Content distribution network

Abstract

Systems, methods, and computer-readable media provide content items to clients. In one implementation, a system stores data identifying a plurality of cache servers, the cache servers storing the content items for download by a plurality of clients. The system receives a request from a first one of the clients to download one of the content items. The system selects one or more of the cache servers for providing the requested content item to the first client. The system transmits identifiers of the selected one or more cache servers to the first client, and transmits instructions to the first client. The instructions are operable, when executed by the first client, to determine whether the selected one or more cache servers have a local copy of the requested content item. When the first client determines that a first one of the selected one or more cache servers has a local copy of the requested content item, the first client downloads the requested content item from the first selected cache server.

Description

BACKGROUND OF THE INVENTION

Field of the Invention

Content distribution networks (“CDN's”) provide a wide variety of electronic content items, such as music, video, or games, to users located at various locations. The users typically download the electronic content items to a client device, such as a computer, portable digital assistant (PDA), or cell phone, and then use a local copy of the downloaded content. In many cases, the client devices download the content items from a central server. However, downloading the content items may take a long time for client devices that are located far away from the central server.

Description of the Related Art

One solution to the problem of long download times in a CDN is to distribute the content items to cache servers that are located more closely to the client devices. By doing so, the client devices can download the content items from the cache servers, rather than the central server. Even when the client devices are geographically dispersed over a large area, this approach can reduce the download times for client devices by providing the client devices with sources for downloading the content items that are closer than the central server.

However, the cache servers may not always have local copies of the content items. As a result, the client devices will not always be able to download requested content items from the closest cache server. When the requested content item is not available from the closest cache server, this problem can be partially solved by tracking the content items that are available from the cache servers and redirecting the client devices to cache servers that have local copies of the requested content items. However, tracking availability of content items on cache servers can present difficult problems. For example, tracking availability of content items can require substantial overhead on the cache servers, central server, and/or client devices.

Therefore, systems and methods are needed to overcome these limitations of traditional content distribution.

BRIEF DESCRIPTION OF THE DRAWINGS

The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate various disclosed embodiments. In the drawings:

FIG. 1 is a diagram of an example of a system for providing content items;

FIG. 2A is diagram of an example of an architecture of a control server;

FIG. 2B is diagram of an example of an architecture of a cache server;

FIG. 2C is diagram of an example of an architecture of a client device;

FIG. 3 is a diagram of an example of a cache list;

FIG. 4 is a diagram of an example of an interface for downloading content items;

FIG. 5 is a diagram of a example of a client-specific cache list;

FIG. 6 is a diagram of an interface for providing the download status of cache servers;

FIG. 7 is a flow diagram of an example of a routine for providing content items to clients;

FIG. 8 is a flow diagram of a routine for downloading a content item; and

FIG. 9 is a diagram of an administrator interface.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENT

The following detailed description refers to the accompanying drawings. Wherever possible, the same reference numbers are used in the drawings and the following description to refer to the same or similar parts. While several exemplary embodiments are described herein, modifications, adaptations and other implementations are possible. For example, substitutions, additions or modifications may be made to the components illustrated in the drawings, and the exemplary methods described herein may be modified by substituting, reordering, deleting, or adding steps to the disclosed methods. Accordingly, the following detailed description is not limiting of the disclosed embodiments. Instead, the proper scope is defined by the appended claims.

Disclosed embodiments provide systems and methods for providing content items, such as multimedia items, to clients. The systems and methods may receive a request from a client for a particular content item, and respond to the requests by providing the client with identifiers of cache servers that stare various content items. In addition, the systems and methods may provide instructions, such as computer code, to the client. The client may use the instructions for determining which, if any, of the cache servers have a local copy of the content item requested by the client. Using the provided instructions, the client may identify a cache server with a local copy of the requested content item and proceed to download the requested content item from the identified cache server. The instructions and identifiers may be provided to the client together in a document, such as a web page.

Consistent with a disclosed embodiment, a computer-implemented method provides content items to a plurality of clients. According to the method, data identifying a plurality of cache servers is stored in a storage device, and the cache servers stare the content items for download by the clients. Instructions are stored, and the instructions are operable to, when executed by the clients, determine whether the cache servers are storing local copies of the content items. A request is received from a first one of the clients to download one of the content items. One or more of the cache servers are selected for providing the requested content item to the first client, based at least on a proximity of the selected cache servers to the first client. A document is generated, and the document includes identifiers of the selected cache servers and the instructions. The document is transmitted to the first client. The first client executes the instructions to determine whether the selected cache servers have local copies of the requested content item. When the first client determines that a first one of the selected cache servers has a local copy of the requested content item, the first client downloads the requested content item from the first selected cache server.

