April 25, 2005
Industry, Academia Meet on the Grid
** This is the first in a short series of
articles commissioned by GRIDtoday and CERN on scientific and academic
Grid projects, and how they might be relevant to commercial and
Industrial uses of Grid computing. The series will be accompanied by a
more formal overview of academic and scientific Grid projects that will
be published at a later date.
Grid computing has been the buzzword in computing circles for some time
now, and the Internet is awash with pronouncements on how it will
change the future of networking. Both industry and academia have
invested heavily in developing Grid technology, but the commercial
sector has been struggling to identify end users for its new systems.
This in part reflects the wide range of activities that can be
clustered under the Grid umbrella, from cycle scavenging on the
SETI@home model to processing petabytes of data on distributed but
dedicated machines in a "data Grid." But even without a clear customer
base, commercial development of Grids might have been generated by
purely commercial factors, with companies feeling that they must be
seen to be involved in a new field, even if they have little immediate
idea of how they will sell it.
Commercial uncertainty strikes a sharp contrast to academia's hunger
for the Grid. While some computer scientists might carry out
development for its own sake, the emergence of many large-scale Grid
projects across the world has been in no small part driven by need.
Perhaps the clearest example of this is the international effort to
build a Grid for analyzing data from CERN's next-generation particle
accelerator, the LHC (Large Hadron Collider). This Grid, called the LCG
(LHC Computing Grid), is vital for analyzing the predicted 15 petabytes
of data the accelerator will produce annually after it is turned on in
2007. In parallel, both the United States and Europe are building
large-scale infrastructures for their scientific communities, both
field-specific and general e-Science Grids.
While it can be argued that cooperation between industry and academia
would benefit both parties, such ventures have not always gone well,
and are burdened by differences of pace, regulation and work
environment. Now, it seems that the Grid might provide a more
appropriate meeting point for these traditionally antipathetic
hemispheres of IT development.
EGEE (Enabling Grids for E-sciencE), is a large-scale e-infrastructure
project designed to provide a 24/7 Grid service for scientists under
the EU's Information Society Technologies program. Interconnected with
LCG, this project's infrastructure comprises academic and research
institutions spread across 31 countries. However, like all EU programs,
it also has an obligation to support technology transfer to industry.
As a result, it has made efforts in several areas to facilitate
interaction with commercial IT companies, including an Industry Forum
to garner feedback on their work. Perhaps more surprisingly, one of the
project partners is a commercial company.
CGG, Compagnie General de Geophyisique, is a French company providing
geophysical services and products, mostly for the oil and gas industry.
It joined EGEE, but, rather than becoming a sponsor, chose to become an
integral part of the project, with responsibility for European Grid
support, operation and management. CGG was already interested in Grid
computing prior to EGEE, as its business model requires it to process
large amounts of seismic data.
"Typically, a survey is around 10TB, and the dataset becomes 10 times
larger when processed," said CGG software development manager Dominique
Thomas. "We also carry out several surveys in parallel, so, typically,
we have around 1.5 petabytes of disk storage at any one time and
several petabytes near line."
While still some way short of the data mass the LHC will produce, this
is still a considerable amount for a single company to deal with and,
as Thomas explained, it is still increasing. "We need to double our
computing power every year, and we are already at the limit of our
computing room. We've been pioneers in cluster computing since 2000.
Now we are looking at what could be the next computing technology."
While participation in a publicly funded project such as EGEE might
have many side benefits for a commercial organization -- by generating
a positive PR image, for instance -- CGG has taken its involvement
somewhat deeper. After first becoming involved in EGEE, it experimented
with Grid technology on the GILDA testbed, a Grid provided for
dissemination activities by Italy's INFN (an EGEE partner). In the
light of positive experiences, CGG formed a virtual organization,
Expanding Geosciences on Demand (EGEODE), to support both its own
research activities and those of the geosciences community in general.
"The goal was to share our experience with people doing geosciences, so
we decided to give universities free access to geocluster, our seismic processing
solution," said Thomas.
