From owner-freebsd-stable@FreeBSD.ORG Tue Jan 17 23:32:46 2012 Return-Path: Delivered-To: freebsd-stable@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 67D96106566C for ; Tue, 17 Jan 2012 23:32:46 +0000 (UTC) (envelope-from hausen@punkt.de) Received: from kagate.punkt.de (kagate.punkt.de [217.29.33.131]) by mx1.freebsd.org (Postfix) with ESMTP id E6E828FC15 for ; Tue, 17 Jan 2012 23:32:45 +0000 (UTC) Received: from hugo10.ka.punkt.de ([217.29.45.10]) by gate1.intern.punkt.de with ESMTP id q0HNWiCi093230; Wed, 18 Jan 2012 00:32:44 +0100 (CET) Received: from [217.29.46.8] ([217.29.46.8]) by hugo10.ka.punkt.de (8.14.2/8.14.2) with ESMTP id q0HNWiMi073018; Wed, 18 Jan 2012 00:32:44 +0100 (CET) (envelope-from hausen@punkt.de) References: <201201171859.10812.peter@hk.ipsec.se> <201201180014.53247.peter@hk.ipsec.se> In-Reply-To: <201201180014.53247.peter@hk.ipsec.se> Mime-Version: 1.0 (1.0) Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset=us-ascii Message-Id: X-Mailer: iPad Mail (9A405) From: "Patrick M. Hausen" Date: Wed, 18 Jan 2012 00:32:45 +0100 To: peter h Cc: "freebsd-stable@freebsd.org" Subject: Re: about thumper aka sun fire x4500 X-BeenThere: freebsd-stable@freebsd.org X-Mailman-Version: 2.1.5 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, 17 Jan 2012 23:32:46 -0000 Hi all, Am 18.01.2012 um 00:14 schrieb peter h : > On Tuesday 17 January 2012 23.15, Ronald Klop wrote: >> On Tue, 17 Jan 2012 18:59:08 +0100, peter h wrote: >>=20 >>> I have been beating on of these a few days, i have udes freebsd 9.0 and = =20 >>> 8.2 >>> Both fails when i engage > 10 disks, the system craches and messages : >>> "Hyper transport sync flood" will get into the BIOS errorlog ( but =20 >>> nothing will >>> come to syslog since reboot is immediate) >>>=20 >>> Using a zfs radz of 25 disks and typing "zpool scrub" will bring the =20= >>> system down in seconds. >>>=20 >>> Anyone using a x4500 that can comfirm that it works ? Or is this box =20= >>> broken ? >>=20 >> Does it work if you make 3 raid groups of 8 disks and 1 spare? > No, i did not test this. =20 > I did some simple ones ( 5 disks in a raidz ) but what i wanted this box > to do is a more powerful work. For smaller stuff i use simple hardware >=20 > I guess i'll buy some supermicro box instead. But Ronald is right. I apologize for not reading your initial post thoroughl= y and jumping on your suspicion that the hardware might be to blame. Did you really create one vdev of 25 disks? This is strongly discouraged by the documentation provided by Sun/Oracle. You should (IIRC) never have more than 9 disk in a single vdev. Of course you can join N vdevs of type, say, raidz2 to a single zpool. See for example http://forums.freebsd.org/archive/index.php/t-4641.html I'm writing from my iPad and cannot quickly find the Link to the Sun documen= tation. Kind regards, HTH, Patrick=