CN111857996A - Interrupt processing method, system, device and computer-readable storage medium - Google Patents

Abstract

The application discloses an interrupt processing method, a system, equipment and a computer readable storage medium, which are applied to a server and used for acquiring the real-time CPU utilization rate of own service; judging whether the real-time CPU utilization rate exceeds a preset CPU utilization rate or not; if the real-time CPU utilization rate exceeds the preset CPU utilization rate, generating interrupt merging information based on the real-time CPU utilization rate; transmitting the interrupt merging information to a hardware accelerator connected with the server; and controlling the hardware accelerator to perform interrupt merging so that the hardware accelerator performs interrupt merging based on the interrupt merging information. In the application, the server generates the interruption combination information based on the real-time CPU utilization rate under the condition that the real-time CPU utilization rate exceeds the preset CPU utilization rate, and controls the hardware accelerator to perform interruption combination based on the interruption combination information, so that the interruption times of the hardware accelerator are reduced, the utilization rate of the hardware accelerator to the server CPU resource is reduced, and the utilization rate of a service to the server CPU resource is ensured.

Description

An interrupt processing method, system, device and computer-readable storage medium

technical field

The present application relates to the technical field of interrupt processing, and more particularly, to an interrupt processing method, system, device, and computer-readable storage medium.

Background technique

With the vigorous development of network services, massive data processing has become the norm in various application fields, especially in the server field. Relying solely on software for data processing obviously cannot meet the speed requirements of massive data processing. In this case, various hardware accelerator applications Instead, such as PCIe (peripheral component interconnectexpress) hardware accelerators, etc. The PCIe hardware accelerator processes data by using hardware instead of software to improve the speed of data processing. After the data processing is completed, the server is notified of the processing result by means of an interrupt, and the server obtains the data processed by the hardware accelerator for subsequent operations.

However, there are usually other services running on the server at the same time. If the accelerator interrupts the server too frequently, it will consume a lot of resources of the server CPU (central processing unit, central processing unit) and affect the processing of other services on the server. , resulting in unsatisfactory server CPU usage efficiency.

To sum up, how to improve the service CPU usage efficiency of the server is an urgent problem to be solved by those skilled in the art.

SUMMARY OF THE INVENTION

The purpose of this application is to provide an interrupt processing method, which can solve the technical problem of how to improve the service CPU usage efficiency of the server to a certain extent. The present application also provides an interrupt processing system, device and computer-readable storage medium.

In order to achieve the above purpose, the application provides the following technical solutions:

An interrupt handling method, applied to a server, includes:

Get the real-time CPU usage of your own business;

Determine whether the real-time CPU usage exceeds the preset CPU usage;

If the real-time CPU usage exceeds the preset CPU usage, generating interrupt merge information based on the real-time CPU usage;

transmitting the interrupt coalescing information to a hardware accelerator connected to the server;

Controlling the hardware accelerator to perform interrupt merging, so that the hardware accelerator performs interrupt merging based on the interrupt merging information.

Preferably, the judging whether the real-time CPU usage exceeds the preset CPU usage includes:

According to the corresponding relationship between the preset load level and the CPU usage rate, determine the real-time load level of the service based on the real-time CPU usage rate;

determining the maximum amount of traffic in the load level based on the preset CPU usage;

determining the real-time traffic in the real-time load level;

determining whether the real-time traffic volume is greater than the maximum amount of the real-time load level, and if the real-time traffic volume is greater than the maximum amount of the real-time load level, determining that the real-time CPU usage exceeds the preset CPU usage, If the real-time traffic volume is less than or equal to the maximum amount of the real-time load level, it is determined that the real-time CPU usage rate does not exceed the preset CPU usage rate.

Preferably, the generating interrupt merge information based on the real-time CPU usage includes:

obtaining the interruption time slot corresponding to the real-time load level;

determining a real-time time slot to be merged in the outage time slot based on the real-time traffic volume and the maximum amount of the real-time load level;

The real-time time slot is used as the interrupt merge information.

Preferably, the controlling the hardware accelerator to perform interrupt merging includes:

Sending information for controlling the hardware accelerator to perform interrupt merging to the hardware accelerator.

Preferably, the controlling the hardware accelerator to perform interrupt merging includes:

The interrupt on completion flag in the IO request is set to control the hardware accelerator to perform interrupt merging.

Preferably, the obtaining the real-time CPU usage of the own business includes:

Acquire the real-time CPU usage of the own service according to a preset period.

