NASD, GoogleFS, Farsite

From Soma-notes
Revision as of 15:53, 10 March 2008 by Emmellst (talk | contribs)
Jump to navigation Jump to search

Readings

Garth A. Gibson et al., "A Cost-Effective, High-Bandwidth Storage Architecture" (1998)

Sanjay Ghemawat et al., "The Google File System" (2003)

Atul Adya et al.,"FARSITE: Federated, Available, and Reliable Storage for an Incompletely Trusted Environment" (2002)

William J. Bolosky et al., "The Farsite Project: A Retrospective" (2007)

Questions

  1. What were the target environments for these filesystems? How did these environments shape their assumptions?
  2. What are the key ideas behind each filesystem?
  3. What are the strengths and weaknesses of each design?
  4. What are the strengths and weaknesses of each implementation?
  5. Which system is best suited for today's Internet? How about tomorrow's?

Questions for GoogleFS

  1. How does the Google file system implement security?
  2. Is using a central server (point of access) a good design decision?
  3. Is removing random writes a good idea?
  4. Is the speedup attained by GFS's record-append method worth the sacrifice of Application overhead?

Questions for Farsite

  1. Byzantine fault tolerance?
  2. How similar and different compared to OceanStore?

Questions for Farsite retrospective

  1. If using different programming methods... how does this file-system work given different programming models
  2. Details of buyzantine fault tolerance