Issues in the design of distributed shared memory systems

摘要

This thesis examines the various system issues that arise in the design of distributed shared memory (DSM) systems. This work has been motivated by the observation that distributed systems will continue to become popular, and will be increasingly used for solving large computational problems. To this effect, shared memory paradigm is attractive for programming large distributed systems because it offers a natural transition for a programmer from the world of uniprocessors. The goal of this work is to identify a set of system issues, such as integration of DSM with virtual memory management, choice of memory model, choice of coherence protocol, and technology factors; and evaluate the effects of the design alternatives on the performance of DSM systems. The specific question that we are trying to answer is, "Can we determine a set of system design parameters that defines an efficient realization of a distributed shared memory system?" The design alternatives have been evaluated in three steps. First, we do a detailed performance study of a distributed shared memory implementation on the C scLOUDS$sp1$ distributed operating system. Second, we implement and analyze the performance of several applications on a distributed shared memory system. Third, the system issues that could not be evaluated via the experimental study, are evaluated using a simulation-based approach. The simulation model is developed from our experience with the C scLOUDS distributed system. A new workload model that captures the salient features of parallel and distributed programs is developed and used to drive the simulator. The key results of the thesis are: DSM mechanisms have to be integrated with the virtual memory management for providing high performance distributed shared memory systems; the choice of the memory model and coherence protocol does not significantly influence the system performance for applications exhibiting high computation granularity and low state-sharing; and an efficient implementation of DSM requires a careful design of miscellaneous system services (such as synchronization and data servers). The thesis also enumerates several questions related to future research directions. ftn$sp1$C scLOUDS is a distributed object-based operating system developed at Georgia Tech.