CN116991594A - Load balancer creation method, device, equipment and storage medium - Google Patents
Load balancer creation method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN116991594A CN116991594A CN202311245854.1A CN202311245854A CN116991594A CN 116991594 A CN116991594 A CN 116991594A CN 202311245854 A CN202311245854 A CN 202311245854A CN 116991594 A CN116991594 A CN 116991594A
- Authority
- CN
- China
- Prior art keywords
- load balancing
- acceleration
- management platform
- cloud computing
- computing management
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 64
- 230000001133 acceleration Effects 0.000 claims abstract description 235
- 230000006870 function Effects 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 14
- 230000002093 peripheral effect Effects 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 5
- 238000005192 partition Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 14
- 238000004891 communication Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
- G06F9/505—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals considering the load
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5083—Techniques for rebalancing the load in a distributed system
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Stored Programmes (AREA)
Abstract
The application discloses a load balancer creation method, a device, equipment and a storage medium, and relates to the technical field of computers. The method comprises the following steps: adding acceleration instruction forwarding logic into a load balancing service component in the cloud computing management platform; and saving node information of a target node configured with an acceleration card to the cloud computing management platform, so that the cloud computing management platform forwards the acceleration instruction to a computing module of the cloud computing management platform according to the acceleration instruction forwarding logic after acquiring the acceleration instruction, and dispatching a cloud host for load balancing in the cloud computing management platform to the target node to operate according to the node information by utilizing the computing module. The load balancing service component of the cloud computing management platform is combined with the physical acceleration card, so that the data surface can accelerate encryption and decryption processing of the load balancer through the acceleration card, system performance loss is reduced, and overall performance is improved.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method, an apparatus, a device, and a storage medium for creating a load balancer.
Background
The cloud computing management platform (OpenStack) is used as an open-source infrastructure as a service (IaaS) cloud platform, the community provides a component (Octavia) for load balancing service, four-layer and seven-layer load balancing functions are realized, cloud hosts based on load balancing software (Haproxy) are defaulted, SSL (Secure Socket Layer )/TLS (secure transport layer protocol, transport Layer Security) protocol encryption and decryption actions are supported by the cloud hosts, and the cloud hosts can only encrypt and decrypt the cloud hosts based on a processor of the cloud hosts, so that performance bottlenecks can occur when high concurrent requests are processed. Therefore, how to implement encryption and decryption acceleration of load balancing service on a cloud computing management platform is a problem to be solved at present.
Disclosure of Invention
In view of the above, the present invention aims to provide a method, an apparatus, a device, and a storage medium for creating a load balancer, which can combine a load balancing service component of a cloud computing management platform with a physical accelerator card, and the data plane can accelerate encryption and decryption processing of the load balancer through the accelerator card, so as to reduce system performance loss. The specific scheme is as follows:
In a first aspect, the present application discloses a load balancer creation method, including:
adding acceleration instruction forwarding logic into a load balancing service component in the cloud computing management platform;
and saving node information of a target node configured with an acceleration card to the cloud computing management platform, so that the cloud computing management platform forwards the acceleration instruction to a computing module of the cloud computing management platform according to the acceleration instruction forwarding logic after acquiring the acceleration instruction, and dispatching a cloud host for load balancing in the cloud computing management platform to the target node to operate according to the node information by utilizing the computing module.
Optionally, the adding acceleration instruction forwarding logic to the load balancing service component in the cloud computing management platform includes:
and adding acceleration instruction forwarding logic into the load balancing service component in the cloud computing management platform by expanding an interface layer, a control layer, a scheduling layer and load balancing software corresponding to the load balancing service component.
Optionally, the adding acceleration instruction forwarding logic to the load balancing service component in the cloud computing management platform includes:
Adding an application programming interface into an interface layer corresponding to the load balancing service component; the application programming interface is used for receiving an acceleration instruction sent by a user.
Optionally, the adding acceleration instruction forwarding logic to the load balancing service component in the cloud computing management platform includes:
and adding issuing logic aiming at the acceleration instruction into a control layer corresponding to the load balancing service component so as to issue the acceleration instruction to the back end.
Optionally, the adding acceleration instruction forwarding logic to the load balancing service component in the cloud computing management platform includes:
and adding scheduling logic aiming at the cloud host under acceleration to a scheduling layer corresponding to the load balancing service component so as to schedule the load balancing cloud host to a target node for operation.
Optionally, the adding acceleration instruction forwarding logic to the load balancing service component in the cloud computing management platform includes:
and adding the configuration information of the accelerator card engine and the configuration information of the encryption and decryption engine when the acceleration is started into a configuration template of load balancing software in a bottom layer corresponding to the load balancing service component.
Optionally, before adding the acceleration instruction forwarding logic to the load balancing service component in the cloud computing management platform, the method further includes:
Creating a mirror image corresponding to a cloud host for load balancing in the load balancing service component, and configuring a driver of an acceleration card in the mirror image;
correspondingly, the scheduling the cloud host for load balancing in the cloud computing management platform to the target node for running includes:
and creating a target cloud host on the target node according to the mirror image.
Optionally, the configuring the driving of the accelerator card into the mirror image includes:
downloading the driver of the accelerator card to the mirror image, and compiling the driver of the accelerator card on the mirror image so as to add the driver of the accelerator card to the mirror image.