An interrupt handling method, applied to a hardware accelerator, includes:

receiving the interrupt merge information transmitted by the server connected to the hardware accelerator;

Under the control of the server, interrupt merging is performed based on the interrupt merging information;

The server obtains the real-time CPU usage of its own business, and determines whether the real-time CPU usage exceeds the preset CPU usage. If the real-time CPU usage exceeds the preset CPU usage, the real-time CPU usage CPU usage generates the interrupt coalescing information.

An interrupt handling system, applied to a server, includes:

The first obtaining module is used to obtain the real-time CPU usage of its own business;

a first judging module, configured to judge whether the real-time CPU usage exceeds the preset CPU usage; if the real-time CPU usage exceeds the preset CPU usage, generate interrupt merge information based on the real-time CPU usage ;

a first transmission module, configured to transmit the interrupt merge information to a hardware accelerator connected to the server;

A first control module, configured to control the hardware accelerator to perform interrupt merging, so that the hardware accelerator performs interrupt merging based on the interrupt merging information.

An interrupt handling device, comprising:

memory for storing computer programs;

The processor is configured to implement the steps of any of the above interrupt processing methods when executing the computer program.

A computer-readable storage medium, storing a computer program in the computer-readable storage medium, when the computer program is executed by a processor, implements the steps of any of the above interrupt processing methods.

An interrupt processing method provided by this application is applied to a server to obtain the real-time CPU usage rate of its own business; it is judged whether the real-time CPU usage rate exceeds the preset CPU usage rate; if the real-time CPU usage rate exceeds the preset CPU usage rate, based on The real-time CPU usage generates interrupt coalescing information; transmits the interrupt coalescing information to a hardware accelerator connected to the server; controls the hardware accelerator to perform interrupt coalescing, so that the hardware accelerator performs interrupt coalescing based on the interrupt coalescing information. In this application, when the real-time CPU usage exceeds the preset CPU usage, the server will generate interrupt merging information based on the real-time CPU usage, and control the hardware accelerator to perform interrupt merging based on the interrupt merging information, thereby reducing the interruption of the hardware accelerator The number of times, reduce the utilization rate of the server CPU resources by the hardware accelerator, and ensure the utilization rate of the server CPU resources by the business. The interrupt processing system, device and computer-readable storage medium provided by the present application also solve the corresponding technical problems.

Description of drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only It is an embodiment of the present application. For those of ordinary skill in the art, other drawings can also be obtained according to the provided drawings without any creative effort.

FIG. 1 is a first flowchart of an interrupt processing method provided by an embodiment of the present application;

2 is a second flowchart of an interrupt processing method provided by an embodiment of the present application;

3 is a schematic diagram of a first structure of an interrupt processing system provided by an embodiment of the present application;

4 is a schematic diagram of a second structure of an interrupt processing system provided by an embodiment of the present application;

FIG. 5 is a schematic structural diagram of an interrupt processing device provided by an embodiment of the present application;

FIG. 6 is another schematic structural diagram of an interrupt processing device provided by an embodiment of the present application.

Detailed ways

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of this application.

With the vigorous development of network services, massive data processing has become the norm in various application fields, especially in the server field. Relying solely on software for data processing obviously cannot meet the speed requirements of massive data processing. In this case, various hardware accelerator applications Instead, such as PCIe (peripheral component interconnectexpress) hardware accelerators, etc. The PCIe hardware accelerator processes data by using hardware instead of software to improve the speed of data processing. After the data processing is completed, the server is notified of the processing result by means of an interrupt, and the server obtains the data processed by the hardware accelerator for subsequent operations. However, there are usually other services running on the server at the same time. If the accelerator interrupts the server too frequently, it will consume a lot of resources of the server CPU (central processing unit, central processing unit) and affect the processing of other services on the server. As a result, the server CPU usage efficiency is not ideal. The interrupt processing method provided by the present application can improve the service CPU usage efficiency of the server.

Please refer to FIG. 1. FIG. 1 is a first flowchart of an interrupt processing method provided by an embodiment of the present application.

An interrupt processing method provided by an embodiment of the present application, applied to a server, may include the following steps:

Step S101: Obtain the real-time CPU usage of the own service.

In practical applications, the server can first obtain the real-time CPU usage of its own business. The real-time CPU usage is the CPU usage of the business at the moment of acquisition.

