Title :
The Swarm scalable storage system
Author :
Hartman, John H. ; Murdock, Ian ; Spalink, Tammo
Author_Institution :
Dept. of Comput. Sci., Arizona Univ., Tucson, AZ, USA
Abstract :
Swarm is a storage system that provides scalable, reliable, and cost-effective data storage. Swarm is based on storage servers, rather than file servers; the storage servers are optimized for cost-performance and aggregated to provide high-performance data access. Swarm uses a striped log abstraction to store data on the storage servers. This abstraction simplifies storage allocation, improves file access performance, balances server loads, provides fault-tolerance through computed redundancy, and simplifies crash recovery. We have developed a Swarm prototype using a cluster of Linux-based personal computers as the storage servers and clients; the clients access the servers via the Swarm-based Sting file system. Our performance measurements show that a single Swarm client can write to two storage servers at 3.0 MB/s, while four clients can write to eight servers at 16.0 MB/s
Keywords :
client-server systems; fault tolerant computing; information retrieval; local area networks; network servers; redundancy; storage allocation; system recovery; Linux-based personal computer cluster; Swarm scalable storage system; Swarm-based Sting file system; abstraction; computed redundancy; cost performance; cost-effective data storage; crash recovery; fault-tolerance; file access performance; high-performance data access; performance measurements; reliable data storage; scalable data storage; server load balancing; storage allocation; storage clients; storage servers; striped log abstraction; Access protocols; Clustering algorithms; Computer science; Control systems; Costs; Fault tolerance; File servers; File systems; Network servers; Prototypes;
Conference_Titel :
Distributed Computing Systems, 1999. Proceedings. 19th IEEE International Conference on
Conference_Location :
Austin, TX
Print_ISBN :
0-7695-0222-9
DOI :
10.1109/ICDCS.1999.776508
