COMP7305A - Cluster and cloud computing

Semester 2, 2017-18

Instructor
Professor C.L. Wang
Teaching assistants
Mr. Xin Yao
Ms. Zhaorui Zhang
Syllabus This course offers an overview of current cluster and cloud technologies, and discusses various issues in the design and implementation of cluster and cloud systems. Topics include cluster architecture, cluster middleware, and virtualization techniques (e.g., Xen, KVM) used in modern data centers. We will discuss three types of Cloud computing platforms, including SaaS, PaaS, and IaaS, by providing motivating examples from companies such as Google, Amazon, and Microsoft; and introduce Hadoop MapReduce and Spark programming paradigms for large-scale data analysis.
Introduction by Instructor

This course provides an introduction into the technologies behind cloud computing. A combination of lectures and hands-on programming assignment and term project expose the student to the leading cloud computing paradigms (e.g., Amazon EC2, Hadoop MapReduce, Spark). The lecture part will provide an overview of the underlying clustering technologies that make cloud computing possible (e.g., cluster networking, virtual machines). The students will complete a simple assignment using Amazon EC2 individually and a term project performed in groups of 3-4 students. In the term project, the students will build a private Cloud on a PC cluster with at least 3 machines and participate in the design, assembling, configuring, and benchmarking of the private cloud system. The software stack will include Linux, Xen, Ganglia, and Hadoop. Each group is required to do a live demo and a 5-minute presentation at the end of the semester.

Special Note: The maximum class size is limited to 70 students due to the limited resources.

Learning Outcomes
Course Learning Outcomes Relevant Programme Learning Outcome
CLO1. Able to master the key technologies about the Cluster and Cloud Computing, and be able to contrast similar technologies. PLO.4, 5, 6, 7, 8, 9, 10, 11, 12, 14, 15, 16
CLO2. Able to self-learn the latest Cloud Computing technologies and build their own Cloud system on a PC cluster. PLO.3, 6, 7, 8, 9, 10, 11, 12
View Programme Learning Outcomes
Pre-requisites The students are expected to exercise the systems configuration and administration under a Linux cluster. Basic understanding of Linux operating system and some experiences in system level programming (C/C++ or Java) are required.
Compatibility Students who have taken " ICOM6041 An introduction to cloud computing" should not be allowed to take COMP7305.
Topics covered
Course Content No. of Hours Course Learning Outcomes
1. From Cluster to Cloud 3 CLO1
2. Introduction of Cloud Computing (SaaS, PaaS, and IaaS) 3 CLO1
3. Amazon EC2/S3 (workshop) 3 CLO1 & COL2
4. MapReduce and Hadoop 3 CLO1
5. Virtual Machines and CPU Virtualization 3 CLO1
6. Xen and Hadoop Installation (workshop) 3 CLO1 & COL2
7. Memory and Network Virtualization Techniques 3 CLO1
8. Cluster Networking (ARP, DHCP, NAT) 3 CLO1
9. Apache Big Data Stack (Spark) 3 CLO1
10. Data Center Networking: Software Defined Network 3 CLO1
 
Assessment
Description Type Weighting * Examination Period ^ Course Learning Outcomes
Port a simple Java application on a public Cloud (Amazon EC2) Continuous Assessment 15% - CLO2
Build a real Cloud system using Xen and Hadoop on a PC cluster and develop applications using MapReduce programming model. Continuous Assessment 35% - CLO2
Written exam covers all taught content in the course.
Written Examination 50% May 7 to 26, 2018 CLO1
* The weighting of coursework and examination marks is subject to approval
^ The exact examination date uses to be released when all enrolments are confirmed after add/drop period by the Examinations Office.  Students must oblige to the examination schedule. Students should NOT enrol in the course if they are not certain that they will be in Hong Kong during the examination period.  Absent from examination may result in failure in the course. There is no supplementary examination for all MSc curriculums in the Faculty of Engineering.

For reference:

Course materials Recommended readings:
  • Distributed and Cloud Computing: From Parallel Processing to the Internet of Things, by Kai Hwang, Jack Dongarra & Geoffrey C. Fox, Morgan Kaufmann
Session dates
Date Time Venue Remark
Session 1 17 Jan 2018 (Wed) 2:30pm - 5:30pm CPD-LG34  
Session 2 24 Jan 2018 (Wed) 2:30pm - 5:30pm CPD-LG34  
Session 3 31 Jan 2018 (Wed) 2:30pm - 5:30pm CPD-LG34  
Session 4 7 Feb 2018 (Wed) 2:30pm - 5:30pm CPD-LG34  
Session 5 28 Feb 2018 (Wed) 2:30pm - 5:30pm CPD-LG34  
Session 6 14 Mar 2018 (Wed) 2:30pm - 5:30pm CPD-LG34  
Session 7 21 Mar 2018 (Wed) 2:30pm - 5:30pm CPD-LG34  
Session 8 28 Mar 2018 (Wed) 2:30pm - 5:30pm CPD-LG34  
Session 9 4 Apr 2018 (Wed) 2:30pm - 5:30pm CPD-LG34  
Session 10 11 Apr 2018 (Wed) 2:30pm - 5:30pm CPD-LG34  
CPD - Central Podium Levels (Centennial Campus)
Add/drop 15 January, 2018 - 28 January, 2018
Quota 70
Back