Topologically-aware overlay construction and server selection

By Sylvia Ratnasamy, Mark James Handley, Richard M. Karp, Scott Shenker. Proceedings.Twenty-First Annual Joint Conference of the IEEE Computer and Communications Societies, 2002

924 citations recorded by the source corpus.

Subfields: Computer Networks and Communications

View Paper: https://www.semanticscholar.org/paper/4d54edc7ed36cc522ab732c8cc5e3078cd22768b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

1. Emin Gün Sirer
2. Robert Morris
3. Antony Ian Taylor Rowstron
4. Miguel Oom Temudo de Castro
5. Emil Sit
6. Frank Dabek
7. Peter Druschel
8. Jonathan Ledlie

Citations in the corpus

• GEM: Graph EMbedding for routing and data-centric storage in sensor networks without geographic information (2003, background): “There has been work in constructing overlay networks close to the network topology, such as [30], which could alleviate this effect.”
• Designing a DHT for Low Latency and High Throughput (2004, methodology): “DHash++ calculates the key to be the SHA-1 hash of the value, and uses Chord to decide which server should store a given block; each server runs both Chord and DHash++ software.”
• Can ISPS and P2P users cooperate for improved performance? (2007, background): “, [18, 19, 20] or that are within the same AS, e.”
• King: estimating latency between arbitrary internet end hosts (2002, background): “Most of the measurement studies that we have previously mentioned [19], [15], [17] fall under this category.”
• PIC: practical Internet coordinates for distance estimation (2004, background): “Most proposals [9] [17] [13] [22] rely on a small set of infrastructure nodes that are a single point of failure and can limit scalability if they become communication bottlenecks.”
• PlanetLab: an overlay testbed for broad-coverage services (2003, background): “…for Broad-Coverage Services Brent Chun, David Culler, Timothy Roscoe Intel Research Berkeley Andy Bavier, Larry Peterson, Mike Wawrzoniak Mic Bowman Princeton University Intel Corporation ABSTRACT PlanetLabis aglobal overlay networkfordeveloping and ac­cessingbroad-coveragenetwork services.”
• Meridian: a lightweight network location service without virtual coordinates (2005, methodology): “Binning [47] operates similarly, using approximate bin numbers instead of direct latency measurements.”
• Network Coordinates in the Wild (2007, methodology): “Ratnasamy et al. proposed a hybrid approach: nodes that are similar distances away from fixed landmarks place themselves into the same cluster; they also found error was highly dependent on the number of bins [ 23 ].”
• The impact of DHT routing geometry on resilience and proximity (2003, neutral): “While previous studies [2, 8, 9, 21] evaluate proximity methods using one or more of these topology generators along with some rather ad hoc choice of latency assignments, they don’t analyze how their choice of latencies affects the performance of the proximity methods.”
• Operating Systems Support for Planetary-Scale Network Services (2004, background): “It supports over 450 research projects focused on a wide range of services, including file sharing and networkembedded storage [11, 22, 35], content distribution networks [39], routing and multicast overlays [1, 8], QoS overlays [38], scalable object location services [2, 33, 34, 37] anomaly detecti”