DS2: A DHT-based substrate for distributed services
- PDF / 1,970,749 Bytes
- 17 Pages / 595.224 x 790.955 pts Page_size
- 26 Downloads / 175 Views
DS2: A DHT-based substrate for distributed services Lichun Li · Xin Xu · Jun Wang · Wei Wang
Received: 1 September 2012 / Accepted: 9 August 2013 / Published online: 6 September 2013 © Springer Science+Business Media New York 2013
Abstract DHT (Distributed Hash Table) algorithms are very efficient for distributed data management. As one kind of P2P overlay, DHT overlay also has the advantages of high reliability, high scalability and low cost. Because of these advantages, DHT has been proposed to form server farms such as DHT-based NoSQL databases, SIP server farms, IMS server farms, OpenFlow controller farms, etc. This paper presents DS2, a DHT-based substrate designed for the application server farms providing distributed services. DS2 facilitates the deployment of DHT-based distributed services in three aspects. First, DS2 offers a powerful data model to manage complex data. Second, DS2 provides application message routing function and workload migration function, which help application server farm to achieve load balance, failover and service continuity. Third, DS2 allows deploying application server farms across data centers. DS2 deploying across data centers is optimized to
This work is supported by the Ministry of Science and Technology of China under Grant No. 2010ZX03004-001-01. L. Li () · X. Xu · J. Wang Central R&D, ZTE Corporation, Nanjing, Jiangsu, People’s Republic of China e-mail: [email protected] X. Xu e-mail: [email protected] J. Wang e-mail: [email protected] W. Wang State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, People’s Republic of China e-mail: [email protected]
provide better performance and service continuity. We have implemented a DS2 prototype and used it in ZTE’s P2P CSCF prototype and service routing prototype to enable IMS services and service routing services successfully. Keywords Distributed Hash Table · NoSQL · Big data
1 Introduction DHT (Distributed Hash Table) algorithms are very efficient for distributed data management. As one kind of P2P overlay, DHT overlay also has the advantages of high reliability, high scalability, and low deployment cost. Because of above advantages, DHT has been widely used in server farms. It has been used to build NoSQL (Not only SQL) databases and distributed cache in big web sites to manage and cache massive data. Redis [1] , Amazon’s Dynamo [2], Facebook’s Cassandra [3], and Yahoo!’s Pnuts [4] are some good examples. DHT-based application server farms are also proposed to provide distributed services to massive application clients. This paper refers distributed services as the services provided by DHT-based application server farms. Proposed DHT-based application server farms include DHT-based SIP server farm [5, 6], IMS (IP Multimedia Subsystem) CSCF (Call Session Control Function) server farm [7], IMS HSS (Home Subscriber Service) server farm [7, 8], OpenFlow controller farm [9], name resolving system [10, 11], tracker farm [12], etc. Each server in a DHT-based application server farm is both a DH
Data Loading...
