Optimization method of accelerator server system and accelerator server system

Abstract

The optimization method of the accelerator server system comprises the following steps: respectively setting an independent storage device for each server; operating system files of a plurality of servers and data needing to be frequently read and written during operation are stored in each independent storage device; configuring each server, and starting and running by reading operating system files in respective independent storage equipment and data needing to be frequently read and written; establishing communication connection among a plurality of servers; and a plurality of servers are configured to realize a main-standby redundancy function. According to the optimization method of the accelerator server system provided by the invention, the accelerator runs more stably, and troubleshooting is easier. The invention further provides an accelerator server system for implementing the method.

Description

Technical Field

[0001] The present invention relates to the technical field of accelerators, and in particular to an optimization method for an accelerator server system and an accelerator server system. Background Art

[0002] The control system of large accelerators such as proton and heavy ion therapy accelerators is different from general industrial control systems. It controls high-energy accelerators. Large accelerators are large in scale, with a large number of equipment and a wide variety of types. The accelerator server system monitors and controls the accelerator equipment, displays operating parameters, and provides operators with a means of beam adjustment. General industrial server systems do not have high requirements for time response, with response times in seconds and minutes; however, the accelerator control system ultimately controls high-speed charged particles, which run at speeds close to the speed of light, so it requires extremely high control accuracy and real-time response speed.

[0003] Existing accelerator server systems usually have several servers and disk array devices. Each server does not have a separate storage device, but is connected to the disk array device through a network, and starts and runs programs by reading system files stored on the disk array device. Since the data in the disk array device is highly integrated, once the hardware related to data storage and data transmission begins to become unstable, it will cause micro-perturbations to the system with high time resolution requirements, and it is difficult to troubleshoot. Summary of the invention

[0004] The purpose of the present invention is to provide an optimization method for an accelerator server system, so that the accelerator runs more stably and troubleshooting is easier.

[0005] Another object of the present invention is to provide an accelerator server system to make the accelerator run more stably and to facilitate troubleshooting.

[0006] The present invention provides an optimization method for an accelerator server system, the accelerator server system includes several servers, and the optimization method includes:

[0007] Set up an independent storage device for each server;

[0008] Store operating system files of several servers and data that needs to be frequently read and written during operation in each independent storage device;

[0009] Configure each server to start and run by reading the operating system files and data that needs to be read and written frequently in its own independent storage device;

[0010] establishing communications links between the plurality of servers; and

[0011] Configure several servers to achieve active / standby redundancy.

[0012] The optimization method of the accelerator server system provided by the present invention sets an independent storage device for each server, and each server starts and runs by reading the operating system files and data that need to be frequently read and written in its own independent storage device, and establishes a communication connection between several servers to realize the main and standby redundancy function. Each server does not need to rely on a highly integrated disk array device, the operation is more stable, and it is easier to troubleshoot when a fault occurs in each independent storage device.

[0013] In another exemplary implementation of the optimization method of the accelerator server system, establishing a communication connection between several servers specifically includes:

[0014] Connecting several servers in series and connecting them end to end to form a ring communication structure; and

[0015] Configure each server so that it can communicate with the other servers in the chain.

[0016] Several servers form a ring communication structure. When there is a problem in the connection between any two servers, the communication between the servers can still be maintained, thereby improving the stability of the accelerator server system.

[0017] In another schematic implementation of the optimization method of the accelerator server system, each server is provided with a fiber optic communication module, and several servers are connected in series and end to end to form a ring communication structure, specifically, the servers are connected in series using optical fiber lines, and the server at the head end and the server at the end end are connected using optical fiber lines.

[0018] In another exemplary implementation of the optimization method of the accelerator server system, configuring several servers to implement active-standby redundancy functions specifically includes:

[0019] Configure each server to monitor the operating status of multiple servers in real time; and

[0020] When each server is configured to detect a server failure, a normally operating server will replace part or all of the functions of the failed server.

[0021] This balances the load between servers and further improves system stability.

[0022] In another exemplary implementation of the optimization method of the accelerator server system, the optimization method further includes:

[0023] A public storage device is set up, a communication connection is established between several servers and the public storage device, and several servers are configured to store data that does not need to be read and written frequently in the public storage device.