It should be pointed out that the acquisition moment for acquiring the real-time CPU usage of the service can be flexibly determined according to actual needs, for example, the real-time CPU usage of the service can be acquired according to a preset period.

Step S102: judging whether the real-time CPU usage exceeds the preset CPU usage; if the real-time CPU usage exceeds the preset CPU usage, execute step S103; if the real-time CPU usage does not exceed the preset CPU usage, execute step S106 .

Step S103: Generate interrupt merge information based on the real-time CPU usage, and execute Step S104.

In practical applications, since the hardware accelerator sends an interrupt to the server, it will occupy the server's CPU. Therefore, after obtaining the real-time CPU usage of its own business, it is necessary to determine whether the real-time CPU usage exceeds the preset CPU usage. According to the real-time CPU usage The comparison result with the preset CPU usage determines the interrupt handling method for the hardware accelerator, so as to ensure the CPU usage of the business. For example, when the real-time CPU usage exceeds the preset CPU usage, it can be based on the real-time CPU usage The interrupt merge information is generated at a rate, and the interrupt of the hardware accelerator can be kept unchanged under the condition that the real-time CPU usage does not exceed the preset CPU usage.

Step S104: Transmit the interrupt merge information to the hardware accelerator connected to the server.

Step S105: Control the hardware accelerator to perform interrupt merging, so that the hardware accelerator performs interrupt merging based on the interrupt merging information.

In practical applications, since the real-time CPU usage exceeds the preset CPU usage, the interrupt merge information can be generated based on the real-time CPU usage, and the interrupt merge information refers to merging the interrupts, which can reduce the number of hardware accelerators. The server CPU resources are occupied, so after the server generates the interrupt merge information based on the real-time CPU usage, it needs to transmit the interrupt merge information to the hardware accelerator connected to the server, and control the hardware accelerator to perform interrupt merge, so that the hardware accelerator can perform interrupt merge based on the interrupt merge information. .

It should be pointed out that when the real-time CPU usage does not exceed the preset CPU usage, there are many idle CPUs on the server. At this time, if the hardware accelerator sends interrupts to the server for many times, the impact on the CPU usage of the business is relatively light. Therefore, the interruption of the hardware accelerator can be kept unchanged at this time; however, when the real-time CPU usage exceeds the preset CPU usage, the server has less idle CPUs. At this time, if the hardware accelerator sends interruptions to the server for many times, the service will not be affected. The impact of the CPU usage of the server is relatively heavy, which may cause the server to reduce the CPU usage of the business. Therefore, at this time, it is necessary to reduce the interrupt transmission frequency of the hardware accelerator and reduce the consumption of the server CPU resources by the hardware accelerator.

Step S106: Keep the interrupt of the hardware accelerator unchanged.

An interrupt processing method provided by this application is applied to a server to obtain the real-time CPU usage rate of its own business; it is judged whether the real-time CPU usage rate exceeds the preset CPU usage rate; if the real-time CPU usage rate exceeds the preset CPU usage rate, based on The real-time CPU usage generates interrupt coalescing information; transmits the interrupt coalescing information to a hardware accelerator connected to the server; controls the hardware accelerator to perform interrupt coalescing, so that the hardware accelerator performs interrupt coalescing based on the interrupt coalescing information. In this application, when the real-time CPU usage exceeds the preset CPU usage, the server will generate interrupt merging information based on the real-time CPU usage, and control the hardware accelerator to perform interrupt merging based on the interrupt merging information, thereby reducing the interruption of the hardware accelerator The number of times, reduce the utilization rate of the server CPU resources by the hardware accelerator, and ensure the utilization rate of the server CPU resources by the business.

An interrupt processing method provided by this application is applied to a server. Since each service has different CPU usage on the server, a single service will affect the service CPU usage of the server, and all services determine the services in the server. Therefore, in the process of judging whether the real-time CPU usage exceeds the preset CPU usage, you can follow the preset CPU usage. The corresponding relationship between the load level and the CPU usage rate, determine the real-time load level of the business based on the real-time CPU usage rate; determine the maximum amount of business in the load level based on the preset CPU usage rate; determine the real-time business volume in the real-time load level; Determine whether the real-time traffic volume is greater than the maximum amount of the real-time load level. If the real-time traffic volume is greater than the maximum amount of the real-time load level, it is determined that the real-time CPU usage exceeds the preset CPU usage rate. If the real-time traffic volume is less than or equal to the maximum amount of the real-time load level , it is determined that the real-time CPU usage does not exceed the preset CPU usage.

