This paper addresses the problem of churn---the continuous process of node arrival and departure---in distributed hash tables (DHTs). We argue that DHTs should perform lookups quickly and consistently under churn rates at least as high as those observed in deployed P2P systems such as Kazaa. We then show through experiments on an emulated network that current DHT implementations cannot handle such churn rates. Next, we identify and explore three factors affecting DHT performance under churn: reactive versus periodic failure recovery, message timeout calculation, and proximity neighbor selection. We work in the context of a mature DHT implementation called Bamboo, using the ModelNet network emulator, which models in-network queuing, cross-traffic, and packet loss. These factors are typically missing in earlier simulationbased DHT studies, and we show that careful attention to them in Bamboo's design allows it to function effectively at churn rates at or higher than that observed in P2P file-sharing applications, while using lower maintenance bandwidth than other DHT implementations.
|
2449
|
Chord: a scalable peer-to-peer lookup service for Internet applications
– Stoica
- 2001
|
|
1999
|
A scalable content-addressable network
– Ratnasamy, Francis, et al.
- 2001
|
|
1836
|
Congestion avoidance and control
– Jacobson, Karels
- 1988
|
|
1302
|
Pastry: Scalable, distributed object location and routing for large-scale peer-to-peer systems
– Rowstron, Druschel
- 2001
|
|
823
|
Tapestry: An Infrastructure for FaultTolerant Wide-Area Location and Routing
– Zhao, Kubiatowicz, et al.
- 2001
|
|
789
|
S.: A measurement study of peer-to-peer file sharing systems
– Saroiu, Gummadi, et al.
- 2002
|
|
628
|
I.: Wide-area cooperative storage with CFS
– Dabek, Kaashoek, et al.
- 2001
|
|
457
|
Epidemic algorithms for replicated database maintenance
– Demers, Greene, et al.
- 1987
|
|
391
|
Accessing nearby copies of replicated objects in a distributed environment
– Plaxton, Rajaraman, et al.
- 1999
|
|
298
|
Kademlia: A Peer-to-Peer Information System Based on the XOR Metric
– Maymounkov, Mazieres
- 2002
|
|
289
|
emphTapestry: A resilient global-scale overlay for service deployment
– Zhao, Huang, et al.
- 2004
|
|
256
|
Measurement, modeling, and analysis of a peer-to-peer file sharing workload
– Gummadi, Dunn, et al.
- 2003
|
|
226
|
Analyzing peer-to-peer traffic across large networks
– Sen, Wang
- 2002
|
|
194
|
G.: Understanding Availability
– Bhagwan, Savage, et al.
- 2003
|
|
182
|
The impact of DHT routing geometry on resilience and proximity
– Gummadi, Gummadi, et al.
|
|
174
|
A quantitative comparison of graph-based models for internet topology
– Zegura, Calvert, et al.
- 1997
|
|
144
|
Scalability and Accuracy in a Large-Scale Network Emulator
– Vahdat, Yocum, et al.
- 2002
|
|
142
|
Analysis of the evolution of peer-to-peer systems
– Liben-Nowell, Balakrishnan, et al.
- 2002
|
|
140
|
Distributed object location in a dynamic network
– Hildrum, Kubiatowicz, et al.
- 2002
|
|
112
|
Exploiting Network Proximity in Peerto-Peer Overlay Networks
– Castro, Druschel, et al.
- 2002
|
|
107
|
Availability and locality measurements of peer-to-peer file systems
– Chu, Labonte, et al.
- 2002
|
|
97
|
Designing a DHT for low latency and high throughput
– Dabek, Li, et al.
- 2004
|
|
95
|
An evaluation of scalable application-level multicast built using peer-to-peer overlays
– Castro, Jones, et al.
- 2003
|
|
86
|
High availability, scalable storage, dynamic peer networks: Pick two
– Blake
- 2003
|
|
69
|
On spreading a rumor
– Pittel
- 1987
|
|
59
|
Performance and dependability of structured peer-to-peer overlays
– Castro, Costa, et al.
- 2003
|
|
57
|
Controlling the cost of reliability in peer-to-peer overlays
– Mahajan, Castro, et al.
|
|
57
|
Brocade: Landmark routing on overlay networks
– Zhao, Duan, et al.
- 2002
|
|
55
|
Datagram congestion control protocol (DCCP
– Kohler, Handley, et al.
- 2006
|
|
47
|
The Case for a Hybrid P2P Search Infrastructure
– Loo, Huebsch, et al.
- 2004
|
|
43
|
Comparing the performance of distributed hash tables under churn
– Li, Stribling, et al.
- 2004
|
|
31
|
Robust and Efficient Data Management for a Distributed Hash Table
– Cates
- 2003
|
|
10
|
Learning Euclidean coordinates for Internet hosts. www.pdos.lcs.mit.edu/˜rsc/6867.pdf
– Cox, Dabek
- 2002
|
|
8
|
Building a flexible and efficient routing infrastructure: Need and challenges
– Lakshminarayanan, Stoica, et al.
- 2003
|
|
1
|
Measurement, modeling, and analysis of a peerto -peer file-sharing workload
– Gummadi, Dunn, et al.
- 2003
|
