A CSEL presentation based on I. Foster, Z. Yong, I. Raicu, and S. Lu, "Cloud Computing and Grid Computing 360-Degree Compared," in Grid Computing Environments.

Slides:



Advertisements
Similar presentations
Cloud Computing and Grid Computing 360-Degree Compared
Advertisements

The Anatomy of the Grid: An Integrated View of Grid Architecture Carl Kesselman USC/Information Sciences Institute Ian Foster, Steve Tuecke Argonne National.
1 Cloud Computing Prof. Ravi Sandhu Executive Director and Endowed Chair April 12, © Ravi Sandhu World-Leading.
High Performance Computing Course Notes Grid Computing.
An Approach to Secure Cloud Computing Architectures By Y. Serge Joseph FAU security Group February 24th, 2011.
CLOUD COMPUTING AN OVERVIEW & QUALITY OF SERVICE Hamzeh Khazaei University of Manitoba Department of Computer Science Jan 28, 2010.
A Computation Management Agent for Multi-Institutional Grids
Seminar Grid Computing ‘05 Hui Li Sep 19, Overview Brief Introduction Presentations Projects Remarks.
CLOUD Demystifying the Jesse Dunietz SASS Talk A Survey of Cloud Computing.
Milos Kobliha Alejandro Cimadevilla Luis de Alba Parallel Computing Seminar GROUP 12.
4b.1 Grid Computing Software Components of Globus 4.0 ITCS 4010 Grid Computing, 2005, UNC-Charlotte, B. Wilkinson, slides 4b.
Presented by Sujit Tilak. Evolution of Client/Server Architecture Clients & Server on different computer systems Local Area Network for Server and Client.
Grid Computing Net 535.
Applied Architectures Eunyoung Hwang. Objectives How principles have been used to solve challenging problems How architecture can be used to explain and.
Plan Introduction What is Cloud Computing?
Osama Shahid ( ) Vishal ( ) BSCS-5B
A Brief Overview by Aditya Dutt March 18 th ’ Aditya Inc.
Grid Toolkits Globus, Condor, BOINC, Xgrid Young Suk Moon.
Software to Data model Lenos Vacanas, Stelios Sotiriadis, Euripides Petrakis Technical University of Crete (TUC), Greece Workshop.
PhD course - Milan, March /09/ Some additional words about cloud computing Lionel Brunie National Institute of Applied Science (INSA) LIRIS.
Grid Computing. What is a Grid? Many definitions exist in the literature Early definitions: Foster and Kesselman, 1998 –“A computational grid is a hardware.
Cloud Computing 1. Outline  Introduction  Evolution  Cloud architecture  Map reduce operation  Platform 2.
A Lightweight Platform for Integration of Resource Limited Devices into Pervasive Grids Stavros Isaiadis and Vladimir Getov University of Westminster
DISTRIBUTED COMPUTING
Grid Computing - AAU 14/ Grid Computing Josva Kleist Danish Center for Grid Computing
GT Components. Globus Toolkit A “toolkit” of services and packages for creating the basic grid computing infrastructure Higher level tools added to this.
Grid Resource Allocation and Management (GRAM) Execution management Execution management –Deployment, scheduling and monitoring Community Scheduler Framework.
Evaluation of Agent Teamwork High Performance Distributed Computing Middleware. Solomon Lane Agent Teamwork Research Assistant October 2006 – March 2007.
The Anatomy of the Grid Mahdi Hamzeh Fall 2005 Class Presentation for the Parallel Processing Course. All figures and data are copyrights of their respective.
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
GRIDS Center Middleware Overview Sandra Redman Information Technology and Systems Center and Information Technology Research Center National Space Science.
GRID Overview Internet2 Member Meeting Spring 2003 Sandra Redman Information Technology and Systems Center and Information Technology Research Center National.
Introduction to Grids By: Fetahi Z. Wuhib [CSD2004-Team19]
1 Observations on Architecture, Protocols, Services, APIs, SDKs, and the Role of the Grid Forum Ian Foster Carl Kesselman Steven Tuecke.
7. Grid Computing Systems and Resource Management
Globus and PlanetLab Resource Management Solutions Compared M. Ripeanu, M. Bowman, J. Chase, I. Foster, M. Milenkovic Presented by Dionysis Logothetis.
Development of e-Science Application Portal on GAP WeiLong Ueng Academia Sinica Grid Computing
Chapter 8 – Cloud Computing
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-1.
Web Technologies Lecture 13 Introduction to cloud computing.
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.
Directions in eScience Interoperability and Science Clouds June Interoperability in Action – Standards Implementation.
PARALLEL AND DISTRIBUTED PROGRAMMING MODELS U. Jhashuva 1 Asst. Prof Dept. of CSE om.
Distributed Geospatial Information Processing (DGIP) Prof. Wenwen Li School of Geographical Sciences and Urban Planning 5644 Coor Hall
Submitted to :- Neeraj Raheja Submitted by :- Ghelib A. Shuaib (Asst. Professor) Roll No : Class :- M.Tech(CSE) 2 nd Year.
INTRODUCTION TO GRID & CLOUD COMPUTING U. Jhashuva 1 Asst. Professor Dept. of CSE.
© 2012 Eucalyptus Systems, Inc. Cloud Computing Introduction Eucalyptus Education Services 2.
1 Views of Cloud Computing Prof. Ravi Sandhu Executive Director and Endowed Chair March 25, © Ravi Sandhu.
EPIKH Project (Exchange Programme to advance e-Infrastructure Know-How) Giuseppe Andronico INFN Sez. CT & Consorzio COMETA Workshop Clouds.
Parallel Computing Globus Toolkit – Grid Ayaka Ohira.
Prof. Jong-Moon Chung’s Lecture Notes at Yonsei University
Unit 3 Virtualization.
Grid and Cloud Computing
Example: Rapid Atmospheric Modeling System, ColoState U
Recommendation 6: Using ‘cloud computing’ to meet the societal need ‘Faster and transparent access to public sector services’ Cloud computing Faster and.
Globus —— Toolkits for Grid Computing
Grid Computing.
Recap: introduction to e-science
University of Technology
GRID COMPUTING PRESENTED BY : Richa Chaudhary.
Introduction to Cloud Computing
Cloud Computing Dr. Sharad Saxena.
Emerging technologies-
Cloud Computing: Concepts
Views of Cloud Computing
Presentation transcript:

