SEARCH
ISTC-CC NEWSLETTER
RESEARCH HIGHLIGHTS
Ling Liu's SC13 paper "Large Graph Processing Without the Overhead" featured by HPCwire.
ISTC-CC provides a listing of useful benchmarks for cloud computing.
Another list highlighting Open Source Software Releases.
Second GraphLab workshop should be even bigger than the first! GraphLab is a new programming framework for graph-style data analytics.
ISTC-CC Abstract
Performance Overhead Among Three Hypervisors: An Experimental Study using Hadoop Benchmarks
2nd IEEE International Congress on Big Data (BigData’13), June-July 2013.
Jack Li, Qingyang Wang, Deepal Jayasinghe, Junhee Park, Tao Zhu, Calton Pu
Georgia Institute of Technology
Hypervisors are widely used in cloud environments and their impact on application performance has been a topic of significant research and practical interest. We conduct experimental measurements of several benchmarks using Hadoop MapReduce to evaluate and compare the performance impact of three popular hypervisors: a commercial hypervisor, Xen, and KVM. We found that differences in the workload type (CPU or I/O intensive), workload size and VM placement yielded significant performance differences among the hypervisors. In our study, we used the three hypervisors to run several MapReduce benchmarks such as Word Count, TestDSFIO, and TeraSort and further validated our observed hypothesis using microbenchmarks. We observed for CPU-bound benchmark, the performance difference between the three hypervisors was negligible; however, significant performance variations were seen for I/O-bound benchmarks. Moreover, adding more virtual machines on the same physical host degraded the performance on all three hypervisors, yet we observed different degradation trends amongst them. Concretely, the commercial hypervisor is 46% faster at TestDFSIO Write than KVM, but 49% slower in the TeraSort benchmark. In addition, increasing the workload size for TeraSort yielded completion times for CVM that were two times that of Xen and KVM. The performance differences shown between the hypervisors suggests that further analysis and consideration of hypervisors is needed in the future when deploying applications to cloud environments.
FULL PAPER: pdf
