Fresh off last week's Reference Model for enterprise Grids release,
Paul Strong, chairman of the EGA technical steering committee and
systems architect at Sun Microsystems, spoke with GRIDtoday editor
Derrick Harris about what people can expect to find within its pages,
how it will help clear up confusion among those in the Grid space and
how the alliance's first deliverable will "serve as proof of the intent
and value of the EGA."
What, exactly, is the Reference Model? How can interested parties go about viewing it?
The Reference Model is the Enterprise Grid
Alliance's (EGA) first technical output, and as such it forms the
foundation for the work being undertaken by our other working groups
and serves as a basis for collaboration with other stakeholders in the
enterprise Grid space, such as enterprise users, other standards
bodies, vendors and systems integrators. It is composed of a glossary,
a simple model and a set of use cases that capture the requirements for
enterprise Grid computing. Like the EGA, the Reference Model is both
vendor-neutral and technology agnostic. It is a living document that
will evolve as the enterprise Grid technology landscape does,
continuing to deliver relevant information to the enterprise Grid
community. Anyone can download a copy from the EGA's Web site which can
be found at www.gridalliance.org
Can you describe, in some detail, the three main components
(lexicon, model, use cases) and give some examples of what can be found
The glossary provides a small reference of terms that
ensures there is a common understanding of enterprise Grid computing
terminology. We defined terms such as "enterprise Grid computing,"
"Grid component," "utility computing," "virtualization" and "scale
out," etc., and related them to each other to help alleviate the
confusion surrounding them. In general, we seek to define only what
needs defining. We tried not to define terms that are already well-used
and clearly understood.
The model, a significant portion of the document, serves as a resource
to help describe enterprise Grids. It consists of a small set of simple
objects, relationships and verbs/actions that allow the complexity
inherent in enterprise Grids to be easily represented and categorized.
For example, rather than define the enterprise Grid in terms of
services and resources, we define it in terms of a unit of an object of
management, the Grid component. The Grid component could be something
as concrete as a server or disk, or as abstract as a CRM or ERP
application. Grid components have a life cycle, they get provisioned,
managed, monitored and finally decommissioned. The model is technology
agnostic in that it does not assume a great deal about the technology
that is used in building an enterprise Grid. Thus, it can be used to
describe existing data centers, as well as current and future
enterprise Grids. The model itself then provides a context for the use
cases, as well as for comparing various Grid technologies, products and
Lastly, the use cases illustrate a few generic and specific scenarios
within an enterprise Grid. The goal of the EGA is to drive the adoption
and deployment of Grid technologies in the enterprise. In order to
achieve this, the various standards and products delivered in this
space must address a common set of data center requirements and
inhibitors to adoption. Use cases are how we do this, and this
collection represents the first phase of our work in this area. These
serve as a feedback mechanism for enterprise users to ensure that
vendors and standards bodies understand their needs.
How badly was the Grid market in need of this Reference Model?
Clearing up the confusion around terminology and
providing a simple model that allows the comparison of value delivered
by Grid products and solutions is key to driving the adoption of Grid
in the enterprise data center. If people don't understand Grid, Grid
architectures and Grid technologies within the context of their own
data centers and data center processes, such as ITIL or eTOM, then
they're unlikely to adopt them. The Reference Model addresses this, or
at least it starts to, and, thus, we feel that it fills a big gap for
the industry, as well as complementing the valuable work being
undertaken in other bodies, especially the Global Grid Forum, the DMTF
and SNIA. It is more sharply focused on the data center than other Grid
architectural work has been to date, yet it captures more of the
abstract components and their life cycles than perhaps some of the
component centric information models do today.
Actually, if we continue the previous thread on focus, another area
where we felt this work was needed was in driving the needs and
requirements of enterprise data centers into the Grid community. Some
of the needs of an enterprise are significantly different to those
within the community where Grid had its origins. Specifically, a focus
on guarantees for mission-critical applications and on leveraging the
Grid for a variety of workloads, including traditional mixed
transactional (OLTP) and batch workloads, Web services and Service
Oriented Architectures (SOAs), as well as compute intensive workloads.
Enterprises find the potential economies of scale and agility offered
by Grid architectures and Grid technologies (e.g., virtualization,
abstraction and automation) very compelling. The Reference Model use
cases allow us to articulate those needs and to share them with the
Grid community at large and the various standards bodies specifically,
so that our collective output realizes that potential.
