Dynamic Load Management of Virtual Machines in Cloud Architectures

Abstract

Cloud infrastructures must accommodate changing demands for different types of processing with heterogeneous workloads and time constraints. In a similar context, dynamic management of virtualized application environments is becoming very important to exploit computing resources, especially with recent virtualization capabilities that allow live sessions to be moved transparently between servers. This paper proposes novel management algorithms to decide about reallocations of virtual machines in a cloud context characterized by large numbers of hosts. The novel algorithms identify just the real critical instances and take decisions without recurring to typical thresholds. Moreover, they consider load trend behavior of the resources instead of instantaneous or average measures. Experimental results show that proposed algorithms are truly selective and robust even in variable contexts, thus reducing system instability and limit migrations when really necessary.

Tackling uncertainty in long-term predictions for host overload and underload detection in cloud computing

“…Andreolini et al [21] propose an approach for host overload detection in which a host is declared as overloaded when there is a substantial change in the load trend of the host, as a result of applying the CUSUM algorithm. Their goal is similar to the goal of our work for providing a robust and stable approach avoiding unnecessary live migrations, but their load change point detection requires past history usage data to be available, at which point the SLA violations have already happened.…”

Role of Virtual Machine Live Migration in Cloud Load Balancing

“…The Migration of a VM from an overloaded host to another non critical host makes it possible to improve resource utilization and better load sharing [5]. Even though it is a useful concept, it is an expensive operation too in terms of resource utilization at sender host as well as receiver host and network utilization to transfer system and memory states of the sender host.…”

An Autonomic Auto-scaling Controller for Cloud Based Applications

“…It is also worth noticing that there has been work on resource management mechanisms based on the idea of migrating VMs, as for example [7]. In this study migration was not considered as our focus is a public IaaS cloud, where migration services are not commonly available.…”