Wednesday, May 24, 2006

Grid Computing Books: Grid Computing - The Savvy Manager’s Guide

Cross-posted from The Grid Blog

Title: Grid Computing - The Savvy Manager's Guide
Authors: Pawel Plaszczak & Rich Wellner, Jr.
Publisher: Morgan Kaufmann
ISBN: 0127425039
Sample Chapter: N/A
Online Companion: http://www.savvygrid.com/
Review: Taken from the online edition of Primeur
The book starts with some artificial, business cases, explaining how Grid technologies could be useful in business. Then it continues with Grid basics, including notes on the history: Grid computing is not a completely new invention, but builds on a number of developments in the nineties, such as metacomputing and distribtued computing.
The book is meant as a starting point. The reader is presented an overview of some resources for futher investigation, and there is a supporting web site which is kept up to date and with some links per chapter to other sources. However, when reading a book, I prefer the references to be contained in the book: you do not always have Internet at hand and it also disrupts the reading process if you first have to go to a computer to read the reference.
Another review from http://www.agapea.com/Grid-Computing-The-Savvy-Manager-s-Guide-n243334i.htm:
A decade ago, the corporate world viewed grid computing as a curiosity. Today, it views it as an opportunity--a chance to reduce costs, improve performance, fund new projects, and take advantage of under-utilized capacity. The engineering behind this transformation has been amply documented. Until now, however, little has been written to prepare managers, executives, and other decision-makers to implement grid computing in a sensible and effective way.

Grid Computing: The Savvy Manager's Guide examines the technology from a rigorous business perspective, equipping you with the practical knowledge you need to assess your options and determine what grid computing approach is right for your enterprise. This book is heavy on real-world experience, distilling from a rich assortment of case studies the best practices currently at work in a variety of industries. Always attentive to grid computings many competitive advantages, it is also realistic about the challenges of selling the idea to staff and making it a part of your companys culture.
Buy from Amazon: http://www.amazon.com/gp/product/0127425039

Thursday, May 18, 2006

Grid Computing Book: IBM Redbooks - "Patterns: Emerging Patterns for Enterprise Grids"

Cross-posted from The Grid Blog

Title: Patterns: Emerging Patterns for Enterprise Grids
Authors: John Easton, David Kra, Michael Osias, Donald Pazel, Rob Vrablik, David Chisholm, Matthew Haynos, Luiz R. Rocha, Avi Saha, Ellen Stokes, Roberto Jimenez, Richard Appleby, Shweta Gupta, Joachim Dirker, Luis Ferreira, and Jean-Pierre Prost
Publisher: IBM Redbooks
ISBN: N/A
Book Description: http://www.redbooks.ibm.com/abstracts/sg246682.html
Download Link: http://www.redbooks.ibm.com/redpieces/pdfs/sg246682.pdf
Abstract:
The target audience for this redbook are IT architects, consultants, software engineers with a need to use grid computing as a building block to the solution of architectural problems.

In their everyday work, those professionals need to evaluate a business problem and build a solution to solve it. They normally begin by gathering requirements related to the problem, designing a first outline of the solution and taking into consideration any special requirements that must be part of the final solution. After this step, they start the design of the actual solution, which can be comprised of one or more applications, each one requiring its own infrastructure in order to run.
Every time they can reuse the same set of solutions, devised from the experience they have acquired, the next engagement is simplified, reducing time and costs and increasing the levels of client satisfaction. Capturing, categorizing and providing access to the knowledge gained from each engagement into a repository of information can be beneficial to the overall professional community.

Patterns are great vehicles to capture components with a high degree of commonality among engagements and to express their interrelationships. Although most enterprise grid engagements are typically deployed with solutions that could be categorized as "one-of-a-kind", there is enough information gathered today to allow us to devise a set of common components among them and to derive enterprise grid patterns. The proposed patterns are based on grid solutions designed for enterprise clients over the past couple of years and are therefore representative of the current use of grid technologies in the enterprise today. They may not address all emerging grid technologies or be representative of research grids.

