h1

% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@MASTERSTHESIS{Brckner:955544,
      author       = {Brückner, Moritz},
      othercontributors = {Müller, Matthias S. and Geisler, Sandra and Liem, Radita
                          Tapaning Hesti},
      title        = {{P}erformance analysis using {POP} methodology in spark big
                      data applications},
      school       = {RWTH Aachen University},
      type         = {Bachelorarbeit},
      address      = {Aachen},
      publisher    = {RWTH Aachen University},
      reportid     = {RWTH-2023-03557},
      pages        = {1 Online-Ressource : Illustrationen, Diagramme},
      year         = {2023},
      note         = {Veröffentlicht auf dem Publikationsserver der RWTH Aachen
                      University; Bachelorarbeit, RWTH Aachen University, 2023},
      abstract     = {Today’s software applications need to cope with ever
                      increasing amounts of data while processing the data in a
                      reasonable amount of time with limited resources.
                      Specialized frameworks such as Apache Hadoop or Apache Spark
                      are often used to meet those requirements, making it
                      possible to run an application in a distributed and parallel
                      manner on multiple compute nodes in a cluster network. A
                      common issue with these frameworks is that both the
                      configuration of an applications as well as the kind of
                      application and the structure of its data are strongly
                      influencing the application’s performance. In addition to
                      that, there seems to be a current trend of convergence of
                      the originally largely independent disciplines of
                      high-performance computing (HPC) and big data, whose
                      applications increasingly overlap. As a result, the
                      application of Apache Spark on HPC systems is gaining
                      relevance and, consequently, also the study of performance
                      of Spark applications on these systems. In this thesis, the
                      POP methodology, originally developed for analyzing the
                      performance of HPC applications, is applied to Spark big
                      data applications. The core principle of the methodology is
                      to assign a score to individual performance-influencing
                      aspects, which can be used to obtain a comprehensive and
                      direct overview of potential performance bottlenecks of an
                      application. The aim of this thesis is to evaluate selected
                      Spark benchmarks from the HiBench benchmark suite and to use
                      the obtained results to derive POP metrics for Spark
                      applications. Beyond the POP metrics that are used in the
                      HPC context, additional Spark-specific metrics are proposed
                      in order to significantly extend the range of identifiable
                      problems and to allow for a more precise determination of
                      these problems. This thesis comes to the conclusion that, in
                      principle, the POP methodology can be successfully applied
                      to Spark applications, although in some cases certain
                      limitations or assumptions are necessary. Even though it is
                      not possible to verify the correctness and completeness of
                      the proposed metrics beyond any doubt by means of the
                      conducted experiments, the methodology presented in this
                      thesis seems to be suitable for identifying a large number
                      of different performance problems. Yet, further
                      investigations are required in order to eliminate some of
                      the limitations and assumptions made, and to improve and
                      validate both individual metrics as well as the methodology
                      as a whole.},
      cin          = {123010 / 022000 / 120000},
      ddc          = {004},
      cid          = {$I:(DE-82)123010_20140620$ / $I:(DE-82)022000_20140101$ /
                      $I:(DE-82)120000_20140620$},
      typ          = {PUB:(DE-HGF)2},
      doi          = {10.18154/RWTH-2023-03557},
      url          = {https://publications.rwth-aachen.de/record/955544},
}