Deployment optimization method of end-to-end operation and maintenance all-in-one machine, storage medium, equipment and computer program product

Abstract

The invention discloses a deployment optimization method of an end-to-end operation and maintenance all-in-one machine, a storage medium, equipment and a computer program product, and the method comprises the steps: obtaining massive business data in the end-to-end operation and maintenance all-in-one machine, distributing the business data with the same business type to the same thread, and putting the threads with the same data source into the same Socket; all the Sockets are stored in the corresponding vector data blocks at the same time through the synchronization function of the distributed storage system, and the Sockets stored in the vector data blocks are loaded in the starting process of the end-to-end operation and maintenance all-in-one machine; and in the loading process, according to the energy consumption level of each Socket, the switching hysteresis parameter of the corresponding Socket is adjusted, and the Sockets are loaded in sequence from large to small according to the adjusted switching hysteresis parameter. According to the method, the Socket deployment is optimized, so that the energy consumption of the end-to-end operation and maintenance all-in-one machine in the startup process is reduced, and the end-to-end operation and maintenance all-in-one machine is quickly and safely started.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent operation and maintenance technology, and specifically, relates to a deployment optimization method, storage medium, device and computer program product of an end-to-end operation and maintenance integrated machine. Background Art

[0002] The end-to-end operation and maintenance integrated machine includes various devices such as computing power integrated machines and network equipment. Long-term operation is prone to heat and slow operation problems, which leads to operational safety issues for the end-to-end operation and maintenance integrated machine.

[0003] At present, most software is used to monitor various indicators of the end-to-end operation and maintenance integrated machine during the deployment process. Through the monitoring indicator warning, the cause of the warning is preliminarily analyzed, and the corresponding treatment plan is found according to the cause analysis. Although it can play the purpose of security warning for the deployment of the end-to-end operation and maintenance integrated machine to a certain extent, due to the excessive business in the end-to-end operation and maintenance integrated machine and the limitations of the monitoring software, all hidden dangers may not be discovered through software monitoring, resulting in low deployment efficiency of the end-to-end operation and maintenance integrated machine and accompanied by high energy consumption. Summary of the invention

[0004] In view of the problems existing in the prior art, the present invention provides a deployment optimization method, storage medium, device and computer program product of an end-to-end operation and maintenance integrated machine. By optimizing the Socket deployment, the energy consumption of the end-to-end operation and maintenance integrated machine during the startup process is reduced, and the end-to-end operation and maintenance integrated machine can be started quickly and safely.

[0005] To achieve the above technical objectives, the present invention adopts the following technical solution: a deployment optimization method of an end-to-end operation and maintenance integrated machine, specifically comprising the following steps:

[0006] Step S1: Obtain a large amount of business data in the end-to-end operation and maintenance machine, assign business data of the same business type to the same thread, and put threads with the same data source into the same Socket;

[0007] Step S2: Using the synchronization function of the distributed storage system to simultaneously store all the sockets into the corresponding vector data blocks, and loading the sockets stored in the vector data blocks during the startup process of the end-to-end operation and maintenance integrated machine;

[0008] Step S3: During the loading process, according to the energy consumption level of each Socket, the switching hysteresis parameter of the corresponding Socket is adjusted, and the Sockets are loaded in order from large to small according to the adjusted switching hysteresis parameters.

[0009] Furthermore, the specific process of step S2 is: determine whether there is an overload phenomenon in the business data of any thread in each Socket. If so, set a first-level cache, store part of the business data in the overloaded thread in the first-level cache until the overload phenomenon disappears, and directly store the business data in the Socket where the overload phenomenon disappears into the corresponding vector data block; otherwise, store the business data in each Socket directly into the corresponding vector data block.

[0010] Furthermore, the setting parameters of the first-level cache include: the capacity of the first-level cache and the expiration time of the business data in the first-level cache.

