Applying Virtual Storage Management Method to View Materialization

Abstract

The queries in data warehouse and online analytical processing (OLAP) systems have the complex nature and demand a long execution time. One user may deliver a sequence of related queries, and other users may also submit several queries. These queries may have commonalities. Hence, query response times can be greatly improved by caching previous query results to answer the later queries. The earlier researches on query caching can be divided into table level caching and query level caching. Then, other scholar proposed a chunked caching method for large query results. Chunked caching method separates the storage space into small regions, the caching unit. In this paper, we consider the textual feature of dimensions and propose a ranging algorithm to realize chunked caching for non-numerical data. We also use Least Recently Used (LRU) queue to record the time when a chunk in the cache is most recently referenced. Therefore, besides the benefits of query results themselves, the query variation during different period can also be considered in the computation of replacement priorities. According to the experimental result, we prove the efficiency of our proposal and find the optimal threshold to reduce overall response cost.