A multi-node monitoring and adjustment system and device for array servers
By designing and performing point-to-point bus connections of nodes in the server, monitoring and controlling temperature and voltage in real time, the problem of easy attack and unstable server monitoring systems in the existing technology is solved, and higher security is achieved and stability and independent data transmission.
Patent Information
- Application Number
- CN202311649722.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-12-04
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2043-12-04
AI Technical Summary
Existing server monitoring systems are prone to attack when reconfiguring network interfaces, resulting in data leakage and unstable server status, and lack effective security and fault handling capabilities.
A monitoring system is designed, including analysis nodes, execution nodes and multimedia processing modules. Through point-to-point bus connection, the temperature and voltage of the server are monitored in real time, and the control commands are generated to adjust the speed of the radiator and turn off the power supply, realizing independent monitoring of the server status. and control without reconfiguring the network interface.
It improves the security and stability of the server, reduces the risk of data leakage, realizes rapid troubleshooting and independent data transmission, and enhances monitoring effect.
Smart Images

Figure CN117640219B_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of communications, and in particular to a monitoring system, a mainboard and a server. Background Art
[0002] When the server is running, in order to ensure safety, it is necessary to monitor the status of the server. In this regard, the prior art generally uses a baseboard management controller (BMC) for monitoring. The baseboard management controller can be set on the mainboard of the server and collect the working status of other components also set on the server mainboard to determine the status of the server. The baseboard management controller can send the determined server status data to the external network, and the network interface of the server may be reconfigured in this process.
[0003] In this case, it is easy for an attacker to capture the server's network interface reconfiguration information, thereby attacking and controlling the server. When a server is attacked and a vulnerability appears, there is not only a risk of data leakage, but also when necessary operating files are lost, the server will not be able to work properly, resulting in an unstable server status. Summary of the invention
[0004] In view of this, the present disclosure proposes a monitoring system, a mainboard and a server. When the system is used to monitor the server status, the security is stronger, the risk of data leakage can be reduced, the stability of the server working status is improved, and the independence of data transmission and better monitoring effect are achieved.
[0005] According to one aspect of the present disclosure, a monitoring system is proposed, including an analysis node, an execution node, and at least one monitoring node. The system is used to monitor the status of a server and control the server. The analysis node is respectively connected to the execution node and the at least one monitoring node through a point-to-point bus. The types of the monitoring nodes include one or more of a multimedia processing module and a controller. The monitoring node is used to transmit the acquired operating status information to the analysis node; the analysis node is used to analyze the operating status information to determine the temperature of the server, generate a first control instruction and a first monitoring instruction when the temperature is greater than a first threshold, output the first control instruction to the execution node, output the first monitoring instruction to a host communicating with the server, and the first monitoring instruction indicates that the temperature of the server is abnormal; the execution node is used to execute the first control instruction to adjust the speed of the radiator of the server.
[0006] In a possible implementation, the analysis node is also used to analyze the operating status information to determine the voltage of the server, and when the voltage is greater than a second threshold, shut down the power of the server and generate a second monitoring instruction, wherein the second monitoring instruction indicates that the voltage of the server is abnormal; and output the second monitoring instruction to the host.
[0007] In a possible implementation, the analysis node is further configured to output the operating status information to the host when the temperature is less than or equal to a first threshold and the voltage is less than or equal to a second threshold.
[0008] In one possible implementation, the analysis node is further used to, upon receiving at least one status acquisition instruction from the host, output each status acquisition instruction to the corresponding monitoring node; the monitoring node is further used to, in response to the status acquisition instruction, transmit the acquired operating status information to the analysis node.
[0009] In one possible implementation, an asynchronous receive / transmit protocol is used for communication between the analysis node and the monitoring node, and between the analysis node and the execution node, and the transmitted data is packaged and transmitted according to a preset data packet format, wherein the preset data packet format includes a packet header, valid data, and a check bit, the packet header indicates the number of bits of the valid data, the node that outputs the data packet, and the node that receives the data packet, the valid data indicates the type and content of the transmitted data, and the check bit is determined based on the cumulative sum of the packet header and the valid data.
[0010] In one possible implementation, the analysis node is further used to generate a second control instruction and output the second control instruction to the execution node; the execution node is further used to execute the second control instruction to control a display device communicating with the server to display one or more of the temperature and the voltage.
[0011] In one possible implementation, the type of monitoring node also includes a programmable module, which is used to monitor the voltage of the server, and when the voltage is greater than a second threshold, generates overvoltage information and outputs it to the analysis node; the analysis node is also used to, when receiving the overvoltage information, shut down the power of the server and generate a second monitoring instruction, the second monitoring instruction indicating that the server voltage is abnormal; and output the second monitoring instruction to the host.
[0012] In a possible implementation, when the temperature is greater than a first threshold, the analysis node is further used to analyze the operating status information to determine the working status of the radiator, and the first monitoring instruction also indicates the working status of the radiator.
[0013] In one possible implementation, the power supply includes multiple power sub-modules, and when the voltage is greater than a second threshold, the analysis node is also used to analyze the operating status information to determine the working status of each power sub-module, and the second monitoring instruction also indicates the working status of the power sub-module.
[0014] According to another aspect of the present disclosure, a mainboard is provided, comprising the monitoring system described above.
[0015] According to another aspect of the present disclosure, a server is provided, comprising the above-mentioned mainboard.
