We think you have liked this presentation. If you wish to download it, please recommend it to your friends in any social system. Share buttons are a little bit lower. Thank you!
Presentation is loading. Please wait.
Published byJake Pollock
Modified over 4 years ago
© 2007 Open Grid Forum Grids in the IT Data Center OGF 21 - Seattle Nick Werstiuk October 16, 2007
© 2007 Open Grid Forum 2 Setting the Context GFSG Discussions @ OGF 20 Tasked with pulling together a small group to draft an OGF position statement on grids in the IT Data Center Team Included Paul Strong, Bernd Kosch, Hans-Christian Hoppe, Chris Kantarjiev, Robert Fogel, Cheryl Doninger, Mark Linesch, This presentation reflects the output of that group
© 2007 Open Grid Forum 3 Presentation Contents Grids in the Data Center - Definition Trends and Motivations Characteristics Grids in the Data Center - Challenges What are the problems organizations face in building this infrastructure OGF Activities What activities are underway within the OGF to assist the community.
© 2007 Open Grid Forum 4 Trends and Motivations Business Agility/Flexibility Current data centers, based on siloed infrastructure and monolithic applications are no longer sustainable Infrastructure Cost Challenges Drive to increase utilization of data center resources, making the most efficient use of these resources to maximize ROI. Address the power, cooling and floor space issues
© 2007 Open Grid Forum 5 Trends and Motivations Increased Workload Demands More Applications, More Data, Faster Results Many applications have outgrown a single (large) server environment, and a scale out model is the only cost effective option Management Complexity While providing superior price/performance, scale out architectures (100s to 1000s of servers) introduce severe complexity and manageability challenges Shared Services Model Trend toward re-architecting an enterprise IT infrastructure away from a vertical, line-of-business orientation toward a horizontal, shared, service-oriented architecture.
© 2007 Open Grid Forum 6 Data Center Grid - Characteristics Dynamic Infrastructure Multiple competing demands from different applications, lines of business and users require a flexible and ever changing data center infrastructure. Multiple Application Types and Workloads Support multiple business unit applications, mixed application types, and user communities IT Control Infrastructure is centrally managed and controlled by the CIO group Corporate policy and Management Domains guide the processes and procedures around the management, utilization and security of the Grid.
© 2007 Open Grid Forum 7 Data Center Grid - Characteristics Managed by Business policies and Priorities Combination of budgets and business value used to define how resources are applied to meet corporate business objectives. Ability to Scale 10s, 100s and 1000s of resources, Supporting multiple applications on shared infrastructure resources. Integrate and federate diverse, often very large scale data storage and database resources, Provide swift access to static and streaming data, and employ techniques like data affinity scheduling or caching to minimize data access overheads.
© 2007 Open Grid Forum 8 Data Center Grid - Challenges Configuration Management Enable application virtualization where an application service can be flexibly deployed onto resources as required by business demand. Deployment and configuration of all types of resources, and the dependencies between resources in support of the applications. Manage the infrastructure that is in a state of continual change Automated Resource and Application Management, Monitoring and Reporting Enable the ability to respond to problems and provide real time and historical views of both resource usage and application performance against service levels.
© 2007 Open Grid Forum 9 Data Center Grid - Challenges Storage and Data Integration Flexible compute and data environment to support application scalability on the distributed infrastructure. Scalability of Processes and Tools Tools to manage a few statically configured/siloed application environments will not scale to meet the needs of 1000s of servers deployed in a shared infrastructure. Resource Allocation, Sharing, Service Level Management and Chargeback Balance Competing Business priorities across multiple application types vs. Efficiency
© 2007 Open Grid Forum 10 Data Center Grid - Challenges Software Licensing models Enable the dynamic scaling of business applications to meet unpredictable business demand or performance service levels. Psychological/Political issues Overcoming the perceived need to own resources, increase willingness to share, define workable internal budget models for asset acquisition/chargeback.
© 2007 Open Grid Forum 11 OGF Activities Reference Model Working Group Grid and Virtualization Working Group Enterprise Area Activities
© 2007 Open Grid Forum 12 Conclusions - Break the static links … Application Virtualization Data Virtualization Infrastructure Virtualization Access data at any location, in any format Match applications to available resources Pool, share and aggregated resources
© 2007 Open Grid Forum 13 Conclusions - Data Center Grid Enable sharing of infrastructure across application types (batch, services, transactional) based on policy, demand and load Enable an optimal use of a minimum set of infrastructure resources Provide a holistic view of the environment (infrastructure and applications) enabling economies of scale in management and integration of management tool stack Build on similar experiences from Grid in Technical computing.
Connected Health Framework
1/17/20141 Leveraging Cloudbursting To Drive Down IT Costs Eric Burgener Senior Vice President, Product Marketing March 9, 2010.
3. Introduction to Strategic Information Systems Planning (SISP)
Pricing for Utility-driven Resource Management and Allocation in Clusters Chee Shin Yeo and Rajkumar Buyya Grid Computing and Distributed Systems (GRIDS)
Andrew Dolan Markets and Banking Technology May-07 Enterprise Grid at Citi Grids Mean Business.
© 2007 Open Grid Forum Grid & Virtualization Working Group OGF21 gridvirt-wg 2007 Seattle, WA Erol Bozak, Chair SAP, Development Architect Wolfgang Reichert,
Introduction to Grid Application On-Boarding Nick Werstiuk
1 Service Oriented Architectures (SOA): What Users Need to Know. OGF 19: January 31, 2007 Charlotte, NC John Salasin, Ph.D, Visiting Researcher National.
Enterprise Computing Strategies This gig is bigger than grid: from HPC to service orientation John Barr Research.
ETSI Grid Starter Group BT Perspective on Grid and Standardisation Mike Fisher BT Group 24 May 2006.
All rights reserved © 2006, Alcatel Grid Standardization & ETSI (May 2006) B. Berde, Alcatel R & I.
1Copyright © 2013, Oracle and/or its affiliates. All rights reserved.
Hello i am so and so, title/role and a little background on myself (i.e. former microsoft employee or anything interesting) set context for what going.
Deploying Virtualised Infrastructures for Improved Efficiency and Reduced Cost Adrian Groeneveld Senior Product Marketing Manager Adrian Groeneveld Senior.
Introduction to the new mainframe: Large-Scale Commercial Computing © Copyright IBM Corp., All rights reserved. Chapter 2: Capacity.
1 Functional Strategy – IS & IT Geoff Leese November 2006, revised July 2007, September 2008, August 2009.
2 Industry trends and challenges Windows Server 2012: Modern workstyle, enabled Access from virtually anywhere, any device Full Windows experience.
Windows Server Deployment and Management With System Center.
1 Chapter 11: Data Centre Administration Objectives Data Centre Structure Data Centre Structure Data Centre Administration Data Centre Administration Data.
© 2018 SlidePlayer.com Inc. All rights reserved.