Consistent with another disclosed embodiment, a computer-implemented method provides content items to a plurality of clients. According to the method, data identifying a plurality of cache servers is stored in a storage device, and the cache servers stare the content items for download by the clients. A request is received from a first one of the clients to download one of the content items. One or more of the cache servers is selected for providing the requested content item to the first client. Identifiers of the selected cache servers are transmitted to the first client. Instructions operable to determine whether the cache servers have a local copy of the requested content item are transmitted to the first client. When the first client determines that a first one of the selected cache servers has a local copy of the requested content item, the first client downloads the requested content item from the first selected cache server.

Consistent with another disclosed embodiment, a system provides content items to a plurality of clients. The system includes a processor for executing program instructions, and a computer-readable medium storing the program instructions. The program instructions, when executed by the processor, performing a process to provide content items to a plurality of clients. The program instructions may stare data identifying a plurality of cache servers, and the cache servers stare the content items for download by the clients. The instructions may receive a request from a first one of the clients to download one of the content items, and select one or more of the cache servers for providing the requested content item to the first client. The instructions may transmit identifiers of the selected cache servers to the first client, and transmit instructions to the first client, the instructions being operable, when executed by the first client, to determine whether the selected cache servers have a local copy of the requested content item. When the first client determines that a first one of the selected cache servers has a local copy of the requested content item, the first client downloads the requested content item from the first selected cache server.

Consistent with other disclosed embodiments, a computer-readable storage medium may stare program instructions for implementing any of the methods described herein.

FIG. 1 is an example of a system 100 for providing access to a service, consistent with one or more disclosed embodiments. System 100 may provide functionality for one or more client devices to download content items from one or more cache servers. The content items may include files of any type, such as text files, data files, computer programs, or multimedia items such as music or video files. As shown in system 100, control server 110, cache servers 120, 140, and 160, and client devices 130, 150, and 170 are connected to a network 180. One of skill in the art will appreciate that although a particular number of components are depicted in FIG. 1, any number of these components may be provided. One of ordinary skill in the art will also recognize that functions provided by one or more components of system 100 may be combined into one component, or distributed across a plurality of components. For example, control server 110 and cache servers 120, 140, and 160 may be implemented using server farms including several main servers as well as several backup servers. In addition, control server 110 and cache servers 120, 140, and 160 may be implemented by distributing various processing steps discussed herein across multiple servers.

Network 180 provides communications between the various components in system 100. Network 180 may be a shared, public, or private network, may encompass a wide area or local area, and may be implemented through any suitable combination of wired and/or wireless communication networks. Furthermore, network 180 may comprise an intranet or the Internet.

Control server 110 may comprise a general purpose computer (e.g., a personal computer, network computer, server, or mainframe computer) having one or more processors that may be selectively activated or reconfigured by a computer program. Processor 111 may perform steps or methods consistent with disclosed embodiments by reading instructions from memory 112 and executing the instructions. As discussed in more detail below, certain components of server 110 may be implemented as instructions stored in memory 112, suitable for execution by processor 111.

Memory 112 may be one or more memory or storage devices that stare data as well as software. Memory 112 may also comprise, for example, one or more of RAM, ROM, magnetic storage, or optical storage. Furthermore, memory 112 may stare program modules that, when executed by processor 111, perform one or more steps discussed below.

In other embodiments, control server 110 may be specially constructed for carrying-out methods consistent with disclosed embodiments. For example, one or more of the processing steps disclosed herein may be implemented on a field-programmable gate array (“FPGA”), application-specific integrated circuit (“ASIC”) or suitable chipset.

Control server 110 may stare content items, which are downloaded by cache servers 120, 140, and 160. Client devices 130, 150, and 170 may download the content items from cache servers 120, 140, and 160. Client devices 130, 150, and 170 may also download the content items directly tram control server 110.

Cache servers 120, 140, and 160 may be similar in construction to control server 110. For example, cache servers 120, 140, and 160 may comprise general purpose computers (e.g., personal computers, network computers, servers, or mainframe computers) having one or more processors that may be selectively activated or reconfigured by a computer program. Furthermore, cache servers 120, 140, and 160 may communicate via network 180 with control server 110 as well as client devices 130, 150, and 170. Cache servers 120, 140, and 160 may be implemented using server farms, distributed technologies, and various combinations of software and hardware in a manner analogous to the discussion above with respect to control server 110. Cache servers 120, 140, and 160 may also include memories 122, 142, and 162, comprising instructions executable by processors 121, 141, and 161, respectively.

As discussed, cache servers 120, 140, and 160 may download content items from control server 110. Client devices 130, 150, and 170 may request to download the content items from cache servers 120, 140, and 160, which may transmit the requested content items in response to the request.

