Re: Calculating how many LIOs and PIOs/second your system can handle

From: Jonathan Lewis <jonathan_at_jlcomp.demon.co.uk>
Date: Wed, 31 Dec 2003 15:40:41 -0000
Message-ID: <bsurb1$hbs$2$8302bc10@news.demon.co.uk>

Pick up the 'pick an BCHR' code from Connor's site www.oracledba.co.uk This is a good benchmark statement for testing the peak LIO rate for simple LIO's. It's basically a one-block connect by query.

PIOs are a different matter, because they depend so much on non-Oracle caching effects. But there is a small C program (somewhere) on my website that emulates Oracle by reading or writing randomly to a large file in Nkb chunks on an Nkb boundary. It's probably better to use a mechanism like this than trying to control the timing of Oracle's I/O.

-- 
Regards

Jonathan Lewis
http://www.jlcomp.demon.co.uk

  The educated person is not the person
  who can answer the questions, but the
  person who can question the answers -- T. Schick Jr


One-day tutorials:
http://www.jlcomp.demon.co.uk/tutorial.html


Three-day seminar:
see http://www.jlcomp.demon.co.uk/seminar.html
____UK___November


The Co-operative Oracle Users' FAQ
http://www.jlcomp.demon.co.uk/faq/ind_faq.html


"Ryan Gaffuri" <rgaffuri_at_cox.net> wrote in message
news:1efdad5b.0312310721.53bc1b61_at_posting.google.com...


> Does anyone have a performance plan for doing this? any pitfalls in

> doing this? Or can i just do a big select statement and run a 10046

> trace on it to get a rough estimate of the workload my system can

> handle?

>

> Any papers on this? Ive seen posts about doing this, but no detailed

> best practices.

Received on Wed Dec 31 2003 - 09:40:41 CST