You can use this book as a helping guide for your grid solution design and we also expect that your experience and your feedback may be applied in the improvement of this work.

Wednesday, May 17, 2006

Grid Computing Competition from Grid Computing Now!

Cross-posted from The Grid Blog

DTI Knowledge Transfer Network Grid Computing Now! and the British Computer Society have announced a competition for innovative solutions to challenges of the 21st century using the capabilities of grid computing technologies.

See the competition site for details.

The Competition in Outline
The competition is to develop a short description of an application of Grid Computing Technologies to solve a unique problem facing society in the 21st Century. Each submission should provide a short overview of the problem to be solved, an analysis and a description of the potential solution. We believe that the emergence of grid computing provides a new level of capability in high performance distributed computing and thus we would expect the problem addressed to be beyond today’s available solutions, such as cluster computing or other more constrained computing configurations. The competition will be judged by an appointed panel of experts from industry and the fields of science, the environment, engineering, design and arts. Prizes will be awarded for submissions that show the most originality, creativity, clear benefits and a feasible implementation. We expect to be able to offer individuals prizes ranging from computer equipment and software packages as well as an Internship or work placement at Intellect. We will also award membership to the BCS for prize winners. Entrants should be aware that there is a possibility that the competition will attract coverage in the media. The event will be launched early in the spring of 2006 with the aim of accumulating submissions during the summer with a preliminary short list available to be judged in the early autumn. A Competition Final event will be held for the short-listed entrants at which the prizes will be awarded.

Grid Computing Technologies
We are taking a broad view of Grid Computing to encourage a wide range of possible solutions. The key properties of Grid Computing in our view are the virtualising of resources to enable the provision of a more substantial and flexible computing capability to address a problem. There are two basic approaches to Grid Computing relevant in this context. Either a large scale distributed heterogeneous computer system which appears to the user as one large computer or a distributed application which enables the user to obtain a wide deployment of a very large task, broken down into small tasks, which are themselves, distributed across a volunteer computer network. This latter approach is becoming popular in use today, and would not be a particularly innovative approach to solving a problem. To assist entrants without the benefit of an extensive computing background we would recommend the definitions and descriptions offered by the CERN Grid Café. See http://gridcafe.web.cern.ch/gridcafe/ for a primer and explanation.

Competition
There will be three stages to the competition; all submissions will be via the Grid Computing Now! Website www.gridcomputingnow.org , entrants intellectual property rights will be preserved:

* Firstly, an initial competition entry form will be used for submissions of up to 500 words describing the problem and their approach to a solution. The submissions will be reviewed by the organising committee and a selection made to be invited to submit a more complete entry.
* Secondly, those submitting successful proposals from stage 1 (between 30 and 50) will be invited to submit a short written paper, 1000 words, developing their idea further, supported by a short presentation. These submissions will be judged by the appointed panel.
* Thirdly, those proposals judged to be of most interest (a maximum of 10) will be invited to present their proposal in a Competition Final event scheduled for late September. Each competitor will be allocated 20 minutes comprising 10 minutes presentation and 10 minutes questions and answers. Prizes will be awarded on the basis of originality; creativity clear benefits and feasibility.

There will be three prizes awarded:

* 1st Prize: An X-Box 360 with the offer of Microsoft Windows Server 2003 Standard 10 CALs and Microsoft Compute Cluster Server for the prize winner’s employer/university. The winner will also be eligible to attend the Microsoft European Technology Conference held in Brussels and be offered a year’s free membership of the British Computer Society. The winner will also be eligible for an Internship placement with Intellect, the Hi-tech trade association in Summer 2007.
* 2nd Prize: A laptop computer; Opportunity to utilise the eScience National Grid Service for a number of hours to implement a prototype solution. This will be supported by technical advice from the National eScience Centre and National Grid Service teams. A free membership of the British Computer Society for one year.
* 3rd Prize: Office software Microsoft Visual Studio.NET Professional and Microsoft Office Professional and a free membership of the British Computer Society for one year.

