Run Queues
We have used the term run queue frequently in this chapter. Let's take a moment to understand what a run queue is, where it is located, and how it is implemented.
The run queue does not exist as a single structure. It is built by linking together all runnable threads on the system to appropriate queue headers. Which queue header a runnable kthread is linked to depends on its processor affinity, its priority, kt_pri and its scheduling policy stored in kt_schedpolicy (stored in the thread's kthread structure). To enter a processor's run queue, we start with the mp_threadhd structures.
The structures are stored in a number of arrays (dependent on the number of processors and processor sets). Each of the per-processor run queues has 160 ...
Get HP-UX 11i Internals now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
