Two questions are examined, regarding real-time multiprocessor scheduling for large-scale nonuniform memory access (NUMA) architectures: how are the latency and the quality of scheduling affected by different degrees of completeness in the information shared among multiple potentially concurrent schedules, and how can scheduling information be represented so that it is efficiently and concurrently accessible? The authors present a real-time scheduling algorithm for multiprocessors that is scalable in the number of tasks performing scheduling and in the maximum amount of computation time consumed by those tasks. They also develop a flexible representation for shared information within the distributed scheduler that is easily varied regarding its degree of information completeness. It is then shown that the sharing of incomplete (vs. complete) information can lead to increased performance regarding scheduling latency with few or no losses in scheduling quality. In addition, it is shown that this holds for a variety of parallel machines, ranging from NUMA to distributed memory machines.
展开▼
