CN114928615A - Load balancing method, device, equipment and readable storage medium - Google Patents

Abstract

The present application discloses a load balancing method, device, device and readable storage medium. When a new host is added to the load balancing system, the load balancer receives a data packet. If the quintuple of the data packet does not exist in the mapping table, Then, the effective RS for load balancing is determined from the RSs of each host included in the load balancing system, and the target RS is selected from the effective RS and the data packet is sent to the target RS, thereby completing the second load balancing. With this solution, after each new host is added, the load balancer determines the target RS from the valid RSs and sends data packets, ensuring that the load balancer on the newly added host has sufficient time to generate mappings for existing services The mapping table records the mapping relationship between the quintuple of the existing service and the RS, so as to prevent the load balancer from sending the data packet of the existing service to the incorrect RS, and achieve the purpose of improving the service quality.

Description

Load balancing method, apparatus, device and readable storage medium

technical field

The present application relates to the technical field of load balancing, and in particular, to a load balancing method, apparatus, device, and readable storage medium.

Background technique

With the development of cloud technology, the number of accesses faced by servers increases rapidly, and servers need to have the ability to handle large-scale concurrent service accesses. For heavily loaded servers, CPU and I/O processing capabilities quickly become bottlenecks, and the performance of a single server is always limited. Simply improving hardware performance cannot really solve the problem. Therefore, multi-server and load balancing (Load Balance, LB) technology must be adopted to meet the needs of large-scale concurrent service access.

Load balancing refers to: using a load balancer to share a large amount of concurrent access or data traffic to multiple real servers, which are processed by the real servers, reducing the time for users to wait for a response. In a cloud platform, a load balancer usually adopts a Linux virtual server (Linux Virtual Server, LVS) architecture, which consists of a front-end load balancer (LoadBalancer, LB) and a background real server (Real Server, RS) group. After receiving the service request from the client, the LB schedules and forwards the service request to the RS according to the preset scheduling forwarding policy and load balancing scheduling algorithm, and the RS processes the service request and returns a response result. However, LVS load balancing technology has the disadvantages of high performance overhead and LB is easily affected by sudden load increase.

To overcome the problem of the LVS load balancing technology, the industry introduces a load balancing architecture of eXpress Data Path (XDP). However, based on the XDP architecture, when a new host is added to the cluster, the connection of the ongoing business in the cluster will be abnormally disconnected, and the abnormality is proportional to the number of newly added hosts, resulting in abnormal ongoing business.

SUMMARY OF THE INVENTION

The present application provides a load balancing method, device, device and readable storage medium. By improving the load balancer, the impact on existing services when a new host is added based on the XDP architecture can be solved, and the purpose of improving service reliability can be achieved. .

In a first aspect, an embodiment of the present application provides a load balancing method, which is applied to a load balancer on a host in a load balancing system, and the method includes:

Determine that there is a new host in the load balancing system, the load balancer is a load balancer on any one of the multiple hosts included in the load balancing system, and each host in the multiple hosts is deployed on Load Balancer and Real Server RS;

receive packets;

The effective RS is determined from the RSs of each host included in the load balancing system, and the effective RS is the RS involved when the load balancer performs load balancing on the data packets of the existing services before the new host is added. There is a business that the load balancing system is providing to the user before the new host is added;

Determine the target RS from the valid RS;

The data packet is sent to the target RS.

In a second aspect, an embodiment of the present application provides a load balancing method, which is applied to a query device in a load balancing system, and the method includes:

receiving a notification request sent by an RS on a newly added host in the load balancing system, where the notification request is used to indicate the virtual IP address VIP of the RS;

Record the VIP and the notification time point, the notification time point is the time point when the query device receives the notification request, and the VIP and the notification time point are used to determine whether the RS on the newly added host is It is transformed into an effective RS, and the effective RS in the load balancing system is the RS involved when the load balancer in the load balancing system performs load balancing on the data packets of the existing service, and the existing service is before the new host is added. The service that the load balancing system is providing to the user.

In a third aspect, an embodiment of the present application provides a load balancing device, a load balancer integrated on a host in a load balancing system, the device comprising:

The determining module is configured to determine that a new host exists in the load balancing system, the load balancer is a load balancer on any one of the multiple hosts included in the load balancing system, and each of the multiple hosts A load balancer and a real server RS are deployed on each host;

A receiving module for receiving data packets;

A processing module, configured to determine an effective RS from the RSs of each host included in the load balancing system, where the effective RS is involved when the load balancer performs load balancing on the data packets of existing services before the new host is added RS, the existing service is the service that the load balancing system is providing to the user before the new host is added, and the target RS is determined from the valid RS;

A sending module, configured to send the data packet to the target RS.

In a fourth aspect, an embodiment of the present application provides a load balancing device integrated on a query device in a load balancing system, the device comprising:

a transceiver module, configured to receive a notification request sent by an RS on a newly added host in the load balancing system, where the notification request is used to indicate the virtual IP address VIP of the RS;

A processing module, configured to record the VIP and the notification time point, the notification time point is the time point when the query device receives the notification request, and the effective RS in the load balancing system is before the newly added host , the RS involved when the load balancer in the load balancing system performs load balancing on the data packets of the existing service, and the existing service is the service that the load balancing system is providing to the user before the new host is added.

In a fifth aspect, an embodiment of the present application provides an electronic device, including: a processor, a memory, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program so that all The electronic device implements the method described in the first aspect or various possible implementation manners of the first aspect.

In a sixth aspect, an embodiment of the present application provides an electronic device, including: a processor, a memory, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program so that all The electronic device implements the method described in the second aspect or various possible implementation manners of the second aspect.

In a seventh aspect, embodiments of the present application provide a computer-readable storage medium, where computer instructions are stored in the computer-readable storage medium, and when executed by a processor, the computer instructions are used to implement the first aspect or the first aspect above. The method described in various possible implementations of the aspect.

In an eighth aspect, embodiments of the present application provide a computer-readable storage medium, where computer instructions are stored in the computer-readable storage medium, and when executed by a processor, the computer instructions are used to implement the second aspect or the second aspect above. The method described in various possible implementations of the aspect.

In a ninth aspect, an embodiment of the present application provides a load balancing system, including a switch, multiple hosts, and a query device, the switch establishes a network connection with each of the multiple hosts, and the query device is connected to the multiple hosts. Each of the hosts establishes a network connection, where:

the switch, configured to perform load balancing to determine a target load balancer from the load balancers included in the plurality of hosts and send data packets;

A load balancer and a real server RS are deployed on each of the multiple hosts, and the load balancer is configured to execute the load balancing method described in the first aspect or various possible implementation manners of the first aspect.

