DocumentCode :
3012381
Title :
High-level parallelisation in a database cluster: a feasibility study using document services
Author :
Grabs, Torsten ; Böhm, Klemens ; Schek, Hans-Jörg
Author_Institution :
Swiss Federal Inst. of Technol., Zurich, Switzerland
fYear :
2001
fDate :
2001
Firstpage :
121
Lastpage :
130
Abstract :
Our concern is the design of a scalable infrastructure for complex application services. We want to find out if a cluster of commodity database systems is well-suited as such an infrastructure. To this end, we have carried out a feasibility study based on document services, e.g. document insertion and retrieval. We decompose a service request into short parallel database transactions. Our system, implemented as an extension of a transaction processing monitor, routes the short transactions to the appropriate database systems in the cluster. Routing depends on the data distribution that we have chosen. To avoid bottlenecks, we distribute document functionality, such as term extraction, over the cluster. Extensive experiments show the following. (1) A relatively small number of components - for example eight components $already suffices to cope with high workloads of more than 100 concurrently active clients. (2) Speedup and throughput increase linearly for insertion operations when increasing the cluster size. These observations also hold when bundling service invocations into transactions at the semantic layer. A specialized coordinator component then implements semantic serializability and atomicity. Our experiments show that such a coordinator has minimal impact on CPU resource consumption and on response times
Keywords :
document handling; parallel databases; transaction processing; workstation clusters; CPU resource consumption; atomicity; bottlenecks; cluster size; commodity database systems; complex application services; concurrently active clients; data distribution; database cluster; distributed document functionality; document insertion; document retrieval; document services; feasibility study; high-level parallelisation; insertion operations; response times; scalable infrastructure; semantic layer; semantic serializability; service invocation bundling; service request decomposition; short parallel database transactions; specialized coordinator component; speedup; term extraction; throughput; transaction processing monitor; transaction routing; workloads; Atomic layer deposition; Data mining; Data structures; Database systems; Delay; Interconnected systems; Routing; Scalability; Throughput; Transaction databases;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Data Engineering, 2001. Proceedings. 17th International Conference on
Conference_Location :
Heidelberg
ISSN :
1063-6382
Print_ISBN :
0-7695-1001-9
Type :
conf
DOI :
10.1109/ICDE.2001.914820
Filename :
914820
Link To Document :
بازگشت