Grid and Cloud Computing

GRID AND CLOUD COMPUTING
Kai Hwang, Geoffery C. Fox and Jack J. Dongarra, “Distributed

and Cloud Computing: Clusters, Grids, Clouds and the Future
of Internet”, First Edition, Morgan Kaufman Publisher.
Prepapred by AbdurRahman/AP/CSE/JCE 1
UNIT I INTRODUCTION
• Evolution of Distributed computing: Scalable
computing over the Internet –
• Technologies for network based systems –
• clusters of cooperative computers –
• Grid computing Infrastructures –
• Cloud computing –
• service oriented architecture –
• Introduction to Grid Architecture and standards
• Elements of Grid –
• Overview of Grid Architecture.
UNIT II GRID SERVICES
• Introduction to Open Grid Services
Architecture (OGSA) –
• Motivation –
• Functionality Requirements –
• Practical & Detailed view of OGSA/OGSI – Data
intensive grid service models –
• OGSA services.
UNIT III VIRTUALIZATION
• Cloud deployment models: public, private, hybrid,
community –
• Categories of cloud computing: Everything as a
service: Infrastructure, platform, software –
• Pros and Cons of cloud computing
• Implementation levels of virtualization
• Virtualization structure –
• Virtualization of CPU, Memory and I/O devices
• Virtual clusters and Resource Management
• Virtualization for data center automation
UNIT IV PROGRAMMING MODEL
• Open source grid middleware packages –
• Globus Toolkit (GT4) Architecture , Configuration –
• Usage of Globus –
• Main components and Programming model -
Introduction to Hadoop Framework –
• Mapreduce, Input splitting, map and reduce functions,
specifying input and output parameters, configuring
and running a job –
• Design of Hadoop file system, HDFS concepts,
command line and java interface, dataflow of File read
& File write.
UNIT V SECURITY
• Trust models for Grid security environment
• Authentication and Authorization methods – Grid
security infrastructure –
• Cloud Infrastructure security: network, host and
application level –
• Aspects of data security, provider data and its
security,
• Identity and access management architecture
• IAM practices in the cloud, SaaS, PaaS, IaaS
availability in the cloud, Key privacy issues in the
cloud.
Unit –I
Scalable computing over the Internet
• Evolutionary changes in Technology:
• Machine architecture,
• Operating system platform,
• Network connectivity, and
• Application workload
• The Age of Internet Computing
• High-performance computing (HPC)
• High-throughput computing (HTC)
The Platform Evolution
Year Technology Example
1950 to 1970 Mainframes IBM 360 and CDC 6400
1960 to 1980 Minicomputers DEC PDP 11 and VAX
1970 to 1990, Personal computers
1980 to 2000 Portable computers and

