Grid Computing Resource virtualization and optimization via Grid and Cloud Computing Moon J Kim IBM Senior Technical Staff Member/Chief Architect/Master Inventor moonkim@us.ibm.com
Grid Computing Grid Motivations Grid Focus Areas Accelerate and enhance the R&D process by Research ����������������������������� enabling the sharing data Public and and computing power Industrial ���������� Development � Faster, more accurate decision making seamlessly for research intensive applications Share data and computing Engineering power, for computing and intensive engineering and Industrial scientific applications, to Design accelerate product design ������������������������������ Enable faster and more ����������� � Access to distributed data, information comprehensive business Financial Business planning and analysis Industrial insight Analytics through the sharing of data Public and computing power Optimize computing and Financial Enterprise data assets to improve Industrial Optimization utilization, efficiency and Public business continuity ��������������� �������� Create large-scale IT � Improve efficiency and cost structure infrastructures to drive Government economic development Public Development and/or enable new government services
Grid Computing An On Demand Infrastructure Solution Business-driven An on demand operating Development environment is an integrated On Demand On Demand On Demand infrastructure aligned to Operating Operating Operating Infrastructure Environment Integration Management Environment Environment business goals and processes in a resilient and secure manner All designed with an architecture that allows you manage services as components Results: Simplification and Optimization of IT to meet the needs of the business responsively
Grid Computing ��� ��� ��� ��� is the only solution provider that can help Virtualize Outside the clients realize value from the full spectrum of Enterprise grid computing solutions Virtualize the Enterprise Suppliers, partners, customers and external resources Virtualize Unlike Resources Enterprise wide Grids and Global Fabrics Virtualize Like Resources Heterogeneous systems, application based Grids and networks Cluster Single System (Partitioning) Simple Sophisticated (2-4) (4+) Homogenous systems, storage and networks ���������� ������������� ������������������� ���������������������� ��������������� ���������������
Grid Computing Realizing Increasing Levels of Business Value Virtualize Outside the Enterprise Virtualize the Enterprise ��� ������������������ Virtualize Unlike Resources �����������!�����"����� ������#����"����� $��%���� &�������"����� Virtualize Like Resources ��������������������������� ��������� ������������������� Cluster ������������������������ Single System (Partitioning) ����������������� Simple Sophisticated ���� (2-4) (4+) ������������� ������������������������ ���������������� ���� ��������������
Grid Computing IBM’s Business Drivers � Competitive pressure to decrease time to market – Grids can help reduce cycle time, improve quality, and enable more effective collaboration � Many business processes require long compute time – Grids can cut processing time through effective management of heterogeneous resources – Reduced compute time allows additional iterations for greater accuracy and/or reduced cycle time � Reduce total cost of ownership (TCO) for traditional data center resources – Grids help drive down TCO through optimized use of existing compute resources and centralized system management
Grid Computing Grid Value Summary Business Value Technical Value � Improve Operating Efficiency/ROI � Improve Asset Optimization � Reduce Capital Expenses � Integrate Heterogeneous Resources � Accelerate Business Processes � Enable Data Access, Integration and � Enhance Employee Productivity Collaboration � Quickly Adapt to Changing � Strengthen Redundancy and Resiliency Requirements � Quickly Respond to Variable Demands Staffing Value Marketing Value � Embracing "hot" technology attracts � Grid is open, a key part of on demand best technical talent. � College I/T students involved with � Leverages the full range of IBM products Grid technologies and services (hardware, software and services) � Next generation distributed computing � Grid is solutions focused � Grid has mindshare in the marketplace
Grid Computing How can I simplify my IT infrastructure if my complexity is accelerating? …it may be easier than you may think, it is about simplifying your environments to align to your business goals. This means making your IT environments interoperable, fully integrated; and automated for greater efficiency, productivity and service quality.
Grid Computing Today’s complex infrastructure create challenges Business data Firewall Routers SSL UNIX servers switches appliances Mainframe PCs Web servers Security and Database servers directory servers UNIX Application servers IP logical Services PCs DNS/NTP/DDNS Servers File/Print servers Caching appliances UI data LAN (IP PBX) servers � Management of complex, heterogeneous environments too hard � IT asset utilization is too low and no interoperability in multiplatforms � Privacy, security and business continuity � Swamped by the proliferation of technology and platforms to support � Operational speed is too slow; IT flexibility too limited � Inability to manage the infrastructure seamlessly
Grid Computing Server / Storage Utilization Peak-hour Prime-shift 24-hour Period Utilization Utilization Utilization Mainframe 85-100% 70% 60% UNIX 50-70% 10-15% <10% Intel-based 30% 5-10% 2-5% Storage N/A N/A 52% Source: IBM Scorpion White Paper: Simplifying the Corporate IT Infrastructure,
Grid Computing Utilization-week (AFS) 'Week' Graph (30 Minute Average)
Grid Computing Optimize IT Through Infrastructure Management: Virtualization and Automation ������������������������� �������������� �������������� ���������� ���������� ������������������������� Sense and respond to changes, manage and optimize for the needs of the business via Automation and Virtualization ���������� ���������� �������������� �������������� � Build enterprise-wide application fabrics � Increase flexibility and reduce costs by simplifying and exploiting internal and automating your IT best practices and external resources extend across process disciplines and resources
Grid Computing Virtualization is a fundamental imperative “Virtualization is the process of presenting computing resources in ways that users and applications can easily get value out of them, rather than presenting them in a way dictated by their implementation, geographic location, or physical packaging. In other words, it provides a logical rather than physical view of data, computing power, storage capacity, and other resources.” Jonathan Eunice, Illuminata Inc. …Virtualization is far more than just partitioning or single products
Grid Computing Virtual Servers Virtualization - levels of technologies Create multiple images of a resource within a Hypervisor physical resource Physical Virtual Memory - LPAR’s – Virtual Machines – Logical Channels Server OS OS OS OS Create functions and facilities which appear to be real although they do not exist within the physical Device Device Device Device Driver Driver Driver Driver resource Proxy Proxy Proxy Proxy Virtual Networks, Hipersockets, Virtual Disk and Caches Virtual Ethernet LAN Hypervisor Pool multiple separate “distributed” resources so they appear as a single resources from the user point of view Cluster Clusters – GSA Grid - SAN Volume Controller - SAN File Sharing Create SERVICE’s using open interfaces and Virtualization based on GRID standards, where the services are “unaware of” and Computing capabilities and “have no dependency” on the underlying WebServices (SOA) “distributed”, “heterogeneous” and “shared” physical infrastructure Convergence of Systems Management across Enterprise GRID Enterprise-wide Grid of Resources evolving into WSRF WebServices Resource Framework (WSRF)
Recommend
More recommend
