1 Grids: The Future of Computing Jacques P. Sauvé – UFCG 2004.

Slides:



Advertisements
Similar presentations
What is Cloud Computing? Massive computing resources, deployed among virtual datacenters, dynamically allocated to specific users and tasks and accessed.
Advertisements

What is Cloud Computing? Massive computing resources, deployed among virtual datacenters, dynamically allocated to specific users and tasks and accessed.
1 From Grids to Service-Oriented Knowledge Utilities research challenges Thierry Priol.
GT 4 Security Goals & Plans Sam Meder
Agreement-based Distributed Resource Management Alain Andrieux Karl Czajkowski.
SLA-Oriented Resource Provisioning for Cloud Computing
What is Grid Computing? Cevat Şener Dept. of Computer Engineering, METU.
High Performance Computing Course Notes Grid Computing.
By Adam Balla & Wachiu Siu
Cloud Computing to Satisfy Peak Capacity Needs Case Study.
Seminar Grid Computing ‘05 Hui Li Sep 19, Overview Brief Introduction Presentations Projects Remarks.
1 Software & Grid Middleware for Tier 2 Centers Rob Gardner Indiana University DOE/NSF Review of U.S. ATLAS and CMS Computing Projects Brookhaven National.
IBM Solutions for Grid Computing. I. IT view on “GRID” II. IBM and GRID III. IBM Storage and GRID Index …
 Amazon Web Services announced the launch of Cluster Compute Instances for Amazon EC2.  Which aims to provide high-bandwidth, low- latency instances.
Computing and Data Infrastructure for Large-Scale Science Deploying Production Grids: NASA’s IPG and DOE’s Science Grid William E. Johnston
Milos Kobliha Alejandro Cimadevilla Luis de Alba Parallel Computing Seminar GROUP 12.
SPRING 2011 CLOUD COMPUTING Cloud Computing San José State University Computer Architecture (CS 147) Professor Sin-Min Lee Presentation by Vladimir Serdyukov.
New Challenges in Cloud Datacenter Monitoring and Management
WORKFLOWS IN CLOUD COMPUTING. CLOUD COMPUTING  Delivering applications or services in on-demand environment  Hundreds of thousands of users / applications.
Module 2: Information Technology Infrastructure
Cloud computing Tahani aljehani.
TECHNOLOGY GUIDE 3: Emerging Types of Enterprise Computing
VAP What is a Virtual Application ? A virtual application is an application that has been optimized to run on virtual infrastructure. The application software.
1.Training and education 2.Consulting 3.Travel 4.Hardware 5.Software Which of the following is not included in a firm’s IT infrastructure investments?
“ Does Cloud Computing Offer a Viable Option for the Control of Statistical Data: How Safe Are Clouds” Federal Committee for Statistical Methodology (FCSM)
Computing in Atmospheric Sciences Workshop: 2003 Challenges of Cyberinfrastructure Alan Blatecky Executive Director San Diego Supercomputer Center.
Cloud computing is the use of computing resources (hardware and software) that are delivered as a service over the Internet. Cloud is the metaphor for.
Grid Computing. What is a Grid? Many definitions exist in the literature Early definitions: Foster and Kesselman, 1998 –“A computational grid is a hardware.
© Copyright 2011 Hewlett-Packard Development Company, L.P. 1 Sundara Nagarajan (“SN”) CLOUD SYSTEMS AUTOMATION.
PCGRID ‘08 Workshop, Miami, FL April 18, 2008 Preston Smith Implementing an Industrial-Strength Academic Cyberinfrastructure at Purdue University.
Introduction to Cloud Technology StratusLab Tutorial (Orsay, France) 28 November 2012.
DISTRIBUTED COMPUTING
Grid Computing at The Hartford Condor Week 2008 Robert Nordlund
C5- IT Infrastructure and Emerging Technologies. Input – Process - Output 2 A computer  Takes data as input  Processes it  Outputs information CPU.
Service - Oriented Middleware for Distributed Data Mining on the Grid ,劉妘鑏 Antonio C., Domenico T., and Paolo T. Journal of Parallel and Distributed.
Service Oriented Architecture (SOA) Dennis Schwarz November 21, 2008.
Middleware for Grid Computing and the relationship to Middleware at large ECE 1770 : Middleware Systems By: Sepehr (Sep) Seyedi Date: Thurs. January 23,
Grid Middleware Tutorial / Grid Technologies IntroSlide 1 /14 Grid Technologies Intro Ivan Degtyarenko ivan.degtyarenko dog csc dot fi CSC – The Finnish.
Chapter 5 McGraw-Hill/Irwin Copyright © 2011 by The McGraw-Hill Companies, Inc. All rights reserved.
Ames Research CenterDivision 1 Information Power Grid (IPG) Overview Anthony Lisotta Computer Sciences Corporation NASA Ames May 2,
NA-MIC National Alliance for Medical Image Computing UCSD: Engineering Core 2 Portal and Grid Infrastructure.
Authors: Ronnie Julio Cole David
Cracow Grid Workshop ‘06 17 October 2006 Execution Management and SLA Enforcement in Akogrimo Antonios Litke Antonios Litke, Kleopatra Konstanteli, Vassiliki.
What is SAM-Grid? Job Handling Data Handling Monitoring and Information.
GRID Overview Internet2 Member Meeting Spring 2003 Sandra Redman Information Technology and Systems Center and Information Technology Research Center National.
Ruth Pordes November 2004TeraGrid GIG Site Review1 TeraGrid and Open Science Grid Ruth Pordes, Fermilab representing the Open Science.
RESERVOIR RESERVOIR Resources and Services Virtualization without Barriers Philippe Massonet (CETIC)
© Copyright 2012 Hewlett-Packard Development Company, L.P. The information contained herein is subject to change without notice. 1 Automate your way to.
The EPIKH Project (Exchange Programme to advance e-Infrastructure Know-How) Giuseppe Andronico INFN Sez. CT / Consorzio COMETA Beijing,
Nov 22/26 Tech Forum 2015 Roberto Trinconi Cloud the New Path to the Business Leadership.
Globus and PlanetLab Resource Management Solutions Compared M. Ripeanu, M. Bowman, J. Chase, I. Foster, M. Milenkovic Presented by Dionysis Logothetis.
Simplifying Cloud Connectivity for Your Clients Presenter: Tom SharkeyTom Sharkey December 8,
Securing the Grid & other Middleware Challenges Ian Foster Mathematics and Computer Science Division Argonne National Laboratory and Department of Computer.
GRID ANATOMY Advanced Computing Concepts – Dr. Emmanuel Pilli.
3/12/2013Computer Engg, IIT(BHU)1 CLOUD COMPUTING-2.
1 TCS Confidential. 2 Objective : In this session we will be able to learn:  What is Cloud Computing?  Characteristics  Cloud Flavors  Cloud Deployment.
© 2009 IBM Corporation IBM Cloud Computing Tivoli Service Automation Manager V7.2 The Core of the Service Management System for Cloud Computing.
INTRODUCTION TO GRID & CLOUD COMPUTING U. Jhashuva 1 Asst. Professor Dept. of CSE.
Internet2 Applications & Engineering Ted Hanss Director, Applications Development.
Bob Jones EGEE Technical Director
Introduction to Cloud Technology
Clouds , Grids and Clusters
SuperComputing 2003 “The Great Academia / Industry Grid Debate” ?
Access Grid and USAID November 14, 2007
Grid Computing.
GRID COMPUTING PRESENTED BY : Richa Chaudhary.
Cloud Computing.
Optena: Enterprise Condor
Large Scale Distributed Computing
Review of grid computing
Presentation transcript:

