From mboxrd@z Thu Jan 1 00:00:00 1970 From: Roman Mamedov Subject: Re: possible HighPoint RocketRAID 2720SGL failure Date: Thu, 21 Sep 2017 17:20:19 +0500 Message-ID: <20170921172019.2067e49b@natsu> References: <73afd1f8-176a-07e9-1024-57692dc96904@eyal.emu.id.au> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <73afd1f8-176a-07e9-1024-57692dc96904@eyal.emu.id.au> Sender: linux-raid-owner@vger.kernel.org To: Eyal Lebedinsky Cc: list linux-raid List-Id: linux-raid.ids On Thu, 21 Sep 2017 21:12:36 +1000 Eyal Lebedinsky wrote: > It looks like the controller failed as all 7 disks disappeared together and did not respond > to any i/o or even smart. > > After power off/on things look OK. The raid6 did a very short recovery, then the ext4 fs did > a quick recovery. fsck found no problems. > > I later started a raid 'check' but it failed in less that an hour (out of 10) in the same way. > A day later I tried again and it failed within 15 minutes. > > So far it looks like nothing was lost but I am uncomfortable with this situation. > No surprise here... > > The controller did not log any errors. > > Does this look familiar to anyone? The controller is based on the Marvell 9485 chip and Marvell SATA/RAID controllers seem to have a bad reputation for reliability: https://www.jethrocarr.com/2013/11/24/adventures-in-io-hell/ https://www.youtube.com/watch?v=010urq9wY3A I have also faced some CRC errors or disk drop-outs/reconnects on 9123 cards, and in one case all disks (or possibly the controller itself) disappear from the system until reboot on a 88SX7042 based controller. -- With respect, Roman