TWI602054B - Method of providing error status data for computer device - Google Patents

Description

Error status data providing method for computer device

The present invention relates to error status information of a computer device, and more particularly to a method for providing error status data for a computer device.

A computer device currently used as a server typically includes a baseboard management controller system that is used to provide error status information for the computer device to assist the administrator in managing the computer device.

When the substrate management control system receives an error notification from the central processing unit, such as a fatal error (CATERR) notification, the substrate management control system reads the internal temporary storage of a central processing unit of the computer device. The error status information. However, in practice, since the computer device is restarted in the event of an abnormality such as a fatal error (CATERR), the error state data retained by the central processing unit and corresponding to the abnormal condition is cleared. It is worth noting that the operation of the baseboard management control system will not be affected when the computer device is restarted. Therefore, if the central processing unit receives the error notification from the substrate management control system after the computer device is restarted, the internal processing unit of the central processing unit read and stored by the substrate management control system The error status data stored in the machine check structure error status (Machine Check Architecture error status) data does not correspond to the error status data when the abnormal condition occurs, but corresponds to the error status of the state after the computer device is restarted. Therefore, the administrator of the computer device cannot correctly analyze the cause of the abnormality of the computer device based on the error status data provided by the baseboard management control system.

Accordingly, it is an object of the present invention to provide an error status data providing method.

Therefore, the error state data providing method of the present invention is implemented by a substrate management control system included in a computer device, the computer device further comprising a central processing unit electrically connected to the substrate management control system, and the error state data providing method The method comprises the steps of: (A) reading and storing the error status data stored in the central processing unit; (B) determining whether the error status data contains at least one of a plurality of specific errors; (C) determining the error status. If the data does not contain the at least one specific error, proceed to step (A); and (D) When it is determined that the error status data contains the at least one specific error, after receiving a data request from a user terminal, transmitting the error status data previously stored in step (A) to the user terminal.

The effect of the present invention is that the error management data when the computer device generates the at least one specific error is read and stored by the substrate management control system, and in the case that the error state data contains the at least one specific error, After receiving the data request from the user end, transmitting the error status data of the at least one specific error to the user terminal to the user end, so as to prevent the error status data when the computer device generates the at least one specific error is The substrate management control system is cleared before being stored, so that the administrator can analyze the cause of the error of the computer device according to the error data received by the user terminal.

1‧‧‧Computer equipment

11‧‧‧Base management control system

111‧‧‧Non-volatile memory module

112‧‧‧Communication module

113‧‧‧Processing module

12‧‧‧Central Processing Unit

2‧‧‧Use side

100‧‧‧Communication network

30~34‧‧‧Steps

Other features and advantages of the present invention will be apparent from the embodiments of the present invention, which is illustrated in the accompanying drawings. FIG. 1 is a block diagram illustrating a computer device including an embodiment of the method for providing error status data of the present invention. A substrate management control system is electrically connected to a central processing unit included in the computer device, and is connected to a user terminal via a communication network; FIG. 2 is a flowchart illustrating an embodiment of the error state data providing method of the present invention; Figure 3 is a flow chart showing another embodiment of the error status data providing method of the present invention.

Referring to FIG. 1, an embodiment of a method for providing error status data according to the present invention is implemented by a substrate management control system 11 included in a computer device 1. The baseboard management control system 11 is connected to a user terminal 2 via a communication network 100. The computer device 1 further includes a central processing unit 12 electrically connected to the substrate management control system 11. In the embodiment, the computer device 1 is, for example, a server, and the substrate management control system 11 includes, for example, a non-volatile The memory module 111, a communication module 112 connected to the communication network 100, and a processing module 113 electrically connected to the non-volatile memory module 111 and the communication module 112, and the central processing unit 12 is, for example, an Intel The processor produced by the company.

Referring to Figures 1 and 2, an embodiment of the error status data providing method of the present invention comprises the following steps.

