On Tue, Mar 5, 2013 at 7:02 PM, Josh Berkus <josh@agliodbs.com> wrote:
>
>> Do these basically sniff right?
>
> Well, the read test seems reasonable. I'm impressed by the speed of the
> write test ... how large is the raid card cache?
>
> And why 8.4? Can you try 9.2?
8.4 because it's what I've got, basically. I might be able to try 9.2
later, but I'm targeting 8.4 right now.
512MB of memory on the card.
>> (NOTE: with barriers off, I get a slight increase - 10% - in the
>> read-write test, and a larger *decrease* - 15% - with the read-only
>> test @ 400. No change @ 100)
>
> Oh, interesting. Can you reproduce that? I wonder what would cause
> read-only to drop without barriers ...
I'll try to test again soon.
I know that if I use writethrough instead of writeback mode the
performance nosedives.
Does anybody have suggestions for stripe size? (remember: *4* disks)
--
Jon