From owner-freebsd-questions@FreeBSD.ORG Mon Jan 2 14:58:38 2012 Return-Path: Delivered-To: freebsd-questions@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id E291A106566C for ; Mon, 2 Jan 2012 14:58:38 +0000 (UTC) (envelope-from bgold@simons-rock.edu) Received: from hedwig.simons-rock.edu (hedwig.simons-rock.edu [208.81.88.14]) by mx1.freebsd.org (Postfix) with ESMTP id BFBAD8FC12 for ; Mon, 2 Jan 2012 14:58:38 +0000 (UTC) Received: from hp6000new (behemoth.simons-rock.edu [10.30.2.44]) by hedwig.simons-rock.edu (Postfix) with ESMTP id 4D5D62BB366 for ; Mon, 2 Jan 2012 09:30:12 -0500 (EST) From: "Brian Gold" To: Date: Mon, 2 Jan 2012 09:30:11 -0500 Message-ID: <06d501ccc95b$089f0d30$19dd2790$@simons-rock.edu> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit X-Mailer: Microsoft Outlook 14.0 Thread-Index: AczJWwiAIVpX5jJoQY2z0hzcMVOelw== Content-Language: en-us Subject: freebsd 8.2 lockups on Dell T610 w/ Perc 6/i X-BeenThere: freebsd-questions@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: User questions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 02 Jan 2012 14:58:39 -0000 I have been running 8.2 Release patched with ZFS v28 support (via http://mfsbsd.vx.sk) since early September. In that time, we have gotten multiple errors every day regarding mfi timeouts (mfi0: COMMAND 0xffffff80007ba5b8 TIMEOUT AFTER 32 SECONDS) and we have experienced a full system lockup every 2-4 weeks. When the system locks up it will still respond to pings, but is totally unresponsive via ssh or directly from the console. After hard booting the system, everything comes back up without any issues. I have come across other users who have experienced similar issues (http://lists.freebsd.org/pipermail/freebsd-questions/2011-February/227650.html). In their cases, they were able to resolve the issue by disabling C-States, Turbo Mode, and setting the bios to "Maximum Performance". We have made these changes and ensured that all of our device's firmware are up to date. We are still experiencing the issue however. Fortunately, iDrac continues to work during the lockup, so we have been able to power-cycle the server remotely, but it is still a big pain. If anyone has any suggestions, I would be very appreciative. Brian Gold System Administrator Bard College at Simon's Rock