An asymptotically optimal real-time locking protocol for clustered scheduling under suspension-aware analysis
Björn B. Brandenburg · ACM SIGBED Review · 2013
The purpose of real-time locking protocols is to limit priority inversions [5], which, intuitively, occur when a high-priority task is delayed by a lower-priority task. Such locking-related delay, also called priority inversion blocking ( pi-blocking ), is problematic in real-time systems because it can result in deadline misses. However, some pi-blocking is unavoidable when using locks and thus must be bounded and accounted for during schedulability analysis.