[0011] Furthermore, step S3 includes the following sub-steps:

[0012] Step S3.1, calculating the resource occupancy rate of each socket during the startup process of the end-to-end operation and maintenance integrated machine, and determining the energy consumption level of each socket according to the resource occupancy rate of each socket;

[0013] Step S3.2, the energy consumption level is divided into low energy consumption, second lowest energy consumption, medium energy consumption, second highest energy consumption and high energy consumption. If the resource occupancy rate of the Socket is less than 20%, the energy consumption level of the Socket is low energy consumption, and the switching hysteresis parameter of the Socket is increased by two bits; if the resource occupancy rate of the Socket is between 20% and 40%, the energy consumption level of the Socket is second lowest energy consumption, and the switching hysteresis parameter of the Socket is increased by one bit; if the resource occupancy rate of the Socket is between 40% and 60%, the energy consumption level of the Socket is medium energy consumption, and the switching hysteresis parameter of the Socket remains unchanged; if the resource occupancy rate of the Socket is between 60% and 80%, the energy consumption level of the Socket is second highest energy consumption, and the switching hysteresis parameter of the Socket is decreased by one bit; if the resource occupancy rate of the Socket is between 80% and 100%, the energy consumption level of the Socket is high energy consumption, and the switching hysteresis parameter of the Socket is decreased by two bits;

[0014] Step S3.3, loading the sockets in order from large to small according to the adjusted switching hysteresis parameters.

[0015] Furthermore, the calculation process of the resource occupancy rate of each Socket in step S3.1 is:

[0016] C=w1C1+w2C2+w3C3

[0017] Among them, C represents the resource usage of the socket, C1 represents the memory usage of the socket, w1 represents the weight coefficient of C1, C2 represents the resource usage of all threads in the socket, w2 represents the weight coefficient of C2, C3 represents the CPU usage of the socket during loading, and w3 represents the weight coefficient of C3.

[0018] Furthermore, after the Socket stored in the vector data block is loaded during the startup process of the end-to-end operation and maintenance integrated machine, the business data in the first-level cache is matched to the thread of the corresponding Socket according to the data source and business type, and then loaded during the startup process of the end-to-end operation and maintenance integrated machine according to the method of steps S3.1-S3.3.

[0019] Furthermore, the present invention also provides a computer-readable storage medium storing a computer program, wherein the computer program enables a computer to execute the deployment optimization method of the end-to-end operation and maintenance integrated machine.

[0020] Furthermore, the present invention also provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the deployment optimization method of the end-to-end operation and maintenance integrated machine is implemented.

[0021] Furthermore, the present invention also provides a computer program product, including a computer program, which implements the deployment optimization method of the end-to-end operation and maintenance integrated machine when executed by a processor.

[0022] Compared with the prior art, the present invention has the following beneficial effects: the deployment optimization method of the end-to-end operation and maintenance integrated machine of the present invention adopts the synchronization function of the distributed storage system to store all Sockets at the same time, which can ensure that multiple vector data blocks in the distributed storage system can achieve data synchronization in a very short time, thereby significantly improving the consistency of the data. At the same time, all Sockets are stored and synchronized, which can more reasonably allocate and utilize these resources to avoid waste and idleness of resources; at the same time, the present invention adjusts the switching hysteresis parameter of the corresponding Socket according to the energy consumption level of each Socket, and loads the Sockets in order from large to small according to the adjusted switching hysteresis parameter. The higher the energy consumption level, the smaller the switching hysteresis parameter of the corresponding Socket, and the later the loading order, thereby improving the response speed and processing capacity of the socket loading in the end-to-end operation and maintenance integrated machine. In summary, the deployment optimization method of the end-to-end operation and maintenance integrated machine of the present invention reduces the energy consumption of the end-to-end operation and maintenance integrated machine during the startup process by optimizing the deployment of the Socket, and realizes the fast and safe startup of the end-to-end operation and maintenance integrated machine. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a flow chart of the deployment optimization method of the end-to-end operation and maintenance integrated machine of the present invention;

[0024] Figure 2 The present invention is a flowchart of the Socket being loaded during the startup process of the end-to-end operation and maintenance integrated machine. DETAILED DESCRIPTION

[0025] The technical solution of the present invention is further explained below in conjunction with the accompanying drawings.

