Lifetime-Based Memory Management for Distributed Data Processing Systems

Lu Lu, Xuanhua Shi, Yongluan Zhou, Xiong Zhang, Hai Jin, Cheng Pei, Ligang He, Yuanzhen Geng

    Research output: Chapter in Book/Report/Conference proceedingConference abstract in proceedingsResearchpeer-review

    179 Downloads (Pure)


    In-memory caching of intermediate data and eager combining of data in shuffle buffers have been shown to be very effective in minimizing the re-computation and I/O cost in distributed data processing systems like Spark and Flink. However, it has also been widely reported that these techniques would create a large amount of long-living data objects in the heap, which may quickly saturate the garbage collector, especially when handling a large dataset, and hence would limit the scalability of the system. To eliminate this problem, we propose a lifetime-based memory management framework, which, by automatically analyzing the user-defined functions and data types, obtains the expected lifetime of the data objects, and then allocates and releases memory space accordingly to minimize the garbage collection overhead. In particular, we present Deca, a concrete implementation of our proposal on top of Spark, which transparently decomposes and groups objects with similar lifetimes into byte arrays and releases their space altogether when their lifetimes come to an end. An extensive experimental study using both synthetic and real datasets shows that, in comparing to Spark, Deca is able to 1) reduce the garbage collection time by up to 99.9%, 2) to achieve up to 22.7x speed up in terms of execution time in cases without data spilling and 41.6x speedup in cases with data spilling, and 3) to consume up to 46.6% less memory.
    Original languageEnglish
    Title of host publicationProceedings of the VLDB Endowment
    EditorsSurajit Chaudhuri, Jayant Haritsa
    Publication date5. Feb 2016
    Publication statusPublished - 5. Feb 2016
    Event42nd International Conference On Very Large Data Bases - New Delhi, India
    Duration: 5. Sep 20169. Sep 2016
    Conference number: 42


    Conference42nd International Conference On Very Large Data Bases
    CityNew Delhi
    SeriesProceedings of the VLDB Endowment


    Dive into the research topics of 'Lifetime-Based Memory Management for Distributed Data Processing Systems'. Together they form a unique fingerprint.

    Cite this