CN104021054A - Server fault visual detecting and processing method and system and programmable chip - Google Patents

Abstract

The invention discloses a server fault visual detecting and processing method and system and a programmable chip. The method includes the steps that the programmable chip receives fault information sent by a BMC in a server; the programmable chip sends the fault information to an OLED displayer to be displayed, the fault level is judged according to the fault information, and a corresponding processing strategy is fed back to the BMC according to the fault level so as to drive the BMC to conduct corresponding processing on the server according to the processing strategy. According to the server fault visual detecting and processing method and system and the programmable chip, the occupancy rate of the BMS can be reduced, the purpose of rapid fault positioning can further be achieved, and a multi-node system and a redundant system can be well supported. In addition, the programmable chip can judge the level of occurred faults and can feed back corresponding processing strategies to drive the BMC to conduct corresponding processing on the faults.

Description

Server fault visual detection and processing method, system and programmable chip

technical field

The invention relates to the field of computer application technology, in particular to a server fault visual detection and processing method, system and programmable chip.

Background technique

As an important feature of the server, high reliability makes fault detection an important function of the server. At present, server fault detection mainly uses the combination of LED light and fault manual. Specifically, the user first judges the status of the LED light, and then consults the fault manual to locate the specific fault. The disadvantage of this method is that the fault manual generally contains a lot of information. It takes a lot of time to search for users, and the purpose of quickly locating faults cannot be achieved.

Secondly, the traditional fault detection method is to directly control the LED driver through the BMC. As shown in Figure 1, the Baseboard Management Controller (BMC for short) directly controls the LED driver through the SMB (abbreviation of SMBUS), so that the LED matrix can be controlled at any time. Displays the running status of the server. At present, in order to better realize human-computer interaction, the requirements for richness and immediacy of displayed content for fault detection are also getting higher and higher. However, this will take up a lot of resources of the BMC with limited computing power, and may even cause the display to be out of time. Moreover, the traditional fault detection method is only suitable for single-node non-redundant systems, that is, the BMC intelligent control of each node is relative to the LED matrix, and this architecture is not suitable for multi-node systems and redundant systems.

Contents of the invention

The technical problem to be solved by the present invention is to provide a server fault visual detection and processing method, system and programmable chip, which can not only reduce the occupancy rate of BMS, but also achieve the purpose of quickly locating faults.

In order to solve the above technical problems, the present invention provides a method for visual detection and processing of server faults, including:

The programmable chip receives the fault information sent by the baseboard management controller BMC in the server;

The programmable chip sends the fault information to the OLED display for display, and judges the fault level according to the fault information, and feeds back a corresponding processing strategy to the BMC according to the fault level, so as to drive the BMC according to the fault level. The processing policy performs corresponding processing on the server.

Further, it also includes:

The programmable chip receives the working status information of the server sent by the BMC;

The programmable chip sends the working status information to the OLED display for display.

Further, the programmable chip uses the intelligent platform management interface IPMI protocol to communicate with the BMC; the programmable chip receives the fault information sent by the BMC through the I2C bus, and receives the fault information through the UART interface of the universal asynchronous transceiver. The working status information sent by the BMC; the programmable chip feeds back the corresponding processing strategy to the BMC through the UART interface;

Wherein, the programmable chip is a programmable system on chip PSOC series chip.

Further, the fault information includes: positioning information and error reporting information;

The method also includes: the BMC communicates with the FPGA to locate, and sends the fault information to the programmable chip in a data packet format; the positioning information is the hardware information of the fault, and the error message is the fault information. Error message for faulty hardware.

Further, the method further includes: setting a corresponding threshold and a processing strategy for each fault level,

Said judging the fault level according to the fault information, feeding back a corresponding processing strategy to the BMC according to the fault level, so as to drive the BMC to perform corresponding processing on the server according to the processing strategy, including:

If the error information reaches the threshold corresponding to a certain fault level, then it is judged that the fault occurred is the fault level, and the corresponding processing strategy is queried, and the processing strategy is sent to the BMC, wherein the processing strategy also includes Including: the positioning information and the fault level.

Further, the BMC includes one or more.

In order to solve the above technical problems, the present invention also provides a programmable chip for visual detection and processing of server faults, including:

The receiving module is used to receive the fault information sent by the BMC;

A display control module, configured to send the fault information to an OLED display for display;

The fault control module is configured to judge a fault level according to the fault information, and feed back a corresponding processing policy to the BMC according to the fault level, so as to drive the BMC to perform corresponding processing on the server according to the processing policy.

