RAID Controller policy on Dell 2950-III PERC 6/i

Hi All,

Im currently in the process of rebuilding my Dell 2950-III server which has got these specs:

1x Quadcore Xeon 5420 @ 2.33 GHz
5x 400 GB SAS 10k rpm HDD
RAID connector 0: 4 HDD
RAID connector 1: 1 HDD
Dell PERC 6/I RAID Controllers

While inside the Dell RAID configuration utility apps, I saw the following configuration:
Stripe Element Size: 64k
Read Policy: No Read Ahead*
Write Policy: Write Back
Disk Cache Policy: Disabled

"      From:  You cannot set the read policy on a RAID-5 data plex. RAID-5 plexes have their own read policy (RAID).

As Im about to use this server as the RAID-5 for Exchange Server 2007, is there anything that I could tune for the best performance?

Who is Participating?
I wear a lot of hats...

"The solutions and answers provided on Experts Exchange have been extremely helpful to me over the last few years. I wear a lot of hats - Developer, Database Administrator, Help Desk, etc., so I know a lot of things but not a lot about one thing. Experts Exchange gives me answers from people who do know a lot about one thing, in a easy to use platform." -Todd S.

Assuming you have servers on ups and configured to properly shutdown on a power loss, I would think:

Read policy = adaptive read ahead, Write Policy = Write Back, and Disk Cache = Enabled

Experts Exchange Solution brought to you by

Your issues matter to us.

Facing a tech roadblock? Get the help and guidance you need from experienced professionals who care. Ask your question anytime, anywhere, with no hassle.

Start your 7-day free trial
jjozAuthor Commented:
ok, or else just leave it as it is i presume :-)
Thanks for the comment.
Re: Disk Cache Policy: Disabled

This means the internal cache inside the hard drive is disabled.   If you enable it, certain operations will be dramatically improved (writes).    When I load large (100g) databases with "Disk Cache Policy: Enabled", I see a 5 times performance improvement.

But some Dell 2950's use Hitachi disk drives (HUA72101 disks, aka Ultrastar A7K1000).  These disks can use their own internal write cache (the default). If a power loss occurs during heavy write activity, writes will be lost, possibly corrupting your disk  (even though the drive tells the operating system that the writes had completed!)

Just halting the operating system won't cause this corruption, it's a power failure problem.   With a Sybase database, we could get database corruption more than 80% of the time by pulling the plug during heavy write activity with internal hard drive caching enabled.  We had no corruption in this scenario with internal hard drive caching  disabled.

I don't know what other brands of disks do for this option.
jjozAuthor Commented:
Hi all, thanks for the reply.

Is there a way to enable this option when the hard drive RAID has been created ?

There are commands in the megacli (MegaRaid disk controller (aka Perc) command line interpreter) for turning on "hard disk cache" (bad wording, it should say "hard disk internal cache" to separate it from the disk controller hard disk cache)

Command to turn hard drive internal disk cache on (power failure can corrupt the disks):

  /opt/MegaRAID/MegaCli/MegaCli -LDSetProp -EnDskCache -LALL -aALL

Command to turn hard drive internal disk cache off (slower writes):

  /opt/MegaRAID/MegaCli/MegaCli -LDSetProp -DisDskCache -LALL -aALL

It's more than this solution.Get answers and train to solve all your tech problems - anytime, anywhere.Try it for free Edge Out The Competitionfor your dream job with proven skills and certifications.Get started today Stand Outas the employee with proven skills.Start learning today for free Move Your Career Forwardwith certification training in the latest technologies.Start your trial today

From novice to tech pro — start learning today.