Chunqiang Tang
ABSTRACT
The routing tables of Distributed Hash Tables (DHTs) can vary from size O(1) to O(n). Currently, what is lacking is an analytic framework to suggest the optimal routing table size for a given workload. This paper (1) compares DHTs with O(1) to O(n) routing tables and identifies some good design points; and (2) proposes protocols to realize the potential of those good design points.We use total traffic as the uniform metric to compare heterogeneous DHTs and emphasize the balance between maintenance cost and lookup cost. Assuming a node on average processes 1,000 or more lookups during its entire lifetime, our analysis shows that large routing tables actually lead to both low traffic and low lookup hops. These good design points translate into one-hop routing for systems of medium size and two-hop routing for large systems.Existing one-hop or two-hop protocols are based on a hierarchy. We instead demonstrate that it is possible to achieve completely decentralized one-hop or two-hop routing, i.e., without giving up being peer-to-peer. We propose 1h-Calot for one-hop routing and 2h-Calot for two-hop routing. Assuming a moderate lookup rate, compared with DHTs that use O(log n) routing tables, 1h-Calot and 2h-Calot save traffic by up to 70% while resolving lookups in one or two hops as opposed to O(log n) hops.
- C. Blake and R. Rodrigues. High Availability, Scalable Storage, Dynamic Peer Networks: Pick Two. In HotOS, 2003. Google Scholar
Digital Library
- F. Dabek, M. Kaashoek, D. Karger, R. Morris, and I. Stoica. Wide-area cooperative storage with CFS. In SOSP, 2001. Google ScholarDigital Library
- F. Dabek, J. Li, E. Sit, J. Robertson, M. F. Kaashoek, and R. Morris. Designing a DHT for Low Latency and High Throughput. In NSDI, 2004. The network latency data set is available at http://www.pdos.lcs.mit.edu/p2psim/kingdata. Google ScholarDigital Library
- M. J. Freedman, E. Freudenthal, and D. Maziéres. Democratizing Content Publication with Coral. In NSDI, 2004. Google ScholarDigital Library
- A. Ganesh, A.-M. Kermarrec, and L. Massoulié. HiScamp: self-organising hierarchical membership protocol. In European ACM SIGOPS Workshop, 2002. Google ScholarDigital Library
- K. P. Gummadi, R. Gummadi, S. D. Gribble, S. Ratnasamy, S. Shenker, and I. Stoica. The Impact of DHT Routing Geometry on Resilience and Proximity. In SIGCOMM, 2003. Google ScholarDigital Library
- A. Gupta, B. Liskov, and R. Rodrigues. Efficient Routing for Peer-to-Peer Overlays. In NSDI, 2004. Google ScholarDigital Library
- I. Gupta, K. Birman, P. Linga, A. Demers, and R. V. Renesse. Kelips: building an efficient and stable P2P DHT through increased memory and background overhead. In IPTPS, 2003.Google ScholarCross Ref
- F. Kaashoek and D. R. Karger. Koorde: A simple degree-optimal hash table. In IPTPS, 2003.Google ScholarCross Ref
- KaZaA. http://www.kazaa.com.Google Scholar
- S. Kumar, A.and Merugu, J. Xu, and X. Yu. Ulysses: A Robust, Low-Diameter, Low-Latency Peer-to-peer Network. In ICNP, 2003. Google ScholarDigital Library
- J. Li, J. Stribling, T. Gil, R. Morris, and F. Kaashoek. Comparing the performance of distributed hash tables under churn. In IPTPS, 2004. Google ScholarDigital Library
- D. Loguinov, A. Kumar, V. Rai, and S. Ganesh. Graph-theoretic analysis of structured peer-to-peer systems: routing distances and fault resilience. In SIGCOMM, 2003. Google ScholarDigital Library
- D. Malkhi, M. Naor, and D. Ratajczak. Viceroy: A Scalable and Dynamic Emulation of the Butterfly. In PODC'02, 2002. Google ScholarDigital Library
- A. Mizrak, Y. Cheng, V. Kumar, and S. Savage. Structured Superpeers: Leveraging Heterogeneity to Provide Constant-Time Lookup. In WIAPP, 2003. Google ScholarDigital Library
- V. Ramasubramanian and E. G. Sirer. Beehive: O(1) Lookup Performance for Power-Law Query Distributions in Peer-to-Peer Overlays. In NSDI, 2004. Google ScholarDigital Library
- S. Rhea, D. Geels, T. Roscoe, and J. Kubiatowicz. Handling churn in a dht. In USENIX Annual Technical Conference, 2004. Google ScholarDigital Library