[0016] According to the monitoring system of the embodiment of the present disclosure, it includes an analysis node, an execution node, and at least one monitoring node. The monitoring node transmits the acquired operation status information to the analysis node; the analysis node analyzes the operation status information to determine the temperature of the server, so as to realize the monitoring of multiple monitoring nodes; the analysis node generates a first control instruction and a first monitoring instruction when the temperature is greater than a first threshold value, outputs the first control instruction to the execution node, and outputs the first monitoring instruction to the host communicating with the server. The first monitoring instruction indicates that the temperature of the server is abnormal, and the abnormal situation can be notified to the host in time; and there is no need to reconfigure the network interface of the server, thereby reducing the probability of the server being attacked and generating vulnerabilities, reducing the risk of data leakage, and improving security. The execution node is used to execute the first control instruction to adjust the speed of the radiator of the server, so when an emergency occurs, there is no need to wait for the host to process, and the server can process it by itself, thereby improving the efficiency of fault handling and reducing the risk of server damage. Since the analysis node is respectively connected to the execution node and at least one monitoring node through a point-to-point bus, the monitoring-related data including the operation status information and the first control instruction can be transmitted separately through the point-to-point bus, decoupled from the business data of the analysis node, the execution node and the monitoring node, and have the independence of data transmission; the types of monitoring nodes include one or more of multimedia processing modules and controllers, so that the obtainable operation status information is richer and the monitoring effect is better. In summary, the monitoring system of the embodiment of the present disclosure can monitor the status of the server and control the server. When using the system to implement server status monitoring, the security is stronger, the risk of data leakage can be reduced, the stability of the server working status can be improved, and the independence of data transmission and good monitoring effect can be achieved.
[0017] The monitoring system of the disclosed embodiment has multi-node monitoring capability and can adapt to monitoring nodes of different business scenarios and different business attributes. The host can obtain the operating status information of the monitoring node of the server by issuing a status acquisition instruction, realize remote monitoring of the server status, and can be refined to monitor the status of each monitoring node. By building a complete asynchronous receiving and sending protocol to transmit data and defining a preset data packet format, the communication interface of monitoring nodes with different hardware attributes can be unified, and decoupled from business communications, to build a monitoring management layer.
[0018] When the monitoring system is running, it can monitor the server temperature in real time, and adjust the server's radiator speed in real time according to the temperature. It is understandable that if the host sends an adjustment instruction for the radiator speed to the analysis node, the analysis node can also transmit the instruction to the execution node through the point-to-point bus for execution, so the system can remotely control and adjust the server's radiator speed.
[0019] When the monitoring system is running, it can monitor the power status of the server in real time, and can directly shut down the power without going through the host if necessary. It is understandable that if the host sends a shutdown command or a restart command to the analysis node, the analysis node can also transmit the command to the execution node through the point-to-point bus for execution, so the system can realize remote restart and shutdown of the server.
[0020] When the monitoring system is running, the operating status information can be analyzed to determine the temperature anomalies and voltage anomalies of the server. Furthermore, instructions can be sent to the execution node to control the execution node to present the cause of the fault (such as specific temperature and / or specific voltage) to the display device.
[0021] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0022] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the disclosure and, together with the description, serve to explain the principles of the disclosure.
[0023] Figure 1 An exemplary application scenario of the monitoring system according to an embodiment of the present disclosure is shown.
[0024] Figure 2 A schematic diagram showing the structure of a monitoring system according to an embodiment of the present disclosure.
[0025] Figure 3 A schematic diagram showing the workflow of a monitoring system according to an embodiment of the present disclosure.
[0026] Figure 4A schematic diagram showing the workflow of a monitoring system according to an embodiment of the present disclosure.
[0027] Figure 5 A schematic diagram showing the interaction flow between the information processing module MPU and the programmable module CPLD according to an embodiment of the present disclosure.
[0028] Figure 6 A schematic diagram showing the structure of a mainboard according to an embodiment of the present disclosure. DETAILED DESCRIPTION
[0029] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.
[0030] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.
[0031] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can also be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the subject matter of the present disclosure.
[0032] Figure 1 An exemplary application scenario of the monitoring system according to an embodiment of the present disclosure is shown.
[0033] like Figure 1 As shown, the application scenario may include a remote host, a switch, and multiple servers. Each server is connected to the switch via a network cable, and the host is connected to the switch. Therefore, the host can communicate with each server separately through the switch. The host can be a computer or a server. The embodiment of the present disclosure does not limit the specific type of the host.
[0034] Each server includes a motherboard, on which a monitoring system of an embodiment of the present disclosure is disposed. The monitoring system can analyze the status of the server where it is located, and when the server is in an abnormal state (such as the temperature exceeding the first threshold value and the voltage exceeding the second threshold value as described below), the information that the server is abnormal is transmitted to the host through instructions (such as the first monitoring instruction and the second monitoring instruction as described below), so that the host can be informed that the server is abnormal. The monitoring system can directly control the working mode of the modules on the server (such as the power module and the radiator as described below) to adjust the status of the server.
[0035] When the server is not in an abnormal state, the monitoring system may also transmit operating status information indicating the server status to the host, so that the host can learn the real-time status of the server and monitor it.
[0036] The host can send instructions to the monitoring system, and the monitoring system executes the instructions to control the working mode of the modules on the server (such as the power module and heat sink described below) to adjust the status of the server.
[0037] The monitoring system according to the embodiment of the present disclosure is introduced below.
[0038] In a possible implementation, the monitoring system includes an analysis node, an execution node, and at least one monitoring node. The system is used to monitor the status of the server and control the server. The analysis node is connected to the execution node and the at least one monitoring node through a point-to-point bus. The types of monitoring nodes include one or more of a multimedia processing module and a controller.