All prize winners will have their entries featured in communication materials, on the Grid Computing Now! website and if the opportunity arises, in the press.

Competition Launch Plans and Timeline:

* The Competition will be launched in the 2nd week of May. This will be via the GCN!, Intellect, BCS and NeSC websites and a press release.
* Initial Entries will be accepted until the end of June.
* These entries will be assessed in the first two weeks of July and an initial short-list created of between 30 and 50 entries.
* These entrants will be encouraged to submit by early September and a selection of up to 10 entrants will be invited to appear at the Competition Final event in central London in front of the judges on September 28th at the BCS offices in Southampton Street.

Contact:
competition@gridcomputingnow.org
Competition Website

GGF launches Grid standards wiki

Cross-posted from The Grid Blog.

From Grid Meter:
The SCRM working group within the GGF has launched a Wiki that attempts to corral the work done by the many different organizations that have their fingers in the cake of emerging grid computing standards.

SCRM stands for 'Standards Development Organization Collaboration on Networked Resources Management' which in and of itself is a mouthful. The Wiki is a collection of descriptions with links that leads the user to text on the actual standards and specifications.

Tuesday, May 16, 2006

NMI Release 9 and OGCE Version 2.0 Released

Cross-posted from The Grid Blog

From Grid Today: NSF Releases NMI-R9,
Providing new event diagnostic, privilege management and portal-building tools, the ninth release of the National Science Foundation Middleware Initiative (NMI-R9) makes further progress in addressing the challenge of collaborating online in a shared cyberinfrastructure environment. NMI-R9 is available to the public for downloading under open-source licenses at www.nsf-middleware.org.
New for this release is NMI-EDIT's End-to-END Diagnostic Discovery (EDDY) Toolkit that supports integrated analysis and diagnosis of distributed, layered and interdependent components and systems. "This release offers a critical step towards managing and troubleshooting the complex distributed environments that we're building to support science," said Ken Klingenstein, director of middleware and security at Internet2. "NMI-EDIT's EDDY Toolkit is a diagnostic model intended to encourage discussion and experimentation in this area."

OGCE Version 2.0 provides a complete toolkit for building science-portal gateways. Newly incorporated Sakai collaboration portlets provide access to their tools such as calendar scheduling, document sharing and chat functions. Also included are Grid portlet clients to the Globus Toolkit 4 services for credential acquisition, remote command execution, and remote file management. The release also features new portlets for Condor and the Storage Resource Broker and optional support for PURSe Grid account management. The OGCE portlet software and plugin modules are integrated with the GridSphere 2.1 portal container and include GridPort information and file management Web services, which may be deployed as separate "science gateway" services.

Sunday, May 14, 2006

Lessons learned from the TeraGrid

Cross-posted from The Grid Blog

IBM Developer Works is running a series on "Lessons learned from the TeraGrid". Up till now, two articles belonging to this series have been published:
Even though, the grid computing community is already aware of the TeraGrid, it is a NSF-funded project to provide integrated computational and data infrastructure for research scientists within the United States. The TeraGrid currently delivers more than 50 teraFLOPS of compute power and 600 TB of storage.
TeraGrid sites provide include IBM IA64 clusters, IBM and Dell IA32 clusters, all running Linux®, 32-processor and 8-processor IBM POWER4/AIX® clusters, an IBM Blue Gene®/L rack, a Cray XT3, and SPARC/Solaris nodes. Data resources include at least six IBM General Parallel File System (GPFS) systems and an assortment of other parallel file systems, including file systems based on Parallel Virtual File System 2 (PVFS2), Lustre, Sun Microsystems' QFS, and IBRIX, along with several Mass Storage Systems (MSS) and Hierarchical Storage Management (HSM) systems.


