Control system and server

Abstract

The invention provides a control system and a server, and relates to the technical field of artificial intelligence, in particular to the technical fields of cloud computing, intelligent hardware and the like. The control system comprises a control element used for generating an abnormal signal when the control software is in an abnormal state; the control software is used for controlling the fan in a normal state; and the switch element is used for communicating a power supply with the fan according to the abnormal signal so as to control the fan through the power supply. The heat dissipation stability can be improved.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, specifically to technical fields such as cloud computing and intelligent hardware, and in particular to a connection structure, a GPU module and a server. Background Art

[0002] The server is the basic equipment for building cloud computing. The server's main board (MB) integrates components such as the central processing unit (CPU) and baseboard management controller (BMC). In order to dissipate the heat of the components on the main board, a fan is set near the main board. Summary of the invention

[0003] The present disclosure provides a control system and a server.

[0004] According to one aspect of the present disclosure, a control system is provided, comprising: a control element for generating an abnormal signal when control software is in an abnormal state; the control software is used to control a fan when in a normal state; and a switch element for connecting a power supply with the fan according to the abnormal signal to control the fan through the power supply.

[0005] According to another aspect of the present disclosure, a server is provided, comprising: a chassis; a fan, a power supply and a control system arranged in the chassis; wherein the control system is as described in any one of the above aspects.

[0006] According to the technical solution of the present disclosure, the heat dissipation stability can be improved.

[0007] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0009] Figure 1 is a schematic diagram according to a first embodiment of the present disclosure;

[0010] Figure 2 is a schematic diagram according to a second embodiment of the present disclosure;

[0011] Figure 3 is a schematic diagram according to a third embodiment of the present disclosure;

[0012] Figure 4It is a schematic diagram of a status signal between the control software and the CPLD according to an embodiment of the present disclosure;

[0013] Figure 5 is a schematic diagram of another state signal between the control software and the CPLD according to an embodiment of the present disclosure;

[0014] Figure 6 is a schematic diagram according to a fourth embodiment of the present disclosure. DETAILED DESCRIPTION

[0015] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0016] In the related art, the fan is usually controlled by a BMC on a motherboard through built-in control software.

[0017] However, if the BMC control software fails, the BMC will not be able to control the fan, and the heat cannot be dissipated. The server will trigger overheating protection, causing the server to crash and affecting normal business operations.

[0018] In order to improve heat dissipation stability, the present disclosure provides the following embodiments.

[0019] Figure 1 It is a schematic diagram according to the first embodiment of the present disclosure. This embodiment provides a control system.

[0020] Taking a server as an example, the control software may be control software built into a BMC. When the control software is working normally, the control software controls the fan, for example, controls the fan to run at a set speed, so that the server is cooled by the rotation of the fan.

[0021] There may be one or more fans in the server, and a plurality of fans means at least two.

[0022] like Figure 1 As shown, each fan includes a control end and a power end, and the control software is connected to the control end via a first control line. In this way, when the control software is in a normal state, a control signal is transmitted via the first control line, and the speed of the fan is controlled based on the control signal.

[0023] When the control software works normally, the fan can be controlled by the control software.

[0024] In order to ensure the stability of heat dissipation, a control system is provided in the server in this embodiment, so that when an abnormality occurs in the control software, the fan can still be controlled to meet the heat dissipation demand of the server.

[0025] like Figure 1 As shown, the control system 100 includes: a control element 101 and a switch element 102 .

[0026] The control element 101 is used to generate an abnormal signal when the control software is in an abnormal state; the control software is used to control the fan when it is in a normal state; the switch element 102 is used to connect the power supply and the fan according to the abnormal signal to control the fan through the power supply.

[0027] Specifically, the control element is used to detect whether the control software is working properly, that is, to determine whether the control software is in a normal state or an abnormal state, and to generate an abnormal signal when the control software is in an abnormal state. In addition, the control element may not generate a signal or generate a normal signal when determining that the control software is in a normal state.

[0028] The switch element has three terminals, namely a control terminal and two connection terminals. The control terminal of the switch element is used to control the two connection terminals to be in a connected state or a disconnected state.

[0029] The control end of the switch element is connected to the control element, receives the signal generated by the control element, and connects the two connection ends of the switch element after the signal is an abnormal signal.

