@article{KossmannHalfpapJankriftetal.2020,
  author    = {Kossmann, Jan and Halfpap, Stefan and Jankrift, Marcel and Schlosser, Rainer},
  title     = {Magic mirror in my hand, which is the best in the land?},
  series = {Proceedings of the VLDB Endowment},
  volume    = {13},
  journal   = {Proceedings of the VLDB Endowment},
  number    = {11},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {2150-8097},
  doi       = {10.14778/3407790.3407832},
  pages     = {2382 -- 2395},
  year      = {2020},
  abstract  = {Indexes are essential for the efficient processing of database workloads. Proposed solutions for the relevant and challenging index selection problem range from metadata-based simple heuristics, over sophisticated multi-step algorithms, to approaches that yield optimal results. The main challenges are (i) to accurately determine the effect of an index on the workload cost while considering the interaction of indexes and (ii) a large number of possible combinations resulting from workloads containing many queries and massive schemata with possibly thousands of attributes. <br /> In this work, we describe and analyze eight index selection algorithms that are based on different concepts and compare them along different dimensions, such as solution quality, runtime, multi-column support, solution granularity, and complexity. In particular, we analyze the solutions of the algorithms for the challenging analytical Join Order, TPC-H, and TPC-DS benchmarks. Afterward, we assess strengths and weaknesses, infer insights for index selection in general and each approach individually, before we give recommendations on when to use which approach.},
  language  = {en}
}
@misc{HalfpapSchlosser2019,
  author    = {Halfpap, Stefan and Schlosser, Rainer},
  title     = {Workload-Driven Fragment Allocation for Partially Replicated Databases Using Linear Programming},
  series = {2019 IEEE 35th International Conference on Data Engineering (ICDE)},
  journal   = {2019 IEEE 35th International Conference on Data Engineering (ICDE)},
  publisher = {IEEE},
  address   = {New York},
  isbn      = {978-1-5386-7474-1},
  issn      = {1084-4627},
  doi       = {10.1109/ICDE.2019.00188},
  pages     = {1746 -- 1749},
  year      = {2019},
  abstract  = {In replication schemes, replica nodes can process read-only queries on snapshots of the master node without violating transactional consistency. By analyzing the workload, we can identify query access patterns and replicate data depending to its access frequency. In this paper, we define a linear programming (LP) model to calculate the set of partial replicas with the lowest overall memory capacity while evenly balancing the query load. Furthermore, we propose a scalable decomposition heuristic to calculate solutions for larger problem sizes. While guaranteeing the same performance as state-of-the-art heuristics, our decomposition approach calculates allocations with up to 23\% lower memory footprint for the TPC-H benchmark.},
  language  = {en}
}
@misc{HalfpapSchlosser2019,
  author    = {Halfpap, Stefan and Schlosser, Rainer},
  title     = {A Comparison of Allocation Algorithms for Partially Replicated Databases},
  series = {2019 IEEE 35th International Conference on Data Engineering (ICDE)},
  journal   = {2019 IEEE 35th International Conference on Data Engineering (ICDE)},
  publisher = {IEEE},
  address   = {New York},
  isbn      = {978-1-5386-7474-1},
  issn      = {1084-4627},
  doi       = {10.1109/ICDE.2019.00226},
  pages     = {2008 -- 2011},
  year      = {2019},
  abstract  = {Increasing demand for analytical processing capabilities can be managed by replication approaches. However, to evenly balance the replicas' workload shares while at the same time minimizing the data replication factor is a highly challenging allocation problem. As optimal solutions are only applicable for small problem instances, effective heuristics are indispensable. In this paper, we test and compare state-of-the-art allocation algorithms for partial replication. By visualizing and exploring their (heuristic) solutions for different benchmark workloads, we are able to derive structural insights and to detect an algorithm's strengths as well as its potential for improvement. Further, our application enables end-to-end evaluations of different allocations to verify their theoretical performance.},
  language  = {en}
}