Virtual memory support for distributed computing environments using a shared data object model
Huang, Feng and Bacon, Jean and Mapp, Glenford E. (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
Full text is not in this repository.
Official URL: http://dx.doi.org/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.
|Research Areas:||Science & Technology > Algorithms, Architecture & Networks|
|Deposited On:||09 Sep 2011 07:06|
|Last Modified:||04 Oct 2013 05:01|
Repository Staff Only: item control page
Full text downloads (NB count will be zero if no full text documents are attached to the record)
Downloads per month over the past year