While this particular collaboration between industry and academia seems
harmonious, it still requires special considerations not seen in
traditional academic collaboration. One of the most obvious is the
issue of licensing. EGEE, like most academic Grid projects, releases
its software under a broadly open source license, though one designed
to be industry-friendly. In contrast, EGEE makes use of GEANT, the
European high-speed network infrastructure for research and education,
which runs under a license that explicitly forbids its use for
profit-making calculations. As a result, CGG runs only R&D-related
jobs on the EGEE production service, enabling it to gather the
experience of a large-scale Grid without needing to build one itself.
Running commercial data on a public network also raises several other
issues, especially those of security, since CGG is a contributor to
EGEE as well as a user. "We give a node to the general EGEE
infrastructure -- not a large one, but not a small one either," Thomas
explained, "though typically it runs EGEODE jobs."
In order to participate in this way, CGG had to look at two issues.
"First is the security of the dataset and the software. The other is to
avoid people using our resources who are not allowed to. We received a
warning about this from our security manager, so our node is not linked
to our internal computer network at all."
Porting existing software to the Grid is also an important issue for
uptake by businesses, especially those who use rather than develop
high-performance computing. This did not prove difficult for CGG, as
Thomas explained. "There are two parts to our computing, one is the
traditional seismic processing. This was very easy to move as it
already worked in a cluster environment, and so was well adapted for
running on a Grid. The other part is for research and development, and
here the seismic dataset is not large, so it is not difficult to move
to the Grid either."
Such positive experiences might bode well for future adoption of Grid
technology in the commercial sector, particularly for users of cluster
technology who need to increase their computing resources.
CGG's experience also bodes well for future academic-industrial
collaborations. "For us, it is a very interesting experience," said
Thomas. "We discovered new people with a lot of expertise, but also new
requirements. These requirements were very similar to ours, such as the
use of big data sets."
This easy interaction is perhaps surprising, but Thomas attributes it
to the kind of academics CGG was working with. "EGEE is a production
Grid and that makes a difference. We have always worked with academics,
but this is the first time we've worked with computer scientists rather
than geoscientists. Working with more theoretical researchers can be
difficult, but working on research into a production Grid has been very
Given its unique experience, CGG is also in a good position to comment
on the future of the Grid for similar companies. Thomas seems generally
enthusiastic, at least about the future for CGG. "We will continue to
experiment with the Grid, and we want to continue with EGEE. As we are
a technical company, we need people around us with a very good level of
technology. With EGEODE, we will continue to support the virtual
organization. EGEODE is for research and education, and we will
continue to support the geosciences that way. In parallel, we will
continue to explore the Grid architecture from a commercial point of
view. We are also a service company for our clients, and we will help
them use Grid technology as well."
On the other hand, Thomas also identifies a number of barriers to
commercial use of the Grid. "There are technical and economic issues.
Technically, there is the issue of network bandwidth, and there is no
network for industry like GEANT is for academia. A network with good
bandwidth is just not affordable. On the other side, there is no
economics for the Grid, no usage model, so we don't know how much it
costs; there is no business model around the Grid at all."
Thomas also raised the thorny issue of Grid standards, remarking on the
need for more middleware support, and the difficulty of getting such
support for current open source software. While applauding GGF's
efforts in that area, he didn't see them as a full solution.
"That is where standards start, but we need the large manufacturers,
like IBM or HP, to really invest in this technology. We need standards,
and we can't afford to change our software every two or three years as
they change. I think these standards need to come from industry, so we
need to wait for [large IT companies], to say 'we fully support this.'"
While Thomas and CGG clearly have some outstanding concerns, they
remain enthusiastic, as demonstrated by their active and ongoing
involvement with EGEE. Whatever issues must be dealt with in the
future, Thomas's attitude to the Grid in general, and to the
collaboration program, seems both simple and positive: "We feel that
the best way to understand this new technology is to participate in its