The first article looks at the use of grid computing to enable large scale resource sharing throughout the TeraGrid transparently and easilly.
This article introduced the TeraGrid, currently the largest set of public high-end computational resources in the United States. It described the motivations behind the project and briefly introduced some of the challenges inherent in managing a large geographically distributed grid. A wide variety of strategies and tools is required to address these challenges, and this article provides an overview of some of the most significant ways in which the TeraGrid project has overcome these challenges.


The second article focuses on the two main data management approaches used in the TeraGrid. The two are GridFTP and the GPFS-WAN file system. GridFTP as we know is a set of extensions to the FTP protocol used to transfer files between the grid nodes. The GPFS-WAN file system, based on IBM's General Parallel File System, supports parallel file system within the Grid nodes. The various security and other flexible features of the system are of specific intrerest. As per the information in teh article the TeraGrid team was allocated 64 server nodes for file system and 6 server nodes for performing metadata operations.

It was the first time, I read about this, so let me quote a few sentences from the article.
two primary challenges must be overcome when providing a parallel file system on a grid: authentication and user-identity mapping; and providing a high level of performance under heavy load when potentially thousands of machines could be accessing the same file system simultaneously.

For GPFS-WAN, the TeraGrid team began by allocating a large number of disks to the file system (twice the amount available to any other high-performance file system), ensuring that the underlying storage would be more than sufficient to fill the available bandwidth.

Saturday, May 13, 2006

Call for Participation: GlobusWORLD 2006

Cross-posted from The Grid Blog

The GlobusWORLD Community Program at GridWorld. Join the Globus Software Community and GGF18 Participants at GridWorld 2006 at the Washington Convention Center.

Whether you're a Globus expert with technical advice to share, or an executive with visions for the future of open source enterprise Grid computing, GlobusWORLD is the premier event for delivering your message to the Grid community. In 2005 hundreds of Grid professionals from research and industry attended GlobusWORLD to discuss Grid adoption issues, receive training and exchange information related to Globus Software, the open-source solution for Grid Computing. This year we join forces with IDG World Expo and GGF to present the most comprehensive event on Grid computing to date.

The GlobusWORLD program will offer a wide variety of conference sessions, mini-symposiums, panel discussions, and tutorials. Speaking opportunities range from highly technical research, development, and deployment presentations to enterprise targeted panels on commercial Grid adoption considerations. The GlobusWORLD program will run in parallel with other GridWorld program tracks and every attempt will be made in scheduling to minimize unnecessary clashes.

Submissions may be wide ranging and should be centered on the theme of Globus Software in Grid Computing applications solutions and / or technology.

KEY DATES AND DEADLINES
Abstract submission deadline - May 26, 2006
Acceptance notification - June 2, 2006
Presentation Slides Due - September 1, 2006
GlobusWORLD Date - September 11-15, 2006

SPEAKING TOPICS
Submissions may be wide ranging and can include, but are not limited to the following
topics.

Technology:
  • Security
  • Resource / Service Management
  • Data Access and Integration
  • Service Oriented Architectures
  • Monitoring and Discovery
  • Provisioning / SLA
  • Meta-scheduling
  • Workflow
  • Web Services
  • Tools
  • Resource Virtualization
Solutions:
  • ROI / Time to Market
  • Data Intensive Applications
  • Compute Intensive Applications
  • Tele-Instrumentation Applications
  • Collaborative Applications
  • Other Applications
  • Utility Computing
  • Standards
  • Building Grid Services
  • Experiences
  • Testbeds
SUBMISSION GUIDELINES

ABSTRACT GUIDELINES
All submissions must include an abstract of no more than 500 words. Abstracts should be written so as to be self-contained and to provide the technical substance required for the program committee to evaluate the session's contribution to the Globus(r) Software and Grid community. If the presentation was given at another conference, then the name, date, and location of the event must be noted in the submission. Abstracts should be submitted in plain text format either as an attachment or in the main body of the e-mail. Abstracts for accepted submissions will be published on the GlobusWORLD website and in other conference material as the description of the session. Presentation slides will be distributed with conference material.

