8.2. Factors affecting the performance of concurrent code

If you’re using concurrency in order to improve the performance of your code on systems with multiple processors, you need to know what factors are going to affect the performance. Even if you’re just using multiple threads to separate concerns, you need to ensure that this doesn’t adversely affect the performance. Customers won’t thank you if your application runs more slowly on their shiny new 16-core machine than it did on their old single-core one.

As you’ll see shortly, many factors affect the performance of multithreaded code—even something as simple as changing which data elements are processed by each thread (while keeping everything else identical) can have a dramatic effect on performance. So, without further ado, let’s look at some of these factors, starting with the obvious one: how many processors does your target system have?