Abstract:

The data access on grid is of low quality because the existing query optimization techniques do not consider the dynamic properties of data resources in grid environments. In order to solve this problem, a QoS （ Quality of Service） -based approach to data access is proposed, which considers not only the dynamic properties of data resources but also the QoS goals of users, and selects generated query plans according to the QoS goals of users. Mo- reover, a segmented pipe tree based on the pipelined parallelism is presented to optimize multi-join queries, which not only improves the parallelism but also returns some results to users as soon as possible. Experimental results show that the proposed approach is effective in providing data access at different levels for different users.

Key words: data access, grid environment, quality of service, query optimization, segmented pipe tree