The query device is configured to execute the load balancing method described in the second aspect or various possible implementation manners of the second aspect.

In the load balancing method provided by the embodiment of the present application, when the load balancer on each host in the load balancing system detects a new host in the load balancing system, once a load balancer receives a data packet, if the load balancer does not exist in the mapping table The five-tuple of the data packet, the effective RS for load balancing is determined from the RSs of each host included in the load balancing system, the target RS is selected from the effective RS, and the data packet is sent to the target RS, thereby completing the second Secondary load balancing. With this solution, after each new host is added, the load balancer determines the target RS from the valid RSs and sends data packets, ensuring that the load balancer on the newly added host has sufficient time to generate mappings for existing services The mapping table records the mapping relationship between the quintuple of the existing service and the RS, so as to prevent the load balancer from sending the data packet of the existing service to the incorrect RS. That is to say, each time a host is added, the load balancer on the host takes effect, but the RS does not immediately participate in load balancing. Instead, the mapping table of the load balancer on the host to be added saves all existing services in the mapping table. After the mapping relationship between the tuple and the RS, the RS on the newly added host is used for load balancing to ensure that the data packets of the existing services after the newly added host are sent to the correct RS, and the purpose of improving the service quality is achieved without any modification. switches, reducing the impact surface and operational complexity.

Description of drawings

In order to illustrate the technical solutions in the embodiments of the present application more clearly, the following briefly introduces the drawings that are used in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can also be obtained from these drawings without creative effort.

FIG. 1 is a schematic diagram of the architecture of a load balancing system to which the load balancing method provided by an embodiment of the present application is applicable;

2 is a schematic diagram of a working level of an XDP-based load balancing architecture provided by an embodiment of the present application on a host;

FIG. 3 is a flowchart of a load balancing method provided by an embodiment of the present application;

FIG. 4 is another flowchart of the load balancing method provided by the embodiment of the present application;

FIG. 5 is a schematic diagram of an application scenario of the load balancing method provided by an embodiment of the present application;

FIG. 6 is a schematic diagram of a load balancing apparatus provided by an embodiment of the present application;

FIG. 7 is a schematic diagram of another load balancing apparatus provided by an embodiment of the present application;

FIG. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application

Detailed ways

In order to make the objectives, technical solutions and advantages of the present application clearer, the embodiments of the present application will be further described in detail below with reference to the accompanying drawings.

With the development of cluster technology, load balancing, as the core of cluster technology, has also received extensive attention and research. While load balancing ensures that the load on the backend servers is equal, it also needs to ensure that packets belonging to the same connection are sent to the same backend server. The quintuple of packets belonging to the same connection is the same.

Load balancing aims to provide high-availability and high-performance cluster technology. It provides a cheap, effective and transparent method to expand the bandwidth of the cluster, increase the throughput of the cluster, strengthen the cluster's ability to process network data, and ensure high service availability.

The existing four-layer load balancing technology uses the LVS architecture, which is a TCP/IP-based load balancing technology, implemented through an IP Virtual Server (IP Virtual Server, IPVS) module, and works in the kernel. The LVS architecture has the following disadvantages:

First, the performance overhead is serious.

Based on the LVS architecture, the forwarding of data packets needs to pass through the network card and the kernel system to achieve forwarding. From a design point of view, in order to ensure security and isolation of the operating system, data packets must go through: allocation of socket buffers (Socket Buffer, SKB), socket locking, TCP (or UDP)... …protocol stack, kernel mode and user mode switching. Causes serious performance overhead. At the same time, the LVS architecture needs to ensure synchronization between the load balancers in the cluster, resulting in an abnormal increase in traffic and high performance overhead of the load balancer.

Second, load balancers are susceptible to load spikes.

Based on the LVS architecture, due to the high performance overhead, the possibility of equipment failure will increase when the data traffic is large. Therefore, in order to reduce the machine failure rate, the number of load balancers is less than the number of RSs by placing the load balancer and the RS that the backend really provides services on different hosts, which makes the load balancer vulnerable to load surges. influences. This problem is exacerbated by the fact that packets go through the regular linux networking stack before being processed by the load balancer.

In order to overcome the problems of LVS load balancing technology, the industry has introduced a load balancing architecture based on XDP. In this architecture, the data packets are directly filtered or processed before entering the user mode. Compared with the LVS-based load balancing architecture, the XDP-based load balancing architecture has better performance. The XDP-based load balancing architecture has the following advantages:

a. Timely and efficient packet processing.

Under the XDP-based load balancing architecture, after the load balancer is enabled in driver mode, the load balancer processes the data packets after the network card receives the data packets and before the kernel intercepts the data packets. During the processing, for each incoming data packet, the load balancer will always call the Berkeley Packet Filter (BPF) procedure. If the network card has multiple queues, the load balancer calls the BPF program in parallel for each queue. Also, the BPF program used to process packets is lock-free, using a BPF map specific to each CPU. Based on this parallel mechanism, the performance of load balancing scales linearly with the number of receive queues of the network card.

b. There is no need to ensure synchronization between load balancers in the cluster.

The XDP-based load balancing architecture uses a consistent hash algorithm to replace the traditional load balancing algorithm, avoiding the LVS-based load balancing architecture to ensure synchronization between load balancers in the cluster, so it can avoid abnormal traffic and load balancing The problem of high performance overhead.

c. Provide a fast path

The XDP-based load balancing architecture provides a fast path for processing packets at high speed, and the load balancer and RS are deployed on the same host to run together without any performance degradation. At the same time, it enhances the adaptability in the face of load surges, host failures and maintenance.

The same point between the XDP-based load balancing architecture and the LVS-based load balancing architecture is that the load balancer needs to have a routing protocol with the switch in the computer room, such as the Open Shortest Path First (OSPF) protocol, in order to The outside world advertises the virtual IP address (vertical IP, VIP) of the load balancer. After that, the client can send the packet to the corresponding load balancer in the cluster. Finally, the load balancer selects one RS from the multiple RSs according to the load balancing algorithm, and sends the data packet to the RS.

Usually, the number of hosts in the cluster is unavoidable and frequent when the cluster provides services to the outside world. Actual usage discovery: When a host is added to the cluster, the data packet originally sent to RS A of the cluster is sent to RS B, causing an exception to the ongoing business in the cluster. Moreover, the proportion of anomalies increases with the number of new hosts.

