Magnet: A novel scheduling policy for power reduction in cluster with virtual machines

Liting Hu, Hai Jin, Xiaofei Liao, Xianjie Xiong, Haikun Liu

2008 · 75 citations · 21 references

Concepts

TL;DR

Green computing has attracted attention in cluster computing, but prior local approaches lack a global view and yield limited power savings, while existing cluster‑wide techniques are restricted to homogeneous workstations and specific applications. The study proposes a novel VM live‑migration policy that transfers load across nodes on a multilayer ring overlay to reduce cluster power. The approach employs live migration of VMs across a multilayer ring overlay, and its effectiveness and performance are analytically verified. Experiments demonstrate that the method reduces cluster power consumption by up to 74.8 % over the baseline with acceptable overhead, and works on both homogeneous and heterogeneous servers.

Abstract

The concept of green computing has attracted much attention recently in cluster computing. However, previous local approaches focused on saving the energy cost of the components in a single workstation without a global vision on the whole cluster, so it achieved undesirable power reduction effect. Other cluster-wide energy saving techniques could only be applied to homogeneous workstations and specific applications. This paper describes the design and implementation of a novel approach that uses live migration of virtual machines to transfer load among the nodes on a multilayer ring-based overlay. This scheme can reduce the power consumption greatly by regarding all the cluster nodes as a whole. Plus, it can be applied to both the homogeneous and heterogeneous servers. Experimental measurements show that the new method can reduce the power consumption by 74.8% over base at most with certain adjustably acceptable overhead. The effectiveness and performance insights are also analytically verified.

References

21