Home > Events > PhD Defense - Dinesh Rajan

PhD Defense - Dinesh Rajan

Start: 4/6/2015 at 10:30AM
End: 4/6/2015 at 1:00PM
Location: 100 Stinson Remick
Add to calendar:
iCal vCal

Dinesh Rajan

Dissertation Defense

April 6, 2015        10:30 am        100 Stinson Remick


Dr. Douglas Thain

Committee Members

Dr. Scott Emrich        Dr. Jesus Izaguirre        Dr. Aaron Striegel

Faculty and students are welcome to attend the presentation portion of the defense.  Light snacks and refreshments will be served.


"Principles for the Design and Operation of Elastic Scientific
Applications on Distributed Systems"


Scientific applications often harness the concurrency in their workloads to partition and operate them as independent tasks and achieve reasonable performance. To improve performance at scale, the partitions are operated in parallel on large pools of resources in distributed computing systems, such as clouds, clusters, and grids.  However, the exclusive and on-demand deployment of applications on these platforms presents challenges. The target hardware is unknown until runtime and variable between deployments when applications are deployed on these platforms.  So operating parameters such as the number of partitions and the instances to provision for execution must be determined at runtime for efficient operation.

In this work, I build and demonstrate elastic applications to provide the desired characteristics for operation on distributed computing systems.  I present case-studies of elastic applications from different scientific domains and draw broad observations on their design and the challenges to their efficient operation.  I develop and evaluate techniques at the middleware and the application layer to achieve efficient operation. In effect, the presented techniques create self-operating elastic applications that dynamically determine the partitions of their workloads and the scale of resources to utilize. I conclude by showing that self-operating applications achieve high time- and cost-efficiency in their deployed environments in distributed computing systems.