Live object pattern for use with a distributed cache

摘要

A live object pattern is described that enables a distributed cache to store live objects as data entries thereon. A live object is a data entry stored in the distributed cache which represents a particular function or responsibility. When a live object arrives to the cache on a particular cluster server, a set of interfaces are called back which inform the live object that it has arrived at that server and that it should initiate to perform its functions. A live object is thus different from “dead” data entries because a live object performs a set of function, can be started/stopped and can interact with other live objects in the distributed cache. Because live objects are backed up across the cluster just like normal data entries, the functional components of the system are more highly available and are easily transferred to another server's cache in case of failures.

主权项

1. A method for providing a live object pattern for a distributed data grid, said method comprising:
storing a set of data entries in a cache distributed across a cluster of computing devices, said cache providing insert, update and delete operations on said data entries; detecting that a new data entry has been placed into said cache on a particular computing device in said cluster or that a data entry is modified on said cache on a particular computing device in said cluster; determining whether the new data entry is a live object upon detecting that the new data entry has been mutated in the cache; and if said new data entry is determined to be the live object, calling the live object to perform a function on the particular computing device.