For ease of understanding, it is assumed that the load level is divided into a first load level, a second load level and a third load level, and the service CPU usage of the first load level is greater than that of the second load level, and the service CPU usage of the second load level is is greater than the third load level, then, even in the case where the traffic volume in the first load level is small, the total CPU usage of all services in the first load level may still be relatively large, while in the third load level When there is a lot of business volume, the total CPU usage of all services in the third load level may be larger. Therefore, the default CPU usage can be determined according to the CPU usage of a single business in the load level and the business volume in the load level. Rate.

An interrupt processing method provided by the present application is applied to a server. In the process of generating interrupt merge information based on the real-time CPU usage, the interrupt time slot corresponding to the real-time load level can be obtained; based on the real-time traffic volume and the maximum real-time load level , determine the real-time time slot to be merged in the interruption time slot; take the real-time time slot as the interruption merge information.

That is to say, in practical applications, the interruption merge information can be determined according to the interruption time slot corresponding to each real-time load level; in a specific application scenario, based on the maximum amount of real-time traffic and real-time load level, the interruption time slot is determined to be merged. In the process of real-time time slots, the difference between the real-time traffic volume and the maximum real-time load level can be calculated, and the real-time time slots can be determined according to the principle that the number of real-time time slots is equal to the difference; The real-time time slot is determined according to the principle that the difference is greater than the difference, or the real-time time slot is determined according to the principle that the number of real-time time slots is less than the difference value; Alternatively, the interrupted time slot with a long duration is preferentially used as a real-time slot, etc., which is not specifically limited in this application.

An interrupt processing method provided by the present application is applied to a server. In the process of controlling the hardware accelerator to perform interrupt merging, the server can directly send the information of controlling the hardware accelerator to perform interrupt merging to the hardware accelerator; or set the interupt in the IO request. The on completion flag is used to control the hardware accelerator for interrupt merging.

Please refer to FIG. 2 , which is a second flowchart of an interrupt processing method provided by an embodiment of the present application.

An interrupt processing method provided by an embodiment of the present application, applied to a hardware accelerator, may include the following steps:

Step S201: Receive the interrupt merge information transmitted by the server connected to the hardware accelerator.

Step S202: Under the control of the server, interrupt merging is performed based on the interrupt merging information; wherein, the server obtains the real-time CPU usage of its own business, and determines whether the real-time CPU usage exceeds the preset CPU usage, and if the real-time CPU usage exceeds the preset CPU usage CPU usage, the interrupt coalescing information is generated based on real-time CPU usage.

For the description of each step in the interrupt processing method applied to the hardware accelerator provided by the embodiment of the present application, please refer to the foregoing embodiment, and details are not repeated here.

Please refer to FIG. 3 , which is a schematic diagram of a first structure of an interrupt processing system provided by an embodiment of the present application.

An interrupt processing system provided by an embodiment of the present application, applied to a server, may include:

The first obtaining module 101 is used to obtain the real-time CPU usage of its own business;

The first judgment module 102 is used for judging whether the real-time CPU usage exceeds the preset CPU usage; if the real-time CPU usage exceeds the preset CPU usage, the interrupt merge information is generated based on the real-time CPU usage;

a first transmission module 103, configured to transmit the interrupt merge information to the hardware accelerator connected to the server;

The first control module 104 is configured to control the hardware accelerator to perform interrupt merging, so that the hardware accelerator performs interrupt merging based on the interrupt merging information.

An interrupt processing system provided by an embodiment of the present application is applied to a server, and the first judgment module may include:

The first determination submodule is configured to determine the real-time load level of the service based on the real-time CPU usage rate according to the preset correspondence between the load level and the CPU usage rate;

The second determination submodule is used to determine the maximum amount of business in the load level based on the preset CPU usage;

The third determination sub-module is used to determine the real-time traffic volume in the real-time load level;

The first judgment sub-module is used to judge whether the real-time traffic volume is greater than the maximum amount of the real-time load level. If the real-time traffic volume is greater than the maximum amount of the real-time load level, it is determined that the real-time CPU usage exceeds the preset CPU usage, and if the real-time traffic is less than is equal to the maximum amount of the real-time load level, it is determined that the real-time CPU usage does not exceed the preset CPU usage.

