A System for Googling Operational Data in Clouds

Cloud computing is a paradigm where computing resources in a datacenters are provisioned on-demand
as a service to clients over the internet. Cloud computing services execute on clusters of servers.
These clusters are characterized by a large number of configuration parameters and operational real-time
data, for instance, CPU type and utilization, storage type and occupancy, network access and utilization.
At the same time, information is available about configuration and utilization of services such as virtual
machines and communication patterns. We envision a search function for the cloud that “googles” data in
the cloud infrastructure in real-time. For instance, the search query find information about a specific cloud
service X would return virtual machines that execute the functionality of the service, their IP Addresses,
the physical servers on which they execute and information about their communication behaviour.