Introduction to Cloud Computing

and the Aneka Platform

Dr. Rajkumar Buyya

Cloud Computing and Distributed Systems (CLOUDS) Lab
Dept. of Computing and Information Systems
The University of Melbourne, Australia
www.cloudbus.org
www.manjrasoft.com

Major Sponsors/Supporters

Manjrasoft
 The Next Revolution in IT
The Big Switch in IT
 Classical Computing  Cloud Computing
 Buy & Own  Subscribe
 Hardware, System  Use
Software, Applications
Every 18 months?

often to meet peak needs.

 Install, Configure,
Test, Verify, Evaluate
 Manage
 ..
 Finally, use it  $ - pay for what you
 $$$$....$(High CapEx) use, based on QoS

2
 Outline

 “Computer Utilities”
 Vision and Promising IT Paradigms/Platforms
 Cloud Computing and Related Paradigms
 Trends, Definition, Cloud Benefits and Challenges
 Market-Oriented Cloud Architecture
 SLA-oriented Resource Allocation
 Global Cloud Exchange
 Aneka: Cloud Application Platform
 Summary and Thoughts for Future

3
 “Computer Utilities” Vision:
Implications of the Internet
 1969 – Leonard Kleinrock, ARPANET project
 “As of now, computer networks are still in their
infancy, but as they grow up and become
sophisticated, we will probably see the spread
of “Computer Utilities”, which, like present
electric and telephone utilities, will service
individual homes and offices across the
country”.
 During the last 40 years, several advances
have taken place in both “computing” and
“communications” areas that are turning the
vision of “Computer Utilities” in to a reality.
4
 Computing Paradigms and
Attributes: Realizing the ‘Computer
Utilities’ Vision

} ?
 Web
 Data Centres
 Utility Computing
 Service Computing
 Grid Computing +
 P2P Computing
 Market-Oriented
Computing
-Ubiquitous
 Cloud Computing -Reliable
- Trillion $ business
 … -Scalable
-Autonomic

-Dynamic
Paradigms
discovery
- Composable
-QoS
-SLA
-…

5
Attributes/Capabilities
 Outline

 “Computer Utilities”
 Vision and Promising IT Paradigms/Platforms
 Cloud Computing and Related Paradigms
 Trends, Definition, Cloud Benefits and Challenges
 Market-Oriented Cloud Architecture
 SLA-oriented Resource Allocation
 Global Cloud Exchange
 Aneka: Cloud Application Platform
 Summary and Thoughts for Future

6
 Very popular: too many are
“In Search” of Cloud Computing

7
 Open Data Center Alliance (ODCA)
for Cloud Computing

8
 Defining Clouds: There are many
views for what is cloud computing?

 Over 20 definitions:
 http://cloudcomputing.sys-con.com/read/612375_p.htm
 Renting “remote storage”  backup
 Renting “remote server”  hosting Web server
 Renting “remote more servers”  to manage large workload
 Buyya’s Scientific definition of Cloud Computing 
 “Cloud is a market-oriented distributed computing system consisting
of a collection of inter-connected and virtualised computers that are
dynamically provisioned and presented as one or more unified
computing resources based on service-level agreements (SLAs)
established through negotiation between the service provider and
consumers.”
 SLA = {negotiated and agreed QoS parameters + rewards
+ penalties for violation of agreement....}
9
 Subscription-Oriented Cloud Services:
X{compute, apps, data, ..}
as a Service (..aaS)
Public Cloud

Cloud
Manager

Private
Clients Cloud

Other Govt.
Cloud Services Cloud Services

10
 Rentable Cloud Services

 Infrastructure as a Service
(IaaS)
Software as a Service (SaaS)
 CPU, Storage: Amazon.com,
Nirvanix, GoGrid….
 Platform as a Service (PaaS)
Platform as a Service (PaaS)
 Google App Engine, Microsoft
Azure, Manjrasoft Aneka..
 Software as a Service (SaaS)
Infrastructure as a Service (IaaS)
 SalesForce.Com

....

11 Manjrasoft
 Cloud Deployment Models

Public/Internet Private/Enterprise Hybrid/Inter

Clouds Clouds Clouds

3rd party, Mixed usage of

Cloud model run
multi-tenant Cloud private and public
within a company’s
infrastructure Clouds: Leasing public
own Data Center /
& services: cloud services
infrastructure for
when private cloud
internal and/or
* available on capacity is
partners use.
subscription basis insufficient

12
 Cloud Applications

•Scientific/Tech Applications
•Business Applications

•Consumer/Social Applications

Science and Technical Applications

Business Applications

13 Consumer/Social Applications
 When will Cloud spending become
50% of IT spending or reach to a
trillion $ business/year?
2000

600?

30% 1000? 50%

120?
15%

2016 2020? 2020?

