Transport protocol processing at GBPS rates
SIGCOMM '90 Proceedings of the ACM symposium on Communications architectures & protocols
Architectural considerations for a new generation of protocols
SIGCOMM '90 Proceedings of the ACM symposium on Communications architectures & protocols
The X-Kernel: An Architecture for Implementing Network Protocols
IEEE Transactions on Software Engineering
A Parallel Approach to OSI Connection-Oriented Protocols
Proceedings of the IFIP WG6.1/WG6.4 Third International Workshop on Protocols for High-Speed Networks III
The Parallel Protocol Framework
The Parallel Protocol Framework
IEEE/ACM Transactions on Networking (TON)
Parallel architectures for processing high speed network signaling protocols
IEEE/ACM Transactions on Networking (TON)
Networking support for large scale multiprocessor servers
Proceedings of the 1996 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
IEEE/ACM Transactions on Networking (TON)
Cache behavior of network protocols
SIGMETRICS '97 Proceedings of the 1997 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
Structuring Communication Software for Quality-of-Service Guarantees
IEEE Transactions on Software Engineering
IEEE Transactions on Parallel and Distributed Systems
Performance modeling of multiprocessor implementations of protocols
IEEE/ACM Transactions on Networking (TON)
Runtime support for collaborative air pollution models
Systems Analysis Modelling Simulation - Special issue: Applications of information systems in environmental modelling
Flexible Control of Parallelism in a Multiprocessor PC Router
Proceedings of the General Track: 2002 USENIX Annual Technical Conference
Exploiting task-level concurrency in a programmable network interface
Proceedings of the ninth ACM SIGPLAN symposium on Principles and practice of parallel programming
An operating system architecture for network processors
Proceedings of the 2005 ACM symposium on Architecture for networking and communications systems
Performance issues in parallelized network protocols
OSDI '94 Proceedings of the 1st USENIX conference on Operating Systems Design and Implementation
A scheduling scheme for network saturated NT multiprocessors
NT'97 Proceedings of the USENIX Windows NT Workshop on The USENIX Windows NT Workshop 1997
A framework for the non-monolithic implementation of protocols in the x-kernel
HSNS'94 Proceedings of the High-Speed Networking Symposium on USENIX 1994 High-Speed Networking Symposium
Reconciling performance and programmability in networking systems
Proceedings of the 2007 conference on Applications, technologies, architectures, and protocols for computer communications
LATA: a latency and throughput-aware packet processing system
Proceedings of the 47th Design Automation Conference
The case for hardware transactional memory in software packet processing
Proceedings of the 6th ACM/IEEE Symposium on Architectures for Networking and Communications Systems
The effectiveness of affinity-based scheduling in multiprocessor networking
INFOCOM'96 Proceedings of the Fifteenth annual joint conference of the IEEE computer and communications societies conference on The conference on computer communications - Volume 1
Improving the efficiency of automated protocol implementation using Estelle
Computer Communications
| Hi-index | 0.00 |
We investigate how to exploit shared memory multiprocessors for parallel protocol processing. We present a multiprocessor implementation of the x-kernel protocol environment from the University of Arizona. A "processor-per-message" paradigm is used to partition the work over processors. Locks are used to protect shared protocol state and data. Mutual exclusion by locking can be costly if the parallel protocol code frequently accesses shared state and data. This paper addresses the effect of locking on performance.The x-kernel is implemented in user address space on a Sequent Symmetry. Performance results of UDP/IP and TCP/IP are given, and we compare them to performance predictions from simulations. The measured speedups for the parallel implementations relative to the sequential ones are more than 12 times for UDP and 3 times for TCP. These limits are set by locking and machine contention.