Abstract: A SAN management agent computes a validator corresponding to a full data set from which a relative (change) data set is derived. The validator, such as a checksum, identifies the full data set to which the relative data set is applicable. The validator is transmitted with the relative data set, and the store process compares the validator with the previous validator stored with the full data set in a database. If the validators correspond (i.e. match), then the received relative data set is applicable to the full data set stored at the database, and the relative data set may be processed as a change set. The remote agent therefore computes the validator on a full data set at a remote node, and transmits the validator with the change set. Subsequent relative data sets may then compare the current validator of the DB data set with the validator from which the relative set was derived.

Abstract: An agent collecting management data from the resource operating in the managed network to form a management data set and identifies segregated regions of management data within the management data set. Each segregated region is a respective partial transitive closure of the collected management data taken over a graph representing the entire management data set. For each segregated region of management data, the agent partitions that segregated region of management data into a set of logical partitions and transfers each logical partition of the segregated region of management data to a network management application in the managed network for access by the network management application. A network management application receives the partitions and only needs to keep objects in memory related to partitions that are currently received and being processed thus saving memory and processing resources.

Abstract: Mechanisms and techniques for processing information in a network management application, such as a storage area network management application, include an agent and store process. The agent collects a current management data set from managed entity(s) in a network and compares the current management data set to a former management data set previously collected from the managed entity to identify differences in the current management data set as compared to the former management data set. The agent transmits the current management data set to a store process. The store process receives the current management data set and uses verification values and change indicators contained therein to identifying current portions of management data in the current management data that reflect a change. For any changed data portions, the store process modifies or updates managed object data in the management database.

Abstract: In a managed information network, unavailable agents have a detrimental effect on user access to manageable entities. Intelligent, optimal assignment of manageable entities to available agents becomes a formidable task, particularly in a large storage area network. The task becomes especially complex when there are deployed agents of different types capable to manage a different scope of functionality of managed elements of the same type. A failover processor provides reliable, rule based methods for initial assignment of manageable entities (elements) to best available management agents, and a reliable, dynamic, rule based mechanism to reallocate manageable entities to a best management agent in case when current agent, responsible for element management, become unavailable or new best agent for element management starts up. A prioritized list of failover rules specifies metrics for determining alternate agents for manageable entities in the event agents become unavailable.