Distributed on-demand computing system

• US 20050228856A1
• Filed: 03/24/2005
• Published: 10/13/2005
• Est. Priority Date: 11/22/1999
• Status: Active Grant

• Current Assignee: Akamai Technologies, Inc.
• Original Assignee: Akamai Technologies, Inc.
• Inventors: Swildens, Eric Sven-Johan, Day, Richard David, Liu, Zaide "Edward", Garg, Vikas
• Granted Patent: US 7,590,739 B2
• Time in Patent Office: Days
• US Class Current: 709/200
• CPC Class Codes: G06F 9/50 Allocation of resources, e.g. of the central processing unit [CPU]
• CPC Class Codes: G06F 9/5061 Partitioning or combining of resources
• CPC Class Codes: H04L 47/745 Reaction in network
• CPC Class Codes: H04L 67/1001 for accessing one among a plurality of replicated servers
• 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 67/1017 based on a round robin mechanism
• CPC Class Codes: H04L 67/1029 using data related to the state of servers by a load balancer
• CPC Class Codes: Y10S 707/99932 Access augmentation or optimizing

Abstract

A method and mechanism for a distributed on-demand computing system. The system automatically provisions distributed computing servers with customer application programs. The parameters of each customer application program are taken into account when a server is selected for hosting the program. The system monitors the status and performance of each distributed computing server. The system provisions additional servers when traffic levels exceed a predetermined level for a customer'"'"'s application program and, as traffic demand decreases to a predetermined level, servers can be un-provisioned and returned back to a server pool for later provisioning. The system tries to fill up one server at a time with customer application programs before dispatching new requests to another server. The customer is charged a fee based on the usage of the distributed computing servers.

Claims

1. A method for dynamically distributing computing resources for application programs across a plurality of servers in a content delivery network, comprising:

partitioning the plurality of servers into a Web cache server partition and a distributed computing server partition;

tracking the status of each distributed computing server in the distributed computing server partition;

automatically provisioning a server from the distributed computing server partition to run a customer'"'"'s application program; and

load balancing traffic across servers in the Web cache server partition and the distributed computing server partition.

2. The method of claim 1, wherein the partitioning step varies the size of the Web cache server partition and the distributed computing server partition based on demand for the each set of servers.

3. The method of claim 1, wherein the provisioning step provisions the server based on demand for the customer'"'"'s application program.

4. The method of claim 1, further comprising:

un-provisioning a server in the distributed computing server partition that has been provisioned for a customer'"'"'s application program if demand for the customer'"'"'s application program has fallen below a predetermined level.

5. The method of claim 1, wherein if the customer'"'"'s application program requires a particular operating system then the provisioning step provisions the server to run the required operating system.

6. The method of claim 1, wherein the provisioning step creates an image of the customer'"'"'s application program and sends the image to the server.

7. The method of claim 5, wherein the provisioning step creates an image of the customer'"'"'s application program combined with the required operating system and sends the image to the server.

8. The method of claim 1, wherein the provisioning step provisions servers in the distributed computing server partition that have already been provisioned with at least one other application program with the customer'"'"'s application program to reach a predetermined level of server usage.

9. The method of claim 1, further comprising:

charging a fee to the customer based on usage of servers in the distributed computing server partition.

10. The method of claim 1, wherein the provisioning step selects servers in the distributed computing server partition based on the characteristics of the customer'"'"'s application program.

11. A method for dynamically distributing computing resources for application programs across a plurality of servers, comprising:

creating a pool of servers;

tracking the status of each server in the pool of servers;

automatically provisioning a server from the server pool to run a customer'"'"'s application program based on demand for the customer'"'"'s application program;

wherein if the customer'"'"'s application program requires a particular operating system then the provisioning step provisions the server to run the required operating system; and

un-provisioning a server that has been provisioned for a customer'"'"'s application program if demand for the customer'"'"'s application program has fallen below a predetermined level.

12. The method of claim 11, wherein the provisioning step creates an image of the customer'"'"'s application program and sends the image to the server.

13. The method of claim 11, wherein the provisioning step creates an image of the customer'"'"'s application program combined with the required operating system and sends the image to the server.

14. The method of claim 11, wherein the provisioning step provisions servers that have already been provisioned with at least one other application program with the customer'"'"'s application program to reach a predetermined level of server usage.

15. The method of claim 11, further comprising:

charging a fee to the customer based on usage of servers in the server pool.

16. The method of claim 11, wherein the provisioning step selects servers based on the characteristics of the customer'"'"'s application program.

17. The method of claim 11, further comprising:

load balancing traffic across a plurality of servers that been provisioned with the customer'"'"'s application program.

18. An apparatus for dynamically distributing computing resources for application programs across a plurality of servers in a content delivery network, comprising:

partitioning the plurality of servers into a Web cache server partition and a distributed computing server partition;

tracking the status of each distributed computing server in the distributed computing server partition;

automatically provisioning a server from the distributed computing server partition to run a customer'"'"'s application program; and

load balancing traffic across servers in the Web cache server partition and the distributed computing server partition.

19. The apparatus of claim 18, wherein the partitioning module varies the size of the Web cache server partition and the distributed computing server partition based on demand for the each set of servers.

20. The apparatus of claim 18, wherein the provisioning module provisions the server based on demand for the customer'"'"'s application program.

21. The apparatus of claim 18, further comprising:

un-provisioning a server in the distributed computing server partition that has been provisioned for a customer'"'"'s application program if demand for the customer'"'"'s application program has fallen below a predetermined level.

22. The apparatus of claim 18, wherein if the customer'"'"'s application program requires a particular operating system then the provisioning module provisions the server to run the required operating system.

23. The apparatus of claim 18, wherein the provisioning module creates an image of the customer'"'"'s application program and sends the image to the server.

24. The apparatus of claim 22, wherein the provisioning module creates an image of the customer'"'"'s application program combined with the required operating system and sends the image to the server.

25. The apparatus of claim 18, wherein the provisioning module provisions servers in the distributed computing server partition that have already been provisioned with at least one other application program with the customer'"'"'s application program to reach a predetermined level of server usage.

26. The apparatus of claim 18, further comprising:

charging a fee to the customer based on usage of servers in the distributed computing server partition.

27. The apparatus of claim 18, wherein the provisioning module selects servers in the distributed computing server partition based on the characteristics of the customer'"'"'s application program.

28. An apparatus for dynamically distributing computing resources for application programs across a plurality of servers, comprising:

creating a pool of servers;

tracking the status of each server in the pool of servers;

automatically provisioning a server from the server pool to run a customer'"'"'s application program based on demand for the customer'"'"'s application program;

wherein if the customer'"'"'s application program requires a particular operating system then the provisioning module provisions the server to run the required operating system; and

un-provisioning a server that has been provisioned for a customer'"'"'s application program if demand for the customer'"'"'s application program has fallen below a predetermined level.

29. The apparatus of claim 28, wherein the provisioning module creates an image of the customer'"'"'s application program and sends the image to the server.

30. The apparatus of claim 28, wherein the provisioning module creates an image of the customer'"'"'s application program combined with the required operating system and sends the image to the server.

31. The apparatus of claim 28, wherein the provisioning module provisions servers that have already been provisioned with at least one other application program with the customer'"'"'s application program to reach a predetermined level of server usage.

32. The apparatus of claim 28, further comprising:

charging a fee to the customer based on usage of servers in the server pool.

33. The apparatus of claim 28, wherein the provisioning module selects servers based on the characteristics of the customer'"'"'s application program.

34. The apparatus of claim 28, further comprising:

load balancing traffic across a plurality of servers that been provisioned with the customer'"'"'s application program.