Summary: Managing Server Load in Global Memory Systems
Geoffrey M. Voelker, Herv’e A. Jamrozik y ,
Mary K. Vernon \Lambda , Henry M. Levy, and Edward D. Lazowska
Department of Computer Science and Engineering
University of Washington
\Lambda Computer Sciences Department
University of Wisconsin ­ Madison
Abstract
New high­speed switched networks have reduced the latency of
network page transfers significantly below that of local disk. This
trend has led to the development of systems that use network­wide
memory, or global memory, as a cache for virtual memory pages or
file blocks. A crucial issue in the implementation of these global
memory systems is the selection of the target nodes to receive re­
placed pages. Current systems use various forms of an approximate
global LRU algorithm for making these selections. However, us­
ing age information alone can lead to suboptimal performance in
two ways. First, workload characteristics can lead to uneven dis­
tributions of old pages across servers, causing increased contention
delays. Second, the global memory traffic imposed on a node can

Source: Anderson, Richard - Department of Computer Science and Engineering, University of Washington at Seattle

Collections: Computer Technologies and Information Sciences