Duke DBGroup Logo

Data-intensive Computing Systems
Written Assignment
Final Report for Project 1

Course information
Course schedule and notes
Extra Materials
Wednesday, November 2 is the tentative date when the final report for for Project 1 is due. On the same day, we will have 15-minute presentations in class from each group.

Please read the detailed instructions very carefully. If you have questions about Project 1 it is for the benefit of everyone to ask them in class.

Each group will be submitting one Final Report with the following structure:
  • Section 1
    Description of workload (for overall group).
  • Section 2
    Description of data used (for overall group).
  • Section 3
    Description of systems considered for evaluation. One subsection of Section 3 will be written per system by the 1-2 group members
    responsible for that system. Also include a single high-level comparison table/chart to point out the similarities and dissimilarities among
    the systems.
  • Section 4
    Description of evaluation methodology (for overall group). This part should include aspects like what performance, ease-of-use, reliability,
    and any other metrics that you are measuring for system evaluation purposes. Why are you
    measuring these metrics specifically? How are you measuring these metrics for each system? Etc.
  • Section 5
    Detailed description of evaluation results observed (for overall group). Plot graphs as much as possible for easy readability. Include your
    explanation for why the results are as they are (especially results that are not as you had expected originally).
  • Appendix 1
    Detailed description of installation and configuration instructions for each system. One subsection of Appendix 1 will be written per system by
    the 1-2 group members responsible for that system.
  • Appendix 2
    Step-by-step instructions to run the workload and collect results for each system (including Hadoop as appropriate). Each of the 1-2 members
    subgroups will write a subsection of Appendix 2 for the system that the subgroup was responsible for.
Automate, Automate, Automate. Once Project 1 is complete, you will be submitting the AMI, source code, and step-by-step instructions to run the workloads (in addition to a project report). Rozemary and I should be able to run your code and replicate all your evaluation results. We will be grading you on the ease with which we were able to run your code and replicate your results.