In order to add machines to the cluster, the industry considers improving the switches. But in reality, a switch is connected to many hosts, and each host has traffic. If the switch is changed, it means that when a machine needs to be added or replaced in the cluster due to changes in planning or machine downtime, if it is achieved by changing the switch, all the traffic of the entire cluster needs to be backed up. The ongoing business has an impact, consumes manpower and material resources, leads to poor business quality, and causes customer complaints. Among them, the ongoing service is referred to as an old service, an existing service, etc., and a connection for transmitting data packets of an ongoing service is referred to as an old connection.

Obviously, the existing XDP-based load balancing architecture cannot add new machines to the cluster, which greatly limits the scalability and availability of the cluster.

Based on this, the embodiments of the present application provide a load balancing method, apparatus, device, and readable storage medium. By improving the load balancer, the load balancer has the function of querying the mount duration of each RS, so as to solve the problem based on XDP It can improve the reliability of the service without changing the switch when the new server is added.

FIG. 1 is a schematic structural diagram of a load balancing system to which the load balancing method provided by the embodiment of the present application is applicable. Referring to FIG. 1 , the load balancing system includes a host 11 , a query device 12 , a switch 13 and a terminal device 14 . A network connection is established between the inquiring device 12 and each host 11 . A network connection is established between each host 11 and the switch 13 , and a network connection is established between the terminal device 14 and the switch 13 .

The host 11 is also referred to as a machine, a server, etc., and an XDP-based load balancer 111 and an RS 112 are deployed on each host 11 . The load balancer 111 has the function of querying the VIP of each RS 112 , and can obtain the VIP of the RS 112 on each host 11 and the announcement time point of the VIP through the query device 12 . It should be noted that since the load balancer 111 and the RS12 are deployed on each host 11, the VIP of the host 11, the load balancer 111 on the host 11, and the VIP of the RS112 on the host 11 are the same.

The query device 12 is also called an IP watcher component, which can be a machine independent of the host 11, or a host 11. While deploying the load balancer 111 and the RS 112 on the host 11, it also saves each host in the load balancing system. 11's VIP and the announcement time of the VIP. Each time a host 11 is added in the load balancing system, the RS 112 of the newly added host 11 announces the VIP to the query device 12, and the query device 12 records the VIP of the RS 112 and the notification time point. It can be seen that the query device 12 is used to collect and record the VIP of each RS 112 in the load balancing system and the notification time point. The announcement time point is the time point when the host 11 is added.

The switch 13 is used to connect the terminal device 14 and the host 11 for the first load balancing. After receiving the data packet from the terminal device 14, the switch 13 selects one host 11 from the plurality of hosts 11 and transmits the data packet. After receiving the data packet, the load balancer 111 of the selected host 11 executes the load balancing method provided by the embodiment of the present application to perform a second load balancing, selects a target RS from multiple RSs 112, and sends the data packet to the target RS.

The terminal device 14 may be hardware or software. When the terminal device 14 is hardware, the terminal device 14 is, for example, a mobile phone, tablet computer, personal computer, e-book reader, Laptops, desktops, etc. When the terminal device 14 is software, it can be installed in the hardware devices listed above. In this case, the terminal device 14 is, for example, multiple software modules or a single software module, which is not limited in the embodiment of the present application.

Referring to FIG. 1 , the load balancer 111 uses Fast Reroute (FRR), quagga, etc. to perform peering with the switch 13 , and advertises the VIP of the load balancer 111 to the switch 13 . Then, the switch 13 uses the Equal-Cost Multipath Routing (ECMP) mechanism to select a target load balancer from the load balancers 111 that have advertised the VIP and send the data packet, thereby completing the first load balancing. The load balancer 111 usually uses an Open Shortest Path First (Open Shortest Path First, OSPF) routing protocol or the like when advertising the VIP to the switch 13 .

It can be known from the above that there are two types of VIP advertisements in this embodiment of the present application. One is that the load balancer 111 uses the OSPF routing protocol to advertise the VIP of the load balancer 111 to the outside world, that is, to the switch 13 and the like. One is that RS112 announces the VIP of RS112 to the inquiry device 12 .

After the first load balancing, after the data packet reaches the load balancer 111 through the switch 13, the load balancer 111 will select the target RS from the RS112 on the host 11 included in the load balancing system, and send the data packet to the target RS, This completes the second load balancing. In order to ensure that data packets of the same service are sent to the same target RS, the load balancer 111 will use a consistent hashing algorithm after receiving the first data packet of a service. The consistent hash algorithm determines the target RS according to the quintuple of the data packet, the VIP of each RS in the load balancing system, and the number of RSs. After the target RS is determined for the first data packet of a service, the load balancer 111 records the mapping relationship between the quintuple of the first data packet and the target RS in the local mapping table. In this way, after each subsequent load balancer 111 receives a data packet of the same service, the target RS can be determined by querying the mapping table according to the quintuple of the data packet.

That is to say, in this embodiment of the present application, after each time the load balancer 111 receives a data packet, it preferentially queries the mapping table according to the quintuple of the data packet. The RS corresponding to the tuple is used as the target RS. If the quintuple of the data packet does not exist in the mapping table, the valid RS is determined, and the target RS is determined from the valid RS.

With this solution, the load balancer first checks the mapping table to determine the target RS each time it performs the second load balancing, and only determines the target RS from the valid RSs when the target RS cannot be determined by querying the mapping table. , to avoid the performance consumption caused by repeated consistent hashing.

Optionally, in the above embodiment, after the load balancer determines the target RS from the valid RS, the mapping relationship between the quintuple of the data packet and the target RS is added to the mapping table. In this way, each time a new mapping relationship between the quintuple and the RS is determined, a new record is added to the mapping table. Since the quintuple of the data packets of the same service is the same, after receiving the data packets of the same service, the target RS can be determined by directly querying the mapping table without performing consistent hash operation, which is fast and consumes performance. Low.

With this solution, by storing the mapping relationship between the quintuple and the target RS in the mapping table, the performance consumption caused by the subsequent repeated execution of consistent hashing can be avoided.

Optionally, in the above-mentioned embodiment, when the load balancer determines the target RS from the effective RS, it performs a consistent hash operation according to the VIP of the effective RS, the quintuple of the data packet, the number of the effective RS, etc., so as to determine the target RS. Target RS.

In addition, since the quintuple of all data packets of the same service is the same, when the number of RSs in the load balancing system remains unchanged, no matter which load balancer 111 receives the data packet, it can The packets are sent to the same target RS. Therefore, synchronization of the various load balancers 111 within the load balancing system is not required.

