Abstract: Computational methods and systems that proactively manage usage of computational resources of a distributed computing system are described. A sequence of metric data representing usage of a resource is detrended to obtain a sequence of non-trendy metric data. Stochastic process models, a pulse wave model and a seasonal model of the sequence of non-trendy metric data are computed. When a forecast request is received, a sequence of forecasted metric data is computed over a forecast interval based on the estimated trend and one of the pulse wave or seasonal model that matches the periodicity of the sequence of non-trendy metric data. Alternatively, the sequence of forecasted metric data is computed based on the estimated trend and the stochastic process model with a smallest accumulated residual error. Usage of the resource by virtual objects of the distributed computing system may be adjusted based on the sequence of forecasted metric data.

Abstract: This disclosure is directed to tagging tokens or sequences of tokens in log messages generated by a logging source. Event types of log messages in a block of log messages are collected. A series of tagging operations are applied to each log message in the block. For each tagging operation, event types that are qualified to receive the corresponding tag are identified. When a log message is received, the event type is determined and compared with the event types of the block in order to identify a matching event type. The series of tagging operations are applied to the log message to generate a tagged log message with the restriction that each tagging operation only applies a tag to token or sequences of tokens when the event type is qualified to receive the tag. The tagged log message is stored in a data-storage device.

Abstract: The current document is directed to systems, and methods incorporated within the systems, that execute queries against log-file entries. A monitoring subsystem within a distributed computer system uses query results during analysis of log-file entries in order to detect changes in the state of the distributed computer system, identify problems or potential problems, and predict and forecast system characteristics. Because of the large numbers of log-file-entry containers that may need to be opened and processed in order to execute a single query, and because opening and reading through the entries in a log-file-entry container is a computationally expensive and time-consuming operation, the currently disclosed systems employ event-type metadata associated with log-file-entry containers to avoid opening and reading through the log-file entries of log-file-entry containers that do not contain log-file entries with event types relevant to the query.

Abstract: The current document is directed to methods and systems for processing, classifying, and efficiently storing large volumes of event messages generated in modern computing systems. In a disclosed implementation, received event messages are normalized to identify non-parameter tokens within the event messages. The non-parameter event tokens are used to compute a metric for each event message. The metrics are used, in turn, to identify a type-associated cluster to which to assign each received event message. The type-associated clusters are created dynamically as streams of event messages are processed. The type-associated clusters may be dynamically split and merged to refine event-message typing.

Abstract: The current document is directed to methods and systems for processing, classifying, and efficiently storing large volumes of event messages generated in modern computing systems. In a disclosed implementation, received event messages are assigned to event-message clusters based on non-parameter tokens identified within the event messages. A parsing function is generated for each cluster that is used to extract data from incoming event messages and to prepare event records from event messages that more efficiently and accessible store event information. The parsing functions also provide an alternative basis for assignment of event massages to clusters.

Abstract: Methods and systems that detect computer system anomalies based on log file sampling are described. Computers systems generate log files that record various types of operating system and software run events in event messages. For each computer system, a sample of event messages are collected in a first time interval and a sample of event messages are collected in a recent second time interval. Methods calculate a difference between the event messages collected in the first and second time intervals. When the difference is greater than a threshold, an alert is generated. The process of repeatedly collecting a sample of event messages in a recent time interval, calculating a difference between the event messages collected in the recent and previous time intervals, comparing the difference to the threshold, and generating an alert when the threshold is violated may be executed for each computer system of a cluster of computer systems.

Abstract: Methods and systems to identify log write instructions of a source code as potential sources of an event message of interest are described. Methods identify non-parametric tokens, such as text strings and natural language words and phrases, of an event message of interest. Candidate log write instructions and associated line numbers in a source code are identified. Non-parametric tokens of each event message of the one or more candidate log write instructions are determined. A confidence score is calculated for each candidate log write instruction based the number of non-parametric tokens the event message of interest and event message of the candidate log write instruction have in common. The candidate log write instructions are rank ordered based on the corresponding one or more confidence scores and the rank ordered candidate log write instructions and associated line numbers of the source code may be displayed in a graphical user interface.

Abstract: The current document is directed to methods and systems that process, classify, efficiently store, and display large volumes of event messages generated in modern computing systems. In a disclosed implementation, event messages are assigned types and transformed into event records with well-defined fields that contain field values. Recurring patterns of event messages, referred to as “transactions,” are identified within streams or sequences of time-associated event messages and streams or sequences of time-associated event records.

