Server system operation control method

• US 20030079093A1
• Filed: 08/28/2002
• Published: 04/24/2003
• Est. Priority Date: 10/24/2001
• Status: Active Grant

• Current Assignee: Hitachi, Ltd.
• Original Assignee: Hitachi, Ltd.
• Inventors: Takamura, Akihiro, Fujii, Hiroaki, Miki, Yoshio, Kawashimo, Tatsuya
• Granted Patent: US 6,832,298 B2
• Time in Patent Office: Days
• US Class Current: 711/147
• CPC Class Codes: G06F 11/203 using migration
• CPC Class Codes: G06F 11/2038 with a single idle spare processing component
• CPC Class Codes: G06F 11/2041 with more than one idle spare processing component
• CPC Class Codes: G06F 11/2043 where the redundant components share a common memory address space
• CPC Class Codes: G06F 11/2046 where the redundant components share persistent storage G06F11/2043 takes precedence
• CPC Class Codes: G06F 11/2051 in regular structures

Abstract

A main logical unit and a standby logical unit are defined by a process controller in a shared main memory multiprocessor, and an information storage space accessible from both logical units is provided. The main logical unit stores address information onto that information storage space by indicating a memory area it controls as the main memory area. When failover or cloning becomes necessary, the standby logical unit searches the information on the applicable address. Then from the applicable information, it also searches information on the main memory area controlled by the main logical unit to establish in itself and forms a processing environment and state identical to the main logical unit such that the standby logical unit takes over all or a portion of the processing of the main logical unit. This enables the construction of a server system of high operability to overcome failures and poor response times by failover and cloning, etc.

Claims

1. A server system operation control method implemented by a single shared memory type multiprocessor system made up of a plurality of processors, a main memory device, an external memory device and a connection means for mutually connecting these components, comprising the steps of:

designating a main logical unit made up of a group of said processors and a portion of said main memory device and a standby logical unit made up of another group of said processors and another portion of said main memory device, each operating independently;

providing a memory segment on the main memory device to be accessible from both of the main logical unit and the standby logical unit and setting a take-over information storage space on said memory segment to store information for take-over of control from the main logical unit to the standby logical unit;

storing, by the main logical unit, information required for take-over of control to the information storage space at every time when the information is made in said main logical unit; and

searching, by the standby logical unit, information stored in the information storage space when a take-over request is sent to the standby logical unit from the main logical unit and forming a processing environment and status in said standby logical unit which are identical to those of the main system, to take over all or a portion of the processing of the main logical unit.

2. A server system operation control method according to claim 1, wherein, when the standby logical unit receives said take-over request from the main logical unit, the standby logical unit searches information stored in the information storage space and, based on the information obtained from the search results, accesses the main memory resources controlled by the main logical unit to form the processing environment and status identical to those of the main logical unit.

3. A server system operation control method according to claim 1 or claim 1, wherein said information for take-over of control includes main memory addresses of main memory areas where information of processing environment and status is stored, and said main memory addresses are updated by said main logical unit when said main memory areas are generated or moved in said main memory device.

4. A server system operation control method according to any of claim 3, wherein said standby logical unit obtains said information of processing environment and status by referring said main memory device using said main memory addresses.

5. A server system operation control method according to claim 1, wherein a control processor designates said main logical unit and standby logical unit, and said take-over request is issued by said control processor.

6. A server system operation control method according to claim 5, wherein said control processor is one of said plurality of processors.

7. A server system operation control method according to claim 5, wherein said control processor is an external control terminal provided for the shared main memory type multiprocessor system.

8. A server system operation control method according to any of claims 5, wherein, when a main memory area controlled by the main logical unit is protected from access by other logical units, the control processor receives a request from the standby logical unit to access the main memory area controlled by the main logical unit, executes access, and transfers information obtained by the access to the standby logical unit.

9. A server system operation control method implemented by a shared memory type multiprocessor system including plural processors, a main memory device and connection means for mutually connecting therein, comprising:

designating a main logical unit, a standby logical unit, and a shared memory accessible from both the main logical unit and the standby logical unit;

updating periodically a main logical unit status;

monitoring periodically the updated main logical unit status to check whether a failure occurs in the main logical unit;

storing periodically the updated main logical unit status in a memory of the main logical unit; and

once the failure occurs in the main logical unit, instructing the standby logical unit, to take over the main logical unit by retrieving the updated main logical unit status from the memory of the main logical unit so as to restore the updated main logical unit status in the standby logical unit, or to share a workload of the main logical unit by retrieving the updated main logical unit status from the memory of the main logical unit so as t duplicate the updated main logical unit status in the standby logical unit.

10. The server system operation control method according to claim 9, wherein the monitoring step involves determining the failure is a crash or an overload.

11. The server system operation control method according to claim 10, wherein the instructing step involves instructing the standby logical unit to take over the main logical unit if the failure is determined as a crash or to share the workload of the main logical unit if the failure is determined as an overload.