The outline will be updated over weeks. Please check out the readings one week before the date.
| Lecture | Date | Topics | Papers | Notes/Resources |
|---|---|---|---|---|
| 1 | 09/02 | Class Overview | ||
| 2 | 09/09 | Introduction | How to read a paper (CCR'07) | |
| 3 | 09/16 | Cloud Computing |
Cloud Computing and Grid Computing 360-Degree
Compared (GCE'08) Above the Clouds: A Berkeley View of Cloud Computing (TechRep'09) CloudCmp: Comparing Public Cloud Providers (IMC'10) The Cost of a Cloud: Research Problems in Data Center Networks (CCR'08) |
|
| 4 | 09/23 | Pricing and Resource Management |
How to Bid the Cloud (SIGCOMM'15) A PTAS Mechanism for Provisioning and Allocation of Heterogeneous Cloud Resources (TPDS'15) A Two-Sided Market Mechanism for Trading Big Data Computing Commodities (Big Data'14) Project Discussion |
|
| 5 | 09/30 | Cloud Federations | Dynamically Scaling Applications in the Cloud (CCR'11) Cloud Federations in the Sky: Formation Game and Mechanism (TCC'15) A Framework for Data Protection in Cloud Federations (ICPP'14) A Reputation-Based Mechanism for Dynamic Virtual Organization Formation in Grids (ICPP'12) | |
| 6 | 10/07 | MapReduce |
MapReduce: Simplified Data Processing on Large
Clusters (OSDI'04) Improving MapReduce Performance in Heterogeneous Environments (OSDI'08) MapReduce and parallel DBMSs: friends or foes? (CACM'10) Project Discussion |
Project Proposal Due |
| 7 | 10/14 | Parallel Processing | Dryad: Distributed Data-Parallel Programs from
Sequential Building Blocks (SIGOPS'07) Spark: Cluster Computing with Working Sets (HotCloud'10) Naiad: A Timely Dataflow System (SOSP'13) An introduction to Docker for reproducible research (SIGOPS'15) |
|
| 8 | 10/21 | Resource Management | Mesos: A Platform for Fine-Grained Resource
Sharing in the Data Center (NSDI'11) Apache Hadoop YARN: Yet Another Resource Negotiator (SoCC'13) Project Discussion |
|
| 9 | 10/28 | Scheduling |
Dominant Resource Fairness: Fair Allocation of
Multiple Resource Types (NSDI'11) Large-scale cluster management at Google with Borg (EuroSys'15) Omega: flexible, scalable schedulers for large compute clusters (EuroSys'13) Hopper: Decentralized Speculation-aware Cluster Scheduling at Scale (SIGCOMM'15) |
|
| 10 | 11/04 | INFORMS | No Class | |
| 11 | 11/11 | Energy |
Energy-aware Scheduling of MapReduce Jobs for Big
Data Applications (TPDS'15) Evaluation and Analysis of GreenHDFS: A Self-Adaptive, Energy-Conserving Variant of the Hadoop Distributed File System (CloudCom'10) Towards Energy Efficiency in Heterogeneous Hadoop Clusters by Adaptive Task Assignment (ICDCS'15) Project Discussion |
|
| 12 | 11/18 | BigData | The Google File System (SIGOPS'03) Bigtable: A distributed storage system for structured data (TOCS'08) Managing Data Transfers in Computer Clusters with Orchestra (SIGCOMM'11) Low Latency Geo-distributed Data Analytics (SIGCOMM'15) |
|
| - | 11/25 | Thanksgiving Break | No Class | |
| 13 | 12/02 | Final Project Presentations | ||
| 14 | 12/09 | Final Project Presentations | Project Paper Due |
Final paper template