronPort-Anti-Spam-Filtered: true X-IronPort-Anti-Spam-Result: A2CtBACe5o1V/61jaINbhEQGgxi6EIdeAoF1EwEBAQEBAQGBCoQiAQEBAwEjSQoDEAIBCBgCAg0ZAgJXAgQTiCcIuHeWGAEBAQEBAQEDAQEBAQEBARuBIYophCQuNAeCaIFDBZQEjQyOfId/AiZjgzMiMYEEQoECAQEB X-IronPort-AV: E=Sophos;i="5.13,687,1427774400"; d="scan'208";a="221965703" Received: from nipigon.cs.uoguelph.ca (HELO zcs1.mail.uoguelph.ca) ([131.104.99.173]) by esa-annu.net.uoguelph.ca with ESMTP; 26 Jun 2015 19:58:43 -0400 Received: from localhost (localhost [127.0.0.1]) by zcs1.mail.uoguelph.ca (Postfix) with ESMTP id 60A2715F533; Fri, 26 Jun 2015 19:58:43 -0400 (EDT) Received: from zcs1.mail.uoguelph.ca ([127.0.0.1]) by localhost (zcs1.mail.uoguelph.ca [127.0.0.1]) (amavisd-new, port 10032) with ESMTP id eBrU9Qq9Ultu; Fri, 26 Jun 2015 19:58:42 -0400 (EDT) Received: from localhost (localhost [127.0.0.1]) by zcs1.mail.uoguelph.ca (Postfix) with ESMTP id BA05615F538; Fri, 26 Jun 2015 19:58:42 -0400 (EDT) X-Virus-Scanned: amavisd-new at zcs1.mail.uoguelph.ca Received: from zcs1.mail.uoguelph.ca ([127.0.0.1]) by localhost (zcs1.mail.uoguelph.ca [127.0.0.1]) (amavisd-new, port 10026) with ESMTP id W4CgJsW8D4NY; Fri, 26 Jun 2015 19:58:42 -0400 (EDT) Received: from zcs1.mail.uoguelph.ca (zcs1.mail.uoguelph.ca [172.17.95.18]) by zcs1.mail.uoguelph.ca (Postfix) with ESMTP id 8F5A115F533; Fri, 26 Jun 2015 19:58:42 -0400 (EDT) Date: Fri, 26 Jun 2015 19:58:42 -0400 (EDT) From: Rick Macklem To: Gerrit =?utf-8?B?S8O8aG4=?= Cc: freebsd-net@freebsd.org, carsten aulbert Message-ID: <570481533.408618.1435363122433.JavaMail.zimbra@uoguelph.ca> In-Reply-To: <20150626115943.7d0b441cda2c6cc5b817b181@aei.mpg.de> References: <20150625145238.12cf9da3b368ef0b9a30f193@aei.mpg.de> <623856025.328424.1435279751389.JavaMail.zimbra@uoguelph.ca> <20150626115943.7d0b441cda2c6cc5b817b181@aei.mpg.de> Subject: Re: NFS on 10G interface terribly slow MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 7bit X-Originating-IP: [172.17.95.10] X-Mailer: Zimbra 8.0.9_GA_6191 (ZimbraWebClient - FF34 (Win)/8.0.9_GA_6191) Thread-Topic: NFS on 10G interface terribly slow Thread-Index: DBslsicAPKZWNDtaWYC99kEXrub3IA== X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 26 Jun 2015 23:58:45 -0000 Gerrit Kuhn wrote: > On Thu, 25 Jun 2015 20:49:11 -0400 (EDT) Rick Macklem > wrote about Re: NFS on 10G interface terribly slow: > > > RM> Recent commits to stable/10 (not in 10.1) done by Alexander Motin > RM> (mav@) might help w.r.t. write performance (it avoids large writes > RM> doing synchronous writes when the wcommitsize is exceeded). If you can > RM> try stable/10, that might be worth it. > > Ok, I'll schedule an update then, I guess. OTOH, Scott reported that a > similar setup is working fine for him with 10.0 and 10.1, so there is > probably not much to gain. I'll try anyway... > > RM> Otherwise, the main mount option you can try is "wcommitsize", which > RM> you probably want to make larger. > > Hm, which size would you recommend? I cannot find anything about this > setting, not even what the default value would be. Is this reflected in > some sysctl, or how can I find out what the actual value is? > The default (auto tuned) value is reported by "nfsstat -m". It can be set with a mount option (should be something in "man mount_nfs"). If you are doing a test with 1 megabyte writes, I'd set it to at least 1 megabyte. (Basically, writing will be slower for write(2) syscalls that are larger than wcommitsize. After mav@'s patch, the difference isn't nearly as noticable. His other commit makes the auto tuned value more reasonable). If you set it large enough with the "wcommitsize=" mount option, you don't need the updates stable/10. rick > > cu > Gerrit >