Group-Scope Query and Its Access Method
Nowadays, large scale workloads of typical Web 2.0 applications are well supported by NoSQL systems. The most efficient query that NoSQL systems have provided us is the key-lookup, but it is not quite efficient for some kinds of complex queries. One of these kinds of queries, which we name as Group-Scope Query, is very common in practical applications. In this paper, we explore an access method for group-scope queries. In this method, data are partitioned into groups, and a multi-dimensional primary index is built for each group. Meanwhile, we avoid establishing secondary indexes which are known to require additional expenses. YCSB is used to evaluate the performance of our approach, and the results show that our access method is scalable and efficient.
KeywordsRange Query Access Method Gray Code Region Query Secondary Index
Unable to display preview. Download preview PDF.
- 2.Faloutsos, C.: Multiattribute hashing using gray codes. In: ACM SIGMOD Record, vol. 15, pp. 227–238. ACM (1986)Google Scholar
- 3.Cooper, B.F., Silberstein, A., Tam, E., Ramakrishnan, R., Sears, R.: Benchmarking cloud serving systems with ycsb. In: Proceedings of the 1st ACM Symposium on Cloud Computing, pp. 143–154. ACM (2010)Google Scholar
- 5.Hastorun, D., Jampani, M., Kakulapati, G., Pilchin, A., Sivasubramanian, S., Vosshall, P., Vogels, W.: Dynamo: amazons highly available key-value store. In: Proc. SOSP. Citeseer (2007)Google Scholar
- 6.Tropf, H., Herzog, H.: Multidimensional range search in dynamically balanced trees. Angewandte Info., 71–77 (1981)Google Scholar