Cluster Computing
By Aakash Kumar Singh
NETAJI SUBHASH ENGINEERING COLLEGE
Name:- AAKASH KUMAR SINGH
Stream:- Information Technology
Section:- ‘A’
Class Roll No.:- ‘01’
University Roll No.:-
10900214001
Subject:- Seminar
Contents
 Introduction
 Cluster Computing
 History
 Architecture
 How cluster Computing works
 Type of cluster
 High performance clusters
 High availability cluster or Failover Clusters
 Load balancing cluster
 Components of clusters
 Advantage
 Disadvantage
 Applications
 Conclusion
Introduction
 Grouping of objects into classes such a way that
 Objects in same cluster are similar
 Objects in different clusters are dissimilar
Clustering is the task of grouping a set of
objects.
The group of objects are known as Cluster.
Group of some objects Clustering 1 (by Type)
Clustering 2 (by colour) Clustering 3 (by shape)
What is cluster computing?
 A computer cluster consists of a set of loosely
connected computers that work together so that in
many respects they can be viewed as a single system.
 Clusters are commonly connected through fast local
area networks.
About Cluster Computing
 Consists of many of the same or similar type of machines.
 Tightly-coupled using dedicated network connections.
 The components of a cluster are usually connected to each
other through fast local area networks, each node running its
own instance on an operating system.
 All machines share resources.
 They must trust each other so that does not require a
password, otherwise you would need to do a manual start on
each machine.
HISTORY
 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.
ARCHITECTURE
 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
• Generally 2 or more computers (nodes) connected together
• In a single cabinet, or physically separated & connected via
a LAN
• Appear as a single system to users and applications
• Provide a cost-effective way to gain features and benefits
ARCHITECTURE
How cluster computers works
How cluster computers works
 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.
Types of cluster
 High performance clusters
 High availability cluster or Failover Clusters
 Load balancing cluster
High performance cluster
 Start from 1994
 Donald becker of nasa assembled this cluster.
 Also called beowulf cluster.
• Dependable parallel computers
• Application like data mining , simulations , parallel processing ,
weather modeling etc.
High availability clusters or failover clusters
 Avoid single point of failure.
 Designed 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.
Load balancing cluster
 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.
Components of cluster
 The basic building blocks of clusters are broken down into
multiple categories:
 The cluster nodes,
 Cluster operating system,
 Network switching hardware and
 The node/switch interconnect
ADVANTAGES
 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
added 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.
DISADVANTAGES
 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.
Applications
 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.
Difference between cloud, grid and clusters
computing
 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 computting that relies on
sharing computing resources rather than having local servers or
personal devices to handle applications.
Conclusion
 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!!
Cluster Computing

Cluster Computing

  • 1.
  • 2.
    NETAJI SUBHASH ENGINEERINGCOLLEGE Name:- AAKASH KUMAR SINGH Stream:- Information Technology Section:- ‘A’ Class Roll No.:- ‘01’ University Roll No.:- 10900214001 Subject:- Seminar
  • 3.
    Contents  Introduction  ClusterComputing  History  Architecture  How cluster Computing works  Type of cluster  High performance clusters  High availability cluster or Failover Clusters  Load balancing cluster  Components of clusters  Advantage  Disadvantage  Applications  Conclusion
  • 4.
    Introduction  Grouping ofobjects into classes such a way that  Objects in same cluster are similar  Objects in different clusters are dissimilar Clustering is the task of grouping a set of objects. The group of objects are known as Cluster.
  • 5.
    Group of someobjects Clustering 1 (by Type) Clustering 2 (by colour) Clustering 3 (by shape)
  • 6.
    What is clustercomputing?  A computer cluster consists of a set of loosely connected computers that work together so that in many respects they can be viewed as a single system.  Clusters are commonly connected through fast local area networks.
  • 7.
    About Cluster Computing Consists of many of the same or similar type of machines.  Tightly-coupled using dedicated network connections.  The components of a cluster are usually connected to each other through fast local area networks, each node running its own instance on an operating system.  All machines share resources.  They must trust each other so that does not require a password, otherwise you would need to do a manual start on each machine.
  • 8.
    HISTORY  Greg Pfisteris 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.
  • 9.
    ARCHITECTURE  A clusteris 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 • Generally 2 or more computers (nodes) connected together • In a single cabinet, or physically separated & connected via a LAN • Appear as a single system to users and applications • Provide a cost-effective way to gain features and benefits
  • 10.
  • 11.
  • 12.
    How cluster computersworks  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.
  • 13.
    Types of cluster High performance clusters  High availability cluster or Failover Clusters  Load balancing cluster
  • 14.
    High performance cluster Start from 1994  Donald becker of nasa assembled this cluster.  Also called beowulf cluster. • Dependable parallel computers • Application like data mining , simulations , parallel processing , weather modeling etc.
  • 16.
    High availability clustersor failover clusters  Avoid single point of failure.  Designed 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.
  • 18.
    Load balancing cluster 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.
  • 20.
    Components of cluster The basic building blocks of clusters are broken down into multiple categories:  The cluster nodes,  Cluster operating system,  Network switching hardware and  The node/switch interconnect
  • 21.
    ADVANTAGES  Availability • Incase 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 added 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.
  • 22.
    DISADVANTAGES  More Spaceis 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.
  • 23.
    Applications  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.
  • 24.
    Difference between cloud,grid and clusters computing  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 computting that relies on sharing computing resources rather than having local servers or personal devices to handle applications.
  • 25.
    Conclusion  Clusters arepromising  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!!