From a CPU perspective, this means the average run queue will always be equal to or greater than the number of CPU cores. But there is a limit to our aggressive resource usage. If we allow the system to push too far into the elbow, the overhead associated with managing the system increases to the point where the elapsed time begins to degrade. Our job as performance analysts is to find the sweet spot and operate the batch processing there!

This chapter is truly about performance analysis. Some would say it is enough to find a problem and make some changes. I respectfully disagree. I believe we can do so much more, be so much more effective, and add greater value to our organization. Nearly any Oracle analysis will result in a number of recommendations. But in order to responsibly decide which changes to implement first, some ranking must occur. This chapter focused on bringing rational debate and consensus to ranking the performance-enhancing solutions. I hope you have found it enlightening and practical.

This final chapter brings a natural and fitting finality to Oracle Performance Firefighting. We started with method, moved into diagnosis and data collection, then into relevant Oracle internals, enabling us to intelligently choose valid performance-enhancing solutions, and then finally anticipate the impact of our proposed solutions. It's part of being an effective Oracle performance firefighter.