Further, the programmable chip communicates with the BMC using the IPMI protocol;

The receiving module is also used to receive the fault information through the I2C bus;

The display control module is further configured to send the fault information to the OLED display through a serial peripheral interface SPI;

The fault control module is further configured to feed back the corresponding processing strategy to the BMC through a UART interface.

Further, the fault information includes: location information and error reporting information; the location information is the location information of the faulty hardware, and the error reporting information is the error information of the sending faulty hardware.

The fault control module is also used to set corresponding thresholds and processing strategies for each fault level;

The fault control module is configured to judge a fault level according to the fault information, and feed back a corresponding processing strategy to the BMC according to the fault level, so as to drive the BMC to perform corresponding processing on the server according to the processing strategy, including:

If the error information reaches the threshold corresponding to a certain fault level, then it is judged that the fault occurred is the fault level, and the corresponding processing strategy is queried, and the processing strategy is sent to the BMC, wherein the processing strategy also includes Including: the positioning information and the fault level.

In order to solve the above technical problems, the present invention also provides a visual detection and processing system for server faults, including: one or more BMCs, the programmable chip as described above, and an OLED display.

Compared with the prior art, at least one embodiment of the present invention provides a server failure visual detection and processing method, system and programmable chip, adding an OLED (organic light-emitting diode) display to the server, and connecting the OLED display and the BMC between the OLED display and the BMC. In addition, the user can quickly locate the fault point through the fault information displayed on the OLED; in another embodiment, the PSOC (Programmable System On Chip, programmable system on chip) series chip is used, and the input can be connected to a or multiple BMCs, output to an OLED display to realize the mode that the BMC controls the PSOC to drive the OLED display, which can not only reduce the occupancy rate of the BMS, but also allow customers to know more about the real-time operation of the server, and multi-node systems and redundant systems are well supported. In another embodiment, the programmable chip can determine the level of the fault, and feed back a corresponding processing strategy to drive the BMC to handle the fault accordingly.

Description of drawings

FIG. 1 is a schematic diagram of fault detection in the prior art;

Fig. 2 is a structural diagram of a server failure visual detection and processing device in an embodiment;

Fig. 3 is the structural diagram of programmable chip in the embodiment;

FIG. 4 is a flow chart of a server fault visual detection and processing method in an embodiment.

Detailed ways

In order to make the purpose, technical solution and advantages of the present invention more clear, the embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings. It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined arbitrarily with each other.

Example:

As shown in Figure 2, the present embodiment provides a visual detection and processing system for server faults, including: BMC, programmable chip and OLED display, wherein:

The BMC and the programmable chip are connected to each other, and communicate with the programmable chip through the Intelligent Platform Management Interface (Intelligent Platform Management Interface, referred to as IPMI); Status information, sending fault information to the programmable chip through the I2C bus; the programmable chip feeds back the fault handling strategy to the BMC through the UART interface;

The BMC obtains the working status information or fault information of the server by communicating with the FPGA;

The programmable chip and the OLED display are connected to each other, and the fault information is sent to the OLED display through a serial peripheral interface (Serial Peripheral Interface, SPI for short).

Wherein, the programmable chip can adopt PSOC series chips, such as Cypress PSOC4 series chips produced by Cypress Corporation.

Preferably, the system includes one or more BMCs, and one programmable chip can drive OLED displays to display fault information by connecting multiple BMCs, so as to support multi-node systems and redundant systems. For example, now an eight-way server (eight CPUs) can have two working modes, eight-way working mode and dual four-way working mode. In the eight-way working mode, one BMC works. Two BMCs work, and the number of BMCs depends on the specific working mode.

As shown in Figure 3, this embodiment provides a programmable chip for visual detection and processing of server faults, including:

The receiving module is used to receive the fault information sent by the BMC;

A display control module, configured to send the fault information to an OLED display for display;

The fault control module is configured to judge a fault level according to the fault information, and feed back a corresponding processing policy to the BMC according to the fault level, so as to drive the BMC to perform corresponding processing on the server according to the processing policy.

Wherein, the BMC includes one or more, and the display control module sends the fault information of one or more BMCs to the OLED display for display; the fault control module feeds back the processing strategy corresponding to the BMC to the server to which the BMC belongs.