[0026] like Figure 1 The flowchart of the deployment optimization method of the end-to-end operation and maintenance integrated machine of the present invention specifically includes the following steps:

[0027] Step S1, obtaining a large amount of business data in the end-to-end operation and maintenance integrated machine. The processing logic for business data of different business types is very different. If threads are frequently switched between business data of different business types, a large amount of context switching overhead will be caused. The present invention assigns business data of the same business type to the same thread, which can reduce such unnecessary context switching, thereby improving processing efficiency. Reducing context switching and optimizing resource utilization can directly improve the efficiency of business data processing; Socket connection is an important resource in network communication, and its establishment and closing require certain overhead. If threads with the same data source communicate through different Sockets, this overhead will increase. The present invention puts threads with the same data source into the same Socket. Threads with the same data source may need to be synchronized and coordinated during the communication process to ensure the consistency and correctness of the data. Putting them into the same Socket can simplify this synchronization and coordination process.

[0028] Step S2, using the synchronization function of the distributed storage system to store all Sockets in the corresponding vector data blocks at the same time, and loading the Sockets stored in the vector data blocks during the startup process of the end-to-end operation and maintenance integrated machine, which can ensure that multiple vector data blocks in the distributed storage system can achieve data synchronization in a very short time, thereby significantly improving data consistency. At the same time, all Sockets are stored and synchronized, which can more reasonably allocate and utilize these resources to avoid waste and idleness of resources; specifically, if the amount of data processed by the thread is too large or the processing logic is complex, it may cause thread overload and affect the overall performance. It is determined whether the business data of any thread in each Socket is overloaded. If so, set a first-level cache, store part of the business data in the overloaded thread in the first-level cache until the overload disappears, and directly store the business data in the Socket where the overload disappears into the corresponding vector data block; otherwise, the business data in each Socket is directly stored in the corresponding vector data block. The present invention sets a first-level cache. First, the overloaded business data is temporarily stored in the first-level cache, which can reduce the burden of the thread and enable the thread to continue to process other tasks, thereby optimizing resource utilization; secondly, when the thread is overloaded, the ability to process data will decrease, resulting in an increase in the delay in data processing. By storing the overloaded business data in the first-level cache, it is possible to wait until the thread load is reduced before processing, thereby reducing the delay in data processing; further, thread overload may cause resource exhaustion of the end-to-end operation and maintenance integrated machine, thereby affecting the stability and availability of the end-to-end operation and maintenance integrated machine. By storing the overloaded business data in the first-level cache, the end-to-end operation and maintenance integrated machine can be prevented from crashing due to resource exhaustion, thereby improving the stability of the end-to-end operation and maintenance integrated machine; finally, in a high-concurrency scenario, multiple threads may process a large amount of data at the same time. By storing the overloaded business data in the first-level cache, the end-to-end operation and maintenance integrated machine can be able to process more concurrent requests at the same time, thereby improving the concurrent processing capability of the end-to-end operation and maintenance integrated machine.

[0029] In one technical solution of the present invention, the setting parameters of the first-level cache include: the capacity of the first-level cache and the expiration time of the business data in the first-level cache. Since the business data may become outdated or inaccurate after being stored in the first-level cache for a period of time, setting the expiration time of the business data in the first-level cache can ensure that the business data in the first-level cache is automatically cleared after the specified time is reached, thereby prompting the end-to-end operation and maintenance integrated machine to reload the latest business data from the data source to maintain data consistency; at the same time, since the space of the first-level cache is limited, retaining business data that is no longer needed for a long time will waste precious cache resources. Setting the expiration time can allow the first-level cache to automatically clean up business data that is no longer frequently accessed, making room for new business data, and improving the utilization rate of the first-level cache.

