[CentOS] Write performance with 3ware 9550

[Bowie Bailey]

chrism at imntv.com wrote:
> Kirk Bocek wrote:
> > I saw a definite improvement by turning off NCQ and setting StorSave
> > to 'Balanced.' Are these 1.5GB/Sec or 3.0GB/Sec SATA drives? During
> > my testing I changed from non-interleaved memory and 1.5GB to
> > interleaved and 3.0GB. Made a big difference in bonnie++ results.
> > Unfortunately, I can't say which was more important.
> > 
> > If you have the patience, read through my recent (but lengthy)
> > thread on the 3Ware 9550 titled "Calling All FS Fanatics." There's
> > a lot of good info from many helpful people. I've only gotten full
> > performance using JFS or XFS. 
> > 
> 
> I'm doing this from memory as the machine is at another location now.
> I think I did this:
> 
> turned off ncq (per Josh's suggestion)

Tried that, it made a small improvement (see my previous post).

> turned on write caching (it's on an oversized ups and the data isn't
> critical)

Write caching is on.  I've got a BBU, so the data is protected.

> set storsave to "performance"

I prefer to leave this one as is to take advantage of the write
journaling.

> changed the memory interleave (thanks to kirk's suggestion).  It was
> off by default.

This one I would like to try.  Can you tell me where I can make the
change?

> used parted to create gpt disklabel

What is the advantage of gpt over msdos?  Can I make this change
without recreating the filesystem?

> set noatime and one other option that was suggested here for the RAID
> partition

Anyone know if noatime is recommended for a filesystem containing an
Oracle database?

What was the other option?

> used mke2fs -j -b 4096 /dev/blah

I used 'mkfs.ext3 /dev/blah'.  It created 4K blocks.

> That was it.
> 
> Also, I tried the same array as a RAID0 device on the same box and the
> performance was approximately the same (maybe ever so slightly
> faster). 

Raid0 should be faster, particularly with writes since it doesn't have
to calculate parity.

-- 
Bowie