Dynamic management of cloud-based systems

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. In this scenario, we explore the following research areas.

• Live Migration algorithms.We propose 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. Preliminar results seem to show that the proposed algorithms are truly selective and robust even in variable contexts, thus reducing system instability and limit migrations when really necessary.
• Monitoring of cloud infrastructures.We analyze the monitoring infrastructures behind current virtualization systems that support cloud computing. Our goal is to find out under which operating conditions (workload, hardware and software configuration) the information obtained from these monitoring infrastructures tools is comparable to operating system level resource measures (CPU, disk, network, memory). We also investigate the correlations among host-based and virtual machine-based performance measurements.

People

• Mauro Andreolini
• Sara Casolari
• Michele Colajanni
• Mirco Marchetti
• Michele Messori

Selected Papers

• M. Andreolini, S. Casolari, M. Colajanni, M. Messori, "Dynamic load management of virtual machines in a cloud architecture",Proc. of the First International Conference on Cloud Computing (CLOUDCOMP 2009), Munich, Germany, October 19-21, 2009.
• Sara Casolari, Michele Colajanni, Francesco Lo Presti, "Runtime state change detector of computer system resources under non stationary conditions", Proc. of the 17th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecomunication Systems (IEEE ACM MASCOTS 2009), London, September 2009.