See

discussions, stats, and author profiles for this publication at:

https://www.researchgate.net/publication/221276709

Cloud Computing: An
Overview

Conference Paper January 2009

DOI: 10.1007/978-3-642-10665-1_63 Source: DBLP

CITATIONS READS

84 3,308

4 authors, including:

Zhiguo Luo
China Mobile Research Institute
7 PUBLICATIONS 110 CITATIONS

SEE PROFILE

All content following this page was uploaded by Zhiguo Luo on 23 March 2017.

The user has requested enhancement of the downloaded file.

 Cloud Computing: An Overview

Ling Qian, Zhiguo Luo, Yujian Du, and Leitao Guo

53A, Xibianmennei Ave, Xuanwu District, Beijing 100053, China

{qianling,luozhiguo,duyujian,guoleitao}@chinamobile.com

Abstract. In order to support the maximum number of user and elastic service
with the minimum resource, the Internet service provider invented the cloud
computing. within a few years, emerging cloud computing has became the hot-
test technology. From the publication of core papers by Google since 2003 to
the commercialization of Amazon EC2 in 2006, and to the service offering of
AT&T Synaptic Hosting, the cloud computing has been evolved from internal
IT system to public service, from cost-saving tools to revenue generator, and
from ISP to telecom. This paper introduces the concept, history, pros and cons
of cloud computing as well as the value chain and standardization effort.

Keywords: Cloud computing, Cloud Storage, Virtualization.

1 Definitions of Cloud Computing

Similar to e-commerce, cloud computing is one of the most vague technique termi-
nologies in history. One reason is that cloud computing can be used in many applica-
tion scenarios, the other reason is that cloud computing are hyped by lots of compa-
nies for business promotion. From the Hyper Cycle published by Gartner Group in
2008, we can see that the cloud computing is in the phase of fast growing.

Fig. 1. Cloud computing is in the phase of fast growing

M.G. Jaatun, G. Zhao, and C. Rong (Eds.): CloudCom 2009, LNCS 5931, pp. 626631, 2009.
Springer-Verlag Berlin Heidelberg 2009
 Cloud Computing: An Overview 627

In the MIT Centennial talk in 1961, John McCarthy said that The computer
utility could become the basis of a new and important industry, which implied the
underlying concepts of cloud computing. However the cloud computing as a whole
is probably first introduced by Eric Schmidt in his talk on Search Engine Strategies
Conferences in 2006[15].
Now there are lots of definitions and metaphors of cloud computing. From our
points of view, cloud computing is a kind of computing technique where IT services
are provided by massive low-cost computing units connected by IP networks. Cloud
computing is rooted in search engine platform design. There are 5 major technical
characteristics of cloud computing: (1) large scale computing resources (2) high scal-
ability & elastic (3)shared resource pool (virtualized and physical resource)
(4)dynamic resource scheduling and (5) general purpose.

2 History and Status

With the explosion of the Internet, tight pressure is put to the existing storage and
computing facilities. The Internet service providers start to use the cheap commodity
PCs as the underlying hardware platform. Various kinds of software technologies are
invented to make these PCs work elastically, which has led to 3 major cloud comput-
ing styles based on the underlying resource abstraction technologies: the Amazon
style, Google Style and Microsoft style.
Amazons cloud computing is based on server virtualization technology.
Amazon released Xen-based Elastic Compute Cloud (EC2), object stor-
age service (S3) and structure data storage service (SimpleDB)[12] during
the 2006 2007, under the name Amazon Web Service (AWS)[9]. On-
demand and cheaper AWS becomes the pioneer of Infrastructure as a Ser-
vice (IaaS) provider.
Googles style is based on technique-specific sandbox. Google published
several research papers from 2003 to 2006[1-5], which outline a kind of
Platform as a Service (PaaS) cloud computing. The platform, which is
called Google App Engine (GAE), is released to public as a service in
2008.
Microsoft Azure [10] is released in Oct. 2008, which uses Windows Az-
ure Hypervisor (WAH) as the underlying cloud infrastructure and .NET as
the application container. Azure also offers services including BLOB ob-
ject storage and SQL service.
Its hard to judge which one is better, but apparently server virtualization is more
flexible and compatible with existing software and applications; while the sandboxes
put more restrictions on programming languages but less abstraction overhead. Cur-
rently, server virtualization is the most popular resource abstraction technique in
cloud computing.
Except these public cloud services, lots of companies has experimented and/or im-
plemented internal cloud computing systems. Cloud computing is already key strategy
for IT vendors, ISP and telecom service providers. Even further, United States of
America and Japan have made cloud computing the national strategy. The following
table lists some of the adopters for each style.
628 L. Qian et al.

