From: Robert Hancock <hancockrwd@gmail.com>
To: Richard <tuxbox.guru@gmail.com>
Cc: linux-ide@vger.kernel.org
Subject: Re: SATA device powerdown
Date: Fri, 30 Jul 2010 12:12:44 -0600 [thread overview]
Message-ID: <4C53161C.6050308@gmail.com> (raw)
In-Reply-To: <4C52CCCC.7010902@gmail.com>
On 07/30/2010 06:59 AM, Richard wrote:
> Hi All,
>
> I have a question relating to the ATA drives and a SATA drive powerdown.
> Currently you can issue a HDD Spindown/Sleep command to a drive which
> will result in it going to sleep, but I have a hardware platform that
> requires the drive to be Powered-Off completely. (its in an extreme
> energy saving mode)
>
> Normal modes the HDD can sleep, and when any IO happens the disk wakes..
>
> I can get the HDD to power-off when it enters deep-sleep (SMART register
> reading) but how can I get the disk to re-powered before next access is
> needed. Currently the /dev/sdx deregisters when the SATA bus is
> disconnected and re-registers when the device is avaliable.
>
> Is there a method to keep the open files alive when the HDD is powered
> off and execute a custom hardware relay switch to power the HDD back up
> and continue working with the files that were open previous to the sleep?
>
> Is this at all possible?
At present I don't think this is possible. I suppose one thing you could
do would be to hack whatever ATA driver the system was using to ignore
all hotplug notifications, but then you'd have to make other changes to
wake up the drive again when an access was required.
If you really need to retain apparent access to the disk when it's
switched off, I kind of question whether the power saving from this is
worthwhile compared to just turning on aggressive SATA link power
management and putting the disk in standby mode..
prev parent reply other threads:[~2010-07-30 18:12 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-07-30 12:59 SATA device powerdown Richard
2010-07-30 18:12 ` Robert Hancock [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=4C53161C.6050308@gmail.com \
--to=hancockrwd@gmail.com \
--cc=linux-ide@vger.kernel.org \
--cc=tuxbox.guru@gmail.com \
/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;
as well as URLs for NNTP newsgroup(s).