“Spinlock Contention” reports the number of times an engine encountered spinlock contention on the cache, and had to wait, as a percentage of the total spinlock requests for that cache. This is meaningful for SMP environments only.
When a user task makes any changes to a cache, a spinlock denies all other tasks access to the cache while the changes are being made. Although spinlocks are held for extremely brief durations, they can slow performance in multiprocessor systems with high transaction rates. If spinlock contention is more than 10%, consider using named caches or adding cache partitions.
See “Configuring the data cache to improve performance” on page 220 for information on adding caches, and “Reducing spinlock contention with cache partitions” on page 228 in Performance and Tuning: Basics.
