Title | ||
---|---|---|
Efficient performance models for layered server systems with replicated servers and parallel behaviour |
Abstract | ||
---|---|---|
Capacity planning for large computer systems may require very large performance models, which are difficult or slow to solve. Layered queueing models solved by mean value analysis can be scaled to dozens of servers and hundreds of service classes, with large class populations, but this may not be enough. A common feature of planning models for large systems is structural repetition expressed through replicated subsystems, which can provide both scalability and reliability, and this replication can be exploited to scale the solution technique. A model has recently been described for symmetrically replicated layered servers, and their integration into the system, with a mean-value solution approximation. However, parallelism is often combined with replication; high-availability systems use parallel data-update operations on redundant replicas, to enhance reliability, and grid systems use parallel computations for scalability. This work extends the replicated layered server model to systems with parallel execution paths. Different servers may be replicated to different degrees, with different relationships between them. The solution time is insensitive to the number of replicas of each replicated server, so systems with thousands or even millions of servers can be modelled efficiently. |
Year | DOI | Venue |
---|---|---|
2007 | 10.1016/j.jss.2006.07.022 | Journal of Systems and Software |
Keywords | Field | DocType |
replication,different relationship,parallel behaviour,client–server performance,different degree,analytic performance model,parallel computation,parallelism,large system,layered server system,different server,parallel data-update operation,layered queueing networks,efficient performance model,mean-value solution approximation,large class population,large performance model,large computer system,high availability,layered queueing network,parallel computer,mean value analysis,client server | Mean value analysis,Server farm,Computer science,Server,Real-time computing,Capacity planning,Queueing theory,Layered queueing network,Computation,Scalability,Distributed computing | Journal |
Volume | Issue | ISSN |
80 | 4 | The Journal of Systems & Software |
Citations | PageRank | References |
7 | 0.56 | 20 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tariq Omari | 1 | 23 | 3.22 |
Greg Franks | 2 | 409 | 29.08 |
Murray Woodside | 3 | 1215 | 81.20 |
Amy Pan | 4 | 7 | 0.56 |