FIG. 1 illustrates three exemplary cache server/client device pairs, e.g., cache server 120 and client device 130, cache server 140 and client device 150, and cache server 160 and client device 170. Each client device is illustrated as being paired with a cache server based on the distance between them. Thus, client device 130 is paired with cache server 120 because cache server 120 is the closest available cache server, i.e., cache server 120 is closer to client device 130 than either cache server 140 or cache server 160. Similarly, client device 150 is in closer proximity to cache server 140 than cache servers 120 or 160, and client device 170 is in closer proximity to cache server 160 than cache servers 120 or 140.

As used herein, the term “proximity” may refer to various criteria for evaluating the distance between devices on network 180. For example, proximity may refer to geographical proximity, i.e., a physical distance from one device to another, for example, measured as the linear distance between two devices. Proximity may also refer to a network distance between two devices, for example, the length of the network path between two devices on network 180. Similarly, the term “distance” may refer to the geographic distance between two devices, the network distance between two devices on network 180, or other suitable measures of distance between any two devices.

Note that having a shorter geographical proximity to a given device does not necessarily equate to having a shorter network distance. For example, cache server 160 may be geographically closer to control server 110 than cache server 120, yet communications from cache server 160 to control server 110 may travel a longer distance aver network 180 than communications from cache server 120 to control server 110. Such circumstances may arise due to the paths on which communications are routed on network 180. Other measures, such as network latency or bandwidth, can also be used to determine the relative proximity of devices on network 180.

One of skill in the art will recognize that other arrangements of cache servers and client devices are consistent with disclosed embodiments, and the illustration of cache server/client device pairs is exemplary. For example, there may be more than one client device in proximity to a given cache server. Moreover, multiple client devices and cache servers may be located in relatively close proximity to one another.

Client devices 130, 150, and 170 may be any type of device for communicating with control server 110 and/or cache servers 120, 140, and 160. For example, client devices 130, 150, and 170 may be personal computers, handheld devices such as PDAs or cellular phones, or any other appropriate computing platform or device capable of exchanging data with network 180. Client devices 130, 150, and 170 may include, for example, processors 131, 151, and 171, and memories 132, 152, and 172, respectively.

FIG. 2A shows a diagram of an example of an architecture of control server 110, in accordance with one or more disclosed embodiments. As discussed above, memory 112 in control server 110 may stare content items 113. Control server 110 may also include a cache server monitor 114 that monitors content items available locally on each cache server. Control server 110 may also include a script generator 115 that generates instructions, such as computer code. The instructions may subsequently be used by client devices 130, 150, and 170 to determine which, if any, of cache servers 120, 140, and 160 have local copies of requested content items. As discussed in more detail below, control server 110 may include the computer code in a document, such as a web page, provided by web server module 116.

FIG. 2B shows a diagram of an example of an architecture of cache server 120, in accordance with one or more disclosed embodiments. Although not shown, cache servers 140 and 160 may have similar architectures as shown for cache server 120, and the corresponding components of cache servers 140 and 160 may operate in a similar manner as discussed below. As shown in FIG. 2B, cache server 120 may store content items 123 in memory 122. In some embodiments, cache server 120 downloads content items 123 from control server 110. Cache server 120 may also include an update module 124, which communicates with cache server monitor 114 on control server 110. Update module 124 may identify the content items that have been downloaded by cache server 120 to control server 110.

FIG. 2C shows a diagram of an example of an architecture of client device 130, in accordance with one or more disclosed embodiments. Although not shown, client devices 150 and 170 may have similar architectures as shown for client device 130, and the corresponding components of client devices 150 and 170 may operate in a similar manner as discussed below. As shown in FIG. 2C, client device 130 may include a web browser 133 for interacting with control server 110 and cache servers 120, 140, and 160. Client device 130 may also include a content display module 134 that displays content items downloaded from control server 110 or cache servers 120, 140, and 160. Client device 130 may also include a script executor 135, which executes instructions provided by control server 110 to determine whether cache servers 120, 140, and 160 have content items available for download. In some embodiments, content display module 134 and/or script executor 135 may be part of web browser 133. For example, content display module 134 may be a multi-media browser plugin, and script executor 135 may be implemented as browser support for scripting languages (e.g., JavaScript).

FIG. 3 illustrates an exemplary cache list 300. Cache list 300 may be stored by control server 110 and may include information for various cache servers, such as cache servers 120, 140, and 160. As shown in FIG. 3, cache server 120 is located in Seoul, South Korea, and has a URL of http://content.seoul.com with a corresponding IP address of 192.168.0.2. Similarly, cache server 140 is located in Bangalore, India, has a URL of http://content.bangalore.com, and an IP address of 192.168.0.3, while cache server 160 is located in Tokyo, Japan, and has a URL of http://content.tokyo.com and an IP address of 192.168.0.4. As discussed in more detail below, control server 110 may use cache list 300 to determine which cache servers should be identified to client device 120. New cache servers may be added to system 100 by having the new cache servers register with control server 110. Control Server 110 may then add the new cache servers to cache list 300 as part of the registration process.

