@article{Boissier2021,
  author    = {Boissier, Martin},
  title     = {Robust and budget-constrained encoding configurations for in-memory database systems},
  series = {Proceedings of the VLDB Endowment},
  volume    = {15},
  journal   = {Proceedings of the VLDB Endowment},
  number    = {4},
  publisher = {Association for Computing Machinery (ACM)},
  address   = {[New York]},
  issn      = {2150-8097},
  doi       = {10.14778/3503585.3503588},
  pages     = {780 -- 793},
  year      = {2021},
  abstract  = {Data encoding has been applied to database systems for decades as it mitigates bandwidth bottlenecks and reduces storage requirements. But even in the presence of these advantages, most in-memory database systems use data encoding only conservatively as the negative impact on runtime performance can be severe. Real-world systems with large parts being infrequently accessed and cost efficiency constraints in cloud environments require solutions that automatically and efficiently select encoding techniques, including heavy-weight compression. In this paper, we introduce workload-driven approaches to automaticaly determine memory budget-constrained encoding configurations using greedy heuristics and linear programming. We show for TPC-H, TPC-DS, and the Join Order Benchmark that optimized encoding configurations can reduce the main memory footprint significantly without a loss in runtime performance over state-of-the-art dictionary encoding. To yield robust selections, we extend the linear programming-based approach to incorporate query runtime constraints and mitigate unexpected performance regressions.},
  language  = {en}
}