Autonomic selection of a request routing policy based upon cache effectiveness

• US 7,552,235 B2
• Filed: 12/11/2003
• Issued: 06/23/2009
• Est. Priority Date: 12/11/2003
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Chase, Jeffery S., Doyle, Ronald P.
• Primary Examiner(s): Etienne; Ario
• Assistant Examiner(s): Burgess; Barbara N
• Application Number:
  US10/733,996
• Publication Number:
  US 20050144317A1
• Time in Patent Office: 2,021 Days
• Field of Search: 709/203, 709/228, 709/246, 709/223, 709/226, 709/201, 709/232, 709/245, 709/249, 709/241, 709/225, 709/219, 709/323, 709/229, 709/224, 709/242, 709/202, 709/218, 370/395.2, 370/390, 370/432, 370/349, 370/401, 370/389, 370/351, 726/28, 719/317, 710/316, 455/432.1, 455/435.1, 715/705, 718/105, 718/104
• US Class Current: 709/238
• CPC Class Codes: H04L 67/1001 for accessing one among a plurality of replicated servers
• CPC Class Codes: H04L 67/1023 based on a hash applied to IP addresses or costs
• CPC Class Codes: H04L 67/563 Data redirection of data network streams
• CPC Class Codes: H04L 67/63 Routing a service request depending on the request content or context

Abstract

The present invention is a system, method and apparatus for autonomic request routing policy selection. The system of the invention can include a multiplicity of pre-configured request routing policies and a data store of cache metrics for the pre-configured request routing policies. A routing policy selector can be configured for communicative linkage to a server cluster having one or more servers and programmed to select a particular one of the request routing policies for use in routing content requests in the server cluster based upon the cache metrics. In this regard, the routing policy selector further can include a coupling to the routing policies and the data store of cache metrics.

Claims

1. An autonomic request routing policy selection method comprising the steps of:

identifying a contemporary trace footprint experienced by a coupled server cluster;

identifying a cache allocation for said coupled server cluster;

retrieving at least two sets of hit rate metrics, each set of metrics corresponding to a particular routing policy;

comparing said hit rate metrics based upon said identified trace footprint and said identified cache allocation to determine a preferred routing policy; and

,

selecting said preferred routing policy for use in routing content requests to said server cluster.

2. The method of claim 1, further comprising the steps of:

computing with said hit rate metrics, an optimal server cluster configuration for said preferred routing policy; and

,

provisioning an optimal number of servers in said server cluster based upon said computed optimal server cluster configuration.

3. The method of claim 1, wherein said selecting step comprises the step of selecting a server load balancing type routing policy when said identified cache allocation approaches in value said identified trace footprint.

4. The method of claim 1, wherein said selecting step comprises the step of selecting a content localizing type routing policy when either said identified cache allocation is small, or when said trace footprint is large.

5. A machine readable storage having stored thereon a computer program for autonomic request routing policy selection, the computer program comprising a routine set of instructions which when executed by the machine cause the machine to perform the steps of:

identifying a contemporary trace footprint experienced by a coupled server cluster;

identifying a cache allocation for said coupled server cluster;

retrieving at least two sets of hit rate metrics, each set of metrics corresponding to a particular routing policy;

comparing said hit rate metrics based upon said identified trace footprint and said identified cache allocation to determine a preferred routing policy; and

,

selecting said preferred routing policy for use in routing content requests to said server cluster.

6. The machine readable storage of claim 5, further comprising the steps of:

computing with said hit rate metrics, an optimal server cluster configuration for said preferred routing policy; and

,

provisioning an optimal number of servers in said server cluster based upon said computed optimal server cluster configuration.

7. The machine readable storage of claim 5, wherein said selecting step comprises the step of selecting a server load balancing type routing policy when said identified cache allocation approaches in value said identified trace footprint.

8. The machine readable storage of claim 5, wherein said selecting step comprises the step of selecting a content localizing type routing policy when either said identified cache allocation is small, or when said trace footprint is large.