Optionally, the configuring the driving of the accelerator card into the mirror image includes:
and installing an engine corresponding to the accelerator card in the mirror image.
Optionally, after the target cloud host is created on the target node according to the mirror image, the method further includes:
and mounting the acceleration card on the target node to the target cloud host.
Optionally, the mounting the acceleration card on the target node on the target cloud host includes:
and mounting the acceleration card on the target node to the target cloud host by configuring the peripheral component interconnection bus address of the acceleration card.
Optionally, before the saving the node information of the target node configured with the accelerator card to the cloud computing management platform, the method further includes:
and searching whether the acceleration card parameters exist in the node information corresponding to each node, and screening out target nodes configured with the acceleration card from the node set corresponding to the cloud computing management platform.
Optionally, the acquiring an acceleration instruction includes:
and acquiring an acceleration instruction sent by a user after issuing a load balancer creation instruction.
Optionally, the scheduling the cloud host for load balancing in the cloud computing management platform to run on the target node includes:
creating a target cloud host on the target node according to the mirror image of the cloud host for load balancing in the cloud computing management platform;
initializing the target cloud host, adding acceleration card information into the configuration of load balancing software in the target cloud host, and starting the load balancing software after the addition is completed.
Optionally, the load balancer creating method further includes:
the single root virtualization of the accelerator card is configured to partition the physical accelerator card into management channels of multiple virtual functions.
Optionally, the load balancer creating method further includes:
And configuring the drive of the acceleration card in the mirror image corresponding to the cloud host for load balancing according to the configuration rule of single virtualization.
Optionally, the scheduling the cloud host for load balancing in the cloud computing management platform to run on the target node includes:
creating a target cloud host on the target node according to the mirror image;
and mounting a management channel of the virtual function of the acceleration card on the target node to the target cloud host.
In a second aspect, the present application discloses a load balancer creation apparatus, including:
the configuration module is used for adding acceleration instruction forwarding logic into a load balancing service component in the cloud computing management platform;
the node information storage module is used for storing node information of a target node configured with an acceleration card to the cloud computing management platform, so that after the cloud computing management platform acquires an acceleration instruction, the acceleration instruction is forwarded to a computing module of the cloud computing management platform according to the acceleration instruction forwarding logic, and a cloud host for load balancing in the cloud computing management platform is scheduled to the target node to operate according to the node information by utilizing the computing module.
In a third aspect, the present application discloses an electronic device, comprising:
a memory for storing a computer program;
and a processor for executing the computer program to implement the load balancer creation method.
In a fourth aspect, the present application discloses a computer-readable storage medium for storing a computer program; wherein the computer program, when executed by a processor, implements the load balancer creation method described previously.
In the application, acceleration instruction forwarding logic is added into a load balancing service component in a cloud computing management platform; and saving node information of a target node configured with an acceleration card to the cloud computing management platform, so that the cloud computing management platform forwards the acceleration instruction to a computing module of the cloud computing management platform according to the acceleration instruction forwarding logic after acquiring the acceleration instruction, and dispatching a cloud host for load balancing in the cloud computing management platform to the target node to operate according to the node information by utilizing the computing module.
The method has the beneficial effects that the acceleration instruction forwarding logic is added into the load balancing service component of the cloud computing management platform, and the information of the target node provided with the acceleration card is stored, so that the load balancing service component of the cloud computing management platform is combined with the physical acceleration card, the encryption and decryption processing of the load balancer can be accelerated by the acceleration card on the data surface, the system performance loss is reduced, and the overall performance is improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the related art, the drawings that are required to be used in the embodiments or the related technical descriptions will be briefly described, and it is apparent that the drawings in the following description are only embodiments of the present application, and other drawings may be obtained according to the provided drawings without inventive effort for those skilled in the art.
FIG. 1 is a flow chart of a method for creating a load balancer provided by the application;
FIG. 2 is a flowchart of a specific load balancer creation method provided by the present application;
FIG. 3 is a schematic diagram illustrating a specific acceleration card single root virtualization provided by the present application;
fig. 4 is a schematic structural diagram of a load balancer creating device according to the present application;
fig. 5 is a block diagram of an electronic device according to the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
In the related art, a cloud computing management platform is used as an open-source infrastructure, namely a service cloud platform, a community provides a component for load balancing service, four-layer and seven-layer load balancing functions are realized, cloud hosts based on load balancing software are defaulted, encryption and decryption actions of SSL/TLS protocols for processing https protocols are supported, but encryption and decryption can only be performed based on a processor of the cloud hosts by defaults, and thus performance bottlenecks can occur in high concurrent requests. In order to overcome the technical problems, the application provides a load balancer creation method, which can combine a load balancing service component of a cloud computing management platform with a physical acceleration card, and the data plane can accelerate encryption and decryption processing of the load balancer through the acceleration card, so that system performance loss is reduced.
The embodiment of the application discloses a load equalizer creation method, which is shown in fig. 1, and can comprise the following steps:
step S11: acceleration instruction forwarding logic is added to a load balancing service component in the cloud computing management platform.