[0039] The monitoring node is used to transmit the acquired operation status information to the analysis node;
[0040] The analysis node is used to analyze the operation status information to determine the temperature of the server, generate a first control instruction and a first monitoring instruction when the temperature is greater than a first threshold, output the first control instruction to the execution node, output the first monitoring instruction to a host communicating with the server, and the first monitoring instruction indicates that the temperature of the server is abnormal;
[0041] The execution node is used to execute the first control instruction to adjust the rotation speed of the radiator of the server.
[0042] Figure 2 A schematic diagram showing the structure of a monitoring system according to an embodiment of the present disclosure. Figure 3 A schematic diagram showing the workflow of a monitoring system according to an embodiment of the present disclosure.
[0043] like Figure 2As shown, for example, the monitoring system may include an analysis node (data processing module), an execution node (information processing module (Message Processing Unit, MPU)), and three monitoring nodes (multimedia processing module, controller A, controller B). The analysis node is connected to the execution node and the monitoring node respectively through a point-to-point bus. The point-to-point bus can be used specifically to transmit monitoring-related data, which may include operating status information indicating the status of the server and a first control instruction for controlling the server, etc. A software module may be provided on the analysis node. When data is transmitted through the point-to-point bus, the software module can be used to package the transmitted data for transmission. For the packaging method, please refer to the relevant description of Tables 1 to 8 below. The monitoring-related data of the disclosed embodiment can be transmitted separately, decoupled from the original business data of the analysis node, the execution node, and the monitoring node.
[0044] Those skilled in the art should understand that the analysis node, execution node, and monitoring node may also be other modules or devices, and the monitoring system may also include more monitoring nodes, as long as they can complete the functions of the analysis node, execution node, and monitoring node described below, the embodiments of the present disclosure are not limited to this.
[0045] The functions of each type of node are described below. Figure 3 As shown, the monitoring node is used to transmit the acquired operation status information to the analysis node (step S31). The operation status information acquired by the monitoring node indicates the state of the server. For example, multiple temperature sensors can be set at different positions in the monitoring system, and the operation status information can include the temperature of each temperature sensor. A radiator can also be set in the server, and the acquired status information can include the actual rotation speed of the radiator, etc. A plurality of power submodules can also be set in the server, and the acquired status information can include the voltage of each power submodule, etc. Since the temperature sensor, the radiator, and the power submodule are all set on the server, the status of these modules and devices can indicate the status of the server.
[0046] The status information of the monitoring node may also include the operating status information of the monitoring node itself, such as the temperature and voltage of each monitoring node. Since the monitoring node is also set on the server, the temperature and voltage of the monitoring node also indicate the status of the server. Those skilled in the art should understand that as long as the operating status information obtained by the monitoring node can indicate the status of the server, the embodiments of the present disclosure do not limit the specific content of the obtained operating status information.
[0047] The analysis node may analyze the operation status information to determine the temperature of the server. Exemplarily, the maximum value of the multiple temperatures actually included in the operation status information may be used as the temperature of the server. A first threshold may be pre-set, and when the temperature of the server is greater than the first threshold, it is considered that the temperature of the server is too high and reaches an emergency state, and a first control instruction and a first monitoring instruction may be generated (step S32), the first control instruction may be a radiator control instruction, and the first monitoring instruction may indicate that the server temperature is abnormal.
[0048] Those skilled in the art should understand that the method of analyzing and determining the temperature of the server should be more than the above examples. For example, the temperature detected at various locations of the server can also be directly transmitted. The embodiment of the present disclosure does not limit the method of analyzing the operating status information to determine the temperature of the server.
[0049] The analysis node may output the first control instruction to the execution node (step S33), and the execution node may adjust the speed of the radiator of the server by executing the first control instruction (step S34). The adjustment method may be to increase the speed of the radiator or directly force it to run at the maximum speed.
[0050] The analysis node can output the first monitoring instruction to the host communicating with the server (step S35) to notify the host of the abnormal temperature of the server. The host can determine that the server temperature is abnormal after receiving the first monitoring instruction. In this case, the server does not need to wait for the host to issue an instruction to control the radiator. Once the temperature abnormality is found, it can be handled in time, thereby improving the efficiency of fault handling.
[0051] Examples of the operating status information, the first control instruction and the first monitoring instruction may refer to the relevant descriptions in Table 2, Table 3 and Table 7 below.
[0052] According to the monitoring system of the embodiment of the present disclosure, it includes an analysis node, an execution node, and at least one monitoring node. The monitoring node transmits the acquired operation status information to the analysis node; the analysis node analyzes the operation status information to determine the temperature of the server, so as to realize the monitoring of multiple monitoring nodes; the analysis node generates a first control instruction and a first monitoring instruction when the temperature is greater than a first threshold value, outputs the first control instruction to the execution node, and outputs the first monitoring instruction to the host communicating with the server. The first monitoring instruction indicates that the temperature of the server is abnormal, and the abnormal situation can be notified to the host in time; and there is no need to reconfigure the network interface of the server, thereby reducing the probability of the server being attacked and generating vulnerabilities, reducing the risk of data leakage, and improving security. The execution node is used to execute the first control instruction to adjust the speed of the radiator of the server, so when an emergency occurs, there is no need to wait for the host to process, and the server can process it by itself, thereby improving the efficiency of fault handling and reducing the risk of server damage. Since the analysis node is respectively connected to the execution node and at least one monitoring node through a point-to-point bus, the monitoring-related data including the operation status information and the first control instruction can be transmitted separately through the point-to-point bus, decoupled from the business data of the analysis node, the execution node and the monitoring node, and have the independence of data transmission; the types of monitoring nodes include one or more of multimedia processing modules and controllers, so that the obtainable operation status information is richer and the monitoring effect is better. In summary, the monitoring system of the embodiment of the present disclosure can monitor the status of the server and control the server. When using the system to implement server status monitoring, the security is stronger, the risk of data leakage can be reduced, the stability of the server working status can be improved, and the independence of data transmission and good monitoring effect can be achieved.
