Methods and system are presented for monitoring database processes to generate machine learning predictions. A plurality of database processes executed on database implementations can be monitored, wherein the monitoring includes determining a start time, an end time, and a number of rows impacted by portions of the database processes, and the monitored database processes generate instances of machine learning data including at least the number of rows impacted and an associated duration of time. Using a machine learning component and the machine learning data, a duration of time can be predicted for a candidate database process for execution on a database implementation.

A method and system for distributing a compute model and data to process to heterogeneous and distributed compute devices. The compute model and a portion of the data is processed on a benchmark system and the timing used to make a job execution speed estimate for each compute device. Compute devices are selected and assigned data chunks based on the estimate so distributed processing is completed within a predefined time period. The compute model and data chunks can be sent to the respective compute devices using separate processes, such as a payload manager configured to transfer compute jobs to remote devices and a messaging engine configured to transfer data messages, and where the payload manager and messaging engine communicate with corresponding software engines on the compute devices.

Methods, apparatus, and processor-readable storage media for server classification using machine learning techniques are provided herein. An example computer-implemented method includes obtaining, from at least one data source, data pertaining to server activity attributed to one or more servers; processing at least a portion of the obtained data using one or more rule-based analyses; selecting at least a particular machine learning classification algorithm from a set of multiple machine learning classification algorithms, based at least in part on results from the processing and one or more portions of the obtained data; classifying an activity level of at least a portion of the one or more servers by processing at least a portion of the obtained data using the selected machine learning classification algorithm; and performing at least one automated action based at least in part on results of the classifying.

Technology for computerized anomaly detection, where the machine logic (for example, software) utilizes a multi-layer anomaly detection method that may include three (3) layers: (a) a baseline model for each feature at a single point, (b) a dynamic time window for historical data, and/or (c) correlation analysis for different model features.

Aspects of the present disclosure relate to the visualization of product usage utilizing telemetry data associated with the product. More specifically, a first object identifier associated with an object, such as a method, function, or other portion of code, may be provided as part of the telemetry data together with an execution time stamp. A second object identifier may also be received, where the second object identifier is associated with object execution subsequent to the first object. Based on the first and second object identifier, an object pair may be determined and graphed at a path execution tree. In some instances, the object pairs may be filtered in accordance with a number of occurrences within a certain period of time, where a high number of occurrences is indicative of an intended path of one or more users.

A system and method for inferring device models. The method includes determining block statistics for each block of a plurality of blocks of a plurality of media access control (MAC) addresses, the plurality of blocks having a plurality of respective prefixes, wherein the plurality of blocks are grouped based on commonalities among the plurality of respective prefixes; generating an aggregated statistical model for the plurality of blocks based on the plurality of MAC addresses and the block statistics, wherein each block is a string of digits included in one of the plurality of MAC addresses; and applying the aggregated statistical model to the block statistics of at least one block of the plurality of blocks in order to determine at least one inferred device model, wherein each of the at least one block is grouped into the same group.

Properties associated with computing resources are received. At least a portion of the received properties is used to cluster the computing resources into one or more operating groups. At least a portion of the received properties is used to determine a recommendation of an operation schedule for at least one of the one or more operating groups. The recommendation is provided. A feedback is received in response to the recommendation.

Methods and systems for detecting and responding to erroneous application configurations are presented. In one embodiment, a method is provided that includes receiving a configuration for an application and receiving execution metrics for the application. The configuration and the execution metrics may be compared to a knowledge base of reference configurations and reference execution metrics and a particular reference configuration may be identified from the knowledge base that corresponds to the configuration. The particular reference configuration may represent an erroneous configuration of the application that needs to be corrected. A configuration correction may then be identified based on the particular reference configuration.

A command is transmitted to a storage device to relocate first data that partially fills a first erase block of the storage device and second data that partially fills a second erase block of the storage device to a third erase block of the storage device, wherein the command causes the relocation of the first data and the second data while bypassing sending the data to the storage controller. An acknowledgement that the first data and the second data have been stored at the third erase block is received from the storage device.

Methods and systems for detecting and responding to an anomaly include determining a first system-level performance prediction using system-level statistics. A second system-level performance prediction is determined using system-level statistics and service-level statistics. The first prediction to the second prediction are compared to identify a discrepancy. It is determined that a service corresponding to the service-level statistics is a cause of a detected failure in a distributed computing system. An action directed to the service is performed responsive to the detected failure.