Re: Managing CPU_COUNT for micro-partitioning on AIX

From: Connor McDonald <mcdonald.connor_at_gmail.com>
Date: Mon, 3 Jul 2006 11:15:07 +0800
Message-ID: <5e3048620607022015s13e1ed29r9a761ec7fefc3ecd@mail.gmail.com>

On 7/3/06, Mark Brinsmead <pythianbrinsmead_at_gmail.com> wrote:

> "First off, correct me if I'm wrong (I probably am, and I'm sure somebody here likely
> will), but isn't CPU_COUNT mainly used by the database to decide the degree of
> parallelism that can/should be used?"

The other thing that is (perhaps) more significant (in systems where latch contention is an issue), is that with a single CPU box, it makes no sense to spin for a latch (after all, on a one CPU system, if someone else has a latch, the only way they'll release it is it I get off the CPU and give them a chance to get some CPU time)....

-- 
Connor McDonald
===========================
email: connor_mcdonald_at_yahoo.com
web:   http://www.oracledba.co.uk

"Semper in excremento, sole profundum qui variat"
--
http://www.freelists.org/webpage/oracle-l

Received on Sun Jul 02 2006 - 22:15:07 CDT