[0053] In a possible implementation, the analysis node is further used to analyze the operation status information to determine the voltage of the server, and when the voltage is greater than a second threshold, shut down the power supply of the server and generate a second monitoring instruction, the second monitoring instruction indicating that the voltage of the server is abnormal;
[0054] The second monitoring instruction is output to the host.
[0055] Figure 4 A schematic diagram showing the workflow of a monitoring system according to an embodiment of the present disclosure.
[0056] For example, the abnormality of the server may also manifest itself in other forms besides overtemperature, such as overvoltage. Referring to the description above, the acquired status information may include the voltage of each power submodule and the voltage of each monitoring node. The power submodule and the monitoring node may be located in different power domains of the server (for example, an area powered by a single power submodule). Therefore, the various voltages of the server can be analyzed and determined based on the acquired status information. For example, the maximum value of multiple voltages of each power domain actually included in the operating status information can be used as the voltage of the power domain. The voltage of each power domain is a component of the server voltage. A second threshold value may be set in advance, and when the voltage of the server is greater than the second threshold value, it is considered that the server voltage is too high and reaches an emergency state. In this case, if Figure 4 As shown, the analysis node can directly shut down the power of the server (step S41), and at the same time generate a second monitoring instruction (step S42) and output it to the host (step S43), and the second monitoring instruction can indicate that the server voltage is abnormal. The host can determine that the server voltage is abnormal after receiving the second monitoring instruction.
[0057] For an example of the second monitoring instruction, please refer to the relevant description of Table 8 below.
[0058] Those skilled in the art should understand that the method of analyzing and determining the voltage of the server is more than the above example. For example, multiple voltages can be sampled and analyzed to obtain the voltage of the server. The embodiment of the present disclosure does not limit the method of analyzing the operating status information to determine the voltage of the server.
[0059] In this way, the power supply can be quickly shut down in an emergency due to overvoltage, further improving the safety of the server.
[0060] In a possible implementation, the analysis node is further configured to output the operating status information to the host when the temperature is less than or equal to a first threshold and the voltage is less than or equal to a second threshold.
[0061] For example, if the analysis of status information determines that the temperature and voltage of the server have not reached an emergency state, then the monitoring system does not need to control the status of the server, and the status of the server is still controlled by the instructions issued by the host. Figure 4 As shown, the analysis node can output the operation status information to the host (S44), which is stored by the host. The host can then analyze and monitor the status of the server based on the operation status information.
[0062] In this way, the host can obtain the operating status information indicating the status of the server, which facilitates the host to analyze and monitor the status of the server.
[0063] In a possible implementation, the analysis node is further used to:
[0064] When receiving at least one status acquisition instruction from the host, output each status acquisition instruction to the corresponding monitoring node;
[0065] The monitoring node is further configured to transmit the acquired operation status information to the analysis node in response to the status acquisition instruction.
[0066] For example, each monitoring node can be preset to obtain the running status information and output it to the analysis node at a certain period, and the host can also actively instruct a specific monitoring node of the monitoring system to output the running status information to the analysis node at any time.
[0067] For example, Figure 4 As shown, when the host wants at least one monitoring node of the monitoring system to obtain the running status information, it can send at least one status acquisition instruction corresponding to at least one monitoring node to the analysis node (step S45), and each status acquisition instruction corresponds to one monitoring node. When the analysis node receives at least one status acquisition instruction from the host, it can output each status acquisition instruction to the corresponding monitoring node (step S46). For examples of status acquisition instructions, see the relevant description of Table 6 below.
[0068] In response to the status acquisition instruction, the monitoring node may transmit the acquired operation status information to the analysis node (S47). The analysis node may continue to perform the operations corresponding to the above steps S32, S33, S35, S41-S44.
[0069] In this way, the host can monitor the status of the server more flexibly.
[0070] In a possible implementation, the analysis node is further used to generate a second control instruction, and output the second control instruction to the execution node;
[0071] The execution node is further used to execute the second control instruction to control the display device communicating with the server to display one or more of temperature and voltage.
[0072] For example, the server may communicate with a display device, and the execution node may also have the ability to control the display. After the analysis node analyzes and determines the temperature and / or voltage of the server, the analysis node may generate a second control instruction. The second control instruction may be a display control instruction, indicating that one or more of the temperature and voltage determined by the analysis is displayed. For an example of the second control instruction, see the relevant description of Table 4 below.
[0073] The analysis node may output the second control instruction to the execution node. The execution node executes the second control instruction to control the display device communicating with the server to display one or more of temperature and voltage.
[0074] In this way, the temperature and voltage determined by analysis can be displayed, making it easier for users to know the status of the server.
[0075] In a possible implementation, the type of monitoring node also includes a programmable module.
[0076] The programmable module is used to monitor the voltage of the server, and when the voltage is greater than a second threshold, overvoltage information is generated and output to the analysis node;
[0077] The analysis node is further used to, upon receiving the overvoltage information, shut down the power supply of the server and generate a second monitoring instruction, the second monitoring instruction indicating that the voltage of the server is abnormal;
[0078] The second monitoring instruction is output to the host.
[0079] For example, the server may further include a programmable module, such as a complex programmable logic device (CPLD). The programmable module can monitor the voltage of the server and generate overvoltage information to output to the analysis module when the voltage is greater than the second threshold. Therefore, when the analysis module receives the overvoltage information, it can directly determine that the server has reached an emergency state due to voltage abnormality.