In step 31, the processing module 113 of the substrate management control system 11 reads and stores the internal register of the central processing unit 12 via a platform environmental control interface (PECI) (not shown). The error status data stored in the file, wherein the error status data is associated with the computer device 1. In this embodiment, the error status data includes a machine check architecture. Error status data. In addition, the processing module 113 of the substrate management control system 11 stores the error status data that has been previously stored in the non-volatile memory module 111 to the currently read error status data to store the error. Status data.

In step 32, the processing module 113 of the substrate management control system 11 determines whether the error status data stored therein (that is, the error status data stored in the non-volatile memory module 111) contains a plurality of specific errors. At least one of them. These specific errors are consistent with a fatal error (CATERR), an uncorrectable PCI error, a fatal peripheral error (Fatal PCI error), a system management interrupt timeout (SMI timeout), together with At least one of a bit error (PERR), and a system error (SERR) error type. When it is determined that the error status data contains the at least one specific error, the flow proceeds to step 33. Otherwise, the flow proceeds to step 34.

In step 33, after the processing module 113 of the substrate management control system 11 receives a data request from the user terminal 2 via the communication module 112, the processing module 113 of the substrate management control system 11 communicates via the communication module 112. The module 112 transmits the error status data previously stored in step 31 to the user terminal 2. In other embodiments of the present invention, the error status data providing method further includes a step 30 (see FIG. 3) before the step 31, and the processing module 113 of the baseboard management control system 11 determines that the computer device 1 is in a current time. Whether it was restarted during the previous reference time period. When judged When the computer device 1 is restarted during the reference time period before the current time, the flow proceeds to step 33. Otherwise, the flow proceeds to step 31.

In step 34, after the processing module 113 of the substrate management control system 11 counts a preset time period, the process proceeds to step 31.

It should be particularly noted that, in actual use, the existing substrate management control system 11 stores a system event log (System Event Log, SEL for short) related to the computer device 1 when detecting that the computer device 1 is not operating normally. ) to assist the manager in understanding the cause of the abnormal operation of the computer device 1. However, in addition to referencing the system event log, the administrator must refer to information such as the machine check architecture error status data to understand the reason why the computer device 1 is abnormal. When the error status data contains the at least one specific error, the computer device 1 will not operate normally, and thus the system event log will contain some abnormal information, when the administrator learns from the system event log that the computer device 1 is brought When there is some abnormal information and does not operate normally, the administrator uses the user terminal 2 to issue the error status data to the substrate management control system 11 for the non-volatile memory module 111 stored in the substrate management control system 11. According to the data request, the substrate management control system 11 requests to return the error status data stored by the non-volatile memory module 111 inside the substrate management control system 11 according to the data request, and the manager obtains the The error status data stored by the substrate management control system 11 when the at least one specific error occurs.

When the administrator sends the data request by using the terminal 2 to obtain the error state data stored by the substrate management control system 11 when the at least one specific error occurs, the substrate management control system 11 continues to perform the steps. 31~Step 32 (see FIG. 2) or Step 30~Step 32 (see FIG. 3), in other words, the substrate management control system 11 receives the non-volatile memory module 111 stored in the substrate management control system 11 Before the data of the error status data is requested, the baseboard management control system 11 does not periodically read any error status data to the internal register of the central processing unit 12, nor does it internal to the central processing unit 12. The error state data stored in the temporary storage device is stored in the non-volatile memory module 111 inside the substrate management control system 11 so as not to be overwritten or destroyed during storage. The at least one specific error is stored in the substrate management. The error status data of the non-volatile memory module 111 inside the control system 11.