In this embodiment, acceleration instruction forwarding logic is added to a load balancing service component in the cloud computing management platform, where the acceleration instruction is an acceleration instruction started for an acceleration card, and the acceleration card may be specifically an Intel QAT card (QuickAssist chip provided by Intel). In this embodiment, adding acceleration instruction forwarding logic to a load balancing service component in the cloud computing management platform may include: and adding acceleration instruction forwarding logic into the load balancing service component in the cloud computing management platform by expanding an interface layer, a control layer, a scheduling layer and load balancing software corresponding to the load balancing service component. The acceleration card is expanded through the control plane logic, so that the acceleration card is used by the load balancing service assembly.
In this embodiment, adding acceleration instruction forwarding logic to a load balancing service component in the cloud computing management platform may include: adding an application programming interface into an interface layer corresponding to the load balancing service component; the application programming interface is used for receiving an acceleration instruction sent by a user. Specifically, an extension interface (API, application Programming Interface, application programming interface) layer, and an acceleration instruction (qat _enable) for expanding and opening an acceleration card are obtained, and a user selects whether to start acceleration of the acceleration card when creating load balancing.
In this embodiment, adding acceleration instruction forwarding logic to a load balancing service component in the cloud computing management platform may include: and adding issuing logic aiming at the acceleration instruction into a control layer corresponding to the load balancing service component so as to issue the acceleration instruction to the back end. Namely, a control layer (controller layer) corresponding to the load balancing service component is expanded, and the acceleration instruction selected by a user can be ensured to be issued to the back end through a load balancing software driver (Amphora-driver) by adding issuing logic for the acceleration instruction.
In this embodiment, adding acceleration instruction forwarding logic to a load balancing service component in the cloud computing management platform may include: and adding scheduling logic aiming at the cloud host under acceleration to a scheduling layer corresponding to the load balancing service component so as to schedule the load balancing cloud host to a target node for operation. Adding scheduling logic aiming at the cloud host under acceleration to a scheduling layer corresponding to the load balancing service component, specifically, when a user selects acceleration, the load balancing service component transmits node information of a target node to a computing module (nova) of the load balancing service component, and the computing module schedules the cloud host for load balancing in the cloud computing management platform to a host node with an acceleration card.
In this embodiment, adding acceleration instruction forwarding logic to a load balancing service component in the cloud computing management platform may include: and adding the configuration information of the accelerator card engine and the configuration information of the encryption and decryption engine when the acceleration is started into a configuration template of load balancing software in a bottom layer corresponding to the load balancing service component. The method comprises the steps of expanding a configuration template of bottom layer load balancing software (haproxy), adding an acceleration card engine, and executing an acceleration card engine algorithm and an encryption and decryption engine algorithm if acceleration of the acceleration card is required to be started, wherein the acceleration card engine can adopt an asynchronous mode.
Therefore, the control plane realizes the automatic issuing of the acceleration card acceleration command through expanding the control logic of the load balancing service component, the load balancing cloud host is directionally scheduled to the computing node configured with the acceleration card equipment through expanding the acceleration command, and the data plane can accelerate the encryption and decryption processing through the QAT card by automatically configuring whether the load balancing software in the cloud host starts the acceleration card acceleration or not through sensing the acceleration command, so that the system performance loss is reduced, and the overall performance is improved.
Step S12: and saving node information of a target node configured with an acceleration card to the cloud computing management platform, so that the cloud computing management platform forwards the acceleration instruction to a computing module of the cloud computing management platform according to the acceleration instruction forwarding logic after acquiring the acceleration instruction, and dispatching a cloud host for load balancing in the cloud computing management platform to the target node to operate according to the node information by utilizing the computing module.
It can be understood that, at present, with the development of technologies such as mobile internet, the requirements of enterprise services on network and concurrency performance are higher and higher, and the enterprise needs to improve the performance and operation efficiency of service applications through a load balancer. Meanwhile, with the development of cloud computing technology, more and more enterprise businesses are already in cloud, network traffic is transferred to a cloud platform, and load balancing on the cloud is particularly important. In the related technology, the load balancer can process the workload of four layers and seven layers of networks, when processing the load of seven layers, https load is required to be received, encryption and decryption of SSL/TLS are required to be processed, the encryption and decryption of SSL/TLS belongs to computation intensive business, and when the business load is high, the performance of load balancing is influenced. Under the background, some manufacturers release SSL/TLS processing accelerator cards, such as QuickAssist (QAT for short) of Intel, which can accelerate SSL encryption and decryption based on hardware devices, so as to improve the performance of the load balancer. However, hardware equipment acceleration cannot be realized on the cloud platform at present, so in this embodiment, acceleration instruction forwarding logic is added to a load balancing service component of the cloud computing management platform, and information of a target node configured with an acceleration card is stored, so that the load balancing service component of the cloud computing management platform is combined with a physical acceleration card, and therefore, a data plane can accelerate encryption and decryption processing of a load balancer through the acceleration card, system performance loss is reduced, and overall performance is improved.
