Energy-Aware Migration and Replication of Processes in a Cluster

Abstract

Application processes have to be efficiently performed in presence of server faults in a cluster. Replicas of a process are performed on multiple servers to be tolerant of server faults. However, the more number of replicas of a process are performed, the more reliably and availably the process can be performed but the more amount of electric energy is consumed by servers. In this paper, we take a process migration approach to reliably and energy-efficiently performing process replicas. A process is replicated to multiple replicas. Each replica is performed on a server different from the other replicas to realize fault-tolerant computation. In addition, each replica of process migrates from a current server to another server if the current server is expected to consume the more electric energy. Thus, replicas migrate to servers to reduce the total electric energy consumption of the cluster.

Read-abortion (RA) based synchronization protocols to prevent illegal information flow

“…We showed that no illegal information flow occur but about 10% to 20% of transactions are shown to be aborted in the RA-RBS and RA-OBS protocols. We are now discussing synchronization protocols to reduce the number of transactions to be aborted and to reduce the electric power consumption [18] of computer.…”

ExaMig Matrix: Process Migration based on Matrix Definition of Selecting Destination in Distributed Exascale Environments

“…In [46], the process migration based on parameters decision and the system purpose, chooses one of four mechanisms: total copy, precopy, lazy copy, flushing, and designing the transfer process based on it. In [47], a migration mechanism is introduced based on a genetic algorithm that effectively mitigates the load imbalance in multiple processors. In this mechanism, the genetic algorithm is used to find the best destination for migrating the process.…”