International Business Machines Corporation

Elasticsearch B.v.

Andrew Wilkins

Luke Rowan McKenna

Ron Cohen

Peter Gareth Woodward

Ashley Neil Clementi

Bradley Matthew Gorman

Graeme Stanley Chambers

Tee Yen Ng

Robert Ching Kong Cheung

Systems and methods for application performance management across one or more networks are disclosed. A system includes a plurality of geographically distributed computing devices executing one or more applications. A plurality of collectors are distributed across the one or more networks, each collector being positioned proximate a respective computing device. The collectors may sample, by each of the plurality of collectors, a plurality of trace events received from the applications executing on the computing devices proximate the collector. The collectors may retain in memory sampled trace events that meet a configurable attribute. The collectors may use probabilistic sets and tail-based sampling to determine root events and policies for identifying relevant traces. Benefits can be achieved in bandwidth savings, network cost and cyber security.

Distributed network data management systems and methods

An approach is provided that receives a set of tracking data from a monitored activity. The set of tracking data includes name-value pairs. The received set name-value pairs are compared with context masks. Each context mask include one or more name-filter pairs. One of the sets of context masks is selected in response to determining that the incoming name-value pairs matches the mask name-filter pairs of the selected context mask. Name-value pairs are selected based upon the selected context mask. The selected name-value pairs are then stored in an aggregate data store. If the received set of tracking data fails to match at least one of the name-filter pairs then the received set of tracking data is disregarded and none of the name-value pairs are stored in the aggregate data store.

Processing and presenting multi-dimensioned transaction tracking data

An API can be extended to automatically correlate events based on context. Started events for each context (e.g. threads of execution) are maintained on independent stacks. When an instrumented application starts a new transaction, the API generates a started event. A transaction correlation unit within the API can determine if the new transaction started during a previous transaction. If there is a previous started event on the stack, the new transaction started during the previous transaction. The transaction correlation unit can insert an outbound indicator into the new started event to associate the new transaction and the previous transaction. Then, the new started event can be pushed on the stack.

Automatically correlating transaction events

A computer implemented method, apparatus, and computer usable program code for the distributed monitoring of a SOAP service is provided. A test configuration file specifying a test input is distributed from a central reporting location to at least one remote data processing system that has access to a SOAP service to be tested. The test configuration file is created without accessing the SOAP service to be tested. Furthermore, the user that created the test configuration file is not allowed access to the SOAP service to be tested.

Growing community of inventors

Perth, Australia

Andrew Wilkins