Grid Computing & Cloud Computing

----by HuJing
----2009.4.10
Progress
Cloud Computing

3
Definition for Cloud computing
 A large-scale distributed computing paradigm that is driven by ec
onomies of scale, in which a pool of abstracted, virtualized, dyna
mically-scalable, managed computing power, storage, platforms,
and services are delivered on demand to external customers over
the Internet. (Ian Foster)
 特点：
 超大规模
 虚拟化
 高可扩展性
 高可靠性
 按需服务
 极其廉价
 通用性
Relation
Grid Computing & Cloud Computing
Grid Computing & Cloud Computing

 Clouds and Grids share a lot commonality in their

vision, architecture and technology, but they also differ
in various aspects such as security, programming
model, business model, compute model, data model,
applications, and abstractions.
 The vision is the same
 reduce the cost of computing;
 increase reliability;
 increase flexibility.
 the problems are mostly the same
 manage large facilities;
 define methods by which consumers discover, request and use
resources provided by the central facilities;
 implement the often highly parallel computations that execute on
those resources.
Business Model
 Traditional business model
 software has been a one-time payment for unlimited use
(usually on 1 computer) of the software.
 Cloud-based business model
 a customer will pay the provider on a consumption basis,
such as electricity, gas, and water, relies on economies of
scale in order to drive prices down for users and profits up for
providers.
 The business model for Grids
 project-oriented in which the users or community represented
by that proposal have certain number of service units (i.e.
CPU hours) they can spend.
Architecture

SaaS
如： Saleforce online CRM 服
务
PaaS
如： Google App Engine

IaaS
如： Amazon EC2/S3/SQS 服
务
Resource Management

 Compute Model
 Grids ：
 batch-scheduled compute model, don’t natively s
upport interactive applications
 Clouds:
 resources being shared by all users at the same
time, allow latency sensitive applications to oper
ate natively
Resource Management

 Data Model
 Internet Computing will be centralized around Data,
Clouding Computing, as well as Client Computing.
Resource Management
 Combining compute and data
management
 Grid
 Data-aware schedulers and dispersing data
close to processors
 Cloud
 data-intensive applications are not typical
applications today,
 as the scales of Clouds grow, it may just be a
matter of time for many Clouds
Resource Management

 Visualization
 Grid
 do not rely on virtualization as much as Clouds
do, each individual organization maintain full
control of their resources
 Cloud
 an indispensable ingredient for almost every
Cloud
Programming Model

 Grid
 MPI, Globus Tookit, WSRF, CoG etc
 Cloud
 MapReduce, Sawzall, Hadoop etc
Application Model
 Grid
 support many different kinds of applications
 HPC (high performance computing )
 HTC (high throughput computing )
 scientific gateways
 Cloud
 in principle cater to a similar set of applications,
except HPC
 adopt gateways to Cloud resources for end-user
interaction
 The browser and Web 2.0 technologies will play
a central role on how users will interact with
Grids and Clouds in the future.
Security Model
 Grid ： stricter
 single sign-on, delegation, privacy etc
 Cloud: simpler, less secure
 create and manage account information for end-use
rs, and allows users to reset their passwords and re
ceive new passwords via Emails in an unsafe and u
nencrypted communication.
 new users could use Clouds relatively easily and al
most instantly, with a credit card and/or email addre
ss
刘鹏：做网格的该如何看待云计算

 网格已经走过了十年历程，大家对它已经
有审美疲劳，新的叫法让人耳目一新，因
而迅速被人接受了。
 我们不要为名称问题所困扰，叫网格计算
也好，叫云计算也好，能够解决问题就好
！
 君不见自从云计算概念提出之后，这种模
式的分布式计算的确得到了空前的发展！
未来 10 年

 科学
Science 2.0
网格计算

 商业
Business 2.0
云计算
 云计算与网格计算将走向融合
Web Application Service Collaboration Services

Datacenter
Infrastructure
Compute Service
Database service

Cloud + Grid
Computing
Job Scheduling Service Catalog

Service Storage service

Computing center
Infrastructure

Storage backup,
Virtual Client Content archive… service
service Classification
Reference
 [1] Ian Foster, Yong Zhao, Ioan Raicu, Shiyong Lu. Cloud Computing an
d Grid Computing 360-Degree Compared. IEEE Grid Computing Environ
ments (GCE08), 31 Dec, 2008
 [2] 刘鹏 , 网格计算与云计算 (PPT), 2009
 [3] 刘鹏 , 做网格的该如何看待云计算 (0.1 版 ),
http://www.chinacloud.cn/show.aspx?id=773&cid=17 , 2009
 [4] ……
Thank you!