Abstract

We describe our experiences with the implementation of a process migration mechanism for the distributed operating system Amoeba. After describing our design goals, we present our implementation for Amoeba. Though our goals have very largely been met, we have fallen short of the goal of complete transparency, and we discuss the consequences of that. We also present performance figures, indicating that the speed of process migration is limited only by the throughput of the network adapters used in our configuration, and that the overhead is comparable to that of process creation. We conclude with a review of the degree to which our design goals have been met, and discussion of the lessons learnt.

Citations