From owner-freebsd-fs@FreeBSD.ORG Thu May 2 18:46:45 2013 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.FreeBSD.org [8.8.178.115]) by hub.freebsd.org (Postfix) with ESMTP id 620EB364 for ; Thu, 2 May 2013 18:46:45 +0000 (UTC) (envelope-from scrappy@hub.org) Received: from hub.org (hub.org [200.46.208.146]) by mx1.freebsd.org (Postfix) with ESMTP id D8DAB101F for ; Thu, 2 May 2013 18:46:44 +0000 (UTC) Received: from maia.hub.org (unknown [200.46.151.188]) by hub.org (Postfix) with ESMTP id 68F681F8AE2B; Thu, 2 May 2013 15:46:43 -0300 (ADT) Received: from hub.org ([200.46.208.146]) by maia.hub.org (mx1.hub.org [200.46.151.188]) (amavisd-maia, port 10024) with ESMTP id 61380-05; Thu, 2 May 2013 18:46:42 +0000 (UTC) Received: from [10.5.250.150] (remote.ilcs.sd63.bc.ca [142.31.148.2]) by hub.org (Postfix) with ESMTPA id 4AAAE1F8AE2A; Thu, 2 May 2013 15:46:42 -0300 (ADT) Content-Type: text/plain; charset=windows-1252 Mime-Version: 1.0 (Mac OS X Mail 6.3 \(1503\)) Subject: oldnfs vs nfs ( Was: Re: Initial NFS Test: Linux vs FreeBSD (769% slower) ) From: "Marc G. Fournier" In-Reply-To: <971747745.58619.1367458184334.JavaMail.root@erie.cs.uoguelph.ca> Date: Thu, 2 May 2013 11:46:40 -0700 Content-Transfer-Encoding: quoted-printable Message-Id: References: <971747745.58619.1367458184334.JavaMail.root@erie.cs.uoguelph.ca> To: Rick Macklem X-Mailer: Apple Mail (2.1503) Cc: freebsd-fs@freebsd.org 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: Thu, 02 May 2013 18:46:45 -0000 Okay, I think I can make the pitch against Linux based on concerns as to = what exactly it is doing to get 'near local drive' performance on start = up of jboss =85 it has to be short circuiting something in favour of = speed =85 and this project (to us) is such that any reduction in risk of = data loss is desirable =85 we have a lot of naysayers against us =85 But, that said, the newnfs code does appear to be slower then the oldnfs = =85 just over 60s slower to start up =85 is that to be expected? OLDNFS: JBoss AS 7.1.1.Final "Brontes" started in 246381ms root@server04:/usr/local/jboss-as-7.1.1.Final # nfsstat -o -c Client Info: Rpc Counts: Getattr Setattr Lookup Readlink Read Write Create = Remove 237199 5 17224 0 233935 234240 3743 = 1 Rename Link Symlink Mkdir Rmdir Readdir RdirPlus = Access 0 0 0 307 0 71 0 = 8420 Mknod Fsstat Fsinfo PathConf Commit 0 467 0 0 0 Rpc Info: TimedOut Invalid X Replies Retries Requests 0 0 0 0 735611 Cache Info: Attr Hits Misses Lkup Hits Misses BioR Hits Misses BioW Hits = Misses 712242 237197 527641 17224 -100768 233774 13164 = 234240 BioRLHits Misses BioD Hits Misses DirE Hits Misses Accs Hits = Misses 0 0 934 71 467 0 544719 = 8420 NEWNFS: JBoss AS 7.1.1.Final "Brontes" started in 305919ms root@server04:~ # nfsstat -c Client Info: Rpc Counts: Getattr Setattr Lookup Readlink Read Write Create = Remove 236644 5 17306 0 230891 231140 3743 = 1 Rename Link Symlink Mkdir Rmdir Readdir RdirPlus = Access 0 0 0 307 0 71 0 = 8481 Mknod Fsstat Fsinfo PathConf Commit 0 531 0 0 0 Rpc Info: TimedOut Invalid X Replies Retries Requests 0 0 0 0 729116 Cache Info: Attr Hits Misses Lkup Hits Misses BioR Hits Misses BioW Hits = Misses 717990 236647 530738 17306 -101086 230812 13164 = 231140 BioRLHits Misses BioD Hits Misses DirE Hits Misses Accs Hits = Misses 0 0 1087 55 531 0 548059 = 8481 Both using same mount options *other then* oldnfs vs nfs =85