Draft Version 4
Over the past decade, the field of Grid computing has seen a lot of hype of
activity. The term “Grid computing”
attributed to Ian Foster, who created a
point checklist to define a “Grid” as follows
. A Grid:
Coordinates resources that are not subject to centralized control. A grid
integrates and coordinates resources and users that live within differen
for example, different administrative units of the same
company, or even different companies. A grid addresses the issues of
security, policy, payment membership, and so forth that arise in these
Uses standard, open, general
purpose protocols and interfaces. A grid is
built from multi
purpose protocols and interfaces that address such
fundamental issues as authentication, authorization, resource discovery,
and resource access. It is important that these protocols and interface
standard and open. Otherwise, we are dealing with application, hardware,
Delivers nontrivial qualities of service. A grid should be transparent to the
end user, addressing issues of response time, throughput, availability,
urity, and/or co
allocation of multiple resource types to meet complex
user demands. The goal is that the utility of the combined system is
significantly greater than that of the sum of its parts.
world grids exhibit one or more of the above p
in practice, it
can be often observed that none of the so
called grid systems satisfy all of the
above requirements to qualify as a true Grid system. For instance, the TeraGrid
performance computers, data resources
and tools, and high
end experimental facilities
at 11 partner sites
. The TeraGrid satisfies requirements 1 and 2 above, but it is debatable
how much it satisfies requirement 3, if at all.
The TeraGrid coordinates resources
across the individual partner sites, which define the local policies and
administrative setup. And w
ith the help of the Open Grid Services Architecture
Web service concepts and technologies are being used to
satisfy the second requirement.
allocation of multiple
resources across various administrative domains and
scheduling remains a
for all practical purposes, users
and are fully
being used for their applications
In the industry, the term Grid computing is often used
In fact, most
in the past and present
(e.g. Oracle Grid, Sun Grid, etc.)
enable access to resources that are subject to centralized
and do not use any standard, open, general
Grids relied heavily o
n virtualization to create a pool of assets to distribute
In many ways, this looser definition of Grid computing in the
industry and the resulting
technologies to support the same
have led to the
evolution of Cloud Computing
Several definitions for Cloud Computing
can be found on the Internet.
and Company [McK09] define Clouds as hardware
based services that offer
computer, network and storage capacity, where
ent is highly
abstracted from the buyer, buyers incur infrastructure cost as variable
Operational Expenditure (
, and where infrastructure cost is highly elastic
(up or down).
They define the following characteristics of clouds:
Enterprises incur no in
frastructure capital costs, just operational costs on a
Architecture specifics are abstracted
Capacity can be scaled up or down dynamically, and immediately
The underlying hardware can be anywhere geographically
In [AMBR09], the authors
define Cloud Computing as both applications delivered
as services over the Internet
, and the hardware and software in the datacenters
that provide those services. They view Cloud Computing as a sum of Software as
a Service (SaaS) and Utility Computing, whi
ch is defined as when such a service
is sold (in possibly, a pay
They emphasize three aspects of
Cloud Computing from a hardware point of view:
The illusion of infinite computing resources available on demand
The elimination of up
commitment by Cloud users
The ability to pay for use of computing resources on a short
term basis as
The difference between the two definitions above is that the abstraction of
infrastructure is explicitly emphasized in [McK09], whereas it is impl
[AMBR09]. Additionally, [McK09] differentiates “Cloud services” from Clouds as a
service where the underlying infrastructure is abstracted and can scale elastically
in other words, it views Clouds as mostly abstractions for hardware.
Institute of Standards and Technology (NIST)
Cloud Computing as a model for enabling convenient,
access to a shared pool of configurable computing resources (e.g., networks,
servers, storage, applications, and services)
that can be rapidly provisioned and
with minimal management effort or service provider interaction
ive essential characteristics:
demand self service
A consumer can unilaterally provision computing
capabilities, such as server
time and network storage, as needed
automatically without requiring human interaction with the service
Ubiquitous network access
Capabilities are available over the network
and accessed through standard mechanisms that promote use by
ous thin or thick client platforms (e.g., mobile phones, laptops,
The customer generally has no
control or knowledge over the exact location of the provided resources.
The service provider assigns different
physical and virtual resources
dynamically according to consumer demand.
Capabilities can be rapidly and elastically provisioned to
quickly scale up and rapidly released to quickly scale down.
