From: Mark Lord <kernel@teksavvy.com>
To: Greg Freemyer <greg.freemyer@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
foo saa <foosaa@gmail.com>,
linux-kernel@vger.kernel.org, linux-ide@vger.kernel.org,
Jens Axboe <jens.axboe@oracle.com>,
linux-mm@kvack.org
Subject: Re: Linux kernel - Libata bad block error handling to user mode program
Date: Thu, 04 Mar 2010 09:41:48 -0500 [thread overview]
Message-ID: <4B8FC6AC.4060801@teksavvy.com> (raw)
In-Reply-To: <87f94c371003040617t4a4fcd0dt1c9fc0f50e6002c4@mail.gmail.com>
On 03/04/10 09:17, Greg Freemyer wrote:
..
> I think / suspect your major problem is you say above that you use a
> 512-byte buffer to wipe with. The kernel is using 4K pages. So when
> you write to a 4K section of the drive for the first time, the kernel
> implements read-modify-write logic.
>
> Your i/o failures are almost certainly on the read cycle of the above,
> not the write cycle. You need to move to 4K buffers and you need to
> ensure your 4K writes are aligned with how the kernel is working with
> the disk. ie. You need your 4K buffer to perfectly align with the
> kernels 4K block handling so you never have a read-modify-write cycle.
..
You'll also need to disable Linux read-ahead for the drive,
or it may try reading beyond even the 4KB block.
But really.. isn't "hdparm --security-erase NULL /dev/sdX" good enough ???
Cheers
WARNING: multiple messages have this Message-ID (diff)
From: Mark Lord <kernel@teksavvy.com>
To: Greg Freemyer <greg.freemyer@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
foo saa <foosaa@gmail.com>,
linux-kernel@vger.kernel.org, linux-ide@vger.kernel.org,
Jens Axboe <jens.axboe@oracle.com>,
linux-mm@kvack.org
Subject: Re: Linux kernel - Libata bad block error handling to user mode program
Date: Thu, 04 Mar 2010 09:41:48 -0500 [thread overview]
Message-ID: <4B8FC6AC.4060801@teksavvy.com> (raw)
In-Reply-To: <87f94c371003040617t4a4fcd0dt1c9fc0f50e6002c4@mail.gmail.com>
On 03/04/10 09:17, Greg Freemyer wrote:
..
> I think / suspect your major problem is you say above that you use a
> 512-byte buffer to wipe with. The kernel is using 4K pages. So when
> you write to a 4K section of the drive for the first time, the kernel
> implements read-modify-write logic.
>
> Your i/o failures are almost certainly on the read cycle of the above,
> not the write cycle. You need to move to 4K buffers and you need to
> ensure your 4K writes are aligned with how the kernel is working with
> the disk. ie. You need your 4K buffer to perfectly align with the
> kernels 4K block handling so you never have a read-modify-write cycle.
..
You'll also need to disable Linux read-ahead for the drive,
or it may try reading beyond even the 4KB block.
But really.. isn't "hdparm --security-erase NULL /dev/sdX" good enough ???
Cheers
WARNING: multiple messages have this Message-ID (diff)
From: Mark Lord <kernel@teksavvy.com>
To: Greg Freemyer <greg.freemyer@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
foo saa <foosaa@gmail.com>,
linux-kernel@vger.kernel.org, linux-ide@vger.kernel.org,
Jens Axboe <jens.axboe@oracle.com>,
linux-mm@kvack.org
Subject: Re: Linux kernel - Libata bad block error handling to user mode program
Date: Thu, 04 Mar 2010 09:41:48 -0500 [thread overview]
Message-ID: <4B8FC6AC.4060801@teksavvy.com> (raw)
In-Reply-To: <87f94c371003040617t4a4fcd0dt1c9fc0f50e6002c4@mail.gmail.com>
On 03/04/10 09:17, Greg Freemyer wrote:
..
> I think / suspect your major problem is you say above that you use a
> 512-byte buffer to wipe with. The kernel is using 4K pages. So when
> you write to a 4K section of the drive for the first time, the kernel
> implements read-modify-write logic.
>
> Your i/o failures are almost certainly on the read cycle of the above,
> not the write cycle. You need to move to 4K buffers and you need to
> ensure your 4K writes are aligned with how the kernel is working with
> the disk. ie. You need your 4K buffer to perfectly align with the
> kernels 4K block handling so you never have a read-modify-write cycle.
..
You'll also need to disable Linux read-ahead for the drive,
or it may try reading beyond even the 4KB block.
But really.. isn't "hdparm --security-erase NULL /dev/sdX" good enough ???
