Exploiting Data Skew for Improved Query Performance

Analytic queries enable sophisticated large-scale data analysis within many commercial, scientific and medical domains today. Data skew is a ubiquitous feature of these real-world domains. In a retail database, some products are typically much more popular than others. In a text database, word frequencies follow a Zipf distribution with a small number of very common words, and a long tail of infrequent words. In a geographic database, some regions have much higher populations (and therefore data measurements) than others. Current systems do not make the most of caches for exploiting skew. In particular, a whole cache line may remain cache resident even though only a small part of the cache line corresponds to a popular data item. In this article, we propose a novel index structure for repositioning data items to concentrate popular items into the same cache lines. The net result is better spatial locality, and better utilization of limited cache resources. We develop a theoretical model for analyzing the cache utilization, and implement database operators that are efficient in the presence of skew. Our experimental evaluation on real and synthetic data shows that exploiting skew can significantly improve in-memory query performance. In some cases, our techniques can speed up queries by over an order of magnitude.