Virtual memory support for distributed computing environments using a shared data object model

Huang, Feng, Bacon, Jean and Mapp, Glenford E. ORCID logoORCID: (1995) Virtual memory support for distributed computing environments using a shared data object model. Distributed Systems Engineering, 2 (4) . pp. 202-211. ISSN 0967-1846 [Article] (doi:10.1088/0967-1846/2/4/003)


Conventional storage management systems provide one interface for accessing memory segments and another for accessing secondary storage objects. This hinders application programming and affects overall system performance due to mandatory data copying and user/kernel boundary crossings, which in the microkernel case may involve context switches. Memory-mapping techniques may be used to provide programmers with a unified view of the storage system. This paper extends such techniques to support a shared data object model for distributed computing environments in which good support for coherence and synchronization is essential. The approach is based on a microkernel, typed memory objects, and integrated coherence control. A microkernel architecture is used to support multiple coherence protocols and the addition of new protocols. Memory objects are typed and applications can choose the most suitable protocols for different types of object to avoid protocol mismatch. Low-level coherence control is integrated with high-level concurrency control so that the number of messages required to maintain memory coherence is reduced and system-wide synchronization is realized without severely impacting the system performance. These features together contribute a novel approach to the support for flexible coherence under application control.

Item Type: Article
Research Areas: A. > School of Science and Technology > Computer and Communications Engineering
A. > School of Science and Technology > Computer Science > SensoLab group
Item ID: 8125
Useful Links:
Depositing User: Dr G E Mapp
Date Deposited: 09 Sep 2011 07:06
Last Modified: 13 Oct 2016 14:23

Actions (login required)

View Item View Item


Activity Overview
6 month trend
6 month trend

Additional statistics are available via IRStats2.