2. Introduction: A Golden Era in
Computing
Powerful multi-
core processors
General
purpose graphic
processors
Superior software
methodologies
Virtualization
leveraging the
powerful
hardware
Wider bandwidth for
communication
Proliferation of
devices
Explosion of
domain
applications
2
3. Evolution of Internet Computing
Publish
Inform
Interact
Integrate
Transact
Discover
(intelligence)
Automate
(discovery)
time
scale
Social
media
and
networking
Semantic
discovery
Data-intensive
HPC, cloud
web
deep web
Data
marketplace
and
analytics
3
4.
5. Challenges
• Alignment with the needs of the business / user / non-
computer specialists / community and society
• Need to address the scalability issue: large scale data, high
performance computing, automation, response time, rapid
prototyping, and rapid time to production
• Need to effectively address (i) ever shortening cycle of
obsolescence, (ii) heterogeneity and (iii) rapid changes in
requirements
• Transform data from diverse sources into intelligence and
deliver intelligence to right people/user/systems
• What about providing all this in a cost-effective manner?
5
6. It is a changed world now…
• Explosive growth in applications: biomedical informatics, space
exploration, business analytics, web 2.0 social networking: YouTube,
Facebook
• Extreme scale content generation: e-science and e-business data deluge
• Extraordinary rate of digital content consumption: digital gluttony: Apple
iPhone, iPad, Amazon Kindle
• Exponential growth in compute capabilities: multi-core, storage,
bandwidth, virtual machines (virtualization)
• Very short cycle of obsolescence in technologies: Windows Vista
Windows 7; Java versions; CC#; Phython
• Newer architectures: web services, persistence models, distributed file
systems/repositories (Google, Hadoop), multi-core, wireless and mobile
• Diverse knowledge and skill levels of the workforce
• You simply cannot manage this complex situation with your traditional IT
infrastructure
6
7. The cloud
• Cloud computing is the delivery of Internet-based computing
services, whereby shared resources, software and information are
provided to computers and other devices on-demand.
• Cloud Computing is a general term used to describe a new
class of network based computing that takes place over the
Internet,
– basically a step on from Utility Computing
– a collection/group of integrated and networked hardware,
software and Internet infrastructure (called a platform).
– Using the Internet for communication and transport
provides hardware, software and networking services to
clients
7
8. • It is a paradigm where computing resources are available
when needed, and you pay for their use in much the same
way as for household utilities
• It allows users to access resources and services on-demand,
without the need for physical infrastructure or local servers.
• These platforms hide the complexity and details of the
underlying infrastructure from users and applications by
providing very simple graphical interface or API (Applications
Programming Interface).
9. • In addition, the platform provides on demand services, that are always on,
anywhere, anytime and any place.
• Pay for use and as needed, elastic
– scale up and down in capacity and functionalities
• The hardware and software services are available to
– general public, enterprises, corporations and businesses markets
10. • The NIST Definition of Cloud Computing
• Cloud computing is a model for enabling ubiquitous, convenient, on-
demand network access to a shared pool of configurable computing
resources (e.g., networks, servers, storage, applications, and services) that
can be rapidly provisioned and released with minimal management effort
or service provider interaction.
• In the term 'cloud computing,' the word 'cloud' refers to the provider or
the service provider that offers services over the Internet, while
'computing' refers to the processing, calculations, or various resources
provided by the computer.
• In layman's terms, the cloud refers to a network of remote servers that
allow users to store, manage, and access data and applications over the
internet.
12. • The promise of cloud computing is to deliver all the functionality of
existing information technology services (and in fact enable new
functionalities that are hitherto infeasible) even as it dramatically reduces
the upfront costs of computing that deter many organizations from
deploying many cutting-edge IT services.
• Cloud computing represents a convergence of two major trends in
information technology —
a) IT efficiency, whereby the power of modern computers is utilized
more efficiently through highly scalable hardware and software
resources and
b) business agility, whereby IT can be used as a competitive tool through
rapid deployment, parallel batch processing, use of compute-
intensive business analytics and mobile interactive applications that
respond in real time to user requirements.
13. Common Characteristics
• Scalability: Infrastructure capacity allows for traffic spikes and minimizes
delays.
• Resiliency: Cloud providers have mirrored solutions to minimize downtime
in the event of a disaster. This type of resiliency can give businesses the
sustainability they need during unanticipated events.
• Homogeneity: No matter which cloud provider and architecture an
organization uses, an open cloud will make it easy for them to work with
other groups, even if those other groups choose different providers and
architectures.
• Geographic Distribution
• Virtualization
• Low Cost Software
• Service Orientation
• Advanced Security
15. On-Demand Self-Service
• Consumers must be able to obtain cloud services – at the
infrastructure, platform, or application level – whenever they want,
without requiring significant assistance.
• Often, these services must be paid for. In some situations,
particularly with private cloud, payment is not needed.
16. • Although the concept of cloud computing gives the illusion of
infinite resource, clearly this in reality does not exist, and most
certainly does not exist for all consumers at the same point in time.
• How well providers are able to forecast demand, and how efficient
they are at provisioning their services, are fundamental to their
ability to meet consumer expectations and service levels.
• Providers typically set usage limits in line with their ability to
provision resources and with a buyer’s credit worthiness.
• They may determine that usage requests that require a large
amount of application or infrastructure resource, or that cost more
than a set amount, are subject to minimum notice, pre-
reservations, or additional financial vetting.
