A method and apparatus for dynamically adjusting an ingestion rate for backup operations on a source system. The method generally includes monitoring a resource utilization related to one or more performance metrics of the source system in performing at least a primary workload. Based on the monitored resource utilization, the backup system determines a data ingestion rate for backup operations on the source system. The backup system ingests data from the source system to a backup repository at the determined data ingestion rate.

A method and system are provided for monitoring a protected network. The method includes, in a scoring phase, receiving a learned model having clusters of learning requests of learning network traffic observed during non-strain operation of the protected network, wherein each cluster has an associated characteristic learning response time. The method further includes receiving a score request to score a network service request of the network traffic, classifying the network service request with one of the clusters by comparing fields of the network service request to fields used for clustering the learning requests with the cluster, calculating a score based on the characteristic learning response times generated for the learned cluster to which the network service request is classified, and adjusting supportive handling of the network service request based on the score.

A method and system are provided for monitoring a protected network. The method includes, in a scoring phase, receiving a learned model having clusters of learning requests of learning network traffic observed during non-strain operation of the protected network, wherein each cluster has an associated characteristic learning response time. The method further includes receiving a score request to score a network service request of the network traffic, classifying the network service request with one of the clusters by comparing fields of the network service request to fields used for clustering the learning requests with the cluster, calculating a score based on the characteristic learning response times generated for the learned cluster to which the network service request is classified, and adjusting supportive handling of the network service request based on the score.

Apparatus and methods are disclosed for processing messages from agents of a network environment including the use of collectors. Collectors can use configurable pipelines to improve processing of messages received from the agents. In one example of the disclosed technology, a number of networked agents are configured to gather data describing operational aspects of an agent's computing host. A collector is configured to receive reports from the agent and send the gathered data to one or more destination agent data consumers designated by augmentation information in the reports. In some examples, the collector transforms data using one or more stage selector rules.

Apparatus and methods are disclosed for processing messages from agents of a network environment including the use of collectors. Collectors can use configurable pipelines to improve processing of messages received from the agents. In one example of the disclosed technology, a number of networked agents are configured to gather data describing operational aspects of an agent's computing host. A collector is configured to receive reports from the agent and send the gathered data to one or more destination agent data consumers designated by augmentation information in the reports. In some examples, the collector transforms data using one or more stage selector rules.

Techniques for data source driven expected network policy control are described. A policy enforcement service receives, from a compute instance in a virtual network implemented within a service provider system, a request to access data. The policy enforcement service determines that a virtual network security condition of a policy statement is not satisfied. The policy statement was configured by a user for use in controlling access to the data. The virtual network security condition defines a condition of the virtual network that is to be met. The policy enforcement service performs one or more security actions in response to the determination that the virtual network security condition of the policy statement is not satisfied.

A computer-implemented method upgrades an edge network based on analysis by a learning model. The method includes identifying, in a network, a plurality of devices, where each device in the network is configured to provide data on at least one other device in the network. The method also includes determining capabilities of each device of the plurality of devices. The method further includes monitoring, for each device, capacity information and tasks performed during operation of the network. The method includes analyzing, based on the monitoring, each use of each device. The method also includes recommending, in response to the analyzing and by a learning model, a first upgrade to the network. The method further includes implementing the first upgrade.

Architectures and techniques are presented that provide an improved mechanism for a subscriber entity to report to a network provider a network issue that affects the performance of an application that uses a service provided by the network provider. The improved mechanism can enable fine granularity with respect to the network issue by identifying the issue on a per-session basis. In response to feedback data that is reported by the subscriber entity, the network provider can perform self-healing or other upgrade techniques to rapidly remedy the network issue.

Architectures and techniques are presented that provide an improved mechanism for a subscriber entity to report to a network provider a network issue that affects the performance of an application that uses a service provided by the network provider. The improved mechanism can enable fine granularity with respect to the network issue by identifying the issue on a per-session basis. In response to feedback data that is reported by the subscriber entity, the network provider can perform self-healing or other upgrade techniques to rapidly remedy the network issue.

In one embodiment, a service that monitors a network detects a plurality of anomalies in the network. The service uses data regarding the detected anomalies as input to one or more machine learning models. The service maps, using a conceptual space, outputs of the one or more machine learning models to symbols. The service applies a symbolic reasoning engine to the symbols, to rank the anomalies. The service sends an alert for a particular one of the detected anomalies to a user interface, based on its corresponding rank.