Process migration in virtual memory multicomputer systems

In a distributed virtual memory system (DVM) environment, process migration can be achieved by transferring the process control block of a process to the destination node. Under DVM, the pages of a process are dynamically distributed over several nodes in the system. Therefore, a migrating process is likely to find part of its virtual space allocated to the same node to which the process has migrated. The authors address when to invoke migration, which process to migrate, and where to send the selected process. They present two approaches for solving these questions. A load index is defined as a function of the number of jobs at the node, the page fault rate, and the remaining unused memory. The load index is used to determine whether migration is needed or not. Trace driven simulation of a dynamic distributed system was used to evaluate the performance of the various process migration techniques