Distribution in a single address space operating system

Published

Conference Paper

The recent, appearance of architectures with Hat 64-bit virtual addressing opens an opportunity to reconsider the way our operating systems use virtual address spaces. We are building an operating system called Opal for these wide-address architectures. The key feature of Opal is a single global virtual address space that extends to data on long-term storage and across the network. I lard ware-en forced memory protection exists within this single address space. This paper outlines our ideas for extending Opal to a distributed environment, focusing on the naming and binding of data and services to allow uniform treatment across the network. Our central point is that although the meaning of names (i.e., the entities denoted by those names) should be uniform throughout the network, at a lower level the binding of names to physical delta or servers may vary with the node uttering the name, in order to accommodate caching, replication, and migration. This principle a Heels Opal's handling of both data names (virtual addresses) and resource names (capabilities).

Full Text

Duke Authors

Cited Authors

  • Chase, J; Issarny, V; Levy, H

Published Date

  • September 21, 1992

Published In

  • Proceedings of the 5th Acm Sigops European Workshop: Models and Paradigms for Distributed Systems Structuring, Ew 1992

Digital Object Identifier (DOI)

  • 10.1145/506378.506391

Citation Source

  • Scopus