Client assisted autonomic computing

• US 7,657,779 B2
• Filed: 09/18/2002
• Issued: 02/02/2010
• Est. Priority Date: 09/18/2002
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Kaminsky, David L., Ogle, David M.
• Primary Examiner(s): Beausoliel; Robert
• Assistant Examiner(s): Manoskey; Joseph D
• Application Number:
  US10/246,902
• Publication Number:
  US 20040078622A1
• Time in Patent Office: 2,694 Days
• Field of Search: 714/4, 714/7, 714/13, 714/18, 714/43, 370/242
• US Class Current: 714/6.32
• CPC Class Codes: G06F 11/0748 in a remote unit communicating with a single-box computer node experiencing an error/fault remote testing G06F11/2294
• CPC Class Codes: G06F 11/0793 Remedial or corrective actions recovery from an exception in an instruction pipeline G06F9/3861; by retry G06F11/1402; for recovering from a failure of a protocol instance or entity H04L69/40
• CPC Class Codes: G06F 11/1415 at system level
• CPC Class Codes: G06F 11/2023 Failover techniques
• CPC Class Codes: H04L 41/0661 by reconfiguring faulty entities
• 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 67/1019 Random or heuristic server selection
• CPC Class Codes: H04L 67/1034 Reaction to server failures by a load balancer
• CPC Class Codes: H04L 69/40 for recovering from a failure of a protocol instance or entity, e.g. service redundancy protocols, protocol state redundancy or protocol service redirection management of faults, events, alarms or notifications in data switching networks H04L41/06

Abstract

A method, system and apparatus for server failure diagnosis and self-healing in a server farm. An autonomic server farm which has been configured in accordance with the inventive arrangements can include a multiplicity of servers enabled to respond to requests received from clients which are external to the server farm. A resource director such as an IP sprayer or a network dispatcher can be configured to route requests to selected ones of the servers, in accordance with resource allocation algorithms such as random, round-robin and least recently used. Significantly, unlike conventional server farms whose management of failure diagnosis and self-healing relies exclusively upon the capabilities of the resource director, in the present invention, client-assisted failure detection logic can be coupled to the resource director so as to provide client-assisted management of failure diagnosis and self-healing.

Claims

1. A method of server failure diagnosis and self-healing in a server farm comprising a plurality of separately assignable servers, comprising the steps of:

receiving a retry request from a client attempting to engage in a communicative request/response session with an assigned server from said plurality of separately assignable servers in the server farm;

determining from said retry request received from the client, an occurrence of a failure in said assigned server; and

performing operations for remediating said failure in said assigned server, wherein

said determining step comprises indentifying an indicator associated with said retry request, said indicator indicating said occurrence of said failure in said assigned servers.

2. The method of claim 1, wherein said performing step comprises the step of performing at least one remedial operation selected from the group consisting of recycling said assigned server having said failure, restarting a device in said assigned server having said failure, and restarting an application in said assigned server having said failure.

3. The method of claim 1, wherein said performing step further comprises the step of notifying an administrative node of said failure.

4. The method of claim 1, wherein said performing step comprises the steps of:

diagnosing said failure; and

,

performing at least one remedial operation based upon said diagnosis wherein said remedial operation is selected from the group consisting of recycling said assigned server having said failure, restarting a device in said assigned server having said failure, and restarting an application in said assigned server having said failure.

5. The method of claim 4, wherein said diagnosing step comprises the steps of:

pinging said assigned server having said failure; and

,

performing a traceroute between said assigned server having said failure and said client.

6. The method of claim 4, wherein said diagnosing step comprises the steps of:

injecting a test transaction into said assigned server having said failure; and

,

monitoring a result produced by said injection.

7. The method of claim 6, wherein said injecting step comprises the step of inducing said client to inject a test transaction into said assigned server having said failure.

8. A method of server failure diagnosis and self-healing in a server farm, comprising the steps of:

receiving a retry request from client attempting to engage in a communicative request/response session with an assigned server in the server farm;

determining from said retry request, an occurrence of a failure in said assigned server; and

,

performing operations to said assigned server for remediating said failure in said assigned server, wherein said determining step comprises the step of locating in a request string associated with said retry request an indication of said occurrence of said failure in said assigned server.

