IEEE/ACM Transactions on Networking (TON)
IEEE/ACM Transactions on Networking (TON)
SOSP '01 Proceedings of the eighteenth ACM symposium on Operating systems principles
Tiny Tera: A Packet Switch Core
IEEE Micro
Internet indirection infrastructure
Proceedings of the 2002 conference on Applications, technologies, architectures, and protocols for computer communications
Recovering Internet Symmetry in Distributed Computing
CCGRID '03 Proceedings of the 3st International Symposium on Cluster Computing and the Grid
A 320-Gb/s IP router with QoS control
ICCC '02 Proceedings of the 15th international conference on Computer communication
A routing underlay for overlay networks
Proceedings of the 2003 conference on Applications, technologies, architectures, and protocols for computer communications
HPDC '04 Proceedings of the 13th IEEE International Symposium on High Performance Distributed Computing
Optimizing 10-Gigabit Ethernet for Networks of Workstations, Clusters, and Grids: A Case Study
Proceedings of the 2003 ACM/IEEE conference on Supercomputing
Scalable routing overlay networks
ACM SIGOPS Operating Systems Review
Overcast: reliable multicasting with on overlay network
OSDI'00 Proceedings of the 4th conference on Symposium on Operating System Design & Implementation - Volume 4
nCap: wire-speed packet capture and transmission
E2EMON '05 Proceedings of the End-to-End Monitoring Techniques and Services on 2005. Workshop
Towards virtual networks for virtual machine grid computing
VM'04 Proceedings of the 3rd conference on Virtual Machine Research And Technology Symposium - Volume 3
OCALA: an architecture for supporting legacy applications over overlays
NSDI'06 Proceedings of the 3rd conference on Networked Systems Design & Implementation - Volume 3
Smartsockets: solving the connectivity problems in grid computing
Proceedings of the 16th international symposium on High performance distributed computing
Reconciling performance and programmability in networking systems
Proceedings of the 2007 conference on Applications, technologies, architectures, and protocols for computer communications
N2N: A Layer Two Peer-to-Peer VPN
AIMS '08 Proceedings of the 2nd international conference on Autonomous Infrastructure, Management and Security: Resilient Networks and Services
Packet capture in 10-gigabit Ethernet environments using contemporary commodity hardware
PAM'07 Proceedings of the 8th international conference on Passive and active network measurement
A virtual network (ViNe) architecture for grid computing
IPDPS'06 Proceedings of the 20th international conference on Parallel and distributed processing
VIOLIN: virtual internetworking on overlay infrastructure
ISPA'04 Proceedings of the Second international conference on Parallel and Distributed Processing and Applications
Evaluation of the HPC challenge benchmarks in virtualized environments
Euro-Par'11 Proceedings of the 2011 international conference on Parallel Processing - Volume 2
Hi-index | 0.00 |
Connectivity limitations in the current Internet have motivated the development of many overlay networking technologies that enable applications to transparently overcome such limitations. For easy development and deployment, overlay networks are typically implemented via a user-level network virtualization software layer, often using highlevel languages. Existing solutions report performance that can keep up with slow wide-area links--however, the question remains as to how overlay networks perform on new high-speed Internet connections. This paper characterizes the performance of user-level packet processing, which is at the core of most overlay networks implementations. To this end, building blocks of packet-processing software are identifi ed and characterized, and performance of IP forwarders developed in C and Java are compared through extensive measurements. Factors that affect the performance of overlay networks and limitations of existing solutions are characterized, providing insights on possible improvements. Experimental results show the following: to achieve maximum throughput, only a few microseconds (2-5) can be spent in virtual network processing; processing of small packets can limit TCP throughput; and overlays need to be carefully architected as encapsulation overheads can be substantial. Copyright © 2009 John Wiley & Sons, Ltd.