JPH0355640A - Collection system for fault analysis information on peripheral controller - Google Patents

Abstract

PURPOSE:To quickly and easily collect the fault analysis information without affecting a system by securing a constitution where the fault analysis information is saved in a saving area of its own device and an asynchronous interruption at occurrence of a designated fault phenomenon. CONSTITUTION:An operator inputs a saving chance setting instruction to a peripheral controller 3 from a system console 6 prior to the start of an operation. When a fault phenomenon designated from a CPU 2 occurs, the controller 3 saves the fault analysis information to a saving area 31 and at the same time produces an asynchronous interruption. When an operating system detects the asynchronous interruption, the system reads the fault analysis information on the area 31 to a software area 12 of a main memory 1 and transfers it to a hardware-only area 11 to restart the process of the controller 3 stored in an error log file 51 via a service processor 4. Thus it is possible to quickly and easily correct the fault information without giving any big influence to the system.

Description

DETAILED DESCRIPTION OF THE INVENTION [Field of Industrial Application] The present invention relates to a peripheral control device failure analysis information collecting method for collecting failure analysis information of a peripheral control device used in an information processing system.

[Conventional technology]

When a failure occurs in a peripheral control device, it is necessary to collect failure analysis information from the peripheral control device and perform failure analysis, but conventionally, a maintenance device is connected to the peripheral control device where the failure has occurred, and this maintenance The peripheral control device instructs the peripheral control device to stop processing when a certain failure event occurs, and collects the contents of internal registers etc. as failure analysis information when the processing of the peripheral control device stops. That's what I do.
[Problem to be solved by the invention] Conventionally, as described above, a maintenance device is connected to a peripheral control device, and when a failure event instructed by the maintenance device occurs in the peripheral control device, failure analysis information is collected. As a result, it takes time to collect failure analysis information and puts a burden on maintenance personnel.Furthermore, during this time, peripheral control devices cannot be incorporated into the system, so there is no impact on the system. There is also the problem that the impact of The purpose of the present invention is to enable failure analysis information to be collected quickly and easily without significantly affecting the system. [Means for Solving the Problems] In order to achieve the above object, the present invention includes: a main storage device having a hardware-only area and a software area; and a function for transferring information in the software area to the hardware-only area. In a system including a central processing unit having a central processing unit, a service processor having a function of reading information from the hardware-dedicated area, and a peripheral control device, a failure event specified by a higher-level device occurs in the peripheral control device. By doing so, a function is provided to save failure analysis information in a save area within the own device and generate an asynchronous interrupt, and when the peripheral control device generates the asynchronous interrupt, the information is saved in the save area of the peripheral control device. Reads the saved failure analysis information into a software area of the main storage device, then instructs the peripheral control device to restart processing, and outputs a log instruction to log the failure analysis information stored in the main storage device. A fault processing means and an error log file in which information is written by the service processor are provided, and the central processing unit reads a fault analysis stored in the software area by outputting a log instruction from the fault processing means. The information is transferred to the hardware dedicated area and a log instruction is output to the service processor, and the service processor stores the information in the hardware dedicated area in response to the log instruction output from the central processing unit. The failure analysis information that has been detected is stored in the error log file. [Operation] When a failure event specified by the host device occurs, the peripheral control device saves the failure analysis information in the save area within its own device and generates an asynchronous interrupt. The failure processing means reads the failure analysis information saved in the evacuation nod area of the peripheral control device into the software area of the main storage device when the peripheral control device generates an asynchronous interrupt, and then instructs the peripheral control device to resume processing. At the same time, it outputs a log instruction to log the failure analysis information stored in the main storage. When the log instruction is output from the fault processing means, the central processing unit transfers the fault analysis information stored in the software area to the hardware dedicated area and outputs the log instruction to the service processor. The service processor stores failure analysis information stored in the hardware-dedicated area in the error log file in response to a log instruction output from the central processing unit. [Example] Next, an example of the present invention will be described in detail with reference to the drawings. FIG. 1 is a block diagram of an embodiment of the present invention, showing a main memory 1 including a hardware-only area l1 that can only be accessed by hardware and a software area 12 that can also be accessed by software; Software area 12 of memory 1
The central processing unit (CPU) 2, which has the function of transferring the information of A peripheral control unit (PCU) 3 that saves in a provided save area 31 and generates an asynchronous interrupt, a service processor (SVP) 4 that has a function of reading the hardware dedicated area 1 of the main memory l, and an error log. It consists of a magnetic disk device 5 in which files 51 are installed and a system console 6. 2 to 4' are flowcharts showing the processing operation of FIG. 1 when a failure event instructed by the evacuation trigger setting instruction from the higher-level device occurs in the peripheral control device 3. The figure shows an example of operating system (OS) processing.
3 shows an example of processing by the central processing unit 2, and FIG. 4 shows an example of processing by the service processor 4. Next, the operation of this embodiment will be explained with reference to each figure. Prior to the start of system operation, the operator inputs an evacuation trigger setting instruction for the peripheral control device 3 from the system console 6, and the central processing unit 2 adds this evacuation trigger setting instruction to the peripheral control device 3. When the failure event specified by the evacuation trigger setting instruction occurs, the peripheral m control device 3 saves the failure analysis information in the evacuation area 31 within its own device, generates an asynchronous interrupt, and operates on the central processing unit 2. When the operating system detects an asynchronous interrupt generated by the peripheral system II device 3, it starts the process shown in the flowchart of FIG.

