RAID 5 of RAID 5's?

RAID 5 of RAID 5's?

[Dan Stromberg]

[-- Attachment #1: Type: text/plain, Size: 133 bytes --]


Has anyone constructed a RAID 5 of RAID 5's using mdadm on a linux
system?

Was it reliable?

How large was it?

Thanks!


[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 189 bytes --]

Re: RAID 5 of RAID 5's?

[Laurent CARON]

Dan Stromberg a écrit :

>Has anyone constructed a RAID 5 of RAID 5's using mdadm on a linux
>system?
>
>Was it reliable?
>
>How large was it?
>
>Thanks!
>
>  
>
Seems to be a large waste of space....
-
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: RAID 5 of RAID 5's?

[Brad Dameron]

On Fri, 2005-06-10 at 00:11, Laurent CARON wrote:
> Dan Stromberg a écrit :
> 
> >Has anyone constructed a RAID 5 of RAID 5's using mdadm on a linux
> >system?
> >
> >Was it reliable?
> >
> >How large was it?
> >
> >Thanks!
> >
> >  
> >
> Seems to be a large waste of space....
> -

Ya that does. I have done a RAID0 of 2 RAID5's. Or a RAID50. Work's
great. I think a RAID5 of RAID5's is going to have some seriously slow
write performance. 

Brad Dameron
SeaTab Software
www.seatab.com

-
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: RAID 5 of RAID 5's?

[Dan Stromberg]

[-- Attachment #1: Type: text/plain, Size: 763 bytes --]

On Fri, 2005-06-10 at 09:11 +0200, Laurent CARON wrote:
> Dan Stromberg a écrit :
> 
> >Has anyone constructed a RAID 5 of RAID 5's using mdadm on a linux
> >system?
> >
> >Was it reliable?
> >
> >How large was it?
> >
> >Thanks!
> >
> >  
> >
> Seems to be a large waste of space....

Consider:

You have a bunch of "bricks" that can shuffle data between a NAS head
and a bunch of disks.

The disks are RAID'd (through the "bricks"), but if one of the bricks
themselves dies, you're kinda stuck.

But if you RAID 5 the RAID 5's, then you don't end up with massive
parity pounding, and your bricks aren't a single point of failure, and
you don't lose as much space as if you mirrored.

Sound copacetic?

Thanks for your feedback!


[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 189 bytes --]

Re: RAID 5 of RAID 5's?

[Andy Smith]

[-- Attachment #1: Type: text/plain, Size: 2549 bytes --]

On Fri, Jun 10, 2005 at 01:43:39PM -0700, Dan Stromberg wrote:
> Consider:
> 
> You have a bunch of "bricks" that can shuffle data between a NAS head
> and a bunch of disks.
> 
> The disks are RAID'd (through the "bricks"), but if one of the bricks
> themselves dies, you're kinda stuck.
> 
> But if you RAID 5 the RAID 5's, then you don't end up with massive
> parity pounding, and your bricks aren't a single point of failure, and
> you don't lose as much space as if you mirrored.

Off the top of my head, this is what I am thinking, but I could well
have missed something...

Assume you have 50 disks.

If you organise them as 25 two disk RAID 1s and then RAID 0 the RAID
1s you end up with the capacity of 25 disks.  Any given read will
benefit from a 25-way stripe; any given write suffers a 2-way
mirror.

If a disk dies then it alone will be rebuilt from its single mirror
pair.  You can lose up to 25 disks and still not lose any data, as
long as no more than 1 disk from each pair survives.

If you organise them as 10 five disk RAID 5s and then RAID 5 the
RAID 5s you end up with the capacity of (5-1)*(10-1)=36 disks.
Depending on your RAID technology, reads may be as fast as a 10-way
stripe.  As far as I can see though, a write would have to be
striped to 10 RAID 5s, which would itself be striped to 5 disks
each, so it would be a 50-way write.

You could stand to lose a maximum of 1 disk in each of the low-level
RAID 5s, plus one of the top-level RAID 5s, so I suppose the maximum
you could get away with would be 10 (one from each low-level) plus
the other 4 from a single low-level, for a total of 14.  If you lose
a single disk then you'll need a parity rebuild from 4 disks.  If
you lost a low-level RAID 5 then I'm not sure how that would work;
it would be reading to rebuild from parity so presumably it would
take advantage of the stripe and be like only reading from 9 disks?

With 20 disks, the RAID 10 scenario ends up with 10 disks of
capacity, maximum 10 disks can fail, reads are as a 10-way stripe,
writes are as a 2-way mirror.  The RAID 55 scenario assuming 4-disk
low-level RAID 5s would be 15 disks of capacity, could theoretically
have 8 disks fail and still run degraded.  I think reads would be as
from a 5-way stripe, with writes striped across 20 disks.