[0030] Step S3: During the loading process, according to the energy consumption level of each socket, the switching hysteresis parameter of the corresponding socket is adjusted, and the sockets are loaded in descending order according to the adjusted switching hysteresis parameters. The higher the energy consumption level, the smaller the switching hysteresis parameter of the corresponding socket, and the later the loading order, thereby improving the response speed and processing capacity of socket loading in the end-to-end operation and maintenance machine. Figure 2 , specifically including the following sub-steps:

[0031] Step S3.1, calculate the resource occupancy rate of each Socket during the startup process of the end-to-end operation and maintenance integrated machine. The influencing factors of the resource occupancy rate include: the memory occupancy rate of the Socket, the thread resource occupancy rate and the CPU occupancy rate of the Socket during the loading process. During the startup process of the end-to-end operation and maintenance integrated machine, an excessively high thread resource occupancy rate will cause the end-to-end operation and maintenance integrated machine to respond slowly, and even cause the risk of thread exhaustion; the Socket will occupy CPU resources during the loading process. Optimizing the CPU occupancy rate can ensure that the Socket can efficiently utilize CPU resources, reduce unnecessary computing overhead, and improve the overall performance of the end-to-end operation and maintenance integrated machine; if the memory occupancy rate of the Socket is too high, the loading speed will be slowed down. By comprehensively considering the memory occupancy rate of the Socket, the thread resource occupancy rate and the CPU occupancy rate of the Socket during the loading process, it can be ensured that the end-to-end operation and maintenance integrated machine can efficiently utilize limited memory resources and reduce energy consumption; determine the energy consumption level of each Socket according to the resource occupancy rate of each Socket.

[0032] The calculation process of the resource occupancy rate of each Socket in the present invention is:

[0033] C=w1C1+w2C2+w3C3

[0034] Among them, C represents the resource usage of the socket, C1 represents the memory usage of the socket, w1 represents the weight coefficient of C1, C2 represents the resource usage of all threads in the socket, w2 represents the weight coefficient of C2, C3 represents the CPU usage of the socket during loading, and w3 represents the weight coefficient of C3.

[0035] Step S3.2, the energy consumption level is divided into low energy consumption, second lowest energy consumption, medium energy consumption, second highest energy consumption and high energy consumption. If the resource occupancy rate of the Socket is less than 20%, the energy consumption level of the Socket is low energy consumption, and the switching hysteresis parameter of the Socket is increased by two bits; if the resource occupancy rate of the Socket is between 20% and 40%, the energy consumption level of the Socket is second lowest energy consumption, and the switching hysteresis parameter of the Socket is increased by one bit; if the resource occupancy rate of the Socket is between 40% and 60%, the energy consumption level of the Socket is medium energy consumption, and the switching hysteresis parameter of the Socket remains unchanged; if the resource occupancy rate of the Socket is between 60% and 80%, the energy consumption level of the Socket is second highest energy consumption, and the switching hysteresis parameter of the Socket is decreased by one bit; if the resource occupancy rate of the Socket is between 80% and 100%, the energy consumption level of the Socket is high energy consumption, and the switching hysteresis parameter of the Socket is decreased by two bits;

[0036] Step S3.3, loading the sockets in order from large to small according to the adjusted switching hysteresis parameters.

[0037] After the Socket stored in the vector data block is loaded during the startup process of the end-to-end operation and maintenance integrated machine, the business data in the first-level cache is matched to the thread of the corresponding Socket according to the data source and business type, and then loaded during the startup process of the end-to-end operation and maintenance integrated machine according to the method of steps S3.1-S3.3, thereby realizing the deployment optimization of the end-to-end operation and maintenance integrated machine.

[0038] In a technical solution of the present invention, a computer-readable storage medium is also provided, storing a computer program, wherein the computer program enables a computer to execute the deployment optimization method of the end-to-end operation and maintenance integrated machine.

[0039] In a technical solution of the present invention, an electronic device is also provided, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the deployment optimization method of the end-to-end operation and maintenance integrated machine is implemented.

[0040] In a technical solution of the present invention, a computer program product is also provided, including a computer program, and when the computer program is executed by a processor, the deployment optimization method of the end-to-end operation and maintenance integrated machine is implemented.

[0041] In the embodiments disclosed in the present application, the computer storage medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. The computer storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the above. More specific examples of computer storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.

[0042] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in this application can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0043] The above are only preferred embodiments of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should be regarded as the protection scope of the present invention.

