Haupt-Navigation

Publikationen

Efficient Window Aggregation with General Stream Slicing
Zitatschlüssel	TraubGCBKRM19
Autor	Jonas Traub, Philipp Grulich, Alejandro Rodríguez Cuéllar, Sebastian Breß, Asterios Katsifodimos, Tilmann Rabl, Volker Markl
Jahr	2019
Journal	22nd International Conference on Extending Database Technology (EDBT 2019).
Jahrgang	2019
Notiz	Best Paper Award 2019
Zusammenfassung	Window aggregation is a core operation in data stream processing. Existing aggregation techniques focus on reducing latency, elim-inating redundant computations, and minimizing memory usage. However, each technique operates under different assumptions with respect to workload characteristics such as properties of ag-gregation functions (e.g., invertible, associative), window types (e.g., sliding, sessions), windowing measures (e.g., time- or count-based), and stream (dis)order. Violating the assumptions of a tech-nique can deem it unusable or drastically reduce its performance. In this paper, we present the first general stream slicing tech-nique for window aggregation. General stream slicing automat-ically adapts to workload characteristics to improve performance without sacrificing its general applicability. As a prerequisite, we identify workload characteristics which affect the performance and applicability of aggregation techniques. Our experiments show that general stream slicing outperforms alternative con-cepts by up to one order of magnitude.