ACM Transactions on Computer Systems (TOCS)
File access performance of diskless workstations
ACM Transactions on Computer Systems (TOCS)
UIO: a uniform I/O system interface for distributed systems
ACM Transactions on Computer Systems (TOCS)
The C programming language
VMTP: a transport protocol for the next generation of communication systems
SIGCOMM '86 Proceedings of the ACM SIGCOMM conference on Communications architectures & protocols
Distributed process groups in the V Kernel
ACM Transactions on Computer Systems (TOCS)
Host groups: a multicast extension for datagram internetworks
SIGCOMM '85 Proceedings of the ninth symposium on Data communications
A trace-driven analysis of the UNIX 4.2 BSD file system
Proceedings of the tenth ACM symposium on Operating systems principles
Implementing remote procedure calls
ACM Transactions on Computer Systems (TOCS)
Request- Response and Multicast Interprocess Communication in the V Kernel
Proceedings of the International Seminar on Networking in Open Systems
LOCUS a network transparent, high reliability distributed system
SOSP '81 Proceedings of the eighth 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
The Sprite Remote Procedure Call System
The Sprite Remote Procedure Call System
Communications of the ACM
Exploiting recursion to simplify RPC communication architectures
SIGCOMM '88 Symposium proceedings on Communications architectures and protocols
The VMP network adapter board (NAB): high-performance network communication for multiprocessors
SIGCOMM '88 Symposium proceedings on Communications architectures and protocols
A case study of DECnet applications and protocol performance
SIGMETRICS '88 Proceedings of the 1988 ACM SIGMETRICS conference on Measurement and modeling of computer systems
Sirpent: a high-performance internetworking approach
SIGCOMM '89 Symposium proceedings on Communications architectures & protocols
Optimistic implementation of bulk data transfer protocols
SIGMETRICS '89 Proceedings of the 1989 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
A synthetic workload model for a distributed system file server
SIGMETRICS '91 Proceedings of the 1991 ACM SIGMETRICS conference on Measurement and modeling of computer systems
Network locality at the scale of processes
SIGCOMM '91 Proceedings of the conference on Communications architecture & protocols
Efficient support for client/server applications over heterogeneous ATM network
IEEE/ACM Transactions on Networking (TON)
High-performance local area communication with fast sockets
ATEC '97 Proceedings of the annual conference on USENIX Annual Technical Conference
Efficient support for the client/server paradigm over heterogeneous ATM networks
INFOCOM'96 Proceedings of the Fifteenth annual joint conference of the IEEE computer and communications societies conference on The conference on computer communications - Volume 3
| Hi-index | 0.02 |
Communication systems are undergoing a change in use from stream to request-response or transaction communication. In addition, communication systems are becoming increasingly based on high-speed, low delay, low error rate channels. These changes call for a new generation of networks, network interfaces, and transport protocol design. The performance characteristics of request-response protocols on these high-performance networks should guide the design of this new generation, yet relatively little data of this nature is available.In this paper, we present some preliminary measurements of network traffic for a cluster of workstations connected by Ethernet running the V distributed operating system. We claim that this system, with its use of a high-speed local area network and a request-response transport protocol tuned for RPC, provides some indication of the performance characteristics for systems in the next generation of communication systems. In particular, these measurements provide an indication of network traffic patterns, usage characteristics for request-response protocols, and the behavior of the request-response protocol itself. These measurements suggest in general that a key design focus must be on minimizing network latency and that a request-response protocol is well-suited for this goal. This focus has implications for protocol design and implementation as well as for the design of networks and network interfaces.