An interrupt processing system provided by an embodiment of the present application is applied to a server, and the first judgment module may include:

a first obtaining unit, configured to obtain the interrupt time slot corresponding to the real-time load level;

a first determining unit, configured to determine the real-time time slot to be merged in the interruption time slot based on the maximum amount of real-time traffic and real-time load level;

The first setting unit is used for taking the real-time time slot as interrupt combining information.

An interrupt processing system provided by an embodiment of the present application is applied to a server, and the first control module may include:

The first sending unit is configured to send information for controlling the hardware accelerator to perform interrupt merging to the hardware accelerator.

An interrupt processing system provided by an embodiment of the present application is applied to a server, and the first control module may include:

The first setting unit is used to set the interrupt on completion flag in the IO request to control the hardware accelerator to perform interrupt merging.

An interrupt processing system provided by an embodiment of the present application is applied to a server, and the first obtaining module may include:

The second obtaining unit is configured to obtain the real-time CPU usage of the own service according to a preset period.

Please refer to FIG. 4 , which is a schematic diagram of a second structure of an interrupt processing system provided by an embodiment of the present application.

An interrupt processing system provided by an embodiment of the present application, applied to a hardware accelerator, may include:

The first receiving module 201 is configured to receive the interrupt merge information transmitted by the server connected by the hardware accelerator;

The first merging module 202, under the control of the server, performs interrupt merging based on the interrupt merging information;

The server obtains the real-time CPU usage of its own business, determines whether the real-time CPU usage exceeds the preset CPU usage, and if the real-time CPU usage exceeds the preset CPU usage, generates interrupt merge information based on the real-time CPU usage.

The present application further provides an interrupt processing device and a computer-readable storage medium, both of which have the corresponding effects of the interrupt processing method provided by the embodiments of the present application. Please refer to FIG. 5 , which is a schematic structural diagram of an interrupt processing device according to an embodiment of the present application.

An interrupt processing device provided by an embodiment of the present application is applied to a server, and includes a memory 201 and a processor 202. A computer program is stored in the memory 201, and the processor 202 implements the following steps when executing the computer program:

Get the real-time CPU usage of your own business;

Determine whether the real-time CPU usage exceeds the preset CPU usage;

If the real-time CPU usage exceeds the preset CPU usage, interrupt merge information is generated based on the real-time CPU usage;

A hardware accelerator that transmits interrupt coalescing information to the server connection;

The hardware accelerator is controlled to perform interrupt coalescence, so that the hardware accelerator performs interrupt coalescence based on the interrupt coalescing information.

An interrupt processing device provided by an embodiment of the present application is applied to a server, and includes a memory 201 and a processor 202. A computer program is stored in the memory 201. When the processor 202 executes the computer program, the following steps are implemented: according to the preset load level and The corresponding relationship between the CPU usage rates, determine the real-time load level of the service based on the real-time CPU usage rate; determine the maximum amount of services in the load level based on the preset CPU usage rate; determine the real-time traffic volume in the real-time load level; determine the real-time traffic volume Whether it is greater than the maximum amount of the real-time load level, if the real-time traffic volume is greater than the maximum amount of the real-time load level, it is determined that the real-time CPU usage exceeds the preset CPU usage rate. The CPU usage does not exceed the preset CPU usage.

An interrupt processing device provided by an embodiment of the present application is applied to a server, and includes a memory 201 and a processor 202. A computer program is stored in the memory 201. When the processor 202 executes the computer program, the following steps are implemented: acquiring an interrupt corresponding to a real-time load level Time slot; based on the maximum amount of real-time traffic and real-time load level, the real-time time slot to be merged is determined in the interruption time slot; the real-time time slot is used as interruption merge information.

An interrupt processing device provided by an embodiment of the present application is applied to a server, and includes a memory 201 and a processor 202. A computer program is stored in the memory 201. When the processor 202 executes the computer program, the following steps are implemented: sending a control hardware accelerator to perform interrupt merging information to the hardware accelerator.

An interrupt processing device provided by an embodiment of the present application is applied to a server, and includes a memory 201 and a processor 202. A computer program is stored in the memory 201. When the processor 202 executes the computer program, the following steps are implemented: set the interupt in the IO request. The on completion flag is used to control the hardware accelerator for interrupt merging.

An interrupt processing device provided by an embodiment of the present application is applied to a server, and includes a memory 201 and a processor 202. A computer program is stored in the memory 201. When the processor 202 executes the computer program, the following steps are implemented: obtaining its own service according to a preset period real-time CPU usage.

