Described are systems and methods of detecting processes causing degradation of machine performance using heuristics. A device may identify a plurality of time intervals having a use of a resource on a machine above a threshold. The device may identify a percentage of the use of the resource by each of a plurality processes on the machine using the resource during each time interval of the plurality of time intervals. The device may determine a score for each process of the plurality processes based at least on a function of the percentage of the use of the resource over one or more of the plurality of time intervals in which each process used the resource. The device may provide, for display, a selection of one or more processes from the plurality of processes ranked by the score.

In computer-implemented method, computer system, and/or computer program product, a processor(s) obtains a test (of steps(s)) to verify program code for deployment in distributed computing system. The processor(s) determines pre-defined operations correlating to the step(s). The processor(s) automatically distributes the pre-defined operations to a resources of a distributed computing system, for execution. The processor(s) monitors the execution and saves at least one screenshot as each step. The processor(s) generates a user interface with a status indicator. The processor(s) continuously update the user interface, based on the monitoring, to reflect a progression of the portion of the one or more resources through the step(s).

In general, embodiments of the invention relate to a method for generating upgrade recommendations. The method comprising obtaining telemetry data for a target entity, determining, using the telemetry data, at least one of a predicted upgrade time and a upgrade readiness factor for the target entity, generating an recommendation based on the at least one of the predicted upgrade time and the upgrade readiness factor for the target entity, and initiating a display of the recommendation on a graphical user interface of client.

A testing system and method for testing application code against various failure scenarios. The testing system and method generate a test workflow including test source code implementing a series of actions that affect an application component and or an infrastructure component included in application code. The testing system and method execute the test workflow to determine the performance of the application code during one or more failure scenarios caused by the series of actions included in the test workflow. Performance data generated by the test code is analyzed by a performance analysis service or method to identify limitations of the application code and build resiliency patterns that address the limitations and improve the performance of the application code.

Aspects of the disclosure provide for methods, systems, and apparatus, including computer-readable storage media, for anomaly detection using a machine learning framework trained entirely on unlabeled training data including both anomalous and non-anomalous training examples. A self-supervised one-class classifier (STOC) refines the training data to exclude anomalous training examples, using an ensemble of machine learning models. The ensemble of models are retrained on the refined training data. The STOC can also use the refined training data to train a representation learning model to generate one or more feature values for each training example, which can be processed by the trained ensemble of models and eventually used for training an output classifier model to predict whether input data is indicative of anomalous or non-anomalous data.

Mechanisms and techniques are employed for managing the allocation and load balancing of storage system resources for the containerized, distributed execution of applications on a storage system. A control component executing on a processing component of the storage system may control reserving the necessary resources on one or more processing components to implement an application, and control a container management module to create, deploy and/or modify one or more containers on one or more processing components of the storage system. The one or more containers then may be executed to implement the application. Multiple processing components of the storage system may have a resource management module executing thereon. The control component may exchange communications with the one or more resource management modules of each processing component to determine the resources available within the processing component; e.g., to determine whether the processing component can satisfy the resource requirements of the application.

A crash prediction computing system includes a machine learning module capable of analyzing data logs associated with each of a plurality of services or applications to identify and categorize every error, exception, and/or crash, such as those resulting from client system interactions based on crash type, customer profile type, customer screen navigation flow, time or crash. The machine learning algorithms continuously train the crash prediction models for each crash category with associated client computing system navigation flow. The crash prediction computing system applies each model before each screen/activity navigation to predict whether the next move will result in an error, exception or crash, and for each predicted error, exception, or crash, automatically implement alternate route functionality to arrive at a desired target.

A method including performing tests for a computer software that emulate user or application behavior when using the computer software, detecting a first set of resource properties when performing the tests on the computer software, identifying behavior patterns based on a series the event records created from the resource properties detected when running the tests, detecting a second set of properties of resources running the computer software following release of the computer software, comparing the behavior patterns extracted from the tests with a second behavior pattern extracted from real-life operation after release of the computer software, detecting normal software behavior and unnormal software behavior based on the differences between the behavior patterns extracted from the tests and second behavior pattern.

Techniques for automatic adaptive anomaly detection are disclosed. In some embodiments, a system, a process, and/or a computer program product for automatic anomaly detection includes handling invalid or missing data, building a model for the normal or typical statistical relationship between data, using the model to generate an anomaly score for each input set of data, threshold detection and persistence filtering, and automatic label generation for detected anomalies.

A system and method are disclosed associated with a cloud computing environment. The system includes a tracing tool, coupled to a controller in the cloud computing environment, that captures sequences of events associated with the controller and a deployed workload. A detection engine may detect important event patterns in the sequences captured by the tracing tool using a PrefixSpan algorithm in connection with a specific controller action associated with the deployed workload. A neural network, trained with the detected important event patterns, may predict which important event patterns caused the controller to perform the specific action associated with the deployed workload.