Wherein, the programmable chip communicates with the BMC using the IPMI protocol;

The receiving module is also used to receive the fault information through the I2C bus;

The display control module is further configured to send the fault information to the OLED display through a serial peripheral interface SPI;

The fault control module is further configured to feed back the corresponding processing strategy to the BMC through a UART interface.

Wherein, the fault information includes: location information and error reporting information; the location information is the location information of the faulty hardware, and the error reporting information is the error information of the sending faulty hardware. For example, how high is the temperature on memory board No. 1, where board No. 1 is the positioning information, and the temperature is the error reporting information. BMC locates by communicating with Field Programmable Gate Array (FPGA), and sends the fault information to the programmable chip in data packet format, for example, the fault information format can be CPU0error temperature65°;

The fault control module is also used to set corresponding thresholds and processing strategies for each fault level;

The fault control module is configured to judge a fault level according to the fault information, and feed back a corresponding processing strategy to the BMC according to the fault level, so as to drive the BMC to perform corresponding processing on the server according to the processing strategy, including:

If the error information reaches the threshold corresponding to a certain fault level, then it is judged that the fault occurred is the fault level, and the corresponding processing strategy is queried, and the processing strategy is sent to the BMC, wherein the processing strategy also includes Including: the positioning information and the fault level.

For example, set three fault levels, namely: warning fault, serious warning and unrecoverable fault. Taking the CPU as an example, the thresholds corresponding to the three fault levels are set to 70°, 80°, and 90° respectively. That is to say, error In the information, if the CPU temperature reaches 70°C, it is an alarm fault, and if it reaches 90°C, it is an unrecoverable fault. The processing strategy corresponding to warnings and serious warnings can be to check whether the server fan is in place and start it, while the processing strategy corresponding to serious warnings can be to directly shut down. After receiving the processing policy of the programmable chip, the BMC can process the server accordingly according to the processing policy.

In addition, the fault level can also include general warnings, which are first sent to the OLED display, and the OLED will display the user's operable options for this fault. The processing strategy for the common alarm fault is sent to the BMC.

The programmable chip is a programmable system on chip PSOC series chip.

As shown in Figure 4, this embodiment provides a visual detection and processing method for a server failure, including the following steps:

S101: The programmable chip receives the fault information sent by the BMC;

The BMC needs to monitor whether the server is faulty in real time, and when it detects that the server is faulty, it will send the fault information to the programmable chip;

The fault information includes: positioning information and error reporting information; for example, how high is the temperature on the No. 1 memory board, where No. 1 board is the positioning information, and the temperature is the error reporting information. Described location information is the hardware information that breaks down, such as: the hardware that breaks down is CPU, hard disk Disk, fan and memory board MRB, power supply PSU etc., and described error message is the error message of described hardware that breaks down, as Error information of CPU voltage and temperature, Disk error information, fan error information, etc. The BMC communicates with the FPGA for positioning, and then sends the fault information to the PSoC in a data packet format. For example, the fault information format can be CPU0 error temperature65°.

Preferably, the BMC connected with the programmable chip includes one or more, and one programmable chip is connected with multiple BMCs to drive the OLED display to display fault information, which can realize support for multi-node system and redundant system.

S102: The programmable chip sends the fault information to the OLED display for display, and judges the fault level according to the fault information, and feeds back a corresponding processing strategy to the BMC according to the fault level, so as to drive the BMC according to the fault level. The processing policy handles the server accordingly.

Wherein, the method further includes: setting a corresponding threshold and a processing strategy for each fault level,

Said judging the fault level according to the fault information, feeding back a corresponding processing strategy to the BMC according to the fault level, so as to drive the BMC to perform corresponding processing on the server according to the processing strategy, including:

If the error information reaches the threshold corresponding to a certain fault level, then it is judged that the fault occurred is the fault level, and the corresponding processing strategy is queried, and the processing strategy is sent to the BMC, wherein the processing strategy also includes Including: the positioning information and the fault level.

For example, set three fault levels, namely: warning fault, serious warning and unrecoverable fault. Taking the CPU as an example, the thresholds corresponding to the three fault levels are set to 70°, 80°, and 90° respectively. That is to say, error In the information, if the CPU temperature reaches 70°C, it is an alarm fault, and if it reaches 90°C, it is an unrecoverable fault. The processing strategy corresponding to warnings and serious warnings can be to check whether the server fan is in place and start it, while the processing strategy corresponding to serious warnings can be to directly shut down. After receiving the processing policy of the programmable chip, the BMC can process the server accordingly according to the processing policy.