An interrupt processing device provided by an embodiment of the present application is applied to a hardware accelerator, and includes a memory 201 and a processor 202. A computer program is stored in the memory 201, and the processor 202 implements the following steps when executing the computer program: receiving a server connected to the hardware accelerator Interrupt merging information transmitted; under the control of the server, interrupt merging is performed based on the interrupt merging information; wherein, the server obtains the real-time CPU usage of its own business, and determines whether the real-time CPU usage exceeds the preset CPU usage, if the real-time CPU usage If the preset CPU usage is exceeded, interrupt coalescing information is generated based on the real-time CPU usage.

Referring to FIG. 6 , another interrupt processing device provided in this embodiment of the present application may further include: an input port 203 connected to the processor 202 for transmitting external input commands to the processor 202 ; an input port 203 connected to the processor 202 The display unit 204 is used for displaying the processing result of the processor 202 to the outside world; the communication module 205 connected with the processor 202 is used for realizing the communication between the interrupt processing device and the outside world. The display unit 204 can be a display panel, a laser scanning display, etc.; the communication mode adopted by the communication module 205 includes but is not limited to mobile high-definition link technology (HML), universal serial bus (USB), high-definition multimedia interface (HDMI), Wireless connection: wireless fidelity technology (WiFi), Bluetooth communication technology, Bluetooth low energy communication technology, communication technology based on IEEE802.11s.

A computer-readable storage medium provided by an embodiment of the present application is applied to a server, where a computer program is stored in the computer-readable storage medium, and the computer program is executed by a processor to implement the following steps:

Get the real-time CPU usage of your own business;

Determine whether the real-time CPU usage exceeds the preset CPU usage;

If the real-time CPU usage exceeds the preset CPU usage, interrupt merge information is generated based on the real-time CPU usage;

A hardware accelerator that transmits interrupt coalescing information to the server connection;

The hardware accelerator is controlled to perform interrupt coalescence, so that the hardware accelerator performs interrupt coalescence based on the interrupt coalescing information.

A computer-readable storage medium provided by an embodiment of the present application is applied to a server. A computer program is stored in the computer-readable storage medium. When the computer program is executed by a processor, the following steps are implemented: according to a preset load level and CPU usage rate The corresponding relationship between the two, determine the real-time load level of the business based on the real-time CPU usage; determine the maximum amount of business in the load level based on the preset CPU usage; determine the real-time business volume in the real-time load level; determine whether the real-time business volume is greater than the real-time business volume The maximum amount of load level. If the real-time business volume is greater than the maximum amount of the real-time load level, it is determined that the real-time CPU usage exceeds the preset CPU usage rate. If the real-time business volume is less than or equal to the maximum amount of the real-time load level, the real-time CPU usage is determined. The preset CPU usage is not exceeded.

A computer-readable storage medium provided by an embodiment of the present application is applied to a server, where a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the following steps are implemented: acquiring an interruption time slot corresponding to a real-time load level; Based on the maximum amount of real-time traffic and real-time load level, the real-time time slot to be merged is determined in the interruption time slot; the real-time time slot is used as interruption merge information.

A computer-readable storage medium provided by an embodiment of the present application is applied to a server, where a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the following steps are implemented: sending information for controlling a hardware accelerator to perform interrupt merging to hardware accelerator.

A computer-readable storage medium provided by an embodiment of the present application is applied to a server, where a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the following steps are implemented: an interupt on completion flag in an IO request is set. bit to control the hardware accelerator for interrupt coalescing.

A computer-readable storage medium provided by an embodiment of the present application is applied to a server. A computer program is stored in the computer-readable storage medium. When the computer program is executed by a processor, the following steps are implemented: obtaining a real-time CPU of its own service according to a preset period usage.

A computer-readable storage medium provided by an embodiment of the present application is applied to a hardware accelerator, where a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the following steps are implemented: receiving an interruption of transmission from a server connected to the hardware accelerator Merge information; under the control of the server, interrupt merging is performed based on the interrupt merging information; wherein, the server obtains the real-time CPU usage of its own business, and determines whether the real-time CPU usage exceeds the preset CPU usage. If the real-time CPU usage exceeds the preset CPU usage CPU usage, the interrupt coalescing information is generated based on real-time CPU usage.

