Abstract: Methods, computer readable media, and devices for quantifying an infrastructure service health as a score and optimizing performance of the infrastructure service based on benchmarks of dynamically identified control groups are disclosed. One method may include determining, for an infrastructure service of an organization, a metric health score for one or more metrics and an overall health score for the organization, creating, for at least one of the metrics, a number of control groups based on a timeframe criteria and including a set of organizations having a metric health score for the timeframe criteria similar to the organization, and maximizing performance of the infrastructure service using machine learning to compare, for at least one metric, performance impacts to the organization based on service changes with the number of control groups for the at least one metric.

Abstract: A method of early warning and risk assessment of incidents in a multi-tenant cloud environment is provided. The method includes: capturing a plurality of data metrics; automatically generating derived features from the plurality of captured data metrics; automatically selecting risk assessment features from the derived features and the captured data metrics; and predicting the risk of an incident in the multi-tenant cloud environment within a specified time window in the future and one or more possible root causes of the incident by applying the newly selected risk assessment features to a trained risk assessment model. The trained risk assessment model has been trained using machine learning techniques to predict the risk of an incident in the multi-tenant cloud environment within a specified time window in the future, provide an explanation of possible root causes of the incident, and assign a strength level to each possible root cause.

Abstract: A method of data processing includes identifying a segment of entity identifiers that are associated with a target tenant and correspond to a set of clients that are to receive at least one content object via a first channel of a plurality of supported channels. The method includes modifying a feature associated with communication of content for a test subset of the segment relative to a control subset of the segment, determining a first metric corresponding to the control subset and the test subset in association with the communication of the content via the first channel and a second metric associated with the target tenant over a second channel of the plurality of channels. The method includes comparing the second metric to a metric associated with a peer group of tenants, and adjusting subsequent communications for the target based at least in part on the comparing and the first metric.

Abstract: System and methods are described for anomaly detection and root cause analysis in database systems, such as multi-tenant environments. In one implementation, a method comprises receiving an activity signal representative of resource utilization within a multi-tenant environment; detecting a plurality of anomalies in the activity signal; computing a priority score for each of the plurality of anomalies; correlating at least a subset of the plurality of anomalies to one or more performance metrics of the multi-tenant environment; and transmitting a remediation signal to one or more devices in the multi-tenant environment based on the correlations and the priority scores.

Abstract: Multitier, multitenant architecture of pods comprise multiple stacks with different metrics and workload compositions that constantly change over time. A computer system may identify an overall pod time-to-live (TTL) based on the changing metrics and workloads. The TTL may be a forecasted time that pod remediation is needed to avoid negative impact on pod performance and customer experience. Additionally, the computer system may identify the appropriate remediation(s) for each pod. The computer system may compare and prioritize remediations across a collection of pods with different configurations and workload characteristics based on the TTLs. Other embodiments may be described and/or claimed.

Abstract: A method of early warning and risk assessment of incidents in a multi-tenant cloud environment is provided. The method includes: capturing a plurality of data metrics; automatically generating derived features from the plurality of captured data metrics; automatically selecting risk assessment features from the derived features and the captured data metrics; and predicting the risk of an incident in the multi-tenant cloud environment within a specified time window in the future and one or more possible root causes of the incident by applying the newly selected risk assessment features to a trained risk assessment model. The trained risk assessment model has been trained using machine learning techniques to predict the risk of an incident in the multi-tenant cloud environment within a specified time window in the future, provide an explanation of possible root causes of the incident, and assign a strength level to each possible root cause.

Abstract: Among other things, embodiments of the present disclosure relate to detecting performance degradation in database systems. For example, some embodiments of the present disclosure help to identify events associated with anomalous database system parameter states and assess the severity of such anomalous events. Other embodiments may be described and/or claimed.

Abstract: Among other things, embodiments of the present disclosure relate to detecting performance degradation in database systems. Other embodiments may be described and/or claimed.

Abstract: Multitier, multitenant architecture of pods comprise multiple stacks with different metrics and workload compositions that constantly change over time. A computer system may identify an overall pod time-to-live (TTL) based on the changing metrics and workloads. The TTL may be a forecasted time that pod remediation is needed to avoid negative impact on pod performance and customer experience. Additionally, the computer system may identify the appropriate remediation(s) for each pod. The computer system may compare and prioritize remediations across a collection of pods with different configurations and workload characteristics based on the TTLs. Other embodiments may be described and/or claimed.

Abstract: An information system identifies redundant communication paths between a server and a storage device in a storage area network and classifies the state of the paths according to the distribution of workload amongst them. To make the classification, the information system pairs up active paths. For each pair of active paths, the information system identifies traffic data of the two paths. The information system compares the traffic data of the two paths. Based on the comparison, the information system determines whether workload is balanced or imbalanced between the two paths.

Abstract: For each monitored entity in a storage area network (SAN), metric data associated with the entity is collected. Based on the metric data of an entity, a determination is made as to whether the entity experienced abnormal events. For each entity for which one or more abnormal events are identified, the information system determines an aggregated event score based on the abnormal events identified for the entity. Representation of the entities are presented to a user, where the representations are ordered based on the aggregated event scores of the entities.

Abstract: A link in a storage area network (SAN) is identified that is being affected by one or more slow draining devices. Devices in the SAN are identified as candidates for potentially being a slow draining device affecting the link. For each identified candidate device, metric data is identified that describes, for example, traffic activity of the candidate device, such as data transmission rates of the candidate device. Additionally, metric data is identified for the link. For each candidate device, a correlation value is determined that indicates the likelihood that the candidate device is a slow draining device affecting the link. The correlation value of a candidate device is determined based on the correlation between the metric data of the device and the metric data of the link. One or more of the correlation values are presented to a user via a user interface.

Abstract: A monitoring system maintains multiple counts. Each of these counts is associated with a range and indicates a number of network transactions that occurred in a storage area network (SAN) during a time period with values that are within the associated range. When the monitoring system identifies the occurrence of a network transaction between devices in the SAN, the monitoring system determines a time duration and/or a size of the network transaction. The monitoring system identifies a count associated with a time range that includes the determined time duration and increments the identified count. Additionally, the monitoring system identifies a count associated with a size range that includes the determined size and increments the identified count.

Abstract: An information system identifies redundant communication paths between a server and a storage device in a storage area network and classifies the state of the paths according to the distribution of workload amongst them. To make the classification, the information system pairs up active paths. For each pair of active paths, the information system identifies traffic data of the two paths. The information system compares the traffic data of the two paths. Based on the comparison, the information system determines whether workload is balanced or imbalanced between the two paths.