[0030] One connection end of the switch element is connected to the power supply, and the other connection end is connected to the control end of the fan. In this way, when the two connection ends of the switch element are in a connected state, the control end of the fan is connected to the power supply, and the transmission line between the power supply and the control end of the fan can be called a second control line. At this time, the power supply transmits a current signal to the control end of the fan through the second control line to control the fan.

[0031] When the two connection ends of the switch element are in a disconnected state, the control end of the fan and the power supply are also disconnected. At this time, the power supply cannot control the fan.

[0032] Based on this, when the control software is normal, the fan can be controlled by the control software, and when the control software is abnormal, the fan can be controlled by the power supply.

[0033] Furthermore, when the fan is controlled by the control software, the control software can flexibly determine the target speed, that is, different target speeds can be determined in different situations, and the fan can be controlled to run at different target speeds in different situations.

[0034] When the fan is controlled by the power supply, generally only one target speed can be determined. In order to improve the heat dissipation performance, the target speed can be selected as the maximum speed of the fan. At this time, the power supply controls the fan to run at the maximum speed.

[0035] In addition, the power supply is also connected to the power supply end of the fan through a power line to supply power to the fan.

[0036] In this embodiment, the control element generates an abnormal signal when an abnormality occurs in the control software, and the switch element connects the power supply and the control end of the fan according to the abnormal signal. In this way, when an abnormality occurs in the controller, the fan is controlled by the power supply, which can realize heat dissipation disaster recovery processing and improve heat dissipation stability.

[0037] Taking the server scenario as an example, the server's motherboard is equipped with a BMC, and the control software is embedded in the BMC. The control system is also located in the server, such as being set on the motherboard, so that it can respond to abnormal situations of the control software in a timely manner, improving timeliness.

[0038] The control system includes a control element and a switch element, and the switch element can be specifically a triode.

[0039] Transistor, the full name of which is semiconductor triode, also known as bipolar transistor or crystal triode, is a semiconductor device that controls current. Its function is to amplify weak signals into electrical signals with larger amplitude values, and it is also used as a contactless switch.

[0040] The transistor has three terminals, namely the base (B), emitter (E) and collector (C).

[0041] The transistor has three states: saturated conduction state, cut-off state and amplification state. When it is in the non-cut-off state (saturated conduction state or amplification state), current flows between its B pole and E pole, and between the E pole and C pole.

[0042] When a transistor is used as a switching element, its non-off state is regarded as a connected state of the switching element, and its off state is regarded as a disconnected state of the switching element.

[0043] Transistors are divided into PNP type and NPN type. PNP type transistors are composed of two P-type semiconductors with one N-type semiconductor in the middle, while NPN type transistors are composed of two N-type semiconductors with one P-type semiconductor in the middle. P represents the positive pole and N represents the negative pole.

[0044] When in the non-cut-off state, the current direction of the PNP transistor is from the E pole to the B pole, and from the E pole to the C pole. The current direction of the NPN transistor is from the B pole to the E pole, and from the C pole to the E pole.

[0045] Based on the above performance of the transistor, the switching element can specifically be a PNP transistor, and the base of the PNP transistor is used to input the abnormal signal, the emitter of the PNP transistor is connected to the power supply, and the collector of the PNP transistor is connected to the control end of the fan.

[0046] In this way, through the abnormal signal, the emitter (E pole) of the PNP transistor is connected to the collector (C pole), and the current flows from the E pole to the C pole, that is, from the power supply to the control end of the fan, thereby realizing the power supply's control over the fan.

[0047] In this embodiment, by satisfying the above-mentioned setting requirements through transistors, when an abnormal signal is input, the power supply and the control end of the fan can be connected to realize the control of the fan by the power supply, thereby completing the heat dissipation function simply and efficiently through the hardware circuit, improving the stability of the control system, and improving the server performance.

[0048] The switch element is controlled to switch according to the abnormal signal generated by the control element. The control element can generate the abnormal signal by hardware or by software. The following embodiments respectively describe the control element by hardware and the control element by software.

[0049] Figure 2 is a schematic diagram according to a second embodiment of the present disclosure, and this embodiment provides a control system.

[0050] like Figure 2 As shown, the control system 200 includes: a control element 201 and a switch element 202 .

