Supercomputing '08 BoF

pNFS Protocol after Final Draft and before RFC

Session Leader: Sorin Faibish (EMC)

Wednesday, November 19, 2008
5:30 - 7:00 p.m.
Austin Convention Center, Austin, Texas

PRIMARY SESSION LEADER:
Sorin Faibish (EMC)

SECONDARY SESSION LEADERS:
Garth Gibson (Carnegie Mellon University)
Mike Eisler (NetApp)

ABSTRACT:
pNFS is an extension to NFSv4 that allows clients to overcome NFS scalability and performance barriers. Like NFS, pNFS is a client/server protocol implemented with secure and reliable remote procedure calls. A pNFS server manages storage metadata and responds to client requests for storage layout information. pNFS departs from conventional NFS by allowing clients to access storage directly and in parallel. By separating data and metadata access, pNFS eliminates the server bottlenecks inherent to NAS access methods. By combining parallel I/O with the ubiquitous standard for Internet filing, pNFS insulates storage architects from the risks of deploying best-of-breed technologies, promising state of the art performance, massive scalability, and interoperability across standards-compliant application platforms. pNFS is aproaching the RFC publication and this BoF will try to discuss all the 3 pNFS flavors and their advantages and disadvantages in an effort to accelerate its penetration and invite users to try it.

BoF SPEAKERS - slide deck containing all speakers' materials [PDF - 5.7MB]

  • Sorin Faibish, EMC - EMC and pNFS
  • Roger Haskin, IBM - GPFS and pNFS
  • Ken Gibson, LSI - LSI and Block pNFS
  • Joshua Konkle, NetApp - NetApp and pNFS
  • Brent Welch, Panasas - Accelerating Industry-wide Adoption of
    Parallel Storage Solutions
  • Bill Baker, SUN Microsystems - pNFS