In the case that the error state data does not contain the at least one specific error, the substrate management control system 11 counts the preset time period, for example, after 50 ms, the steps 31 to 32 (see FIG. 2) or step 30 are continued. ~ Step 32 (see FIG. 3), since the computer device 1 restarts due to the occurrence of the at least one specific error, it takes a time period of more than 50 ms, so that the at least one specific error is cleared due to the restart of the computer device 1. The time period required for the error status data also exceeds 50 ms, so the baseboard management control system 11 automatically reads the error status data stored in the internal register of the central processing unit 12 periodically every 50 ms. With this, It is possible to avoid that the error status data at the time when the at least one specific error occurs is cleared before being stored by the baseboard management control system 11. Furthermore, since the substrate management control system 11 transmits the error status data stored by the substrate management control system 11 to the user terminal 2 when the at least one specific error occurs, the step 31 to the step are continued. 32 (see FIG. 2) or step 30 to step 32 (see FIG. 3) "that is, the error status data stored by the substrate management control system 11 is transmitted to the user terminal 2 when the at least one specific error occurs. Before, the processing module 113 of the substrate management control system 11 does not perform steps 31 to 32 (see FIG. 2) or steps 30 to 32 (see FIG. 3), thereby avoiding at least one specific error. The error state data of the non-volatile memory module 111 stored in the substrate management control system 11 at the time of occurrence is overwritten or destroyed by the error state data read by the substrate management control system 11. In other embodiments of the present invention, the substrate management control system 11 obtains the error status data by periodically reading the error status data stored in the temporary register of the central processing unit 12 to obtain the error status data. When the substrate management control system 11 receives an error notification from the central processing unit 12, such as a fatal error (CATERR) notification, the baseboard management control system 11 also reads the internal register of the central processing unit 12. The error status data stored in the file is obtained in order to obtain the error status data.

In summary, the error status data providing method of the present invention, the substrate management control system 11 periodically reads and stores the error status data of the temporary register in the central processing unit 12, and the error status data is Containing at least one specific In the case of an error, the baseboard management control system 11 temporarily stops the action of periodically reading and storing any error status data to the temporary register inside the central processing unit 12, after receiving the data request from the use terminal 2 Transmitting the error status data to the user terminal 2 when the at least one specific error occurs to ensure that the manager can obtain the error status data when the at least one specific error occurs, so that the purpose of the present invention can be achieved. .

However, the above is only the embodiment of the present invention, and the scope of the invention is not limited thereto, and all the equivalent equivalent changes and modifications according to the scope of the patent application and the patent specification of the present invention are still The scope of the invention is covered.

31~34‧‧‧Steps

Claims (7)

An error state data providing method is implemented by a substrate management control system included in a computer device, the computer device further comprising a central processing unit electrically connected to the substrate management control system, and the error state data providing method comprises the following steps : (A) reading and storing the error status data stored by the central processing unit; (B) determining whether the error status data contains at least one of a plurality of specific errors; (C) determining that the error status data does not contain When the at least one specific error is continued, the step (A) is continued; and (D) when it is determined that the error status data contains the at least one specific error, after receiving a data request from a user end, transmitting the previous step ( A) storing the error status data to the use end, wherein the substrate management control system does not repeat the step before transmitting the error status data previously stored in step (A) to the use end ( A) to step (B). The error status data providing method according to claim 1, wherein in the step (C), when it is determined that the error status data does not include the at least one specific error, the substrate management control system counts a preset time After the period, repeat steps (A) to (B) once. The method of providing an error status data according to claim 1, wherein the baseboard management control system includes a non-volatile memory module for storing the error status data, wherein in step (A), the baseboard management control system previously The previous error status data stored in the non-volatile memory module is updated to the error status data read in step (A) to store the error status data. The error status data providing method according to claim 1, further comprising a step (E) after the step (D), repeating the steps (A) to (B). The error status data providing method according to claim 1, wherein: in the step (A), the error status data includes a Machine Check Architecture error status data; and in the step (B), the Specific errors include a fatal error (CATERR), an uncorrectable PCI error, a fatal peripheral error (Fatal PCI error), a system management interrupt timeout (SMI timeout), a homobit At least one of the error (PERR), and a system error (SERR) error type. The error status data providing method according to claim 1, wherein in the step (A), the substrate management control system reads the error status data of the central processing unit via a platform environment control interface. The error status data providing method according to claim 1, before the step (A), further comprising the following steps: (F) the substrate management control system determines whether the computer device has been in a reference time period before the current time Restarting; (G) receiving another resource from the user terminal when it is determined that the computer device was restarted during the reference time period before the current time After the request is made, the previous error status data previously stored in step (A) is transmitted to the use end; (H) when it is determined that the computer device has not been restarted during the reference time period before the current time, the step ( A) is executed.