In addition, the fault level can also include general warnings, which are first sent to the OLED display, and the OLED will display the user's operable options for this fault. The processing strategy for the common alarm fault is sent to the BMC.

Preferably, the BMC includes one or more, and the programmable chip receives the fault information sent by each BMC, and sends the fault information of one or more BMCs to the OLED display for display; the processing strategy corresponding to the BMC is fed back to The server to which the BMC belongs.

In addition, when the BMC does not monitor the failure of the server, that is, when the server is in a normal working state, the method further includes:

The BMC sends the working status information of the server to the programmable chip; the programmable chip sends the working status information to the OLED display for display.

The working status information displayed on the OLED display includes: server hardware configuration information (such as: operating system version, CPU model, memory and hard disk size), network configuration parameters (such as: ip address, gateway, subnet mask), BMC firmware version information , OLED firmware version information, user-defined character string display, CPU hard disk memory utilization information under server running status, customer service phone number, etc.

Wherein, in the present embodiment, preferably adopt the PSOC chip that Cypress Company produces; PSOC chip refers to PSOC system single-chip microcomputer, has integrated configurable around a proprietary MCU (Microprogrammed ControlUnit, microprocessing control unit) core The analog and digital peripheral device array PSOC block uses the programmable interconnection array inside the chip to effectively configure the analog and digital block resources on the chip to achieve the purpose of a programmable system on chip. A PSOC is added between the BMC and the OLED, and the code required to control the OLED display is burned in the PSOC.

The programmable chip adopts the intelligent platform management interface IPMI protocol to communicate with the BMC; the programmable chip receives the fault information sent by the BMC through the I2C bus, and the I2C bus is a two-wire serial bus developed by PHILIPS company. row bus, the programmable chip receives the working state information sent by the BMC through the UART interface; the programmable chip feeds back the corresponding processing strategy to the BMC through the UART interface.

In an application example, take the Cypress PSOC4 chip as an example for the programmable chip. The Cypress PSOC4 chip communicates with the BMC through the UART interface to obtain the normal working status and performance information of the server and feed back the corresponding fault handling strategy to the BMC; communicate with the BMC through the I2C bus Communication for failure information in case of server failure.

PSOC4 transmits the parsed data to the buffer of the OLED display through SPI, and the OLED display makes a corresponding display through the data in the buffer.

When the server is not faulty, the PSOC4 chip communicates with the BMC through the IPMI protocol, and sends the obtained relevant server hardware configuration information, network parameters, utilization rate and other information to the OLED display for display.

When the server fails, the BMC sends the fault information to the PSOC4 chip through the I2C bus, and the PSOC4 chip sends the fault information to the OLED display, and the OLED display will jump out of the normal display state of the server and flash the fault information for two seconds. , to return to the normal interface, and an alarm flag will be displayed on the upper left of the display at the same time. The user can judge whether there is a fault and whether the fault has been resolved through the alarm flag on the OLED. If the fault has not been resolved, the user can press the button Operation, perform corresponding simple processing on the located fault source, for example, perform reset processing on the control chip of the fault source. If the user wants to view the fault information, he needs to press the key to enter the fault information menu item and display the fault information.

At the same time, the PSOC4 chip judges the fault level according to the fault information, and feeds back a corresponding processing strategy to the BMC according to the fault level, so as to drive the BMC to process the server accordingly according to the processing strategy. For example, the PSOC4 chip judges that an unrecoverable fault has occurred, and the PSOC4 chip directly feeds back a shutdown processing strategy to the BMC to drive the BMC to shutdown the server.

It can be seen from the above embodiments that, compared to the prior art, at least one embodiment provided in the above embodiments provides a server failure visual detection and processing method, device, and programmable chip, adding an OLED display to the server, and adding an OLED display to the server. A programmable chip is added between the OLED display and the BMC. In addition, the user can quickly locate the fault point through the fault information displayed on the OLED; in another embodiment, the PSOC series chip is used, and the input can be connected to one or more BMCs. Output to an OLED display to realize the mode that the BMC controls the PSOC to drive the OLED display, which can not only reduce the occupancy rate of the BMS, but also allow customers to know more about the real-time operation of the server, and support multi-node systems and redundant systems able to support well. In another embodiment, the programmable chip can determine the level of the fault, and feed back a corresponding processing strategy to drive the BMC to handle the fault accordingly.