[0051] In this embodiment, the switch element 202 is a PNP transistor as an example.

[0052] The control element 201 generates an abnormal signal by hardware.

[0053] For the hardware method: one of the high-level signal and the low-level signal can be used as an abnormal signal, and the other can be used as a normal signal.

[0054] The element for outputting a high level signal or a low level signal may specifically be a general-purpose input / output (GPIO) port.

[0055] For this reason, Figure 2 As shown, the control elements include: GPIO port.

[0056] The GPIO port includes pins and registers, etc. The packaging method of the GPIO port in different architectures may be different, and specifically may have different numbers of pins and registers. Therefore, the specific packaging method can be set according to actual needs.

[0057] The B pole of the PNP transistor as a switching element is connected to the above-mentioned GPIO port, the E pole is connected to the power supply, and the C pole is connected to the control end of the fan.

[0058] Since the PNP transistor connects the C pole and the E pole after receiving the abnormal signal, the current flows from the E pole to the C pole. Therefore, the high level signal can be regarded as an abnormal signal and the low level signal can be regarded as a normal signal. Specifically, the high level signal can be a 3.3V voltage signal and the low level signal can be a 0V voltage signal. The power supply voltage is higher than 3.3V, and the specific value can be set according to actual needs, such as 5V.

[0059] Based on this, when the control software is in a normal state, the GPIO port outputs a low-level signal as a normal signal; when the control software is in an abnormal state, the GPIO port outputs a high-level signal as an abnormal signal.

[0060] In this embodiment, the GPIO port is used as a control element. Since the GPIO port can output a high-level signal or a low-level signal, the high-level signal or the low-level signal can meet the connection or disconnection requirements of the switch element. In this way, the switch element can be controlled through the GPIO port without the need for a complex port, thereby reducing costs and implementation complexity.

[0061] The GPIO port can determine whether the control software is in an abnormal state according to the state value of the hardware component. Specifically, the GPIO port can determine whether the control software is in an abnormal state according to the count value of the counter.

[0062] For this reason, Figure 2 As shown, the control element also includes: a counter.

[0063] The counter is used to perform a counting operation to obtain a counting value, and the control software is also used to control the counting value not to be a preset value when in a normal state; the GPIO port is also used to determine that the control software is in an abnormal state when the counting value is the preset value.

[0064] For example, the counter starts counting from a preset initial value (such as 10), and the count value is decreasing, that is, the count value is 10, 9, 8, etc. in sequence, until it reaches a preset value, which is 0, for example.

[0065] When the control software is working normally, it also controls the counter so that the count value of the counter is not the preset value. Taking the preset value as 0 as an example, the control software can preset the control logic so that the count value restarts counting from the initial value (such as 10) before reaching the preset value (such as when the count value is 1).

[0066] The GPIO port outputs a normal signal when the count value is not the preset value, that is, when the count value is not 0, the GPIO port outputs a low-level signal. At this time, the PNP transistor is in the cut-off state, the power supply and the control end of the fan are disconnected, and the power supply does not control the fan, but the control software controls the fan.

[0067] When an abnormality occurs in the control software, the control software loses control of the counter. Therefore, the count value of the counter will reach a preset value. After the count value of the counter reaches the preset value, the GPIO port outputs a high-level signal, the PNP transistor is in a conducting state or an amplified state, the power supply is connected to the control end of the fan, and the power supply controls the fan.

[0068] In this embodiment, a counter is set, and the control software can control the count value of the counter not to be a preset value under normal circumstances. For this reason, the GPIO port can determine that the control software is in an abnormal state when the count value of the counter reaches the preset value, and then output a high-level signal as an abnormal signal. For this reason, the control of the switching element can be achieved in hardware, which is simpler and more efficient.

[0069] In terms of deployment, the control software is the built-in software of the BMC, that is, the control software is located on the BMC. Figure 2 As shown, the counter and GPIO port can also be set on the BMC, which can improve integration and processing efficiency.

[0070] Figure 3 is a schematic diagram according to a third embodiment of the present disclosure. This embodiment provides a control system.

[0071] like Figure 3 As shown, the control system 300 includes: a control element 301 and a switch element 302 .

