CN103576819B - Server starts control system, method and device on a large scale - Google Patents

Abstract

The present invention proposes a large-scale start-up control system for servers, including: multiple servers; a power supply for supplying power to multiple servers; After power-on, a corresponding delay time is generated according to the unique identifier of the corresponding server, and the corresponding server is controlled to start after the delay time elapses. The present invention also proposes a large-scale start-up control method for servers, including: receiving start-up signals for multiple servers; calculating the corresponding delay time of each server according to the unique identifier of each server; After that, control the server startup. The invention also proposes a system controller for a server. The invention avoids the maximum instantaneous power exceeding the rated power of the power supply caused by restarting of the server group during the restarting process of the power supply by setting different delayed startup times for multiple servers.

Description

Server large-scale startup control system, method and device

technical field

The invention relates to the technical field of server management, in particular to a server large-scale start-up control system and method, and a power controller.

Background technique

In the existing DC power supply for servers, there is no 100% guarantee of uninterrupted power supply for servers. Once the power supply of the server group is powered off and the power supply is restored, the server needs to establish an output voltage level that did not exist at the moment of startup (energy storage, starting from scratch, requiring high-current power supply), and will reach the output voltage level at a certain moment of startup. Instantaneous maximum power. If there are no corresponding protection measures, the instantaneous power of the servers in the entire cabinet may be far greater than the rated power when the server is running. Insufficient power may cause the server to restart repeatedly.

The existing large-scale start-up control technology for processing servers is mainly aimed at optimizing the power supply and power-on power consumption, but the points and details are different from those of the present invention. Realize the processing of power supply and load in different situations. When the total power supply is not enough for the load to start up, the existing patented processing method is to select the optimal number of start-ups. Compared with the present invention, this existing patent is logically too complicated and loaded down with trivial details due to different control methods and targeted problems.

Contents of the invention

The present invention aims at solving one of the above technical problems at least to a certain extent or at least providing a useful commercial choice.

For this reason, the first object of the present invention is to propose a large-scale startup control system for servers, which generates a random number to control the power supply through the logical operation unit of the server, and completes the startup delay of the server, thereby avoiding the server at the same time. The maximum instantaneous current to start. The second object of the present invention is to propose a method for controlling large-scale startup of servers. The third object of the present invention is to provide a power controller for a server.

In order to achieve the above object, the embodiment of the first aspect of the present invention proposes a server large-scale start-up control system, including: a plurality of servers; a power supply, which supplies power to the plurality of servers; a plurality of power controllers, each One or more of the power controllers are connected between one or more of the servers and the power supply, and the power controller is configured to generate a corresponding delay time according to the unique identifier of the corresponding server after the power supply is powered on , and control the corresponding server to start after the delay time elapses.

According to the server large-scale start-up control system of the embodiment of the present invention, by setting different delayed start times for multiple servers, it is possible to avoid simultaneous restart of each server during the restart process after power failure, reach the maximum instantaneous power, and avoid server group restart As a result, the power exceeds the rated power of the power supply, which improves the starting efficiency and service life of the server group, and the present invention makes little changes to the hardware of the server, saves costs, and has no adverse effect on the stability of the server group.

In an embodiment of the present invention, the unique identifier of the server includes one or more of the above-mentioned server's IP address, MAC address and serial number SN.

In one embodiment of the present invention, the power controller is a programmable logic unit CPLD.

In an embodiment of the present invention, the unique identifier of the server is stored in a corresponding power controller.

In one embodiment of the present invention, the delay time=(MAC value+SN value)%n, wherein, the MAC value is the value of the MAC address of the server, the SN value is the serial number of the server, and n is based on The ratio between the maximum instantaneous power of the server group and the rated power of the power supply is determined.

In an embodiment of the present invention, the power controller is further configured to record the delay time, and read the delay time when the server starts next time.

The embodiment of the second aspect of the present invention proposes a large-scale start-up control method for servers, including: receiving a start-up signal for multiple servers; calculating the corresponding delay time of each server according to the unique identifier of each server; After the server's delay time expires, the corresponding server is controlled to start.

