File Systems and File Management

Jump straight to an abstract:

The Abstracts

The File Systems Evolution
Christian Bandulet

File Systems impose structure on the address space of one or more physical or virtual devices.  Starting with local file systems over time additional file systems appeared focusing on specialized requirements such as data sharing, remote file access, distributed file access, parallel files access, HPC, archiving, security etc.. Due to the dramatic growth of unstructured data files as the basic units for data containers are morphing into file objects providing more semantics and feature-rich capabilities for content processing.    This presentation will categorize and explain the basic principles of currently available file systems (e.g. local FS, shared FS, SAN FS, clustered FS, network FS, WAFS, distributed FS, parallel FS, object FS...). It will also explain technologies like NAS aggregation, NAS clustering, scalable NFS, global namespace, parallel NFS, storage grids and cloud storage.     All of these files system categories are complementary. They will be enhanced in parallel with additional value added functionality. New file system architectures will be developed and some of them will be blended in the future.

  • Learning Objectives
  • Understand the basic principles of different files system architectures
  • Understand how file systems evolved over time
  • Being prepared to discuss, position and recommend the most appropriate file system for a customer solution

Find and Select the Right File Storage for Your Application
Philippe Nicolas

Many businesses are linked to file storage technologies as many of these new, recent and even existing applications morph now, rely and support file based data. At the same time, the volume of data explodes especially the file data type which now represents by far the larger portion of enterprise data. With the complexity and variety of market solutions, the challenge for IT buyers and storage managers is to choose and adopt the most adapted solutions aligned to their business and IT needs to address their current and future challenges with a special attention to compliance and data retention regulations, Backup and Archiving, ILM and Tiering. This session covers the most common deployed applications, their attributes in term of file storage needs and maps these to file storage solutions available in the industry with technologies details and advantages. Among the various technologies presented in this session are: Clustered, SAN-based, Distributed, Parallel File Storage and the very last approach is Cloud Storage.

Learning Objectives

  • With a top-down approach, this tutorial improves file storage technologies positioning and understanding aligned to applications needs and challenges.
  • With that survey, technologies segmentation and features matrix, it helps end-users, IT and file storage buyers to select, choose and adopt the right solution.

Panel Discussion:  pNFS - Parallel Storage for Grid and Enterprise Computing
Moderator:  Joshua Konkle
Panelists: David Black, Ken Gibson, Brent Welch, Mark Carlson


This is a complimentary panel to the presentation on pNFS, Parallel Storage for Grid and Enterprise Computing.  In this panel you'll have an opportunity to ask detailed questions about technology.

Learning Objectives

  • Understand pNFS storage layouts in more detail
  • Understand product portfolios of different companies
  • Understand status of pNFS clients

DFS for Not-So-Dummies
Mattew Geddes

DFS is a useful, but often misunderstood or misconfigured piece of technology and has proven to cause some confusion when it comes time to diagnose problems surrounding a DFS namespace. This tutorial is for administrators with existing DFS installations that want to know more or administrators who are considering implementing DFS and wish to know more about what is in store for them. In addition to covering the basics, we'll also delve into essential parts of the protocols to provide a solid foundation for rolling out and supporting a DFS installation.

Learning Objectives

  • A solid understanding of DFS from a high-level point of view
  • An understanding of the important and relevant exchanges in the DFS protocol
  • Some generic use cases for DFS

Exploiting Multi-Tier File Storage Effectively
Paul Massiglia

In the past 12 months, a wave of solid state disk introductions has made storage   administrator life more interesting. There is now literally a 10-15x cost   differential in enterprise storage technologies, and a greater than 100x   performance differential. It has become all the more critical to place the right   files on the right storage media.  This tutorial will survey the various technologies available for file placement and   relocation for best effect in a multi-tier storage environment. It will compare   HSM, multi-tier file systems, FAN switches and front ends, and manual file   placement techniques in terms of efficacy and effort, and contrast them with block   level storage tiering strategies.  The tutorial should be of interest to storage administrators and others concerned  with optimizing online data storage cost and quality of service.

Learning Objectives

  • Appreciate the cost and QoS value of a multi-tier online storage strategy
  • Understand the techniques available for managing files across storage tiers
  • Understand the difference between managing file locations and data block locations

Using Classification to Manage File Servers
Nir Ben-Zvi

As data growth is exploding, IT departments are struggling to manage the increasing amounts of files stored on their file servers. Traditionally, data management application use a directory based approach to manage file servers. This session introduces the concept and opportunities for using classification to manage file servers.  The guiding concept is that an organization can classify files on file servers and then apply data management policies based on this classification.  Given the right file server infrastructure, IT administrators should be able to use in-house tools or available classification products to apply classification to files on their file servers and data management applications such as backup or HSM application can then apply policy based on this classification

Learning Objectives

  • IT - Deploying file server classification based solutions in my organization
  • ISVs - Integration opportunities for classification solution partners and data management solution partners

Massively Scalable File Storage
Philippe Nicolas

With the fast evolution of the Internet, the explosion of data volume and growing online services, massively scalable file storage is a reality today. We all use P2P applications which finally use workstation private storage space to enable an almost infinite space. Compliance and Archiving put also a high pressure on file storage and many solutions use innovative approaches developed recently, some research work was done around RAIN architecture. High Performance applications must run and use high performance file storage infrastructure and many proprietary developments were made to address these needs. Some standard work was also done by many vendors to propose some new parallel mode such as pNFS. This session covers only the high-end part of network file storage with high performance, reliability and huge capacity and presents P2P, CAS, Distributed, Parallel and Cloud file storage with important number of servers and clients such as Google FS, Apache project named Hadoop, PVFS, Lustre, pNFS and a few proprietary ones to illustrate industry answers.

Learning Objectives

  • Introduces and review all high-end network file storage technologies to help better understand vendors’ solutions and standards challenges.
  • Help understand each design, advantages and drawback to align with applications needs.
  • Participate to the education of the market to simplify technology adoption.