You were brought to this page based on an internet search
and as a free service to Oracle DBAs.
The text below is an except from the book,
Oracle Performance Firefighting, written by
Craig Shallahamer of
OraPub, Inc.
Figures and tables are not included on this page, only their reference.
To order the book in either print or PDF form, click
here.
©2009, 2010 by Craig Shallahamer. This is copyrighted material.
PleaseOut of respect for those involved in the creation of the book and also for
their familes, we ask you to respect the copyright both in intent and deed. Thank you.
-------------------------------
Deriving the IO service time based on the utilization formula is fraught with problems because of non-Oracle IO caching. Even more problematic is knowing the actual number of active IO devices dedicated to an Oracle instance. But it gets worse. Having other IO activity on a specific instance's database files IO device further degrades the service time calculation quality.
In summary, calculating IO service time is unreliable. The good news is that we are more interested in IO response time, which is easy to collect, as discussed shortly.
When a transaction arrives into a system ready to be serviced, it may need to wait, or queue, before servicing begins. Service time does not include wait time; that is, queue time. For example, when an IO subsystem is 2.2% utilized, the entire IO processing time is virtually all service time and no queue time.
©2009, 2010 by Craig Shallahamer. This is copyrighted material.
PleaseOut of respect for those involved in the creation of the book and also for
their familes, we ask you to respect the copyright both in intent and deed. Thank you.
|