cluster computing

Cluster computing ppt

1. P resented by 120630107090 Bhandari Anjali Dilipbhai MBICT,VVnagar CLUSTER COMPUTING

2. Introduction History Cluster architecture How Clusters Computer works ? Types of cluster Components of clusters Advantages Disadvantages Issuse to be considered Application Difference Between Cluster, Grid and cloud Computing Conclusion Overview

3. Cluster computing is a group of loosely coupled computers that work together closely so that in many respects it can be viewed as though it were a single computer . Clusters are commonly connected through fast local area networks. CLUSTER COMPUTING

4. Clusters are usually deployed to improve speed and/or reliability over that provided by a single computer, while typically being much more cost effective than single computer the of comparable speed or reliability . In cluster computing each node within a cluster is an independent system, with its own operating system, private memory, and, in some cases, its own file system. Continue...

5. Because the processors on one node cannot directly access the memory on the other nodes, programs or software run on clusters usually employ a procedure called "message passing" to get data and execution code from one node to another. Cluster computing can also be used as a relatively low-cost form of parallel processing for scientific and other applications that lend themselves to parallel operations. Continue...

6. Greg Pfister is a computer scientist and worked a lot for cluster computing, according to him clusters were not invented by any specific vendor but by customers. The first commodity clustering product was ARC net(Attached Resource Computer Network), developed by Datapoint in 1977. The next product was VAXcluster,released by DEC in 1980’s. Microsoft, sun microsystems, and other leading hardware and software companies offer clustering packages. History

7. A cluster is a type of parallel /distributed processing system, which consists of a collection of interconnected stand-alone computers cooperatively working together a single, integrated computing resource. A node: A single or multiprocessor system with memory, I/O facilities, &OS G enerally 2 or more computers (nodes) connected together I n a single cabinet, or physically separated & connected via a LAN A ppear as a single system to users and applications P rovide a cost-effective way to gain features and benefits Clusters Architecture

8. Cluster architecture

9. How cluster computers works Fig :- Cluster Computer at short Glance

10. In the above arrangement of clusters the machines are arranged through the common high speed bus in a manner that they can communicate with each other. A simple High speed LAN can be used to connect these machines through which these machines can be accessed via web or these machines can access the web. LAN arrangement contains numbers of busses for the flow of traffic in circuit,CPU’s to process the data, memory to storage devices to store the unprocessed (received) data and processed (transmitted) data, and shared memory will have data from number of CPU’s. wORKING

11. High performance clusters High availability cluster or Failover Clusters Load balancing cluster Types of cluster

12. Start from 1994 Donald becker of nasa assembled this cluster. Also called beowulf cluster. D ependable parallel computers Application like data mining , simulations , parallel processing , weather modeling etc. High performance cluster

13. Fig :- High performance Cluster

14. Avoid single point of failure. D esigned to provide uninterrupted availability of data or services to the end This requires atleast two nodes a primary and a backup. Always with redundancy. Almost all load balancing cluster are with HA capability. Used to implement database, mail, file print, web application servers. High availability clusters or failover clusters

15. Fig :- High Availability Cluster

16. Pc cluster deliver load balancing performance. It distributes incoming requests for resources or content among multiple nodes running the same programs or having the same content Each node in cluster is able to handle requests for the same content or application. Both the high availability and load balancing cluster technologies can be combined to increase the reliability, availability , and scalability of application and data resources that are widely deployed for web , mail or FTP services. Load balancing cluster

17. Fig :- Load Balancing Cluster

18. The basic building blocks of clusters are broken down into multiple categories : The cluster nodes, C luster operating system, N etwork switching hardware and T he node/switch interconnect Components of cluster

19. Availability In case if server is having a problem another server from the cluster takes over the server having issue. This ensure the high availability of web applications. Scalable Server clustering is completely a scalable solution. Resources can be addeded to the cluster accordingly. Load Handling and maintenance If a dedicated server from the cluster requires maintenance,it can be stopped while other servers handles. Easy to manage More easy cluster management software are emerging to manage the clusters and in present also some are available. aDVANTAGES

20. More Space is required Server clustering usually requires more servers and hardware to manage and monitor thus increases the infrastructure. Some web hosting providers may afford it. Very expensive It is not a cost-effective solution, as it needs a good server design which can be a bit expensive. dISADVANTAGES

21. Cluster networking Cluster software Programming Timing Network selection Speed selection Issuse to be considered

22. Web serving/searching (google search engine) Email , echat , ebook, ebank E-commerce application(amazon.com, ebay.com) Weather forecasting Computational fluid dynamics Petroleum Reservoir Simulation Earthquake Simulation. Image Rendering. ApplicationS

23. Grid Computing : - It is collection of computer resources from multiple locations to reach a common goal. Cluster Computing : - It is a form of computing in which a group of computers are linked together so that they can act like a single entity . Cloud Computing :- It is a type of com putting that relies on sharing computing resources rather than having local servers or personal devices to handle applications. Difference between cloud, grid and clusters computing

24. Characteristics Systems Clusters Grid Cloud Population Commodity Computers High-end Computers Servers, Clusters Commodity Computers ,High-end Servers, and network Attached Storage Size/Scalability 100 1000 100 to 1000 Node OS Linux, Windows Mainly Unix Multiple OSs Running on Virtual Machine Ownership Single Multiple Single InterconnectionNetwork?speed Dedicated, high-end network with low latency and high bandwidth Mostly internet snd high latency and low bandwidth Dedicated, high-end network with low latency and high bandwidth Discovery Membership Services Centralized Indexing and Decentralized Information Services Membership Services Continue…..

25. Characteristics Clusters Grid Cloud Security/privacy Traditional Login/password –based Medium level of privacy Depend on User privileges Public/private key pair based Authentication and mapping a User to an account Limited support for privacy Each user/application is provided with a virtual machine high security, High Security. Privacy is guaranteed Support for selling per-file Access Control List(ACL) User Management Centralized Decentralized, Virtual Organization based Centralized or Decentralized to Third Party Resource Management Centralized Distributed Centralized/ Distributed Allocation/Scheduling Centralized Decentralize Centralized/ Decentralized Single System Image yes no Yes, But Optional Capacity Stable and Guaranteed Varies but High Provisioned on Demand Service Pricing Limited in Non-Open market Mainly Internal Pricing Pricing according to Effects with Discount for VIP Clients Continue…..

26. Characteristics Clusters Grid Cloud Internet Working Multi-clustering within an organization Limited High Potential, support Third-party solution providers loose Coupling of services from Different Clouds Standards/inter-operability Virtual Interface Architecture Based Some Open Grid Standards Web Services (Simple Object Access Protocol and representational store Transfer Application Drivers Science, business, enterprise Computing Data centers Collaborative Scientific and High throughput Computing Applications Dynamically Provisioned Legacy and web applications Content Display Continue…..

27. Clusters are promising Solve parallel processing paradox New trends in hardware and software technologies are likely to make clusters. Clusters based supercomputers(Linux based clusters) can be seen everywhere!! Conclusion