[0024] The present invention provides an accelerator server system, comprising a plurality of servers and a plurality of communication lines. Each server comprises an independent storage device, each independent storage device stores operating system files of the plurality of servers and data that needs to be frequently read and written during operation, and each server is configured to start and operate by reading the operating system files and data that needs to be frequently read and written in the respective independent storage devices; each communication line connects two servers, and the plurality of servers are configured to establish communication with the aid of the plurality of communication lines, and realize the primary-standby redundancy function.

[0025] In the accelerator server system provided by the present invention, each server is provided with an independent storage device, each server starts and runs by reading the operating system files and data that need to be frequently read and written in its own independent storage device, and establishes a communication connection between several servers to realize the main and standby redundancy function. Each server does not need to rely on a highly integrated disk array device, the operation is more stable, and it is easier to troubleshoot when a fault occurs in each independent storage device.

[0026] In another exemplary embodiment of the accelerator server system, several servers are connected in series and end-to-end to form a ring communication structure, and each server can establish communication with other servers in series. When several servers form a ring communication structure, when there is a problem in the connection between any two servers, the communication between the several servers can still be maintained.

[0027] In another exemplary embodiment of the accelerator server system, each server is provided with a fiber optic communication module, and each communication line is a fiber optic line capable of connecting to the fiber optic communication module.

[0028] In another exemplary embodiment of the accelerator server system, each server is configured to monitor the operating status of multiple servers in real time, and when a server failure is detected, a normally operating server replaces part or all of the functions of the failed server, thereby balancing the load between the servers and further improving the stability of the system.

[0029] In another exemplary embodiment of the accelerator server system, the accelerator server system further includes a public storage device, which establishes a communication connection with a plurality of servers, and each server is configured to store data that does not require frequent reading and writing in the public storage device. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The following drawings are only used to schematically illustrate and explain the present invention, and do not limit the scope of the present invention.

[0031] Figure 1 A flowchart of an exemplary implementation of an optimization method for an accelerator server system.

[0032] Figure 2A schematic diagram of an implementation of an optimization method for an accelerator server system.

[0033] Figure 3 A partial flow chart of the accelerator server system.

[0034] Figure 4 A partial flow chart of the accelerator server system.

[0035] Figure 5 A flow chart of another exemplary implementation of an optimization method for an accelerator server system.

[0036] Description of symbols

[0037] 10 Server

[0038] 12 Independent storage devices

[0039] 14 Fiber Optic Communication Module

[0040] 20 Communication lines DETAILED DESCRIPTION

[0041] In order to have a clearer understanding of the technical features, purposes and effects of the invention, the specific embodiments of the present invention are now described with reference to the accompanying drawings. The same reference numerals in the drawings represent components with the same structure or similar structures but the same functions.

[0042] In this document, “exemplary” means “serving as an example, instance or illustration”, and any diagram or implementation described in this document as “exemplary” should not be interpreted as a more preferred or more advantageous technical solution.

[0043] In order to simplify the drawings, each figure only schematically shows the parts related to the present invention, which do not represent the actual structure of the product.

[0044] Figure 1 A flowchart of an exemplary implementation of an optimization method for an accelerator server system. Figure 2 Schematic diagram of an implementation method of an optimization method for an accelerator server system. Figure 1 and Figure 2 The optimization method provided by the present invention is used for an accelerator server system, and the accelerator server system includes a plurality of servers 10. The optimization method includes the following S10 to S50:

[0045] S10: An independent storage device 12 is provided for each server 10. The independent storage device 12 is a high-speed hard disk provided inside each server 10 and is only used for reading and writing of the server 10.

[0046] S20: storing operating system files of several servers 10 and data that need to be frequently read and written during operation in each independent storage device 12. The operating system files and data that need to be frequently read and written during operation depend on the functions of the corresponding servers 10.

[0047] S30: Configuring each server 10 to start and run by reading the operating system files and data that need to be frequently read and written in the respective independent storage devices 12. That is, each server 10 can start and run independently without the help of external devices.

