Event overflow handling by coalescing and updating previously-queued event notification

Abstract

An event notification system for distributed processing systems provides reduction of queue space and event processing bandwidth associated with duplicate events such as a particular event that is duplicated and results in multiple event notifications propagated for multiple consumers. When a duplicate event notification is received at an input to an event notification queue, rather than queuing the duplicate event notification, a sequence number of the event notification already in the queue is updated to indicate to the event consumer, exactly how many duplicate events have been received. The timestamp of the updated event notification may also be set to the timestamp of the most recently received duplicate event notification.

Description

BACKGROUND[0001]1. Field of the Invention[0002]The present invention is related to handling of event notification overflow or potential overflow conditions in computer systems, and more specifically to handling of duplicate events so that additional queue space is not required.[0003]2. Description of Related Art[0004]In large-scale distributed computer systems, such as those using distributed software models to perform tasks, multiple nodes provide independent execution of sub-tasks. In order to keep such a system operational, and further, to provide indication of events occurring at one node that either require a reaction from another node or indicate to the other node that either an erroneous operating condition has occurred, or that a phase of processing is complete. In particular, event notification and event logging are operations used to indicate system health to system administrators or software applications, including operating systems components.[0005]Health monitoring tech...

AI Technical Summary

Problems solved by technology

With the large number of events that may be generated, in particular where the event itself is triggered multiple times due to a resource change or a hardware or media failure, a large number of duplicate events may be buffered at a node, causing event queue overflow and / or consuming processing bandwidth that could be used to handle other events.

While the duplicate events could simply be removed from the queue, information about how many events have occurred and the timing of the events may be lost.

Images