CSE 710

Parallel and Distributed File Systems

Spring 2016

 

 

Instructor:

 

Prof. Tevfik Kosar

Office: 338J Davis Hall

Phone: 645-2323

Email: tkosar@buffalo.edu

Office hours: Tue 10:00am - 12:00pm

 

Course Description:

 

As the data requirements of commercial as well as scientific applications continue to increase, the ability to share large amounts of data across widely distributed sites (i.e. data centers, clouds, clusters, supercomputers) becomes more and more important.

 

This seminar will be discussing state-of-the-art research, development, and deployment efforts in parallel and distributed file systems on clustered, grid, and cloud infrastructures. We will be reading and discussing two papers every week in one of the following areas:

 

·      File System Design Decisions

·      Performance, Scalability, and Consistency issues in File Systems

·      Traditional Distributed File Systems

·      Parallel Cluster File Systems

·      Wide Area Distributed File Systems

·      Cloud File Systems

·      Commercial vs Open Source File System Solutions

 

Course Location and Time:

 

The seminars will be held Wednesdays 10:00am-12:00pm @ 113A Davis Hall. First day of classes will be on Wednesday, January 27th, 2016.

 

Reading List:

 

The "tentative" reading list for this seminar is available here.

 

Projects:

 

The seminar will include a "term project" on comprehensive testing and evaluation of selected parallel and distributed file systems, which will be performned and presented in teams. Project descriptions are available here.

Project Milestones are:

Mar 7th: System Design Document & Literature Survey due
Mar 9th: Midterm Presentations
Apr 25th - May 4th: Final Presentations and Demos
May 14th: Final Reports due

 

Grading:

 

This is a research course. There will be team projects and paper presentations, but no exams. Each student will present at least 1 paper from the reading list provided above. Additionally, each student is expected to read all papers, submit questions and comments about the papers, attend classes, and join the discussion of the papers. Grading will be P/F.

 

Useful Links:

 

·      How to Read a Paper, by S. Keshav.

·      Reviewing a Technical Paper, by M. Ernst

 

Piazza Page:

 

    We will also have an online discussion of the papers at the course piazza page. The details about this will be posted here soon.

 

 

Seminar Schedule:


Date

Week

Papers to be Discussed

Presenter

Jan. 27

1

Introduction: Wide Area Distributed File Systems

Tevfik

Feb. 3

2

The Sun Network File System: Design, Implementation and Experience (NFS)

Aniruddh

Scale and Performance in a Distributed File System (AFS)

Abinash

Feb. 10

3

Disconnected Operation in the Coda File System

Barry

Serverless Network File Systems (xFS)

Balamurugan

Feb. 17

4

PVFS: A Parallel File System for Linux Clusters

Miraj

Lustre: A Scalable, High-Performance File System

Abinash

Feb. 24

5

GPFS: A Shared-Disk File System for Large Computing Clusters

Srikanth

Panache: A Parallel File System Cache for Global File Access

Krishna

Mar. 2

6

Energy-Efficiency and Storage Flexibility in the Blue File System

Mingxuan

Evaluation and Analysis of GreenHDFS

Janani

Mar. 9

7

Mid-semester Project Presentations

Teams 1 - 5

Mar. 16

SPRING BREAK

 

Mar. 23

8

OceanStore: An Architecture for Global-Scale Persistent Storage

Yuan

Shark: Scaling File Servers via Cooperative Caching

Li

Ivy: A Read/Write Peer-to-Peer File System

Mingxuan

Mar. 30

9

The Google File System

Barry

Ceph: A Scalable, High-Performance Distributed File System

Srikanth

Apr. 6

10

Distributed Directory Service in the Farsite File System

Krishna

Flexible, Wide-Area Storage for Distributed Systems with WheelFS

Balamurugan

Apr. 13

11

BlueSky: A Cloud-Backed File System for the Enterprise

Li

Replication, History, and Grafting in the Ori File System

Janani

Apr. 20

12

ViewBox: Integrating Local File Systems with Cloud Storage Services,

Aniruddh

SCFS: A Shared Cloud-backed File System

Yuan

CalvinFS: A Scalable File System Built on Top of a Distributed DBMS

Miraj

Apr. 25

13

Final Project Presentations & Demos (in room Davis 310)

Teams 1 - 2

May. 4

14

Final Project Presentations & Demos (in room Davis 113A)

Teams 3 - 5