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.
-------------------------------
So, while the CPU subsystem is running at 100% utilization, if the IO subsystem is receiving only this specific Oracle instance's IO requests, and assuming there is no non-Oracle caching, the IO subsystem would be running at around 2.2% utilization. It appears the IO subsystem has plenty of capacity.
Service time is how long it takes a single arrival to be served, excluding queue time. If the arrival is defined to be an Oracle user call, then the service time may be something like 4.82 milliseconds per user call, or 4.82 ms/uc.
While the total service time includes all the time to service transactions within a given interval, service time is specifically related to a single arrival service. The unit of time should be in the numerator, and the unit of work should be in the denominator. Depending on your data source, the information may be provided as work over time. Make sure to switch it to time over work. If you forget to do this, any other calculation based on the service time (for example, utilization and response time) will likely be incorrect.
©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.
|