Date: Wed, 07 Feb 2007 22:36:58 -0600
From: Robert Hancock <hancockr@shaw.ca>
Subject: Re: [BUG?] ata disk running maximum at DMA33 with 2.6.20 and new pata
 driver, NV CK804 ide controller.
In-reply-to: <fa.Bv1nbk8Z669RxoYF6zPFpsCsyd4@ifi.uio.no>
To: Alan <alan@lxorguk.ukuu.org.uk>,
       linux-kernel <linux-kernel@vger.kernel.org>
Cc: Luigi Genoni <genoni@sns.it>
Message-id: <45CAA8EA.2010505@shaw.ca>
MIME-version: 1.0
Content-type: text/plain; charset=ISO-8859-1; format=flowed
Content-transfer-encoding: 7bit
References: <fa.xQT7YaGQERXkjuW4tC35jsdiTD0@ifi.uio.no>
 <fa.Bv1nbk8Z669RxoYF6zPFpsCsyd4@ifi.uio.no>
User-Agent: Thunderbird 1.5.0.9 (Windows/20061207)
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1300
Lines: 34

Alan wrote:
> On Wed, 7 Feb 2007 01:19:36 +0100
> Luigi Genoni <genoni@sns.it> wrote:
> 
>> Hi,
>> since upgrading to kernel 2.6.20 my pata disk, using new pata driver, is
>> initialized maximum  in DMA33 mode (and obviously performances drop 
>> consequently), as you can see from:
> 
> Interesting.
> 
>> Willing to test any patch.
> 
> Firstly can you see if its consistently the case that booting 2.6.20
> gives UDMA33 and 2.6.19 UDMA100 over a few reboots. If it is please drop
> the 2.6.19 drivers/ata/pamd_amd into 2.6.20 and try that.

As an aside to this sort of problem, shouldn't we print some kind of 
loud message in dmesg when we force a high-UDMA-capable device down to 
UDMA33 due to a 40-wire cable detection? In the case where it truly is a 
40-wire cable the user may want to know that and replace the cable, if 
it isn't it gives more of a hint of why the drive isn't running at full 
speed..

-- 
Robert Hancock      Saskatoon, SK, Canada
To email, remove "nospam" from hancockr@nospamshaw.ca
Home Page: http://www.roberthancock.com/

-
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/