[0080] In this case, the analysis node may shut down the power supply of the server and generate a second monitoring instruction, which may indicate that the voltage of the server is abnormal. The analysis node may output the second monitoring instruction to the host.
[0081] In combination with the above description of the analysis node analyzing the operating status information obtained by the monitoring node to determine the server voltage, the monitoring system of the embodiment of the present disclosure only needs to have the ability to analyze the operating status information obtained by the monitoring node to determine the server voltage, or include a programmable module that can generate overvoltage information. In this way, it can monitor the server voltage and control the server when the server voltage is abnormal.
[0082] In this way, the way of monitoring the voltage of the server and controlling the server when the server voltage is abnormal is made more flexible.
[0083] In a possible implementation, when the temperature is greater than a first threshold, the analysis node is further configured to analyze the operating status information to determine a working status of the radiator, and the first monitoring instruction includes the working status of the radiator.
[0084] For example, the temperature of the server is related to the state of the radiator. Under the initial condition that other conditions remain unchanged, the higher the speed of the radiator, the stronger the heat dissipation capacity of the server; the lower the speed of the radiator, the relatively weaker the heat dissipation capacity of the server. Therefore, when the temperature is greater than the first threshold and it is determined that the server has reached an emergency state due to excessive temperature, it can be considered that the radiator may be faulty or the circuit is abnormal.
[0085] In this regard, the analysis node can further determine the working state of the radiator. The working state of the radiator is related to the rotation speed of the radiator. For example, when the rotation speed of the radiator is 0, it means that the radiator has stopped rotating. When the rotation speed of the radiator is lower than expected, it can be considered that the radiator is faulty. When the rotation speed of the radiator is greater than or equal to the expected speed, it can be considered that the radiator is working normally.
[0086] The first monitoring instruction may include the working state of the radiator. For example, the first monitoring instruction may include a code indicating the radiator, and one of a code indicating that the radiator stops rotating, a code indicating the actual rotation speed of the radiator, and a code indicating that the radiator fails. For an example of the first monitoring instruction, see the relevant description of Table 7 below.
[0087] In this way, the first monitoring instruction can indicate more content, which makes it easier for the host to perform a more detailed analysis of the root cause of the server abnormality according to the first monitoring instruction.
[0088] In one possible implementation, the power supply includes multiple power sub-modules. When the voltage is greater than a second threshold, the analysis node is also used to analyze the operating status information to determine the working status of each power sub-module, and the second monitoring instruction includes the working status of the power sub-module.
[0089] For example, the power supply may include multiple power submodules, and the voltage of the server is related to the output of the power submodule. Therefore, when the voltage is greater than the second threshold and it is determined that the server has reached an emergency state due to excessive voltage, it can be considered that the power supply may fail.
[0090] Each power submodule has a corresponding serial number. When the voltage is greater than the second threshold, the analysis node may also analyze the operation status information to determine the operation status (normal or abnormal) of each power submodule.
[0091] The second monitoring instruction may include the working state of the power submodule. For example, the second monitoring instruction may include a code indicating the power supply, a code indicating the number of the power submodule, and a code indicating whether the power submodule state is normal / abnormal. For an example of the second monitoring instruction, see the relevant description of Table 8 below.
[0092] In this way, the second monitoring instruction can indicate more content, which makes it easier for the host to perform a more detailed analysis of the root cause of the server abnormality according to the second monitoring instruction.
[0093] Those skilled in the art should understand that the second monitoring instruction may also include more information, for example, the server may also include a main power supply, and the voltage of the server is also related to the output of the main power supply. When the voltage is greater than the second threshold, the analysis node may also be used to analyze the operating status information to determine the working status of the main power supply, and the second monitoring instruction may also include the working status of the main power supply. The present disclosure does not limit the specific content included in the second monitoring instruction.
[0094] In a possible implementation, an asynchronous receiving and sending protocol is used for communication between the analysis node and the monitoring node, and between the analysis node and the execution node. The transmitted data is packaged and transmitted according to a preset data packet format.
[0095] The preset data packet format includes a packet header, valid data, and a check bit.
[0096] The packet header indicates the number of bits of valid data, the node that outputs the data packet, and the node that receives the data packet. The valid data indicates the type and content of the data being transmitted. The check bit is determined based on the cumulative sum of the packet header and the valid data.
[0097] The embodiment of the present disclosure sets an asynchronous receiving and sending protocol between the analysis node and the monitoring node, and between the analysis node and the execution node, and sets a specific data packet format (i.e., a preset data packet format) for the data transmitted under the protocol. The length of the data packet can be set to be less than or equal to 128 bits, or to other values, which is not limited by the present disclosure.
[0098] Therefore, the above-mentioned operation status data, first control instruction, second control instruction, and state acquisition instruction can be packaged into data packets according to a preset data packet format and then transmitted. Optionally, the first monitoring instruction and the second monitoring instruction can also be packaged into data packets according to the preset data packet format and then transmitted. The following first introduces an example of the preset data packet format in conjunction with Table 1, and then gives examples of data packets corresponding to operation status information, state acquisition instructions, first control instructions, second control instructions, first monitoring instructions, second monitoring instructions, and other instructions that may be involved in the monitoring system in conjunction with Tables 1-8.
[0099] Table 1 shows an example of a preset data packet format according to an embodiment of the present disclosure.
