Cluster-based scalable network services
Proceedings of the sixteenth ACM symposium on Operating systems principles
Measurements and analysis of end-to-end Internet dynamics
Measurements and analysis of end-to-end Internet dynamics
IEEE/ACM Transactions on Networking (TON)
The end-to-end effects of Internet path selection
Proceedings of the conference on Applications, technologies, architectures, and protocols for computer communication
SOSP '01 Proceedings of the eighteenth ACM symposium on Operating systems principles
On the use and performance of content distribution networks
IMW '01 Proceedings of the 1st ACM SIGCOMM Workshop on Internet Measurement
The state of the art in locally distributed Web-server systems
ACM Computing Surveys (CSUR)
Globally Distributed Content Delivery
IEEE Internet Computing
End-to-end WAN service availability
IEEE/ACM Transactions on Networking (TON)
Measuring the effects of internet path faults on reactive routing
SIGMETRICS '03 Proceedings of the 2003 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
PlanetLab: an overlay testbed for broad-coverage services
ACM SIGCOMM Computer Communication Review
Measuring ISP topologies with rocketfuel
IEEE/ACM Transactions on Networking (TON)
Geometric generalizations of the power of two choices
Proceedings of the sixteenth annual ACM symposium on Parallelism in algorithms and architectures
Scalable routing overlay networks
ACM SIGOPS Operating Systems Review
Improving the reliability of internet paths with one-hop source routing
OSDI'04 Proceedings of the 6th conference on Symposium on Opearting Systems Design & Implementation - Volume 6
iPlane: an information plane for distributed services
OSDI '06 Proceedings of the 7th USENIX Symposium on Operating Systems Design and Implementation - Volume 7
Hi-index | 0.01 |
In this work we propose to use path information to improve the reliability of the Internet. Previous work put forth a simple idea of using an overlay network of intermediary detour nodes that can be used to route around failures on direct Internet paths [1]. We provide the mechanism for choosing these intermediary nodes. The underlying idea of our work is that knowledge of the point-of-presence (PoP) path between the source and destination as well as the PoP paths between potential detour nodes and destination can be used to pick the intermediary for routing around failures on the direct path. We validate our proposal by performing an experiment using PlanetLab [2] and leveraging the existing iPlane [3] infrastructure. Using the data from iPlane, we obtain a two-fold decrease in path outage probability over the state-of-the-art.