7/30/2019 Cloud Unit 1
1/18
byB. Hari Prasad, Asst.Prof,
CSE Dept. [email protected]
Gopallapuram, Renigunta-Srikalahasti road, Tirupati
7/30/2019 Cloud Unit 1
2/18
Introductory concepts and overview
Parallel Computing Architectures
7/30/2019 Cloud Unit 1
3/18
Parallel Computing
Symmetric multi processing
Massively parallel processing systems
High performance Cluster computing
Grid computing
7/30/2019 Cloud Unit 1
4/18
7/30/2019 Cloud Unit 1
5/18
Symmetric MultiProcessing (SMP)
Processing of programs by multiple processors that share a
common operating system and memory
Tightly Coupled Multi Processing
Dosen't exceed more than 16 Processors
SMP is better than MMP systems when Online Transaction
Processing is Done, in which many users can access the same
database to do a search with a relatively simple set of common
transactions
Its ability to dynamically balance the workload among computers
7/30/2019 Cloud Unit 1
6/18
Massively Parallel Processing (MPP)
Processing of programs by multiple processors that work on different parts
of the program and share different operating systems and memories
Different Processors communicate with each other through message interfaces
Upto 200 processors which run for a single application
InterConnect arrangement of data paths allows messages to be sent between
different processors
loosely coupled
Better than an SMP for applications that allow a number of databases to be
searched in parallel.
7/30/2019 Cloud Unit 1
7/18
Cluster Computing
A set of loosely connected computers work together as a single systemcluster are usually connected to each other through fast local area networks
Each node consists its own operating system
To improve performance and availability over that of a single computer
Characteristics of Cluster computing Tightly coupled system
Single system image
Centralized Job management & scheduling system
http://en.wikipedia.org/wiki/Local_area_networkhttp://en.wikipedia.org/wiki/Local_area_network7/30/2019 Cloud Unit 1
8/18
Grid Computing
Is the federation of computer resources from multiple administrative
domains to reach a common goal
More loosely coupled, heterogeneous, and geographically dispersed
Grids are a form of distributed computing whereby a super virtual
computer is composed of many networked loosely coupled computers
acting together to perform large tasks.
Characteristics of Grid Computing Loosely coupled (Decentralization)
Diversity and Dynamism
Distributed Job Management & scheduling
Areas of Grid Computing and it's applications for modeling and computing1.Predictive Modeling and Simulations
2.Engineering Design and Automation
3.Energy Resources Exploration
4.Medical, Military and Basic Research
5.Visualization
7/30/2019 Cloud Unit 1
9/18
Difference Between Cluster Computing VS. Grid Computing
Cluster Grid
Homogenous Heterogeneous
single location LAN, metropolitan or WAN
All nodes behave like a single
system view
Every node is autonomous
Tightly coupled systems Loosely coupled
Centralized Decentralization
Centralized Job management &
scheduling system
Distributed Job Management &
scheduling
7/30/2019 Cloud Unit 1
10/18
Distributed computing
Distributed computing also refers to the use of distributed systems to
solve computational problems
Consists of multiple autonomous computers that communicate through a
computer network
Distributed computing, a problem is divided into many tasks, each ofwhich is solved by one or more computers
IN parallel computing, all processors may have access to a shared
memory to exchange information between processors.
IN distributed computing, each processor has its own private memory
(distributed memory). Information is exchanged by passing messages
between the processors
Parallel Computing VS. Distributed Computing
7/30/2019 Cloud Unit 1
11/18
Service-Oriented Architecture (SOA)
7/30/2019 Cloud Unit 1
12/18
Set of principles and methodologies for designing and developing
software in the form of interoperable services
Service-Oriented Architecture (SOA)
SOA design principles are used during the phases of systems
development and integration.
Service-orientation requires loose couplingof services with operatingsystems and other technologies that underlie applications
Services and their corresponding consumers communicate with each
other by passing data in a well-defined, shared format, or by co
ordinating an activity between two or more services
SOA defines how to integrate widely disparate applications for a Web-
based environment and uses multiple implementation platforms. Rather
than defining an API, SOA defines the interface in terms of protocols and
functionality
7/30/2019 Cloud Unit 1
13/18
Service-Oriented Architecture (SOA)
7/30/2019 Cloud Unit 1
14/18
Virtualization
Creation of a virtual (rather than actual) version of something, such as ahardware platform, operating system (OS), storage device, or network
resources.
physical computer is actual machine, both subjectively (from theuser's point of view) and objectively (from the hardware system
administrator's point of view), a virtual machine is subjectively acomplete machine (or very close), but objectivelymerely a set of filesand running programs on an actual, physical machine
Types of virtualization
HardwareSoftwareMemoryStorageDataNetwork
http://en.wikipedia.org/wiki/Operating_systemhttp://en.wikipedia.org/wiki/Operating_system7/30/2019 Cloud Unit 1
15/18
HardwarevirtualizationHardware virtualizationorplatform virtualizationrefers to the creation of avirtual machine that acts like a real computer with an operating system
Hardware virtualization, the host machine is the actual machine on whichthe virtualization takes place, and the guest machineis the virtual machine.
Different types of hardware virtualization include
Full virtualization
Partial virtualizationPara virtualization
http://en.wikipedia.org/wiki/Virtual_machinehttp://en.wikipedia.org/wiki/Virtual_machinehttp://en.wikipedia.org/wiki/Virtual_machinehttp://en.wikipedia.org/wiki/Virtual_machine7/30/2019 Cloud Unit 1
16/18
Software virtualization
Operating system-level virtualization, hosting of multiple virtualized
environments within a single OS instance.
Application virtualization and workspace virtualization, the hosting of
individual applications in an environment separated from the underlying
OS.
Service virtualization, emulating the behavior of dependent (e.g., third-
party, evolving, or not implemented) system components that are needed
to exercise an application under test (AUT) for development or testing
purposes.
7/30/2019 Cloud Unit 1
17/18
Memory
Memory virtualization, aggregating Random Access Memory resourcesfrom networked systems into a single memory pool.
Virtual memory, giving an application program the impression that it has
contiguous working memory, isolating it from the underlying physical
memory implementation.
Memory over commitment, allows a computer to grant more memory to the
virtual machines running on it than is installed on the physical computer.
Storage
Storage virtualization, the process of completely abstracting logical
storage from physical storage.
Distributed file system
Storage hypervisor
7/30/2019 Cloud Unit 1
18/18
Data
Data virtualization, the presentation of data as an abstract layer,independent of underlying database systems, structures and storage.
Database virtualization, the decoupling of the database layer, which lies
between the storage and application layers within the application stack
over all.
Network
Network virtualization, creation of a virtualized network addressing space
within or across network subnets