International Business Machines Corporation

Manoj Soni

Manish Satyapal Gupta

Pradipta De

Venkateswara Reddy Madduri

Aditya Thatte

Jai Kumar Singh

Manish Sethi

Narendran Sachindran

Pratik Gupta

An apparatus and an article of manufacture for pre-provisioning a virtual machine instance include deriving a weight function for at least one virtual machine request based on historical data of the at least one virtual machine request to create a weighted virtual machine request for each request, capturing at least one inter-arrival pattern of requests, and applying the at least one pattern to the at least one weighted request to create a prioritized ordering of the at least one weighted request, and pre-provisioning at least one instance of a virtual machine image based on the prioritized ordering of the at least one weighted request.

Rapid provisioning of virtual machines based on multi-dimensional user request patterns in a cloud

A method for pre-provisioning a virtual machine instance includes deriving a weight function for at least one virtual machine request based on historical data of the at least one virtual machine request to create a weighted virtual machine request for each request, capturing at least one inter-arrival pattern of requests, and applying the at least one pattern to the at least one weighted request to create a prioritized ordering of the at least one weighted request, and pre-provisioning at least one instance of a virtual machine image based on the prioritized ordering of the at least one weighted request.

Methods and arrangements for facilitating virtual appliance image delivery. Virtual appliance image templates are stored at a caching location, based on a historical request pattern. A request is received for a virtual appliance image and there is provided, to a second location, a virtual appliance image responsive to the received request. A difference is determined between the requested virtual appliance image and stored virtual appliance image templates.

Computing reusable image components to minimize network bandwidth usage

Methods and arrangements for tracking changes in an information technology environment. Configuration dependencies are learned in a production environment, and a model of the production environment is built. Events on a target system in the production environment are subscribed to. Events are received and correlated with the model to generate an enhanced model, and the enhanced model is thereupon employed to predict configuration errors.

Arrangements for extending configuration management in large IT environments to track changes proactively

A framework instantiates an application from its disk snapshots. The disk snapshots are taken from a different network environment and migrated to a virtualized environment. Modifications to operating systems and hypervisors are avoided, and no special network isolation support is required. The framework is extensible and plug-in based, allowing product experts to provide knowledge about discovering, updating, starting and stopping of software components. This knowledge base is compiled into a plan that executes various interleaved configuration discovery, updates and start tasks such that a required configuration model can be discovered with minimal start and update task execution. The plan generation automatically stitches together knowledge for the various products, thus significantly simplifying the knowledge specification. Once discovery is complete, the framework utilizes the discovered model to update stale network configurations across software stack and customize configurations beyond network settings.

Growing community of inventors

Rajasthan, India

Manoj Soni