ISSN:
1573-7578
Keywords:
database
;
hashing
;
scalable
;
distributed
;
performance
Source:
Springer Online Journal Archives 1860-2000
Topics:
Computer Science
Notes:
Abstract The paper presents a family of distributed file structures, coined DiFS, for record structured, disk resident files with key based exact or interval match access. The file is organized into buckets that are spread among multiple servers, where a server may hold several buckets. Client requests are serviced by mapping keys onto buckets and looking up the corresponding server in an address table. Dynamic growth, in terms of file size and access load, is supported by bucket splits and bucket migrations onto the existing or newly created servers. The major problem that we are addressing is achieving scalability in the sense that both the file size and the client throughput can be scaled up by linearly increasing the number of servers and dynamically redistributing the data. Unlike previous work with similar objectives, our data redistribution considers explicitly the cost/performance ratio of the system by aiming to minimize the number of servers that are used to provide the required performance. A new server is added only if the overall server load in the system does not drop below a pre-specified threshold. Simulation results demonstrate the scalability with controlled cost/performance and the importance of global load control. The impact of various tuning parameters on the effectiveness of the load control is studied in detail. Finally, we compare our approach with other approaches known to date and demonstrate that each of the previous approaches can be recast as a special case of our model.
Type of Medium:
Electronic Resource
URL:
http://dx.doi.org/10.1007/BF00119338
Permalink