Cloud systems automatica
lly control and optimize
resource use by leveraging a metering capability at some level of
abstraction appropriate to the type of service.
This definition is very similar to the two definitions above, except that it
emphasize one more key aspect of Cloud
Computing, which is an ability for a
to unilaterally provision computing capabilities, as needed
automatically without requiring human interaction with each service’s provider.
as a style of computing wher
massively scalable IT
related capabilities are provided “as a service” using
Internet technologies to multiple external customers
several delivery models exist for
, as defined in
Software as a Service
: Delivery of an application that leverages
at the back
end, e.g. Google Mail, Facebook, etc.
Platform as a Service
: Delivery of a “platform” and/or solution
stack as service
using programming languages and tools supported
, e.g. the Google AppEngine.
Infrastructure as a Service
networks, and other fundamental computing resource as a service
Amazon Elastic Compute Cloud (EC2)
Network (SDN), etc.
also have several deployment models
Private: The cloud infrastructure is operated solely for one organization.
This does not imply that it is managed or located within the same
in fact, it can
be managed by a 3
party and located
The cloud infrastructure is shared by several organizations,
which share common concerns.
The cloud infrastructure is made available to the general public,
and is own by an organization se
lling cloud services.
The cloud infrastructure is a composition of two or more
deployment models above.
Irrespective of however Cloud computing is
the consensus is that
Clouds enable a utility or pay
go model without
an upfront commitment to
or human intervention on the part of the service provider
use of virtualization is also
accepted as a de facto norm for providing
based infrastructure and services.
Finally the illusion of elasticit
resources are available on demand, and can be scaled up or down eliminates the
need for Cloud Computing users to plan ahead for peak loads.
Many have said that Cloud computing is just Grid computing
a lot of ways, it delivers o
n the promise of Grid computing addressing the
requirement for non
trivial qualities of service.
However, it is important to note
that the problem domains addressed by Grid and
Cloud computing are
different, at least at the time of writing th
is mostly designed for a smaller number of users in the high performance
computing community, who need exclusive access to a large number of
resources at once. On the other hand, Cloud computing supports a large number
concurrently, each of
access to a small portion of the
resources. The above requirement is often manifested in the way people access
For instance, Grid users typically use a batch queuing system
to submit jobs, and may wait for th
eir jobs for an unspecified amo
unt of time.
Cloud users require and gain access
to resources on
illusion of infinite elastic resources.
There is also a concern that Cloud resources may not be appropriate for high
ng applications due the heavily virtualized nature of the
In [WALK08], the authors concluded t
hat a performance gap exists
between performing HPC computations on a traditional scientific cluster and on
an EC2 provisioned cluster. The performance
gap is seen not only in the MPI
performance of distributed memory parallel programs, but also in the single node
OpenMP performance for shared
memory parallel programs.
Some of the other obstacles in the growth of Cloud Computing listed in
Availability and service up
in, because of which consumers can’t easily transfer their data
from one site to another
Data confidentially and auditability on the Cloud
Data transfer bottlenecks on the edges of the Cloud
Unpredictability of pe
no upfront cost, and infinite capacity and elasticity on
scale distributed systems
Rapid scaling, up and down
Reputation fate sharing between a rogue user and a Cloud provider, and
Cloud Computing can be thought of as an evolution of Grid computing, delivering
on its promise of non
trivial qualities of service. Although it may not yet be
suitable for all classes of applications, it provides an
illusion of infinite computing
resources that can scale up and down, where users can pay for use of resources
as needed (pay
go), thus eliminating the up
front infrastructure capital
For the purposes of this document, we will adopt the NIST v
iew of Cloud
Computing as the definitive definition.
Various scenarios for the use of Cloud Computing at the University of California
may be possible.
UC may itself build its own “
where it may limit access to its resources
to UC staff and students.
an enterprise Cloud such as Amazon EC2 as an overflow service.
] M. Armbrust et al. “Above the Clouds: A Berkeley View of
”. Technical Report No. UCB/EECS
I. Foster. “What is the Grid: A Three Point Checklist”.
Gartner Newsroom. "Gartner Says
Will Be As
Influential As E
IBM Corporation. “Grid Computing: Past, Present and Future. An
McKinsey & Company. “Clearing the air on
NIST Working Definition of Cloud Computing v14,
The Open Grid Services Architecture.
E. Walker. "Benchmarking Amazon EC2 for high
scientific computing". In ;login: online.