JPH02268335A - Computer system - Google Patents

Abstract

PURPOSE:To improve the operation rate of a system by providing a monitor processor which monitors the operation state of a processor and skipping the software loading processing of a stand-by computer for a normally operated management processor. CONSTITUTION:For example, one central processing device 1 is used as the current device, and it is monitored by a monitor processor 5 whether terminal management processors 3 and communication management processors 4 are normal or not. When a stand-by central operation device 2 is raised because of down of the central operation device 1 used as the current device, the processing for management processors which are normal and do not require software loading out of management processors 3 and 4 is skipped. Thus, the time required for rise of the central operation device 2 is shortened by this skip.

Description

DETAILED DESCRIPTION OF THE INVENTION [Object of the Invention] (Industrial Field of Application) The present invention relates to a computer system in which one of a plurality of computers is used as an active computer and the other computer is used as a backup computer.

(Prior art) In a computer system in which one of multiple computers is used as a working computer and the other computer is used as a backup computer, when the computer currently being used goes down, processing is temporarily interrupted and the computer is then used as a backup computer. To automatically start a computer that is on standby for business purposes.

The activated computer then loads software onto each terminal processor and communication management processor via the shared bus, starts up these various processors, and resumes the interrupted processing.

In this way, in such a computer system, when a computer currently in use goes down, a standby computer is activated to continue processing, thereby increasing the operating rate of the system.

(Problems to be Solved by the Invention) However, the conventional system described above has the following problems.

That is, there is a problem in that it takes too long for the computer currently in use to go down until the computer in standby mode resumes processing.

In view of the above-mentioned circumstances, an object of the present invention is to provide a computer system that can increase the operating rate of the system by shortening the processing time for loading software to various processors when starting up a computer kept on standby as a backup. It is said that

[Structure of the invention]

(Means for Solving the Problems) In order to achieve the above object, a computer system according to the present invention includes one or more management processors and a plurality of computers, and uses any one of the computers for current use. , the operating status of each management processor in a computer system in which the remaining computers are put on standby as a backup, and when the computer currently in use goes down, one of the remaining computers is used as a backup. The present invention is characterized in that it includes a monitoring processor that monitors the backup computer and skips the software loading process of the backup computer to a normally operating management processor when starting up the backup computer.

(Operation) In the above configuration, the monitoring processor monitors the operating state of each management processor, and when starting up the backup computer, skips the software loading process of the backup computer for the normally operating management processor.

(Embodiment) FIG. 1 is a block diagram showing an embodiment of a computer system according to the present invention.

The computer system shown in this figure includes two central processing units 1.2 that serve as the core of the system, a plurality of terminal management processors 3 that manage each terminal, and a plurality of communication management processors 4 that manage communication processing. Each of these management processors 3
．． a monitoring processor 5 that checks whether or not the CPU 4 is normal and notifies each central processing unit 1.2 of the check result;
4 and each of the central processing units 1.2.
It is equipped with

Then, one central processing unit, for example, central processing unit 1
While currently using the management processor 3.4, the monitoring processor 5 monitors whether each management processor 3.4 is normal or not. After that, when the central processing unit 1 currently in use goes down and the central processing unit 2 kept on standby as a standby is activated, this central processing unit 2 is activated by each management processor 3.
4 is normal or not, the abnormal management processor is loaded with software and started up, and the normal management processor is skipped the software loading process, thereby allowing the entire system to start up quickly. restart the interrupted process.

Next, the operation of this embodiment will be explained in detail with reference to the flowcharts shown in FIGS. 2 to 4.

First, when one central processing unit 1 is currently used, the other central processing unit 2 is kept on standby as a backup.

The central processing unit 1 currently in use executes the processing of the entire system based on programs stored in the main memory (not shown), and at this time, each terminal management processor 3 and each communication management Each of the processors 4 performs terminal management processing and communication management processing.

In addition, in parallel with this operation, the monitoring broker 5 executes the process shown in the flowchart of FIG. 2 to check whether each terminal management processor 3 and each communication management processor 4 are operating normally.

