From owner-freebsd-fs@FreeBSD.ORG Fri Sep 10 23:32:41 2010 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 543131065670 for ; Fri, 10 Sep 2010 23:32:41 +0000 (UTC) (envelope-from rmacklem@uoguelph.ca) Received: from esa-jnhn.mail.uoguelph.ca (esa-jnhn.mail.uoguelph.ca [131.104.91.44]) by mx1.freebsd.org (Postfix) with ESMTP id 115328FC2B for ; Fri, 10 Sep 2010 23:32:40 +0000 (UTC) X-IronPort-Anti-Spam-Filtered: true X-IronPort-Anti-Spam-Result: ApwEAOhcikyDaFvO/2dsb2JhbACDGZ8grwGRcIEigyd0BIog X-IronPort-AV: E=Sophos;i="4.56,348,1280721600"; d="scan'208";a="93507877" Received: from erie.cs.uoguelph.ca (HELO zcs3.mail.uoguelph.ca) ([131.104.91.206]) by esa-jnhn-pri.mail.uoguelph.ca with ESMTP; 10 Sep 2010 19:32:39 -0400 Received: from zcs3.mail.uoguelph.ca (localhost.localdomain [127.0.0.1]) by zcs3.mail.uoguelph.ca (Postfix) with ESMTP id 5101BB3F28; Fri, 10 Sep 2010 19:32:39 -0400 (EDT) Date: Fri, 10 Sep 2010 19:32:39 -0400 (EDT) From: Rick Macklem To: David Brodbeck Message-ID: <1229417926.760488.1284161559264.JavaMail.root@erie.cs.uoguelph.ca> In-Reply-To: MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 7bit X-Originating-IP: [24.65.230.102] X-Mailer: Zimbra 6.0.7_GA_2476.RHEL4 (ZimbraWebClient - SAF3 (Mac)/6.0.7_GA_2473.RHEL4_64) Cc: freebsd-fs@freebsd.org Subject: Re: Weird Linux - FreeBSD/ZFS NFSv4 interoperability problem X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 10 Sep 2010 23:32:41 -0000 > On Wed, Sep 8, 2010 at 9:28 PM, Rick Macklem > wrote: > > Please try the attached patch, which changes the macro so that it > > compares the entire "struct fid". (I think that is safe, since I > > bzero() the entire structure before calling VOP_VPTOFH().) > > > > Again, thanks for sending the packet traces and, hopefully, this > > patch will do the trick, rick > > Rick, after doing some testing I'm pretty confident that this patch > (nfsdport.patch) has solved both the original problem and the I/O > error problem. > > I'm glad I could help. I know how tricky to debug these > interoperability problems can be. > Ok, thanks for testing it. I've just committed it to head. Maybe you'd like to test one other thing? (Not exactly interop. testing)? A couple of people have reported very slow read rates for the NFSv4 client (actually the experimental client, since they see it for NFSv3 too). If you could easily do the following, using a FreeBSD8.1 or newer client: # mount -t nfs -o nfsv4 :/path - cd to anywhere in the mount that has a 100Mbyte+ file # dd if=<100Mbyte+ file> of=/dev/null bs=1m and then report what read rate you see along with the client's machine-arch/# of cores/ram size/network driver used by the mount rick ps: Btw, anyone else who can do this test, it would be appreciated. If you aren't set up for NFSv4, you can do an NFSv3 mount using the exp. client instead. # mount -t newnfs -o nfsv3 :/path