Shared function container across serverless platforms to mitigate cold start performance penalties
AssigneeDell Products L.P.
InventorsTomasz Podsiadlik, Joel Christner, John Power, Patricia Quill
Life of this patent
Estimating the term…
Abstract
Shared function execution mitigates cold start penalties for execution units. When a serverless platform receives a request, the request is performed when the serverless platform has a warm execution unit for the request. If a warm execution unit is not available or running, the serverless platform may send the request to another serverless platform rather than cold start an execution unit. The cold start is performed when the warm execution unit is not available at other platforms.
Claims20
A method comprising:
- receiving a request at a serverless platform from a client;
- determining whether the serverless platform has an instance of a execution unit running on the serverless platform to perform the request;
- performing the request with the instance of the execution unit when the instance of the execution unit is present and running on serverless platform,
- wherein the serverless platform, when the instance of the execution unit is not present and not running on the serverless platform, accesses a container table to determine a second instance of the execution unit is running on a second serverless platform and transmits the request to the second serverless platform when the second instance of the execution unit is running at the second serverless platform;
- and
- returning a response to the client after the request is performed,
- wherein the container table identifies instances of execution units that are present and running on serverless platforms, wherein the serverless platforms represented in the container table includes the serverless platform and the second serverless platform.
A non-transitory storage medium having stored therein instructions that are executable by one or more hardware processors to perform operations comprising:
- receiving a request at a serverless platform from a client;
- determining whether the serverless platform has an instance of a execution unit running to perform the request;
- performing the request with the instance of the execution unit when the instance of the execution unit is present and running on serverless platform,
- wherein the serverless platform, when the instance of the execution unit is not present and not running on the serverless platform, accesses a container table to determine whether a second instance of the execution unit is running on a second serverless platform and transmits the request to the second serverless platform when the second instance of the execution unit is running at the second serverless platform;
- and
- returning a response to the client after the request is performed,
- wherein the container table identifies instances of execution units that are present and running on other serverless platforms, wherein the serverless platforms represented in the container table includes the serverless platform and the second serverless platform.
Dependencies are inferred from the claim text.