When a host 11 is added in the load balancing system, it is equivalent to adding a load balancer 111 and an RS 112 at the same time. The switch 13 uses the OSPF routing protocol to perform the first load balancing to determine the target load balancer, and it is likely to send the data packet to the load balancer 111 on the newly added host 11, and the mapping table of the load balancer 111 is empty.

The addition of host 11 results in a change in the number of RS112s, which in turn results in a change in the results of the consistent hashing algorithm. Therefore, in the traditional XDP-based load balancing architecture, when the load balancer 111 receives a data packet, and the data packet is a data packet of an existing service, the load balancer 111 determines the target according to the consistent hash algorithm The RS may not be the correct RS. For example, the load balancer 111 sends the data packet that should be sent to RS A to RS B. After RS B receives the data packet, since there is no information such as the quintuple of the existing service on RS B, it directly discards the data packet or feeds back a reset (reset, RST), resulting in an abnormality of the existing service. Obviously, the first load balancing of the switch 13 and the second load balancing of the load balancer 111 cause the proportion of existing service exceptions to soar when a host 11 is added to the load balancing system.

It can be understood that: an existing service refers to at least one host 11 in the load balancing system before the new host 11 is added, and the mapping table of the load balancer 111 on the host 11 contains the quintuple of the service and the target RS. Correspondence. For example, for a video service, before adding a host 11, there are three hosts 11 in the load balancing system, and correspondingly, there are three load balancers in the load balancing system. If the mapping relationship between the quintuple of the video service and the target RS is recorded in the mapping table of all or part of the load balancer, it indicates that the video service is an existing service.

In the embodiment of the present application, each time a host 11 is added, the RS 112 on the new host 11 reports the VIP to the query device 12 , and the query device 12 records the VIP and the notification time point of the RS 112 on the new host 11 . Moreover, each time a new host 11 is added, the function of the load balancer 111 on the newly added host 11 is enabled, and the function of the RS112 on the newly added host 11 is not enabled for the time being, but the newly added host 11 is enabled after a preset time period. function on the RS112. After the function of the RS112 on the newly added host 11 is enabled, the load balancer 111 considers the RS112 when performing the consistent hash operation.

After receiving the data packet, the load balancer 111 determines, from the multiple RSs 112, the RS 112 whose mounting duration exceeds the preset duration as the effective RS 112. After that, the target RS is determined from the valid RS 112 and a data packet is sent. That is to say, after each new host 11 is added, the RS 112 on the newly added host 11 does not immediately participate in the consistent hashing algorithm, and only participates in the consistent hashing algorithm after a preset time period. Within the preset time period, initially, the mapping table of the load balancer 111 on the newly added host 11 is empty. After that, after each data packet is received, if the quintuple of the data packet does not exist in the mapping table, consistent hashing is performed according to the valid RS112, the quintuple of the data packet, etc., to determine the target RS and send the data packet. At the same time, the load balancer 111 on the newly added host 11 records the mapping relationship between the quintuple and the target RS in the mapping table.

In this way, after the preset time period has elapsed for the newly added host 11, the mapping table of the load balancer 111 on the newly added host 11 will record the mapping relationship between the quintuple of the data packets of all existing services and the target RS. After the preset time period, the RS112 on the newly added host 11 takes effect. At this time, if the consistent hash algorithm is used to determine the target RS of the data packet of the existing service, an error is likely to occur. However, for the data packets of existing services, the load balancer 111 preferentially queries the mapping table, so that the correct target RS can be determined. For the data packet of the new service, the load balancer 111 performs a consistent hash algorithm to determine the target RS according to the currently valid RS 112, the quintuple of the data packet of the new service, etc., and adds a new record to the mapping table.

For the load balancer 111 on the original host 11 in the load balancing system, if the mapping table of the load balancer 111 already has a mapping relationship between the quintuple of the existing service data packet and the target RS, the mapping relationship can be obtained by querying the mapping The table can determine the correct target RS. If there is no mapping relationship between the quintuple of the data packet of the existing service and the target RS in the mapping table, the target RS can also be determined according to the effective RS112, the quintuple of the data packet, etc., and the target RS can be sent to send the data packet. .

It should be understood that the numbers of hosts 11, query devices 12, switches 13 and terminal devices 14 in FIG. 1 are only illustrative. In actual implementation, any number of hosts 11 , query devices 12 , switches 13 and terminal devices 14 are deployed according to actual requirements.

FIG. 2 is a schematic diagram of a working level of an XDP-based load balancing architecture on a host provided by an embodiment of the present application. Referring to FIG. 2 , the working layers on the host include: a network card driver, a load balancer, a kernel (kernel) user process, and the like. The load balancer is an XDP-based load balancer, and the user process is a related process in the user mode. When the RS on the host is an edge node in a Content Delivery Network (CDN), the user mode has a squid cache and a shark (scheduling) component.

Referring to Figure 2, the host is enabled in driver mode, and the data packet processing is performed after the network card receives the data packet and before the kernel intercepts it, avoiding the overhead caused by switching between user mode and kernel mode. Therefore, compared with LVS-based Load balancing architecture, the XDP-based load balancing architecture provided by the embodiments of the present application can reduce performance overhead.

Below, based on the load balancing system shown in FIG. 1 , the load balancing method described in the embodiments of the present application will be described in detail. For example, please refer to FIG. 3 , which is a flowchart of a load balancing method provided by an embodiment of the present application. This embodiment is described from the perspective of a load balancer. This embodiment includes:

301. The load balancer determines that a new host exists in the load balancing system.

The load balancer is a load balancer on any one of the multiple hosts included in the load balancing system, and the load balancer and the real server RS are deployed on each of the multiple hosts. Since the load balancer and RS are deployed on each host, each new host means that one load balancer and one RS are added respectively.

In the embodiment of the present application, two load balancing are included, which are referred to as the first load balancing and the second load balancing respectively, and the first load balancing refers to switching to select a target load balancer from the load balancers of multiple hosts. , and send the packet to the target load balancer. The second load balancing means that the target load balancer selects the target RS from the RSs of multiple hosts and sends the data packet to the target RS. The target load balancer and target RS may be on the same host or on different hosts.

In the embodiment of the present application, the load balancer is a load balancer on each host in the load balancing system after the new host is added. That is to say, each load balancer in the load balancing system includes the load balancer on the original host in the load balancing system and the load balancer on the newly added host. After the hosts are added, the load balancing method described in the embodiments of the present application is executed.

