You are here: silicon.com > Resources > White Papers > Networking and Communications > Network Management > Scalability

Scalability White Papers

Peta-Scale I/O With the Lustre File System

Tags:
scalability

Overview This paper describes low-level infrastructure in the Lustre file system that addresses scalability in very large clusters. The features described deal with I/O and networking, lock management, recovery after failure, and other scalability-related issues. The Lustre file system first went into production in Spring 2003 on the Multiprogrammatic Capability Resource (MCR) cluster at Lawrence Livermore National Laboratory (LLNL). The MCR cluster was one of the largest clusters at that time with 1100 Linux compute nodes as Lustre clients. Since then, the Lustre file system has been deployed on larger systems, notably the Sandia Red Storm deployment, with approximately 25,000 liblustre clients, and the Oak Ridge National Laboratory (ORNL) Jaguar system, which is of similar scale and runs Lustre technology both with Client-Node Linux (CNL) and with Catamount.

Further White Paper Details
Publisher	Sun Microsystems	File Format	PDF
Date Published	February 2008	Downloads	1
Format	White Papers
Topics	Scalability, File and Network Servers

Did you find this white paper useful? 7 out of 10 users found this white paper useful

Novell finally rolls-out Netware clustering

The software will support clusters of eight four-processor servers, scaling to 32 servers, Novell officials claim. It has been tested on up to 12 clusters. Servers using NetWare Cluster Services are connected with Fast Ethernet adaptors as well as...

Channel:
Desktops

The Bloor Perspective: NT clusters, open source in healthcare and Bezos' brand new dilemma

Bringing the technology to NT allows users to configure NT clusters of up to 32 nodes and to manage up to 256 clusters from a single workstation. In order to provide scalability from commodity-class servers it is necessary to deploy a large number...

Channel:
Comment & Analysis

IBM to sell supercomputing server

That was the case for the p5-575's star customer, Lawrence Livermore National Laboratory's ASC Purple, a supercomputer for predicting whether nuclear weapons will continue to work as they age. A single node, including AIX, 16GB of memory and a year...

Criminal IT: What you can do to help the fight against cybercrime

The modified timestamp records the last time at which any data is copied into the clusters which form the file. It records the time at which the picture has been completely copied down from the internet, as the last cluster of the JPEG is finally...

Microsoft dishes up test version of new file system

Microsoft surprised developers on Monday by releasing a test version of a new Windows file system. The software giant had originally planned to release WinFS - which it said would make for better desktop file searching - as part of the next version...

Torvalds issues new Linux kernel

This software governs how a single pool of data is shared by a group of servers, a crucial element of Oracle efforts to make clusters of low-end computers a viable database alternative to expensive multiprocessor servers.

Live Webcast: Telecoms 2.0 - Where is telecoms heading?

In this webcast, our panel of experts will review where we are with next generation telecoms in the UK, working through the concept of 'Telecoms 2.0': - Realising the potential of Next Generation Networks - why it isn't just about the technology? - What attributes should firms be looking for in their telco partner? - Is the relationship between telco provider and customer changing? - What things need to happen to make next generation services a reality? - You say you want the supplier to change. Do you want to change too? - What is Telecoms 2.0?

Publisher:
ZDNet UK

Telecom 2.0: Mind over matter

ntl:Telewest Business believes that the role of the telco is evolving. Gone are the days when it was enough to simply focus on circuits and minutes, customers now need a far higher degree of interaction and look for suppliers who will talk business solutions with them.

Publisher:
ntl:Telewest Business

IBM Information Server Change Data Capture

In today's fast-paced world, access to real-time data has never been more important. To be successful, organizations need to be able to report and analyze corporate data quickly and easily, regardless of what applications created the data, what platform they're running on, or what database they're stored in.

Publisher:
IBM

An examination of server consolidation: the trends that can drive efficiencies and help businesses gain a competitive edge

This white paper provides a starting point for organizations contemplating server consolidation. It includes an overview of server consolidation concepts and techniques and provides guidance on methodologies. It also looks at the potential cost savings associated with server consolidation and offers information on how organizations can sustain the advantage they have gained by consolidating their servers.

Publisher:
IBM

Also on silicon.com

Site Navigation:

Scalability White Papers

Peta-Scale I/O With the Lustre File System

Quick Sitemap Links:

About Us

Search

Blogs

Verticals

Advertising Features

CNET Networks in Europe

CNET Networks in the United States

CNET Networks in Asia Pacific