Paper Details

Reference:

Michael Stumm, Ronald C. Unrau, and Orran Krieger,
"Designing a scaleable operating system for shared memory multiprocessors",
In Proceedings Usenix Workshop on Micro-Kernels and Other Kernel Architectures, Seattle, WA, USA, April, 1992, pp. 348–357.

Download:

PDF

Abstract:

We propose a simple structuring technique based on clustering for designing scalable shared memory multiprocessor operating systems. Clustering has a number of advantages. First, distributed systems principles are applied by distributing and replicating system services and data objects to increase locality, increase concurrency, and to avoid centralized bottlenecks, thus making the system scalable. However, since there is tight coupling within a cluster, the system performs well for local interactions. Second, a clustered system can easily be adapted to different hardware configuration and architectures by chaning the size of the clusters. Third, clustering maximizes locality which is key to good performance in large NUMA systems. Finally, clustering leads to a modular system composed from easy-to-design and hence efficient building blocks.

In this paper, we describe clustering and how it is applied to a micro-kernel-based operating system. We present measurements of performance, as obtained from a working prototype implementation.

Keywords:

Operating systems, shared memory multiprocessors, scalability, NUMA, clustering

Reference Info:

ACMid: 692229
ISBN: 1-880446-42-1

BibTeX:

@inproceedings(Stumm-USENIXMKA92,
    author = {Michael Stumm and Ronald C. Unrau and Orran Krieger},
    title = {Designing a scaleable operating system for shared memory multiprocessors},
    booktitle = {Proceedings Usenix Workshop on Micro-Kernels and Other Kernel Architectures},
    location = {Seattle, WA, USA},
    month = {April},
    year = {1992},
    pages = {348-357},
    isbn = {1-880446-42-1},
    keywords = {Operating systems, shared memory multiprocessors, scalability, NUMA, clustering}
)