Improving performance of MapReduce framework on InterCloud by avoiding transmission of unnecessary data
Seungmi Choi, Shin-gyu Kim, Hyuck Han, Heon Young Yeom · ACM SIGMETRICS Performance Evaluation Review · 2011
Recently, cloud computing and MapReduce have become attractive computing environments as the need for data processing rapidly increases. This inflation in the demand for resources led to the introduction of InterCloud, which provisions resources from two or more cloud service providers. However, when MapReduce applications run on InterCloud environments, they underperform contrary to our expectations. In this paper, we suggest a technique that mitigates the performance problem of MapReduce applications on InterCloud environments. As shown in our preliminary results, our technique leads to up to five times better performance in InterCloud environments.