RE: HW RAID Controllers in response to Bruce

From: Schneider, Tim <SCHNEIDER_at_no.spam.please>
Date: Mon Mar 13 2000 - 15:18:49 CST

        1) sorry for the tacky formatting that this mesage may have, I
chopped it out of Netscape.
        2) link:
        3) I think I mis-read the paragraph on RAID 5 - it says Read
Performance is still not as good as it is for mirroring, I musta had a brain
fart or something I was sure it said it was slower that RAID 4.
        4) Thanks for the advice, I wanted RAID 4 due to customer's request.
I will now investigate the software RAID support and see where that goes.

This mailing list is great!

Quote From

        RAID-4 interleaves stripes like RAID-0, but it requires an
additional partition to store parity information. The parity is
           used to offer redundancy: if any one of the disks fail, the data
on the remaining disks can be used to reconstruct the
           data that was on the failed disk. Given N data disks, and one
parity disk, the parity stripe is computed by taking one
           stripe from each of the data disks, and XOR'ing them together.
Thus, the storage capacity of a an (N+1)-disk RAID-4
           array is N, which is a lot better than mirroring (N+1) drives,
and is almost as good as a RAID-0 setup for large N. Note
           that for N=1, where there is one data drive, and one parity
drive, RAID-4 is a lot like mirroring, in that each of the two
           disks is a copy of each other. However, RAID-4 does NOT offer the
read-performance of mirroring, and offers
           considerably degraded write performance. In brief, this is
because updating the parity requires a read of the old parity,
           before the new parity can be calculated and written out. In an
environment with lots of writes, the parity disk can become
           a bottleneck, as each write must access the parity disk.

           RAID-5 avoids the write-bottleneck of RAID-4 by alternately
storing the parity stripe on each of the drives. However,
           write performance is still not as good as for mirroring, as the
parity stripe must still be read and XOR'ed before it is
           written. Read performance is also not as good as it is for
mirroring, as, after all, there is only one copy of the data, not
           two or more. RAID-5's principle advantage over mirroring is that
it offers redundancy and protection against
           single-drive failure, while offering far more storage capacity
when used with three or more drives.

> ----------
> From: Bruce Guenter[]
> Reply To:
> Sent: Monday, March 13, 2000 1:40 PM
> To:
> Subject: Re: HW RAID Controllers
> On Mon, Mar 13, 2000 at 01:29:13PM -0600, Schneider, Tim wrote:
> > I wanted to use RAID 4 from
> > an article I read about RAID, sorry the link is at home. It was under
> the
> > freeBSD handbook hardware install guide. That document described RAID 4
> -
> > stripping with a dedicated device storing parity, RAID 5 - striping with
> the
> > parity distributed across the array. So RAID 4 was slower to write but
> > 5 was considerably slower than RAID 4 while reading. (Sorry - I
> paraphrase)
> Could you elaborate on this? I can think of no reason why RAID 4 would
> be any slower than RAID 5 for reading.
> --
> Bruce Guenter <>
> --
> Saskatoon Linux Group Mailing List.
> --
> To unsubscribe, send mail to
> '' with
> 'unsubscribe' in the body.

Saskatoon Linux Group Mailing List.
To unsubscribe, send mail to
'' with
'unsubscribe' in the body.
Received on Mon Mar 13 15:18:49 2000

This archive was generated by hypermail 2.1.8 : Sun Jan 09 2005 - 13:53:59 CST