According to the server large-scale start-up control method of the embodiment of the present invention, by setting different delayed start times for multiple servers, it is realized that all servers are prevented from restarting at the same time during the restart process after power failure, reaching the maximum instantaneous power, and avoiding server group restart As a result, the power exceeds the rated power of the power supply, which improves the starting efficiency and service life of the server group, and the present invention makes little changes to the hardware of the server, saves costs, and has no adverse effect on the stability of the server group.

In an embodiment of the present invention, the unique identifier of the server includes one or more of the above-mentioned server's IP address, MAC address and serial number SN.

In one embodiment of the present invention, the delay time=(MAC value+SN value)%n, wherein, the MAC value is the value of the MAC address of the server, the SN value is the serial number of the server, and n is based on The ratio between the maximum instantaneous power of the server group and the rated power of the power supply is determined.

The embodiment of the third aspect of the present invention provides a power controller for a server, including: a detection module, used to detect whether the power supply connected to the power controller is powered on; a storage module, used to store the A unique identifier of the server connected to the power controller; a calculation module, configured to calculate a corresponding delay time according to the unique identifier; a control module, configured to control the server to start after the delay time has elapsed.

According to the power controller for the server in the embodiment of the present invention, by setting the delay start time for the server, the specific start timing of the server can be controlled, which provides an effective solution for the restart recovery strategy of the server group after power failure.

In an embodiment of the present invention, the unique identifier of the server includes one or more of the above-mentioned server's IP address, MAC address and serial number SN.

In one embodiment of the present invention, the power controller is a programmable logic unit CPLD.

In one embodiment of the present invention, the delay time=(MAC value+SN value)%n, wherein, the MAC value is the value of the MAC address of the server, the SN value is the serial number of the server, and n is based on The ratio between the maximum instantaneous power of the server group and the rated power of the power supply is determined.

In an embodiment of the present invention, the storage module is also used to record the delay time, and provide the control module to read when the server starts up next time.

Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.

Description of drawings

The above and/or additional aspects and advantages of the present invention will become apparent and easy to understand from the following description of the embodiments in conjunction with the accompanying drawings, wherein:

FIG. 1 is a schematic diagram of a server large-scale startup control system according to an embodiment of the present invention;

Fig. 2 is the layout schematic diagram of the CPLD in the server motherboard according to one embodiment of the present invention;

FIG. 3 is a flow chart of a method for controlling large-scale startup of servers according to an embodiment of the present invention;

Fig. 4 is the flow chart of recovery operation after the server group is powered off according to one embodiment of the present invention; And

FIG. 5 is a schematic diagram of a power controller for a server according to an embodiment of the present invention.

detailed description

Embodiments of the present invention are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals designate the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary only for explaining the present invention and should not be construed as limiting the present invention.

In describing the present invention, it should be understood that the terms "longitudinal", "transverse", "upper", "lower", "front", "rear", "left", "right", "vertical", The orientation or positional relationship indicated by "horizontal", "top", "bottom", "inner", "outer", etc. are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than Nothing indicating or implying that a referenced device or element must have a particular orientation, be constructed, and operate in a particular orientation should therefore not be construed as limiting the invention.

In the description of the present invention, it should be noted that unless otherwise specified and limited, the terms "installation", "connection" and "connection" should be understood in a broad sense, for example, it can be a mechanical connection or an electrical connection, or it can be two The internal communication of each element may be directly connected or indirectly connected through an intermediary. Those skilled in the art can understand the specific meanings of the above terms according to specific situations.

The following describes a server large-scale startup control system according to an embodiment of the present invention with reference to FIG. 1 and FIG. 2 .

As shown in Figure 1, the server large-scale start-up control system according to the embodiment of the first aspect of the present invention includes: multiple servers 101; power supply 102, power supply 102 supplies power for multiple servers 101; A power controller 103 is connected between a server 101 and the power supply 102, and the power controller 103 is used to generate a corresponding delay time according to the unique identification of the corresponding server 101 after the power supply 102 is powered on, and after passing through the delay time The corresponding server 101 is controlled to start.

