Power failure monitoring circuit, distributed storage cluster server and distributed storage server cluster

Abstract

The invention discloses a power failure monitoring circuit, a distributed storage cluster server and a distributed storage server cluster, and the power failure monitoring circuit controls an energy storage module to supply power to a control module and a communication module when monitoring that an external power supply of the server is disconnected; and the communication module sends a power failure signal to other servers in the distributed storage server cluster, so that the other servers can take over the service of the server in time after receiving the data packet, and the cluster service is ensured not to be interrupted.

Description

Technical Field

[0001] The present invention relates to the field of server power failure monitoring, and in particular to a power failure monitoring circuit, a distributed storage cluster server and a distributed storage server cluster. Background Art

[0002] A distributed storage server cluster is generally composed of three or more servers, which are responsible for business processing. At the same time, the three devices send an LLDP data packet through the network port every 30 seconds. The LLDP data packet encapsulates the management address, device identification and interface identification, as well as user-defined information; other servers can receive the data packet through the switch to determine whether the device is working properly, such as Figure 1 However, once a server is powered off, it takes 30 seconds for other devices to be aware of it, which will cause other servers in the cluster to be unable to take over the services of the device in time. Summary of the invention

[0003] The present invention provides a power failure monitoring circuit and a power failure monitoring circuit, a distributed storage cluster server and a distributed storage server cluster, which are used to solve the technical problem that the existing distributed storage server cluster cannot timely detect server power failure, resulting in other servers in the cluster being unable to timely take over the business of the device.

[0004] In order to solve the above technical problems, the technical solution proposed by the present invention is: A power failure monitoring circuit is applied to a distributed storage cluster server, comprising: an energy storage module, a first switch, a second switch, a control module and a communication module, wherein the energy storage module is connected to an external power supply of the distributed storage cluster server, the energy storage module is respectively connected to the control module and the communication module power supply through the first switch, the external power supply is respectively connected to the control module and the communication module power supply through the second switch, and the control module is respectively connected to the external power supply and the communication module signal; The control module is connected to the control ends of the first switch and the second switch respectively; the control module is used to monitor whether the external power supply is disconnected, and when the external power supply is detected to be disconnected, the first switch is turned on and the second switch is turned off, and the communication module is notified to power off in an interrupt manner; The energy storage module is used to supply power to the control module and the communication module when the first switch is turned on; The communication module is used to send a power-off signal to other servers in the distributed storage server cluster when the control module is interrupted.

[0005] Preferably, the energy storage module is a supercapacitor, the supercapacitor is connected to the external power supply via a charging chip, and the external power supply charges the supercapacitor via the charging chip.

[0006] Preferably, the control module is a CPLD, and a signal end of the CPLD is connected to an AC_OK pin of the external power supply.

[0007] Preferably, the first switch and the second switch are both MOS tubes.

[0008] Preferably, it also includes a first power chip and a second power chip, the first switch and the second switch are both connected to the power end of the CPLD through the first power chip, and the first switch and the second switch are both connected to the power end of the communication module through the second power chip.

[0009] Preferably, the communication module is a network port chip, and the network port chip communicates with other servers in other distributed storage clusters through a switch, and the power-off signal is a preset LLDP data packet.

[0010] A distributed storage cluster server comprises the above-mentioned power failure monitoring circuit.

[0011] A distributed storage server cluster comprises the above-mentioned power failure monitoring circuit.

[0012] The present invention has the following beneficial effects: 1. When the present invention detects that the external power supply of the server is disconnected, the energy storage module is controlled to supply power to the control module and the communication module; the communication module is caused to send a power-off signal to other servers in the distributed storage server cluster, so that other servers can take over the services of the server in time after receiving the data packet, thereby ensuring that the cluster services are not interrupted.

