All of lore.kernel.org
 help / color / mirror / Atom feed
From: Lutz Vieweg <lvml@5t9.de>
To: linux-kernel@vger.kernel.org
Subject: Re: Improving SD/SDHC/SDXC write performance by using a discard/TRIM like operation
Date: Mon, 04 Jun 2012 20:49:22 +0200	[thread overview]
Message-ID: <jqivvi$q7m$1@dough.gmane.org> (raw)
In-Reply-To: <jqiull$fvb$1@dough.gmane.org>

I just found another credible reference claiming existence of an "erase" command
for SD cards: The "SD Card Specification Simplified Version of: Part E1" (see:
http://www.sandisk.com/Assets/File/OEM/Manuals/SD_SDIO_specsv1.pdf ) states:

> ERASE_WR_BLK_START Sets the address of the first write block to be Index address erased.
> ERASE_WR_BLK_END Sets the address of the last write block of the address continuous range to be erased.

Since these are "SD bus commands", I wonder whether they are easily accessible
behind usual USB card reader hardware... but the mentioned "formatter" tool
seems to be able to do so.

Regards,

Lutz Vieweg


On 06/04/2012 08:27 PM, Lutz Vieweg wrote:
> When I read reports from (non-expert) users who claimed that they were able
> to restore the initial write performance of their SDXC cards by using a "special
> formatter tool" (while normal "formatting" did not improve performance),
> I was very sceptical, as I also had read that there is no way to discard/TRIM
> blocks on SD/SDHC/SDXC cards.
>
> But then I noticed that this "special formatter" tool was actually offered (for free)
> by the SD Association:
> https://www.sdcard.org/downloads/formatter_3/
> ... and its documentation clearly states that this tool is capable of using
> "flash erase" operations on SD cards, which are said to be different from
> ordinary "overwrites", see
> https://www.sdcard.org/downloads/formatter_3/SDFormatter_3.1e.pdf
> pages 7 ("Format type Erase" vs. "Format type Overwrite") and the screen shot on page 9.
>
> Now I wonder: Is there really such a thing as a command to erase NAND flashes
> in SD cards like there is for SSDs? If so, it would certainly be a good thing
> to support it with Linux block discard...
>
> Regards,
>
> Lutz Vieweg
>


      reply	other threads:[~2012-06-04 18:49 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-06-04 18:27 Improving SD/SDHC/SDXC write performance by using a discard/TRIM like operation Lutz Vieweg
2012-06-04 18:49 ` Lutz Vieweg [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to='jqivvi$q7m$1@dough.gmane.org' \
    --to=lvml@5t9.de \
    --cc=linux-kernel@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.