[0100] Table 1
[0101]
[0102] Referring to Table 1, the preset data packet format may include three parts: a packet header, valid data, and a check bit. The packet header may indicate the number of bits of valid data, the node that outputs the packet, and the node that receives the packet. The valid data indicates the type and content of the data being transmitted. The check bit is determined based on the cumulative sum of the packet header and the valid data.
[0103] Table 2 shows an example of a data packet corresponding to the running status information according to an embodiment of the present disclosure.
[0104] Table 2
[0105]
[0106] As shown in Table 2, the first two bits (0xAA 0xAA, respectively) in the header of the data packet corresponding to the running status information can indicate that the node outputting the data packet is a multimedia processing module, and that the node receiving the data packet is an analysis node. The third bit (0x04) of the header can indicate that the number of bits of valid data is 4. The first bit (0x03) of the valid data can indicate that the type of data being transmitted is the running status information, and the last three bits (0x00 0x00 0x00) of the valid data can indicate the content of the data being transmitted, that is, the specific content of the running status information. The check bit can be the last two bits of the cumulative sum of the header 0xAA 0xAA 0x04 and the valid data 0x03 0x000x00 0x00.
[0107] Table 3 shows an example of a data packet corresponding to the first control instruction according to an embodiment of the present disclosure.
[0108] Table 3
[0109]
[0110] As shown in Table 3, the first two bits (0xAB 0xAB, respectively) in the header of the data packet corresponding to the first control instruction can indicate that the node outputting the data packet is an analysis node, and that the node receiving the data packet is an execution node. The third bit (0x04) of the header can indicate that the number of bits of valid data is 4. The first bit (0x01) of the valid data can indicate that the type of data being transmitted is related to the radiator, and the last three bits of the valid data (0x00 0x00 0x3F / 7F / BF / FF) can indicate the content of the data being transmitted, that is, the specific content of the first control instruction. In the example of Table 3, the specific content of the first control instruction may be the target speed of the radiator, wherein 0x00 0x00 0x3F may indicate that the target speed of the radiator is 25% of the rated speed, 0x00 0x000x7F may indicate that the target speed of the radiator is 50% of the rated speed, 0x00 0x00 0xBF may indicate that the target speed of the radiator is 75% of the rated speed, and 0x00 0x00 0xFF may indicate that the target speed of the radiator is 100% of the rated speed. The check bit may be the last two digits of the cumulative sum of the header 0xAB 0xAB 0x04 and the valid data 0x01 0x00 0x00 0x3F / 7F / BF / FF.
[0111] Table 4 shows an example of a data packet corresponding to the second control instruction according to an embodiment of the present disclosure.
[0112] Table 4
[0113]
[0114] As shown in Table 4, the first two bits (0xAB 0xAB, respectively) in the header of the data packet corresponding to the second control instruction can indicate that the node outputting the data packet is an analysis node, and indicate that the node receiving the data packet is an execution node. The third bit (0x04) of the header can indicate that the number of bits of valid data is 4. The first bit (0x02) of the valid data can indicate that the type of data being transmitted is related to the display, and the last three bits (0x00 0x00 0x19) of the valid data can indicate the content of the data being transmitted, that is, the specific content of the second control instruction. In the example of Table 4, the specific content of the second control instruction can be the displayed temperature, where 0x000x00 0x19 can indicate that the temperature is 25 degrees Celsius. The check bit can be the last two bits of the cumulative sum of the header 0xAB 0xAB 0x04 and the valid data 0x020x00 0x00 0x19.
[0115] It is mentioned above that the analysis node can directly turn off the power supply. Exemplarily, the analysis node can turn off the power supply by issuing a third control instruction. The third control instruction can be sent directly to the power supply, or sent to the execution node, and the execution node executes the third control instruction to turn off the power supply. The embodiment of the present disclosure does not limit the recipient of the third control instruction.
[0116] Table 5 shows an example of a data packet corresponding to the third control instruction according to an embodiment of the present disclosure.
[0117] Table 5
[0118]
[0119] As shown in Table 5, the first two bits (0xAB 0xAB, respectively) in the header of the data packet corresponding to the third control instruction can indicate that the node outputting the data packet is an analysis node, and indicate that the node receiving the data packet is an execution node. The third bit (0x04) of the header can indicate that the number of bits of valid data is 4. The first bit (0x00) of the valid data can indicate that the type of data being transmitted is related to the power supply, and the last three bits (0x00 0x00 0x00) of the valid data can indicate the content of the data being transmitted, that is, the specific content of the third control instruction. In the example of Table 5, the specific content of the third control instruction can be to turn off the power supply. The check bit can be the last two bits of the cumulative sum of the header 0xAB 0xAB 0x04 and the valid data 0x00 0x00 0x00 0x00.
[0120] Table 6 shows an example of a data packet corresponding to a status acquisition instruction according to an embodiment of the present disclosure.
[0121] Table 6
[0122]
[0123] As shown in Table 6, the first two bits (0xAC 0xAC respectively) in the header of the data packet corresponding to the status acquisition instruction can indicate that the node outputting the data packet is the analysis node, and that the node receiving the data packet is the controller A in the monitoring node. The third bit (0x04) of the header can indicate that the number of bits of valid data is 4. The first bit (0x04) of the valid data can indicate that the type of data being transmitted is the status acquisition instruction, and the last three bits (0x00 0x00 0x00) of the valid data can indicate the content of the data being transmitted, that is, the specific content of the status acquisition instruction. In the example of Table 6, the specific content of the status acquisition instruction can be obtaining the operating status information. The check bit can be the last two bits of the cumulative sum of the header 0xAC 0xAC 0x04 and the valid data 0x04 0x00 0x000x00.
[0124] Table 7 shows an example of a data packet corresponding to the first monitoring instruction according to an embodiment of the present disclosure.