- R. Rodrigues, B. Liskov, and L. Shrira. The design of a robust peer-to-peer system. In SIGOPS European Workshop, 2002. Google ScholarDigital Library
- S. Saroiu, P. K. Gummadi, and S. D. Gribble. A measurement study of peer-to-peer file sharing systems. In MMCN, 2002.Google Scholar
- I. Stoica, R. Morris, D. Karger, M. F. Kaashoek, and H. Balakrishnan. Chord: A scalable peer-to-peer lookup service for internet applications. In SIGCOMM, 2001. Google ScholarDigital Library
- C. Tang and S. Dwarkadas. Hybrid Global-Local Indexing for Efficient Peer-to-Peer Information Retrieval. In NSDI, 2004. Google ScholarDigital Library
- The Open DHT Project. http://openhash.org/.Google Scholar
- J. Xu, A. Kumar, and X. Yu. On the Fundamental Tradeoffs between Routing Table Size and Network Diameter in Peer-to-Peer Networks. JSAC, 22(1):151--163, January 2004. Google ScholarDigital Library
Index Terms
- Low traffic overlay networks with large routing tables
Recommendations
Low traffic overlay networks with large routing tables
Performance evaluation reviewThe routing tables of Distributed Hash Tables (DHTs) can vary from size O(1) to O(n). Currently, what is lacking is an analytic framework to suggest the optimal routing table size for a given workload. This paper (1) compares DHTs with O(1) to O(n) ...
PowerTrust: A Robust and Scalable Reputation System for Trusted Peer-to-Peer Computing
Peer-to-Peer (P2P) reputation systems are essential to evaluate the trustworthiness of participating peers and to combat the selfish, dishonest, and malicious peer behaviors. The system collects locally-generated peer feedbacks and aggregates them to ...
Trustworthiness of Acquaintances in Peer-to-Peer(P2P) Overlay Networks
CISIS '10: Proceedings of the 2010 International Conference on Complex, Intelligent and Software Intensive SystemsSystems using peer-to-peer (P2P) overlay networks are getting a central position in information systems. P2P systems are in nature fully distributed, with no centralized coordinator and each peer is autonomous. Each peer has to obtain information on ...
Reviews
Ruay-Shiung Chang
Distributed hashing tables (DHTs) are decentralized data structures that allow objects (keys) to be easily found in a distributed storage system. DHTs are most useful in peer-to-peer file sharing systems. In past research about DHTs, the focus has been on minimizing the number of hops in any routing path, and reducing the maintenance cost for DHTs. These two goals are obviously in conflict, since for a completely connected system with n nodes, the routing path has only one hop. However, each node then has n-1 neighbors, and a routing table update needs to be broadcast to all n-1 neighbors. This incurs a huge maintenance cost since it is common in a peer-to-peer system that nodes join or leave frequently. Another factor is the size of the routing tables. Usually, a small routing table will increase the number of hops in routing. This paper identifies some good design points for DHTs, and proposes two implementation schemes that possess good design points for a peer-to-peer network. The first scheme needs only one-hop routing, and is called 1h-Calot. The second scheme needs two-hop routing, and is called 2h-Calot. However, it is not clear why they are called Calot. Most of this paper is devoted to the analytic and simulation results to prove that the proposed methods are indeed better than the previous results. This is not an introductory paper about DHTs. For those not familiar with DHTs, it will be somewhat difficult to read and understand. Furthermore, I think the authors could have concentrated more on the 1h-Calot scheme, and explained it in greater detail. The 2h-Calot scheme description could have been discussed more briefly, since the concept is similar to the 1h-Calot scheme. Online Computing Reviews Service
Access critical reviews of Computing literature here
Become a reviewer for Computing Reviews.
Comments