In this embodiment, for subsequent automated scheduling, the cloud computing management platform needs to know that the nodes configured with the accelerator card are those, so that node information of the target node configured with the accelerator card is saved to the cloud computing management platform. After the cloud computing management platform acquires the acceleration instruction, the acceleration instruction is forwarded to a computing module of the cloud computing management platform according to the acceleration instruction forwarding logic, and the computing module is utilized to schedule a cloud host for load balancing in the cloud computing management platform to any target node for operation according to the node information. At this time, the target node with the smallest load can be selected to operate according to the load conditions of all the current target nodes.
In this embodiment, before storing the node information of the target node configured with the accelerator card to the cloud computing management platform, the method may further include: and searching whether the acceleration card parameters exist in the node information corresponding to each node, and screening out target nodes configured with the acceleration card from the node set corresponding to the cloud computing management platform. If the acceleration card exists on the node, the acceleration card can be distinguished from the node information, so that whether the acceleration card parameter exists in the node information corresponding to each node is searched, and the target node provided with the acceleration card is screened out from the node set corresponding to the cloud computing management platform.
In this embodiment, before adding the acceleration instruction forwarding logic to the load balancing service component in the cloud computing management platform, the method may further include: creating a mirror image corresponding to a cloud host for load balancing in the load balancing service component, and configuring a driver of an acceleration card in the mirror image; correspondingly, the scheduling the cloud host for load balancing in the cloud computing management platform to run on the target node may include: and creating a target cloud host on the target node according to the mirror image. Specifically, a mirror image file corresponding to a cloud host is created in advance, and in order to support acceleration, a driver of an acceleration card is added in the mirror image file, and when a cloud host for load balancing in a cloud computing management platform is scheduled to a target node to run, a target cloud host is created in the target node according to the mirror image file.
In this embodiment, the configuring the driver of the accelerator card into the mirror image may include: downloading the driver of the accelerator card to the mirror image, and compiling the driver of the accelerator card on the mirror image so as to add the driver of the accelerator card to the mirror image. I.e., download and compile QAT card drivers.
In this embodiment, the configuring the driver of the accelerator card into the mirror image may include: and installing an engine corresponding to the accelerator card in the mirror image. I.e. the QAT card engine needs to be preset into the mirror image in addition to the driver, i.e. the QAT card engine (qatennine, which is a QAT using engine encapsulated by Intel following the OpenSSL standard) is installed.
In this embodiment, after the creating the target cloud host on the target node according to the image, the method may further include: and mounting the acceleration card on the target node to the target cloud host. And after the target cloud host is created, the acceleration card on the target node is mounted on the target cloud host.
In this embodiment, the mounting the acceleration card on the target node on the target cloud host may include: and mounting the acceleration card on the target node to the target cloud host by configuring the peripheral component interconnection bus address of the acceleration card. I.e., the information of the compute node is mounted to the target cloud host, specifically by configuring the peripheral component interconnect bus (Peripheral Component Interconnect, PCI) address of the accelerator card.
In this embodiment, the acquiring an acceleration instruction may include: and acquiring an acceleration instruction sent by a user after issuing a load balancer creation instruction. I.e. the user first creates a load balancer and then starts the hardware acceleration.
In this embodiment, the scheduling, to the target node, the cloud host for load balancing in the cloud computing management platform may include: creating a target cloud host on the target node according to the mirror image of the cloud host for load balancing in the cloud computing management platform; initializing the target cloud host, adding acceleration card information into the configuration of load balancing software in the target cloud host, and starting the load balancing software after the addition is completed. The initialization stage is carried out after the target cloud host is established, specifically, a configuration file of the load balancing software is configured according to an acceleration instruction issued by a user, namely, acceleration card information is added, and then the load balancing software is started after the addition is completed.
From the above, in this embodiment, acceleration instruction forwarding logic is added to a load balancing service component in the cloud computing management platform; and saving node information of a target node configured with an acceleration card to the cloud computing management platform, so that the cloud computing management platform forwards the acceleration instruction to a computing module of the cloud computing management platform according to the acceleration instruction forwarding logic after acquiring the acceleration instruction, and dispatching a cloud host for load balancing in the cloud computing management platform to the target node to operate according to the node information by utilizing the computing module.
Therefore, the method has the beneficial effects that by adding acceleration instruction forwarding logic to the load balancing service component of the cloud computing management platform and storing information of the target node configured with the acceleration card, the load balancing service component of the cloud computing management platform is combined with the physical acceleration card, so that the encryption and decryption processing of the load balancer can be accelerated by the acceleration card on the data surface, the system performance loss is reduced, and the overall performance is improved.
The embodiment of the application discloses a specific load balancer creation method, which is shown in fig. 2, and can comprise the following steps:
step S21: acceleration instruction forwarding logic is added to a load balancing service component in the cloud computing management platform.
Step S22: the single root virtualization of the accelerator card is configured to partition the physical accelerator card into management channels of multiple virtual functions.
In this embodiment, in order to improve the utilization rate of the accelerator card, a Single Root I/O Virtualization (SR-IOV) is performed on the accelerator card, so that the accelerator card is Virtual, for example, as shown in fig. 3, one QAT card provides multiple Virtual Functions (VF) for multiple target cloud hosts.
In this embodiment, the method further includes: and configuring the drive of the acceleration card in the mirror image corresponding to the cloud host for load balancing according to the configuration rule of single virtualization. I.e., it needs to be virtualized by a single root and used in the cloud host, so configuration conforming to single root virtualization is required at the time of drive installation.
