CN113141400A - Network service access method and device - Google Patents
Network service access method and device Download PDFInfo
- Publication number
- CN113141400A CN113141400A CN202110402394.3A CN202110402394A CN113141400A CN 113141400 A CN113141400 A CN 113141400A CN 202110402394 A CN202110402394 A CN 202110402394A CN 113141400 A CN113141400 A CN 113141400A
- Authority
- CN
- China
- Prior art keywords
- node
- network
- network node
- load balancing
- access request
- 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
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0631—Management of faults, events, alarms or notifications using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0654—Management of faults, events, alarms or notifications using network fault recovery
- H04L41/0659—Management of faults, events, alarms or notifications using network fault recovery by isolating or reconfiguring faulty entities
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/10—Active monitoring, e.g. heartbeat, ping or trace-route
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Cardiology (AREA)
- General Health & Medical Sciences (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The embodiment of the invention provides a method and a device for accessing network services, wherein the network services are provided by a plurality of network nodes through load balancing nodes; the method comprises the following steps: the load balancing node receives a first access request aiming at network service and sent by a target node; translating a destination Mac address of the first access request to a Mac address of a first network node, thereby generating the second access request; the first network node is one of the plurality of network nodes; the load balancing node sends the second access request to the first network node through a switch; the first network node is configured to send an access result of the second access request to the target node through the switch. The method can realize flexible scheduling of the network service flow and improve the bandwidth utilization rate of the network node.
Description
Technical Field
The present application relates to the field of network technologies, and in particular, to a method and an apparatus for accessing a network service.
Background
Currently, a network service component adopts a master-slave deployment mode, for example, one network node has multiple tenants, but one tenant can be deployed in only one network node (i.e., a master node), and the other network node (i.e., a slave node) serves as a backup (i.e., does not provide network services). This can only take advantage of the performance of one network node, which can have a performance bottleneck if the single tenant traffic is large enough. In addition, when the main/standby switch is performed due to a fault, the existing connection on the main node cannot be automatically migrated to the standby node, so that the existing connection is interrupted. When a network node fails, all accesses of the tenants of the network node are affected.
Therefore, there is a need for a method and an apparatus for accessing a network service, which can implement flexible scheduling of network service traffic and improve the bandwidth utilization of a network node.
Disclosure of Invention
Embodiments of the present invention provide a method and an apparatus for accessing a network service, which can implement flexible scheduling of network service traffic and improve the bandwidth utilization of a network node.
In a first aspect, an embodiment of the present invention provides an access method for a network service, where the network service is provided by multiple network nodes through a load balancing node, and the method includes:
the load balancing node receives a first access request aiming at network service and sent by a target node;
translating a destination Mac address of the first access request to a Mac address of a first network node, thereby generating the second access request; the first network node is one of the plurality of network nodes;
the load balancing node sends the second access request to the first network node through a switch; the first network node is configured to send an access result of the second access request to the target node through the switch.
In the method, the network service can be provided by a plurality of network nodes, the plurality of network nodes are not distinguished by main and standby nodes, and the network node with better service quality can be determined by the load balancing node according to the service condition of the network node to provide the network service. Therefore, compared with the system architecture of the main network node and the standby network node in the prior art, the system architecture can realize flexible scheduling of network service flow, improve the bandwidth utilization rate of the network nodes and improve the network service quality. And the load balancing node converts the destination Mac address of the first access request into the Mac address of the first network node to generate a second access request, so that the switch sends the second access request to the first network node according to the Mac address of the first network node. In the process, the load balancing node does not need to perform IP address conversion and IP management, and the processing speed of the load balancing node on the access request is increased. For the network node, after the second access request is processed to obtain the access result, the second access request does not need to be forwarded through the load balancing node, but can be directly sent to the target node through the switch, so that the response speed is improved. And because the network service of one target node can be provided by a plurality of network nodes, the reliability of the network service is increased.
Optionally, the load balancing node receives, through the switch, a request packet sent by the first network node; the request message comprises an ARP request message serving as message content, and the ARP request message is used for acquiring a target Mac of the target node; the load balancing node acquires an ARP response message based on broadcasting the ARP request message; the ARP response message comprises a target Mac of the target node; and the load balancing node sends the ARP response message to the first network node through the switch, the first network node acquires the target Mac of the target node in the ARP response message, and sends the access result of the second access request to the target node through the switch.
In the method, although the load balancing node is used as the ARP agent of the network node, as the ARP message between the network node and the load balancing node is still transmitted through the switch, in order to avoid errors when the switch performs Mac learning, when the network node needs to acquire a target Mac through an ARP request, the network node does not adopt the existing ARP message format, but encapsulates the ARP request message into the content of the message to be transmitted, so that errors when the switch performs Mac learning are avoided.
Optionally, the sending, by the load balancing node, the ARP response packet to the first network node through the switch includes: and the load balancing node encapsulates the ARP response message in a transmission layer or a network layer to obtain a response message, and sends the response message to the first network node through the switch.
In the method, because the load balancing node and the network nodes corresponding to the load balancing node have the same IP address, if the ARP request message is encapsulated in the data link layer, the switch learns different Mac addresses of the network nodes corresponding to one IP address and the Mac addresses of the load balancing node, so that the learning of the address of the switch is disordered, and correspondingly, the message sending is also disordered. By encapsulating the ARP response message in the transport layer or the network layer. The switch reads the information of the data link layer, so that the learning of the Mac address of the switch is not influenced, and the learning accuracy of the Mac address of the switch is ensured.
