作者: Tony E. Sawan , Anand Haridass , Prasanna Jayaraman
DOI:
关键词:
摘要: A computer-implemented method includes capping the amount of power available to each a plurality compute nodes, and managing allocation among subsystems within nodes according requirements workloads assigned nodes. The further comprises reporting an actual performance level capability for subsystem monitoring parametric data particular workload. target node is identified from wherein would be capable performing workload if was reallocated first second node. then Optionally, assigning may include migrating another