Claims

1. A deployment optimization method for an end-to-end operation and maintenance integrated machine, characterized in that: The specific steps include: Step S1: Obtain a large amount of business data in the end-to-end operation and maintenance machine, assign business data of the same business type to the same thread, and put threads with the same data source into the same Socket; Step S2: Using the synchronization function of the distributed storage system to simultaneously store all the sockets in the corresponding vector data blocks, and loading the sockets stored in the vector data blocks during the startup process of the end-to-end operation and maintenance integrated machine; Step S3: During the loading process, according to the energy consumption level of each Socket, the switching hysteresis parameter of the corresponding Socket is adjusted, and the Sockets are loaded in order from large to small according to the adjusted switching hysteresis parameters.

2. The deployment optimization method of an end-to-end operation and maintenance integrated machine according to claim 1, characterized in that: The specific process of step S2 is: determine whether the business data of any thread in each Socket is overloaded. If so, set a first-level cache, store part of the business data in the overloaded thread in the first-level cache until the overload disappears, and directly store the business data in the Socket where the overload disappears into the corresponding vector data block; otherwise, store the business data in each Socket directly into the corresponding vector data block.

3. The deployment optimization method of an end-to-end operation and maintenance integrated machine according to claim 2, characterized in that: The setting parameters of the first-level cache include: the capacity of the first-level cache and the expiration time of the business data in the first-level cache.

4. The deployment optimization method of an end-to-end operation and maintenance integrated machine according to claim 2, characterized in that: Step S3 includes the following sub-steps: Step S3.1, calculating the resource occupancy rate of each socket during the startup process of the end-to-end operation and maintenance integrated machine, and determining the energy consumption level of each socket according to the resource occupancy rate of each socket; Step S3.2, the energy consumption level is divided into low energy consumption, second lowest energy consumption, medium energy consumption, second highest energy consumption and high energy consumption. If the resource occupancy rate of the Socket is less than 20%, the energy consumption level of the Socket is low energy consumption, and the switching hysteresis parameter of the Socket is increased by two bits; if the resource occupancy rate of the Socket is between 20% and 40%, the energy consumption level of the Socket is second lowest energy consumption, and the switching hysteresis parameter of the Socket is increased by one bit; If the resource utilization rate of the socket is between 40% and 60%, the energy consumption level of the socket is medium energy consumption, and the switching hysteresis parameter of the socket remains unchanged; if the resource utilization rate of the socket is between 60% and 80%, the energy consumption level of the socket is the second highest energy consumption, and the switching hysteresis parameter of the socket is reduced by one; If the resource occupancy rate of the socket is between 80% and 100%, the energy consumption level of the socket is high energy consumption, and the switching hysteresis parameter of the socket is reduced by two bits; Step S3.3, loading the sockets in order from large to small according to the adjusted switching hysteresis parameters.

5. The deployment optimization method of an end-to-end operation and maintenance integrated machine according to claim 4, characterized in that: The calculation process of the resource occupancy rate of each Socket in step S3.1 is: C=w1C1+w2C2+w3C3 Among them, C represents the resource usage of the socket, C1 represents the memory usage of the socket, w1 represents the weight coefficient of C1, C2 represents the resource usage of all threads in the socket, w2 represents the weight coefficient of C2, C3 represents the CPU usage of the socket during loading, and w3 represents the weight coefficient of C3.

6. The deployment optimization method of an end-to-end operation and maintenance integrated machine according to claim 5, characterized in that: After the Socket stored in the vector data block is loaded during the startup process of the end-to-end operation and maintenance integrated machine, the business data in the first-level cache is matched to the thread of the corresponding Socket according to the data source and business type, and then loaded during the startup process of the end-to-end operation and maintenance integrated machine according to the method of steps S3.1-S3.

3.

7. A computer-readable storage medium storing a computer program, characterized in that: The computer program enables the computer to execute the deployment optimization method of the end-to-end operation and maintenance integrated machine as described in any one of claims 1-6.

8. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the deployment optimization method of the end-to-end operation and maintenance integrated machine as described in any one of claims 1 to 6 is implemented.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the deployment optimization method of the end-to-end operation and maintenance integrated machine described in any one of claims 1-6 is implemented.

Images