Server system, computer system, method for managing server system, and computer-readable storage medium

Patent metadata

Field	Value
Publication number	US-2016266987-A1
Application number	US-201314777883-A
Country	US
Kind code	A1
Filing date	Sep 12, 2013
Priority date	Sep 12, 2013
Publication date	Sep 15, 2016
Grant date	—

Abstract

In a server system, a hardware configuration comparison is made with respect to each combination of a current server and a backup server, and, by referring to hardware configuration matching policy information, the presence or absence of hardware configuration concealment and the possibility of a take-over are determined with respect to each combination of the current server and the backup server. In addition, with respect to each combination of the current server and the backup server, a configuration matching rate indicating the ratio of hardware configuration matching is calculated. Based on information about the presence or absence of hardware configuration concealment, information about the possibility of a take-over, and information about the configuration matching rate with respect to each combination of the current server and the backup server, the backup server as a take-over destination of the current server is allocated.

First claim

1 . A server system comprising:
at least one current server processing an operation; at least one backup server prepared to take over the operation of the current server when the current server fails; and a local management computer that monitors the current server and the backup server and controls server switching, the local management computer includes: a processor that executes a process of allocating the backup server as a take-over destination for the operation of the current server, and a memory that stores at least hardware configuration matching policy information indicating a hardware configuration condition enabling a server take-over, the processor configured to execute: a process of acquiring hardware configuration information from each of the current server and the backup server, a process of making a hardware configuration comparison based on the acquired hardware configuration information with respect to each combination of the current server and the backup server, and determining a presence or absence of hardware configuration concealment and the possibility of a take-over with respect to each combination of the current server and the backup server by referring to the hardware configuration matching policy information read from the memory, a process of calculating a configuration matching rate indicating the ratio of hardware configuration matching with respect to each combination of the current server and the backup server, and a process of allocating the backup server as the take-over destination of the current server on the basis of information about the presence or absence of hardware configuration concealment, information about the possibility of a take-over, and information about the configuration matching rate with respect to each combination of the current server and the backup server.

2 . The server system according to claim 1 , wherein the processor further executes:
a process of acquiring information about the number of ECC errors in the current server, and a process of modifying, based on the acquired number of ECC errors, the backup server allocation that has been executed, and dynamically allocating the backup server to the current server.

3 . The server system according to claim 2 , wherein the processor further executes:
a process of acquiring information about a CPU availability factor of the current server, and information about a CPU core number increase rate in each of the combinations of the current server and the backup server, and a process of dynamically allocating the backup server to the current server using the CPU availability factor and the information about the CPU core number increase rate in addition to the number of ECC errors.

4 . The server system according to claim 2 , wherein
the memory further stores allocation modifying policy information specifying a backup server allocation condition based on at least the number of ECC errors, and the processor reads the allocation modifying policy information from the memory, and executes the process of dynamically allocating the backup server to the current server.

5 . The server system according to claim 3 , wherein
the memory further stores allocation modifying policy information specifying a backup server allocation condition based on the number of ECC errors, a backup server allocation condition based on the CPU availability factor, and a backup server allocation condition based on the CPU core number increase rate, each of the allocation conditions in the allocation modifying policy information having an consideration priority setting, and the processor reads the allocation modifying policy information from the memory, considers the allocation modifying policy information according to the consideration priority, and executes the process of dynamically allocating the backup server to the current server.

6 . The server system according to claim 1 , wherein the processor further executes:
a process of executing, in response to a failure notification with respect to any of the current servers, the information about the presence or absence of hardware concealment process to the backup server allocated as the take-over destination of the current server experiencing failure, a process of receiving from the backup server a completion notification of a hardware concealment process executed based on the information about the presence or absence of hardware concealment, and a process of switching the current server experiencing failure to the backup server allocated as the take-over destination.

7 . A computer system comprising:
a plurality of the server systems according to claim 1 ; and a global management computer that manages the plurality of server systems, wherein the global management computer enables, by managing communication between the local management computers in the plurality of server systems, each local management computers to acquire hardware configuration information about the current servers and the backup servers disposed in different server systems, and the local management computer allocates the backup server in a server system different from the server system of the local management computer as the take-over destination of the current server in the server system of the local management computer.

8 . A method of managing a server system including at least one current server processing an operation, at least one backup server prepared to take over the operation of the current server when the current server fails, and a local management computer that monitors the current server and the backup server and that controls server switching,
the local management computer including a processor that executes a process of allocating the backup server as a take-over destination for the operation of the current server, and a memory that stores at least hardware configuration matching policy information indicating a hardware configuration condition enabling a server take-over, the managing method comprising: a step of the processor acquiring the hardware configuration information from each of the current server and the backup server; a step of the processor making a hardware configuration comparison based on the acquired hardware configuration information with respect to each combination of the current server and the backup server, and, by referring to the hardware configuration matching policy information read from the memory, determining the presence or absence of hardware configuration concealment and the possibility of a take-over with respect to each combination of the current server and the backup server; a step of the processor calculating a configuration matching rate indicating a ratio of hardware configuration matching with respect to each combination of the current server and the backup server; and a process of the processor allocating the backup server as a take-over destination of the current server with respect to each combination of the current server and the backup server, on the basis of information about the presence or absence of hardware configuration concealment, information about the possibility of a take-over, and information about the configuration matching rate.

9 . The server system managing method according to claim 8 , further comprising:
a step of the processor acquiring information about the number of ECC errors in the current server; and a step of the processor modifying an executed backup server allocation on the basis of the acquired number of ECC errors, and dynamically allocating the backup server to the current server.

10 . The server system managing method according to claim 9 , further comprising:
a step of the processor acquiring info

Assignees

• Hitachi Ltd

Inventors

• Kawamura Tetsuo
• Umehara Shunji

Classifications

• G06F11/2025 Primary

  using centralised failover control functionality · CPC title

• G06F11/076

  by exceeding a count or rate limit, e.g. word- or bit count limit · CPC title

• G06F2201/805

  Real-time · CPC title

• G06F11/2033 Primary

  switching over of hardware resources · CPC title

• G06F11/0709

  in a distributed system consisting of a plurality of standalone computer nodes, e.g. clusters, client-server systems · CPC title