Abstract: In several aspects for detecting a computing system resource schedule, a computing device performs a pre-analysis process utilizing a collected log from multiple sources. The pre-analysis process including a data formatter that identifies data based on a metric, and a dimensionality reduction process that distributes the data into an n-dimensional space. Key patterns are extracted to separate a normal status and an abnormal status for the extracted key patterns. A post-analysis process is performed on the extracted key patterns utilizing a threshold formatter to identify a threshold for a health check.

Abstract: A method, computer system, and a computer program product are provided for managing an accelerated shutdown of a networked system having a having a plurality of nodes. The system to be shutdown is analyzed and a priority order is determined for the nodes. An interval period is also determined between each node according to the priority order. A leaf node set is constructed according to different shutdown types required for each node and a dependency tree is constructed by analyzing the leaf node sets. Each node is then shutdown according to the tree and the interval period determined. The dependency tree and the interval period is iteratively modified during the node shutdown until all nodes and ultimately the system shutdown has been completed.

Abstract: A method, system, and computer program product that is configured to: create a three dimensional space by analyzing historical performance data; find an edge surface in the three dimensional space by determining a curve which intersects a plane in the three dimensional space; build a filter based on the edge surface in the three dimensional space; perform a logical operation between raw performance data and the built filter; determine whether the raw performance data has an invalid data value based on a result of the logical operation between the raw performance data and the built filter; and generate an alert that indicates that the raw performance data has the invalid data value in multiple data values in response to determining that a number of raw performance data instances having the invalid data value reaches a predetermined threshold counter number.

Abstract: A system, method, and computer program product include: collecting runtime history capture data by a data agent operable on a computing device; performing a pre-analysis of entries in the history capture data, the history capture data including a plurality of database transactions corresponding to user tables, and providing formatted history capture data; clustering the formatted history capture data into clusters by data characteristics of interval groups; performing a post-analysis on the clusters and providing a unit data profile for capture data of the user tables; and dynamically updating capture policies corresponding to capture processes for the user tables, the updating based at least on the unit data profile provided by the post-analysis. In some embodiments the clustering is density based. Optionally, an alert is sent when capture process capacity is exceeded.

Abstract: An approach is disclosed that receives an incoming data record, the data record including a number of data fields. The approach determines a current Real-Time Resources Score (RTRS). The RTRS being a forecast of the information handling system's ability to handle incoming data transmissions. When the RTRS is lower than a current data accumulation rate, a subset of the data record is sent based on field priorities. The approach assigns priorities to each of the data fields included in the data record based on a priority assessment of the respective data fields. The approach then sends, to a data receiver, a subset of the plurality of data fields based on the assigned priority.

Abstract: Embodiments of the present invention provide computer-implemented methods, computer program products and computer systems. Embodiments of the present invention can, in response to receiving performance data associated with records, identify whether the received performance data is associated with long transactions. Embodiments of the present invention can then, in response to determining that the received performance data is associated with long transactions, storing the performance data. Embodiments of the present invention can then classify the stored performance data according to types of transactions the performance data and aggregate the stored performance data based on the classification.

Abstract: A method, computer system, and computer program product for data monitoring management are provided. A first invalid zero value candidate from a data stream is received. A memory location for the first invalid zero value candidate is received. At a first time an access connection to the memory location is established. At a second time subsequent to the first time the access connection to the memory location is checked. Based on the checking, a determination is made whether the first invalid zero value candidate contains an invalid zero value.

Abstract: Embodiments of the present invention provide computer-implemented methods, computer program products and computer systems. Embodiments of the present invention can, in response to receiving performance data associated with records, identify whether the received performance data is associated with long transactions. Embodiments of the present invention can then, in response to determining that the received performance data is associated with long transactions, storing the performance data. Embodiments of the present invention can then classify the stored performance data according to types of transactions the performance data and aggregate the stored performance data based on the classification.

Abstract: A method, computer system, and computer program product for data monitoring management are provided. A first invalid zero value candidate from a data stream is received. A memory location for the first invalid zero value candidate is received. At a first time an access connection to the memory location is established. At a second time subsequent to the first time the access connection to the memory location is checked. Based on the checking, a determination is made whether the first invalid zero value candidate contains an invalid zero value.

Abstract: An approach for recommending an application of a software code update. The approach receives components of an executable program. The approach scans the components to divide the executable program into units. The approach creates a logical layer of entry lists, based on the units, for instantiations of the executable program. The approach loads the instantiations of the executable program based on the logical layers. The approach monitors the execution of the instantiations to increment counters based on executions of the units. The approach creates a heatmap of the executions based on the counters. The approach generates a recommendation to update the executable based on the heatmap.

Abstract: A method and implementing system protects sensitive data dump information. The method comprises using a processor receiving a dump file (DF) associated with an application. The method further comprises allocating user classification profiles defining security access levels to different regions of the DF and encrypting a first encrypted region that is a proper subset of the different regions using a first encryption key associated with a first user classification profile of the user classification profiles to produce an encrypted DF (EDF). The method further comprises determining a first user to be a member of the first user classification profile, and providing access to the EDF and a first decryption key useable to decrypt the first encrypted region to the first user.