Cheers
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2010-03-04 14:41 UTC|newest]
Thread overview: 85+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-03-04 4:52 Linux kernel - Libata bad block error handling to user mode program foo saa
2010-03-04 6:42 ` Andrew Morton
2010-03-04 6:42 ` Andrew Morton
2010-03-04 12:58 ` foo saa
2010-03-04 12:58 ` foo saa
2010-03-04 16:31 ` Mike Hayward
2010-03-04 16:31 ` Mike Hayward
2010-03-04 18:12 ` s ponnusa
2010-03-04 18:12 ` s ponnusa
2010-03-04 18:12 ` s ponnusa
2010-03-05 0:42 ` Mike Hayward
2010-03-05 0:42 ` Mike Hayward
2010-03-05 0:42 ` Mike Hayward
2010-03-05 2:23 ` s ponnusa
2010-03-05 2:23 ` s ponnusa
2010-03-05 2:23 ` s ponnusa
2010-03-05 16:31 ` Mike Hayward
2010-03-05 16:31 ` Mike Hayward
2010-03-05 6:01 ` Greg Freemyer
2010-03-05 6:01 ` Greg Freemyer
2010-03-05 6:01 ` Greg Freemyer
2010-03-05 13:04 ` Alan Cox
2010-03-05 13:04 ` Alan Cox
2010-03-04 16:37 ` Mike Hayward
2010-03-04 16:37 ` Mike Hayward
2010-03-04 18:23 ` s ponnusa
2010-03-04 18:23 ` s ponnusa
2010-03-04 18:23 ` s ponnusa
2010-03-04 14:17 ` Greg Freemyer
2010-03-04 14:17 ` Greg Freemyer
2010-03-04 14:17 ` Greg Freemyer
2010-03-04 14:41 ` Mark Lord [this message]
2010-03-04 14:41 ` Mark Lord
2010-03-04 14:41 ` Mark Lord
2010-03-04 15:33 ` foo saa
2010-03-04 15:33 ` foo saa
2010-03-04 17:49 ` Mark Lord
2010-03-04 17:49 ` Mark Lord
2010-03-04 18:20 ` s ponnusa
2010-03-04 18:20 ` s ponnusa
2010-03-04 18:20 ` s ponnusa
2010-03-04 19:41 ` Greg Freemyer
2010-03-04 19:41 ` Greg Freemyer
2010-03-04 19:41 ` Greg Freemyer
2010-03-04 19:50 ` s ponnusa
2010-03-04 19:50 ` s ponnusa
2010-03-04 19:50 ` s ponnusa
2010-03-05 1:58 ` Robert Hancock
2010-03-05 1:58 ` Robert Hancock
2010-03-05 2:11 ` s ponnusa
2010-03-05 2:11 ` s ponnusa
2010-03-05 2:16 ` Robert Hancock
2010-03-05 2:16 ` Robert Hancock
2010-03-05 2:16 ` Robert Hancock
2010-03-05 2:17 ` s ponnusa
2010-03-05 2:17 ` s ponnusa
2010-03-05 2:17 ` s ponnusa
2010-03-05 12:03 ` Alan Cox
2010-03-05 12:03 ` Alan Cox
2010-03-05 22:27 ` s ponnusa
2010-03-05 22:27 ` s ponnusa
2010-03-05 22:27 ` s ponnusa
2010-03-11 18:29 ` Greg Freemyer
2010-03-11 18:29 ` Greg Freemyer
2010-03-13 22:44 ` s ponnusa
2010-03-13 22:44 ` s ponnusa
2010-03-13 22:44 ` s ponnusa
2010-03-13 23:44 ` Robert Hancock
2010-03-13 23:44 ` Robert Hancock
2010-03-13 23:44 ` Robert Hancock
2010-03-14 0:12 ` s ponnusa
2010-03-14 0:12 ` s ponnusa
2010-03-14 0:12 ` s ponnusa
2010-03-14 5:06 ` Robert Hancock
2010-03-14 5:06 ` Robert Hancock
2010-03-14 16:02 ` Mark Lord
2010-03-14 16:02 ` Mark Lord
2010-03-14 16:02 ` Mark Lord
2010-03-14 16:12 ` Greg Freemyer
2010-03-14 16:12 ` Greg Freemyer
-- strict thread matches above, loose matches on Subject: below --
2010-03-04 18:40 Kalra Ashish-B00888
2010-03-04 18:40 ` Kalra Ashish-B00888
2010-03-04 18:40 ` Kalra Ashish-B00888
2010-03-04 18:41 Kalra Ashish-B00888
2010-03-04 18:41 ` Kalra Ashish-B00888
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=4B8FC6AC.4060801@teksavvy.com \
--to=kernel@teksavvy.com \
--cc=akpm@linux-foundation.org \
--cc=foosaa@gmail.com \
--cc=greg.freemyer@gmail.com \
--cc=jens.axboe@oracle.com \
--cc=linux-ide@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.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.