US 6,694,358 B1Granted

Performance computer network method

AssigneeSpeedera Networks, Inc.

InventorsEric Sven-Johan Swildens, Ajit Kumar Gupta, Richard David Day

Life of this patent

Estimating the term…

Loading patent…

Abstract

A method for a computer network includes sending a first request from a web client for resolving a first web address of a web page to a client DNS server, sending the first request from the client DNS server to a POP DNS server that determines a customer web server from the plurality of customer web servers, sending the web page that includes static content represented by an embedded URL from the customer web server, sending a second request from the web client for resolving the URL to the client DNS server sending the second request from the client DNS server to the POP DNS server that determines a web cache from the plurality of web caches, sending the static content from the web cache to the web client, and outputting the static content with the web client.

Claims20

Dependent claims

A method for a computer network comprises:

sending a first request from a web client for resolving a first web address of a web page to a client DNS server;
sending the first request from the client DNS server to a POP DNS server within a POP server network;
using a probe server in the POP server network to determine traffic loads of a plurality of customer web servers, each of the customer web servers storing the web page;
using the POP DNS server to determine a customer web server from the plurality of customer web servers, the customer web server having a traffic load lower than traffic loads of other customer web servers in the plurality of customer web servers;
requesting the web page from the customer web server, the web page including static content represented by an embedded URL;
sending the web page from the customer web server to the web client;
sending a second request from the web client for resolving the URL to the client DNS server;
sending the second request from the client DNS server to the POP DNS server within a POP server network;
using the probe server to determine service metrics of a plurality of web caches within the POP server network;
using the POP DNS server to determine a web cache from the plurality of web caches, the web cache having service metrics more appropriate for the second request than service metrics of other web caches in the plurality of web caches;
requesting the static content from the web cache;
sending the static content to the web client;
and
outputting the static content with the web client.

11 more elements

A method for a computer network comprises:

using a web client to enter a first web address of a web page;
sending a first request from the web client to a client DNS server to resolve the first web address;
sending the first request from the client DNS server to a POP DNS server within a POP server network;
using a probe server in the POP server network to determine latencies between the probe server to a plurality of customer web servers, each of the customer web servers having the web page;
using the POP DNS server to determine a customer web server from the plurality of customer web servers in response to the latencies, the customer web server having a latency lower than latencies of other customer web servers in the plurality of customer web servers;
requesting the web page from the customer web server, the web page including an embedded URL representing static content;
sending the web page from the customer web server to the web client;
sending a second request from the web client to the client DNS server for resolving the URL;
sending the second request from the client DNS server to the POP DNS server within the POP server network;
using the probe server to determine loads of a plurality of web caches within the POP server network;
using the POP DNS server to determine a web cache from the plurality of web caches in response to the loads, the web cache having a load lower than loads of other web caches in the plurality of web caches;
retrieving the static content from the web cache;
sending the static content to the web client;
and
outputting the static content with the web client.

12 more elements

A method for a computer network comprises:

using a first web client to enter a first web address of a web page;
using a second web client to enter the first web address of the web page;
sending a first request from the first web client to a first client DNS server to resolve the first web address;
sending a first request from the second web client to a second client DNS server to resolve the first web address;
sending the first request from the first client DNS server to a first POP DNS server within a POP server network;
sending the first request from the second client DNS server to a second POP DNS server within the POP server network;
using a first probe server in the POP server network to determine latencies between the first probe server to a plurality of customer web servers, each of the customer web servers having the web page;
using a second probe server in the POP server network to determine latencies between the second probe server to the plurality of customer web servers, each of the customer web servers having the web page;
using the first POP DNS server to determine a first customer web server from the plurality of customer web servers in response to the latencies measured from the first probe server, the first customer web server having a latency lower than latencies of other customer web servers in the plurality of customer web servers;
using the second POP DNS server to determine a second customer web server from the plurality of customer web servers in response to the latencies measured from the second probe server, the second customer web server having a latency lower than latencies of other customer web servers in the plurality of customer web servers;
requesting the web page from the first customer web server, the web page including an embedded URL representing static content;
requesting the web page from the second customer web server;
sending the web page from the first customer web server to the first web client;
sending the web page from the second customer web server to the second web client;
sending a second request from the first web client to the first client DNS server for resolving the URL;
sending a second request from the second web client to the second client DNS server for resolving the URL;
sending the second request from the first client DNS server to the first POP DNS server within the POP server network;
sending the second request from the second client DNS server to the second POP DNS server within the POP server network;
using the first probe server to determine loads of a plurality of web caches within the POP server network;
using the second probe server to determine loads of the plurality of web caches within the POP server network;
using the first POP DNS server to determine a first web cache from the plurality of web caches in response to the loads, the first web cache having a load lower than loads of other web caches in the plurality of web caches;
using the second POP DNS server to determine a second web cache from the plurality of web caches in response to the loads, the second web cache having a load lower than loads of other web caches in the plurality of web caches;
retrieving the static content from the first web cache;
retrieving the static content from the second web cache;
sending the static content to the first web client ;
sending the static content to the second web client;
outputting the static content with the first web client;
and
outputting the static content with the second web client.

26 more elements

Dependencies are inferred from the claim text.

Facts

Application: 09/645,067Filed 23 Aug 2000 · us provisional application
Priority: 22 Nov 1999
Granted: 17 Feb 2004
Term ends: Not estimatedThe source records don’t support an estimate.

Classification16 codes

H04L 12/14
Details: charging, metering or billing arrangements specially adapted for data communications, e.g. authentication, authorisation and accounting…
H04L 43/00
Arrangements for monitoring or testing data switching networks
H04L 61/4511
Using standardised directories; using standardised directory access protocols: using domain name system [DNS]
H04L 67/1008
Server selection for load balancing: based on parameters of servers, e.g. available memory or workload