From owner-freebsd-fs@FreeBSD.ORG Tue Jul 9 01:41:08 2013 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by hub.freebsd.org (Postfix) with ESMTP id E7B27AE5 for ; Tue, 9 Jul 2013 01:41:08 +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 41EF51BA1 for ; Tue, 9 Jul 2013 01:41:07 +0000 (UTC) X-Cloudmark-SP-Filtered: true X-Cloudmark-SP-Result: v=1.1 cv=ME3lrcP4jFDzpPiCSQywCMKJiHtpRWeRXBDIYmR1BZg= c=1 sm=2 a=2CN1efILQXEA:10 a=FKkrIqjQGGEA:10 a=V5z4IuhVU5kA:10 a=IkcTkHD0fZMA:10 a=GzJd4s-eAAAA:8 a=rvF0lruhulTt8CwKKYcA:9 a=QEXdDO2ut3YA:10 X-IronPort-Anti-Spam-Filtered: true X-IronPort-Anti-Spam-Result: AqIEAMpp21GDaFve/2dsb2JhbABagztNgwi9eYE0dIIjAQEFI1YbGAICDRkCWQYTiA+na5EqBIEmjhE0B4JUgRwDqRuDLSCBbA X-IronPort-AV: E=Sophos;i="4.87,1024,1363147200"; d="scan'208";a="38844549" Received: from muskoka.cs.uoguelph.ca (HELO zcs3.mail.uoguelph.ca) ([131.104.91.222]) by esa-annu.net.uoguelph.ca with ESMTP; 08 Jul 2013 21:41:01 -0400 Received: from zcs3.mail.uoguelph.ca (localhost.localdomain [127.0.0.1]) by zcs3.mail.uoguelph.ca (Postfix) with ESMTP id 64B3BB3F1C; Mon, 8 Jul 2013 21:41:01 -0400 (EDT) Date: Mon, 8 Jul 2013 21:41:01 -0400 (EDT) From: Rick Macklem To: Berend de Boer Message-ID: <1306739954.3352769.1373334061402.JavaMail.root@uoguelph.ca> In-Reply-To: <87obaczgpm.wl%berend@pobox.com> Subject: Re: Terrible NFS4 performance: FreeBSD 9.1 + ZFS + AWS EC2 MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 7bit X-Originating-IP: [172.17.91.201] X-Mailer: Zimbra 7.2.1_GA_2790 (ZimbraWebClient - FF3.0 (Win)/7.2.1_GA_2790) Cc: freebsd-fs X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 09 Jul 2013 01:41:09 -0000 Berend de Boer wrote: > >>>>> "Rick" == Rick Macklem writes: > > > Rick> After you apply the patch and boot the rebuilt kernel, the > Rick> cpu overheads should be reduced after you increase the > value > Rick> of vfs.nfsd.tcphighwater. > > Do I need to umount the share? Restart something after changing this > value? > I think you can safely change it "on the fly". It simply defines how large the DRC cache can grow before the nfsd thread will try to trim it down. The default of 0 means "trim every RPC", which keeps it at a minimal size, but can result in significant CPU overhead. rick > -- > All the best, > > Berend de Boer > > > ------------------------------------------------------ > Awesome Drupal hosting: https://www.xplainhosting.com/ > >