Table 1. Three major cloud computing styles and their adopters, based on the resource abstrac-
tion techniques

Resource Abstraction Tech. Adopters

Server Virtualization Amazon EC2 (Xen), GoGrid (Xen), 21vianet
(Amazon Style) CloudEx (Xen), RackSpace Mosso (Xen),
Joyent (Accelerator), AT&T Synaptic
(Vmware), Verizon CaaS (Vmware)
Technique-specific sandbox GAE (Python & JVM), Heroku (Ruby),
(Google Style) Morph Application Platform(Ruby)
Server Virtualization & Technique- Microsoft Azure (WAH & .NET)
specific sandbox (Microsoft Style)

3 Cloud Computing Architecture

Many organizations and researchers have defined the architecture for cloud comput-
ing. Basically the whole system can be divided into the core stack and the manage-
ment. In the core stack, there are three layers: (1) Resource (2) Platform and (3) Ap-
plication. The resource layer is the infrastructure layer which is composed of physical
and virtualized computing, storage and networking resources.
The platform layer is the most complex part which could be divided into many sub-
layers. E.g. a computing framework manages the transaction dispatching and/or task
scheduling. A storage sub-layer provides unlimited storage and caching capability.
The application server and other components support the same general application
logic as before with either on-demand capability or flexible management, such that no
components will be the bottle neck of the whole system.

OA & M Application
App.

Analytical Transactional Interactive Browsing

Deployment

Configuration Application Capability Components

WebServer AppServer Reporting ESB
Platform

Scheduling
Cache MsqQ Database DW

Performance
Computing Frameworks
Transactional/Dispatching Analytical/Scheduling
Monitor

Fault & logging Virtualized Resource

Server Storage Network
Resource

Virtualization Virtualization Virtualization

Billing

Server Storage Network

Physical Resource

Fig. 2. The Reference architecture

 Cloud Computing: An Overview 629

Based on the underlying resource and components, the application could support
large and distributed transactions and management of huge volume of data. All the
layers provide external service through web service or other open interfaces.

4 Cloud Computing Categories

There are diverse dimensions to classify cloud computing, two commonly used cate-
gories are: service boundary and service type.
* From the service boundarys view, cloud computing can be classified as public
cloud, private cloud and hybrid cloud. The public cloud refers to services provided to
external parties. The enterprises build and operate private cloud for themselves. Hy-
brid cloud shares resources between public cloud and private cloud by a secure net-
work. Virtual Private Cloud (VPC) services released by Google[8] and Amazon[9]
are examples of Hybrid cloud.
* From the service types view, cloud computing can be classified as Infrastructure
as a Service (IaaS), Platform as a Service (PaaS) and Software as a Service (SaaS).
SaaS provide services to end users, while IaaS and PaaS provide services to ISV and
developers - leaving a margin for 3-party application developers.

5 Advantages and Risks

The cloud computing is a Win-Win strategy for the service provider and the service
consumer. We summarize the advantages as below:
9 Satisfy business requirements on demand by resizing the resource occu-
pied by application to fulfill the changing the customer requirements.
9 Lower cost and energy-saving. By making use of low cost PC, customer-
ized low power consuming hardware and server virtualization, both
CAPEX and OPEX are decreased.
9 Improve the efficiency of resource management through dynamic re-
source scheduling.
However there are also some major challenges to be studied.
9 Privacy and security. Customer has concerns on their privacy and data se-
curity than traditional hosting service.
9 The continuity of service. It refers to the factors that may negatively af-
fected the continuity of cloud computing such as Internet problems, power
cut-off, service disruption and system bugs. Followed are some typical
cases of such problems: In November 2007, RackSpace, Amazons com-
petitor, stopped its service for 3 hours because of power cut-off at its data
center; in June 2008, Google App Engine service broke off for 6 hours due
to some bugs of storage system; In March 2009, Microsoft Azure experi-
enced 22 hours out of service caused by OS system update. Currently, the
public cloud provider based on virtualization, defines the reliability of ser-
vice as 99.9% in SLA.
9 Service migration. Currently, no regularity organization have reached the
agreement on the standardization of cloud computings external interface.
630 L. Qian et al.

