Cloud computing is here, but you’ll probably have found that it is nearly impossible to compare compute service performance based solely on information from providers themselves. For example, there is no standard for describing processing capacity of compute services. BTW you can learn a lot more about actual ways to compare PaaS providers by reading trough “State of the Cloud” reports from rightscale.com Most cloud compute services are virtualized. Virtualization lets providers operate more efficiently, provision compute instances faster, and offer lower costs to customers. Virtualization enables the partitioning of physical resources, such as CPU cores, to virtual resources, such as virtual CPUs (often using a one-to-multiple ratio). It also allows providers to oversubscribe resources, on the assumption that many users will not use all their resources all the time. However, virtualization doesn’t change the limited load capacity of the underlying hardware, and if providers do not properly manage virtualization, performance variability and unpredictability can result when many users try to use resources at the same time. Each provider uses a different virtualization strategy, with
Share This

We are using cookies on our website

Please confirm, if you accept our tracking cookies. You can also decline the tracking, so you can continue to visit our website without any data sent to third party services.