pervasive devices
Evolution of HPC and HTC systems
HPC vs HTC
• High-Performance Computing
– large amounts of computing for short period.
– Gflops in 1990s to Pflops in 2010.
– Pflops =1000 tflops / tflop = 1000 gflops
• High-Throughput Computing
– large amounts of computing, for much longer time.
– how many jobs
– high-flux computing
Three New Computing Paradigms
• Radio-frequency identification (RFID),
• Global Positioning System (GPS), and
• Internet of Things (IoT).
Computing Paradigm Distinctions
• Distributed computing is the opposite of
centralized computing.
• Parallel computing overlaps with distributed
computing.
• Cloud computing overlaps with distributed,
centralized, and parallel computing.
Computing Paradigm Contd.,
• Centralized computing: All resources are
shared within one integrated OS.
• Parallel computing: Processors are tightly
coupled with centralized shared memory.
• Distributed computing: Multiple autonomous
computers, each with own private memory.
• Cloud computing: Clouds can be built with
physical or virtualized resources.
Scalable Computing Trends and New
Paradigms
• Moore’s law: Processor speed / 18 months
• Gilder’s law: Bandwidth / year
• Degrees of Parallelism
– bit-level parallelism (BLP) : 4-bit mp 8-,16-, 32-,
and 64-bit CPUs
– Instruction-level parallelism (ILP):pipelining,
superscalar computing, VLIW (very long
instruction word) architectures, and
multithreading.
Degrees of Parallelism Contd.,
• Data-level parallelism (DLP) : SIMD (single
instruction, multiple data).
• Task-level parallelism (TLP): since chip
multiprocessors (CMPs).
• Job-level parallelism (JLP).
Innovative Applications
The Trend toward Utility Computing
The Hype Cycle of New Technologies
The Internet of Things and Cyber-
Physical Systems
• The Internet of Things
– 1,000 to 5,000
– H2H (human-to-human),
– H2T (human-to-thing),
– T2T (thing-to-thing)
• Intelligent cities, clean water, efficient power,
convenient transportation, good food supplies,
responsible banks, fast telecommunications,
green IT, better schools, good health care,
abundant resources, and so on.
Cyber-physical system
• A cyber-physical system (CPS) is the result of
interaction between computational processes
and the physical world.
• A CPS merges the “3C” technologies of
computation, communication, and control.
• CPS emphasizes exploration of virtual reality
(VR) applications.
Technologies for network based systems
Multicore CPUs and Multithreading Technologies
• Millions of instructions per second (MIPS)
• Mbps or Gbps
• Advances in CPU Processors
• Multicore architecture with dual, quad, six, or more
processing cores.
• 10 MHz for the Intel 286 to 4 GHz for the Pentium 4.
• ILP : Modern CPU
• DLP and TLP : Graphics processing units (GPUs)
• Multi-core CPU and many-core GPU handle multiple
instruction threads.
Improvement in processor and
network technologies over 33 years.
Typical Multicore processor
Multicore CPUs and Multithreading
Technologies Contd.,
• Multicore CPU and Many-Core GPU
– Multicore CPUs from the tens of cores to hundreds.
– Limited in Parallelism due to Memory wall Problem.
– GPUs with hundreds or more thin cores.
– RISC replaced with multicore x-86 processors.
– CPU cores and thin GPU on same chip.
Multicore CPUs and Multithreading
Technologies Contd.,
• Multithreading Technology
GPU Computing to Exascale and
Beyond
• A GPU is a graphics coprocessor or accelerator
mounted on a computer’s graphics card or
video card.
– GeForce 256 by NVIDIA in 1999.
– 10 million polygons per second.
– Xeon X5670 CPU has six cores.
– GPU chip with hundreds of processing cores.
– GPGPUs: NVIDIA’s CUDA model.
Beyond Contd.,
• How GPUs Work
– as coprocessors.
– NVIDIA GPU 128 cores on a single chip.
– Eight thread / Core ~ 1024 threads.
– Not restricted to graphics or video coding.
– GPU offloads the CPU.
Beyond Contd.,
• GPU Programming Model
– Offloads CPU
– Match bandwidth on-board
Example : NVIDIA Fermi GPU
Beyond Contd.,
• Power Efficiency of the GPU
– CPU Consumes 2 nJ/instruction
– 200 pJ/instruction, which is 1/10 less
Memory, Storage, and Wide-Area
Networking
“Tape units are dead, disks are tape units, flashes are disks, and memory are caches
now.”
• Memory Technology
Networking Contd.,
• System-Area Interconnects
– LAN : client hosts to big servers.
– SAN : servers to network storage.
– NAS : client hosts directly to the disk arrays.
Networking Contd.,
• Wide-Area Networking
– 10 Mbps in 1979 to 1 Gbps in 1999,
– 40 ~ 100 GE in 2011.
– Speculated 1 Tbps network by 2013.
– According to Berman, Fox, and Hey : 1,000, 1,000,
100, 10, and 1 Gbps bandwidths were reported,
respectively, for international, national,
organization, optical desktop, and copper desktop
connections in 2006.
Virtual Machines and Virtualization
Middleware
• Single OS image.
• Different instruction set.
VM Primitive Operations
Data Center Virtualization for Cloud
Computing
• Data Center Growth and Cost Breakdown
– 30 percent IT equipment (such as servers and
disks)
– 33 percent is attributed to the chiller,
– 18 percent to the uninterruptible power supply
(UPS),
– 9 percent to computer room air conditioning
(CRAC), and
– 7 percent to power distribution, lighting, and
transformer costs.
Grid Computing Infrastructures
• Telnet
• HTTP
• Grid computing
• Forbes Magazine :
– $1 trillion in 2001 to $20 trillion by 2015
Computational Grids
• A computing grid offers an infrastructure that
couples computers, software/middleware,
special instruments, and people and sensors.
• Virtual platforms to support Virtual
organizations.
• Grid System : Workstations, servers, clusters,
and supercomputers.
• Personal computers, laptops, and PDAs.
Computational Grids Contd.,
Grid Computing Infrastructures Contd.,
• Example:
– TeraGrid in US
– EGEE (Enabling Grids for E-Science in Europe)
– ChinaGrid
• Grid Families
– GARUDA(Global Access to Resource Using Distributed Architecture)
– IBM, Sun, HP, Dell, Cisco, EMC, and Platform
Computing.
– Categories :
• Data /Comp Grid
• P2P
Peer to Peer Network
• Example of Distributed System : C-S Arch
• P2P Architecture offers Distributed Model.
• Client Oriented
• P2P Systems
– Node as Client /Server.
– Autonomous.
– No Central Coordination.
– TCP/IP and NAI
Peer to Peer Network Contd.,
Network Overlays
Types:
Structured Overlay
Unstructured Overlay
Peer to Peer Network Contd.,
[Application Families]
• Categories:
– Distributed file sharing
• Gnutella, Napster, and BitTorrent
– Collaboration
• MSN or Skype chatting, instant messaging.
– Distributed P2P computing
• SETI@home - 25 Tflops - 3 million Internet Host.
– P2P platforms
• JXTA, .NET, and FightingAID@home, support naming,
discovery, communication, security, and resource
aggregation
Cloud Computing over the Internet
• Computational science is changing to be data-
intensive.
• Sending the computations (programs) to the
data, rather than copying the data to the
workstations.
• Cloud Computing.
“A cloud is a pool of virtualized computer resources.
A cloud can host a variety of different workloads,
including batch-style backend jobs and interactive
and user-facing applications.” - IBM
Internet Clouds
Cloud service models

Grid and Cloud Computing

Uploaded by

Copyright:

Available Formats

Grid and Cloud Computing

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Grid and Cloud Computing

Uploaded by

Copyright:

Available Formats

GRID AND CLOUD COMPUTING

Kai Hwang, Geoffery C. Fox and Jack J. Dongarra, “Distributed

1950 to 1970 Mainframes IBM 360 and CDC 6400

1960 to 1980 Minicomputers DEC PDP 11 and VAX

1970 to 1990, Personal computers

1980 to 2000 Portable computers and

You might also like