As a result, once a customer started to use the service of a cloud computing

provider, he is most likely to be locked by the provider, which lay the cus-
tomer in unfavorable conditions.

6 Value Chain of Cloud Computing

The following figure depicts the cloud computing value chain with related organiza-
tions and their functionalities.

Fig. 3. The trunk and supporting value chain of cloud computing

9 Cloud Applications: The driven force of cloud computing, which is different

from traditional application module.
9 Cloud Application Operator: Offers cloud computing products. In many cases,
they are same as by application provider or platform provider.
9 Cloud Application Platform Operator: Provides cloud application and develop-
ment platform, such as GAE and Force.com, etc.
9 Cloud infrastructure operator: Provide infrastructure service, such as AWS
and GoGrid.
9 Network Operator: Provide network access service to the above platform opera-
tors and the end users.
9 Technique supporting vendor: Offer technical support to players in this chain,
including software development, testing, provisioning and operation.
9 Terminal equipment vendor: Offer device maintenance service for all players in
the chain.
9 End Users: End users pays for the cloud services.

7 Standardization
Distributed Management Task Force[7] is an industry alliance composed by over 200
IT related corporations including IBM, EMC, HP, Cisco, Oracle and Microsoft, which
is committed to develop, maintain and popularize the IT management system under
enterprise context. DMTF has published Virtualization Management Initiative and
Open Virtualization Format, and the latter is declared to be supported by major ven-
dors. DMFT founded Open Cloud Standards Incubator at the year 2009, whose aim is
to clarify the interoperability between several cloud systems.
 Cloud Computing: An Overview 631

OGF (Open Grid Forum) has started some work to discuss cloud computing related
standards, which is a standardization organization like IETF aiming at promoting the
standardization and best practice of distribute computing related techniques. CCI-WG
(Open Cloud Computing Interface Working Group) is established to design resource
management API for IaaS cloud services by OGF. Some cloud computing service
providers like ElasticHosts, GoGrid, and FlexiScale have announced to adhere this
API in the later developments.
Besides, SNIA (Storage Network Industry Association), CSA (Cloud Security Alli-
ance) and OCC (Open Cloud Consortium) is now working on cloud storage, cloud
security and cloud intercommunication standards respectively. In order to coordinate
the work of above standardization organizations, OMG (Object Management Group)
appealed that all the organizations maintain their own standards on http://cloud-
standards.org.
PaaS and SaaS dont have related cloud computing standards yet. Most current
systems exploit mature protocols and have variety kinds of service forms.

References
[1] Ghemawat, S., Gobioff, H., Leung, S.-T.: The Google File System. In: SOSP (2003)
[2] Dean, J., Ghemawat, S.: MapReduce: Simplifed Data Processing on Large Clusters. In:
OSDI 2004 (2004)
[3] Chang, F., Dean, J., Ghemawat, S., et al.: Bigtable: A Distributed Storage System for
Structured Data. In: OSDI 2006 (2006)
[4] Burrows, M.: The Chubby lock service for loosely-coupled distributed systems. In: OSDI
2006 (2006)
[5] Pike, R., Dorward, S., Griesemer, R., Quinlan, S.: Interpreting the Data: Parallel Analysis
with Sawzall. Scientific Programming (2005)
[6] Open Cloud Computing Interface, http://www.occi-wg.org/doku.php
[7] Distributed Management Task Force, http://www.dmtf.org
[8] Google App Engine, http://appengine.google.com
[9] Amazon Web Service, http://aws.amazon.com
[10] Microsoft Azure, http://www.microsoft.com/azure/
[11] DeCandia, G., Hastorun, D., Jampani, M., et al.: Dynamo: Amazons Highly Available
Key-value Store. In: SOSP 2007 (October 2007)
[12] Schmidt, E.: Conversation with Eric Schmidt hosted by Danny Sullivan. In: Search En-
gine Strategies Conference (August 2006)

View publication stats