[0125] Table 7
[0126]
[0127] As shown in Table 7, the first two bits (0xAD 0xAD respectively) in the header of the data packet corresponding to the first monitoring instruction can indicate that the node outputting the data packet is the analysis node, and indicate that the host is the one receiving the data packet. The third bit (0x04) of the header can indicate that the number of bits of valid data is 4. The first bit (0x01) of the valid data can indicate that the type of data being transmitted is related to the radiator. The last three bits of the valid data (0x01 / FF 0x0000 / 0xFFFF) can represent the content of the data being transmitted, that is, the specific content of the first monitoring instruction. In the example of Table 7, the specific content of the first monitoring instruction may include a code indicating the radiator number (0x01 / FF), and one of a code indicating that the radiator stops rotating (0x0000), a code indicating the actual rotation speed of the radiator (0x0001-0xFFFE), and a code indicating a radiator failure (0xFFFF). The check bit can be the last two digits of the cumulative sum of the packet header 0xAD0xAD 0x04 and the valid data 0x01 0x01 / FF 0x0000 / 0xFFFF.
[0128] Table 8 shows an example of a data packet corresponding to the second monitoring instruction according to an embodiment of the present disclosure.
[0129] Table 8
[0130]
[0131] As shown in Table 8, the first two bits (0xAF 0xAF, respectively) in the header of the data packet corresponding to the second monitoring instruction can indicate that the node outputting the data packet is an analysis node, and that the host is the one receiving the data packet. The third bit (0x04) of the header can indicate that the number of bits of valid data is 4. The first bit (0x00) of the valid data can indicate that the type of data being transmitted is related to the power supply. The last three bits (0x01 / FF 0x0000 / 0xFFFF) of the valid data can represent the content of the data being transmitted, that is, the specific content of the second monitoring instruction. In the example of Table 8, the specific content of the second monitoring instruction can include a code (0x01 / FF) indicating the number of the power submodule, and a code (0x0000) indicating that the power submodule is normal, and a code (0xFFFF) indicating that the power submodule is abnormal. The check bit can be the last two bits of the cumulative sum of the header 0xAF 0xAF 0x04 and the valid data 0x000x01 / FF0x0000 / 0xFFFF.
[0132] Those skilled in the art should understand that the data packets shown in Tables 1 to 8 above are only examples. In actual applications, the coding indicating the node in the packet header, the coding indicating the number of valid data bits, the coding indicating the type of data being transmitted in the valid data, the coding indicating the content of the data being transmitted, and the coding in the check bit can all be set according to the requirements of the application scenario. The data structure of the protocol packet needs to comply with the first two bits of the packet header that can uniquely determine the node that outputs the data and the node that receives the data, the third bit indicates the number of valid data bits, the first bit of the valid data indicates the data type, and the rest of the valid data indicates the specific data being transmitted. The check bit is the last two bits of the cumulative sum of the packet header and the valid data. The embodiments of the present disclosure do not limit the specific contents included in the packet header, valid data, and check bits.
[0133] Furthermore, the execution node may be configured so that the execution node also has the function of obtaining the running status information. In this case, the monitoring node (such as Figure 2 The multimedia processing module, controller A, controller B, and programmable module CPLD in the example (operating status information or overvoltage information) and execution nodes (such as Figure 2 The information (operation status information) of the information processing module MPU) in the example can be uploaded to the analysis node (data processing module) for processing through the point-to-point bus. The analysis node (data processing module) and the execution node (information processing module MPU) can realize information exchange through the point-to-point bus.
[0134] The analysis node (data processing module) can distribute instructions to the execution node (information processing module MPU) through a point-to-point bus, and can also send instructions to the monitoring node (programmable module CPLD, controller A, controller B and multimedia processing module).
[0135] The programmable module CPLD in the execution node (information processing module MPU) and the monitoring node can realize information exchange through the analysis node (data processing module) and the point-to-point bus. Figure 5 A schematic diagram showing the interaction flow between the information processing module MPU and the programmable module CPLD according to an embodiment of the present disclosure.
[0136] like Figure 5 As shown, after the server's power switch is turned on, the information processing module starts running and sends a level signal (such as a high level) indicating that the server has been turned on to the programmable module CPLD to prompt the programmable module CPLD to start working. After that, the programmable module CPLD starts to monitor the power supply status and generates overvoltage information (not shown in the figure) when the voltage is greater than the second threshold.
[0137] At this time, the analysis node works normally and may generate one or more of the first control instruction, the second control instruction and the third control instruction. The analysis node can also transmit the first control instruction and the third control instruction to the programmable module CPLD. After the programmable module CPLD performs instruction analysis and data analysis, the scenario of the server is judged. If it is judged to be a non-emergency, the software that caused the problem is restarted. If it is judged to be an emergency, an instruction to instruct the server to shut down can be generated and sent to the information processing module MPU.
[0138] After the information processing module detects that the power is turned on, it enters a cycle of detection instructions - execution instructions - detection instructions. The information processing module may receive the first control instruction, the second control instruction, the third control instruction from the analysis node, and the instruction to instruct the server to shut down from the programmable module CPLD. The information processing module reports the fault, executes the third control instruction to turn off the power, and executes the instruction to instruct the server to shut down to shut down the server (shutdown). When the information processing module executes the first control instruction, it controls the speed of the radiator, and when it executes the second control instruction, it controls the display to display the temperature or voltage.