[0048] S40: Establishing communication connections between the servers 10. Figure 3 This is a partial flow chart of the accelerator server system, refer to Figure 3 , S40 specifically includes the following S41 and S42:

[0049] S41: Connect several servers 10 in series and connect them end to end to form a ring communication structure.

[0050] S42: Configuring each server 10 so that each server 10 can establish communication with other servers 10 connected in series.

[0051] In the exemplary embodiment, each server 10 is provided with an optical fiber communication module 14, and several servers 10 are connected in series and end to end to form a ring communication structure, specifically, the servers 10 are connected in series using optical fiber lines, and the server 10 at the head end and the server 10 at the end end are connected using optical fiber lines. The optical fiber communication module 14 has a higher communication rate in conjunction with the optical fiber line, which improves the time resolution of the accelerator server system. Several servers 10 form a ring communication structure, and when there is a problem with the connection between any two servers 10, the communication between the several servers 10 can still be maintained, which improves the stability of the accelerator server system.

[0052] S50: configuring several servers 10 to implement active / standby redundancy functions. Figure 4 This is a partial flow chart of the accelerator server system. Figure 4 , S50 specifically includes the following S51 and S52:

[0053] S51: Configuring each server 10 to monitor the operating status of multiple servers 10 in real time.

[0054] S52: configuring each server 10 so that when a server 10 is detected to be faulty, a server 10 that is operating normally will replace part or all of the functions of the faulty server 10 .

[0055] Based on the dynamic primary-standby redundancy function, when a server 10 fails, other normally operating servers 10 can replace part or all of the functions of the failed server 10 according to their own loads. Servers 10 with low loads can replace more functions, while servers 10 with high loads can replace fewer functions or do not need to be replaced at all, thereby balancing the load between the servers 10 and further improving the stability of the system.

[0056] Figure 5 A flowchart of another exemplary implementation of an optimization method for an accelerator server system. Figure 5 , and Figure 1 The same or similar aspects of the optimization method shown are not repeated here, and the difference is that the optimization method further includes:

[0057] S60: Setting up a public storage device, establishing a communication connection between the plurality of servers 10 and the public storage device, and configuring the plurality of servers 10 to store data that does not need to be frequently read and written in the public storage device.

[0058] The public storage device is used to centrally store larger data that does not require frequent reading and writing, which is convenient for reducing the capacity of the independent storage device 12 to save costs. In addition, the public storage device can use more professional and secure equipment such as disk array devices to improve data security.

[0059] The optimization method of the accelerator server system provided by the present invention provides an independent storage device 12 for each server 10, and each server 10 starts and runs by reading the operating system files and data that need to be frequently read and written in its own independent storage device 12, and establishes a communication connection between several servers 10 to realize the main and standby redundancy function. Each server 10 does not need to rely on a highly integrated disk array device, and the operation is more stable, and it is easier to troubleshoot when a fault occurs in each independent storage device 12.

[0060] The present invention provides an accelerator server system, referring to Figure 2 The accelerator server system includes several servers 10 and several communication lines 20. Each server 10 includes an independent storage device 12, and each independent storage device 12 stores operating system files of several servers 10 and data that needs to be frequently read and written during operation. Each server 10 is configured to start and run by reading the operating system files and data that needs to be frequently read and written in its own independent storage device 12. Each communication line 20 connects two servers 10, and the several servers 10 are configured to establish communication with the help of the several communication lines 20 and realize the main and standby redundancy function.

[0061] In the accelerator server system provided by the present invention, each server 10 is respectively provided with an independent storage device 12, each server 10 starts and runs by reading the operating system files and data that need to be frequently read and written in its own independent storage device 12, and a communication connection is established between several servers 10 to realize the main and standby redundancy function. Each server 10 does not need to rely on a highly integrated disk array device, the operation is more stable, and it is easier to troubleshoot when a fault occurs in each independent storage device 12.

[0062] In an exemplary embodiment, referring to Figure 2 , each server 10 is provided with an optical fiber communication module 14, and each communication line 20 is an optical fiber line that can be connected to the optical fiber communication module 14. Several servers 10 are connected in series and connected end to end to form a ring communication structure, and each server 10 can establish communication with other servers 10 connected in series. Several servers 10 form a ring communication structure, and when there is a problem with the connection between any two servers 10, the communication between the several servers 10 can still be maintained.