INDIVIDUAL PRESENTATIONS
Presentation proposals may be submitted for individual time slots of thirty minutes, forty-five minutes, one hour or ninety minutes in length. Please be sure to allow ten minutes for Q&A within this allotted time. Individual presentations of less than ninety minutes will be grouped with similar topic presentations to fill an entire session. The submission must state both the preferred and acceptable durations of the presentation.

BUILD YOUR OWN SESSION
Participants are invited to organize their own, complete, ninety-minute session, including but not limited to the following categories. The submission must include an agenda, and the names and associations of all participants.

Panel Session / Mini-Symposium: These sessions will enable conference attendees to learn from a group of experts on a particular topic. The session organizer may deliver an opening talk to set the context for the remainder of the session. Panelists will then give presentations designed to stimulate audience participation, on their preferably diverse opinions, experiences or expertise regarding the theme of the session. At least ten minutes should be reserved at the end for questions from the audience.

Birds-of-a-Feather (BOF) Sessions: These sessions will allow conference attendees to discuss focused subject areas. The session may include presentations and open discussion. Session organizers will be responsible for moderating these sessions and reporting on their outcomes.

All proposals and questions should be sent to gw-pc@globusworld.org

Friday, May 12, 2006

Infinband primer

Cross-posted from The Grid Blog

A nice primer on Infinband appeared in Computer Technology Review. The author, Dave Ellis, is the director of HPC Architecture, Engenio Storage Group, LSI Logic Corporation.

InfiniBand is one of a few I/O architectures initially developed to address high bandwidth, low latency requirements for High Performance Computing (HPC) environments. While early HPC deployments may have used Ethernet interconnects, a certain amount of latency inherent to TCP/IP limited the overall potential performance of the clusters. Since the transport requirements for compute intensive applications do not need all the features of TCP/IP, development began on streamlined I/O architectures. The resulting solutions like Myrinet and InfiniBand support a Message Passing Interface (MPI) over high bandwidth (10 Gigabits per second, Gb/s), very low latency transport architectures.

InfiniBand is still a relatively new technology and today it is supported only in homogenous networks based on a Linux operating system. As the early adopters in HPC and data center environments continue to deploy it and reap the benefits of immensely increased speed and low latency, InfiniBand will eventually become more mainstream. It is expected to be adapted, in time, for use in more general purpose computing environments, and even has the potential to be a replacement for PCI bus architecture in high-end servers and PCs.
Link: http://www.wwpi.com/index.php?option=com_content&task=view&id=1163&Itemid=44

Infinband primer

Cross-posted from The Grid Blog

A nice primer on Infinband appeared in Computer Technology Review. The author, Dave Ellis, is the director of HPC Architecture, Engenio Storage Group, LSI Logic Corporation.

InfiniBand is one of a few I/O architectures initially developed to address high bandwidth, low latency requirements for High Performance Computing (HPC) environments. While early HPC deployments may have used Ethernet interconnects, a certain amount of latency inherent to TCP/IP limited the overall potential performance of the clusters. Since the transport requirements for compute intensive applications do not need all the features of TCP/IP, development began on streamlined I/O architectures. The resulting solutions like Myrinet and InfiniBand support a Message Passing Interface (MPI) over high bandwidth (10 Gigabits per second, Gb/s), very low latency transport architectures.

InfiniBand is still a relatively new technology and today it is supported only in homogenous networks based on a Linux operating system. As the early adopters in HPC and data center environments continue to deploy it and reap the benefits of immensely increased speed and low latency, InfiniBand will eventually become more mainstream. It is expected to be adapted, in time, for use in more general purpose computing environments, and even has the potential to be a replacement for PCI bus architecture in high-end servers and PCs.
Link: http://www.wwpi.com/index.php?option=com_content&task=view&id=1163&Itemid=44