Method of and system for allocating resources to resource requests

• US 7,321,926 B1
• Filed: 02/11/2002
• Issued: 01/22/2008
• Est. Priority Date: 02/11/2002
• Status: Expired due to Term

• Current Assignee: RPX Corporation
• Original Assignee: Extreme Networks, Inc.
• Inventors: de la Iglesia, Erik, Zhang, Hui, Wang, Wei, Wallace, Mark Aaron, Lowe, Rick K., Liu, Liang, Gomez, Miguel
• Primary Examiner(s): Follansbee, John
• Assistant Examiner(s): PATEL, ASHOKKUMAR B
• Application Number:
  US10/074,462
• Time in Patent Office: 2,171 Days
• Field of Search: 709/105, 709/220, 709/225, 709/226, 709/224, 379/112.04, 379/114.17, 455/453, 718/104, 718/105
• US Class Current: 709/220
• CPC Class Codes: G06F 2209/5011 Pool
• CPC Class Codes: G06F 2209/5016 Session
• CPC Class Codes: G06F 9/5033 considering data affinity
• CPC Class Codes: G06F 9/505 considering the load
• CPC Class Codes: H04L 61/35 involving non-standard use of addresses for implementing network functionalities, e.g. coding subscription information within the address or functional addressing, i.e. assigning an address to a function
• 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 67/101 based on network conditions
• CPC Class Codes: H04L 67/1017 based on a round robin mechanism
• CPC Class Codes: H04L 67/1023 based on a hash applied to IP addresses or costs
• CPC Class Codes: H04L 67/1027 Persistence of sessions during load balancing
• CPC Class Codes: H04L 67/1034 Reaction to server failures by a load balancer

Abstract

A system and method of allocating a resource to a service request. Servers are virtually assigned through a hierarchy including groups of servers and super groups of the groups of servers. Each service request type is associated with a service index that determines both a super group and a load balancing policy for that service request type. A load balancing policy may be applied to select a group of servers among several server groups associated with the super group. Another load balancing policy is applied to the selected group of servers to select a server to handle the service request. The hierarchical data structure allows servers to be configured into overlappable, arbitrary subsets that can address service requests matching configured content rules. Load balancing policies can be selected by service request type.

Claims

1. A system for allocating resources to service requests comprising:

a load balancing manager;

a service index table, part of the load balancing manager, having a plurality of super group indexes, the service index table to receive a first service index corresponding to a service request, the service index table to provide a first of a plurality super group indexes in response to the first service index, the service index table to provide a first of a plurality of balancing policies in response to receiving the service index;

a super group block, part of the load balancing manager, to provide a first of a plurality of super groups, each super group having one or more resource group indexes in response to the provision of the first super group index;

a first load balancer, part of the load balancing manager, to select a first resource group index from among the first super group based on the first load balancing policy;

a group block, part of the load balancing manager, to provide one or more resource indexes in response to the provision of the first resource group index, each resource index corresponding to one of a plurality of resources; and

a second load balancer, part of the load balancing manager, to select a first resource index from among the one or more resource indexes based on a second load balancing policy, to allocate the resource corresponding to the first resource index.

2. The system of claim 1 wherein the resource is a server.

3. The system of claim 1 wherein the second load balancing policy is selected based on the first load balancing policy index.

4. The system of claim 1 wherein the second load balancing policy is selected independently of the first load balancing policy index.

5. The system of claim 1 further comprising a content analysis engine configured to receive at least a portion of a data packet and generate a service index based on at least one of domain name and URL pattern matching.

6. The system of claim 1 further comprising a lookup table coupled to receive at least a portion of a data packet, the lookup table to select the service index based on at least one of a destination IP, a destination port and a protocol corresponding to the data packet.

7. The system of claim 1 further comprising a history table to override the load balancing manager and select a resource based on a persistence policy if a match is found in the history table corresponding to the service request.

8. A method for allocating resources to service requests comprising:

receiving a service index at a load balancing manager comprising a service index table having a plurality of super group indexes, the service index corresponding to a service request;

selecting a first of the super group indexes in response to receiving the service index;

generating a first load balancing policy index in response to receiving the service index;

selecting a first load balancing policy from among a plurality of load balancing policies based on the first load balancing policy index;

generating a plurality of resource group indexes in response to the selecting of the first super group index;

applying the first load balancing policy to select one of the plurality of resource group indexes;

generating one or more resource indexes in response to the selection of the one resource group index, the at least one resource index corresponding to at least one of a plurality of resources;

selecting a second load balancing policy;

applying the second load balancing policy to select one of the at least one resource index; and

assigning a first resource to the service request, the one resource index indicating the resource.

9. The method of claim 8 wherein the resource is a server.

10. The method of claim 8 further comprising selecting the second load balancing policy based on the first load balancing policy index.

11. The method of claim 8 further comprising selecting the second load balancing policy independently of the first load balancing policy index.

12. The method of claim 8 further comprising:

receiving at least a portion of a data packet having a domain name and a URL; and

generating a service index based on the domain name and pattern matching of within the URL.

13. The method of claim 8 further comprising:

receiving at least a portion of a data packet having a destination IP, a destination port and a protocol; and

generating a service index based on at least one of the destination IP, the destination port and the protocol.

14. The method of claim 8 further comprising overriding the assigning of the first resource and assigning a second resource to the service request based on a persistence policy if a match is found in a history table corresponding to the service request.

15. The method of claim 14 wherein the steps of generating the first super group index, generating a first load balancing policy index selecting a first load balancing policy, generating a plurality of group indexes, generating one or more resource indexes, and assigning a first resource being performed only if a match is not found in the history table corresponding to the service request.