J. Zhang and W. Meleis (USA)
Grid computing, resource allocation and co-allocation, workﬂow, task scheduling, message relay.
Our objective is to provide location-, topology-, and
administrative-transparentgrid computing for MPI applications, while hiding the physical details of computing platforms and heterogeneous networks from the application developers and users. To achieve this objective, we introduced a new resource allocation model, workﬂow structures to specify MPI applications involving multiple tasks,
and message relay to enable communication across different networks. We developed the SGR framework, which
integrates workﬂow scheduling, task grouping, and message relay services, while hiding resource allocation, heterogeneous networks, and decentralized resource management systems from application developers and users. The
SGR system has been implemented on a Globus-enabled
We created a simulation environment to investigate
our model and various schedulers. Using the ﬁndings
from simulation, we implemented the SGR framework and
tested the model’s implementation on a two-cluster grid.
We observed that duplication can improve performance
by more than 15%, which matches our simulation results.
Moreover, we evaluated our new message relay service for
cross-site message passing. The test results indicate that
although the SGR’s message relay service has some communication overhead, the system is scalable with respect to
the number of processes and the message size.