After the load balancer determines that a new host is added to the load balancing system, once the load balancer receives the data packet from the switch, it indicates that the load balancer is the target load balancer.

302. The load balancer receives the data packet.

Exemplarily, the switch performs the first load balancing, selects the target load balancer from the load balancers of the multiple hosts, and sends the data packet to the target load balancer. Accordingly, the target load balancer receives the packet. The data packet may be a service request initiated by the user's terminal equipment, etc. After receiving the data packet, the target RS responds to the service request according to the data packet.

From the switch's point of view, like the traditional XDP-based load balancing architecture, the OSPF routing protocol is used to perform the first load balancing to determine the target load balancer, and it is likely to send packets to the load balancer on the newly added host. , the mapping table of the load balancer on the newly added host is empty. Of course, there is also a good chance that the switch will send the packet to the load balancer on the original host.

303. The load balancer determines the effective RS from the RSs of each host included in the load balancing system, and the effective RS is the RS involved when the load balancer performs load balancing on the data packets of the existing services before the new host is added, The existing service is the service that the load balancing system is providing to the user before the new host is added.

In the embodiment of the present application, each time the load balancer receives a data packet, it queries a local mapping table, and if the quintuple of the data packet does not exist in the mapping table, a consistent hash operation is performed to determine the target RS. In the traditional XDP-based load balancing architecture, when a new host is added, the load balancer performs consistent hashing according to the quintuple of data packets, the VIPs of all RSs in the load balancing system, and the number of RSs, resulting in the determination of The target RS is incorrect.

In the embodiment of the present application, after each new host is added, the RS on the host does not take effect immediately, that is, it does not participate in load balancing immediately, but saves all existing After the mapping relationship between the quintuple of the service and the RS, the RS on the newly added host is used for load balancing.

Therefore, when the load balancer cannot determine the target RS by looking up the mapping table and performs consistent hashing, it determines the valid RS from all the RSs. A valid RS may provide at least one RS of an existing service, or may not provide an existing service. However, regardless of whether an existing service is provided, the effective RS is the RS involved when the load balancer performs consistent hashing on the data packets of the existing service before adding a host.

For example, there are two hosts in the load balancing system, namely host 1 and host 2. Load balancers 1a and RS1b are deployed on host 1, and load balancers 2a and RS2b are deployed on host 2. Add host 3, and deploy load balancer 3a and RS3b on host 3. A mapping table is stored on load balancer 1a, which stores the correspondence between quintuple A and RS2b, and the mapping table on load balancer 2a and load balancer 3a is empty, that is, RS2b has provided services to the outside world, and RS1b Business is not provided.

That is to say, before the new host is added, there is an existing service, and the quintuple of the data packet of this service is quintuple A, respectively. Before adding a host, after the load balancer (load balancer 1a or load balancer 2a) receives the data packet whose quintuple is quintuple A for the first time, according to the VIP of quintuple A, RS1b, RS2b, RS Quantity, etc., perform consistent hashing, and determine that the target RS is RS2b. Obviously, before adding host 3, the RSs involved when the load balancer performs consistent hashing on data packets of existing services include RS1b and RS2b. Therefore, the effective RS includes RS1b and RS2b.

304. The load balancer determines the target RS from the valid RSs.

Exemplarily, the load balancer does not directly select the target RS from all the RSs in the load balancing system, but first determines the valid RS from all the RSs, and then selects the target RS from the valid RSs.

For example, there are two hosts in the load balancing system, namely host 1 and host 2. Load balancers 1a and RS1b are deployed on host 1, and load balancers 2a and RS2b are deployed on host 2. Add host 3, and deploy load balancer 3a and RS3b on host 3. Load balancer 1a stores a mapping table, which stores the correspondence between quintuple A and RS2b, and the mapping table on load balancer 2a stores the correspondence between quintuple B and RS1b. The mapping table is empty. That is to say, before the host is added, there are two existing services, and the quintuple of the data packets of the two services are quintuple A and quintuple B, respectively.

It is assumed that the switch performs the first load balancing and selects the load balancer 1a. After receiving the data packet, the load balancer 1a determines that the quintuple of the data packet is quintuple A. Therefore, the load balancer 1a determines that the target RS is RS2b according to the five-tuple query mapping table.

It is assumed that the switch performs the first load balancing and selects the load balancer 2a. After receiving the data packet, the load balancer 2a determines that the quintuple of the data packet is quintuple A. However, since the mapping table is empty, the load balancer 2a determines the valid RS, and the valid RS includes RS1b and RS2b. After that, the load balancer 2a performs a consistent hashing algorithm to determine that the target RS is RS2b.

Assuming that the switch performs the first load balancing and selects the load balancer 3a, after receiving the data packet, the load balancer 3a determines that the quintuple of the data packet is quintuple A. However, since the mapping table is empty, the load balancer 3a determines the valid RS, and the valid RS includes RS1b and RS2b. After that, the load balancer 3a performs a consistent hashing algorithm to determine that the target RS is RS2b.

For another example, there were originally 100 hosts in the load balancing system. When a new host was added, a batch of hosts was added. This batch of hosts totaled 10, making a total of 110 hosts in the load balancing system. The RS on the 100 hosts Numbered 100 to 110. When adding a batch of hosts, the load balancer on each of the 110 hosts detected the new host. When the load balancer on any host receives a data packet, if the target RS cannot be determined by querying the mapping table, the load balancer determines the effective RS. It is assumed that the number of 1-90 RS is before the new host is added. The load balancer determines the target RS according to the quintuple of the data packet, the VIP of each RS in the 90 RSs, and the number of RSs.

305. The load balancer sends the data packet to the target RS.

In this embodiment of the present application, the load balancer that sends the data packet, that is, the target load balancer and the target RS are located on the same host or different hosts.

In the load balancing method provided by the embodiment of the present application, when the load balancer on each host in the load balancing system detects a new host in the load balancing system, once a load balancer receives a data packet, if the load balancer does not exist in the mapping table The five-tuple of the data packet, the effective RS for load balancing is determined from the RSs of each host included in the load balancing system, the target RS is selected from the effective RS, and the data packet is sent to the target RS, thereby completing the second Secondary load balancing. With this solution, after each new host is added, the load balancer determines the target RS from the valid RSs and sends data packets, ensuring that the load balancer on the newly added host has sufficient time to generate mappings for existing services The mapping table records the mapping relationship between the quintuple of the existing service and the RS, so as to prevent the load balancer from sending the data packet of the existing service to the incorrect RS. That is to say, each time a host is added, the load balancer on the host takes effect, but the RS does not immediately participate in load balancing. Instead, the mapping table of the load balancer on the host to be added saves all existing services in the mapping table. After the mapping relationship between the tuple and the RS, the RS on the newly added host is used for load balancing to ensure that the data packets of the existing services after the newly added host are sent to the correct RS, and the purpose of improving the service quality is achieved without any modification. switches, reducing the impact surface and operational complexity.

