Threading as a service

摘要

A service manages a plurality of virtual machine instances for low latency execution of user codes. The plurality of virtual machine instances can be configured based on a predetermined set of configurations. One or more containers may be created within the virtual machine instances. In response to a request to execute user code, the service identifies a pre-configured virtual machine instance suitable for executing the user code. The service can allocate the identified virtual machine instance to the user, create a new container within an instance already allocated to the user, or re-use a container already created for execution of the user code. When the user code has not been activated for a time-out period, the service can invalidate allocation of the virtual machine instance destroy the container. The time from receiving the request to beginning code execution is less than a predetermined duration, for example, 100 ms.

主权项

1. A computer implemented method to process requests to execute user code on one or more virtual machine instances, the method comprising:
as implemented by one or more computing devices configured with specific computer-executable instructions, providing a plurality of warmed virtual machine instances, each of the warmed virtual machine instances being unassigned to a specific user and containing a software component associated with a programming language; subsequent to providing the plurality of warmed, unassigned virtual machine instances, receiving a request to execute a user code, the request comprising configuration information associated with executing the user code, wherein the request is received at a first time; identifying a virtual machine instance from the plurality of warmed virtual machine instances based on the configuration information of the request, wherein the identified virtual machine instance contains a particular software component that is suitable to execute the user code; associating the identified virtual machine instance with a user account associated with the request; creating, within the associated virtual machine instance, a container to execute the user code; loading the particular software component and the user code into the container; and initiating execution of the user code by the container, wherein said initiating occurs at a second time, and wherein a time period from the first time to the second time is less than a predetermined duration.