Abstract: The disclosure describes systems and methods for minimizing latency for users accessing services hosted on a cloud-computing system. A device receives a request to deploy a compute container to provide services to a prefix. The device determines a first prefix-connection location of the prefix. The device deploys the compute container based on the first prefix-connection location. The device determines a second prefix-connection location of the prefix. The device determines that the second prefix-connection location is different from the first prefix-connection location. The device migrates the compute container based on the second prefix-connection location.

Abstract: The disclosure describes systems and methods for minimizing latency for users accessing services hosted on a cloud-computing system. A service of the cloud-computing system periodically queries edge sites of the cloud-computing system for information regarding containers stored on the edge sites. In response to the queries, the edge sites provide information identifying containers hosted on the edge sites, prefixes that the containers service, and connection locations where traffic from the prefixes enter the cloud-computing system. The service may determine whether the connection locations have changed. If a connection location for a prefix has changed, the service modifies a location of a container servicing the prefix. The service may migrate the container to a current connection location for the prefix. Modifying the location may reduce latency experienced by users behind the prefix.

Abstract: The disclosure describes systems and methods for minimizing latency for users accessing services hosted on a cloud-computing system. A service of the cloud-computing system periodically queries edge sites of the cloud-computing system for information regarding containers stored on the edge sites. In response to the queries, the edge sites provide information identifying containers hosted on the edge sites, prefixes that the containers service, and connection locations where traffic from the prefixes enter the cloud-computing system. The service may determine whether the connection locations have changed. If a connection location for a prefix has changed, the service modifies a location of a container servicing the prefix. The service may migrate the container to a current connection location for the prefix. Modifying the location may reduce latency experienced by users behind the prefix.

Abstract: The disclosure describes systems and methods for minimizing latency for users accessing services hosted on a cloud-computing system. A service of the cloud-computing system periodically queries edge sites of the cloud-computing system for information regarding containers stored on the edge sites. In response to the queries, the edge sites provide information identifying containers hosted on the edge sites, prefixes that the containers service, and connection locations where traffic from the prefixes enter the cloud-computing system. The service may determine whether the connection locations have changed. If a connection location for a prefix has changed, the service modifies a location of a container servicing the prefix. The service may migrate the container to a current connection location for the prefix. Modifying the location may reduce latency experienced by users behind the prefix.

Abstract: The disclosure describes systems and methods for minimizing latency for users accessing services hosted on a cloud-computing system. A service of the cloud-computing system periodically queries edge sites of the cloud-computing system for information regarding containers stored on the edge sites. In response to the queries, the edge sites provide information identifying containers hosted on the edge sites, prefixes that the containers service, and connection locations where traffic from the prefixes enter the cloud-computing system. The service may determine whether the connection locations have changed. If a connection location for a prefix has changed, the service modifies a location of a container servicing the prefix. The service may migrate the container to a current connection location for the prefix. Modifying the location may reduce latency experienced by users behind the prefix.

Abstract: Techniques for generating reports from cached data are provided. When a report is requested, a date and time when data in the report data cache was generated is compared with a date and time when data was collected by each of one or more data collectors that gather data used to generate the report data. If one of the data collectors has collected data since the data for the report in the report data cache has been updated, the data for the requested report will be regenerated from the data collected from each of the data collectors associated with the report and the regenerated data inserted into the report data cache. Subsequent requests for the report can be satisfied by generating the report using the data stored in the report data cache rather than regenerating the report data each time a request for a report is received.

Abstract: Techniques for generating reports from cached data are provided. When a report is requested, a date and time when data in the report data cache was generated is compared with a date and time when data was collected by each of one or more data collectors that gather data used to generate the report data. If one of the data collectors has collected data since the data for the report in the report data cache has been updated, the data for the requested report will be regenerated from the data collected from each of the data collectors associated with the report and the regenerated data inserted into the report data cache. Subsequent requests for the report can be satisfied by generating the report using the data stored in the report data cache rather than regenerating the report data each time a request for a report is received.