Improving the Reliability of Internet Paths with One-hop Source Routing Export

@inproceedings{citeulike:800027, abstract = {Recent work has focused on increasing availability in the face of Internet path failures. To date, proposed solutions have relied on complex routing and path-monitoring schemes, trading scalability for availability among a relatively small set of hosts. <P> This paper proposes a simple, scalable approach to recover from Internet path failures. Our contributions are threefold. First, we conduct a broad measurement study of Internet path failures on a collection of 3,153 Internet destinations consisting of popular Web servers, broadband hosts, and randomly selected nodes. We monitored these destinations from 67 PlanetLab vantage points over a period of seven days, and found availabilities ranging from 99.6\% for servers to 94.4\% for broadband hosts. When failures do occur, many appear too close to the destination (e.g., last-hop and end-host failures) to be mitigated through alternative routing techniques of any kind. Second, we show that for the failures that can be addressed through routing, a simple, scalable technique, called <i>one-hop source routing</i>, can achieve close to the maximum benefit available with very low overhead. When a path failure occurs, our scheme attempts to recover from it by routing <i>indirectly</i> through a small set of <i>randomly</i> chosen intermediaries. <P> Third, we implemented and deployed a prototype one-hop source routing infrastructure on PlanetLab. Over a three day period, we repeatedly fetched documents from 982 popular Internet Web servers and used one-hop source routing to attempt to route around the failures we observed. Our results show that our prototype successfully recovered from 56\% of network failures. However, we also found a large number of server failures that cannot be addressed through alternative routing. <P> Our research demonstrates that one-hop source routing is easy to implement, adds negligible overhead, and achieves close to the maximum benefit available to indirect routing schemes, <i>without</i> the need for path monitoring, history, or a-priori knowledge of any kind. <P>}, author = {Gummadi, Krishna P. and Madhyastha, Harsha V. and Gribble, Steven D. and Levy, Henry M. and Wetherall, David}, citeulike-article-id = {800027}, citeulike-linkout-0 = {http://www.usenix.org/publications/library/proceedings/osdi04/tech/gummadi.html}, journal = {OSDI '04}, keywords = {detour, hop, one, overlay, resilient}, pages = {183--198}, posted-at = {2006-08-14 01:38:15}, priority = {0}, title = {Improving the Reliability of Internet Paths with One-hop Source Routing}, url = {http://www.usenix.org/publications/library/proceedings/osdi04/tech/gummadi.html} }

TY - CONF ID - citeulike:800027 L3 - citeulike-article-id:800027 N2 - Recent work has focused on increasing availability in the face of Internet path failures. To date, proposed solutions have relied on complex routing and path-monitoring schemes, trading scalability for availability among a relatively small set of hosts. <P> This paper proposes a simple, scalable approach to recover from Internet path failures. Our contributions are threefold. First, we conduct a broad measurement study of Internet path failures on a collection of 3,153 Internet destinations consisting of popular Web servers, broadband hosts, and randomly selected nodes. We monitored these destinations from 67 PlanetLab vantage points over a period of seven days, and found availabilities ranging from 99.6% for servers to 94.4% for broadband hosts. When failures do occur, many appear too close to the destination (e.g., last-hop and end-host failures) to be mitigated through alternative routing techniques of any kind. Second, we show that for the failures that can be addressed through routing, a simple, scalable technique, called <i>one-hop source routing</i>, can achieve close to the maximum benefit available with very low overhead. When a path failure occurs, our scheme attempts to recover from it by routing <i>indirectly</i> through a small set of <i>randomly</i> chosen intermediaries. <P> Third, we implemented and deployed a prototype one-hop source routing infrastructure on PlanetLab. Over a three day period, we repeatedly fetched documents from 982 popular Internet Web servers and used one-hop source routing to attempt to route around the failures we observed. Our results show that our prototype successfully recovered from 56% of network failures. However, we also found a large number of server failures that cannot be addressed through alternative routing. <P> Our research demonstrates that one-hop source routing is easy to implement, adds negligible overhead, and achieves close to the maximum benefit available to indirect routing schemes, <i>without</i> the need for path monitoring, history, or a-priori knowledge of any kind. <P> JF - OSDI '04 EP - 198 TI - Improving the Reliability of Internet Paths with One-hop Source Routing SP - 183 KW - detour KW - hop KW - one KW - overlay KW - resilient AU - Gummadi, Krishna AU - Madhyastha, Harsha AU - Gribble, Steven AU - Levy, Henry AU - Wetherall, David UR - http://www.usenix.org/publications/library/proceedings/osdi04/tech/gummadi.html ER -