Optionally, in the above embodiment, in the process of determining the effective RS from the RSs of each host included in the load balancing system, the load balancer determines the mounting duration of the RSs of each host, and determines the mounting duration of the RSs of the hosts exceeds the preset duration. RS as the effective RS. The mount duration refers to the duration between the notification time point and the reception time point, the notification time point is the time point when the host's RS announces the VIP to the querying device, and the reception time point is the time point when the load balancer receives the data packet. By comparing the mount duration and the preset duration, the purpose of accurately determining the effective RS is achieved.

In one method, each load balancer records the time point when the host joins the load balancing system, and uses the time point as the notification time point, and the load balancers in the load balancing system can communicate with each other. Therefore, the load balancer can determine the time point when other hosts join the load balancing system, that is, the advertisement time point. The announcement time point of the host is the announcement time point of the RS on the host.

When the load balancer needs to perform consistent hashing after receiving a data packet, the mounting duration of the RS can be determined according to the notification time point of the RS of each host and the reception time point of the received data packet. The RS with the mount duration exceeding the preset duration is used as the effective RS. The preset duration is, for example, 10 minutes, 8 minutes, 20 minutes, and the like. The embodiments of the present application are not limited. The preset duration can at least satisfy: the load balancer on the newly added host performs the second load balancing, so that the mapping table of the load balancer saves the mapping relationship between the quintuple and RS of all existing services.

In another way, as shown in Figure 1, an inquiry device is provided. The load balancer detects the newly added host, and when it receives a data packet and needs to perform consistent hashing, it sends a query request to the query device to request to obtain the notification time point of the RS of each host included in the load balancing system. After receiving the query request, the query device sends a query response to the load balancer, where the query response carries the notification time point of the RS of each host included in the load balancing system. After that, the load balancer determines the mounting duration of the RS of each host according to the receiving time point and the notification time point of the RS of each host.

Exemplarily, a query_VIP function is added to the load balancer, which is used to obtain the notification time point of the RS of each host included in the load balancing system through the query device. In this way, each time the load balancer performs consistent hashing, it does not need to interact with other load balancers in the load balancing system to obtain the notification time point of the RS, but only by interacting with the query device once to determine The notification time point of the RS of each host included in the load balancing system is used to determine the mounting duration of the RS of each host.

With this solution, by setting up a query device in the load balancing system and adding a VIP query function to the load balancer, the purpose of quickly determining the RS mount duration of each host is achieved.

Optionally, in the above embodiment, the load balancer can flexibly determine whether a new host exists in the load balancing system.

In one approach, the load balancer detects whether the number of hosts in the load balancing system has changed. When the number of hosts in the load balancing system changes, it is determined that there are new hosts in the load balancing system. When the number of hosts in the load balancing system has not changed, the load balancer considers that there are no new hosts in the load balancing system.

Exemplarily, each load balancer detects the number of RSs in the load balancing system in real time. Once the number of RSs changes, it means that the number of hosts changes. Therefore, the load balancer can quickly determine whether to add or reduce hosts in the load balancing system by detecting the number of RSs.

In another manner, when the load balancer determines whether a new host exists in the load balancing system, it determines whether there is an RS whose mounting duration does not exceed the preset duration among the RSs of each host included in the load balancing system. This is because when the mount duration of an RS does not exceed the preset duration, and the RS does not take effect, it cannot participate in the consistent hashing operation.

When there is an RS whose mounting duration does not exceed the preset duration in the RSs of each host included in the load balancing system, it is determined that a new host exists in the load balancing system, and the newly added host is the one whose mounting duration does not exceed the preset duration. RS. At this time, once the load balancer receives the data packet and needs to perform consistent hashing, the effective RS is determined from all the RSs included in the load balancing system, and the target RS is determined from the effective RSs.

When the mount duration in the RS of each host included in the load balancing system exceeds the preset duration, the load balancer considers that there is no new host in the load balancing system. At this time, once the load balancer receives the data packet and needs to perform consistent hashing, the target RS is directly determined from all RSs included in the load balancing system.

With this solution, considering that RS cannot be used for consistent hashing operations when it is not in effect, the hosts with RSs whose mounting duration does not exceed the preset duration are regarded as newly added hosts to avoid subsequent consistent hashing operations. Error, to achieve the purpose of improving the service quality of existing services.

FIG. 4 is another flowchart of the load balancing method provided by the embodiment of the present application. This embodiment is described from the perspective of a query device. This embodiment includes:

401. The query device receives a notification request sent by an RS on a newly added host in the load balancing system, where the notification request is used to indicate the virtual IP address VIP of the RS.

402. Record the VIP and the notification time point, where the notification time point is the time point when the query device receives the notification request, and the effective RS in the load balancing system is before the newly added host, the The RS involved when the load balancer in the load balancing system performs load balancing on the data packets of the existing service, where the existing service is the service that the load balancing system is providing to the user before the new host is added.

Exemplarily, each time a host is added, the RS on the newly added host sends a notification request to the inquiring device to pass the VIP. After the query device receives the notification request, it records the VIP of the newly added host and the notification time point. It can be understood that the time point of the newly added host and the time point of initial mounting of the RS on the newly added host are the notification time point, that is, the time point when the query device receives the notification request.

Using this solution, by setting a query device to record the VIP and notification time point of each new host, it is convenient for the load balancer to quickly obtain the mount time of each RS from the query device, and then quickly determine from all the RSs of the load balancing system. out of the effective RS.

Hereinafter, the above load balancing method will be described in detail with an example. For example, please refer to FIG. 5 , which is a schematic diagram of an application scenario of the load balancing method provided by the embodiment of the present application.

Please refer to Figure 5. Before adding a host, there are 3 hosts in the load balancing system, namely host 1, host 2 and host 3. Load balancers 1a and RS1b are deployed on host 1, and load balancers 2a and 2 are deployed on host 2. RS2b, load balancer 3a and RS3b are deployed on host 3. At 18:00, host 4 is added, and load balancer 4a and RS4b are deployed on host 4. Load balancer 1a stores a mapping table, which stores the correspondence between quintuple A and RS2b, the mapping table on load balancer 2a stores the correspondence between quintuple B and RS1b, load balancer 3a and load The mapping table on the equalizer 4a is empty.