[0139] The monitoring system of the disclosed embodiment has multi-node monitoring capability and can adapt to monitoring nodes of different business scenarios and different business attributes. The host can obtain the operating status information of the monitoring node of the server by issuing a status acquisition instruction, realize remote monitoring of the server status, and can be refined to monitor the status of each monitoring node. By building a complete asynchronous transceiver protocol node network to transmit data and defining a preset data packet format, the communication interface of monitoring nodes with different hardware attributes can be unified, and decoupled from business communications, to build a monitoring management layer.
[0140] When the monitoring system is running, it can monitor the server temperature in real time, and adjust the server's radiator speed in real time according to the temperature. It is understandable that if the host sends an adjustment instruction for the radiator speed to the analysis node, the analysis node can also transmit the instruction to the execution node through the point-to-point bus for execution, so the system can remotely control and adjust the server's radiator speed.
[0141] When the monitoring system is running, it can monitor the power status of the server in real time, and can directly shut down the power without going through the host if necessary. It is understandable that if the host sends a shutdown command or a restart command to the analysis node, the analysis node can also transmit the command to the execution node through the point-to-point bus for execution, so the system can realize remote restart and shutdown of the server.
[0142] When the monitoring system is running, the operating status information can be analyzed to determine the temperature anomalies and voltage anomalies of the server. Furthermore, instructions can be sent to the execution node to control the execution node to present the cause of the fault (such as specific temperature and / or specific voltage) to the display device.
[0143] The disclosed embodiment also provides a mainboard. Figure 6 A schematic diagram showing the structure of a mainboard according to an embodiment of the present disclosure.
[0144] like Figure 6 As shown, the mainboard may include the monitoring system described above, as well as the power supply and heat sink described above. The mainboard may also include more modules, such as a processor, etc. The embodiment of the present disclosure does not limit the specific structure of the mainboard.
[0145] The present disclosure also provides a server, including the above-mentioned mainboard. The structural example of the server can be found in Figure 1 .
[0146] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.
Claims
1. A monitoring system, It is characterized in that The system comprises an analysis node, an execution node and at least one monitoring node. The system is used to monitor the status of a server and control the server. The analysis node is connected to the execution node and the at least one monitoring node respectively through a point-to-point bus. The type of the monitoring node comprises one or more of a multimedia processing module and a controller. The monitoring node and the execution node are used to transmit the acquired operation status information to the analysis node; The analysis node is used to analyze the operation status information to determine the temperature of the server, generate a first control instruction and a first monitoring instruction when the temperature is greater than a first threshold, output the first control instruction to the execution node, and output the first monitoring instruction to a host communicating with the server, wherein the first monitoring instruction indicates that the temperature of the server is abnormal; The execution node is further used to execute the first control instruction to adjust the rotation speed of the radiator of the server; The type of monitoring node also includes a programmable module. The analysis node is also used to output the generated control instructions to the programmable module. The programmable module is also used to judge the situation of the server after performing instruction analysis and data analysis. If it is judged to be a non-emergency situation, the software that caused the problem is restarted. If it is judged to be an emergency situation, an instruction to instruct the server to shut down is generated and sent to the execution node; the execution node is also used to execute the instruction to instruct the server to shut down to shut down the server.
2. The system according to claim 1, It is characterized in that The analysis node is also used to: Analyze the operation status information to determine the voltage of the server, and when the voltage is greater than a second threshold, turn off the power of the server and generate a second monitoring instruction, wherein the second monitoring instruction indicates that the voltage of the server is abnormal; The second monitoring instruction is output to the host.
3. The system according to claim 2, It is characterized in that The analysis node is also used to: When the temperature is less than or equal to a first threshold and the voltage is less than or equal to a second threshold, the operating status information is output to the host.
4. The system according to claim 1, It is characterized in that The analysis node is also used to: When receiving at least one status acquisition instruction from the host, output each status acquisition instruction to a corresponding monitoring node; The monitoring node is further configured to transmit the acquired operation status information to the analysis node in response to the status acquisition instruction.
5. The system according to claim 1, It is characterized in that The analysis node and the monitoring node, and the analysis node and the execution node communicate using an asynchronous receiving and sending protocol, and the transmitted data is packaged and transmitted according to a preset data packet format. The preset data packet format includes a packet header, valid data, and a check bit. The packet header indicates the number of bits of the valid data, the node that outputs the data packet, and the node that receives the data packet. The valid data indicates the type and content of the transmitted data. The check bit is determined based on the cumulative sum of the packet header and the valid data.
6. The system according to claim 2, It is characterized in that The analysis node is further used to generate a second control instruction and output the second control instruction to the execution node; The execution node is further configured to execute the second control instruction to control a display device communicating with the server to display one or more of the temperature and the voltage.
7. The system according to claim 1, It is characterized in that The programmable module is used to monitor the voltage of the server, and when the voltage is greater than a second threshold, generate overvoltage information and output it to the analysis node; The analysis node is further configured to, upon receiving the overvoltage information, shut down the power supply of the server and generate a second monitoring instruction, wherein the second monitoring instruction indicates that the voltage of the server is abnormal; The second monitoring instruction is output to the host.
8. The system according to claim 1, It is characterized in that When the temperature is greater than a first threshold, the analysis node is further configured to analyze the operating status information to determine the working status of the radiator, and the first monitoring instruction further indicates the working status of the radiator.
9. The system according to claim 2 or 7, It is characterized in that The power supply includes multiple power sub-modules. When the voltage is greater than a second threshold, the analysis node is further used to analyze the operating status information to determine the working status of each power sub-module. The second monitoring instruction also indicates the working status of the power sub-module.
10. A motherboard, It is characterized in that A monitoring system comprising any one of claims 1-9.
11. A server, It is characterized in that Comprising the mainboard as claimed in claim 10.
