2. A computer cluster is group of loosely coupled
computers that work together closely so that in many res
pects it can be viewed as through it as a single computer.
Clusters are commonly connected through fast
local area networks.
Clusters have evolved to improve speed and also to
support applications ranging from ecommerce, to high p
erformance database applications.
2
3. The first commodity clustering product was ARCnet,
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.
3
4. Price/Performance :-
The reason for the growth in use of clusters is that
they have significantly reduced the cost of processing
power.
Availability:-
Single points of failure can be eliminated, if any one
system component goes down, the system as a whole
stay highly available.
4
5. scalability :-
HPC clusters can grow in overall
capacity because processors and nodes
can be added as demand increases.
5
6. In cluster computing , each node within the cluster
is an independent system.
With its own operating system , private memory
and in some cases own file system.
Because the processors on one node can not
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.
6
8. High Availability or Failover Clusters
Load Balancing Clusters
Parallel / Distributed Processing Clusters
8
9. These clusters are designed to provide
uninterrupted availability of data or services
(typically web services) to the end-users
community.
If node fails, the service can be restored wit
hout affecting the availability of the services
provided by the clusters.
9
10. While the application will still be
available ,there will be a performance
drop due to the missing node.
The purpose of these clusters is to ensure that a
single instance of an application is only ever running
on one cluster member at a time but if and when
that cluster member is no longer available , the
application will failover to another cluster member.
10
13. This type of cluster distributes incoming request
s for resources or content among multiple nodes
running the same programs or having the same
content.
Both the high availability and load-balancing
cluster technologies can be combined to
increase the reliability, availability, and scalabilit
y of application and data resources that are widely
deployed for web, mail, news, or FTP services.
13
14. Every node in the cluster is able to h
andle requests for the same content or
application.
This type of distribution is typically
seen in a web-hosting environment.
14
17. parallel processing was performed by multiple
processors in a specially designed parallel compu
ter. These are systems in which multiple process
ors
share a single memory and bus interface within a
single computer.
These types of cluster increase availability, perf
ormance, and scalability for applications, particu
larly computationally or data intensive tasks.
17
18. The basic building blocks of clusters are
broken down into multiple categories:
1. Cluster Nodes
2. Cluster Network
3. Network Characterization
18
19. There are three primary categories of
applications that use parallel clusters:
Compute Intensive Application.
Data or I/O Intensive Applications.
Transaction Intensive Applications.
19
20. A user submits a job to the head node.
The job identifies the application to run on the
cluster.
The job scheduler on the head node assigns each
task defined by the job to a node and then starts e
ach application instance on the assigned node.
Results from each of the application instances are
returned to the client via files or databases.
20
22. The main benefits of clusters are:
1. Availability
2. Performance
3. Scalability
These benefits map to needs of today's enterprise
business, education, military and scientific commun
ity infrastructures.
22
24. Cluster networking
If you are mixing hardware that has
different networking technologies, there will
be large differences in the speed with which
data will be accessed and how individual
nodes can communicate. If it is in your budge
t make sure that all of the machines you want
to include in your cluster have similar ne
tworking capabilities, and if at all possible, ha
ve network adapters from the same man
ufacturer.
24
25. Cluster Software
You will have to build versions of
clustering software for each kind of system
you include in your cluster.
25
26. Programming
Our code will have to be written t
o support the lowest common denominator
for data types supported by the least powe
rful node in our cluster. With mixed machi
nes, the more powerful machines will have
attributes that cannot be attained in the
powerful machine.
26
27. Timing
This is the most problematic aspec
t of cluster. Since these machines have diffe
rent performance profile our code will exe
cute at different rates on the different kinds
of nodes. This can cause serious bottlen
ecks if a process on one node is waiting for
results of a calculation on a slower node..
27
28. Network Selection
There are a number of different ki
nds of network topologies, including buses,
cubes of various degrees, and grids/meshes.
These network topologies will be
implemented by use of one or more network
interface cards, or NICs, installed into the
head-node and compute nodes of our cluster.
28
29. Speed Selection
No matter what topology you choose f
or your cluster, you will want to get fastest net
work that your budget allows. Fortunately,
the availability of high speed computers has al
so forced the development of high speed
networking systems.
Examples are :
10Mbit Ethernet, 100Mbit Ethernet, gigabit
networking, channel bonding etc.
29
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. 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.
High Availability or Failover Clusters
Load Balancing Cluster
Parallel/Distributed Processing Clusters
These clusters are designed to provide uninterrupted availability of data or services (typically web services) to the end-user community.
if a node fails, the service can be restored without affecting the availability of the services provided by the cluster.
While the application will still be available, there will be a performance drop due to the missing node.
The purpose of these clusters is to ensure that a single instance of an application is only ever running on one cluster member at a time but if and when that cluster member is no longer available, the application will failover to another cluster member.