Re: single session I/O bandwidth

From: Tanel Poder <tanel_at_tanelpoder.com>
Date: Wed, 13 Mar 2013 15:19:08 +0200
Message-ID: <CAMHX9JJW9UCmPaJH39=+BVn25CsWkD5KADrsjq1n0TqdZN1ePw_at_mail.gmail.com>



Google for Frits Hoogland's multiblock reads slides to get useful extra info about this ...
-- 
*Tanel Poder*
Enkitec (The Exadata Experts)
Training <http://blog.tanelpoder.com/seminar/> |
Troubleshooting<http://blog.tanelpoder.com/>
 | Exadata<http://www.amazon.com/Expert-Oracle-Exadata-Apress/dp/1430233923>
 | Voicee App <http://voic.ee/>



On Wed, Mar 13, 2013 at 3:17 PM, Tanel Poder <tanel_at_tanelpoder.com> wrote:


> what's the wait profile for this single session? 90% on CPU or 90%
> waiting? (run snapper :)
>
> if it's a buffered scan (db file scattered reads) then you will do an IO
> operation, wait, process on CPU, do another IO operation, wait again etc...
> so you'll be wasting a lot of time on waiting for the synchronous IO
> operations to complete. So it's about the latency. Easily measurable.
>
>
-- http://www.freelists.org/webpage/oracle-l
Received on Wed Mar 13 2013 - 14:19:08 CET

Original text of this message