From: Andrew Dunn <andrew.g.dunn@gmail.com>
To: Beolach <beolach@gmail.com>
Cc: linux-raid@vger.kernel.org
Subject: Re: Successful RAID 6 setup
Date: Sun, 08 Nov 2009 08:31:45 -0500 [thread overview]
Message-ID: <4AF6C841.5070908@gmail.com> (raw)
In-Reply-To: <aebf5d970911072307u2168cf1am793aa6c4b17a1b14@mail.gmail.com>
Thanks for the replies.
I began using mdadm in ubuntu 8.04, which I believe was the 2.6.24
kernel. The rebuild times under this kernel with 6 500GiB drives were
very fast... I think like 100-200m, but that was with a raid5.
Using raid6 under ubuntu 9.04 , which was 2.6.28 I would get 20m rebuild
times on raid6 with 1TiB drives. This would take literally 10-14 hours
depending on my array size.
Now with ubuntu 9.10, which is 2.6.31 I get like 50-75m on the same
exact raid6 rebuild.
I didn't realize that software/OS mattered so much for performance from
kernel to kernel.
I need to look more into this bitmap that people have mentioned.
Beolach wrote:
> On Wed, Nov 4, 2009 at 11:03, Andrew Dunn <andrew.g.dunn@gmail.com> wrote:
>
>> I sent this a couple days ago, wondering if it fell through the cracks or if I am asking the wrong questions.
>>
>> ------
>>
>> I will preface this by saying I only need about 100MB/s out of my array
>> because I access it via a gigabit crossover cable.
>>
>> I am backing up all of my information right now (~4TB) with the
>> intention of re-creating this array with a larger chunk size and
>> possibly tweaking the file system a little bit.
>>
>> My original array was a raid6 of 9 WD caviar black drives, the chunk
>> size was 64k. I use USAS-AOC-L8i controllers to address all of my drives
>> and the TLER setting on the drives is enabled for 7 seconds.
>>
>>
> <snip mdadm -D>
>
> That array should easily be able to fill your 100MB/s speed requirement. If
> you really are only accessing over a 1Gib/s link, I wouldn't worry much
> about tweaking for performance.
>
>
>> I have noticed slow rebuilding time when I first created the array and
>> intermittent lockups while writing large data sets.
>>
>> Per some reading I was thinking of adjusting my chunk size to 1024k, and
>> trying to figure out the weird stuff required when creating a file system.
>>
>>
>
> Can you quantify "slow rebuilding time"? And was that just when you first
> created the array, or do you still see slowness when you check/repair the
> array? Using a write-intent bitmap might help here.
>
> I don't know that any of the options discussed so far are likely to help w/
> intermittent lockups. When you see them, are you writing your data over
> the network? How badly does it lock up your system? What kernel version
> are you using?
>
>
> Good Luck,
> --
> Conway S. Smith
>
--
Andrew Dunn
http://agdunn.net
prev parent reply other threads:[~2009-11-08 13:31 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-11-04 18:03 Successful RAID 6 setup Andrew Dunn
2009-11-04 18:40 ` Leslie Rhorer
2009-11-07 18:35 ` Doug Ledford
2009-11-08 6:42 ` Beolach
2009-11-08 16:15 ` Doug Ledford
2009-11-09 17:37 ` Bill Davidsen
2009-11-06 21:22 ` Thomas Fjellstrom
2009-11-08 7:07 ` Beolach
2009-11-08 13:31 ` Andrew Dunn [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=4AF6C841.5070908@gmail.com \
--to=andrew.g.dunn@gmail.com \
--cc=beolach@gmail.com \
--cc=linux-raid@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).