1 Grids: The Future of Computing Jacques P. Sauvé – UFCG 2004

2 Agenda Problems Solutions The State of the Art Challenges for the Future

3 Problems Remember that business needs drive technology However, technology itself can also change enough to upset the status quo So let’s look at: –Business drivers that lead to grids –Technology drivers that lead to grids

4 “Business” needs in Science and Engineering Domains Scientists and engineers can always use up as much computing power as you can throw at them! They generate lots of data (petabytes) and always need cycles, storage, etc. One computer, even a supercomputer, isn’t enough New needs –Much more collaboration between remote sites –Lots of disperse data

5 Business Drivers in the Business Domain E-Commerce and E-Business have led to large distributed systems Need to interconnect with partners and cross administrative domains Demands on the CIO –Improve availability –Increase business relevance –Reduce complexity –Support rapid change –Drive costs down Grids will try to address items in bold

6 The Mission in Technological Terms The aggregate effect is that qualities of service traditionally associated with mainframe host- centric computing are now essential to the effective conduct of e-business across distributed compute resources, inside as well as outside the enterprise. For example, enterprises must provide consistent response times to customers, despite workloads with significant deviations between average and peak utilization

7 Why it’s difficult and expensive Four main problems 1.How to handle scale and large demand variations while maintaining QoS 2.How to cross administrative domains while maintaining security 3.How to deal with high cost of operating computers 4.How to deal with the appearance of service providers (eUtilities)

8 Problem 1 Scale, Demand Variation and QoS Should a business have resources to handle the peak (to maintain QoS)? –Peak demand may be 10 times normal demand –Systems have to handle tens of thousands of users We would not accept a situation in which every home and business had to operate its own power plant, library, printing press and water reservoir. Why should we do so for computers?

