Description
From Grid Monitoring to Analysis (90 mins)
Cecile Germain-Renaud (EGEE Grid Observatory and LRI-CNRS) and Ramin Yahyapour (OGF AD Compute, CoreGRID Institute RMS, EC project SLA@SOI, German D-Grid)
A major operational and scientific challenge is to progress towards a better understanding and sound optimization of the e-science and business infrastructures.
* Grid models are required for dimensioning, capacity planning, or optimizing applications.
* Self-regulation and self-maintenance are desired functionalities in many areas, ranging from resource allocation to real-time fault diagnosis, including green computing as an increasingly urgent constraint.
* Information on usage patterns based on VO provenance, differences in national Grid initiatives or on commercial production sites can help to improve management strategies.
* The exciting and new area of convergence between Grid and
Cloud Computing, including hosting scenarios in SOA environments requires to explore the similarities and discrepancies of e-science and business applications.
Extensive grid monitoring facilities have already been developed, and
to some extent standardized or became de-facto standards. However, the availability of the resulting data is often very limited, hampering the investment of the scientific community into the abovementioned challenges.
This joint session will contribute to fostering collaboration between data providers and potential users. The session will be an opportunity to:
* disseminate recent advances in grid monitoring, data publication, and exploration tools which are oriented towards the scientific view of grids;
* promote interoperability of the developing repositories of grid traces;
* show examples of experimental work on grid analysis and optimization.
A major operational and scientific challenge is to progress towards a better understanding and sound optimization of the e-science and business infrastructures.
* Grid models are required for dimensioning, capacity planning, or optimizing applications.
* Self-regulation and self-maintenance are desired functionalities in many areas, ranging from resource allocation to real-time fault diagnosis, including green computing as an increasingly urgent constraint.
* Information on usage patterns based on VO provenance, differences in national Grid initiatives or on commercial production sites can help to improve management strategies.
* The exciting and new area of convergence between Grid and
Cloud Computing, including hosting scenarios in SOA environments requires to explore the similarities and discrepancies of e-science and business applications.
Extensive grid monitoring facilities have already been developed, and
to some extent standardized or became de-facto standards. However, the availability of the resulting data is often very limited, hampering the investment of the scientific community into the abovementioned challenges.
This joint session will contribute to fostering collaboration between data providers and potential users. The session will be an opportunity to:
* disseminate recent advances in grid monitoring, data publication, and exploration tools which are oriented towards the scientific view of grids;
* promote interoperability of the developing repositories of grid traces;
* show examples of experimental work on grid analysis and optimization.
Agenda:
4 talks plus one short panel
