Anticipatory response pre-caching

摘要

Interaction between a client and a service in which the service responds to requests from the client. In addition to responding to specific client requests, the service also anticipates or speculates about what the client may request in the future. Rather than await the client request (that may or may not ultimately be made), the service provides the unrequested anticipatory data to the client in the same data stream as the response data that actual responds to the specific client requests. The client may then use the anticipatory data to fully or partially respond to future requests from the client, if the client does make the request anticipated by the service. Thus, in some cases, latency may be reduced when responding to requests in which anticipatory data has already been provided. The service may give priority to the actual requested data, and gives secondary priority to the anticipatory data.

主权项

1. One or more computer-readable storage device having stored computer-executable instructions that, when executed by one or more processors of a computing system, cause the computing system to obtain pre-fetched data from a service by implementing a method that includes:
an act of the computing system interacting with the service by making one or more requests to the service; an act of the computing system receiving historical response data from the service responsive to the one or more requests made in the act of interacting, the historical response data being received in one or more responses, the received historical response data being cached into a historical cache; and an act of the computing system receiving pre-fetched data from the service, wherein the pre-fetched data is data that is not used for satisfying the one or more requests made by the computing system during the act of interacting, but is received in anticipation of a possible future request, the received pre-fetched data being cached into an anticipatory cache that is distinguished from the historical cache wherein the method further includes: while a portion of the received pre-fetched data is cached by the computing system, an act of identifying a new request for the service; an act of evaluating the new request to determine that at least a portion of the new request may be at least partially satisfied by the portion of the cached pre-fetched data; and an act of using the portion of the cached pre-fetched data to at least partially satisfy the new request.