From: Steven Haigh <netwiz@crc.id.au>
To: linux-raid@vger.kernel.org
Subject: Re: What layout with 6x2TB, Intel Atom?
Date: Tue, 05 Feb 2013 09:59:59 +1100 [thread overview]
Message-ID: <51103D6F.8060602@crc.id.au> (raw)
In-Reply-To: <20130205031232.61813f6c@natsu>
[-- Attachment #1: Type: text/plain, Size: 1711 bytes --]
On 5/02/2013 8:12 AM, Roman Mamedov wrote:
> On Mon, 4 Feb 2013 20:27:42 +0000
> Mathias Burén <mathias.buren@gmail.com> wrote:
>
>> I read that the far layout gives faster read performance compared to
>> standard RAID1 in a 2 HDD array, so that's why I used it. I then
>> created yet another RAID10 f2 layout of the 3x 2 disk RAID10 volumes,
>> giving me /dev/md124. Filesystem doesn't matter, I need something
>> that's stable with good performance over the RAID set.
>> I just realized that out of 12 TB raw space I now only have 3TB
>> available, heh. So I suppose I'm going for a different layout.
>>
>> Any opinions?
>
> Hello,
>
> Why won't you even consider RAID6? To me it seems like the perfect choice,
> given the details you described (mostly reads, large files, few clients).
> And the disk count is perfect, not too few and not too many, so to say :D
>
I was going to say the same. I run a 4 x 2Tb SATA RAID6. The read speeds
will *easily* saturate GigE. Random seeks slow things down quite a bit -
but you'll get that with any setup except SSD.
If its mainly sequential reads, then RAID6 will be fine.
And as I know someone will ask... Why 4 drives in RAID6? Firstly, you
still get the redundancy of surviving 2 drive failures - but also when I
start to run low on space I can easily add another 2Tb disk and reshape
to 5 drives, then 6. My chassis has 8 x SATA hot swap bays - 2 x 80Gb
RAID1 leaving the other 6 for the RAID6. By the time I fill up 6 x 2Tb
drives, there will be other cheap multi-Tb drives to use.
--
Steven Haigh
Email: netwiz@crc.id.au
Web: http://www.crc.id.au
Phone: (03) 9001 6090 - 0412 935 897
Fax: (03) 8338 0299
[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 4240 bytes --]
prev parent reply other threads:[~2013-02-04 22:59 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-02-04 20:27 What layout with 6x2TB, Intel Atom? Mathias Burén
2013-02-04 20:29 ` Mathias Burén
2013-02-04 20:47 ` Mathias Burén
2013-02-04 23:15 ` Stan Hoeppner
2013-02-05 0:01 ` Roy Sigurd Karlsbakk
2013-02-05 14:17 ` Stan Hoeppner
2013-02-05 0:04 ` Roy Sigurd Karlsbakk
2013-02-04 21:12 ` Roman Mamedov
2013-02-04 22:59 ` Steven Haigh [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=51103D6F.8060602@crc.id.au \
--to=netwiz@crc.id.au \
--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).