How will it help to define enterprise Grid standards?
Although the Reference Model was not developed to define
enterprise Grid standards per se, we hope that it will help drive a
consistent set of standards that meet the needs of enterprise users and
drive the adoption of Grid technologies. This is the specific purpose
of the use cases. Standards are clearly critical to enabling
interoperability and thus extracting the maximum value from the
inherently heterogeneous data centers we see today.
How does the Reference Model address Web services -- an
issue that has sparked some confusion among various parties involved
with Grid computing?
As it stands, the Reference Model makes no assumptions
about how an enterprise Grid will be implemented. It allows the
abstract representation of an enterprise Grid. Indeed, it can be used
when describing a non-Grid data center infrastructure as well. This is
particularly useful in that it provides a context for understanding the
potential value of a chosen means of implementation, such as Web
services, without presuming it. Obviously, it is likely that Web
services are going to play a major part in realizing enterprise Grids,
but the model is a model, not a prescriptive architecture. Other EGA
working groups will no doubt focus more on this issue when addressing
the key areas of adoption or inhibitors to adoption.
Personally, and for the EGA as a whole, how does it feel to
finally have concrete evidence of the work being done by EGA members in
the various working groups?
I have to say that we are very pleased with being able
to make the first of our deliverables available. This work reflects the
consensus and contributions of 20 individuals representing the various
EGA member organizations. A real team effort. As our first deliverable,
the Reference Model in some ways sets the standard for the work that
will follow, and which is already underway, from the other EGA working
Does the announcement of the Reference Model help to legitimize the EGA to any skeptics?
I think the Reference Model will serve as proof of the
intent and value of the EGA. We bring a clear focus on the issues
around deploying Grid in enterprise data centers and we seek to resolve
those through collaboration. The EGA is in many ways not a traditional
standards body. Only as a last resort do we expect to develop our
own standards. In the general case, we will seek to encourage the
development and adoption of appropriate existing standards, and if
these do not exist, we will in the first instance seek to find a body
whose natural role it is. The work being undertaken in other EGA
working groups, using and building on the reference model will continue
Is the EGA working with the Globus Consortium in any capacity? If so, how?
We are constantly communicating with other Grid
stakeholder organizations, like the Globus Consortium, to build
relationships and establish a framework for collaboration to ensure
that their output meets the needs of the enterprise. Univa, the company
formed by a number of the key luminaries in the Grid field with the
express purpose of using Globus open source software to transform
enterprise IT infrastructures, is a member of the EGA and is highly
aligned with our goals. I think that this is indicative of the
inclusive and collaborative nature of what the EGA is doing. Expect to
see more announcements on collaboration as we move forward.
Back to the Reference Model -- what kind of effect will it
have on Grid adoption? Will it directly or indirectly affect the EGA's
The Reference Model serves as both an aid to Grid
adoption today and as the foundation for much of the EGA's work going
forward. So it directly impacts our ability to meet our goals -- in a
very positive way of course.
The Reference Model provides a clear context and understanding of this
space enabling enterprise users to determine the applicability of Grid
architectures and technologies, while helping them compare products and
solutions. This is key to driving adoption today. Sharing the
requirements enumerated in the Reference Model serves the EGA and
enterprise Grid stakeholders in the medium to long term by driving
consistent and relevant standards and products. Again, something that
clearly meets our goals.
Finally, what else is going on with the EGA? Can we expect
to see results emerging from other working groups in the near future?
If so, what kind of announcements can we expect?
All of our working groups are working hard to address
specific areas where technology is evolving or where there are known
obstacles. Specifically, we have two groups looking at server and data
provisioning. We have a group looking at security in enterprise Grids,
exploring what is different in terms of requirements versus those of a
more traditional data center. Grids will have a very dynamic nature,
since resources are shared. For example, when two application
components share an operating system or when a resource is repurposed
over time, there are important ramifications with respect to security.
Finally, we have a group looking into utility accounting. In many
cases, the services that enterprise Grids will host or deliver will
almost certainly be offered in a pay per use or value basis. Both of
these needs set requirements for telemetry, billing and accounting. The
Reference Model serves as the foundation for all of these working
groups, plus others we may create in the near future. e expect to
announce additional deliverables from these groups in the next 9-12
Anything to add?
Nothing, other than to thank you for affording me the
opportunity to talk about the EGA Reference Model, and to encourage
folks to get their organizations to join the EGA and help us in our