From: Neil Brown <neilb@suse.de>
To: Peter Rabbitson <rabbit@rabbit.us>
Cc: linux-raid@vger.kernel.org
Subject: Re: mismatch_cnt questions - how about raid10?
Date: Tue, 6 Mar 2007 21:20:12 +1100 [thread overview]
Message-ID: <17901.16476.282987.982971@notabene.brown> (raw)
In-Reply-To: message from Peter Rabbitson on Tuesday March 6
On Tuesday March 6, rabbit@rabbit.us wrote:
> Neil Brown wrote:
> > When we write to a raid1, the data is DMAed from memory out to each
> > device independently, so if the memory changes between the two (or
> > more) DMA operations, you will get inconsistency between the devices.
>
> Does this apply to raid 10 devices too? And in case of LVM if swap is on
> top of a LV which is a part of a VG which has a single PV as the raid
> array - will this happen as well? Or will the LVM layer take the data
> once and distribute exact copies of it to the PVs (in this case just the
> raid) effectively giving the raid array invariable data?
Yes, it applies to raid10 too.
I don't know the details of the inner workings of LVM, but I doubt it
will make a difference. Copying the data in memory is just too costly
to do if it can be avoided. With LVM and raid1/10 it can be avoided
with no significant cost.
With raid4/5/6, not copying into the cache can cause data corruption.
So we always copy.
NeilBrown
next prev parent reply other threads:[~2007-03-06 10:20 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-03-04 11:22 mismatch_cnt questions Christian Pernegger
2007-03-04 11:50 ` Neil Brown
2007-03-04 12:01 ` Christian Pernegger
2007-03-04 22:19 ` Neil Brown
2007-03-06 10:04 ` mismatch_cnt questions - how about raid10? Peter Rabbitson
2007-03-06 10:20 ` Neil Brown [this message]
2007-03-06 10:56 ` Peter Rabbitson
2007-03-06 10:59 ` Justin Piszcz
2007-03-12 5:35 ` Neil Brown
2007-03-12 14:26 ` Peter Rabbitson
2007-03-04 21:21 ` mismatch_cnt questions Eyal Lebedinsky
2007-03-04 22:30 ` Neil Brown
2007-03-05 7:45 ` Eyal Lebedinsky
2007-03-05 14:56 ` detecting/correcting _slightly_ flaky disks Michael Stumpf
2007-03-05 15:09 ` Justin Piszcz
2007-03-05 17:01 ` Michael Stumpf
2007-03-05 17:11 ` Justin Piszcz
2007-03-07 0:14 ` Bill Davidsen
2007-03-07 1:37 ` Michael Stumpf
2007-03-07 13:57 ` berk walker
2007-03-07 15:01 ` Bill Davidsen
2007-03-05 23:40 ` mismatch_cnt questions Neil Brown
2007-03-07 0:22 ` Bill Davidsen
2007-03-08 6:39 ` H. Peter Anvin
2007-03-08 13:54 ` Martin K. Petersen
2007-03-09 2:00 ` Bill Davidsen
2007-03-09 4:20 ` H. Peter Anvin
2007-03-09 5:20 ` Bill Davidsen
2007-03-08 6:34 ` H. Peter Anvin
2007-03-08 7:00 ` H. Peter Anvin
2007-03-08 8:21 ` H. Peter Anvin
2007-03-13 9:58 ` Andre Noll
2007-03-13 23:46 ` H. Peter Anvin
2007-03-06 6:27 ` Paul Davidson
2008-05-12 11:16 ` Bas van Schaik
2008-05-12 14:31 ` Justin Piszcz
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=17901.16476.282987.982971@notabene.brown \
--to=neilb@suse.de \
--cc=linux-raid@vger.kernel.org \
--cc=rabbit@rabbit.us \
/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).