摘要:
A method of generating a web page modifies uniform resource locators (URLs) of embedded resources in a web page. The modified URLs include data prepended to information from the original URLs. The prepended data may be a hostname or an network address that is resolvable to a shared network of servers.
摘要:
A method of processing requests for resources in a system in which a plurality of content providers provide multiple resources. Content providers offload the serving of some of their resources to a shared content delivery network (CDN) formed by a plurality of servers. The CDN is shared among the content providers. Some of a content provider's content may be served from an origin server associated with that content provider, while requests for other content from that content provider are served from the shared CDN.
摘要:
A method for delivering resources to clients in a distributed computing environment. At least a first resource associated with a first content provider and maintained on an origin server references a second resource. The second resource is associated with a network formed by a plurality of repeater servers operable to serve the second resource to clients on behalf of the first content provider, the origin server being distinct from the plurality of repeater servers. Responsive to a request that causes the first resource to be served to a client from the origin server, at least one of the plurality of repeater servers is selected to serve the second resource to the client. If a copy of the second resource is available on the selected repeater server, the copy of the second resource is served to the client from the selected repeater server; otherwise, if a copy of the second resource is not available on the selected repeater server, the second resource is replicated on the selected repeater server.
摘要:
A method of managing information in a content-addressable computer system comprising a plurality of computers including at least a first computer and at least two second computers. The method includes creating a first identifier for a data item, at least in part, by hashing the content of the data item; sending a request including the first identifier from the first computer to the at least two second computers to access the data item, wherein at least one of the at least two second computers uses the first identifier to access the data item; and verifying that the content of the data item has not changed since the creation of the first identifier. 2. The method may include using the first identifier to locate a storage location for the data item on the computer system. The first identifier may be based on the entire content of the data item
摘要:
Resource requests made by clients of origin servers in a network are intercepted by reflector mechanisms and selectively reflected to other servers called repeaters. The reflectors select a best repeater from a set of possible repeaters and redirect the client to the selected best repeater. The client then makes the request of the selected best repeater. The resource is possibly rewritten to replace at least some of the resource identifiers contained therein with modified resource identifiers designating the repeater instead of the origin server.
摘要:
In a data processing system, a mechanism identifies data items by substantially unique identifiers which depend on all of the data in the data items and only on the data in the data items. The system also determines whether a particular data item is present in the database by examining the identifiers of the plurality of data items.
摘要:
A plurality of data items are distributed across a plurality of computers, some of which may form a peer-to-peer network. A first computer receives a request for a data item from a requesting computer. The request includes a True Name of the data item. The first computer causes the requesting computer to obtain the data item from a second computer, distinct from the first computer. The first computer may not have a copy of the requested data item. The first computer may know the location of the data item. The first computer may forward the request for the data item to at least one other computer.
摘要:
A computer-implemented method operable in a computer system comprising a plurality of computers including at least a first computer and at least two second computers, the method includes: obtaining a first identifier from the first computer at the at least two second computers, said first identifier having been determined, at least in part, by applying a first function to the content of the data item, wherein the first function comprises a hash function; and at least one of the at least two second computers using the first identifier to ascertain a storage location for the data item on the computer system. At least one of the at least two second computers may use the first identifier to access the data item on the computer system. The method may include verifying that the content of the data item has not changed since creation of the first identifier.
摘要:
A method, in a system in which a plurality of data items are distributed across a plurality of computers, includes, at a first computer in the network, (a) receiving from a requesting computer in said network, a request, the request including a specific name of a particular data item, wherein the particular data item comprises a particular sequence of bits, and wherein the specific name of the particular data item is based at least in part on the data comprising the particular data item, the specific name of the particular data item having been determined, at least in part, using a given function of the particular sequence of bits, wherein two identical sequences of bits have the same name as determined using the given function; and (b) causing said requesting computer to obtain at least a portion of said particular data item from a second computer in said network, said second computer being distinct from said first computer.
摘要:
A plurality of content providers provide multiple resources to multiple clients. At least some of the resources are to be served to clients from a shared content delivery network (CDN) formed by a plurality of repeater servers. Each content provider provides at least some resources via one or more content sources associated with that content provider. Transmission data rates from the CDN on behalf of some of the content providers are monitored. Based at least in part on the monitored data rates, requests for resources are directed to a source other than the CDN. Redirection of requests may be based on a pricing policy.