9 Problem 2 Crossing Admin Domains, Security Very tough technical problem to solve Solutions are labor-intensive and prone to error Trust is inherently non-scalable because it cannot be automated!

10 Problem 3 High Cost of Operating Computers Total cost of ownership is always going up –We are now using very complex distributed systems Responding to change leads to frequent reconfigurations with very high maintenance costs Businesses are screaming for a way to reduce all this complexity Outsourcing is a trend that highlights this

11 Problem 4 e-Utilities Specialized e-Utilities leverage economies of scale to drive costs down for certain services How to factor them into a business’ IT architecture?

12 Solutions: Grids What? How? Definitions

13 Solutions: What we want 1.Decoupling production and consumption Enables specialized functions and common services to be turned into commodities 2.Demand-driven access to (decoupled) computational resources 3.Transparency

14 What we want: A Picture Looks like the Web?? –Inside the cloud are resources, not information Computational Grid (Resources) Computational Grid (Resources)

15 Solutions: How is this achieved? Virtualization –Hide implementation behind an interface –User receives a virtual computer –Looks like a “utility grid” whence the name “computing grid” Provisioning of computational resources (compute-power, storage, network bandwidth), on a per-need basis

16 Solutions: How is this achieved? Service Orientation –If resources are not “here”, how do I get to them? Access a service –You promise a behavior: natural way to virtualize –Since services are distributed, use Web Services to access middleware functions With some modifications for grids, this was turned into Web Services Resource Framework (old OGSI)

17 Grids: A Definition Coordinated resource sharing and problem solving in dynamic, multi- institutional virtual organizations –Not subject to centralized control –Based on standards –Delivers non-trivial QoS

18 State of The Art: Applications Distributed Supercomputing –Distributed supercomputing applications use grids to aggregate substantial computational resources in order to tackle problems that cannot be solved on a single system High-Throughput Computing (Scavenging grids) –Harness many otherwise idle resources to increase aggregate throughput

19 State of the Art: Applications Data-Intensive Computing –Focus is on synthesizing new information from data that is maintained in geographically distributed repositories, digital libraries, and databases On-Demand Computing –Use grid capabilities to meet short-term requirements for resources that can not be cost-effectively or conveniently located locally Collaborative Computing –Enabling and enhancing human-to-human interactions

20 Commercial Grids Closer to last 2 (on-demand, collaboration) but there are other differences –Business applications run continuously –Over long periods of time... –Have more stringent requirements on reliability, security and accountability Virtualizing IT assets Phrases used (marketing!) –“utility computing,” “e-business on demand,” “planetary computing,” “autonomic computing,” “enterprise grids”

21 Infrastructure for Computational Grids State of the Art: we are still working on building a robust infrastructure Still trying to standardize basic pieces –Ex.: OGSI just changed to WSRF to make Web Services people happy No planetary deployment yet –Largest grid: China Educational and Research Grid 500 TeraBytes, 6 TeraFLOPS (30 MFLOPS/student)

22 State of the Art: Grid Components 1. User view: a portal

23 State of the Art: Grid Components 2. Security (GSI – Grid Security Infra)

24 State of the Art: Grid Components 3. Broker Service (MDS = Monitoring and Discovery Service)

25 State of the Art: Grid Components 4. Scheduler

26 State of the Art: Grid Components 5. Data Management (GASS = Grid Access to Secondary Storage)

27 State of the Art: Grid Components 6. Job Submission (GRAM = Grid Resource Allocation Manager)

28 State of the Art: HP Utility Data Center (UDC) –Wire-once, programmatically reconfigurable, virtualized data center, with fined-grained allocation, security and control of every resource UDC can be a node in a larger grid (virtual data center with many UDCs) Go to Planetary scale: planetary scale computing –“The” Grid

29 State of the Art: IBM

30 Challenges for the Future We’re at the very beginning Lots of marketing and hype “The” grid doesn’t exist Standardization still going on Where are the challenges...?

31 Challenges The Nature of Applications –Given a grid, what is possible in terms of applications in scientific and engineering domains and in other areas such as business, art, and entertainment?

32 Challenges Programming models and tools –Need new thinking about this System architecture –Many conflicting requirements Infrastructure support –Resource management (allocation, coordination, …) –Security, defining and managing sharing relationships and other policies

33 Challenges Grid management –Grid configuration and discovery –Fault handling –Accounting –Instrumentation –How to handle planetary scale?

34 Thank You.