Skip site navigation (1)Skip section navigation (2)
Date:      Sun, 30 Mar 2003 18:50:20 +0200
From:      Mattias Pantzare <pantzer@ludd.luth.se>
To:        Lukas Ertl <l.ertl@univie.ac.at>
Cc:        freebsd-stable@freebsd.org
Subject:   Re: vinum performance
Message-ID:  <3E87204C.5060304@ludd.luth.se>
In-Reply-To: <20030330175605.E23911@leelou.in.tern>
References:  <20030330125138.K23911@leelou.in.tern> <3E870CC7.5000204@mac.com> <20030330175605.E23911@leelou.in.tern>

next in thread | previous in thread | raw e-mail | index | archive | help
Lukas Ertl wrote:

> Ok. But I still don't understand why RAID 5 write performance is _so_ bad.
> The CPU is not the bottle neck, it's rather bored. And I don't understand
> why RAID 0 doesn't give a big boost at all. Is the ahc driver known to be
> slow?

To do a RAID 5 write you do this:
1. Read the old data on the blocks that you will write to.
2. Read the coresponding parity data.
3. Write the new data.
4. Write the new parity.

So one write is 4 I/O before it hits the disk. There are some 
optimizations that
can be done if you are doing writes that span a stripe, but RIAD 5 _is_ 
slower.

Hardware RAID 5 can help a lot if it has battery backed RAM as it can 
hide some of that
delay. Hardware RAID 5 without battery backed RAM will only use less CPU.


For RAID0 to be faster than a singel disk you have to do reads that 
match or are larger
than a stripe. Or have several processes generate the IO.

Try running two bonnie in paralell and se what hapens.




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?3E87204C.5060304>