Show simple item record

dc.contributor.authorHaddad, Emile K.en_US
dc.date.accessioned2013-06-19T14:36:33Z
dc.date.available2013-06-19T14:36:33Z
dc.date.issued1990
dc.identifierhttp://eprints.cs.vt.edu/archive/00000185/en_US
dc.identifier.urihttp://hdl.handle.net/10919/19568
dc.description.abstractThe problem of allocating a given total amount of main memory page-frames M(t) available at time t, among a given set of concurrently active processes {P-sub i} is examined. Memory allocation is managed under the working set policy, and it is assumed that M(t) is larger than the total sum of all working-set sizes but less than the sum of distinct pages in {P-sub i}. It is required that each process receive at least an allocation equal to its working-set size and that the excess memory be additionally distributed among the concurrent processes to enhance their performance. The upper and lower bounds on the individual memory allocations for each process are derived. A fair policy for apportioning the excess memory among the concurrent processes is presented. A procedure for rounding off fragmented page apportionment is described. An application example, illustrating dynamically changing conditions in the concurrent active processes, is described.en_US
dc.format.mimetypeapplication/pdfen_US
dc.publisherDepartment of Computer Science, Virginia Polytechnic Institute & State Universityen_US
dc.relation.ispartofHistorical Collection(Till Dec 2001)en_US
dc.titleDynamic Working Set Memory Allocation for Concurrent Processesen_US
dc.typeTechnical reporten_US
dc.identifier.trnumberTR-90-03en_US
dc.type.dcmitypeTexten_US
dc.identifier.sourceurlhttp://eprints.cs.vt.edu/archive/00000185/01/TR-90-03.pdf


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record