Abstract: Aspects of the invention include a computer-implemented method by executing, via a processor, a bottleneck model training process for microservices in a microservice system, wherein for each of the microservices the bottleneck model training process filters out a subset of training data based at least in part on a current situation setting. Building, via the processor, a bottleneck indicator model for each of the microservices using information from the bottleneck model training process, convergence points for an expected response time. Executing, via the processor, a bottleneck identification process for providing system alerts when a bottleneck is identified, wherein the bottleneck identification process uses analysis to monitor a data stream according to the bottleneck indicator model which uses the convergence points for response times.

Abstract: Computer-implemented methods, computer program products, and computer systems are provided. A method includes generating a running result matrix for a plurality of batch jobs, indicating corresponding running results for respective processing actions in batch jobs of the plurality of batch jobs. The method further includes obtaining an internal dependency matrix for the plurality of batch jobs, indicating corresponding dependencies between respective processing actions within a batch job of the plurality of batch jobs. The method further includes calculating a recovery matrix for the plurality of batch jobs based, at least in part, on the running result matrix and the internal dependency matrix, the recovery matrix indicating corresponding recovery actions for respective processing actions in batch jobs of the plurality of batch jobs. The method further includes executing failover management for one or more batch jobs based, at least in part, on the calculated recovery matrix.

Abstract: Computer-implemented methods, computer program products, and computer systems are provided. A method includes generating a running result matrix for a plurality of batch jobs, indicating corresponding running results for respective processing actions in batch jobs of the plurality of batch jobs. The method further includes obtaining an internal dependency matrix for the plurality of batch jobs, indicating corresponding dependencies between respective processing actions within a batch job of the plurality of batch jobs. The method further includes calculating a recovery matrix for the plurality of batch jobs based, at least in part, on the running result matrix and the internal dependency matrix, the recovery matrix indicating corresponding recovery actions for respective processing actions in batch jobs of the plurality of batch jobs. The method further includes executing failover management for one or more batch jobs based, at least in part, on the calculated recovery matrix.

Abstract: In an approach, a processor obtains a first set of training samples, one of the training samples including values of a plurality of performance indicators of a target system observed at a historical point in time. A processor determines whether the first set of training samples are qualified for training a prediction model, the prediction model predicting an operational status of the target system at a target point in time based on values of the plurality of performance indicators observed at the target point in time. A processor, in response to determining that the first set of training samples are qualified for training the prediction model, trains, the prediction model based on the first set of training samples.

Abstract: An approach is provided in which a set of provision information is generated from a set of provisioners that are in process of fulfilling a client's provision request. The approach creates a set of provision events based on the set of provision information and, in response to detecting a failure of the provision request, the approach generates a provision chain from the set of provision events. The provision chain links the set of provision events based on correlation rules and identifies at least one isolation point of the failure. The approach informs the client of the at least one isolation point of the failure identified in the provision chain.

Abstract: Embodiments include cognitive control of runtime resource monitoring scope. Aspects include obtaining historical data for each of a plurality of metrics for a computer system and calculating, based on the historical data, an anomaly relationship score for each of the plurality of metrics. Aspects also include calculating, based on the historical data, a sensitivity score for each of the plurality of metrics and determining a priority score for each of the plurality of metrics based upon a weighted combination of the anomaly relationship score and the priority score. Aspects further include receiving real-time data for each of the plurality of metrics and presenting a subset of the real-time data to a user, the subset created by selecting one or more of the plurality of metrics based on the priority score of each of the plurality of metrics.

Abstract: Embodiments include cognitive control of runtime resource monitoring scope. Aspects include obtaining historical data for each of a plurality of metrics for a computer system and calculating, based on the historical data, an anomaly relationship score for each of the plurality of metrics. Aspects also include calculating, based on the historical data, a sensitivity score for each of the plurality of metrics and determining a priority score for each of the plurality of metrics based upon a weighted combination of the anomaly relationship score and the priority score. Aspects further include receiving real-time data for each of the plurality of metrics and presenting a subset of the real-time data to a user, the subset created by selecting one or more of the plurality of metrics based on the priority score of each of the plurality of metrics.

Abstract: Aspects of the invention include detecting and predicting application performance. A non-limiting example computer-implemented method includes receiving source code and generating a first model of the source code by labeling a word of the source code. The computer implemented method optimizes the first model of the source code by assembling the first model of the source code with a plurality of models generated by a model generation module into a second model of the source code and extracts at least two basic features from the second model of the source code. The computer-implemented method provides an estimated performance of the source code based on historical data of the basic features extracted from the second model of the source code.

Abstract: In an approach for maintaining data synchronization, a processor scans a set of data fields at each stage of a data analysis process. A processor generates a relationship tree model, wherein the set of data fields each correspond to a node in the relationship tree model. A processor prunes the relationship tree model. Responsive to an update to a data field of the set of data fields, a processor promulgates the update using the relationship tree model to generate an updated set of insight data. A processor outputs the updated set of insight data.