Introduction to Grid Computing
Max Planck Institute for
What is the Grid.
What does the Grid mean for application users?
What is a Virtual Organization?
Why is the Grid different from the Internet?
What should application users and developers be
doing right now to be ready for the Grid?
High level overview of today’s testbeds.
Grid Intro 2
History and Motivation
1970s - 80s: Internet
Email, ftp, etc
1980s - 90s: Remote-, Distributed-, Meta-computing
Beginning to think of ways to exploit distributed resources
US SC Centers Programs
– Had to access remotely
– Think of harnessing together
See examples later
First large scale experiments
Most failed, but I-Way a success!
Post I-Way: The Grid
Explosion of activity, but still immature. Get prepared for
Grid Intro 3
Grid Computing: A New Paradigm
Computational Resources Scattered Across the World
Compute servers (double each 18 months)
QuickTime™ and a
Photo - JPEG decompressor
are needed to see this picture.
Networks (double each 9 months)
Playstations, cell phones etc…
How to take advantage of this for
Harness multiple sites and
Simulations at new level of QuickTime™ and a Photo decompressor are ne eded to see this picture.
complexity and scale, interacting
Grid Intro 4
Grid vs. Internet/Web Services?
We’ve had computers connected by networks for
We’ve had web services for 5-10 years
The Grid combines these things, and brings
Infrastructure to enable computation to be carried
out across these
– Authentication, monitoring, information, resource discovery,
status, coordination, etc
Can I just plug my application into the Grid?
No! Much work to do to get there!
Grid Intro 5
Components for Grid Computing
All have to work for real applications
Teams with a need to share data, or develop common code
Communities can be very diverse
Experimentalists, computer scientists, simulation scientists, network
All may need to work together to solve a specific problem
May co-develop a code, or contribute modules that should work
These communities may have very different resources
Within company or university
Across the world
Grids aim to bring them together, allow them to harness their
These communities may form a type of (virtual) organization
Grid Intro 6
Machines, networks, archives, file systems, etc at different sites
What is a Virtual Organization (VO)?
groups of organizations that use the Grid to share resources for
– EU DataGrid, Alliance, TeraGrid, SC02 Global Grid Testbed, etc
Typically deploy same technology
Deploy directory service: resources registered, and may be
“discovered”. Globus has MDS (Monitoring and Discovery Service)
– GIIS (Grid Index Information Service) provides info for entire VO
– GRIS (Grid Resource Information Service), installed locally, reports to
GIIS so people or applications can search GIIS for info
Authentication: Certificates and Gridmap file
– Sometimes a VO offers a “certificate” for individuals and resources
– Sometimes they use other VO’s certificates
So far, there is no Global GIIS that links together all VOs
Grid Intro 7
Infrastructure: Globus Metacomputing Toolkit
Fundamental technologies needed to build computational grids.
Security: logins, data transfer
Information (GRIS, GIIS)
More generally: Grid Services
Application Monitoring systems
We focus today on Globus, Cactus, and GridLab
Other: Legion, Unicore, Juxta…
Grid Intro 8
Components for Grid Computing
Grid Aware Applications (Cactus example):
Grid Enabled Modular Toolkits for Parallel
Computation: Provide to Scientist/Engineer, etc..
Plug your Science/Eng. Applications in!
Must Provide, Register as Grid Services
Ease of Use: automatically find resources, given need!
Distributed simulations: use as many machines as needed!
Remote Viz and Steering, tracking: watch what happens!
Take advantage of infrastructure
Collaborations of groups with different expertise: no
single group can do it! Grid is natural for this…
Grid Intro 9
Ten machines in Europe for developers of Grid tools
SC2001 ARG Testbed & Global Grid Testbed Collaboration
Hastily assembled loose federation of world machines for SC2001
and now SC2002 demonstrations
NCSA Virtual Machine Room and PACI Grid
USA distributed terascale facility at 4 sites for open scientific
Information Power Grid (www.ipg.nasa.gov)
NASAs high performance computing grid
Grid Intro 10
NSF PACI Grid
Grid Intro 11
The NSF TeraGrid
13.6 Tflop facility
Some Grids are tightly coupled facilities, like TeraGrid
Some are testbeds, like Global Grid Testbed Collaboration
Some are long term, loosely coupled: PACI Grid (includes TeraGrid)
All try to provide organized access to distributed resources
Most are depending on Globus as the base infrastructure
Grid Intro 12
What does this mean now for
users and developers?
There is a grand vision of the future
Collecting resources around the world into Vos
Seamless access to them, with a single signon
NEW applications to exploit of them in unique ways!
Today we want to help you prepare for this
There is a frustrating reality of the present
These technologies are not yet fully mature
Not fully deployed
Not consistent across even single Vos
But centers and funding agencies worldwide are pushing
this very, very hard
Better get ready now
You can help! Work with your centers to get this deployed
Grid Intro 13
Getting Ready for the Grid
Need to start imagining how your applications
can exploit the Grid (simplify use of HPC,
provide more processing power, better access to
data, allow new scenarios to forward your
science, better collaborations).
Applications codes will need modifications for
the Grid, depending on much of it you want to be
able to exploit!
Write new codes with the Grid in mind.
Consider using frameworks which are already
Grid Intro 14