Buyya’s Guestimate!
14
 Cloud Computing Challenges:
Dealing with too many issues
ng
P r i ci

z at ion Scalability
uali Res
Vi r t our
ce Met
er i ng
QoS Reliability
v el
e Le nts Billing
e
r v i c em
Se gre E ne
rgy
A E ff i
ci en
Provision cy
ing Utility & Risk
on Deman
d Management
a l & ry
uri ty g to
Sec Le ula
g
Re
Uhm, I am not quite
Privacy Programming Env.
clear…Yet another
& Application Dev.
st complex IT paradigm?
Tru

Software Eng.
Complexity
15
 Outline

 “Computer Utilities”
 Vision and Promising IT Paradigms/Platforms
 Cloud Computing and Related Paradigms
 Trends, Definition, Cloud Benefits and Challenges
 Market-Oriented Cloud Architecture
 SLA-oriented Resource Allocation
 Global Cloud Exchange
 Aneka: Cloud Application Platform
 Summary and Thoughts for Future

16
 Market-Oriented Cloud Architecture:
QoS negotiation and SLA-based Resource Allocation

Users/
Brokers

Service Request Examiner and

Admission Control
- Customer-driven Service Management
- Computational Risk Management
SLA - Autonomic Resource Management
Resource
Allocator Pricing Accounting

VM Service Request
Monitor Dispatcher Monitor

Virtual
Machines
(VMs)

Physical
Machines

17
 Cloud to expand (lease more
resources) with increase in demand
Users/
Brokers

Service Request Examiner and

Admission Control
- Customer-driven Service Management
- Computational Risk Management
SLA - Autonomic Resource Management
Resource
Allocator Pricing Accounting

VM Service Request
Monitor Dispatcher Monitor

Virtual
Machines
(VMs)

Physical
Machines

18
 Cloud to shrink (unlease resources)
with decrease in demand
Users/
Brokers

Service Request Examiner and

Admission Control
- Customer-driven Service Management
- Computational Risk Management
SLA - Autonomic Resource Management
Resource
Allocator Pricing Accounting

VM Service Request
Monitor Dispatcher Monitor

Virtual
Machines
(VMs)

Physical
Machines

19
 Outline

 “Computer Utilities”
 Vision and Promising IT Paradigms/Platforms
 Cloud Computing and Related Paradigms
 Trends, Definition, Cloud Benefits and Challenges
 Market-Oriented Cloud Architecture
 SLA-oriented Resource Allocation
 Global Cloud Exchange
 Aneka: Cloud Application Platform
 Summary and Thoughts for Future

20
 Aneka: The Cloud Application Platform
(CAP) for Resource-Intensive Apps
(Available as Manjrasoft Product)
 Lightweight Container hosting Multiple Applications
multiple services.
 All programming models Thread Task ... MapReduce
available from within the
same container (unlike others) 1. SDK
 SDK containing APIs for
multiple programming
models and tools Aneka
 Runtime Environment for
managing application
execution management
 Suitable for 2. Runtime
 Development of Enterprise
Cloud Applications Multi-core Cluster Grid Cloud
 Cloud enabling legacy 2100 2100 2100 2100

applications
 Portability for Customer Apps: 2100 2100 2100 2100

 Enterprise ↔ Public Clouds

 .NET/Win ↔ Mono/Linux Multiple Infrastructures
21
 Aneka: The Cloud Application Platform
(CAP) for Resource-Intensive Apps
(Available as Manjrasoft Product)
Application Management Kit
 Lightweight Container hosting Management Administration

multiple services.
Studio Portal
Software Development Kit

All programming models

Design SLA-Negotiation Management
 APIs Explorer Web Services Web Services

available from within the Conta ine r

same container (unlike others) Programming Models

 SDK containing APIs for Task

Model
Thread
Model
Map Reduce
Model
Other
Models

Persistence
multiple programming

Security
Foundation Services
models and tools Patent Membership Reservation Storage License Accounting
Services Services Services Services Services
 Runtime Environment for (PCT)
managing application Fabric Services
Dynamic Resource Provisioning Services
execution management Hardware Profile Services
 Suitable for
Infrastructure
 Development of Enterprise .NET @ Windows Mono @ Linux
Cloud Applications
Physical Machines/Virtual Machines
 Cloud enabling legacy
applications Amazon
Private Cloud Microsoft Google
 Portability for Customer Apps: IBM
 Enterprise ↔ Public Clouds
22
 .NET/Win ↔ Mono/Linux LAN network Data Center
 Aneka as a Cloud Application
Platform

Applications
& Services Application Development

Bag of Tasks Dist. Threads MapReduce …

Cloud Middleware

SLA & QoS User

Platform Application
Management
Management Dynamic
Aneka Provisioning

Scheduling & Monitoring Billing

Execution

Infrastructure
Clusters Public Clouds
Datacenters Desktop PCs

23
 Aneka: components

public DumbTask: ITask

{
…
public void Execute()
Aneka enterprise Cloud
{
…… i=0; i<n; i++)
for(int
{ }
}…
DumbTask task = new DumbTask();
app.SubmitExecution(task); Executor Executor
work units
}

