Some Deadlock Properties of Computer Systems
ACM Computing Surveys (CSUR)
Linearizer: a heuristic algorithm for queueing network models of computing systems
Communications of the ACM
A model of shared DASD and multipathing
Communications of the ACM
Analysis of locking policies in database management systems
Communications of the ACM
A performance model for hardware/software issues in computer-aided design of protocol systems
SIGCOMM '84 Proceedings of the ACM SIGCOMM symposium on Communications architectures and protocols: tutorials & symposium
StarOS, a multiprocessor operating system for the support of task forces
SOSP '79 Proceedings of the seventh ACM symposium on Operating systems principles
The distributed V kernel and its performance for diskless workstations
SOSP '83 Proceedings of the ninth ACM symposium on Operating systems principles
Analytic Queueing Models for Programs with Internal Concurrency
IEEE Transactions on Computers
Performance Analysis Using Stochastic Petri Nets
IEEE Transactions on Computers
On detecting parallelism in software
Journal of Systems and Software
| Hi-index | 0.00 |
A method is presented for analyzing the performance of multitasking multiprocessor software that uses rendezvous, possibly implemented by message passing, for interprocess communication and synchronization. The rendezvous is a feature of several modern systems supporting concurrency and implies two phases of service that could be termed ''within-rendezvous'' and ''post-rendezvous'' service. The paper gives a notation for the pattern of rendezvous, a framework for translating a software/hardware system structure into an active-server queueing network model, and an implicit decomposition algorithm for solving for the system performance. The active-server model has servers with a dual nature as servers and customers, so it is distinct in concept from a network of queues, although there are many points of similarity.