[0013] In addition to the above-described purposes, features and advantages, the present invention has other purposes, features and advantages. The present invention will be further described in detail below with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The drawings constituting a part of this application are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings: Figure 1 It is a simplified structural diagram of a distributed storage server cluster; Figure 2 This is a simplified structural diagram of a distributed storage cluster server in a preferred embodiment of the present invention. In the figure, G represents a gate, S represents a source, and D represents a drain. DETAILED DESCRIPTION

[0015] The embodiments of the present invention are described in detail below with reference to the accompanying drawings, but the present invention can be implemented in many different ways as defined and covered by the claims.

[0016] Embodiment 1: like Figure 2 As shown, this embodiment discloses a power failure monitoring circuit, which is applied to a distributed storage cluster server, including: an energy storage module, a first switch, a second switch, a control module and a communication module, wherein the energy storage module is connected to an external power supply of the distributed storage cluster server, the energy storage module is respectively connected to the control module and the communication module power supply through the first switch, the external power supply is respectively connected to the control module and the communication module power supply through the second switch, and the control module is respectively connected to the external power supply and the communication module signal; The control module is connected to the control ends of the first switch and the second switch respectively; the control module is used to monitor whether the external power supply is disconnected, and when the external power supply is detected to be disconnected, the first switch is turned on and the second switch is turned off, and the communication module is notified to power off in an interrupt manner; The energy storage module is used to supply power to the control module and the communication module when the first switch is turned on; The communication module is used to send a power-off signal to other servers in the distributed storage server cluster when the control module is interrupted.

[0017] In a preferred embodiment, the energy storage module is a supercapacitor, the supercapacitor is connected to the external power source via a charging chip, and the external power source charges the supercapacitor via the charging chip.

[0018] Supercapacitors are a new type of energy storage device between traditional capacitors and batteries. They have both the fast charging and discharging characteristics of capacitors and the energy storage characteristics of batteries. The capacitance of supercapacitors reaches the Farad level, which is hundreds or even millions of times that of traditional capacitors. The volume of supercapacitors is slightly larger than that of ordinary capacitors, but much smaller than that of batteries. At the same time, supercapacitors inherit the advantages of traditional capacitors such as high power density, short charging and discharging time, wide temperature range, and long life, and can be recycled repeatedly.

[0019] In a preferred solution, the control module is a CPLD, and a signal end of the CPLD is connected to an AC_OK pin of the external power supply.

[0020] In a preferred solution, both the first switch and the second switch are MOS transistors (ie, MOS transistors B and A).

[0021] In the preferred embodiment, it also includes a first power chip and a second power chip, the first switch and the second switch are both connected to the power end of the CPLD through the first power chip, and the first switch and the second switch are both connected to the power end of the communication module through the second power chip.

[0022] In a preferred solution, the communication module is a network port chip, the network port chip communicates with other servers in other distributed storage clusters through a switch, and the power-off signal is a preset LLDP data packet.

[0023] LLDP (Link Layer Discovery Protocol) is an IEEE standard protocol (IEEE 802.1AB) that defines messages encapsulated in Ethernet frames with the purpose of providing a way for devices to announce basic device information to other devices on a LAN (Local Area Network) by periodically retransmitting from each port every 30 seconds by default. It is a standardized protocol similar to CDP. It is a vendor-independent link layer protocol used for network topology, troubleshooting, and network management automation.

[0024] The present invention ensures that the network port chip can immediately send a preset LLDP data packet containing a power-off signal after receiving an interruption by constructing a charging circuit using a supercapacitor as an emergency power supply. After the external power supply is powered on normally, the supercapacitor will be charged through the charging circuit. The CPLD monitors the AC_OK signal of the external power supply in real time. Once the external power supply is disconnected, the CPLD can timely control the MOS tube B to turn on and turn off the MOS tube A, allowing the supercapacitor to power the CPLD and the network port, thereby ensuring that the network port chip can normally complete the sending of the preset LLDP data packet when the external power is off.

[0025] In addition, in this embodiment, a distributed storage cluster server is also disclosed, which includes the above-mentioned power failure monitoring circuit.

[0026] In addition, in this embodiment, a distributed storage server cluster is also disclosed, including the above-mentioned power failure monitoring circuit.