[0072] In this embodiment, the switch element 302 is a PNP transistor as an example.

[0073] The control element 301 generates an abnormal signal by software.

[0074] To this end, the control element 301 may be a programmable element, which is used to determine that the control software is in an abnormal state and generate the abnormal signal when the state signal sent by the control software does not meet a preset condition.

[0075] Programmable elements may specifically include: Complex Programmable Logic Device (CPLD), Field Programmable Gate Array (FPGA), etc.

[0076] like Figure 3 As shown, the programmable element takes CPLD as an example.

[0077] The server's motherboard has a built-in CPLD, which can be programmed so that when the status signal sent by the control software does not meet the preset conditions, the CPLD determines that the control software is in an abnormal state and generates an abnormal signal. Conversely, when the status signal sent by the control software meets the preset conditions, the CPLD determines that the control software is in a normal state and generates a normal signal.

[0078] The CPLD is connected to the control software to detect whether the control software is abnormal; and the CPLD is also connected to the B pole of the PNP transistor to output an abnormal signal to the B pole of the PNP transistor when the control software is abnormal, otherwise, when the control software is normal, it outputs a normal signal to the B pole of the PNP transistor. Specifically, the abnormal signal can be a high-level signal, and the normal signal is a low-level signal.

[0079] The E pole of the PNP transistor is connected to the power supply, and the C pole is connected to the control end of the fan. When the B pole receives an abnormal signal, the E pole and the C pole are connected, and at this time, the fan is controlled by the power supply; when the B pole receives a normal signal, the E pole and the C pole are disconnected, and the power supply cannot control the fan.

[0080] In this embodiment, programmable elements are used to control switch elements, which can improve flexibility and reuse existing programmable elements to save resources.

[0081] The programmable component determines whether the control software is abnormal based on the status signal sent by the control software.

[0082] Figure 4 It is a schematic diagram of a status signal between control software and CPLD provided according to an embodiment of the present disclosure. In this embodiment, the status signal is taken as a heartbeat signal as an example.

[0083] The status signal may be a heartbeat signal. When the control software is working normally, it may send a heartbeat signal at a set period (such as 10 seconds), that is, a data packet with a small amount of data may be sent once every set period through the data port on the BMC. At this time, if the programmable component detects that the control software does not send a heartbeat signal at the set period, it can be determined that the control software is in an abnormal state, thereby generating an abnormal signal; otherwise, if the programmable component detects a heartbeat signal sent at the set period, it can be determined that the control software is in a normal state, thereby generating a normal signal.

[0084] In this embodiment, the programmable component detects whether the control software is abnormal through the heartbeat signal, which can easily and efficiently determine whether the control software is abnormal.

[0085] Figure 5It is a schematic diagram of another state signal between the control software and the CPLD according to an embodiment of the present disclosure. In this embodiment, the state signal is taken as an example of a high level signal and a low level signal.

[0086] The status signal may also be a high level signal and a low level signal sent by the control software through the GPIO port on the BMC, and when the control software is in a normal state, the high level signal and the low level signal are switched according to a preset period (such as 10 seconds). At this time, the programmable element is connected to the GPIO port of the BMC. If it is detected that the high level signal and the low level signal output by the GPIO port are not switched according to the set period, it can be determined that the control software is in an abnormal state, thereby generating an abnormal signal.

[0087] In this embodiment, the programmable element detects whether the control software is abnormal through periodically switching high-level signals and low-level signals. The high-level signals and low-level signals output by the GPIO port can be used, without generating additional data packets, thus saving resources.

[0088] In terms of deployment, the control software is the built-in software of the BMC, that is, the control software is located on the BMC. Figure 3 As shown, the programmable element can be set outside the BMC, and specifically can be an existing programmable element on the mainboard, so that existing resources can be reused to improve resource reusability.

[0089] Figure 6 It is a schematic diagram according to the fourth embodiment of the present disclosure. This embodiment provides a server.

[0090] like Figure 6 As shown, the server 600 includes: a chassis 601 ; a fan 602 , a power supply 603 and a control system 604 arranged in the chassis 601 .

[0091] The control system 603 is as shown in any of the above embodiments.

