JPH0287235A - Information processor - Google Patents

Abstract

PURPOSE:To early exchange if to an alternative equipment concerning the job to have the alternative equipment without executing the many times of retry by considering the contents of the job to be just executed at the time of a trouble and executing the number of the retry to be determined in each job in advance. CONSTITUTION:When an error is generated, a magnetic disk device 3 informs the contents of the error of a processor 1 and likewise informs the contents of the error of a retry number deciding circuit 7 as well. Then, the processor 1 informs the contents of the job, which is just executed, of the retry number deciding circuit 7 of a retry control part 6. The retry number deciding circuit 7 determines the number of the retry according to the informed contents of the error and job and a deciding condition, which is registered in advance, and sends the data of the retry number to a retry number instructing circuit 8. The retry number instructing circuit 8 selects a retry circuit 9 or a retry circuit 10 according to the retry number and activates the selected circuit. Thus, the retry can be executed by the optimum time according to the job.

Description

DETAILED DESCRIPTION OF THE INVENTION (Industrial Application Field) The present invention relates to an information processing apparatus that can attempt to overcome the error by re-executing the information processing when an error occurs in the information processing.

(Prior Art) In conventional information processing devices of this type, the number of retries in the event of a failure is a fixed value determined at the time of device design. When a failure occurs, the system retries a predetermined number of times, and if it succeeds, the process continues; if it fails, the process is interrupted and restarted.

(Problem to be Solved by the Invention) The conventional retry method in the event of a failure (occurrence of an error) in the information processing device described above does not take into account the content of the work being executed at the time of failure, so Even though it would be more efficient to immediately switch to an alternative device when a failure occurs for operations that have alternative equipment, retries were mechanically executed the number of times determined at the time of equipment design.

As described above, in the conventional processing method, it is not possible to switch to an alternative device unless a predetermined number of retries are performed, and therefore, depending on the job, the time required to switch is unnecessarily long. As described above, conventional information processing devices had problems to be solved.6 The purpose of the present invention is to solve these problems and retry an optimal number of times depending on the business when an error occurs in information processing. The aim is to provide information processing equipment.

(Means for Solving the Problems) In order to solve the above-mentioned problems, the information processing device provided by the present invention, when an error occurs in information processing, causes the part that caused the error to execute the same process again. the first and second retry circuits, and a means for determining the number of times to re-execute the process according to the work being performed in the information processing; The number of times of processing is stored in advance, and the processing number determining means stores the number of times of re-execution processing determined in advance according to the task and the content of the error as a table, and the number of times of processing is re-executed when the error occurs. the first or second retry circuit that receives information about the work being performed and the content of the error that has occurred, refers to the table to determine the number of re-execution processes, and stores the determined number of re-execution processes; It is characterized by starting.

(Example) Next, the present invention will be explained with reference to the drawings.

FIG. 1 is a block diagram showing a magnetic disk processing device which is an embodiment of the present invention.6 This figure shows a magnetic disk processing device 2 and a processing wave fi (CPU etc.) 1 connected thereto.
and a magnetic disk device 3. The magnetic disk processing device 2 includes a processing device adapter 4, a magnetic disk main control section 5, and a retry control section 6.
It consists of The retry control section 6 includes a retry count determination circuit 7, a retry count instruction circuit 8, a first retry circuit 9, and a second retry circuit 10.

Next, the operation of the retry control section 6 will be explained.

First, when constructing the system, the number of retries is individually registered in the retry times FIs 89 and 10, depending on system environment conditions such as business content, error content, and configuration of alternative equipment. Further, at this time, the business content and the judgment conditions are also registered in the retry count judgment circuit 7. Specifically, the judgment conditions are determined as appropriate depending on the business content and error content.・It is the number of lies.

Normally, data reading/writing operations performed between the processing device 1 and the magnetic disk device 3 are performed by the processing device 1 accessing the magnetic disk device 3 via the magnetic disk processing device [2]. Assume that a failure occurs in the magnetic disk device 3 during read/write operations and an error occurs. When this error occurs, the magnetic disk drive 3 notifies the processing device 1 of the error details via the magnetic disk main control unit 5 and the processing device adapter 4, and also notifies the retry count determination circuit 7 of the error details. Notice. When the processing device 1 receives the error details, it notifies the retry count determination circuit 7 of the task details being executed.

The retry count determination circuit 7 determines the number of retries determined by the job content and error content based on the notified error content and business content and pre-registered judgment conditions, and sends data on the number of retries to the retry count instruction circuit 8. send. The retry count instruction circuit 8 selects either the retry circuit 9 or the retry count R10 depending on the retry count, and activates the selected retry circuit.

(Effects of the Invention) As explained above, the information processing apparatus of the present invention takes into account the content of the work being executed at the time of a failure and performs a predetermined number of retries for each work, thereby providing alternative equipment. For tasks that are currently in use, the number of retries will be set to the minimum value, and the system will be switched to an alternative device at an early stage without having to perform multiple retries. On the other hand, in the information processing apparatus of the present invention, the number of retries is set to the maximum value for tasks that no alternative device has, so that the retry process can be made as successful as possible.

In this way, by changing the number of retries in the event of a failure depending on the business content, system operation can be made more efficient and the operating rate of the entire system can be increased.

[Brief explanation of the drawing]

FIG. 1 is a block diagram showing a magnetic disk processing apparatus which is an embodiment of the present invention. 1... Processing device, 2... Magnetic disk processing device, 3
...Magnetic disk device, 4...Processing device adapter,
5...Magnetic disk main control unit, 6...-Retry system #
Part 11, 7... Retry count determination circuit, 8... Retry count instruction circuit, 9... First retry circuit, 10
...Second retry circuit.

Claims (1)

[Scope of Claims] First and second retry circuits that cause the part that caused the error to re-execute the same process when an error occurs in information processing; means for determining the number of times the process is to be re-executed, the number of times the process is to be re-executed is stored in advance in the first and second retry circuits; A predetermined number of re-executions is stored as a table according to the content of the error, and the table is referred to upon receiving information about the task being executed when the error occurred and the content of the error that occurred. An information processing apparatus characterized in that the number of times of re-execution processing is determined and the first or second retry circuit in which the determined number of times of re-execution processing is stored is activated.