Projects

NVM Databases

The design of a database management system’s (DBMS) architecture is predicated on the target storage hierarchy. Traditional disk-oriented systems use a two-level hierarchy, with fast volatile memory used for caching, and slower, durable device used for primary storage. As such, these systems use a buffer pool and complex concurrency control schemes to mask disk latencies. Compare this to main memory DBMSs that assume all data can reside in DRAM, and thus do not need these components.

But emerging non-volatile memory (NVM) technologies require us to rethink this dichotomy. Such memory devices are slightly slower than DRAM, but all writes are persistent, even after power loss. These devices promise to overcome the disparity between processor performance and DRAM storage capacity limits that encumber data-centric applications.

We are studying NVMs to understand their performance characteristics in the context of big data systems and build the groundwork for new DBMS architectures.

People

Acknowledgements

This research was funded (in part) by the Intel Science and Technology Center for Big Data and the National Science Foundation (CCF-1438955 and CCF-1438967).

Publications

  • J. Arulraj and A. Pavlo, "How to Build a Non-Volatile Memory Database Management System," in Proceedings of the 2017 ACM International Conference on Management of Data, 2017, pp. 1753-1758. [PDF] [BIBTEX]
    @inproceedings{arulraj17,
      author = {Arulraj, Joy and Pavlo, Andrew},
      title = {How to Build a Non-Volatile Memory Database Management System},
      booktitle = {Proceedings of the 2017 ACM International Conference on Management of Data},
      series = {SIGMOD '17},
      year = {2017},
      pages = {1753--1758},
      numpages = {6},
      url = {http://db.cs.cmu.edu/papers/2017/p1753-arulraj.pdf},
     }
  • J. Arulraj, A. Pavlo, and P. Menon, "Bridging the Archipelago Between Row-Stores and Column-Stores for Hybrid Workloads," in Proceedings of the 2016 International Conference on Management of Data, 2016, pp. 583-598. [PDF] [BIBTEX]
    @inproceedings{arulraj16,
      author = {Arulraj, Joy and Pavlo, Andrew and Menon, Prashanth},
      title = {Bridging the Archipelago Between Row-Stores and Column-Stores for Hybrid Workloads},
      booktitle = {Proceedings of the 2016 International Conference on Management of Data},
      series = {SIGMOD '16},
      year = {2016},
      pages = {583--598},
      numpages = {16},
      doi = {10.1145/2882903.2915231},
      url = {http://db.cs.cmu.edu/papers/2016/arulraj-sigmod2016.pdf},
     }
  • J. Arulraj, M. Perron, and A. Pavlo, "Write-Behind Logging," Proc. VLDB Endow., vol. 10, pp. 337-348, 2016. [PDF] [BIBTEX]
    @article{arulraj16-vldb,
      author = {Arulraj, Joy and Perron, Matthew and Pavlo, Andrew},
      title = {Write-Behind Logging},
      journal = {Proc. VLDB Endow.},
      volume = {10},
      issue = {4},
      month = {December},
      year = {2016},
      pages = {337--348},
      publisher = {VLDB Endowment},
      url = {http://db.cs.cmu.edu/papers/2016/p337-arulraj.pdf},
     }
  • P. Bailis, C. Fournier, J. Arulraj, and A. Pavlo, "Research for Practice: Distributed Consensus and Implications of NVM on Database Management Systems," Commun. ACM, vol. 59, iss. 11, pp. 52-55, 2016. [PDF] [BIBTEX]
    @article{bailis16,
      author = {Bailis, Peter and Fournier, Camille and Arulraj, Joy and Pavlo, Andrew},
      title = {Research for Practice: Distributed Consensus and Implications of NVM on Database Management Systems},
      journal = {Commun. ACM},
      issue_date = {November 2016},
      volume = {59},
      number = {11},
      month = oct, year = {2016},
      issn = {0001-0782},
      pages = {52--55},
      numpages = {4},
      url = {http://db.cs.cmu.edu/papers/2016/cacm-nvm2016.pdf},
      doi = {10.1145/2949033},
     }
  • J. Arulraj, A. Pavlo, and S. R. Dulloor, "Let's Talk About Storage \& Recovery Methods for Non-Volatile Memory Database Systems," in Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data, 2015, pp. 707-722. [PDF] [BIBTEX]
    @inproceedings{arulraj15,
      author = {Arulraj, Joy and Pavlo, Andrew and Dulloor, Subramanya R.},
      title = {Let's Talk About Storage \& Recovery Methods for Non-Volatile Memory Database Systems},
      booktitle = {Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data},
      series = {SIGMOD '15},
      year = {2015},
      pages = {707--722},
      url = {http://db.cs.cmu.edu/papers/2015/p707-arulraj.pdf},
     }
  • A. Pavlo, "Emerging Hardware Trends in Large-Scale Transaction Processing," IEEE Internet Computing, vol. 19, iss. 3, pp. 68-71, 2015. [PDF] [BIBTEX]
    @article{pavlo15,
      author = {Andrew Pavlo},
      title = {Emerging Hardware Trends in Large-Scale Transaction Processing},
      journal = {IEEE Internet Computing},
      volume = {19},
      number = {3},
      month = {May/June},
      year = {2015},
      pages = {68--71},
      url = {http://www.cs.cmu.edu/~pavlo/static/papers/IC_20150501_May_2015.pdf},
     }
  • J. DeBrabant, J. Arulraj, A. Pavlo, M. Stonebraker, S. Zdonik, and S. Dulloor, "A Prolegomenon on OLTP Database Systems for Non-Volatile Memory," in ADMS@VLDB, 2014, pp. 57-63. [PDF] [BIBTEX]
    @inproceedings{debrabant14,
      author = {DeBrabant, Justin and Arulraj, Joy and Pavlo, Andrew and Stonebraker, Michael and Zdonik, Stan and Dulloor, Subramanya},
      title = {A Prolegomenon on OLTP Database Systems for Non-Volatile Memory},
      booktitle = {ADMS@VLDB},
      pages = {57--63},
      year = {2014},
      url = {http://hstore.cs.brown.edu/papers/hstore-nvm.pdf},
     }
Visit Project Homepage