Those skilled in the art can understand that all or part of the steps in the above method can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium, such as a read-only memory, a magnetic disk or an optical disk, and the like. Optionally, all or part of the steps in the foregoing embodiments may also be implemented using one or more integrated circuits. Correspondingly, each module/unit in the foregoing embodiments may be implemented in the form of hardware, or may be implemented in the form of software function modules. The present invention is not limited to any specific combination of hardware and software.

The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. According to the content of the present invention, there can also be other various embodiments. Those skilled in the art can make various corresponding changes and deformations according to the present invention without departing from the spirit and essence of the present invention. Within the spirit and principles of the present invention, any modifications, equivalent replacements, improvements, etc., shall be included within the protection scope of the present invention.

Claims (10)

1. A server fault visual detection and processing method, comprising: The programmable chip receives the fault information sent by the baseboard management controller BMC in the server; The programmable chip sends the fault information to the OLED display for display, and judges the fault level according to the fault information, and feeds back a corresponding processing strategy to the BMC according to the fault level, so as to drive the BMC according to the fault level. The processing policy performs corresponding processing on the server. 2. The method of claim 1, further comprising: The programmable chip receives the working status information of the server sent by the BMC; The programmable chip sends the working status information to the OLED display for display. 3. The method of claim 2, wherein: The programmable chip adopts the intelligent platform management interface IPMI protocol to communicate with the BMC; the programmable chip receives the fault information sent by the BMC through the I2C bus, and receives the fault information sent by the BMC through a UART interface. The working status information; the programmable chip feeds back the corresponding processing strategy to the BMC through the UART interface; Wherein, the programmable chip is a programmable system on chip PSOC series chip. 4. The method of claim 1, wherein: The fault information includes: positioning information and error reporting information; The method also includes: the BMC communicates with the FPGA to locate, and sends the fault information to the programmable chip in a data packet format; the positioning information is the hardware information of the fault, and the error message is the fault information. Error message for faulty hardware. 5. The method of claim 4, wherein: The method also includes: setting a corresponding threshold and a processing strategy for each fault level, Said judging the fault level according to the fault information, feeding back a corresponding processing strategy to the BMC according to the fault level, so as to drive the BMC to perform corresponding processing on the server according to the processing strategy, including: If the error information reaches the threshold corresponding to a certain fault level, then it is judged that the fault occurred is the fault level, and the corresponding processing strategy is queried, and the processing strategy is sent to the BMC, wherein the processing strategy also includes Including: the positioning information and the fault level. 6. The method according to any one of claims 1 to 5, characterized in that: The BMC includes one or more. 7. A programmable chip for visual detection and processing of server faults, including: The receiving module is used to receive the fault information sent by the BMC; A display control module, configured to send the fault information to an OLED display for display; The fault control module is configured to judge a fault level according to the fault information, and feed back a corresponding processing policy to the BMC according to the fault level, so as to drive the BMC to perform corresponding processing on the server according to the processing policy. 8. The programmable chip according to claim 7, characterized in that: The programmable chip communicates with the BMC using the IPMI protocol; The receiving module is also used to receive the fault information through the I2C bus; The display control module is further configured to send the fault information to the OLED display through a serial peripheral interface SPI; The fault control module is further configured to feed back the corresponding processing strategy to the BMC through a UART interface. 9. The programmable chip according to claim 8, characterized in that: The fault information includes: positioning information and error reporting information; the positioning information is the location information of the hardware that has failed, and the error reporting information is the error information of the hardware sending the fault; The fault control module is also used to set corresponding thresholds and processing strategies for each fault level; The fault control module is configured to judge a fault level according to the fault information, and feed back a corresponding processing strategy to the BMC according to the fault level, so as to drive the BMC to perform corresponding processing on the server according to the processing strategy, including: If the error information reaches the threshold corresponding to a certain fault level, then it is judged that the fault occurred is the fault level, and the corresponding processing strategy is queried, and the processing strategy is sent to the BMC, wherein the processing strategy also includes Including: the positioning information and the fault level. 10. A visual detection and processing system for server faults, comprising: one or more BMCs, the programmable chip according to claims 7-9, and an OLED display.