On concurrency control in sliding window queries over data streams

Data stream systems execute a dynamic workload of long-running and one-time queries, with the streaming inputs typically bounded by sliding windows. For efficiency, windows may be advanced periodically by replacing the oldest part of the window with a batch of new data. Existing work on stream processing assumes that a window cannot be advanced while it is being accessed by a query. In this paper, we argue that concurrent processing of queries (reads) and window-slides (writes) is required by data stream systems in order to allow prioritized query scheduling and improve the freshness of answers. We prove that the traditional notion of conflict serializability is insufficient in this context and define stronger isolation levels that restrict the allowed serialization orders. We also design and experimentally evaluate a transaction scheduler that efficiently enforces the new isolation levels.