The pre-set duration on the query device 12 is 10 minutes, that is, from 18:00, the function of the load balancer 4a is enabled, but the function of the RS4b is not enabled, and does not participate in the consistent hashing operation.

During the period from 18:00 to 18:10, the switch 13 receives the data packet from the terminal device 14 and performs the first load balancing. The quintuple of the data packet is quintuple A, that is, the data packet is a data packet of an existing service. If no new host 4 is added, the switch 13 sends the data packet to the load balancer 1a. However, since the load balancer 4a is turned on, the switch 13 performs the first load balancing, and there is a high possibility that the packet that should be sent to the load balancer 1a will be sent to the load balancer 2a, the load balancer 3a or the load balancer 4a. .

Regardless of which load balancer it is sent to, the load balancer determines that valid RSs include RS1b, RS2b, and RS3b. Therefore, by performing a consistent hash operation, it is determined that the target RS is RS2b, and then the data packet is sent to RS2b.

Similarly, when the quintuple of the data packet is quintuple B and the first load balancing should be sent to load balancer 2a, the switch is likely to send the packet to load balancer 1a and load balancer 3a Or the load balancer 4a, the processing method is the same as above, and details are not repeated here.

During the period from 18:00 to 18:10, the load balancer 4a can establish a mapping table that stores the mapping relationship between the quintuple and the RS of all existing services.

After 18:10, after the switch receives the data packet of the existing service, for the switch, there is no new load balancer (because the newly added load balancer is turned on at 18:00), so the switch will not Misclassify packets. After the data packet arrives at the load balancer, the result of the consistent hash operation changes due to the presence of the newly added RS (the new RS will be opened after 18:10). However, after 18:10, each load balancer, including the newly added load balancer at 18:00, has stored the mapping table of the mapping relationship between the quintuple and RS of all existing services. Therefore, the mapping table should be queried first. surface. If there is a quintuple of data packets in the mapping table, it means that it is a data packet of an existing service, and the RS corresponding to the quintuple is directly used as the target RS. If there is no quintuple of the data packet in the mapping table, it means that the data packet is a data packet of a new service, and the load balancer (load balancer 1a, load balancer 2a, load balancer 3a or load balancer 4a) determines The valid RS includes RS1b, RS2b, RS3b and RS4b, and a consistent hash operation is performed according to the quintuple of the data packet of the new service and the VIP, quantity, etc. of the valid RS, so as to determine the target RS, which may be RS1b, RS2b, RS3b or RS4b. After that, the load balancer adds the mapping relationship between the five-tuple of the data packet of the new service and the target RS in the local mapping table.

The following are apparatus embodiments of the present application, which can be used to execute the method embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the method embodiments of the present application.

FIG. 6 is a schematic diagram of a load balancing apparatus provided by an embodiment of the present application. The load balancing apparatus 600 includes: a determining module 61 , a receiving module 62 , a processing module 63 and a sending module 64 .

The determining module 61 is configured to determine that a new host exists in the load balancing system, and the load balancer is a load balancer on any one of the multiple hosts included in the load balancing system. A load balancer and a real server RS are deployed on each host;

a receiving module 62 for receiving data packets;

The processing module 63 is configured to determine the effective RS from the RSs of the hosts included in the load balancing system, where the effective RS is involved when the load balancer performs load balancing on the data packets of the existing services before the new host is added. RS, the existing service is the service that the load balancing system is providing to the user before the new host is added, and the target RS is determined from the effective RS;

A sending module 64, configured to send the data packet to the target RS.

In a feasible implementation manner, when the processing module 63 determines the effective RS from the RSs of the hosts included in the load balancing system, it is used to determine the mounting duration of the RSs of the hosts, and the mounting duration is The RS that exceeds the preset duration is used as the effective RS, and the mount duration refers to the duration between the notification time point and the reception time point, and the notification time point is the time point when the RS of the host announces the virtual IP address VIP to the query device , the receiving time point is the time point when the load balancer receives the data packet.

In a feasible implementation manner, the sending module 64 is further configured to send a query request to the query device to request to obtain the notification time point of the RS of each host included in the load balancing system;

The receiving module 62 is further configured to receive a query response from the query device, where the query response carries the notification time point of the RS of each host included in the load balancing system;

The processing module 63 is configured to determine, according to the reception time point and the notification time point of the RS of each host, the mounting duration of the RS of each host.

In a feasible implementation manner, the determining module 61 is configured to determine whether there is an RS whose mounting duration does not exceed the preset duration in the RSs of each host included in the load balancing system; When there is an RS whose mounting duration does not exceed the preset duration in the RS of the host, it is determined that there is a new host in the load balancing system.

In a feasible implementation manner, the determining module 61 is configured to detect whether the number of RSs in the load balancing system changes; when the number of RSs in the load balancing system changes, determine the load balancing system There are new hosts in .

In a feasible implementation manner, when the processing module 63 determines the effective RS from the RSs of each host included in the load balancing system, it is used to query the mapping table according to the quintuple of the data packet, and the mapping The table stores the correspondence between the quintuple and the RS; when the quintuple of the data packet does not exist in the mapping table, the effective RS is determined from the RSs of each host included in the load balancing system.

In a feasible implementation manner, after the processing module 63 determines the target RS from the valid RS, it is also used to add the quintuple of the data packet and the target RS in the mapping table. Mapping relations.

In a feasible implementation manner, when the processing module 63 determines the target RS from the valid RS, it is used to determine the target RS according to the quintuple of the data packet, the VIP of each valid RS, and the valid RS. The number performs consistent hashing to determine the target RS.

The load balancing apparatus provided in the embodiment of the present application can perform the action of the load balancer in the foregoing embodiment, and the implementation principle and technical effect thereof are similar, and are not repeated here.

FIG. 7 is a schematic diagram of another load balancing apparatus provided by an embodiment of the present application. The load balancing apparatus 700 includes: a transceiver module 71 and a processing module 72 .

A transceiver module 71, configured to receive a notification request sent by an RS on a newly added host in the load balancing system, where the notification request is used to indicate the virtual IP address VIP of the RS;

The processing module 72 is configured to record the VIP and the announcement time point, the announcement time point is the time point when the query device receives the announcement request, and the VIP and the announcement time point are used to determine the new Whether the RS on the increase host is converted into an effective RS, the effective RS in the load balancing system is the RS involved when the load balancer in the load balancing system performs load balancing on the data packets of the existing service, and the existing RS is The service is the service that the load balancing system is providing to the user before the new host is added.