Wherein, the unique identifier of the server 101 may include: one or more combinations of the server 101's IP address, MAC address, and serial number SN.

Specifically, the power controller 103 may use a programmable logic unit CPLD (Complex Programmable Logic Device), and the CPLD obtains the unique identifier of the server 101, wherein the unique identifier includes a MAC address (Media Access Control, hardware address) and an SN (SerialNumber, serial number ), etc., and store the unique identifier. The calculation formula for CPLD to calculate the delay time according to the unique identification of server 101 is:

t=(MAC+SN)%n

Among them, t is the delay time, the MAC value is the value of the MAC address of the server, the SN value is the serial number of the server, and n is determined according to the ratio of the maximum instantaneous power of the server group to the rated power of the power supply. After calculating the delay time, the CPLD records the delay time and reads the delay time when the server group starts next time. When starting the server group, after the power is turned on, the CPLD waits for the delay time to end, then turns on the power of the corresponding server 101, and starts the server 101.

In one embodiment of the present invention, a CPLD is added between the power supply and the server as an enable to control the access of the server power supply. Because there are many servers, a server group can be controlled by several CPLDs. The clocks of all CPLDs in a server group can provide the clocks of each CPLD through one server in the server group, so that the synchronization of each CPLD clock can be guaranteed, and when the delay time is set, it can be achieved between each CPLD. The purpose of time synchronization.

FIG. 2 is a schematic layout diagram of a CPLD in a server motherboard according to an embodiment of the present invention. Figure 2 shows the logical location layout of the CPLD as the power control unit of the server on the server motherboard. Add corresponding power control codes to the existing CPLD controllers in all servers, so that the CPLD completes the delay control of the server power supply. It is worth noting that CPLD is the power management controller of the server and is the hardware in the server. The present invention only needs to add the corresponding control program in the CPLD that manages the power supply on the server, and the inventive effect of the present invention can be achieved, that is, different delay start times are set for multiple servers, so as to avoid the delay of each server during the restart process after power failure. Restart at the same time to reach the maximum instantaneous power. The CPLD includes the control of server power supply management, and the present invention only adds the random number delayed start technology to the original hardware of the server. In the hardware part, the CPLD is located between the low-power device and the high-power device, and controls the random number startup of the high-power device on the server board.

According to the server large-scale start-up control system of the embodiment of the present invention, by setting different delayed start times for multiple servers, it is possible to avoid simultaneous restart of each server during the restart process after power failure, reach the maximum instantaneous power, and avoid server group restart The power exceeds the rated power of the power supply, which improves the startup efficiency and service life of the server group, and the present invention does not need to add new hardware to complete the control of the server, and the hardware changes are very small, which saves costs and has no adverse effects on the stability of the server group influences.

As shown in Figure 3, the server large-scale start-up control method according to the embodiment of the second aspect of the present invention includes the following steps:

S301: Receive a start signal for multiple servers.

When the power supply is powered on, each power controller connected between the power supply and the server will receive a start signal to the server. In one embodiment of the present invention, the power controller adopts a programmable logic unit CPLD.

S302: Calculate the corresponding delay time of each server according to the unique identifier of each server.

Wherein, the unique identifier of the server may include: one or more combinations of the server's IP address, MAC address, and serial number SN.

The formula for calculating the delay time is:

t=(MAC+SN)%n

Among them, t is the delay time, the MAC value is the value of the MAC address of the server, the SN value is the serial number of the server, and n is determined according to the ratio of the maximum instantaneous power of the server group to the rated power of the power supply.

S303: After the delay time of each server ends, control the corresponding server to start.

From the calculation formula of the delay time in step S302, it can be known that since the MAC value and SN value of each server are unique, from the perspective of probability, the delay time values of each server should be evenly distributed between 0~n-1 Therefore, each server waits for its own delay time before starting, which can effectively distribute the number of servers started at each time, thus effectively avoiding the problem that too many servers start at the same time, causing the power to exceed the rated power of the power supply .

