Re: Help with low raid5 performance

[Greg Oster <oster%cs.usask.ca@localhost>]

On Tue, 11 Jan 2011 08:43:12 -0500
Thor Lancelot Simon <tls%panix.com@localhost> wrote:

> On Tue, Jan 11, 2011 at 09:34:27AM +0000, Stephen Borrill wrote:
> >
> > >>I'm using a 4-disk RAID 5 with the partition starting at 45416448
> > >>(which is very well aligned (on a 65536 boundary!).
> 
> This should not be aligned on a 64k boundary with 3 data disks.  It
> should be aligned on a 48K boundary!
> 
> Greg, with RAIDframe sector 0 should always be at the beginning of a
> stripe, so 48K alignment with no remainder is correct, yes?

Yes, and yes. (in this case)

> > Changing to 32 1 1 5 gave:
> >       -------Sequential Output-------- ---Sequential Input--
> > --Random-- -Per Char- --Block--- -Rewrite-- -Per Char- --Block---
> > --Seeks--- MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU K/sec
> > %CPU  /sec %CPU 2048  9137  9.6  7440  3.3  3045  1.3 61801 82.3
> > 149558 37.1 228.2  2.4
> > 
> > These were formatted with: newfs -O 2 -f 4096 -b 32768
> 
> This newfs command line is wrong.  32 doesn't go evenly into 48.
> Remember that the RAIDframe sectors-per-stripe is in half-kilobyte
> units...
> 
> You probably want newfs -f 2048 -b 16384 -a 3.

I'm curious to see the results of the above. 

As well: you don't need to do 'raidctl -i' on the set if you're just
doing quick benchmarking and don't care about the ability to recover
the data on the disks.  That is, you needn't wait 15 hours for the set
to rebuild just to try a different set of parameters.  (ya, it'll say
the parity is dirty, but for a RAID 5 set that won't affect the IO
performance at all..)

Later...

Greg Oster