FIG. 4 illustrates an exemplary content download web page 400. Content download web page 400 may include links to various content items which are available for download. For example, content download web page 400 may include a link 401 to a first content item (“content item 1”), a link 402 to a second content item (“content item 2”), a link 403 to a third content item (“content item 3”), and a link 404 to a fourth content item (“content item 4”). Control server 110 may transmit content download web page 400 to client device 130, and client device 130 may display content download web page 400 using web browser 133. A user at client device 130 may click one of links 401-404, and client device 130 may download the corresponding content item from control server 110, or one of cache servers 130, 150, or 170.

FIG. 5 illustrates a client-specific cache list 500. As discussed in more detail below, control server 110 may receive a request from client device 130 for a content item. Control server 110 may then determine which cache servers on cache list 300 are in the closest proximity to client device 130, e.g., by comparing the geographic or network distance between the cache servers and client device 130. Control server 110 may then create client-specific cache list 500, which includes the closest cache servers to client device 130. Control server may then include client-specific cache list 500 in content download webpage 400, along with the script code. Client device 130 may then execute the script code to see which, if any, of the cache servers on content-specific cache list 500 have an available copy of a content item that the user of client device 130 wishes to download.

FIG. 6 illustrates a download progress web page 600. In some embodiments, control server 110 may transmit download progress web page 600 to one of client devices 130, 150, and 170 when a user requests to download a particular content item. Web browser 133 then displays download progress web page 600 so that the user can visually see that the content item is being downloaded. In some embodiments, client-specific cache list 500 may be embodied as HTML code in download progress web page 600. Furthermore, the instructions from script generator 115 may be embodied as JavaScript code. In such embodiments, control server 110 may include client-specific cache list 500 as HTML code in download progress web page 600. Control server 110 may also include the instructions as JavaScript code in download progress web page 600.

As discussed in more detail below, while the user is viewing download progress web page 600, the instructions may perform operations to determine which cache server from client-specific cache list has a local copy of the requested content item. For example, when the instructions and client-specific cache list 500 are included together in download progress web page 600 as JavaScript and HTML, respectively, web browser 133 may execute the JavaScript code, which reads the HTML client-specific cache list 500 from download progress web page 600. The JavaScript code may then send a request to each of the cache servers listed in client-specific cache list 500 to identify whether the cache servers have a local copy of the requested content item. The JavaScript code may then operate to download the requested content item from a cache server that responds with an indication that a local copy is available. As the JavaScript code executes in web browser 133 to perform these operations, the user may continue to see download progress web page 600 displayed by web browser 133.

FIG. 7 is a flow diagram of an example of a routine 700 for providing content items to a plurality of client devices. Routine 700 may implement processes according to one or more of program modules stored in memory 112 of control server 110.

In block 701, control server 110 may stare data identifying various cache servers. For example, as shown in FIG. 3, control server 110 may maintain cache list 300, which reflects a number of cache servers that are available for providing content items to different client devices. Of the cache servers reflected in cache list 300, only cache servers 120, 140, and 160 are shown in FIG. 1. However, the additional cache servers reflected in FIG. 3 may also be connected to network 180, and have similar structure and functionality as discussed for cache server 120.

Next, in block 702, control server 110 may receive a request to download one of content items 113. For example, control server 110 may first transmit content download web page 400 to client device 130. The user at client device 130 may choose from among the tour content items reflected in content download web page 400, and click the corresponding hyperlink. As an example, the user may click hyperlink 401, and in turn web browser 133 may transmit a request identifying content item 1 to control server 110.

Next, in block 703, control server 110 may select one or more cache servers from which client device 130 may be able to download content item 1. Control server 110 may select the cache servers based on the geographical or network distance between client device 130 and the various cache servers. For example, control server 110 may determine that, from among the cache servers reflected in cache list 300, cache server 120 is closest to client device 130, cache server 140 is the second closest cache server, and cache server 160 is the third closest cache server to client device 130.

Next, in block 704, control server 110 may transmit identifiers of the selected cache servers, e.g., cache servers 120, 140, and 160, to client device 130. For example, control server 110 may prepare client-specific cache list 500, shown in FIG. 5, which may include the cache servers selected in block 703. As discussed above, in some embodiments, control server 110 may include client-specific cache list 500 in download progress web page 600, and transmit download progress web page 600 to client device 130.