[0092] In this embodiment, the control element generates an abnormal signal when an abnormality occurs in the control software, and the switch element connects the power supply and the control end of the fan according to the abnormal signal. In this way, when an abnormality occurs in the controller, the fan is controlled by the power supply, which can achieve heat dissipation disaster recovery processing, improve heat dissipation stability, and then improve the stability of the server to avoid affecting business operations.

[0093] It can be understood that in the embodiments of the present disclosure, the same or similar contents in different embodiments can be referenced to each other.

[0094] It can be understood that the “first”, “second”, etc. in the embodiments of the present disclosure are only used for distinction and do not indicate the degree of importance, time sequence, etc.

[0095] It can be understood that in the embodiments of the present disclosure, the directions or positional relationships indicated by "up", "down", "left", "right", "front", "back", "inside", "outside", "top", "bottom", "vertical", "horizontal", etc. are based on the directions or positional relationships shown in the accompanying drawings, and are only used to illustrate the relative positional relationships between the various components or components, and do not particularly limit the specific installation orientation of the various components or components.

[0096] In addition, some of the above terms may be used to express other meanings in addition to indicating orientation or positional relationship. For example, the term "on" may also be used to express a certain dependency or connection relationship in some cases. For those skilled in the art, the specific meanings of these terms in this disclosure can be understood according to specific circumstances.

[0097] In addition, the terms "installed", "set", "provided with", "provided with", "connected", and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral structure; it can be a mechanical connection, or an electrical connection; it can be a direct connection, or an indirect connection through an intermediate medium, or it can be an internal connection between two devices, elements, or components. For those skilled in the art, the specific meanings of the above terms in the embodiments of the present disclosure can be understood according to specific circumstances.

[0098] In addition, the shapes, structures, proportions, sizes, etc. drawn in the drawings of the present disclosure are only used to match the contents disclosed in the specification so that those skilled in the art can understand and read them, and are not used to limit the conditions under which the present disclosure can be implemented. Any modification of shape or structure, change in proportion or adjustment of size should still fall within the scope of the technical contents disclosed in the present disclosure without affecting the effects and purposes that can be achieved by the present disclosure.

[0099] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A control system, comprising: A control element, used to generate an abnormal signal when the control software is in an abnormal state; The control software is used to control the fan when in a normal state; A switch element is used to connect the power supply and the fan according to the abnormal signal, so as to control the fan through the power supply.

2. The system according to claim 1, wherein: The switch element is a PNP transistor, and the base of the PNP transistor is used to input the abnormal signal, the emitter of the PNP transistor is connected to the power supply, and the collector of the PNP transistor is connected to the control end of the fan.

3. The system according to claim 1, wherein: The control element comprises: The GPIO port is used to generate a high-level signal when the control software is in an abnormal state, and the high-level signal is used as an abnormal signal.

4. The system according to claim 3, wherein: The control element also includes: A counter, used to perform a counting operation to obtain a count value, and the control software is also used to control the count value not to be a preset value when in a normal state; The GPIO port is further used to determine that the control software is in an abnormal state when the count value is the preset value.

5. The system according to claim 3, wherein: The control software, the counter and the GPIO port are all located on the BMC.

6. The system according to claim 1, wherein: The control element comprises: The programmable element is used to determine that the control software is in an abnormal state and generate the abnormal signal when the state signal sent by the control software does not meet the preset conditions.

7. The system according to claim 6, wherein: The state signal is a heartbeat signal, and the control software is further used to send the heartbeat signal according to a preset period when in a normal state; The programmable element is further configured to: If the heartbeat signal is not received according to the preset period, it is determined that the control software is in an abnormal state, and the abnormal signal is generated.

8. The system according to claim 6, wherein: The state signal includes: a high level signal and a low level signal sent by the control software through the GPIO port on the BMC, and the high level signal and the low level signal are switched according to a preset period when the control software is in a normal state; The programmable element is further configured to: If the received high level signal and the received low level signal are not switched according to the preset cycle, it is determined that the control software is in an abnormal state, and the abnormal signal is generated.

9. The system according to claim 6, wherein: The control software is located on the BMC, and the BMC is located on the mainboard; The programmable element is located on the main board and outside the BMC.

10. A server, comprising: Chassis; A fan, a power supply and a control system are arranged in the chassis; Wherein, the control system is as described in any one of claims 1-9.

Images