Dynatrace Corporation

Other

Otmar Ertl

Ernst Ambichl

Herwig Moser

Bernhard Lackner

Jordi Masramon

Edyta Kalka

Helmut Spiegl

Alfonso Corretti

Bernd Greifeneder

Martin Carpella

Jordi Masramon Solans

A technology for the optimized capturing of resource file content for resources referred in recorded user interaction sequences is disclosed. Individual resource files are typically referred in multiple recorded resources, therefore it is desired to capture those resources only once and reuse them for all recorded session capturing them. As user interaction sequences are executed and captured in independently operating web-browsers, a direct coordination between recording web-browsers to avoid multiple captures of the same resource is not possible. Data about the global resource capturing and demand situation is generated on a monitoring server that receives all session recording data and transferred to session recording browsers in form of lists identifying resources that are referred in sessions but are still unresolved and should therefore be captured, and for resources that should not captured, because they are already available and capturing them again should be avoided.

Optimized sampling of resource content data for session recording under communication constraints by independently capturing agents

Technologies are disclosed for the automated, rule-based generation of models from arbitrary, semi-structured observation data. Context data of received observation data, like data describing the location of on which a phenomenon was observed, is used to identify related observations, to generate entities in a model describing the observed data and to assign observations to model data. Mapping rules may be used for the on-demand generation of models, and different sets of mapping rules may be used to generate different models out of the same observation data for different purposes. Further, observation time data may be used to observer the temporal evolution of the generated model. Possible use cases of the so generated models include the interpretation of observation data that describes unexpected operation conditions in view of the generated model, or to determine how a monitored system reacts on changing conditions, like increased load.

Method and system for the on-demand generation of graph-like models out of multidimensional observation data

A technology is disclosed for the browser side capturing of user interaction session data and replay of the session data for a high-fidelity reconstruction of the experience the user perceived. In addition to capturing central structuring and markup documents and browser side updates thereof, additional resource documents that are loaded and used by the browser to render the central documents are captured and added to the session recording data. Identification information is created for resource documents, based on the content of those documents, which allows the capturing system to distinguish different versions of those content documents that share the same name but have different content. The captured session data contains data to identify the correct versions of resource documents during replay. Various measures to reduce the amount of transferred resource content data are applied, that consider already captured resource document versions or the usage frequency of a monitored application.

Method and system for application performance neutral, network bandwidth optimized capturing of resources used during the interaction of user with a web-based application to create monitoring data for an accurate visual reconstruction of the user experience

A system and method for the analysis of log data is presented. The system uses SuperMinHash based locality sensitive hash signatures to describe the similarity between log lines. Signatures are created for incoming log lines and stored in signature indexes. Later similarity queries use those indexes to improve the query performance. The SuperMinHash algorithm uses a two staged approach to determine signature values, one stage uses a first random number to calculate the index of the signature value that is to update. The two staged approach improves the accuracy of the produced similarity estimation data for small sized signatures. The two staged approach may further be used to produce random numbers that are related, e.g. each created random number may be larger than its predecessors. This relation is used to optimize the algorithm by determining and terminating when further created random numbers have no influence on the created signature.

Method and system for log data analytics based on SuperMinHash signatures

A system and method for the creation of locality sensitive hash signatures using weighted feature sets is disclosed. The disclosed methodology takes advantage of discretization mechanisms commonly used in computer systems to model the influence of the feature weights on the calculated hash signature. Pseudo random numbers required for the signature calculation are created in ascending order, which enables the signature generation mechanism to identify and avoid the unnecessary creation of pseudo random numbers to improve the performance of the signature calculation process. Further, hierarchic, tree-search like algorithms are used during the processing of signature weights to further decrease the number of required random numbers. The features of the Poisson Process model, like its ability to provide random numbers in ascending order and the split—and mergeability of Poisson Processes are used to further improve the performance of the signature calculation process.

Method and system for calculating minwise hash signatures from weighted sets

A system and method is proposed for estimating the contribution of components of a distributed computing environment to the generation of economically relevant values, like e.g., revenue numbers. Agents are deployed to the computing environment that trace executed transactions and that monitor components used to execute those transactions. The transaction trace data also contains data about the origin/user of transactions, which may be used to group transactions corresponding to particular interactions of individual users with the monitored application into visit data. Data describing economically relevant activities of transactions, like the purchase of goods, are also observed by agents and reported in trace data. Functional dependencies described in transaction trace data and resource related dependencies derived from component monitoring data are used to identify functionality and components that contributed to the generation of business value. The generated business value is assigned to contributing components to incrementally create data describing the economic value of those components. The so generated data can be used for various business-related analyses.