Next, in block 705, control server 110 may transmit instructions to client device 130. Client device 130 may execute the instructions to select one or more of the cache servers on client-specific cache list 500 from which to download content item 1. For example, control server 110 may include script code in download progress web page 700, and client device 110 may execute the script code to identify a cache server from which to download the content item. Client device 130 may then download the content item from the identified cache server.

In some embodiments, the script code included in download progress web page 700 may be JavaScript or any other client-side scripting language. In embodiments where the script code and client-specific cache list 500 are both included in download progress web page 700, blocks 704 and 705 may occur concurrently when control server 110 transmits download progress web page 700 to client device 130.

In some embodiments, client-specific cache list 500 may be sorted by control server 110 in increasing order of proximity from client device 130. In such embodiments, control server 110 may first determine a geographical location of client device 130, and then compare the location of client device 130 with the locations of the cache servers in cache list 300. For example, control server 110 may use techniques for mapping the IP address of client device 130 to the geographical location of client device 130. Alternatively, control server 110 may determine a network distance between client device 130 and the cache servers, for example, by looking up the network distances in a table, or using a traceroute command or similar technique to determine the path that communications on network 180 use to travel between client device 130 and the various cache servers.

FIG. 8 is a flow diagram of an example of a routine 800 for downloading a content item. For example, routine 800 may implement processes according to one or more of program modules stored in memory 132 of client device 130. One skilled in the art will understand that routine 800 may generally correspond to operations performed from the perspective of client device 130, while control server 110 implements routine 700.

In block 801, client device 130 may send a request for a content item to control server 110. The request may identify the content item. For example, a user may click on one of hyperlinks 401-404 in content download web page 400 to identify a content item to download.

Next, in block 802, client device 130 may receive identifiers of one or more cache servers. As discussed above with respect to routine 700, the identifiers may be included in client-specific cache list 500. In turn, client-specific cache list 500 may be included in download progress web page 600, which is displayed by client device 130 while the user waits for the content item to be downloaded.

Next, in block 803, client device 130 may receive instructions for determining one or more cache servers from which the content item should be downloaded. As discussed, the instructions may comprise script code that is included in download progress web page 600 by control server 110. Thus, download progress web page 600 may include both a list of possible cache servers (e.g., client-specific cache list 500) for obtaining the content item, as well as instructions (e.g., script code) operable to select one or more of the cache servers and download the content item.

Next, in block 804, client device 130 may execute the instructions. In embodiments where the instructions use a client-side scripting language such as JavaScript, web browser 133 may execute the instructions. The instructions may be operable to send requests to each of the cache servers identified in client-specific cache list 500, i.e. cache servers 120, 140, and 160. Cache servers 120, 140, and 160 may then respond with an indication of whether they have a corresponding local copy of the requested content item.

Next, in block 805, client device 130 may download the requested content item from one of the cache servers that has a local copy. For example, if cache server 120 responds to the request sent in block 804 with an indication that cache server 120 has a local copy of the requested content item, client device 130 downloads the requested content item from cache server 120.

As one of ordinary skill in the art will appreciate, one or more of blocks 701-705 and 801-805 may be optional and may be omitted from implementations in certain embodiments. Furthermore, in some implementations, blocks 701-705 and 801-805 may be reordered, including substitute steps, and/or include additional steps.

Client-Specific Cache List 500

Client-specific cache list 500 may include identifiers of each of the cache servers identified therein. As shown in FIG. 5, the identifiers may include IP addresses for the cache servers, URLs for the cache servers, or both. In the embodiments described above, client-specific cache list 500 and the instructions were included in download progress web page 600, and the instructions were executed after the user selected a content item to download.

However, in some embodiments, client-specific cache list 500 and the instructions may be provided to client device 120 earlier in routine 700. For example, at block 702 of routine 700, control server 110 may include client-specific cache list 500 and the instructions as HTML and JavaScript code, respectively, in content download web page 400. In such embodiments, links 401-404 may initially correspond to storage locations of the corresponding content items 1-4 on control server 110. When the instructions are executed by client device 120, they may be operable to rewrite the link selected by the user with a corresponding link to the cache server from which the content item will be downloaded. In such embodiments, the instructions may rewrite the link to the content item on control server 110 with a URL or IP address from client-specific cache list 500.

In some embodiments, the requested content item may be displayed in a video or audio player within a browser window at client device 120. For example, the video or audio player may run in a webpage such as content download web page 400 or download progress web page 600. In such embodiments, the rewritten link may be provided to the video or audio player, and the video or audio player may download the content item from the rewritten link.

