Method and Apparatus For Increasing Performance of HTTP Over Long-Latency Links

• US 20100100687A1
• Filed: 12/21/2009
• Published: 04/22/2010
• Est. Priority Date: 05/04/2005
• Status: Active Grant

• Current Assignee: Venturi Wireless Incorporated
• Original Assignee: Venturi Wireless Incorporated
• Inventors: RAMADAS, Krishna
• Granted Patent: US 7,945,692 B2
• Time in Patent Office: Days
• US Class Current: 711/137
• CPC Class Codes: G06F 16/9574 of access to content, e.g. by caching

Abstract

The invention increases performance of HTTP over long-latency links by pre-fetching objects concurrently via aggregated and flow-controlled channels. An agent and gateway together assist a Web browser in fetching HTTP contents faster from Internet Web sites over long-latency data links. The gateway and the agent coordinate the fetching of selective embedded objects in such a way that an object is ready and available on a host platform before the resident browser requires it. The seemingly instantaneous availability of objects to a browser enables it to complete processing the object to request the next object without much wait. Without this instantaneous availability of an embedded object, a browser waits for its request and the corresponding response to traverse a long delay link.

Claims

1. A method for increasing performance of Web page loading over a long-latency link, comprising the steps of:

a browser, associated with a client, requesting a Web page from a first end of said long-latency link;

a gateway receiving said request at a second end of said long-latency link, said gateway retrieving a Web page description from an original Web server and sending said Web page description to said client via said long-latency link;

said browser receiving and parsing said Web page description;

while said Web page description is operated upon by said browser to load said Web page, parsing said page description independently of, and concurrently with, said browser to identify objects of a selected Web page object type that are normally sequentially fetched;

using a pre-fetch mechanism concurrently with said browser to access said original Web server to fetch said objects while said browser is still loading said Web page;

after fetching said objects with said pre-fetch mechanism, storing said objects in a local cache; and

said browser accessing said local cache for said objects to complete loading of said Web page;

wherein said objects are loaded without said browser requesting said objects via said long-latency link.

2. The method of claim 1, wherein said step of parsing determines if there are any JavaScripts or Style Sheets, in said Web page;

and wherein said pre-fetch mechanism fetches said objects concurrently with said browser'"'"'s loading of said Web page.

3. The method of claim 1, further comprising the step of:

said pre-fetch mechanism performing a selective pre-fetch of any specified objects'"'"' wherein said pre-fetch mechanism applies any of heuristics, rules, and adaptive behavior to determine which objects are to be pre-fetched selectively to reduce the impact that a prefetching operation has on delaying the fetching of objects already requested by the browser.

4. The method of claim 1, wherein said Web pages comprise metatags which are supplied by said gateway through application of any heuristics at a centralized point, said method further comprising the step of:

interpreting said metatags with said pre-fetch mechanism to determine which objects are to be selectively pre-fetched.

5. A method for increasing performance of HTTP over long-latency links, comprising the steps of:

using a browser within a host platform;

providing a client associated with said platform comprising an agent having pre-fetch functionality and a Web object cache, said agent explicitly pre-fetching selected, sequentially loaded Web, page objects and storing said pre-fetched objects in said Web object cache;

providing a server in communication with said client via a long latency link; and

accessing an original Web server which is in communication with said server;

wherein sequentially loaded Web page objects that are requested from said original Web server pursuant to a request therefor via said browser are loaded into said Web object cache via said agent, wherein said sequentially loaded Web page objects are available at, and are loaded from, said Web object cache upon said request; and

wherein said request and a response thereto does not traverse said long-latency link.

6. The method of claim 5, wherein said sequentially loaded objects comprise any of JavaScripts and Style Sheets.

7. An apparatus for increasing performance of Web page loading over a long-latency link, comprising:

a browser, associated with a client, for requesting a Web page from a first end of said long-latency link, said browser receiving and parsing a Web page description;

a gateway for receiving said request at a second end of said long-latency link, said gateway retrieving said Web page description from an original Web server and sending said Web page description to said client via said long-latency link;

a parser for parsing said page description independently of, and concurrently with, said browser, while said Web page description is operated upon by said browser to load said Web page, to identify objects of a selected Web page object type that are normally sequentially fetched;

a pre-fetch mechanism for use concurrently with said browser to access said original Web server to fetch said objects while said browser is still loading said Web page; and

a local cache for storing said objects after fetching said objects with said pre-fetch mechanism;

wherein said browser accesses said local cache for said objects to complete loading of said Web page; and

wherein said objects are loaded without said browser requesting said objects via said long-latency link.

8. The apparatus of claim 7, wherein said parser determines if there are any JavaScripts or Style Sheets, in said Web page;

and wherein said pre-fetch mechanism fetches said objects concurrently with said browser'"'"'s loading of said Web page.

9. The apparatus of claim 7, further comprising:

means associated with said pre-fetch mechanism for performing a selective pre-fetch of any specified objects'"'"' wherein said pre-fetch mechanism applies any of heuristics, rules, and adaptive behavior to determine which objects are to be pre-fetched selectively.

10. The apparatus of claim 7, wherein said Web pages comprise metatags supplied to an agent by said gateway which applies centralized intelligence about various flows, said apparatus further comprising:

means associated with said pre-fetch mechanism for interpreting said metatags to determine which objects are to be selectively pre-fetched.