Step S23: and saving node information of a target node configured with an acceleration card to the cloud computing management platform, so that the cloud computing management platform forwards the acceleration instruction to a computing module of the cloud computing management platform according to the acceleration instruction forwarding logic after acquiring the acceleration instruction, and dispatching a cloud host for load balancing in the cloud computing management platform to the target node to operate according to the node information by utilizing the computing module.
In this embodiment, the scheduling, to the target node, the cloud host for load balancing in the cloud computing management platform may include: creating a target cloud host on the target node according to the mirror image; and mounting a management channel of the virtual function of the acceleration card on the target node to the target cloud host. Specifically, when the virtual function of the accelerator card is mounted, the management channel of the virtual function of the accelerator card is mounted on the target cloud host.
The specific process of steps S21 to S23 may refer to the corresponding content disclosed in the foregoing embodiment, and will not be described herein.
From the above, in this embodiment, acceleration instruction forwarding logic is added to a load balancing service component in the cloud computing management platform; configuring single root virtualization of the acceleration card to divide the physical acceleration card into a plurality of management channels with virtual functions; and saving node information of a target node configured with an acceleration card to the cloud computing management platform, so that the cloud computing management platform forwards the acceleration instruction to a computing module of the cloud computing management platform according to the acceleration instruction forwarding logic after acquiring the acceleration instruction, and dispatching a cloud host for load balancing in the cloud computing management platform to the target node to operate according to the node information by utilizing the computing module. Therefore, a plurality of virtual functions can be provided for a plurality of target cloud hosts, and the utilization rate of the acceleration card is improved.
Correspondingly, the embodiment of the application also discloses a load balancer creation device, which is shown in fig. 4, and comprises:
the configuration module 11 is used for adding acceleration instruction forwarding logic into a load balancing service component in the cloud computing management platform;
The node information storage module 12 is configured to store node information of a target node configured with an acceleration card to the cloud computing management platform, so that after the cloud computing management platform acquires an acceleration instruction, the acceleration instruction is forwarded to a computing module of the cloud computing management platform according to the acceleration instruction forwarding logic, and a cloud host for load balancing in the cloud computing management platform is scheduled to run on the target node according to the node information by using the computing module.
From the above, in this embodiment, acceleration instruction forwarding logic is added to the load balancing service component in the cloud computing management platform; and saving node information of a target node configured with an acceleration card to the cloud computing management platform, so that the cloud computing management platform forwards the acceleration instruction to a computing module of the cloud computing management platform according to the acceleration instruction forwarding logic after acquiring the acceleration instruction, and dispatching a cloud host for load balancing in the cloud computing management platform to the target node to operate according to the node information by utilizing the computing module.
Therefore, the method has the beneficial effects that by adding acceleration instruction forwarding logic to the load balancing service component of the cloud computing management platform and storing information of the target node configured with the acceleration card, the load balancing service component of the cloud computing management platform is combined with the physical acceleration card, so that the encryption and decryption processing of the load balancer can be accelerated by the acceleration card on the data surface, the system performance loss is reduced, and the overall performance is improved.
In some specific embodiments, the configuration module 11 may specifically include:
and the expansion unit is used for adding acceleration instruction forwarding logic into the load balancing service component in the cloud computing management platform by expanding an interface layer, a control layer, a scheduling layer and load balancing software corresponding to the load balancing service component.
In some specific embodiments, the extension unit may specifically include:
the interface layer library expansion unit is used for adding an application programming interface into an interface layer corresponding to the load balancing service component; the application programming interface is used for receiving an acceleration instruction sent by a user.
In some specific embodiments, the extension unit may specifically include:
and the control layer expansion unit is used for adding issuing logic aiming at the acceleration instruction into the control layer corresponding to the load balancing service component so as to issue the acceleration instruction to the rear end.
In some specific embodiments, the extension unit may specifically include:
and the scheduling layer expansion unit is used for adding scheduling logic aiming at the cloud host under the acceleration condition into the scheduling layer corresponding to the load balancing service component so as to schedule the load balancing cloud host to the target node for running.
In some specific embodiments, the extension unit may specifically include:
the bottom layer expansion unit is used for adding the accelerating card engine configuration information and the encryption and decryption engine configuration information when the accelerating is started to the configuration template of the load balancing software in the bottom layer corresponding to the load balancing service component.
In some specific embodiments, the load balancer creating apparatus may specifically include:
the system comprises a mirror image creation unit, a load balancing service module and a cloud host, wherein the mirror image creation unit is used for creating a mirror image corresponding to the cloud host for load balancing in the load balancing service module before acceleration instruction forwarding logic is added into the load balancing service module in the cloud computing management platform, and configuring a driver of an acceleration card in the mirror image;
correspondingly, the node information storage module 12 may specifically include:
and the target cloud host creation unit is used for creating a target cloud host on the target node according to the mirror image.
In some specific embodiments, the image creation unit may specifically include:
and the drive adding unit is used for downloading the drive of the accelerator card to the mirror image and compiling the drive of the accelerator card on the mirror image so as to add the drive of the accelerator card to the mirror image.
