On Makespan, Migrations, and QoS Workloads' Execution Times in High Speed Data Centers

Daniel LAGO

IEICE TRANSACTIONS on Communications   Vol.E98-B    No.11    pp.2099-2110
Publication Date: 2015/11/01
Online ISSN: 1745-1345
DOI: 10.1587/transcom.E98.B.2099
Type of Manuscript: Special Section INVITED PAPER (Special Section on Network Systems for Virtualized Environment)
high speed networks,  cloud computing,  scheduling algorithm,  quality of service,  VM migration,  

Full Text: FreePDF

With the growth of cloud-based services, cloud data centers are experiencing large growth. A key component in a cloud data center is the network technology deployed. In particular, Ethernet technology, commonly deployed in cloud data centers, is already envisioned for 10 Tbps Ethernet. In this paper, we study and analyze the makespan, workload execution times, and virtual machine migrations as the network speed increases. In particular, we consider homogeneous and heterogeneous data centers, virtual machine scheduling algorithms, and workload scheduling algorithms. Results obtained from our study indicate that the increase in a network's speed reduces makespan and workloads execution times, while aiding in the increase of the number of virtual machine migrations. We further observed that the number of migrations' behaviors in relation to the speed of the networks also depends on the employed virtual machines scheduling algorithm.