[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <CAAJw_ZvCHz0N==MCCVbartfUzCBzsmkKcj_+0BUKa3okNf3JfA@mail.gmail.com>
Date: Wed, 15 Feb 2012 12:41:55 +0800
From: Jeff Chua <jeff.chua.linux@...il.com>
To: Philip Rakity <prakity@...vell.com>
Cc: Jaehoon Chung <jh80.chung@...sung.com>,
Chris Ball <cjb@...top.org>, Pierre Ossman <pierre@...man.eu>,
lkml <linux-kernel@...r.kernel.org>,
"linux-mmc@...r.kernel.org" <linux-mmc@...r.kernel.org>,
"arindam.nath@....com" <arindam.nath@....com>,
"zhangfei.gao@...il.com" <zhangfei.gao@...il.com>,
Adrian Hunter <adrian.hunter@...el.com>,
Greg KH <greg@...ah.com>,
Linus Torvalds <torvalds@...ux-foundation.org>
Subject: Re: mmc sdhci mmcblk0: error -110 sending status command, retrying
On Mon, Feb 13, 2012 at 1:20 PM, Jeff Chua <jeff.chua.linux@...il.com> wrote:
> On Mon, Feb 13, 2012 at 1:16 PM, Jeff Chua <jeff.chua.linux@...il.com> wrote:
>> On Mon, Feb 13, 2012 at 12:41 PM, Jeff Chua <jeff.chua.linux@...il.com> wrote:
>>> I ran tests for frequency that works dd out 1G of data from 8MHz to
>>> 16MHz, and it seems frequency less than 8.4MHz can only transfer at
>>> rate of 14.3MB/s and above 8.4MHz, speed goes up to 18.3 MB/s. Above
>>> 17MHz, errors encounters.
>>>
>>> hz1 8000000 73.5029 s 14.3 MB/s
>>> hz2 8000000 73.4740 s 14.3 MB/s
>>> hz3 8000000 73.3982 s 14.3 MB/s
>>> hz1 8200000 71.9677 s 14.6 MB/s
>>> hz2 8200000 73.4936 s 14.3 MB/s
>>> hz3 8200000 73.3462 s 14.3 MB/s
>>> hz1 8400000 56.6296 s 18.5 MB/s
>>> hz2 8400000 56.7616 s 18.5 MB/s
>>> hz3 8400000 56.7926 s 18.5 MB/s
>>> hz1 8600000 56.6622 s 18.5 MB/s
>>> hz2 8600000 56.7201 s 18.5 MB/s
>>> hz3 8600000 56.6476 s 18.5 MB/s
>>> hz1 8800000 56.8846 s 18.4 MB/s
>>> hz2 8800000 56.8226 s 18.5 MB/s
>>> hz3 8800000 56.7070 s 18.5 MB/s
>>
>> I've turned on write, and there's no error writing. But speed is
>> slower than accessing it via USB2 SD card reader. Same SD.
>>
>
> Via SD PCI
> 18.779 sec 4.04 %cpu
>
> Via USB2.0 Card Reader
> 12.205 sec 2.04 %cpu
>
> Via USB3.0 Card Reader
> 11.427 sec 2.01 %cpu
>
>
> Shouldn't PCI SD be faster? Same SD used for all tests.
Are there any thoughts on this or I should give up hope on the SD :((
Or is there something else I should try?
Thanks,
Jeff
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists