Automatic demand-driven resource scaling for relational database-as-a-service

A database-as-a-service method, comprising acts of:

• computing container sizes of containers for databases based on production telemetry from the databases by assigning specific container sizes to resource utilization values, each of the containers comprising a plurality of resources;
• transforming the telemetry into a plurality of signals, each of the plurality of signals representing performance data for one or more of the plurality of resources in a container;
• determining a state of each of the plurality of signals by applying a corresponding latency threshold to each of the plurality signals;
• combining the states of each of the plurality of signals to estimate a resource demand for the container;
• and
• automatically scaling a size of the container for a billing interval on behalf of a tenant based on a demand of the one or more of the plurality of resources in the container.

A database-as-a-service method, comprising acts of:

• collecting telemetry of database servers, wherein the database servers host containers for corresponding tenant databases, the containers each having corresponding container sizes based on resource utilization values, each of the containers comprising a plurality of resources;
• estimating resource demands of the containers based on processing of the telemetry;
• transforming the telemetry into a plurality of signals, each of the plurality of signals representing performance data for one or more of the plurality of resources in a container;
• determining a state of each of the plurality of signals by applying a corresponding latency threshold to each of the plurality signals;
• combining the states of each of the plurality of signals to estimate a resource demand for the container;
• and
• automatically scaling a size of the container for a subsequent billing interval in correlation with a demand of the one or more of the plurality of resources in for the container.