In a feasible implementation manner, the transceiver module 71 is further configured to receive a query request from a load balancer, where the load balancer is the data packet received in the load balancer of each host included in the load balancing system. and send a query response to the load balancer, where the query response carries the notification time point of the RS of each host included in the load balancing system.

The load balancing apparatus provided in the embodiment of the present application can perform the action of querying the device in the foregoing embodiment, and the implementation principle and technical effect thereof are similar, and are not repeated here.

FIG. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in FIG. 8 , the electronic device 800 is, for example, the above-mentioned query device or host, and the electronic device 800 includes:

processor 81 and memory 82;

the memory 82 stores computer instructions;

The processor 81 executes the computer instructions stored in the memory 82, so that the processor 81 executes the load balancing method implemented by the load balancer in the host as above; or, causes the processor 81 to execute the load implemented by the query device as above Balance method.

For the specific implementation process of the processor 81, reference may be made to the foregoing method embodiments, and the implementation principles and technical effects thereof are similar, and details are not described herein again in this embodiment.

Optionally, the electronic device 800 further includes a communication component 83 . Among them, the processor 81 , the memory 82 and the communication part 83 can be connected through the bus 84 .

Embodiments of the present application further provide a computer-readable storage medium, where computer instructions are stored in the computer-readable storage medium, and when the computer instructions are executed by a processor, are used to implement the load balancing implemented by the load balancer in the host as above method; or, implement the load balancing method implemented by the query device as above.

Embodiments of the present application further provide a computer program product, the computer program product includes a computer program, and when the computer program is executed by the processor, implements the load balancing method implemented by the load balancer in the host as above; or, implements the load balancing method implemented by the above query device Balance method.

Other embodiments of the present application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses or adaptations of this application that follow the general principles of this application and include common knowledge or conventional techniques in the technical field not disclosed in this application . The specification and examples are to be regarded as exemplary only, with the true scope and spirit of the application being indicated by the following claims.

It is to be understood that the present application is not limited to the precise structures described above and illustrated in the accompanying drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.

Claims (13)

1. A load balancing method, characterized in that, applied to a load balancer on a host in a load balancing system, the method comprising: Determine that there is a new host in the load balancing system, the load balancer is a load balancer on any one of the multiple hosts included in the load balancing system, and each host in the multiple hosts is deployed on Load Balancer and Real Server RS; receive packets; The effective RS is determined from the RSs of each host included in the load balancing system, and the effective RS is the RS involved when the load balancer performs load balancing on the data packets of the existing services before the new host is added. There is a business that the load balancing system is providing to the user before the new host is added; Determine the target RS from the valid RS; The data packet is sent to the target RS. 2 . The method according to claim 1 , wherein the determining an effective RS from the RSs of each host included in the load balancing system comprises: 2 . Determine the mount duration of the RS of each host, and take the RS with the mount duration exceeding the preset duration as the effective RS, the mount duration refers to the duration between the notification time point and the reception time point, and the notification time point is The time point at which the RS of the host announces the virtual IP address VIP to the querying device, and the receiving time point is the time point when the load balancer receives the data packet. 3. The method according to claim 2, wherein the determining the mounting duration of the RS of each host comprises: Send a query request to the query device to request to obtain the notification time point of the RS of each host included in the load balancing system; receiving a query response from the query device, where the query response carries the notification time point of the RS of each host included in the load balancing system; According to the reception time point and the notification time point of the RS of each host, the mounting duration of the RS of each host is determined. 4. The method according to any one of claims 1-3, wherein the determining that a new host exists in the load balancing system comprises: Determine whether there is an RS whose mounting duration does not exceed a preset duration in the RSs of each host included in the load balancing system; When there is an RS whose mounting duration does not exceed the preset duration in the RSs of each host included in the load balancing system, it is determined that a new host exists in the load balancing system. 5. The method according to any one of claims 1-3, wherein the determining that a new host exists in the load balancing system comprises: Detecting whether the number of RSs in the load balancing system changes; When the number of RSs in the load balancing system changes, it is determined that a new host exists in the load balancing system. 6. The method according to any one of claims 1-3, wherein the determining an effective RS from the RSs of each host included in the load balancing system comprises: Query the mapping table according to the quintuple of the data packet, and store the correspondence between the quintuple and the RS in the mapping table; When the quintuple of the data packet does not exist in the mapping table, the effective RS is determined from the RSs of each host included in the load balancing system. 7. The method according to claim 6, wherein after determining the target RS from the valid RS, the method further comprises: A mapping relationship between the quintuple of the data packet and the target RS is added to the mapping table. 8. The method according to any one of claims 1-3, wherein the determining the target RS from the valid RS comprises: The target RS is determined by performing consistent hashing according to the quintuple of the data packet, the VIP of each valid RS, and the number of the valid RSs. 9. A load balancing method, characterized in that it is applied to a query device in a load balancing system, the method comprising: receiving a notification request sent by an RS on a newly added host in the load balancing system, where the notification request is used to indicate the virtual IP address VIP of the RS; Record the VIP and the notification time point, the notification time point is the time point when the query device receives the notification request, and the VIP and the notification time point are used to determine whether the RS on the newly added host is It is transformed into an effective RS, and the effective RS in the load balancing system is the RS involved when the load balancer in the load balancing system performs load balancing on the data packets of the existing service, and the existing service is before the new host is added. The service that the load balancing system is providing to the user. 10. The method of claim 9, further comprising: receiving a query request from a load balancer, where the load balancer is the load balancer that receives the data packet among the load balancers of each host included in the load balancing system; Send a query response to the load balancer, where the query response carries the notification time point of the RS of each host included in the load balancing system. 11. A load balancing system, comprising: a switch, multiple hosts, and a query device, the switch establishes a network connection with each of the multiple hosts, and the query device is connected to the multiple hosts Each host in establishes a network connection, where: the switch, configured to perform load balancing to determine a target load balancer from the load balancers included in the plurality of hosts and send data packets; A load balancer and a real server RS are deployed on each of the multiple hosts, and the load balancer is configured to execute the method according to any one of claims 1-8; The query device is adapted to perform the method of claim 9 or 10. 12. An electronic device, comprising a processor, a memory, and a computer program stored on the memory and executable on the processor, characterized in that, when the processor executes the computer program, the electronic The device implements the method of any one of claims 1 to 10. 13. A computer-readable storage medium on which a computer program is stored, characterized in that, when the computer program is executed by a processor, the method according to any one of claims 1 to 10 is implemented.

Images