RAID-3?

[Greg 'groggy' Lehey]

[Format recovered--see http://www.lemis.com/email/email-format.html]

Broken quotes fixed.

On Thursday, 19 August 2004 at  0:00:55 -0600, Scott Long wrote:
> Greg 'groggy' Lehey wrote:
>> On Tuesday, 17 August 2004 at 15:44:04 +0200, Poul-Henning Kamp wrote:
>>> In message <20040817132740.GA32139 at freebie.xs4all.nl>, Wilko Bulte writes:
>>>
>>>> RAID-3 IIRC uses a dedicated parity disk, and small stripes.  I
>>>> don't think it must be bytelevel striping.  Just small enough
>>>> stripes that all disks contribute to every I/O
>>>
>>> RAID3 differs from RAID5 in that you always access the entire stripe
>>> and never have R/M/W cycles.
>>
>> That's not the definition I know, and I haven't been able to find it
>> during a quick Google.  I have:
>>
>>  http://sbc.webopedia.com/TERM/R/RAID.html :
>>  ...
>>  http://www.acnc.com/04_01_03.html :
>>  ...
>
> I think that you're really reading far too much into this.

That depends on whether you care about accurate terminology or not.
Or maybe it's you who is reading too much into the matter.

> The key to all of the definitions that you quoted is that all drives
> are accessed during a read or write, unlike RAID-4.

That's a feature, but it's only part of the definition.  Note that
RAID-4 and RAID-5 can also access all drives, depending on the size of
a read or write, so it can't be a complete definition.

> Your quoted text also seems a bit subjective as there are very valid
> reasons for RAID-3, especially if one is looking for consistent
> low-latency transactions like in video recorders and servers.

Well, I did use *exactly* this example.  I also pointed out that the
relative performance of modern disk subsystems is adequate for a
single streaming video channel.

Low latency depends on the number of concurrent accesses.  RAID-3
handles concurrent access poorly, exactly because it accesses all
disks for each transfer.

> That is a world of difference from a general purpose
> multi-transaction, multi-process workload, 

Agreed.  I was just wondering why anybody would bother.

> so comparing against RAID-4 or RAID-5 really doesn't make sense.

I didn't.

> Whether Pawel's implementation conforms to your ideas of RAID-3 is
> somewhat irrelevant.

I don't know.  "My ideas" of RAID-3 appear to be in keeping with the
standard definitions.  To draw from a discussion currently under way
on the IRC channel, we're not Humpty Dumpty, who said "When I use a
word, it means exactly what I intend it to mean".

> He's doing an excellent job with storage research at the moment, 

I'm not criticizing Pawel.  

> I don't see why he should get bogged down with idle nit-picking.

If you think this is idle nit-picking, that's fine.  I think we owe it
to people to use correct terminology.

Pawel, what do you see as the use of RAID-3?

Greg
--
When replying to this message, please take care not to mutilate the
original text.  
For more information, see http://www.lemis.com/email.html
Note: I discard all HTML mail unseen.
Finger grog at FreeBSD.org for PGP public key.
See complete headers for address and phone numbers.
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 187 bytes
Desc: not available
Url : http://lists.freebsd.org/pipermail/cvs-src/attachments/20040819/99c893a8/attachment.bin