FIG. 4 is a flow chart of recovery operations when a power outage occurs during the work of a server group according to an embodiment of the present invention.

S401: When the power supply is normal, each server runs normally.

S402: Burn the MAC address and serial number SN of each server connected to the CPLD into the CPLD, and make a one-to-one correspondence with each server.

S403: CPLD calculates the delay time of each server through the MAC address and SN of the server, that is, obtains the random number corresponding to each machine through the MAC address and SN, and the calculation formula is as follows:

t=(MAC+SN)%n

Among them, t is the delay time, the MAC value is the value of the MAC address of the server, the SN value is the serial number of the server, and n is determined according to the ratio of the maximum instantaneous power of the server group to the rated power of the power supply.

The CPLD saves the calculated delay time and waits for the power to restart after power failure.

S404: Monitor the status of the power supply in real time. If the power supply is cut off, perform S405; if the power supply is not cut off, maintain the monitoring status of the power supply.

S405: The recovery process of the server group starts. CPLD detects various hardware parameters of the server.

S406: The CPLD reads the delay time calculated in step S403, and starts timing.

S407: When the delay time of a certain server connected to the CPLD ends, the CPLD turns on the power of the server and starts the server.

It is worth noting that, in the embodiment of the present invention, the CPLD not only completes the logic control shown in FIG. 4 , but also completes control such as the management of the server power supply, but this is omitted in the embodiment of the present invention.

According to the server large-scale start-up control method of the embodiment of the present invention, by setting different delayed start times for multiple servers, it is realized that all servers are prevented from restarting at the same time during the restart process after power failure, reaching the maximum instantaneous power, and avoiding server group restart As a result, the power exceeds the rated power of the power supply, which improves the starting efficiency and service life of the server group, and the present invention makes little changes to the hardware of the server, saves costs, and has no adverse effect on the stability of the server group.

As shown in FIG. 5 , the power controller for a server according to the embodiment of the third aspect of the present invention includes: a detection module 510 , a storage module 520 , a calculation module 530 and a control module 540 .

Specifically, the detection module 510 is used to detect whether the power supply connected to the power controller is powered on. The storage module 520 is used for storing the unique identification of the server connected to the power controller. The calculation module 530 is configured to calculate a corresponding delay time according to the unique identifier. The control module 540 is used to control the corresponding server to start after the delay time elapses.

Wherein, the unique identifier of the server may include: one or more combinations of the server's IP address, MAC address, and serial number SN.

Specifically, the power controller may use a programmable logic unit CPLD. The calculation module 530 of CPLD calculates the delay time of the server connected with CPLD

t=(MAC+SN)%n

Among them, t is the delay time, the MAC value is the value of the MAC address of the server, the SN value is the serial number of the server, and n is determined according to the ratio of the maximum instantaneous power of the server group to the rated power of the power supply. After the delay time is calculated, the delay time is stored in the storage module 520. After the detection module 510 detects that the power is turned on next time, the control module 540 reads the delay time, and after waiting for the delay time to end, controls the corresponding server to start .

According to the power controller for the server in the embodiment of the present invention, by setting the delay start time for the server, the specific start timing of the server can be controlled, which provides an effective solution for the restart recovery strategy of the server group after power failure.

Any process or method descriptions in flowcharts or otherwise described herein may be understood to represent modules, segments or portions of code comprising one or more executable instructions for implementing specific logical functions or steps of the process , and the scope of preferred embodiments of the invention includes alternative implementations in which functions may be performed out of the order shown or discussed, including substantially concurrently or in reverse order depending on the functions involved, which shall It is understood by those skilled in the art to which the embodiments of the present invention pertain.

