ישי מנשה (מיקרוסופט, רדמונד)
יום שלישי, 27.12.2016, 11:30
Existing resource management frameworks for large scale cloud systems leave unresolved the problematic tension between high resource utilization and job's performance predictability - respectively coveted by operators and users. In this talk, I will present recent efforts to resolve this tension through temporal planning: unlike popular scheduling and routing schemes, we propose mechanisms that plan the resource allocations into future time steps. Intuitively, such planning allows the operator to pack the cloud more densely, while offering performance SLAs to users. I will describe two recent systems that incorporate forms of temporal planning: (i) Morpheus - a cluster resource management system that offers automated SLAs to customers while reducing the cluster footprint; and (ii) Pretium - a combined traffic engineering and pricing framework for WAN bandwidth.
Ishai Menache is a researcher in Microsoft Research, Redmond. He received his PhD from the Technion - Israel Institute of Technology. Subsequently, he was a postdoc at the Laboratory for Information and Decision Systems in MIT. Ishai's research focuses on developing large-scale resource management and optimization frameworks for datacenters. More broadly, his areas of interest include systems and networking, algorithms and machine learning.