In this process, the monitoring processor 5 first checks whether or not the preset periodic timing has arrived based on the measurement result of the timer for detecting a certain period, and when this timing arrives, each terminal management processor 3 and each communication management processor 4, the management processor to be processed this time is selected (step 5TI).

Thereafter, the monitoring processor 5 writes specific data to a common address for all management processors 3.4, and issues an execution request to the management processor currently being processed (step 5T2).

As a result, the management processor currently being processed takes in the specific data stored at the address B as shown in FIG. For example, perform an addition operation as shown in the following equation (step STI 1)
.

B"-B+1 However, B゛: calculation result.

B Specification stored in near address B data value.

Thereafter, the management processor currently being processed stores this calculation result B" in address A of its own memory (step 5T12).

When this process is completed, the monitoring processor 5 reads out the data stored at the address A of the management processor currently being processed (step 5T3), and correctly identifies the specific data written to the address B. Please check whether it has been processed or not (Step 5T4)
, if it is not processed correctly, sets an error sign for this management processor (step 5T5).

Furthermore, if the data stored at the address A of the management processor currently being processed has been correctly processed, the monitoring processor 5 skips the error sign setting process.

Thereafter, the monitoring processor 5 sequentially selects the remaining management processors and executes the above-described processing on each of these management processors.

Then, when the check processing for all management processors 3.4 is completed (step 5T6), the monitoring processor 5
sets a timer for constant period detection, and ends the current process (step 5T7).

Further, if the central processing unit 1 currently in use goes down, the central processing unit 2 kept on standby as a backup starts operating and performs the processing shown in FIG. 4.

In this process, the central processing unit 2 first performs processes necessary for startup, such as loading the main program into the main memory (step 5T15).

After this, the central processing unit 2 takes in the error sign for each management processor 3.4 output from the monitoring processor 5, and if there is a management processor for which an error sign is set (step 5T16), the central processing unit 2 receives the error sign for each management processor 3.4. The corresponding software is loaded (step 5T17).

Then, once the software has finished loading for all management processors with error signs set (
Step 5T18), the central processing unit 2 performs processing such as starting up the entire system (Step 5T19),
Resume interrupted processing.

As described above, in this embodiment, when the central processing unit 1 currently in use is down and the central processing unit 2 is put on standby as a standby, the software of each management processor 3.4 is activated. By skipping the loading process for software that does not need to be loaded, that is, for those that have been operating normally, the time required to start up the central processing unit 2 can be reduced accordingly. can.

Since each management processor 3.4 has a small number of elements and a low failure rate, this method reduces the time required to load software for each management processor 3.4 when the currently used central processing unit 1 goes down. can be reduced to almost zero.

〔Effect of the invention〕

As described above, according to the present invention, when starting up a computer kept on standby as a backup, the processing time for loading software to various processors can be shortened, thereby increasing the system operating rate.

[Brief explanation of drawings]

FIG. 1 is a block diagram showing an embodiment of a computer system according to the present invention, FIG. 2 is a flowchart showing an example of the operation of a monitoring processor used in the embodiment, and FIG. 3 is a block diagram showing an example of the operation of a monitoring processor used in the embodiment. FIG. 4 is a flowchart showing an example of the operation of the management processor, and FIG. 4 is a flowchart showing an example of the start-up operation of the central processing unit used as a reserve in the same embodiment. 1.2... Computer (central processing unit) 3... Terminal management processor 4... Communication processing processor 5... Monitoring processor

Claims (1)

[Claims] (1) Equipped with one or more management processors and multiple computers, one of the computers is used as a working computer, the remaining computers are kept on standby as a backup, and the computer currently being used goes down. In a computer system in which one of the remaining computers on standby as a backup computer is used as the active computer, the operating status of each management processor is monitored, and when the backup computer is started up, the management processor that is operating normally is monitored. A computer system comprising: a monitoring processor that skips software loading processing for a backup computer.