Cross-layer scheduling in cloud computing systems

Distributed System;Software-Defined Networking;Stream Processing

Alkaff, Hilfi ; Gupta ; Indranil

关键词: Distributed System;    Software-Defined Networking;    Stream Processing;   

Others  :  https://www.ideals.illinois.edu/bitstream/handle/2142/50739/Hilfi_Alkaff.pdf?sequence=1&isAllowed=y

美国|英语

来源: The Illinois Digital Environment for Access to Learning and Scholarship

【 摘 要 】

Today, application schedulers are decoupled from routing level schedulers, leading to sub-optimal throughput for cloud computing platforms. In this thesis, we propose a cross-layer scheduling framework that bridges the application level scheduler with the routing level scheduler (SDN). We realize our framework in a batch-processing framework (Hadoop) and a stream-processing framework (Storm [2]). Our experimental results show that weare able to improve throughput of jobs in Storm and Hadoop by up to 32% and 29% respectively.