CACHE MANAGEMENT IN CONTENT DELIVERY SYSTEMS

    公开(公告)号:US20230035033A1

    公开(公告)日:2023-02-02

    申请号:US17966859

    申请日:2022-10-16

    Inventor: William Crowder

    Abstract: Examples described herein relate to apparatuses and methods for managing caching for a content delivery system, which may include receiving a content request indicating that the caching agent is requesting content data for a client, filling the content data in a first cache storage of the business logic agent, providing the cached content data to the caching agent, and while a second cache storage of the caching agent is being filled with the content data, maintaining the cached content data in response to receiving additional content requests from the caching agent. The additional content requests may indicate that the caching agent is requesting the same content data for additional clients.

    SYSTEMS AND METHODS FOR STORING CONTENT ITEMS IN SECONDARY STORAGE

    公开(公告)号:US20230026912A1

    公开(公告)日:2023-01-26

    申请号:US17958355

    申请日:2022-10-01

    Inventor: William Crowder

    Abstract: Examples described herein relate to systems and methods for storing content items. The methods may be implemented by a computer comprising a processor, primary storage device, secondary storage, device and network interface. The primary storage device may receive, via the network interface, a plurality of content items responsive to respective requests from clients. The plurality of content items may be distributed, via the network interface, from the primary storage device to clients responsive to the respective requests from the clients. The processor may generate a dynamic priority list for the content items based on the respective requests from the clients over time, and may write, based on the dynamic priority list, only a subset of the content items to the secondary storage device.

    Caching in a content delivery framework

    公开(公告)号:US11425223B2

    公开(公告)日:2022-08-23

    申请号:US16909245

    申请日:2020-06-23

    Abstract: A computer-implemented method, operable with a content delivery network (CDN) uses late binding of caching policies; by a caching node in the CDN, in response to a request for content, determining if the content is cached locally. When it is determined that said content is cached locally, then: determining a current cache policy associated with the content; and then determining, based on said current cache policy associated with the content, whether it is acceptable to serve the content that is cached locally; based on said determining, when it is not acceptable to serve the content that is cached locally, obtaining a new version of the content and then serving the new version of the content, otherwise when it is acceptable to serve the content that is cached locally, serving the content that is cached locally.

    Object integrity verification in a content delivery network (CDN)

    公开(公告)号:US10862790B2

    公开(公告)日:2020-12-08

    申请号:US16429455

    申请日:2019-06-03

    Inventor: William Crowder

    Abstract: A computer-implemented method, in a content delivery (CD) network, wherein said CD network delivers content on behalf of multiple content providers. The method includes, at a client, requesting one or more parts of a randomly generated test object; in response to said requesting, receiving one or more response objects; generating one or more portions of said randomly generated test object, and comparing the one or more response objects received to at least some of the one or more portions of the object generated. Based on said comparing, when said one or more response objects received do not match said at least some of the one or more portions of the object generated, reporting and logging an error.

    Time and location-based trend prediction in a content delivery network (CDN)

    公开(公告)号:US10834180B2

    公开(公告)日:2020-11-10

    申请号:US15727704

    申请日:2017-10-09

    Abstract: A content delivery (CD) network delivers content on behalf of multiple content providers. A method includes determining that certain content is trending in a first geographic region during a first time period; and, based on the determining, causing the certain content to be prefetched by the CDN in a second geographic region by a given time after said first time period, wherein, during the first time period, the time in the second geographic region is earlier than the time in the first geographic region.

    Caching in a content delivery framework

    公开(公告)号:US10701173B2

    公开(公告)日:2020-06-30

    申请号:US15588935

    申请日:2017-05-08

    Abstract: A computer-implemented method, operable with a content delivery network (CDN) uses late binding of caching policies; by a caching node in the CDN, in response to a request for content, determining if the content is cached locally. When it is determined that said content is cached locally, then: determining a current cache policy associated with the content; and then determining, based on said current cache policy associated with the content, whether it is acceptable to serve the content that is cached locally; based on said determining, when it is not acceptable to serve the content that is cached locally, obtaining a new version of the content and then serving the new version of the content, otherwise when it is acceptable to serve the content that is cached locally, serving the content that is cached locally.

    SPECULATIVE CACHING IN A CONTENT DELIVERY NETWORK

    公开(公告)号:US20190327326A1

    公开(公告)日:2019-10-24

    申请号:US15960393

    申请日:2018-04-23

    Abstract: A server in a content delivery (CD) network that distributes content on behalf of one or more subscribers. Responsive to a request from a client for a particular resource, if the particular resource is already in a cache on the server, serving the particular to the client from the cache; otherwise if the particular resource is not already cached on the server, when a count value exceeds a first threshold value, obtaining, caching, and serving the particular resource. When the count value is less than a second threshold value, obtaining and serving the particular resource. When the count value is: (i) not less than the second threshold value, and (ii) not greater than the first threshold value, then obtaining the particular resource and selectively caching the particular resource; and serving the particular resource to the client.

    RENDEZVOUS OPTIMIZATION IN A CONTENT DELIVERY FRAMEWORK

    公开(公告)号:US20190109772A1

    公开(公告)日:2019-04-11

    申请号:US16202589

    申请日:2018-11-28

    Abstract: A computer-implemented method in a content delivery (CD) network includes determining at least one pseudo client IP address using first log information and second log information. The first log information being from a rendezvous service in the content delivery (CD) network, and includes at least one resolver IP address associated with at least one first request made at the rendezvous service. The second log information is from at least one probe service in the CD network, and includes at least one client IP address associated with at least one second request to the at least one probe service. The method also includes making an association between (i) the at least one pseudo client IP address and (ii) the at least one resolver IP address; and then, responsive to a name resolution request, the name resolution request including the at least one resolver IP address, the rendezvous service using the at least one pseudo client IP address instead of the resolver IP address to resolve the name.

Patent Agency Ranking