• On-demand access: Pay-as-you-go, no upfront commitment and anyone
can access it
17. Broad network access
• Cloud services are accessible over the internet via standard
protocols and devices.
• The user of a cloud service or added service might have a PC or a
tablet, a PDA, or a mobile phone.
• These could have browsers or be browser-less devices. Or the cloud
services could be integrated into a consumer enterprise’s IT
architecture, with access from large and sophisticated computer
systems.
18. • The cloud services must be accessible through standardized
mechanisms. This introduces an important consideration for all
cloud implementations – the use of standards.
• Commercial companies generally want maximum market access.
The greater the accessibility of their services, the greater is the
potential for sales.
19. Resource pooling
• The provider’s computing resources are pooled to serve multiple
consumers using a multi-tenant model, with different physical and
virtual resources dynamically assigned and reassigned according to
consumer demand.
• There is a sense of location independence in that the customer
generally has no control or knowledge over the exact location of the
provided resources.
• Examples of resources include storage, processing, memory,
network bandwidth, and virtual machines..
20.
21. • Multi-tenancy means that a single instance of a computing resource
serves multiple client organizations providing a separate environment for
each.
• Having them in diverse locations means that services can be maintained in
the event of loss of a data center, of power, or of network connectivity.
• From the user’s point of view, it can be hard to distinguish a multi-tenant
application from a single-tenant application running on a multi-tenant
platform, or to distinguish a multi-tenant platform from a single-tenant
platform running on multi-tenant infrastructure.
23. Rapid elasticity
• One of the key benefits of cloud computing is the ability to have a flexible
computing service which can expand or contract in line with business
demand.
• Elasticity has three major features:
• Linear scaling: The performance experience for one of a thousand
users is the same as for a single user.
• On-demand utilization: Allocation of virtual resources follows the
demand profile exactly, so that the user appears to have 100%
utilization of the service.
• Pay-as-you-go: Payment for IT resources is on a per-use basis using an
OPEX style charging principle. This means that the asset ownership is
with the service provider, and the user pays for consumption of the
service on the basis of the resource units consumed.
24.
25. • Resource pooling helps providers to achieve elasticity. A resource that is
no longer needed by one consumer can be allocated to another consumer
that needs more resources.
• Consumers must understand how elasticity is provided and how different
usage levels are priced, in order to exploit this characteristic to best
advantage.
• Pricing can be complex, and can vary widely between suppliers. Use of
applications that provide the same function may be charged by
transaction, by number of users, by data quantity, or by infrastructure
consumed.
• Pricing of infrastructure resources may take into account factors such as
virtual machine size, memory and disc size, and network usage.
26. Measured service
• Cloud systems automatically control and optimize resource use by
leveraging a metering capability at some level of abstraction
appropriate to the type of service (e.g., storage, processing,
bandwidth, and active user accounts).
• Resource usage can be monitored, controlled, and reported,
providing transparency for both the provider and consumer of the
utilized service.
• Consumers require sufficient measurements from their cloud
computing service providers to enable them to make purchasing
and operational judgments.
• Usage of different components may need to be measured
separately.
27. What is the purpose and benefits?
• Cloud computing enables companies and applications, which are
system infrastructure dependent, to be infrastructure-less.
• By using the Cloud infrastructure on “pay as used and on demand”,
all of us can save in capital and operational investment!
• Clients can:
– Put their data on the platform instead of on their own desktop
PCs and/or on their own servers.
– They can put their applications on the cloud and use the servers
within the cloud to do processing and data manipulations etc.
28. “A Cloudy History of Time”
1940
1950
1960
1970
1980
1990
2000
Timesharing Companies
& Data Processing Industry
Grids
Peer to peer systems
Clusters
The first datacenters!
PCs
(not distributed!)
Clouds and datacenters
2012
28
32. “A Cloudy History of Time”
1940
1950
1960
1970
1980
1990
2000
2012 Clouds
Grids (1980s-2000s):
•GriPhyN (1970s-80s)
•Open Science Grid and Lambda Rail (2000s)
•Globus & other standards (1990s-2000s)
Timesharing Industry (1975):
•Market Share: Honeywell 34%, IBM 15%,
•Xerox 10%, CDC 10%, DEC 10%, UNIVAC 10%
•Honeywell 6000 & 635, IBM 370/168,
Xerox 940 & Sigma 9, DEC PDP-10, UNIVAC 1108
Data Processing Industry
- 1968: $70 M. 1978: $3.15 Billion
First large datacenters: ENIAC, ORDVAC, ILLIAC
Many used vacuum tubes and mechanical relays
Berkeley NOW Project
Supercomputers
Server Farms (e.g., Oceano)
P2P Systems (90s-00s)
•Many Millions of users
•Many GB per day
32
33. Quiz: Where is the World’s Largest
Datacenter?
• Largest by square footage – China Telecom: total square footage of 10.7
million square foot
• Largest by power consumption – The Citadel Campus: 650 megawatts
• Largest for a single company – Meta, Prineville: 3.8 million square foot
• Largest government data center – NSA Bumblehive: 1.1 million square feet
33
34. What does a datacenter look like
from inside?
• A virtual walk through a datacenter
• Reference:
https://datacenters.microsoft.com/globe/explore/datacent
er
34
36. Power
Off-site
On-site
•WUE = Annual Water Usage / IT Equipment Energy (L/kWh) – low is good
•PUE = Total facility Power / IT Equipment Power – low is good
(e.g., Google~1.1)
36
37. Cooling
Air sucked in from top (also, Bugzappers) Water purified
Water sprayed into air 15 motors per server bank
37