Abstract: Methods and systems to identify log write instructions of a source code as potential sources of an event message of interest are described. Methods identify non-parametric tokens, such as text strings and natural language words and phrases, of an event message of interest. Candidate log write instructions and associated line numbers in a source code are identified. Non-parametric tokens of each event message of the one or more candidate log write instructions are determined. A confidence score is calculated for each candidate log write instruction based the number of non-parametric tokens the event message of interest and event message of the candidate log write instruction have in common. The candidate log write instructions are rank ordered based on the corresponding one or more confidence scores and the rank ordered candidate log write instructions and associated line numbers of the source code may be displayed in a graphical user interface.

Abstract: Methods and systems that detect computer system anomalies based on log file sampling are described. Computers systems generate log files that record various types of operating system and software run events in event messages. For each computer system, a sample of event messages are collected in a first time interval and a sample of event messages are collected in a recent second time interval. Methods calculate a difference between the event messages collected in the first and second time intervals. When the difference is greater than a threshold, an alert is generated. The process of repeatedly collecting a sample of event messages in a recent time interval, calculating a difference between the event messages collected in the recent and previous time intervals, comparing the difference to the threshold, and generating an alert when the threshold is violated may be executed for each computer system of a cluster of computer systems.

Abstract: The current document is directed to methods and systems that process, classify, efficiently store, and display large volumes of event messages generated in modern computing systems. In a disclosed implementation, received event messages are assigned to event-message clusters based on non-parameter tokens identified within the event messages. A parsing function is generated for each cluster that is used to extract data from incoming event messages and to prepare event records from event messages that more efficiently and accessible store event information. The parsing functions also provide an alternative basis for assignment of event messages to clusters. Event types associated with the clusters are used for gathering information from various information sources with which to automatically annotate event messages displayed to system administrators, maintenance personnel, and other users of event messages.

Abstract: The current document is directed to systems, and methods incorporated within the systems, that carry out probability-distribution-based analysis of log-file entries. A monitoring subsystem within a distributed computer system uses probability-distribution-based analysis of log-file entries to detect changes in the state of the distributed computer system. A log-file-analysis subsystem within a distributed computer system uses probability-distribution-based analysis of log-file entries to identify subsets of log-file entries that predict anomalies and impending problems in the distributed computer system. In many implementations, a numerical comparison of probability distributions of log-file-entry types is used to detect state changes in the distributed computer system.

Abstract: Large amounts of unstructured log data generated by software and infrastructure components of a computing system are processed and analyzed in real time to identify anomalies and potential problems within the computing system. A log analytics module reduces both the volume and level of detail of log data by first classifying log messages into message types based on their content similarity. The log analytics module may then further reduce data by grouping bursts of log messages into log events. Patterns within these log events, such as the collection and number of different message types that comprise the event, can be used to identify anomalous events.

Abstract: The current document is directed to methods and systems for processing, classifying, and efficiently storing large volumes of event messages generated in modern computing systems. In a disclosed implementation, received event messages are normalized to identify non-parameter tokens within the event messages. The non-parameter event tokens are used to compute a metric for each event message. The metrics are used, in turn, to identify a type-associated cluster to which to assign each received event message. The type-associated clusters are created dynamically as streams of event messages are processed. The type-associated clusters may be dynamically split and merged to refine event-message typing.

Abstract: The current document is directed to methods and systems for processing, classifying, and efficiently storing large volumes of event messages generated in modern computing systems. In a disclosed implementation, received event messages are assigned to event-message clusters based on non-parameter tokens identified within the event messages. A parsing function is generated for each cluster that is used to extract data from incoming event messages and to prepare event records from event messages that more efficiently and accessible store event information. The parsing functions also provide an alternative basis for assignment of event massages to clusters.

Abstract: The current document is directed to methods and systems for processing, classifying, and efficiently storing large volumes of event messages generated in modern computing systems. In a disclosed implementation, received event messages are assigned to clusters based on metrics computed for the event messages. In addition, a significance value is determined for each received event message. When the significance value exceeds a threshold value, one or more actions are taken, including marking an event record corresponding to the event message, storing an event record corresponding to the event message in a significant-event log, and generating a notice or alarm.

Abstract: Large amounts of unstructured log data generated by software and infrastructure components of a computing system are processed and analyzed in real time to identify anomalies and potential problems within the computing system. A log analytics module reduces both the volume and level of detail of log data by first classifying log messages into message types based on their content similarity. The log analytics module may then further reduce data by grouping bursts of log messages into log events. Patterns within these log events, such as the collection and number of different message types that comprise the event, can be used to identify anomalous events.