In some specific embodiments, the image creation unit may specifically include:
and the engine installation unit is used for installing the engine corresponding to the accelerator card in the mirror image.
In some specific embodiments, the target cloud host creation unit may specifically include:
and the mounting unit is used for mounting the acceleration card on the target node to the target cloud host.
In some specific embodiments, the mounting unit may specifically include:
and the address configuration unit is used for mounting the acceleration card on the target node to the target cloud host by configuring the peripheral component interconnection bus address of the acceleration card.
In some specific embodiments, the load balancer creating apparatus may specifically include:
and the target node screening unit is used for intensively screening target nodes configured with the acceleration cards from the nodes corresponding to the cloud computing management platform by searching whether the acceleration card parameters exist in the node information corresponding to each node.
In some specific embodiments, the load balancer creating apparatus may specifically include:
the instruction acquisition unit is used for acquiring an acceleration instruction sent by a user after issuing a load balancer creation instruction.
In some specific embodiments, the node information saving module 12 may specifically include:
the target cloud host creation unit is used for creating a target cloud host on the target node according to the mirror image of the cloud host for load balancing in the cloud computing management platform;
the initialization unit is used for initializing the target cloud host, adding acceleration card information into the configuration of the load balancing software in the target cloud host, and starting the load balancing software after the addition is completed.
In some specific embodiments, the load balancer creating apparatus may specifically include:
and the single root virtualization unit is used for configuring single root virtualization of the acceleration card so as to divide the physical acceleration card into a plurality of management channels with virtual functions.
In some specific embodiments, the load balancer creating apparatus may specifically include:
and the drive configuration unit is used for configuring the drive of the acceleration card in the mirror image corresponding to the cloud host for load balancing according to the configuration rule of single virtualization.
In some specific embodiments, the load balancer creating apparatus may specifically include:
a target cloud host creation unit configured to create a target cloud host on the target node according to the mirror image;
And the management channel mounting unit is used for mounting the management channel of the virtual function of the acceleration card on the target node to the target cloud host.
Further, the embodiment of the application also discloses an electronic device, and referring to fig. 5, the content in the drawing should not be considered as any limitation on the application scope of the application.
Fig. 5 is a schematic structural diagram of an electronic device 20 according to an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input output interface 25, and a communication bus 26. Wherein the memory 22 is configured to store a computer program that is loaded and executed by the processor 21 to implement the relevant steps in the load balancer creation method disclosed in any of the foregoing embodiments. The method comprises the steps that acceleration instruction forwarding logic can be added to a load balancing service component in a cloud computing management platform; and saving node information of a target node configured with an acceleration card to the cloud computing management platform, so that the cloud computing management platform forwards the acceleration instruction to a computing module of the cloud computing management platform according to the acceleration instruction forwarding logic after acquiring the acceleration instruction, and dispatching a cloud host for load balancing in the cloud computing management platform to the target node to operate according to the node information by utilizing the computing module. Therefore, by adding acceleration instruction forwarding logic into the load balancing service component of the cloud computing management platform and storing information of the target node configured with the acceleration card, the load balancing service component of the cloud computing management platform is combined with the physical acceleration card, so that the encryption and decryption processing of the load balancing device can be accelerated by the acceleration card on the data surface, the system performance loss is reduced, and the overall performance is improved.
In this embodiment, the power supply 23 is configured to provide an operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and an external device, and the communication protocol to be followed is any communication protocol applicable to the technical solution of the present application, which is not specifically limited herein; the input/output interface 25 is used for acquiring external input data or outputting external output data, and the specific interface type thereof may be selected according to the specific application requirement, which is not limited herein.
The memory 22 may be a carrier for storing resources, such as a read-only memory, a random access memory, a magnetic disk, or an optical disk, and the resources stored thereon include an operating system 221, a computer program 222, and data 223 including node information, and the storage may be temporary storage or permanent storage.
The operating system 221 is used for managing and controlling various hardware devices on the electronic device 20 and the computer program 222, so as to implement the operation and processing of the processor 21 on the mass data 223 in the memory 22, which may be Windows Server, netware, unix, linux, etc. The computer program 222 may further include a computer program that can be used to perform other specific tasks in addition to the computer program that can be used to perform the load balancer creation method performed by the electronic device 20 disclosed in any of the foregoing embodiments.
Further, the embodiment of the application also discloses a computer storage medium, wherein the computer storage medium stores computer executable instructions, and when the computer executable instructions are loaded and executed by a processor, the steps of the load balancer creating method disclosed in any embodiment are realized.
The method comprises the steps that acceleration instruction forwarding logic can be added to a load balancing service component in a cloud computing management platform; and saving node information of a target node configured with an acceleration card to the cloud computing management platform, so that the cloud computing management platform forwards the acceleration instruction to a computing module of the cloud computing management platform according to the acceleration instruction forwarding logic after acquiring the acceleration instruction, and dispatching a cloud host for load balancing in the cloud computing management platform to the target node to operate according to the node information by utilizing the computing module. Therefore, by adding acceleration instruction forwarding logic into the load balancing service component of the cloud computing management platform and storing information of the target node configured with the acceleration card, the load balancing service component of the cloud computing management platform is combined with the physical acceleration card, so that the encryption and decryption processing of the load balancing device can be accelerated by the acceleration card on the data surface, the system performance loss is reduced, and the overall performance is improved.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, so that the same or similar parts between the embodiments are referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software modules may be disposed in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above describes in detail a method, apparatus, device and medium for creating a load equalizer, and specific examples are applied to illustrate the principles and embodiments of the present invention, where the above examples are only used to help understand the method and core idea of the present invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.
