From mboxrd@z Thu Jan 1 00:00:00 1970 From: Robert Hancock Subject: Re: Please add ST3120827AS 3.42 to NCQ blacklist Date: Wed, 11 Feb 2009 22:30:22 -0600 Message-ID: <4993A5DE.4000403@gmail.com> References: <20090202132824.09984F805@i3.golden.dom> <49937FB5.3000608@kernel.org> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Return-path: Received: from yw-out-2324.google.com ([74.125.46.29]:35203 "EHLO yw-out-2324.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753559AbZBLEa0 (ORCPT ); Wed, 11 Feb 2009 23:30:26 -0500 Received: by yw-out-2324.google.com with SMTP id 5so294891ywh.1 for ; Wed, 11 Feb 2009 20:30:25 -0800 (PST) In-Reply-To: <49937FB5.3000608@kernel.org> Sender: linux-ide-owner@vger.kernel.org List-Id: linux-ide@vger.kernel.org To: Tejun Heo Cc: giulioo@pobox.com, linux-ide@vger.kernel.org Tejun Heo wrote: > Hello, > > Giulio Orsero wrote: >> Supermicro P8SC8, CENTOS/RHEL 5.x 2.6.18-128.el5 >> HD: Seagate SATA ST3120827AS fw3.42 [2 disks in md raid1] >> >> 00:1f.1 0101: 8086:266f (rev 03) >> 00:1f.2 0101: 8086:2652 (rev 03) >> >> 2652 is handled by both ata_piix and ahci. >> Using ata_piix everything is fine, using ahci will cause periodic errors >> like: >> >> ata1.00: exception Emask 0x0 SAct 0x1 SErr 0x0 action 0x6 frozen >> ata1.00: cmd 61/08:00:4d:6d:c0/00:00:00:00:00/40 tag 0 ncq 4096 out >> res 40/00:00:b5:95:a7/00:00:00:00:00/40 Emask 0x4 (timeout) >> ata1.00: status: { DRDY } >> ata1: hard resetting link >> ata1: SATA link up 1.5 Gbps (SStatus 113 SControl 300) >> ata1.00: configured for UDMA/133 >> ata1: EH complete >> SCSI device sda: 234441648 512-byte hdwr sectors (120034 MB) >> sda: Write Protect is off >> SCSI device sda: drive cache: write back >> >> Using >> echo 1 > /sys/block/sda/device/queue_depth >> echo 1 > /sys/block/sdb/device/queue_depth >> will eliminate the issue, so please add >> { "ST3120827AS", "3.42", ATA_HORKAGE_NONCQ }, >> to the NCQ blacklist. > > That's a 7200.7 which has been quite popular && happens to be used > extensively during libata development, so I'm highly doubtful the > problem is a wide spread one. The problem is more likely to be > something specific to your configuration. Indeed, I have a ST3160827AS (the 160GB version of that drive) with 3.42 firmware and haven't seen any problems with NCQ..