Hasso-Plattner-Institut
Prof. Dr. h.c. mult. Hasso Plattner
 

Martin Boissier

PhD Candidate

Email:martin.boissier(at)hpi.de
Address:August-Bebel-Str. 88, 14482 Potsdam
Room:V-2.05
Links:DBLP - personal website

 

Research Area: Autonomous Data Management

Research

Main Memory Footprint Reduction of In-Memory Database Systems

Database systems that keep their data primarily in main memory provide high query performance but also incur high costs. We have analyzed various real-world enterprise systems and their workload and data characteristics. We found that the main memory footprint can be efficiently reduced by (i) data encoding and (ii) tiering without degrading performance significantly. 
To encode and compress a database instance, we use learned cost models to predict runtimes of various data encodings. We use linear programming models to determine optimal encoding configurations within a given memory budget. For the applicability in real-world scenarios, the models incorporate robustness measures that mitigate unexpected performance degradations. To efficiently tier data to secondary storage, we extended the hybrid data layout of the first version of Hyrise and evict infrequently accessed columns in a row-major format.

 

Selected Publications

Sorry, the requested view was not found.

The technical reason is: No template was found. View could not be resolved for action "view" in class "AcademicPuma\ExtBibsonomyCsl\Controller\DocumentController".

Teaching

Lectures and Seminars:

Supervised Master Theses:

  • "Workload-Driven Smooth Index and Filter Selection for In-Memory Database Scan Acceleration" (November 2022)
  • "Cost-aware Filtering in Query Processing on Serverless Cloud Infrastructure" (October 2022)
  • "Automatic Tiering in Hyrise" (September 2022)
  • "Automatic Clustering in Hyrise" (October 2020)
  • "Learned Cost Models for Query Optimization" (March 2019)
  • "Improving Cardinality Estimation and Access Avoidance in Hyrise" (November 2018)
  • "Data-Driven Ordering and Dynamic Pricing Competition on Online Marketplaces" (May 2018)
  • "Probabilistic Data Structures for In-Memory Databases" (May 2018)
  • "Maintainable and Self-Adapting Column Compression Schemes for HTAP Databases" (April 2018)
  • "Optimizing Database Scan Performance through Access Avoidance in Chunk-Based Databases using Multi-Dimensional Filters" (August 2017)
  • "Predicting movie success before release – Using individualized econometric models to predict box office performance." (January 2017)
  • "Workload-Aware Partitioning and Query Pruning for Mixed Workloads on In-Memory Databases" (January 2016)