Message-ID: <4682211D.4040808@garzik.org>
Date: Wed, 27 Jun 2007 04:34:37 -0400
From: Jeff Garzik <jeff@garzik.org>
User-Agent: Thunderbird 1.5.0.12 (X11/20070530)
MIME-Version: 1.0
To: Peer Chen <pchen@nvidia.com>
CC: Robert Hancock <hancockr@shaw.ca>, kuan luo <kuanluo@gmail.com>,
       linux-kernel@vger.kernel.org, akpm@linux-foundation.org,
       Kuan Luo <kluo@nvidia.com>
Subject: Re: [PATCH] ata: Add the SW NCQ support to sata_nv for MCP51/MCP55/MCP61
References: <fa.5TBvnXzjCgAIfcuKOLBWeXi+y5I@ifi.uio.no> <4681F06F.1050302@shaw.ca> <15F501D1A78BD343BE8F4D8DB854566B15830128@hkemmail01.nvidia.com>
In-Reply-To: <15F501D1A78BD343BE8F4D8DB854566B15830128@hkemmail01.nvidia.com>
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1150
Lines: 26

Peer Chen wrote:
> We did the many test with the new version driver and didn't encounter
> that problem, but in certain cases, DMASETUP command packets from drive
> to the controller are corrupted, and the controller issues an R_ERR to
> the drive. Drives that comply with SATA spec will re-transmit the
> corrupted packet and normal operation continues. However, some Maxtor
> NCQ drives do not re-transmit the DMASETUP command packet, resulting in
> software timeout for this command. So if you are using the Maxtor HD and
> meet this problem,please don't enable the NCQ function.

Users should not be expected to know those details, nor be forced to 
suffer discovering this in the field (over and over again for each 
customer).

We have a list of problem devices ata_device_blacklist[] in 
drivers/ata/libata-core.c that should be modified to note each drive 
where NCQ should never be used.

	Jeff


-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/