[ale] Confusing RAID Performance

[Greg Freemyer]

On Wed, Feb 2, 2011 at 4:23 PM, Jeff Hubbs <jhubbslist at att.net> wrote:
> On 2/2/11 2:15 PM, scott wrote:
>> Remember that RAID6 is slower than RAID5.  RAID5 calculates the parity
>> once.  RAID6 does it twice.  This is to make sure that you have parity
>> protection incase you drop a drive. I would only recommend RAID6 on
>> large drives (1TB or larger).
> I sure wouldn't.  For >=~1TB drives, the probability of having an
> unrecoverable read error among all the drives at recover time starts
> becoming significant.  Sure, you can use it - as long as a restore from
> tape, etc. is an acceptable fallback if you can't rebuild after a drive
> replacement.

If you have a double drive failure with raid-6, then yes a single
non-recoverable read error will prevent the recovery from working.

With a single drive failure raid 6 survives a non-recoverable read
error during raid recovery so I don't understand your comment.

For raid-6 to fail to recover with a single dead drive, you need to
have two non-recoverable errors at the same LBA on two of the drives
you are trying to recover from.  That is a 1 in billion event.  (Or
even less likely).

Thus raid-6 with large drives offers the same basic protection raid-5
did with small drives.  Ie. both will survive a single drive failure
and allow rebuild as long as you get it rebuilt prior to a second
drive failing.

Maybe you are thinking of Raid5.  I totally would avoid raid 5 with
large drives.

Greg