The logic and/or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium, For use with an instruction execution system, device, or device (such as a computer-based system, a system including a processor, or other systems that can fetch instructions from an instruction execution system, device, or device and execute instructions), or in conjunction with such an instruction execution system, device or equipment for use. For the purposes of this specification, a "computer-readable medium" may be any device that can contain, store, communicate, propagate or transmit a program for use in or in conjunction with an instruction execution system, device or device. More specific examples (non-exhaustive list) of computer-readable media include the following: electrical connection with one or more wires (electronic device), portable computer disk case (magnetic device), random access memory (RAM), Read Only Memory (ROM), Erasable and Editable Read Only Memory (EPROM or Flash Memory), Fiber Optic Devices, and Portable Compact Disc Read Only Memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program can be printed, since the program can be read, for example, by optically scanning the paper or other medium, followed by editing, interpretation or other suitable processing if necessary. The program is processed electronically and stored in computer memory.

It should be understood that various parts of the present invention can be realized by hardware, software, firmware or their combination. In the above described embodiments, various steps or methods may be implemented by software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented by any one or combination of the following techniques known in the art: Discrete logic circuits, ASICs with suitable combinational logic gates, Programmable Gate Arrays (PGAs), Field Programmable Gate Arrays (FPGAs), etc.

Those of ordinary skill in the art can understand that all or part of the steps carried by the methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. During execution, one or a combination of the steps of the method embodiments is included.

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing module, each unit may exist separately physically, or two or more units may be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware or in the form of software function modules. If the integrated modules are realized in the form of software function modules and sold or used as independent products, they can also be stored in a computer-readable storage medium.

In the description of this specification, descriptions referring to the terms "one embodiment", "some embodiments", "example", "specific examples", or "some examples" mean that specific features described in connection with the embodiment or example , structure, material or characteristic is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

Although the embodiments of the present invention have been shown and described, those skilled in the art can understand that various changes, modifications and substitutions can be made to these embodiments without departing from the principle and spirit of the present invention. and modifications, the scope of the invention is defined by the appended claims and their equivalents.

Claims (8)

1. A server large-scale start-up control system, characterized in that, comprising: multiple servers; a power supply, the power supply supplies power to the plurality of servers; A plurality of power controllers, each of the power controllers is connected between one of the servers and the power supply, and the power controller is used to generate Corresponding delay time, and after the delay time, the corresponding server is controlled to start, the delay time=(MAC value+SN value)%n, wherein the MAC value is the value of the MAC address of the server, The SN value is the serial number of the server, and n is determined according to the ratio of the maximum instantaneous power of the server group to the rated power of the power supply. 2. The server large-scale start-up control system according to claim 1, wherein the power controller is a programmable logic unit (CPLD). 3. The server large-scale start-up control system according to claim 1, wherein the unique identifier of the server is stored in a corresponding power controller. 4. The server large-scale start-up control system according to claim 1, wherein the power controller is further configured to record the delay time, and read the delay time when the server is started next time. 5. A large-scale startup control method for servers, comprising the following steps: receiving start signals to multiple servers; Calculate the corresponding delay time of each server according to the unique identifier of each server respectively, and the delay time=(MAC value+SN value)%n, wherein, the MAC value is the value of the MAC address of the server, and the SN value is all The serial number of the server, n is determined according to the ratio of the maximum instantaneous power of the server group to the rated power of the power supply; and After each server's delay time has elapsed, the corresponding server is controlled to start. 6. A power controller for a server, comprising: A detection module, configured to detect whether the power supply connected to the power controller is powered on; a storage module, configured to store the unique identifier of the server connected to the power controller; A calculation module, configured to calculate a corresponding delay time according to the unique identifier, the delay time=(MAC value+SN value)%n, wherein the MAC value is the value of the MAC address of the server, and the SN value is the The serial number of the server, n is determined according to the ratio of the maximum instantaneous power of the server group to the rated power of the power supply; and A control module, configured to control the server to start after the delay time elapses. 7. The power controller for a server according to claim 6, wherein the power controller is a programmable logic unit (CPLD). 8 . The power controller of the server according to claim 6 , wherein the storage module is further configured to record the delay time, and provide the control module to read when the server starts next time.