Abstract: An apparatus comprises a processing device configured to obtain monitoring data for devices comprising a plurality of features, determining two or more rankings of the features using two or more filter-based feature selection algorithms, and selecting a subset of the features based at least in part on the two or more rankings. The processing device is also configured to generate a failure prediction for a given one of the devices using at least one classifier that takes as input the selected subset of features, and applying a conformal prediction framework to the generated failure prediction to obtain a confidence measure indicating a quality of the generated failure prediction and a credibility measure indicating a quality of the monitoring data. The processing device is further configured to initiate one or more remedial actions based at least in part on the generated failure prediction, the confidence measure, and the credibility measure.

Abstract: An apparatus comprises a processing device configured to receive a request to schedule a workload and to generate a graph representation of tasks of the workload, the graph representation comprising two or more levels each comprising nodes representing tasks of the workload. The processing device is also configured to identify a plurality of paths each representing a sequence of tasks of the workload that starts at a root node in a first level of the graph representation and traverses one or more additional nodes in one or more additional levels of the graph representation. The processing device is further configured to determine a ranking of the plurality of paths and to assign the tasks of the workload for execution on assets of an information technology infrastructure based at least in part on the determined ranking of the plurality of paths.

Abstract: Systems and methods for implementing a workload fairness policy at the data cache level within a non-volatile memory express solid-state drive utilizes a prioritization technique that predicts a degree of intensity for workloads based on a request generation rate. The degree of intensity is used to prioritize and rank workloads, thereby, avoiding interference between requests from each other.

Abstract: Security drift can be automatically handled in cloud environments. A security audit engine can be configured to extract security configuration datasets from cloud resources and create text sentences from the datasets as well as from a golden configuration. These text sentences can be encoded as vectors in an n-dimensional space. Probability distributions can then be generated using the vectors such as by using an unsupervised clustering algorithm. Distance matrixes can then be generated from the probability distributions. A probability distribution pertaining to a dataset and a probability distribution pertaining to the golden configuration can then be compared and normalized using a transport to thereby yield a security drift score representing a divergence of the corresponding security settings from the golden configuration. When a security drift score exceeds a threshold, the security audit engine can take appropriate action.

Abstract: An apparatus comprises a processing device configured to obtain workload traces characterizing resource execution metrics associated with workloads executing in an information technology infrastructure and to generate sets of workload causality profiles characterizing relationships between the resource execution metrics, the sets of workload causality profiles comprising first and at least second sets of workload causality profiles generated using first and at least second different types of models. The processing device is also configured to determine sets of causal topics comprising recurring patterns of the relationships between different ones of the resource execution metrics found in each of the sets of workload causality profiles. The processing device is further configured to identify clusters of causal topics each comprising at least one causal topic that is part of the first and second sets of causal topics, and to perform diagnosis of issues affecting the workloads based on the identified clusters.

Abstract: A method for managing bugs includes obtaining, by a bug deduplication system, a set of bugs, performing an encoding on each section of a first bug of the set of bugs to obtain encoded sections, wherein the encoded sections comprise a first encoded section and a second encoded section, applying a first classification model to the first encoded section to obtain a first section score, applying a second classification model to the second encoded section to obtain a second section score, generating a confidence score based on the first encoded section and the second section, and providing the confidence score to a client, wherein the client initiates a corrective action for the first bug based on the confidence score.

Abstract: A method for managing bugs includes obtaining, by a bug deduplication system, a set of bugs, performing an encoding on each section of a first bug of the set of bugs to obtain encoded sections, wherein the encoded sections comprise a first encoded section and a second encoded section, applying a first classification model to the first encoded section to obtain a first section score, applying a second classification model to the second encoded section to obtain a second section score, generating a confidence score based on the first encoded section and the second section, and providing the confidence score to a client, wherein the client initiates a corrective action for the first bug based on the confidence score.

Abstract: An apparatus comprises a processing device configured to receive a request to schedule a workload and to generate a graph representation of tasks of the workload, the graph representation comprising two or more levels each comprising nodes representing tasks of the workload. The processing device is also configured to identify a plurality of paths each representing a sequence of tasks of the workload that starts at a root node in a first level of the graph representation and traverses one or more additional nodes in one or more additional levels of the graph representation. The processing device is further configured to determine a ranking of the plurality of paths and to assign the tasks of the workload for execution on assets of an information technology infrastructure based at least in part on the determined ranking of the plurality of paths.

Abstract: An apparatus comprises at least one processing device configured to generate, for a storage system that is part of an active tier of a storage environment, at least one storage capacity forecast comprising probability values for storage capacity of the storage system over a designated time period. The processing device is also configured to determine whether any of the probability values exceed at least one designated storage capacity threshold and, responsive to determining that a given one of the probability values exceeds the at least one designated storage capacity threshold, to select remedial actions for freeing up space on the active tier of the storage environment. The processing device is further configured to initiate the selected remedial actions for freeing up space on the active tier of the storage environment to prevent the storage system from reaching a designated storage capacity error condition.

Abstract: An apparatus comprises a processing device configured to obtain monitoring data for devices comprising a plurality of features, determining two or more rankings of the features using two or more filter-based feature selection algorithms, and selecting a subset of the features based at least in part on the two or more rankings. The processing device is also configured to generate a failure prediction for a given one of the devices using at least one classifier that takes as input the selected subset of features, and applying a conformal prediction framework to the generated failure prediction to obtain a confidence measure indicating a quality of the generated failure prediction and a credibility measure indicating a quality of the monitoring data. The processing device is further configured to initiate one or more remedial actions based at least in part on the generated failure prediction, the confidence measure, and the credibility measure.

Abstract: An apparatus comprises at least one processing device configured to generate, for a storage system that is part of an active tier of a storage environment, at least one storage capacity forecast comprising probability values for storage capacity of the storage system over a designated time period. The processing device is also configured to determine whether any of the probability values exceed at least one designated storage capacity threshold and, responsive to determining that a given one of the probability values exceeds the at least one designated storage capacity threshold, to select remedial actions for freeing up space on the active tier of the storage environment. The processing device is further configured to initiate the selected remedial actions for freeing up space on the active tier of the storage environment to prevent the storage system from reaching a designated storage capacity error condition.