First, in step 200, the operating system determines which peripheral system generated the asynchronous interrupt. 1! A read instruction is issued to read out the failure analysis information stored in the save area 31 of the storage area 3, and thereby the failure analysis information is read out to the software area 12. Thereafter, in step 201, the operating system issues a CPU command instructing to store the failure analysis information read into the software area 12 in the error log file 51. When the CPU command is issued, the central processing unit 2 executes the third CPU command.
As shown in the flowchart of the figure, first, in step 300, the information instructed by the CPU command, that is, the failure analysis information stored in the software area 12, is transferred to the hardware dedicated area 11, and then in the next step 301. Hardware dedicated area 1 for service processor 4
1 to log the failure analysis information stored in the error log file 51, and then terminates the processing for the CPU instruction. In addition, service processor 4
When a log instruction is applied from the central processing unit 2, it performs the processing shown in the flowchart of FIG. (Step 4
00). When the operating system issues a CPU instruction in step 201 of FIG.
After resetting the peripheral AM device 3 and restarting the processing of the peripheral control device 3, the process returns to normal processing.

〔Effect of the invention〕

As explained above, the present invention provides central processing'! A trigger for saving failure analysis information is set from a host device such as a PCI to a peripheral control device, and when a specified failure event occurs, the peripheral control device releases the failure in the evacuation area provided within its own device. It saves the analysis information and generates an asynchronous interrupt to the host device, and when the asynchronous interrupt occurs, the failure analysis information saved in the save area is logged to the error log file and the processing of the peripheral control device is restarted. This has the effect of allowing failure analysis information to be collected easily and quickly without significantly affecting the system.

[Brief explanation of drawings]

Fig. 1 is a block diagram of an embodiment of the present invention, Fig. 2 is a flowchart showing an example of processing by the operating system, Fig. 3 is a flowchart showing an example of processing by the central processing unit, and Fig. 4 is an example of processing by the service processor. This is a flowchart showing the process.

Claims (1)

[Scope of Claims] A main storage device having a hardware-only area and a software area; a central processing unit having a function of transferring information in the software area to the hardware-only area; In a system that includes a service processor with a reading function and a peripheral control device, when a failure event specified by a higher-level device occurs in the peripheral control device, failure analysis information is saved in a save area within the device itself. The peripheral control device generates the asynchronous interrupt, thereby saving the failure analysis information saved in the save area of the peripheral control device to the software in the main storage device. failure processing means for outputting a logging instruction for reading failure analysis information stored in the main storage device and logging the failure analysis information stored in the main storage device, and then instructing the peripheral control device to restart processing; and an error log file, and upon output of a log instruction from the failure processing means, the central processing unit transfers the failure analysis information stored in the software area to the hardware dedicated area, and also transfers the failure analysis information stored in the software area to the hardware dedicated area. The service processor outputs a log instruction to the central processing unit, and upon output of the log instruction from the central processing unit, the service processor instructs the service processor to store the failure analysis information stored in the hardware dedicated area in the error log file. Features a fault analysis information collection method for peripheral control devices.