Optimizing cloud-based IT-systems towards business objectives: automatic topology-based analysis to determine impact of IT-systems on business metrics

A system and method for the distributed analysis of high frequency transaction trace data to constantly categorize incoming transaction data, identify relevant transaction categories, create per-category statistical reference and current data and perform statistical tests to identify transaction categories showing overall statistically relevant performance anomalies. The relevant transaction category detection considers both the relative transaction frequency of categories compared to the overall transaction frequency and the temporal stability of a transaction category over an observation duration. The statistical data generated for the anomaly tests contains next to data describing the overall performance of transactions of a category also data describing the transaction execution context, like the number of concurrently executed transactions or transaction load during an observation period. Anomaly tests consider current and reference execution context data in addition to statistic performance data to determine if detected statistical performance anomalies should be reported.

Method and system for real-time and scalable anomaly detection and classification of multi-dimensional multivariate high-frequency transaction data in a distributed environment

A system and method for the creation of locality sensitive hash signatures using weighted feature sets is disclosed. The disclosed methodology takes advantage of discretization mechanisms commonly used in computer systems to model the influence of the feature weights on the calculated hash signature. Pseudo random numbers required for the signature calculation are created in ascending order, which enables the signature generation mechanism to identify and avoid the unnecessary creation of pseudo random numbers to improve the performance of the signature calculation process. Further, hierarchic, tree-search like algorithms are used during the processing of signature weights to further decrease the number of required random numbers. The features of the Poisson Process model, like its ability to provide random numbers in ascending order and the split- and mergeability of Poisson Processes are used to further improve the performance of the signature calculation process.

A system and method for the estimation of the cardinality of large sets of transaction trace data is disclosed. The estimation is based on HyperLogLog data sketches that are capable to store cardinality relevant data of large sets with low and fixed memory requirements. The disclosure contains improvements to the known analysis methods for HyperLogLog data sketches that provide improved relative error behavior by eliminating a cardinality range dependent bias of the relative error. A new analysis method for HyperLogLog data structures is shown that uses maximum likelihood analysis methods on a Poisson based approximated probability model. In addition, a variant of the new analysis model is disclosed that uses multiple HyperLogLog data structured to directly provide estimation results for set operations like intersections or relative complement directly from the HyperLogLog input data.

Method and system to estimate the cardinality of sets and set operation results from single and multiple HyperLogLog sketches

A system and method is disclosed for the automated identification of causal relationships between a selected set of trigger events and observed abnormal conditions in a monitored computer system. On the detection of a trigger event, a focused, recursive search for recorded abnormalities in reported measurement data, topological changes or transaction load is started to identify operating conditions that explain the trigger event. The system also receives topology data from deployed agents which is used to create and maintain a topological model of the monitored system. The topological model is used to restrict the search for causal explanations of the trigger event to elements of that have a connection or interact with the element on which the trigger event occurred. This assures that only monitoring data of elements is considered that are potentially involved in the causal chain of events that led to the trigger event.

Method and system for automatic real-time causality analysis of end user impacting system anomalies using causality rules and topological understanding of the system to effectively filter relevant monitoring data

A system and method is disclosed for identifying and evaluating the business relevant impact of observed operating anomalies of monitored components of computing environments like data centers or cloud computing environments. The disclosed technology uses end-to-end transaction trace, availability and resource utilization data in combination with topology data received from agents deployed to the monitored computing environment. An abnormal operating condition is localized within a topological model of the monitored environment and has a defined temporal extent. On detection of an anomaly, affected transaction traces are selected that used the topology entity on which the anomaly was observed while the anomaly existed. Those transactions are then traced backwards, until a topology entity is reached that represents an entry point of monitored system. The affected transactions are compared with unaffected transactions that entered via the entry point to determine the extent to which the entry service is affected by the abnormal behavior.

Growing community of inventors

Linz, Austria

Otmar Ertl