So, unless I have misunderstood, depending on how you split the RAID
5s you'll get about 75% of the disk as opposed to 50% for RAID 10,
but the write performance and the reliability seem much worse.

[-- Attachment #2: Digital signature --]
[-- Type: application/pgp-signature, Size: 189 bytes --]

Re: RAID 5 of RAID 5's?

[Laurent CARON]

Dan Stromberg a écrit :

>On Fri, 2005-06-10 at 09:11 +0200, Laurent CARON wrote:
>  
>
>>Dan Stromberg a écrit :
>>
>>    
>>
>>>Has anyone constructed a RAID 5 of RAID 5's using mdadm on a linux
>>>system?
>>>
>>>Was it reliable?
>>>
>>>How large was it?
>>>
>>>Thanks!
>>>
>>> 
>>>
>>>      
>>>
>>Seems to be a large waste of space....
>>    
>>
>
>Consider:
>
>You have a bunch of "bricks" that can shuffle data between a NAS head
>and a bunch of disks.
>
>The disks are RAID'd (through the "bricks"), but if one of the bricks
>themselves dies, you're kinda stuck.
>
>But if you RAID 5 the RAID 5's, then you don't end up with massive
>parity pounding, and your bricks aren't a single point of failure, and
>you don't lose as much space as if you mirrored.
>
>Sound copacetic?
>
>Thanks for your feedback!
>
>  
>
RAID 10 is IMHO a bit more efficient.

Raid 5 means at least 9 disks:
Usable capacity: 4 Disks
Read speed: Good
Write speed: poor

Raid 10 with 8 disks can store the same amount of data.
Read speed: Average
Write Speed: Better than raid5


-
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: RAID 5 of RAID 5's?

[Andy Smith]

[-- Attachment #1: Type: text/plain, Size: 896 bytes --]

On Mon, Jun 13, 2005 at 09:15:39AM +0200, Laurent CARON wrote:
> Dan Stromberg a ?crit :
> >>>Has anyone constructed a RAID 5 of RAID 5's using mdadm on a linux
> >>>system?
> >>>
> >>>Was it reliable?
> >>>
> >>>How large was it?
> >
> RAID 10 is IMHO a bit more efficient.
> 
> Raid 5 means at least 9 disks:
> Usable capacity: 4 Disks
> Read speed: Good
> Write speed: poor

With a low number of disks, you would indeed get the same or less
capacity with RAID 5 + RAID 5 as compared to RAID 10, but as the
number of disks gets higher, doesn't the capacity of RAID 5 on top
of RAID 5 (we need a name for this, is RAID 55 technically correct?)
get better?

For example, 30 disks, organised as 10 3-disk RAID 5s, have 9*2 or
18 disks of capacity, whereas a RAID 10 of same would be 15 disks.

The write performance seems bad though, and maybe the rebuild time
as well.

[-- Attachment #2: Digital signature --]
[-- Type: application/pgp-signature, Size: 189 bytes --]

Re: RAID 5 of RAID 5's?

[Dan Stromberg]

[-- Attachment #1: Type: text/plain, Size: 1718 bytes --]

On Sun, 2005-06-12 at 00:45 +0000, Andy Smith wrote:
> On Fri, Jun 10, 2005 at 01:43:39PM -0700, Dan Stromberg wrote:
> > Consider:
> > 
> > You have a bunch of "bricks" that can shuffle data between a NAS head
> > and a bunch of disks.
> > 
> > The disks are RAID'd (through the "bricks"), but if one of the bricks
> > themselves dies, you're kinda stuck.
> > 
> > But if you RAID 5 the RAID 5's, then you don't end up with massive
> > parity pounding, and your bricks aren't a single point of failure, and
> > you don't lose as much space as if you mirrored.
> 
> Off the top of my head, this is what I am thinking, but I could well
> have missed something...
> 
> Assume you have 50 disks.

I guess we're talking about 200 or so, but the ideas are pretty similar
in either case I imagine.

> If you organise them as 10 five disk RAID 5s and then RAID 5 the
> RAID 5s you end up with the capacity of (5-1)*(10-1)=36 disks.
> Depending on your RAID technology, reads may be as fast as a 10-way
> stripe.  As far as I can see though, a write would have to be
> striped to 10 RAID 5s, which would itself be striped to 5 disks
> each, so it would be a 50-way write.

Well...  Does RAID not usually read from n-1 disks, and write to 2, in a
typical RAID 5 config when writing a single block?



> So, unless I have misunderstood, depending on how you split the RAID
> 5s you'll get about 75% of the disk as opposed to 50% for RAID 10,
> but the write performance and the reliability seem much worse.

Hmmmmmm...  What about these forms of RAID that are supposed to be able
to say, lose n-4 disks for an up-to-4-disk failure?  What would they be
like on a 200 disk RAID array?



[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 189 bytes --]