The computer-readable storage medium referred to in this application includes random access memory (RAM), internal memory, read only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disks, removable disks, CD-ROMs , or any other form of storage medium known in the art.

For the description of the relevant parts of the interrupt processing system, device, and computer-readable storage medium provided by the embodiments of the present application, please refer to the detailed description of the corresponding parts of the interrupt processing method provided by the embodiments of the present application, and details are not repeated here. In addition, parts of the above technical solutions provided in the embodiments of the present application that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail, so as to avoid redundant descriptions.

It should also be noted that in this document, relational terms such as first and second are used only to distinguish one entity or operation from another, and do not necessarily require or imply those entities or operations There is no such actual relationship or order between them. Moreover, the terms "comprising", "comprising" or any other variation thereof are intended to encompass a non-exclusive inclusion such that a process, method, article or device that includes a list of elements includes not only those elements, but also includes not explicitly listed or other elements inherent to such a process, method, article or apparatus. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in a process, method, article or apparatus that includes the element.

The above description of the disclosed embodiments enables any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, this application is not intended to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (10)

1. An interrupt processing method, applied to a server, includes:

acquiring the real-time CPU utilization rate of the self service;

judging whether the real-time CPU utilization rate exceeds a preset CPU utilization rate or not;

if the real-time CPU utilization rate exceeds the preset CPU utilization rate, generating interrupt merging information based on the real-time CPU utilization rate;

transmitting the interrupt merge information to a hardware accelerator connected to the server;

and controlling the hardware accelerator to perform interrupt merging so that the hardware accelerator performs interrupt merging based on the interrupt merging information.

2. The method of claim 1, wherein the determining whether the real-time CPU usage rate exceeds a preset CPU usage rate comprises:

determining the real-time load grade of the service based on the real-time CPU utilization rate according to the corresponding relation between the preset load grade and the CPU utilization rate;

determining the maximum amount of traffic in the load class based on the preset CPU usage rate;

determining real-time traffic in the real-time load level;

and judging whether the real-time traffic is greater than the maximum of the real-time load level, if so, judging that the utilization rate of the real-time CPU exceeds the preset CPU utilization rate, and if not, judging that the utilization rate of the real-time CPU does not exceed the preset CPU utilization rate.

3. The method of claim 2, wherein generating interrupt coalescing information based on the real-time CPU utilization comprises:

acquiring an interrupt time slot corresponding to the real-time load grade;

determining a real-time slot to be merged in the interrupt time slot based on the real-time traffic and the maximum amount of the real-time load level;

and taking the real-time slot as the interrupt merging information.

4. The method of claim 1, wherein the controlling the hardware accelerator to perform interrupt coalescing comprises:

and sending information for controlling the hardware accelerator to perform interrupt merging to the hardware accelerator.

5. The method of claim 1, wherein the controlling the hardware accelerator to perform interrupt coalescing comprises:

setting an interrupt on completion flag bit in the IO request to control the hardware accelerator to perform interrupt merging.

6. The method according to claim 1, wherein the obtaining the real-time CPU utilization of the self-service comprises:

and acquiring the real-time CPU utilization rate of the self service according to a preset period.

7. An interrupt processing method applied to a hardware accelerator, comprising:

Receiving interrupt merging information transmitted by a server connected with the hardware accelerator;

performing interrupt merging based on the interrupt merging information under the control of the server;

the server acquires the real-time CPU utilization rate of own service, judges whether the real-time CPU utilization rate exceeds a preset CPU utilization rate, and generates the interruption merging information based on the real-time CPU utilization rate if the real-time CPU utilization rate exceeds the preset CPU utilization rate.

8. An interrupt processing system, applied to a server, comprising:

the first acquisition module is used for acquiring the real-time CPU utilization rate of the self service;

the first judgment module is used for judging whether the real-time CPU utilization rate exceeds a preset CPU utilization rate or not; if the real-time CPU utilization rate exceeds the preset CPU utilization rate, generating interrupt merging information based on the real-time CPU utilization rate;

the first transmission module is used for transmitting the interrupt merging information to a hardware accelerator connected with the server;

and the first control module is used for controlling the hardware accelerator to perform interrupt merging so as to enable the hardware accelerator to perform interrupt merging based on the interrupt merging information.

9. An interrupt processing device, comprising:

a memory for storing a computer program;

a processor for implementing the steps of the interrupt handling method of any of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the interrupt processing method according to any one of claims 1 to 7.

Images