[0027] In this embodiment, the working process of the power failure monitoring circuit is as follows: The CPLD chip on the motherboard is used to control the conduction of the two MOS tubes. Under normal startup conditions, MOS tube B is not conducting, while MOS tube A is conducting normally. When the external power supply of the server is normal, MOS tube A is conducting normally, and the external power supply supplies power to the motherboard CPLD and the network port chip. In addition, the power supply will charge the supercapacitor through the charging chip. The CPLD will always monitor the AC_OK signal sent by the external power supply. The signal is high when the external power supply is normal and low when the external power supply is disconnected.

[0028] Once the external power supply is disconnected, the AC_OK signal immediately changes to a low level. After the CPLD receives the low-level AC_OK signal, it immediately turns on the MOS tube B through the CTRL2 signal and turns off the MOS tube A. The supercapacitor continues to supply power to the CPLD and the network port circuit through the MOS tube to ensure that the network port circuit can continue to work for a period of time. After the CPLD receives the low-level AC_OK signal, it immediately notifies the network port chip through an interrupt. After receiving the interrupt, the network port chip immediately sends a preset LLDP data packet to the outside. The whole process does not exceed 3 milliseconds. As a result, other servers in the storage system can take over the services of the server in a timely manner after receiving the data packet, ensuring that the cluster service is not interrupted.

[0029] In summary, the present invention adds a super capacitor and a charging control chip to the server motherboard. When the external power supply is disconnected, the CPLD controls the MOS tube to conduct, so that the super capacitor supplies power to the CPLD and the network port chip, ensuring that the network port chip can continue to work for a period of time. The power supply status is monitored in real time by the CPLD, and the network port chip is notified by interruption, so that the network port chip can immediately send a preset LLDP data packet. After receiving the preset LLDP data packet, other servers in the cluster can take over the business of the power-off server in time to ensure that the cluster business is not interrupted.

[0030] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A power failure monitoring circuit, applied to a distributed storage cluster server, characterized in that: include: An energy storage module, a first switch, a second switch, a control module and a communication module, wherein the energy storage module is connected to an external power supply of a distributed storage cluster server, the energy storage module is respectively connected to the control module and the communication module power supply through the first switch, the external power supply is respectively connected to the control module and the communication module power supply through the second switch, and the control module is respectively connected to the external power supply and the communication module signal; The control module is connected to the control ends of the first switch and the second switch respectively; the control module is used to monitor whether the external power supply is disconnected, and when the external power supply is detected to be disconnected, the first switch is turned on and the second switch is turned off, and the communication module is notified to power off in an interrupt manner; The energy storage module is used to supply power to the control module and the communication module when the first switch is turned on; The communication module is used to send a power-off signal to other servers in the distributed storage server cluster when the control module is interrupted.

2. The power failure monitoring circuit according to claim 1, characterized in that: The energy storage module is a supercapacitor, the supercapacitor is connected to the external power source through a charging chip, and the external power source charges the supercapacitor through the charging chip.

3. The power failure monitoring circuit according to claim 1, characterized in that: The control module is a CPLD, and a signal end of the CPLD is connected to an AC_OK pin of the external power supply.

4. The power failure monitoring circuit according to claim 3, characterized in that: The first switch and the second switch are both MOS tubes.

5. The power failure monitoring circuit according to claim 4, characterized in that: It also includes a first power chip and a second power chip. The first switch and the second switch are both connected to the power end of the CPLD through the first power chip, and the first switch and the second switch are both connected to the power end of the communication module through the second power chip.

6. The power failure monitoring circuit according to claim 5, characterized in that: The communication module is a network port chip, and the network port chip communicates with other servers in other distributed storage clusters through a switch, and the power-off signal is a preset LLDP data packet.

7. A distributed storage cluster server, characterized in that: The invention comprises the power-off monitoring circuit described in any one of claims 1 to 6.

8. A distributed storage server cluster, characterized in that: The invention comprises the power-off monitoring circuit described in any one of claims 1 to 6.

Images