In embodiments where client-specific cache list 500 is sorted according to criteria such as geographical or network distance from client device 130, the instructions may be operable to iterate through the listed cache servers one by one. For example, the instructions may be operable to first attempt to download the requested content item from the closest cache server, i.e., cache server 120. If cache server 120 responds with an indication that a local copy is available, client device 130 may download the requested content item from cache server 120 without proceeding to iterate through cache servers 140 and 160. Otherwise, if cache server 120 responds with an indication that the requested content item is not available, the instructions may be operable to request the content item from cache server 140. The instructions may further be operable to continue iterating through client-specific cache list 500 in increasing order of geographic or network distance until a cache server with a local copy of the requested content item is found.

Because the instructions may iterate through client-specific cache list 500, system 100 is tolerant of faults by the various cache servers. For example, if cache server 120 is inoperable or disconnected from network 180, the instructions may recognize that cache server 120 has not responded to the request for the content item, and continue to the next-closest cache server. In some embodiments, the instructions may implement a time-out mechanism to iterate through client-specific cache list 500. For example, the instructions may be operable to wait five seconds for a response from each cache server before requesting the content item from the next cache server on client-specific cache list 500.

In some embodiments, cache server 120 may intentionally throttle network bandwidth by not providing content items for download by client device 130, even when cache server 120 has a locally stored copy of the requested content item. For example, if cache server 120 determines that network traffic has reached a threshold level where throttling is necessary, cache server 120 may respond to requests from client devices by sending an indication that a requested content item is not available from cache server 120, despite having a local copy of the requested content item. In other embodiments, cache server 120 may not actually send such an indication, but may simply decline to respond to requests for content items until network traffic returns to an acceptable level. Cache server 120 may also throttle communications to preserve other computational resources such as processor utilization, memory usage, or storage space.

Tracking Content Items by Control Server 110

It may be desirable for control server 110 to track which content items are available for download from which cache servers. In such embodiments, control server 110 may generate client-specific cache list 500 based not only on the proximity of the cache servers to the requesting client device, but also based on whether the cache servers have a local copy of the requested content item. In the example discussed above, if control server 110 does not have an indication that cache server 140 has a local copy of requested content item 1, control server 110 may omit cache server 140 from client-specific cache list 500. Instead, control server 110 may include the next closest cache server with a local copy of content item 1.

In some cases, the cache servers may periodically request and download new content items from control server 110. For example, the content items may each be assigned a sequence number, and the cache servers may download each successive content item from control server 110 in sequence number order. The sequence numbers may be assigned to the content items in increasing or decreasing order, or using any other suitable sequencing technique to track the content items. As each content item download is completed, the cache server may request the content item for the next sequence number. As shown in FIG. 2B, for example, cache server 120 may include an update module 124. Update module 124 may be implemented as a software application that notifies control server 110 of each completed download of a content item. Update module 124 may also perform functions such as responding to client device requests to download content items.

Various methods may be used to for control server 110 to track the download status of the various content items by the cache servers. For example, the instructions may be operable to provide feedback to control server 110 about content items that are available and the cache servers upon which the content items are stored. For example, if the instructions determine that cache server 120 has a locally stored copy of content item 1, the instructions may also be operable to send an indication from client device 130 to control server 110 indicating that content item 1 is available locally from cache server 120. However, if the instructions determine that cache server 120 does not have a locally stored copy of content item 1, the instructions may be operable to send an indication to control server 110 indicating that content item 1 is not available locally from cache server 120.

In other embodiments, the cache servers may directly provide feedback to control server about which content items have been downloaded. As discussed, each content item may be assigned a corresponding sequence number. As the cache servers complete downloads of the content items from control server 110, they may send the sequence numbers of the downloaded content items to control server 110. In other embodiments, control server 110 may directly track the downloads of each content item by each control server. For example, control server 110 may stare an indication of the sequence number of each downloaded content item. In such embodiments, control server 110 may determine that the content item has been completely downloaded when the downloading cache server acknowledges receipt of the last data packet of a content item.

In embodiments where control server 110 tracks downloaded content items, it may also be desirable for content server 110 to control which content items should be downloaded by a particular cache server. For example, assume several client devices in close proximity to cache server 140, such as client device 150, are issuing many requests for content item 3. However, control server 110 may determine, based on the tracking, that cache server 140 does not have a locally stored copy of content item 3. Based on the relatively high demand for content item 3 by clients in close geographic or network proximity to cache server 140, control server 110 may send an instruction to cache server 140 indicating that the next content item downloaded by cache server 140 should be content item 3.

In still further embodiments, control server 110 may allocate content items across several cache servers within a predetermined geographic or network distance of each client device. For example, control server 110 may group the cache servers into geographical regions, and allocate the content items across the cache serves in each geographical region. As an example, control server 110 may group cache servers 120 and 140 into a single geographical region for the cache servers in mainland Asia.

