Cache eviction

摘要

A method and apparatus for downloading content within a video-on-demand system is provided herein. During operation a Video Home Office (VHO) will cache a subset of the Video Service Office (VSO) content. When a user requests content that is not stored on the VHO, the VHO will request that content from another VHO or the VSO. In order to reduce the additional network load imposed during item forwarding while attempting to balance the total load on all the links interconnecting the VSO and VHOs, recorded traffic history metrics are used to predict their future or current traffic. A VHO or VSO is chosen for fetching the content that will result in the lowest predicted traffic on the interconnecting links.

主权项

1. A method comprising:
receiving, by a processing apparatus at a first server, a request for content from a client device; determining that the content is not stored by the first server; determining that there is not enough room to cache the content at the first server; and selecting one or more items to evict from a cache at the first server to make room for the content, wherein the selection of the items minimizes a network penalty associated with the eviction of the items, wherein the network penalty is based on sizes of the content and the items, numbers of requests expected to be received for the content and the items, and fetch costs associated with retrieving the content and the items, wherein each of the fetch costs is based on a sum of link weights of links in a network path for fetching each of the content and the items, and wherein each of the link weights is based on traffic predicted on a link in the links of the network path.