A CSEL presentation based on I. Foster, Z. Yong, I. Raicu, and S. Lu, "Cloud Computing and Grid Computing 360-Degree Compared," in Grid Computing Environments Workshop, GCE '08, 2008, pp

Overview Grid and Cloud Comparison Business Model Architecture Resource Management Programming Model Application Model Security Model 2

3 To meet computational needs Single supercomputer is too expensive A distributed system Coordination of existing resources (e.g. computer clusters) to form virtual supercomputer Mostly used in universities and government laboratories 1 hard-working person VS many average person Parallelizing jobs

Do you know what exactly is Cloud computing? Born as a relative to Grid computing and Utility computing Cluster computing Distributed systems Moving computation on PC to centrally managed resources By oneself - private Cloud By third-party – public Cloud (e.g. Amazon) Hybrid 4

“In the mid 1990s, the term Grid was coined to describe technologies that would allow consumers to obtain computing power on demand. Ian Foster and others posited that by standardizing the protocols used to request computing power, we could spur the creation of a Computing Grid, analogous in form and utility to the electric power grid.” I. Foster, Z. Yong, I. Raicu, and S. Lu, "Cloud Computing and Grid Computing 360-Degree Compared," in Grid Computing Environments Workshop, GCE '08, 2008, pp

Resources: compute resource, file (data) exchange, software and others. Virtual Organization (VO): organisations usually with common interest contribute to (and thus form) the Grid 6 “…coordinated resource sharing and problem solving in dynamic, multi-institutional virtual organizations.” I. Foster, "The Anatomy of the Grid: Enabling Scalable Virtual Organizations," in Proceedings of the 7th International Euro-Par Conference Manchester on Parallel Processing, 2001, pp. 1-4.

7 The Grid provides high computation capacity and data storage through the coordination of shared distributed resources. Economies of scale Driven by the need for higher computation capacity and storage while reducing costs, organizations share their resources - thus forming the Grid environment - in exchange for access to the resources owned by other organizations inside the Grid S. Smanchat, "Scheduling Parameter Sweep Workflow in the Grid," PhD, Caulfield School of Information Technology, Monash University, Australia, 2012.

8 Enabling ways to solve problem that were not possible Enables organisations to perform the tasks that require computation power exceeding their own by delegating tasks to be executed by others. Increasing resource utilization Other parties can make use of any idle resources in the Grid according to resource sharing agreement S. Smanchat, "Scheduling Parameter Sweep Workflow in the Grid," PhD, Caulfield School of Information Technology, Monash University, Australia, 2012.

9 Ground concept remains similar: reducing cost, increasing reliability and flexibility by using federated resources Context changes: Big Data Virtualization Clusters are expensive Virtualization of commodity servers (or even clusters) is a better choices Problems in the resource management also remains similar. Usage Discovery Programming

10 “A large-scale distributed computing paradigm that is driven by economies of scale, in which a pool of abstracted, virtualized, dynamically- scalable, managed computing power, storage, platforms, and services are delivered on demand to external customers over the Internet.” I. Foster, Z. Yong, I. Raicu, and S. Lu, "Cloud Computing and Grid Computing 360-Degree Compared," in Grid Computing Environments Workshop, GCE '08, 2008, pp

11 Massively scalable Abstract entity No complicated setup is required (unlike Grid) Different levels of services (e.g. packages) for end users: Economies of scale Services can be re-configured and delivered on demand.

