Virtual machine monitors improve your cloud performance

Cloud computing is quickly becoming the platform of choice for many web services. Virtualization is the key underlying technology enabling cloud providers to host services for a large number of customers. Effective resource management for shared storage systems is challenging, even in research systems with complete end-to-end control over all system components. We evaluate the effectiveness of our implementation using quantitative experiments, demonstrating that this approach is practical. In this paper, we presented a novel I/O workload based performance attack which uses a carefully designed workload to incur significant delay on a targeted application running in a separate VM but on the same physical system. Such a performance attack poses an especially serious threat to data-intensive applications which require a large number of I/O requests. Hence, no hypervisor is needed to allocate resources dynamically, emulate I/O devices, support system discovery after boot up, or map interrupts and other identifiers.