RE: Benchmark with RAC & NON-RAC Database - To use 1 or 2 Databases
- From: "Kevin Closson" <kevinc@xxxxxxxxxxxxx>
- To: <mark.bobak@xxxxxxxxxxxxxxx>, <sudheendra.vijayakumar@xxxxxxxxx>
- Date: Sat, 30 Dec 2006 09:10:30 -0800
On Sat, 2006-12-30 at 11:46 +0530, Sudheendra Vijayakumar wrote:
> Wonder how much of a difference would it make if you truned RAC off on
> the same binaries. Any thoughts?
Just "turning off RAC" is only part of it. You will want to test linked
and unlinked. I have workloads that show the "tare weight" of simply
having RAC linked in to cost as much as 10%...that is with RAC linked in
but CLUSTER_DATABASE=FALSE...hey, it used to be a LOT worse with OPS :-)
--
http://www.freelists.org/webpage/oracle-l
- References:
- Re: Benchmark with RAC & NON-RAC Database - To use 1 or 2 Databases
- From: Mark J. Bobak
Other related posts:
- » Benchmark with RAC & NON-RAC Database - To use 1 or 2 Databases
- » Re: Benchmark with RAC & NON-RAC Database - To use 1 or 2 Databases
- » Re: Benchmark with RAC & NON-RAC Database - To use 1 or 2 Databases
- » Re: Benchmark with RAC & NON-RAC Database - To use 1 or 2 Databases
- » RE: Benchmark with RAC & NON-RAC Database - To use 1 or 2 Databases
- Re: Benchmark with RAC & NON-RAC Database - To use 1 or 2 Databases
- From: Mark J. Bobak