CSE 710

Wide Area Distributed File Systems

Spring 2013

 

 

Instructor:

 

Prof. Tevfik Kosar

Office: 338J Davis Hall

Phone: 645-2323

Email: tkosar@buffalo.edu

Office hours: Tuesdays 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 wide-area 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 16th, 2013.

 

Reading List:

 

The reading list for this seminar is available here.

 

Projects:

 

The seminar will include a "term project" on the implementation of the core wide-area distributed file system components, which will be implemented and presented in teams. Some project ideas include:

Project-1: MDS: Distributed Metadata Server for Global Name Space in a WAFS
      + WADS_coders (Nikhil, Sharath, Shijith) [Design doc]
      + Team7 (Varun, Kshitijkumar) [Design doc]
Project-2: SmartFS: Serverless Distributed File System for Smartphones
      + BeyondPetaByte (Vijay, Mithun, Sonali) [Design doc]
      + Team DNS (Dev, Nitesh, Sameer) [Design doc]
Project-3: DLS: Cloud-hosted Directory Listing Service for Lightweight Clients
      + Aryans (Deeshen, Malay, Yogesh) [Design doc]
Project-4: WideFS: Fuse-based POSIX Wide-area File System for GridFTP Servers
      + DYADS (Adarsh, Aditya, Sharath) [Design doc]
      + 710Group (Huiqiong, Fengwei) [Design doc]
Detailed project descriptions are available here.

Project Milestones are:

Feb 08th: Survey of Related Work
Feb 22nd: System Design Document
Mar 06th: Midterm Presentations
Apr 05th: Implementation Status Report
Apr 17th: Final Presentations and Demos
May 09th: Final Reports

 

Grading:

 

This is a research course. There will be team projects and paper presentations, but no exams. Each student will present 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

 

Course Blog:

 

    All paper abstracts and links will be posted on the course blog at http://cse710.blogspot.com/. Please make sure you visit this blog regularly, and do not forget to post your questions and comments on papers to be discussed every Tuesday by Midnight.

 

 

Seminar Schedule:

 

   

Date

Week

Papers to be Discussed

Presenter

Jan. 16

1

Introduction: Wide Area Distributed File Systems

Tevfik

Jan. 23

2

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

Dev Ashis

[2] Scale and Performance in a Distributed File System (AFS)

Vijay

Jan. 30

3

[3] Disconnected Operation in the Coda File System

Fengwei

[4] Serverless Network File Systems (xFS)

Kshitijkumar

Feb. 6

4

[5] PVFS: A Parallel File System for Linux Clusters

Aditya

[6] Lustre: A Scalable, High-Performance File System

Malay

Feb. 13

5

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

Deeshen

[8] Scalable Performance of the Panasas Parallel File System

Nikhil

Feb. 20

6

[9] Nache: Design and Implementation of a Caching Proxy for NFSv4

Mithun

[10] Panache: A Parallel File System Cache for Global File Access

Huiqiong

Mar. 6

7

[11] OceanStore: An Architecture for Global-Scale Persistent Storage

Yogesh

[12] Shark: Scaling File Servers via Cooperative Caching

Nitesh

Mar. 13

 

 

Mar. 20

8

Midterm Project Presentations

Teams 1 – 4

Midterm Project Presentations

Teams 5 – 8

Mar. 27

9

[13] Ivy: A Read/Write Peer-to-Peer File System

Adarsh

[14] zFS – A Scalable Distributed File System Using Object Disks

Varun

Apr. 3

10

[15] The Google File System

Shijith

[16] The Hadoop Distributed File System

Sharath

Apr. 10

11

[17] Ceph: A Scalable, High-Performance Distributed File System

Sharath Pandiri

[18] Distributed Directory Service in the Farsite File System

Sameer

[19] BlueSky: A Cloud-Backed File System for the Enterprise

Sonali

 

Apr. 17

13

Final Project Presentations & Demos

Teams 1 - 4

Final Project Presentations & Demos

Teams 5 - 8

Apr. 24

14

Wrap-up

Wrap-up