Performance computer network method

• US 6,694,358 B1
• Filed: 08/23/2000
• Issued: 02/17/2004
• Est. Priority Date: 11/22/1999
• Status: Expired due to Term

• Current Assignee: Akamai Technologies, Inc.
• Original Assignee: Speedera Networks Incorporated (Akamai Technologies, Inc.)
• Inventors: Gupta, Ajit Kumar, Swildens, Eric Sven-Johan, Day, Richard David
• Primary Examiner(s): Maung, Zarni
• Assistant Examiner(s): Hu, Jinsong
• Application Number:
  US09/645,067
• Time in Patent Office: 1,273 Days
• Field of Search: 709/218, 709/223, 709/224, 709/225, 705/1, 370/229, 711/118, 711/133
• US Class Current: 709/218
• CPC Class Codes: H04L 12/14 Charging , metering or billing arrangements for data wireline or wireless communications
• CPC Class Codes: H04L 41/5012 determining service availability, e.g. which services are available at a certain point in time
• CPC Class Codes: H04L 41/509 wherein the managed service relates to media content delivery, e.g. audio, video or TV
• CPC Class Codes: H04L 43/00 Arrangements for monitoring or testing data switching networks
• CPC Class Codes: H04L 43/0858 One way delays
• CPC Class Codes: H04L 43/12 Network monitoring probes
• CPC Class Codes: H04L 61/4511 using domain name system [DNS]
• CPC Class Codes: H04L 67/1001 for accessing one among a plurality of replicated servers
• CPC Class Codes: H04L 67/10015 Access to distributed or replicated servers, e.g. using brokers
• CPC Class Codes: H04L 67/1008 based on parameters of servers, e.g. available memory or workload monitoring of computer activity G06F11/30
• CPC Class Codes: H04L 67/101 based on network conditions
• CPC Class Codes: H04L 67/56 Provisioning of proxy services store-and-forward switching systems in data switching networks H04L12/54
• CPC Class Codes: H04L 67/563 Data redirection of data network streams
• CPC Class Codes: H04L 67/568 Storing data temporarily at an intermediate stage, e.g. caching
• CPC Class Codes: H04L 69/329 in the application layer [OSI layer 7]
• CPC Class Codes: H04L 9/40 Network security protocols

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.

Claims

1. 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.

2. The method of claim 1 wherein the service metrics comprise metrics selected from the class:

HTTp response time, FTP response time, CPU load, memory load.

3. The method of claim 1 further comprising:

determining whether the web cache includes the static content;

determining a web server that includes the static content when the web cache does not include the static content;

retrieving the static content from the web server; and

storing the static content from the web server in the web cache.

4. The method of claim 3 wherein determining the web server comprises:

using the probe server to determine traffic loads of a plurality of customer web servers that stores the static content; and

using the POP DNS server to determine another customer web server from the plurality of customer web servers that stores the static content, the other customer web server having a traffic load lower than traffic loads of other customer web servers in the plurality of customer web servers that stores the static content.

5. The method of claim 4 wherein retrieving the static content from the web server comprises:

using the POP DNS server to determine another customer web server; and

requesting a web page from the other customer web server.

6. The method of claim 1 wherein the network of point of presence servers comprises more than one POP DNS server.

7. The method of claim 1 wherein the traffic loads comprise latency traffic between the probe server loads and the plurality of customer web servers.

8. 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.

9. The method of claim 8 wherein the loads comprise measurements selected from:

CPU load, memory load, HTTP response time, FTP response time.

10. The method of claim 8 wherein the latencies comprise data selected from:

CPU load, memory load, HTTP response time, FTP response time.

11. The method of claim 8

determining whether the web cache includes the static content;

determining a web server that includes the static content when the web cache does not include the static content;

retrieving the static content from the web server; and

storing the static content from the web server in the web cache.

12. The method of claim 11 wherein determining the web server comprises:

using the probe server to determine latencies of a plurality of customer web servers that stores the static content; and

using the POP DNS server to determine another customer web server from the plurality of customer web servers that stores the static content, the other customer web server having a latency lower than latencies of other customer web servers in the plurality of customer web servers that includes the static content.

13. The method of claim 8 further comprising:

using another web client to enter a second web address of another web page;

sending a first request from the other web client to another client DNS server to resolve the second web address;

sending the first request from the other client DNS server to the POP DNS server;

using the probe server in the POP server network to determine latencies between the probe server to a plurality of second customer web servers, each of the second customer web servers having the other web page;

using the POP DNS server to determine a second customer web server from the plurality of second customer web servers in response to the latencies, the second customer web server having a latency lower than latencies of other second customer web servers in the plurality of second customer web servers;

requesting the other web page from the second customer web server, the other web page including a web address associated with static data; and

sending the other web page from the second customer web server to the other web client.

14. The method of claim 13 further comprising:

sending a second request from the other web client to the client DNS server for resolving the web address;

sending the second request from the other 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 data from the web cache;

sending the static data to the other web client; and

outputting the static data with the other web client.

15. 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.

16. The method of claim 15 wherein the loads comprise CPU load and memory load.

17. The method of claim 15 wherein the static content is selected from the class:

image, video, text, documents, plug-in data.

18. The method of claim 15 further comprising updating the static content stored on the first web cache and the second web cache.

19. The method of claim 18

wherein the first probe server also determines a load of a customer web server that includes the static content within the plurality of customer web servers; and

wherein the first POP DNS server determines the 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 and lower than the load of the customer web server.

20. The method of claim 15 wherein first web cache and second web cache reside on different servers.