Client
Agent Executor
internet

work units
Scheduler
Aneka Worker
internet
Aneka Manager Service
Executor
Client
Agent
Programming / Deployment Model
Aneka User Agent
24
 Aneka - Dynamic deployment of
Application Tasks on Clouds

 Application

Aneka
Workker/Executor
Aneka Application

Aneka
Manager

Manager / Executor
Aneka Threads

25
 Aneka Support for InterCloud /
Federation of Resource Pools

 XenServer Pool
 Aneka + Xen Server Executors

private Cloud Executor Executor

 VMWare Pool private enterprise

Scheduler

 Aneka + VMWare network

internet
publicly available resources
private Cloud Private
Cloud
(physical and virtual)

Amazon EC2 Pool

Scheduler

 Aneka + public EC2
 Windows Azure Client Libraries
VPN
(virtual resources)
Executors/Schedulers

Public Cloud
 Aneka + public Azure

26
Aneka Case Studies
 (GoFront: A unit of China
Southern Railway Group)
Application: Locomotive design CAD rendering
Aneka Maya Renderer
GoFront Private Aneka
Cloud

Use private
Aneka Cloud
LAN network
(Running Maya Batch Mode on
demand)

Case 2: Aneka
Enterprise Cloud Manjrasoft
Time
(in hrs)

Case 1: Single Server

Raw Locomotive Design Files
(Using AutoDesk Maya) Using Maya
Graphical Mode Single Aneka
Directly
Server Cloud
4 cores Aneka utilizes idle desktops
server (30) to decrease task time
28
from days to hours
 A scalable architecture for TitanStrike on-
line Gaming Portal

The local scheduler TitanStrike Private Aneka

interacts with Aneka Cloud
and distributes the load
Aneka-based in the cloud.
GameController Manjrasoft

LAN network
Case 2: Aneka Enterprise Cloud = Scalability (Running Game plugins on Demand)
Gamers profiles
Players statistics Distributed logs
logs
Team playing
Multiple games
log parsing

Titan Strike On Line

Gaming Portal

Case 1: Single Server = Huge Overload

logs

Centralized
log parsing

Single scheduler
controlling the
execution of all the logs
Single matches.
GameController Game Servers
29
 Indian Space Research
Organization (ISRO) - ADRIN

Distribution
Manjrasoft

Aneka Cloud

Receiving station
processing
Private Cloud Public Cloud
Citrix Xen Archiving Amazon AWS
30
 Health Care: SaaS Cloud for
ECG Sensor Data Analysis
Millions of users

User Requests
A User Wireless ECG Sensor
Embedded Bluetooth
Enabled
Data Processor &
Communication Module

ECG Sensor Module

ECG Data

SaaS
User Requests
1 Analysis
Software
2
Bluetooth connectivity

Dynamic Scalable Runtime

PaaS
User QoS based Scaling of
4 Compute Resources

3
IaaS

Wireless/ Mobile 3G Network

5
6
31
 IEEE Scalable Computing Challenge
at CCGrid 2010 Conference

32
 Global Recognition for Aneka:
Frost, Telstra….

-> 2010 Frost & Sullivan "New

Product Innovation" Award

-> 2011 Telstra Innovation

Challenge, “People’s Choice”
Award

33
 Outline

 “Computer Utilities”
 Vision and Promising IT Paradigms/Platforms
 Cloud Computing and Related Paradigms
 Trends, Definition, Cloud Benefits and Challenges
 Market-Oriented Cloud Architecture
 SLA-oriented Resource Allocation
 Global Cloud Exchange
 Aneka: Cloud Application Platform
 Summary and Thoughts for Future

34
 Summary

 Several Computing Paradigms have promised to

deliver “Computing Utilities” vision:
 Cloud Computing is the most recent kid in the block
promising to turn vision into reality
 Many exciting business and consumer applications
enabled.
 Aneka is rapidly emerging as a platform for:
 Building Clouds (especially “private”) and their apps.
 Accelerating Applications and Managing their
execution.
 Already used in engineering, life science, gaming, and
business intelligence applications.
35
 References

 Quick Overview:
 Rajkumar Buyya and Karthik Sukumar,
Platforms for Building and Deploying Applicatio
ns for Cloud Computing
, CSI Communications, Vol.35, No. 1, Pages:
6-11, ISSN 0970-647X, Computer Society of
India (CSI), Mumbai, India, May 2011.
 Aneka:
 C. Vecchiola, X. Chu, and R. Buyya,
Aneka: A Software Platform for .NET-based Clo
ud Computing
, High Speed and Large Scale Scientific
Computing, 267-295pp, IOS Press,
Amsterdam, Netherlands, 2009.
 Software – download:
 http://www.manjrasoft.com/

Wiley Press, New York, USA,

Feb 2011

36