Control server 110 may allocate each content item with an even sequence number to cache server 120, and each content item with an odd sequence number to cache server 140. Regions can also be defined based on network distance instead of geographic distance. In such embodiments, control server 110 may also determine to which cache server a requested content item is allocated before generating client-specific cache list 500. Control server 110 may then include only the cache server to which the content item is allocated in client-specific cache list 500.

Administrator Interface 900

As shown in FIG. 9, control server 110 may provide an administrator interface 900 for viewing the status of content item downloads by the cache servers. Administrator interface 900 may include graphical representations of the download status of cache servers 120, 140, and 160, and other cache servers reflected in cache list 300. Administrator interface 900 may identify how many content items have been cached by each cache server (e.g., 1100 videos for cache server 120), as well as how many content items that are to be downloaded by each cache server (e.g., 1101).

Administrator interface 900 may also reflect how long, at present download rates, it will take before each cache server has downloaded all of the content items (e.g., less than one minute). Administrator interface 900 may also reflect disk utilization for each cache server, as well as when the most recent communication (e.g., “ping”) was received from each cache server.

The foregoing description has been presented for purposes of illustration. It is not exhaustive and is not limiting to the precise forms or embodiments disclosed.

Modifications and adaptations will be apparent to those skilled in the art from consideration of the specification and practice of the disclosed embodiments. For example, the described implementations include software, but systems and methods consistent with the disclosed embodiments be implemented as a combination of hardware and software or in hardware alone. Examples of hardware include computing or processing systems, including personal computers, servers, laptops, mainframes, micro-processors and the like. Additionally, although aspects of the disclosed embodiments are described as being stored in memory, one skilled in the art will appreciate that these aspects can also be stored on other types of computer-readable media, such as secondary storage devices, for example, hard disks, floppy disks, or CD-ROM, or other forms of RAM or ROM, USB media, DVD, or other optical drive media.

Computer programs based on the written description and disclosed methods are within the skill of an experienced developer. The various programs or program modules can be created using any of the techniques known to one skilled in the art or can be designed in connection with existing software. For example, program sections or program modules can be designed in or by means of NET Framework, NET Compact Framework, programming languages such as Visual Basic, C, Java, C++, C#, HTML, HTML/AJAX combinations, XML, or HTML with included Java applets. One or more of such software sections or modules can be integrated into a computer system or existing e-mail or browser software.

Moreover, while illustrative embodiments have been described herein, the scope of any and all embodiments having equivalent elements, modifications, omissions, combinations (e.g., of aspects across various embodiments), adaptations and/or alterations as would be appreciated by those in the art based on the present disclosure. The limitations in the claims are to be interpreted broadly based on the language employed in the claims and not limited to examples described in the present specification or during the prosecution of the application, which examples are to be construed as non-exclusive. Further, the blocks of the disclosed routines may be modified in any manner, including by reordering blocks and/or inserting or deleting blocks. It is intended, therefore, that the specification and examples be considered as exemplary only, with a true scope and spirit being indicated by the following claims and their full scope of equivalents.

Claims

1. A computer-implemented method comprising: receiving, at a control server, a request for a content item from a first client computing device;selecting, by the control server, two or more cache servers from a set of cache servers to provide the requested content item to the first client computing device, the selection based at least on a proximity of the two or more cache servers to the first client computing device;generating and transmitting, by the control server to the first client computing device, identifiers of the two or more cache servers and computer-executable code for causing the first client computing device to process the identifiers to send a request to the two or more cache servers, based at least in part on the identifiers, for an indication of whether the two or more cache servers are storing a local copy of the requested content item, wherein the computer-executable code also causes the first client computing device to rewrite a hyperlink in a Web page to identify the cache server from the two or more cache servers that provides an indication to the first client computing device that the cache server has a local copy of the requested content;providing a first indication, to the first client computing device from a first cache server of the two or more cache servers, that the local copy is not stored at the first cache server;providing a second indication, to the first client computing device from a second cache server of the two or more cache servers, that the local copy is stored at the second cache server;receiving a request at the second cache server, from the first client computing device, for the local copy of the requested content item; andtransmitting the local copy of the requested content item from the second cache server to the first client computing device.

2. The computer-implemented method according to claim 1, further comprising storing locations of individual cache servers in the set of cache servers.

3. The computer-implemented method according to claim 2, further comprising: determining a geographical location of the first client computing device; andcomparing the geographical location of the first client computing device to the locations of the individual cache servers in the set of cache servers to select the two or more cache servers included in the identifiers transmitted to the first client computing device for providing the requested content item.

4. The computer-implemented method according to claim 3, wherein the geographical location of the first client computing device is determined by geolocating based on an internet protocol (IP) address of the first client computing device.

5. The computer-implemented method according to claim 1, wherein the identifiers of the two or more cache servers are transmitted in an ordered list based on proximity to the first client computing device.

