2013 · 15 citations · 8 references
ComputingComputer ScienceData ManagementData StructuresDatabasesData Structure AlgorithmsHash TablesQuery ProcessingStream ProcessingStreaming AlgorithmsData Stream ProcessingHash Table ImplementationsJoinJoin AlgorithmsJoin OperationsJoin ProcessingSliding WindowsStream Joins
Sliding window equijoins are commonly used in data stream applications. In their implementation, a hash table is generally allocated for each stream source. However, this structure may degrade join performance because all tuples in the hash tables need to be scanned to find expired tuples whenever windows are updated periodically. This paper presents an alternative structure to improve the performance of sliding window equijoins. The basic idea of the proposed method is to allocate a hash table for each set of tuples arriving for a window slide interval. This organization facilitates the identification of expired tuples and improves the join performance, which we observed through our experimental results.
8
Models and issues in data stream systems
Brian Babcock, Shivnath Babu, Mayur Datar et al. · 2002 · 2.5K citations
Models and issues in data stream systems
Brian Babcock, Shivnath Babu, Mayur Datar et al. · 2002 · 746 citations
Evaluating window joins over unbounded streams
Jaewoo Kang, Jeffrey F. Naughton, Stratis D. Viglas · 2004 · 355 citations
Flexible time management in data stream systems
Utkarsh Srivastava, Jennifer Widom · 2004 · 277 citations
Semantics and evaluation techniques for window aggregates in data streams
Jin Li, David Maier, Kristin Tufte et al. · 2005 · 244 citations