Aggregating and managing memory capacity across computing nodes in cloud environments

Abstract

Managing memory capacity in cloud environments is a challenging issue, mainly due to the temporal variability in virtual machine (VM) memory demand. The Virtual Machine Manager or the hypervisor allocates a portion of the physical memory to the VMs, and it can change their allocation dynamically, depending on their needs. In a cloud-coimputing infrastructure, every computing node has an instance of a hypervisor. In many cases, the VMs demand for memory creates too much pressure on the memory resources of a node, prompting the need to make more memory resources available to the computing node. In our research, we have addressed and provided solutions for the two following problems: 1) how to efficiently manage the memory capacity available to a hypervisor? 2) how to aggregate memory capacity across multiple nodes?