Claims (20)
1. A method for creating a load balancer, comprising:
adding acceleration instruction forwarding logic into a load balancing service component in the cloud computing management platform;
and saving node information of a target node configured with an acceleration card to the cloud computing management platform, so that the cloud computing management platform forwards the acceleration instruction to a computing module of the cloud computing management platform according to the acceleration instruction forwarding logic after acquiring the acceleration instruction, and dispatching a cloud host for load balancing in the cloud computing management platform to the target node to operate according to the node information by utilizing the computing module.
2. The method for creating a load balancer according to claim 1, wherein adding acceleration instruction forwarding logic to a load balancing service component in a cloud computing management platform comprises:
and adding acceleration instruction forwarding logic into the load balancing service component in the cloud computing management platform by expanding an interface layer, a control layer, a scheduling layer and load balancing software corresponding to the load balancing service component.
3. The method for creating a load balancer according to claim 2, wherein adding acceleration instruction forwarding logic to a load balancing service component in a cloud computing management platform comprises:
adding an application programming interface into an interface layer corresponding to the load balancing service component; the application programming interface is used for receiving an acceleration instruction sent by a user.
4. The method for creating a load balancer according to claim 2, wherein adding acceleration instruction forwarding logic to a load balancing service component in a cloud computing management platform comprises:
and adding issuing logic aiming at the acceleration instruction into a control layer corresponding to the load balancing service component so as to issue the acceleration instruction to the back end.
5. The method for creating a load balancer according to claim 2, wherein adding acceleration instruction forwarding logic to a load balancing service component in a cloud computing management platform comprises:
and adding scheduling logic aiming at the cloud host under acceleration to a scheduling layer corresponding to the load balancing service component so as to schedule the load balancing cloud host to a target node for operation.
6. The method for creating a load balancer according to claim 2, wherein adding acceleration instruction forwarding logic to a load balancing service component in a cloud computing management platform comprises:
and adding the configuration information of the accelerator card engine and the configuration information of the encryption and decryption engine when the acceleration is started into a configuration template of load balancing software in a bottom layer corresponding to the load balancing service component.
7. The method for creating a load balancer according to claim 1, further comprising, before adding acceleration instruction forwarding logic to a load balancing service component within a cloud computing management platform:
creating a mirror image corresponding to a cloud host for load balancing in the load balancing service component, and configuring a driver of an acceleration card in the mirror image;
Correspondingly, the scheduling the cloud host for load balancing in the cloud computing management platform to the target node for running includes:
and creating a target cloud host on the target node according to the mirror image.
8. The load balancer creation method according to claim 7, wherein said configuring the driver of the accelerator card into the mirror image includes:
downloading the driver of the accelerator card to the mirror image, and compiling the driver of the accelerator card on the mirror image so as to add the driver of the accelerator card to the mirror image.
9. The load balancer creation method according to claim 7, wherein said configuring the driver of the accelerator card into the mirror image includes:
and installing an engine corresponding to the accelerator card in the mirror image.
10. The load balancer creation method according to claim 7, further comprising, after the creating a target cloud host on the target node according to the image:
and mounting the acceleration card on the target node to the target cloud host.
11. The method for creating a load balancer of claim 10, wherein said mounting the acceleration card on the target node onto the target cloud host comprises:
And mounting the acceleration card on the target node to the target cloud host by configuring the peripheral component interconnection bus address of the acceleration card.
12. The load balancer creation method according to claim 1, wherein before saving node information of the target node configured with the accelerator card to the cloud computing management platform, further comprising:
and searching whether the acceleration card parameters exist in the node information corresponding to each node, and screening out target nodes configured with the acceleration card from the node set corresponding to the cloud computing management platform.
13. The load balancer creation method according to claim 1, wherein the acquisition acceleration instruction includes:
and acquiring an acceleration instruction sent by a user after issuing a load balancer creation instruction.
14. The method for creating a load balancer of claim 13, wherein the scheduling the cloud hosts for load balancing in the cloud computing management platform to run on the target node comprises:
creating a target cloud host on the target node according to the mirror image of the cloud host for load balancing in the cloud computing management platform;
initializing the target cloud host, adding acceleration card information into the configuration of load balancing software in the target cloud host, and starting the load balancing software after the addition is completed.
15. The load balancer creation method according to any one of claims 1 to 14, further comprising:
the single root virtualization of the accelerator card is configured to partition the physical accelerator card into management channels of multiple virtual functions.
16. The load balancer creation method of claim 15, further comprising:
and configuring the drive of the acceleration card in the mirror image corresponding to the cloud host for load balancing according to the configuration rule of single virtualization.
17. The method for creating a load balancer of claim 16, wherein the scheduling the cloud hosts for load balancing in the cloud computing management platform to run on the target node comprises:
creating a target cloud host on the target node according to the mirror image;
and mounting a management channel of the virtual function of the acceleration card on the target node to the target cloud host.