[0063] In an exemplary embodiment, each server 10 is configured to monitor the operating status of several servers 10 in real time. When a server 10 is detected to be faulty, a normally operating server 10 replaces part or all of the functions of the faulty server 10.

[0064] In an exemplary embodiment, the accelerator server system further includes a public storage device, which establishes a communication connection with a plurality of servers 10, and each server 10 is configured to store data that does not require frequent reading and writing in the public storage device.

[0065] It should be understood that although this specification is described according to various embodiments, not every embodiment contains only one independent technical solution. This narrative method of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation methods that can be understood by those skilled in the art.

[0066] The series of detailed descriptions listed above are only specific descriptions of feasible embodiments of the present invention. They are not intended to limit the scope of protection of the present invention. Any equivalent implementation scheme or changes that do not deviate from the technical spirit of the present invention, such as combination, division or repetition of features, should be included in the scope of protection of the present invention.

Claims

1. An optimization method for an accelerator server system, wherein the accelerator server system comprises a plurality of servers, characterized in that: The optimization method comprises: An independent storage device is provided for each of the servers; Storing operating system files of several servers and data that need to be frequently read and written during operation in each of the independent storage devices; Configuring each of the servers to start and run by reading operating system files and data that need to be frequently read and written in the respective independent storage devices; establishing a communication connection between the plurality of said servers; and Several of the servers are configured to realize the active-standby redundancy function.

2. The optimization method of the accelerator server system according to claim 1, characterized in that: Establishing a communication connection between the plurality of servers, specifically comprising: Connecting several of the servers in series and connecting them end to end to form a ring communication structure; and Each of the servers is configured so that each of the servers can establish communication with other servers connected in series.

3. The optimization method of the accelerator server system according to claim 2, characterized in that: Each server is provided with an optical fiber communication module, and several servers are connected in series and end to end to form a ring communication structure, specifically, the servers are connected in series using optical fiber lines, and the server at the head end and the server at the end end are connected using optical fiber lines.

4. The optimization method of the accelerator server system according to claim 1, characterized in that: Configuring several of the servers to implement active / standby redundancy functions specifically includes: configuring each of the servers to monitor the operating status of a plurality of the servers in real time; and When each of the servers is configured to detect that a server fails, a normally operating server will replace part or all of the functions of the failed server.

5. The optimization method of the accelerator server system according to claim 1, characterized in that: The optimization method further comprises: A public storage device is provided, a communication connection is established between the plurality of servers and the public storage device, and the plurality of servers are configured to store data that does not need to be frequently read and written in the public storage device.

6. The accelerator server system is characterized in that: include: A plurality of servers (10), each of the servers (10) comprising an independent storage device (12), each of the independent storage devices (12) storing operating system files of the plurality of servers (10) and data that needs to be frequently read and written during operation, each of the servers (10) being configured to start and operate by reading the operating system files and data that needs to be frequently read and written in its own independent storage device (12); and A plurality of communication lines (20), each of the communication lines (20) connecting two of the servers (10), and the plurality of servers (10) being configured to establish communication with the aid of the plurality of communication lines (20) and to achieve a primary-standby redundancy function.

7. The accelerator server system according to claim 6, characterized in that: A plurality of the servers (10) are connected in series and end-to-end to form a ring communication structure, and each server (10) is capable of establishing communication with other servers (10) connected in series.

8. The accelerator server system according to claim 7, characterized in that: Each of the servers (10) is provided with an optical fiber communication module (14), and each of the communication lines (20) is an optical fiber line capable of connecting to the optical fiber communication module (14).

9. The accelerator server system according to claim 6, characterized in that: Each of the servers (10) is configured to monitor the operating status of a plurality of the servers (10) in real time, and when a failure of one of the servers (10) is detected, a normally operating server (10) replaces part or all of the functions of the failed server (10).

10. The accelerator server system according to claim 6, characterized in that: The accelerator server system also includes a public storage device, the public storage device establishes a communication connection with a plurality of the servers (10), and each of the servers (10) is configured to store data that does not need to be frequently read and written in the public storage device.

Images