Dynamically assigning, by functional domain, separate pairs of servers to primary and backup service processor modes within a grouping of servers

Patent metadata

Field	Value
Publication number	US-10069688-B2
Application number	US-201615062270-A
Country	US
Kind code	B2
Filing date	Mar 7, 2016
Priority date	Mar 7, 2016
Publication date	Sep 4, 2018
Grant date	Sep 4, 2018

Abstract

Multiple functional domains are identified for controlling a grouping of servers. A controller assigns, to each functional domain of the multiple functional domains, a separate primary server from among the grouping of servers and a separate backup server from among the grouping of servers, wherein for each functional domain the separate primary server is different from the separate backup server based on a separate affinity selection for each functional domain. Responsive to detecting a failure in a particular primary server of the grouping of servers, the controller automatically switches control of a particular functional domain assigned to the particular primary server from the particular primary server to a particular backup server assigned to the particular functional domain.

First claim

What is claimed is:

1. A method comprising:
identifying a plurality of functional domains for controlling a grouping of a plurality of servers;
determining a separate affinity selection for each of a plurality of separate groupings each of two or more of the plurality of functional domains indicating a strength of an affinity that each of the two or more of the plurality of functional domains need to reside on one or more of a same service processor and a same chassis within the plurality of servers;
assigning, to each functional domain of the plurality of functional domains, a separate primary server from among the plurality of servers and a separate backup server from among the plurality of servers, wherein for each functional domain the separate primary server is different from the separate backup server and positioned on the plurality of servers based on the separate affinity selection for each of the plurality of separate groupings; and
responsive to detecting a failure in a particular primary server of the plurality of servers, automatically switching control of a particular functional domain assigned to the particular primary server from the particular primary server to a particular backup server assigned to the particular functional domain, such that only the particular functional domain from among the plurality of functional domains is down during the failure and switching control.

2. The method according to claim 1 , wherein assigning, to each functional domain of the plurality of functional domains, a separate primary server from among the plurality of servers and a separate backup server from among the plurality of servers, wherein for each functional domain the separate primary server is different from the separate backup server and positioned on the plurality of servers based on the separate affinity selection for each of the plurality of separate groupings, further comprises:
forming a pre-configured mapping with an entry for each functional domain specifying a separate pair of servers from among the plurality of servers by assigning, to each functional domain, the separate primary server from among the plurality of servers and the separate backup server from among the plurality of servers.

3. The method according to claim 1 , wherein assigning, to each functional domain of the plurality of functional domains, a separate primary server from among the plurality of servers and a separate backup server from among the plurality of servers, wherein for each functional domain the separate primary server is different from the separate backup server and positioned on the plurality of servers based on the separate affinity selection for each of the plurality of separate groupings, further comprises:
determining the separate affinity selection for each of the plurality of separate groupings of each of two or more of the plurality of functional domains indicating a strength of the affinity that each of the two or more of the plurality of functional domains need to reside on one or more of the same service processor, the same chassis, a same chassis management module, and a same switch.

4. The method according to claim 1 , further comprising:
identifying each functional domain of the plurality of functional domains using a service location protocol.

5. The method according to claim 1 , wherein identifying a plurality of functional domains for controlling a grouping of a plurality of servers further comprises:
identifying the grouping of the plurality of servers, each of the plurality of servers comprising one or more of a blade and a rack, each of the plurality of servers installed within one or more chassis, each of the one or more chassis operating in a non-uniform memory access mode with a single instance of a hypervisor virtualizing resources across the plurality of servers and controlled by a management console.

6. The method according to claim 1 , wherein identifying a plurality of functional domains for controlling a grouping of a plurality of servers further comprises:
identifying the grouping of the plurality of servers wherein each server of the plurality of servers comprises a service processor for managing one or more of the plurality of functional domains assigned to the server housing the service processor.

7. The method according to claim 1 , wherein identifying a plurality of functional domains for controlling a grouping of a plurality of servers further comprises:
selecting each functional domain from among the plurality of functional domains from one or more of interaction with a primary chassis management module, interaction with a backup chassis management module, interaction with a primary management console, interaction with a backup management console, interaction with a hypervisor, hosting web server based interfaces, interaction with one or more common information model clients, a service processor to host a processor bus ownership, hardware surveillance, soft function surveillance, virtual serial terminal connections to virtual partitions running on a host processor, support interface bus ownership, and debug info and error log aggregation.

8. The method of claim 1 , wherein responsive to detecting a failure in a particular primary server of the plurality of servers, automatically switching control of a particular functional domain assigned to the particular primary server from the particular primary server to a particular backup server assigned to the particular functional domain further comprises:
identifying the particular functional domain assigned to the particular primary server;
identifying the particular backup server assigned to the particular functional domain;
notifying the particular backup server to take over a primary role for the particular functional domain;
assigning a second server from among the plurality of servers to a backup role for the particular functional domain; and
notifying the second server that the second server is assigned to the backup role for the particular functional domain.

9. A computer system comprising one or more processors, one or more computer-readable memories, one or more computer-readable storage devices, and program instructions, stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, the stored program instructions comprising:
program instructions to identify a plurality of functional domains for controlling a grouping of a plurality of servers;
program instructions to determine a separate affinity selection for each of a plurality of separate groupings each of two or more of the plurality of functional domains indicating a strength of an affinity that each of the two or more of the plurality of functional domains need to reside on one or more of a same service processor and a same chassis within the plurality of servers;
program instructions to assign, to each functional domain of the plurality of functional domains, a separate primary server from among the plurality of servers and a separate backup server from among the plurality of servers, wherein for each functional domain the separate primary server is different from the separate backup server and positioned on the plurality of servers based on the separate affinity selection for each of the plurality of separate groupings; and
program instructions, responsive to detecting a failure in a particular primary server of the plurality of servers, to automatically switch control of a particular functional domain assigned to the particular primary server from the particular primary server to a particular backup server assigned to the particular functional domain.

10. The com

Assignees

• IBM

Inventors

• Atyam Balaji V
• Sainath Venkatesh
• Subbanna Vishwanatha

Classifications

• H04L67/1034

  Reaction to server failures by a load balancer · CPC title

• H04L69/40

  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) · CPC title

• H04L41/0663

  Performing the actions predefined by failover planning, e.g. switching to standby network elements · CPC title

• H04L67/1008

  based on parameters of servers, e.g. available memory or workload (monitoring of computer activity G06F11/30) · CPC title

• H04L41/0816

  the condition being an adaptation, e.g. in response to network events · CPC title