mirror of https://lore.kernel.org/lkml/
 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 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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®