Speaker
Mr
Lukasz Skital
(ACC Cyfronet AGH / University of Science and Technology)
Description
Introduction
Contemporary grid environment achieved high level of maturity. With still
increasing number of various available resources, their optimal exploitation
becomes a significant problem. One of solutions to the problem are Virtual
Organizations (VO), which groups users and resources to solve a particular
problem or a set of problems. Each problem has its own specific requirements in
name of computational power, network bandwidth, storage capacity, resource
availability etc. During VO design process, appropriate resources have to be
selected from all available. This task can be vary difficult or time consuming,
if done manually.
Current EGEE middleware (lcg 2.6 or glite 1.4.1) with VOMS or VOMRS systems
address the problem of users management in existing VOs, offering web based
interfaces for user registration and membership administration. However,
creation of new VO is a heavy weight task, which is not automated. Existing EGEE
procedures covers very well all administrative aspects, but in current form
they are not feasible for automation of the VO creation task. There is no tool,
which support design of new VO in EGEE environment.
In the presentation we propose a methodology of VO design. This methodology can
be used to build a knowledge based system, which would support the process of
VO creation by automating tasks, which do not need user interaction and support
user, when the interaction is necessary. The methodology is general and can be
adapted to EGEE grid environment. The knowledge based system can be used to
support design of new VO without changing existing EGEE procedures.
Methodology
We propose the way of VO design which consists of three steps: definition of
the VO, creation of abstract VO, creation of solid VO.
The first step of VO design is definition of the VO purpose with all
requirements and constraints. This step has to be performed by an expert who
knows the problem for which the VO is created. The definition of VO should be
written in a form, which can be easily processed by machine, therefore we
propose to use ontology for this task. The expert from the VO domain, does not
have to be familiar with any ontology language. There is a need for a tool
which will allow VO definition by fulfilling forms and questions. This tool
can support the expert in the task, by providing hints and possible answers to
questions.
The next step is creation of abstract VO. Abstract VO consists of resource
types and their amount which is needed to fulfill VO requirements. Abstract VO
is derived from VO definition (and available resources). Abstract VO has exact
information about required computational resources, storage resources and all
other specific resources, like data sources (e.g. physical experiment), but
does not aim to any specific instance of resource (site). However, the expert
can state, that a specific site is required in VO, and this requirement will be
fulfilled in the next step - creation of solid VO. For each resource type,
there are functional and not functional requirements. The functional
requirements are for example installed specific software on computational
resources. Non functional requirements can be availability of resource or cost
of usage.
The last step of VO design is creation of solid VO. During this step abstract
resources are exchanged by real instances. This task can be performed
automatically. Resources selection is based on specified requirements and
knowledge about the grid environment. The knowledge consists of many kinds of
facts and information about each resource, like computational power, storage
capacity, bandwidth (network, storage), statistics about resource availability,
etc. Because of a dynamic nature of the Grid, available resources can change in
time. To support VO requirements, unavailable resources should be replaced with
new ones during the VO lifetime. Therefore the last step of VO design should be
repeated any time when needed.
During the first step of design, apart form getting the information on needed
resources, a workflow, which defines the problem would be created. The workflow
visualizes a process of VO usage, from data gathering, through each necessary
step, like preprocessing, computations, postprocessing and visualisation. Using
the workflow, one can easily generate a specific job description (can take
advantage of DAG jobs) to solve the problem. This step can be done
automatically.
Summary
Optimal resource utilization is a very important task for contemporary grid
environments. With grid environments growth in size and complexity, this task
becomes more and more complicated. We proposed the methodology, which can
positively influence the process of optimal resource utilization by supporting
design of a VO. Well designed VO hides size and complexity of the grid
environments, reveling only parts, which are important for the specific problem
(for which VO was created). Selection of appropriate resources for VO is time
consuming task, therefore it's automation can significantly improve process of
VO establishment.
References
[1] EGEE Home page <http://public.eu-egee.org/>
[2] EGEE NA4 Home page <http://egee-na4.ct.infn.it/egaap/>
[3] InteliGrid <http://www.inteligrid.com/>
[4] KWf-Grid <http://www.kwfgrid.net/main.asp>
Summary
Optimal resource utilization is a very important task for contemporary grid
environments. With grid environments growth in size and complexity, this task
becomes more and more complicated. We proposed the methodology, which can
positively influence the process of optimal resource utilization by supporting
design of a VO. Well designed VO hides size and complexity of the grid
environments, reveling only parts, which are important for the specific problem
(for which VO was created). Selection of appropriate resources for VO is time
consuming task, therefore it's automation can significantly improve process of
VO establishment.
Authors
Prof.
Jacek Kitowski
(ACC Cyfronet AGH / University of Science and Technology)
Mr
Lukasz Skital
(ACC Cyfronet AGH / University of Science and Technology)
Dr
Renata Slota
(University of Science and Technology)