9. A method of server failure diagnosis and self-healing in a server farm, comprising the steps of:

receiving a retry request from client attempting to engage in a communicative request/response session with an assigned server in the server farm;

determining from said retry request, an occurrence of a failure in said assigned server; and

,

performing operations to said assigned server for remediating said failure in said assigned server, wherein

said determining step comprises the step of locating in a cookie associated with said retry request an indication of said occurrence of said failure in said assigned server.

10. An autonomic server farm comprising:

a plurality of separately assignable servers configured to respond to requests received from clients which are external to the server farm;

a resource director configured to route requests to an assigned first one of said servers;

client-assisted failure detection logic coupled to said resource director to determine an occurrence of a failure in said assigned first one of said servers; and

a doctor communicatively coupled to said resource director and configured to perform an operation to said assigned first one of said servers for remediating said failure in said assigned first one of said servers, wherein

responsive to determining the occurrence of the failure in said assigned first one of said server, assigning a second one of said servers to process a retry request received from said clients, the assigned second one of said servers different than the assigned first one of said servers server having said failure, and

said failure detection logic indentifying an indicator associated with said retry request, said indicator indicating said occurrence of said failure in said assigned first one of said server.

11. A computer readable storage having stored thereon a computer program for performing server failure diagnosis and self healing in a server farm comprising a plurality of separately assignable servers, said computer program comprising a routine set of instructions which when executed cause a computer to perform the steps of:

receiving a retry request from a client attempting to engage in a communicative request/response session with an assigned server from said plurality of separately assignable servers in the server farm;

determining from said retry request received from the client, an occurrence of a failure in said assigned server; and

performing operations for remediating said failure in said assigned server, wherein

said determining step comprises indentifying an indicator associated with said retry request, said indicator indicating said occurrence of said failure in said assigned server.

12. The computer readable storage of claim 11, wherein said performing step comprises the step of performing at least one remedial operation selected from the group consisting of recycling said assigned server having said failure, restarting a device in said assigned server having said failure, and restarting an application in said assigned server having said failure.

13. The computer readable storage of claim 11, wherein said performing step further comprises the step of notifying an administrative node of said failure.

14. The computer readable storage of claim 11, wherein said performing step comprises the steps of:

diagnosing said failure; and

,

performing at least one remedial operation based upon said diagnosis wherein said remedial operation is selected from the group consisting of recycling said assigned server having said failure, restarting a device in said assigned server having said failure, and restarting an application in said assigned server having said failure.

15. The computer readable storage of claim 14, wherein said diagnosing step comprises the steps of:

pinging said assigned server having said failure; and

,

performing a traceroute between said assigned server having said failure and said client.

16. The computer readable storage of claim 14, wherein said diagnosing step comprises the steps of:

injecting a test transaction into said assigned server having said failure; and

,

monitoring a result produced by said injection.

17. The computer readable storage of claim 16, wherein said injecting step comprises the step of inducing said client to inject a test transaction into said assigned server having said failure.

18. A computer readable storage having stored thereon a computer program for performing server failure diagnosis and self healing in a server farm, said computer program comprising a routine set of instructions which when executed cause a computer to perform the steps of:

receiving a retry request from client attempting to engage in a communicative request/response session with an assigned server in the server farm;

determining from said retry request, an occurrence of a failure in said assigned server; and

,

performing operations to said assigned server for remediating said failure in said assigned server, wherein

said determining step comprises the step of locating in a request string associated with said retry request an indication of said occurrence of said failure in said assigned server.

19. A computer readable storage having stored thereon a computer program for performing server failure diagnosis and self-healing in a server farm, said computer program comprising a routine set of instructions which when executed cause a computer to perform the steps of:

receiving a retry request from client attempting to engage in a communicative request/response session with an assigned server in the server farm;

determining from said retry request, an occurrence of a failure in said assigned server; and

,

performing operations to said assigned server for remediating said failure in said assigned server, wherein

said determining step comprises the step of locating in a cookie associated with said retry request an indication of said occurrence of said failure in said assigned server.