18. A load balancer creation apparatus, comprising:
the configuration module is used for adding acceleration instruction forwarding logic into a load balancing service component in the cloud computing management platform;
the node information storage module is used for storing node information of a target node configured with an acceleration card to the cloud computing management platform, so that after the cloud computing management platform acquires an acceleration instruction, the acceleration instruction is forwarded to a computing module of the cloud computing management platform according to the acceleration instruction forwarding logic, and a cloud host for load balancing in the cloud computing management platform is scheduled to the target node to operate according to the node information by utilizing the computing module.
19. An electronic device, comprising:
a memory for storing a computer program;
a processor for executing the computer program to implement the load balancer creation method of any of claims 1 to 17.
20. A computer-readable storage medium storing a computer program; wherein the computer program when executed by a processor implements the load balancer creation method of any of claims 1 to 17.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311245854.1A CN116991594B (en) | 2023-09-26 | 2023-09-26 | Load balancer creation method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311245854.1A CN116991594B (en) | 2023-09-26 | 2023-09-26 | Load balancer creation method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116991594A true CN116991594A (en) | 2023-11-03 |
| CN116991594B CN116991594B (en) | 2024-02-09 |
Family
ID=88525107
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311245854.1A Active CN116991594B (en) | 2023-09-26 | 2023-09-26 | Load balancer creation method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116991594B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111240800A (en) * | 2020-01-03 | 2020-06-05 | 华云数据有限公司 | Hardware acceleration equipment mounting method and cloud platform |
| CN111935238A (en) * | 2020-07-16 | 2020-11-13 | 浪潮思科网络科技有限公司 | Cloud platform load balancing management system, method, equipment and medium |
| CN114356456A (en) * | 2022-01-12 | 2022-04-15 | 北京金山云网络技术有限公司 | Service processing method, device, storage medium and electronic equipment |
| CN114995961A (en) * | 2022-08-04 | 2022-09-02 | 浙江大学 | Request scheduling method, device and storage medium |
| CN116383248A (en) * | 2023-04-28 | 2023-07-04 | 山东浪潮科学研究院有限公司 | Data query task acceleration method, device, equipment and storage medium |
-
2023
- 2023-09-26 CN CN202311245854.1A patent/CN116991594B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111240800A (en) * | 2020-01-03 | 2020-06-05 | 华云数据有限公司 | Hardware acceleration equipment mounting method and cloud platform |
| CN111935238A (en) * | 2020-07-16 | 2020-11-13 | 浪潮思科网络科技有限公司 | Cloud platform load balancing management system, method, equipment and medium |
| CN114356456A (en) * | 2022-01-12 | 2022-04-15 | 北京金山云网络技术有限公司 | Service processing method, device, storage medium and electronic equipment |
| CN114995961A (en) * | 2022-08-04 | 2022-09-02 | 浙江大学 | Request scheduling method, device and storage medium |
| CN116383248A (en) * | 2023-04-28 | 2023-07-04 | 山东浪潮科学研究院有限公司 | Data query task acceleration method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116991594B (en) | 2024-02-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10735345B2 (en) | Orchestrating computing resources between different computing environments | |
| US7823023B2 (en) | Test framework for testing an application | |
| CN102427481B (en) | System for managing cloud computing service and cloud computing management method | |
| CN108089913B (en) | Virtual machine deployment method of super-fusion system | |
| US7886292B2 (en) | Methodology of individualized software deployment for hardware-independent personal computer mass development | |
| CN101207516B (en) | Remote installation performance improvement on management controllers in monolithic and modular systems | |
| CN110058894B (en) | Method, apparatus and computer program product for executing applications in a hybrid cloud | |
| US7882232B2 (en) | Rapid resource provisioning with automated throttling | |
| CN110855746A (en) | Middleware management method, electronic device and storage medium | |
| CN106911741B (en) | Method for balancing virtual network management file downloading load and network management server | |
| CN114489954A (en) | Tenant creation method based on virtualization platform, tenant access method and equipment | |
| EP3193253B1 (en) | Method, apparatus and system for displaying names of virtual machine | |
| CN114490062A (en) | Local disk scheduling method and device, electronic equipment and storage medium | |
| CN113268254A (en) | Cluster system installation method and device, electronic equipment and storage medium | |
| JP2023545985A (en) | Managing task flows in edge computing environments | |
| CN116991594B (en) | Load balancer creation method, device, equipment and storage medium | |
| US20230138867A1 (en) | Methods for application deployment across multiple computing domains and devices thereof | |
| CN112860421A (en) | Method, apparatus and computer program product for job processing | |
| US7571221B2 (en) | Installation of network services in an embedded network server | |
| CN112152988B (en) | Method, system, computer device and medium for asynchronous NBMP request processing | |
| CN110661852B (en) | Service processing method and device in cloud environment | |
| CN111431951B (en) | Data processing method, node equipment, system and storage medium | |
| CN111008043A (en) | Server starting method of cloud platform and terminal | |
| US11953972B2 (en) | Selective privileged container augmentation | |
| US20240028375A1 (en) | Control plane lifecycle management with dpu devices |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |