From: "Kristin Vadas Marsicano" <kristin.marsicano@gmail.com>
To: Alan Cox <alan@lxorguk.ukuu.org.uk>
Cc: linux-ide@vger.kernel.org
Subject: Re: Trouble with hdparm -d on Dell D610
Date: Tue, 15 Jan 2008 13:26:49 -0500 [thread overview]
Message-ID: <7f68de3e0801151026t5c92d56am5a4f5274a744a642@mail.gmail.com> (raw)
In-Reply-To: <20080111213415.56d90f0d@lxorguk.ukuu.org.uk>
I've tried the following configurations, none of which ended up in DMA
functioning on the D610.
# CONFIG_BLK_DEV_PIIX is not set
CONFIG_ATA_PIIX=y
CONFIG_PATA_MPIIX=y
CONFIG_PATA_OLDPIIX=y
# CONFIG_BLK_DEV_PIIX is not set
CONFIG_ATA_PIIX=y
CONFIG_PATA_MPIIX=y
# CONFIG_PATA_OLDPIIX is not set
Ultimately, my goal is to run shred at as quick a pace as possible on
all machines. The D610 runs slow with the kernel config I was using
for the D600 (any various other machines). I had success on making it
run quickly on the D610 by configured the kernel with
ATA/ATAPI/MFM/RLL support turned off completely.
Any thoughts as to why the configs listed above don't seem to work for
DMA on my D610?
On 1/11/08, Alan Cox <alan@lxorguk.ukuu.org.uk> wrote:
> > My concern with disabling the new drivers is as follows: I use this
> > linux kernel and config image to boot machines over PXE and call a
> > shred program on each of the harddrives. If I turn off CONFIG_ATA,
> > will this limit my ability to support various new IDE and SATA drives
> > for running shred? So far, the configuration I have works well with
>
> Yes. In that case you can build without CONFIG_IDE_PIIX and with the
> CONFIG_ATA_PIIX driver and you should be fine too (but your disk will
> move to /dev/sda on that box). The PIIX is an awkward case as in some
> modes it combines both the SATA and PATA onto one 'device'.
>
> > most of the machines I encounter (and with both SATA and IDE drives),
> > except for the Dell D610 and HP 7700 (small desktop pc). The models I
> > just mentioned run the shred really slow, which I believe is due to
> > the DMA problem I was having (outlined in my previous emails). Any
> > thoughts?
>
> If your shred program is relying on DMA then you are using the wrong tool
> for the job. The correct way to erase a disk is to send it a security
> erase command. Rewriting over the data may not do what is wanted.
>
--
Kristin Vadas Marsicano
kristin.marsicano@gmail.com
kristinisme.blogspot.com
prev parent reply other threads:[~2008-01-15 18:26 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-01-11 19:18 Trouble with hdparm -d on Dell D610 Kristin Vadas Marsicano
2008-01-11 19:30 ` Alan Cox
2008-01-11 19:49 ` Kristin Vadas Marsicano
2008-01-11 19:55 ` Alan Cox
2008-01-11 20:27 ` Kristin Vadas Marsicano
2008-01-11 21:05 ` Alan Cox
2008-01-11 21:27 ` Kristin Vadas Marsicano
2008-01-11 21:34 ` Alan Cox
2008-01-11 21:49 ` Kristin Vadas Marsicano
2008-01-11 21:54 ` Greg Freemyer
2008-01-12 5:08 ` Mark Lord
2008-01-11 21:51 ` Greg Freemyer
2008-01-12 0:06 ` Alan Cox
2008-01-14 22:48 ` Kristin Vadas Marsicano
2008-01-14 23:14 ` Alan Cox
2008-01-15 18:26 ` Kristin Vadas Marsicano [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=7f68de3e0801151026t5c92d56am5a4f5274a744a642@mail.gmail.com \
--to=kristin.marsicano@gmail.com \
--cc=alan@lxorguk.ukuu.org.uk \
--cc=linux-ide@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;
as well as URLs for NNTP newsgroup(s).