摘要:
Described herein are—among other things—systems, methods, and apparatus for accelerating and increasing the reliability of content delivery by serving objects redundantly over multiple paths from multiple servers. In preferred embodiments, the decision to use such multipath delivery is made on the server side. A content server can modify or generate a given web page so as to invoke multipath, e.g., by injecting markup language directives and/or script instructions that will cause the client device to make multiple requests for a given object on the page. Preferably the multiple requests are made to separate content servers in separate points of presence. The teachings hereof may be advantageously implemented, without limitation, in intermediary servers such as caching proxy servers and/or in origin servers.
摘要:
Described herein are—among other things—systems, methods, and apparatus for accelerating and increasing the reliability of content delivery by serving objects redundantly over multiple paths from multiple servers. In preferred embodiments, the decision to use such multipath delivery is made on the server side. A content server can modify or generate a given web page so as to invoke multipath, e.g., by injecting markup language directives and/or script instructions that will cause the client device to make multiple requests for a given object on the page. Preferably the multiple requests are made to separate content servers in separate points of presence. The teachings hereof may be advantageously implemented, without limitation, in intermediary servers such as caching proxy servers and/or in origin servers.
摘要:
A system for measuring and monitoring performance of online content is provided. In one embodiment, the system includes an intermediary device, such as a web proxy, that receives client requests for content, such as requests for web pages. The device obtains the requested content, modifies it by applying one or more performance optimizations, and serves it to the client. The device also inserts code into the content for execution by the client to gather and report data reflecting, e.g., how quickly the client is able to get and process the content. The code includes information identifying the modifications the device made, and this is reported with the timing data, so that the effect on performance can be analyzed. In other embodiments, the device selects one of multiple versions of content, and the inserted code contains information identifying the selected version. The foregoing are merely examples; other embodiments are described herein.
摘要:
Described herein are—among other things—systems, methods, and apparatus for accelerating and increasing the reliability of content delivery by serving objects redundantly over multiple paths from multiple servers. In preferred embodiments, the decision to use such multipath delivery is made on the server side. A content server can modify or generate a given web page so as to invoke multipath, e.g., by injecting markup language directives and/or script instructions that will cause the client device to make multiple requests for a given object on the page. Preferably the multiple requests are made to separate content servers in separate points of presence. The teachings hereof may be advantageously implemented, without limitation, in intermediary servers such as caching proxy servers and/or in origin servers.
摘要:
A system for measuring and monitoring performance of online content is provided. In one embodiment, the system includes an intermediary device, such as a web proxy, that receives client requests for content, such as requests for web pages. The device obtains the requested content, modifies it by applying one or more performance optimizations, and serves it to the client. The device also inserts code into the content for execution by the client to gather and report data reflecting, e.g., how quickly the client is able to get and process the content. The code includes information identifying the modifications the device made, and this is reported with the timing data, so that the effect on performance can be analyzed. In other embodiments, the device selects one of multiple versions of content, and the inserted code contains information identifying the selected version. The foregoing are merely examples; other embodiments are described herein.
摘要:
A system for measuring and monitoring performance of online content is provided. In one embodiment, the system includes an intermediary device, such as a web proxy, that receives client requests for content, such as requests for web pages. The device obtains the requested content, modifies it by applying one or more performance optimizations, and serves it to the client. The device also inserts code into the content for execution by the client to gather and report data reflecting, e.g., how quickly the client is able to get and process the content. The code includes information identifying the modifications the device made, and this is reported with the timing data, so that the effect on performance can be analyzed. In other embodiments, the device selects one of multiple versions of content, and the inserted code contains information identifying the selected version. The foregoing are merely examples; other embodiments are described herein.
摘要:
This patent document describes, among other things, methods and systems for determining which if any page resources a server might push to a client (using, e.g., an HTTP 2.0 server push mechanism). The approaches described herein improve web page load times by pushing page resources that a client is likely to need to render the base page, while reducing wasteful server pushes of resources that the client is unlikely to request from the server because, for example, they are already cached at the client.
摘要:
A system for measuring and monitoring performance of online content is provided. In one embodiment, the system includes an intermediary device, such as a web proxy, that receives client requests for content, such as requests for web pages. The device obtains the requested content, modifies it by applying one or more performance optimizations, and serves it to the client. The device also inserts code into the content for execution by the client to gather and report data reflecting, e.g., how quickly the client is able to get and process the content. The code includes information identifying the modifications the device made, and this is reported with the timing data, so that the effect on performance can be analyzed. In other embodiments, the device selects one of multiple versions of content, and the inserted code contains information identifying the selected version. The foregoing are merely examples; other embodiments are described herein.
摘要:
A system for measuring and monitoring performance of online content is provided. In one embodiment, the system includes an intermediary device, such as a web proxy, that receives client requests for content, such as requests for web pages. The device obtains the requested content, modifies it by applying one or more performance optimizations, and serves it to the client. The device also inserts code into the content for execution by the client to gather and report data reflecting, e.g., how quickly the client is able to get and process the content. The code includes information identifying the modifications the device made, and this is reported with the timing data, so that the effect on performance can be analyzed. In other embodiments, the device selects one of multiple versions of content, and the inserted code contains information identifying the selected version. The foregoing are merely examples; other embodiments are described herein.
摘要:
Described herein are—among other things—systems, methods, and apparatus for accelerating and increasing the reliability of content delivery by serving objects redundantly over multiple paths from multiple servers. In preferred embodiments, the decision to use such multipath delivery is made on the server side. A content server can modify or generate a given web page so as to invoke multipath, e.g., by injecting markup language directives and/or script instructions that will cause the client device to make multiple requests for a given object on the page. Preferably the multiple requests are made to separate content servers in separate points of presence. The teachings hereof may be advantageously implemented, without limitation, in intermediary servers such as caching proxy servers and/or in origin servers.