Optimizing VM Placement for HPC in the Cloud

Computing as a service model in clouds has encouraged High Performance Computing to reach out to wider scientific and industrial community. Many small and medium scale HPC users are exploring Infrastructure cloud as a possible platform to run their applications. However, there are gaps between the characterstic traits of an HPC application and existing cloud scheduling algorithms. In this paper, we propose an HPC-aware scheduler and implement it atop Open Stack scheduler. In particular, we introduce topology awareness and consideration for homogeniety while allocating VMs. We demonstrate the benefits of these techniques by evaluating them on a cloud setup on Open Cirrus test-bed.

@inproceedings{GuptaFedCloud,
 author = {Gupta, Abhishek and Milojicic, Dejan and Kal{\'e}, Laxmikant V.},
 title = {{Optimizing VM placement for HPC in the cloud}},
 booktitle = {Proceedings of the 2012 workshop on Cloud services, federation, and the 8th open cirrus summit},
 series = {FederatedClouds '12},
 year = {2012},
 isbn = {978-1-4503-1754-2},
 location = {San Jose, California, USA},
 pages = {1--6},
 numpages = {6},
 url = {http://doi.acm.org/10.1145/2378975.2378977},
 doi = {10.1145/2378975.2378977},
 acmid = {2378977},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {clouds, high performance computing, resource scheduling},
}