12 Cloud is a distributed system Cloud evolves from Grid computing And may use Grid computing as supporting infrastructure Utility computing Computing resources are metered (e.g. utility Grid) Service-Oriented Architecture (SOA)

I. Foster, Z. Yong, I. Raicu, and S. Lu, "Cloud Computing and Grid Computing 360-Degree Compared," in Grid Computing Environments Workshop, GCE '08, 2008, pp

14 G. Mateescu, W. Gentzsch and C. J. Ribbens, "Hybrid Computing—Where HPC meets grid and Cloud Computing," Future Generation Computer Systems, vol. 27, pp , 2011.

15 “Grid is a system that 1) Coordinates resources that are not subject to centralized control 2) Using standard, open, general-purpose protocols and interfaces 3) To deliver nontrivial qualities of services” I. Foster, "What is the Grid? - a three point checklist," GRIDtoday, vol. 1, However, central administration control may be present in some Grids Globus Toolkit Version 4 (de facto standard)

16 Cloud Usage-based payment (e.g. EC2 and S3) VS traditional one-time payment for software Access 100,000 cores without full investment Grid Resource sharing (e.g. CPU cycle) within VO Project-oriented Usually used in academic institutions Give and take

17 I. Foster, "The Anatomy of the Grid: Enabling Scalable Virtual Organizations," in Proceedings of the 7th International Euro-Par Conference Manchester on Parallel Processing, 2001, pp. 1-4.

18 Fabric layer – access to resources E.g. Condor, GARA (General architecture for advanced reservation) Connectivity layer – communication and authentication GSI (Grid Security Infrastructure) Resource layer – protocols related to resources GridFTP, GRAM (Grid Resource Access and Management) Collective layer – monitor and discover VO resources E.g. Condor-G, Nimrod-G Application layer – whatever you want E.g. Grid workflow, Grid portal Globus Toolkit covers the first four layers

19 I. Foster, Z. Yong, I. Raicu, and S. Lu, "Cloud Computing and Grid Computing 360-Degree Compared," in Grid Computing Environments Workshop, GCE '08, 2008, pp

20 Fabric layer – hardware resources Unified resource layer – abstract resources through virtualization Platform layer – specialized services providing development platform E.g. web hosting Application layer – applications on Cloud

21 IaaS – Infrastructure as a Service Hardware (virtual) and software for application environment Scalable (and reconfigurable) dynamically E.g. EC2 and S3 PaaS – Platform as a Service Higher level environment for deployment of application E.g. Google’s App Engine SaaS – Software as a Service Specialized software accessed remotely through the Internet e.g. Office Web Apps

22 G. Sakellari and G. Loukas, "A survey of mathematical models, simulation approaches and testbeds used for research in cloud computing," Simulation Modelling Practice and Theory, 2013.

23 AWS Console as of August 2014

24

25 Grid compute model Batch-scheduled model Users submit job > request resource > wait for resource > run Usually long wait queue and data staging Hardware-bound queuing system Cloud compute model Resources are shared by all users at the same time in the Cloud via virtualization No hardware-bound queuing

26 Cloud data model Everything on the Cloud VS Ian Foster’s vision Can we trust Cloud security? Do we want to do things offline? Listening to music on the Cloud? Desktop supercomputer I. Foster, Z. Yong, I. Raicu, and S. Lu, "Cloud Computing and Grid Computing 360-Degree Compared," in Grid Computing Environments Workshop, GCE '08, 2008, pp

27 Grid data model Data Grid E.g. management of data replicas GridFTP - analogous to BitTorrent Virtual data – data abstraction Location transparency Distributed metadata catalog Privacy and access control Materialization transparency (transfer VS recompute)

28 Other concerns Data locality File system and data transfer Merging compute and data management Moving data around for computation Virtualization Monitoring Provenance Log history of execution Implemented in workflow management systems

29 MPI (Message Passing Interface) – most commonly used For multi-core architecture / cluster MPICH-G2 - Grid-enabled MPI with Globus Toolkit integration Grid programming focuses on management of large numbers of datasets and tasks. The motivation for Grid workflow system MapReduce – distributes program to data Integration and interoperability are the challenges in the Cloud

30 Grid HPC / HTC applications MPI Workflow applications Loosely coupled applications Homogeneous / heterogeneous tasks of small / large sizes Cloud Not well-defined yet Transaction-oriented Interactive

31 Grid Hardware are shared by different institutions Likely to be heterogeneous resources Each site has its own security measure Single sign-on GSI (Grid Security Infrastructure) based on PKI Cloud Hardware usually belong to single organization Likely to be homogeneous resources Simpler and less secure (please check for update) Most important for Cloud’s success

32 Data only accessed by the authorized users Security certificate of Cloud provider Data (physical) location and privacy Data segregation – separate data of each user Recovery Support for investigation Data viability, even though the provider is taken over

33 Random interesting scenario