6. The computer-implemented method according to claim 1, wherein the identifiers are sorted according to one or more criteria, and the computer-executable code, when executed by the first client computing device, is operable to send, based on the one or more criteria, a request for the content item to one of the cache servers from the two or more cache servers providing the indication to the first client computing device that it has a local copy of the content item.

7. The computer-implemented method according to claim 6, wherein the one or more criteria includes a geographic or network proximity of the first client to the cache servers, and the identifiers transmitted to the client are sorted in order based on at least the geographic or network proximity of the corresponding cache servers.

8. The computer-implemented method according to claim 1, wherein the two or more cache servers are operable to preserve computational resources by one or more of: responding to selected requests by indicating that content items are not available for download, even where the cache servers have local copies of the content items, orselectively determining not to respond to certain requests.

9. The computer-implemented method according to claim 1, wherein the identifiers transmitted to the first client computing device include hyperlinks to the two or more cache servers.

10. The computer-implemented method according to claim 9, wherein the hyperlinks include Internet Protocol (IP) addresses of the two or more cache servers.

11. The computer-implemented method according to claim 9, wherein the hyperlinks include Uniform Resource Locators (URLs) of the two or more cache servers, and the first client computing device is operable to request resolution of the URLs into corresponding Internet Protocol (IP) addresses of the two or more cache servers.

12. A system comprising: a plurality of processors for executing program instructions; andat least one computer-readable medium storing the program instructions, the program instructions, when executed by the plurality of processors, performing a process comprising: receiving a request for a content item from a first client computing device;selecting two or more cache servers from a set of cache servers to provide the requested content item to the first client computing device, the selection based at least on a proximity of the two or more cache servers to the first client computing device;generating and transmitting, to the first client computing device, identifiers of the two or more cache servers and computer-executable code for causing the first client computing device to process the identifiers to send a request to the two or more cache servers, based at least in part on the identifiers, for an indication of whether the two or more cache servers are storing a local copy of the requested content item, wherein the computer-executable code causes the first client computing device to rewrite a hyperlink in a Web page to identify the cache server from the two or more cache servers that provides an indication to the first client computing device that the cache server has a local copy of the requested content;providing a first indication, to the first client computing device from a first cache server of the two or more cache servers, that the local copy is not stored at the first cache server;providing a second indication, to the first client computing device from a second cache server of the two or more cache servers, that the local copy is stored at the second cache server;receiving a request at the second cache server, from the first client computing device, for the local copy of the requested content item; andtransmitting the local copy of the requested content item from the second cache server to the first client computing device.

13. The system according to claim 12, wherein the identifiers of the two or more cache servers are transmitted in an ordered list based on proximity to the first client computing device.

14. The system according to claim 12, wherein the identifiers are sorted according to one or more criteria, and the computer-executable code, when executed by the first client computing device, is operable to send, based on the one or more criteria, a request for the content item to one of the cache servers from the two or more cache servers providing the indication to the first client computing device that it has a local copy of the content item.

15. The system according to claim 14, wherein the one or more criteria includes a geographic or network proximity of the first client to the cache servers, and the identifiers transmitted to the client are sorted in order based on at least the geographic or network proximity of the corresponding cache servers.

16. The system according to claim 12, wherein the two or more cache servers are operable to preserve computational resources by one or more of: responding to selected requests by indicating that content items are not available for download, even where the cache servers have local copies of the content items, orselectively determining not to respond to certain requests.

17. A non-transitory computer-readable medium storing program instructions for performing a method executed by a plurality of processors, the method comprising steps performed by the plurality of processors of: receiving, at a control server, a request for a content item from a first client computing device;selecting, by the control server, two or more cache servers from a set of cache servers to provide the requested content item to the first client computing device, the selection based at least on a proximity of the two or more cache servers to the first client computing device;generating and transmitting, from the control server to the first client computing device, identifiers of the two or more cache servers and computer-executable code for causing the first client computing device to process the identifiers to send a request to the two or more cache servers, based at least in part on the identifiers, for an indication of whether the two or more cache servers are storing a local copy of the requested content item, wherein the computer-executable code causes the first client computing device to rewrite a hyperlink in a Web page to identify the cache server from the two or more cache servers that provides an indication to the first client computing device that the cache server has a local copy of the requested content;providing a first indication, to the first client computing device from a first cache server of the two or more cache servers, that the local copy is not stored at the first cache server;providing a second indication, to the first client computing device from a second cache server of the two or more cache servers, that the local copy is stored at the second cache server;receiving a request at the second cache server, from the first client computing device, for the local copy of the requested content item; andtransmitting the local copy of the requested content item from the second cache server to the first client computing device.