Optionally, the load balancing node has the same IP address as the plurality of network nodes; and the load balancing node receives the access request and selects a target network node from the plurality of network nodes as a response of the access request according to a calculation rule.
In the method, the IP address of the load balancing node and the IP addresses of the plurality of network nodes are set to be the same IP address, so that when the network service is provided for the target node, address conversion is not needed in the load balancing node, and the load balancing node does not need to perform the work of IP address conversion and IP management, thereby accelerating the processing speed of the load balancing node on the access request and further accelerating the access speed of the network service.
Optionally, the load balancing node receives heartbeat messages of the plurality of network nodes, where the heartbeat messages are used to determine the working state of the network nodes.
In the method, the load balancing node receives the heartbeat messages of the plurality of network nodes, so that the load balancing node can be ensured to determine the working state of each network node, and the reliability of the system for providing network service is ensured.
Optionally, the load balancing node receives a new request and a heartbeat packet sent by a new network node;
the load balancing node synchronizes first connection tracking information of a current network node to the newly added network node, wherein the first connection tracking information is used for sending network service data generated by the network service provided by the current network node to the newly added network node, so that the newly added network node comprises complete network service data used for providing the network service;
and the load balancing node determines that the newly-added network node provides network service through the load balancing node.
In the system, a network node can be newly added to a plurality of network nodes, and the load balancing node adds the newly added network node into the system by receiving a newly added request sent by the newly added network node; and receiving the heartbeat packet sent by the newly added network node at regular time, and determining that the newly added network node is alive and can be used for providing network service. The load balancing node synchronizes the first connection tracking information of the current network node to the newly added network node, and the newly added network node is ensured to contain complete network service data for providing network service; and the reliability of the network service provided by the newly added network node is improved.
Optionally, the load balancing node receives a deletion request sent by a deletion network node;
the load balancing node synchronizes second connection tracking information of the network node to be deleted to the current network node, wherein the second connection tracking information is used for sending network service data generated by the network node to be deleted providing network service to the current network node, so that the current network node comprises complete network service data used for providing the network service;
and the load balancing node determines to delete the network node and stops providing the network service.
In the system, the load balancing node deletes the deleted network node from the system by receiving the deletion request sent by the deleted network node; it is determined that the deleted network node is no longer being used to provide network services. Therefore, the system realizes the capacity expansion and the capacity reduction of the network nodes by adding or deleting the network nodes, and ensures the reliability of the system for providing the network service. Before deleting the deleted network node from the system, the load balancing node synchronizes the second connection tracking information of the deleted network node to the current network node, and the current network node is ensured to contain complete network service data for providing network service; the reliability of the network service provided by the current network node is improved.
Optionally, the load balancing node receives, through the switch, a fourth access request sent by the first network node, where the fourth access request is generated according to a third access request of a backend server; the first network node is used for converting the message quintuple in the third access request into a message quintuple with the same hash value as the first network node, and taking the converted message quintuple as the message quintuple in the fourth access request;
the load balancing node sends the fourth access request to a target node to obtain an access result of the target node to the fourth access request;
and the load balancer sends the access result of the fourth access request to the first network node through the switch, so that the first network node sends the access result of the fourth access request to the backend server.
In the method, the first network node modifies the message quintuple in the third access request of the back-end server into the message quintuple with the hash value identical to that of the first network node, so that when the load balancer receives the access result of the fourth access request, the access result can be accurately routed to the first network node, and the first network node sends the access result to the back-end server. The accuracy of the request and the routing of the request result is ensured, and the communication reliability is improved.
In a second aspect, an embodiment of the present invention provides an apparatus for accessing a network service, where the network service is provided by multiple network nodes through a load balancing node, the apparatus including:
the system comprises a receiving and sending module, a sending and receiving module and a processing module, wherein the receiving and sending module is used for receiving a first access request aiming at network service and sent by a target node;
a processing module, configured to convert a destination Mac address of the first access request into a Mac address of a first network node, thereby generating the second access request; the first network node is one of the plurality of network nodes;
the transceiver module is further configured to send the second access request to the first network node through a switch; the first network node is configured to send an access result of the second access request to the target node through the switch.
In a third aspect, an embodiment of the present application further provides a computing device, including: a memory for storing a program; a processor for calling the program stored in said memory and executing the method as described in the various possible designs of the first aspect according to the obtained program.
In a fourth aspect, embodiments of the present application further provide a computer-readable non-transitory storage medium including a computer-readable program which, when read and executed by a computer, causes the computer to perform the method as described in the various possible designs of the first aspect.
These and other implementations of the present application will be more readily understood from the following description of the embodiments.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
Fig. 1 is a schematic diagram of an architecture for accessing a network service according to an embodiment of the present invention;
fig. 2 is a schematic flowchart of an access method for a network service according to an embodiment of the present invention;
fig. 3 is a flowchart illustrating a method for accessing a network service according to an embodiment of the present invention;
fig. 4-1 is a partial flowchart of a method for accessing a network service according to an embodiment of the present invention;
fig. 4-2 is a partial flowchart of a method for accessing a network service according to an embodiment of the present invention;
fig. 4-3 is a partial schematic flow chart of a method for accessing a network service according to an embodiment of the present invention;
fig. 5 is a schematic diagram of an access device for a network service according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail with reference to the accompanying drawings, and it is apparent that the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is an access system architecture of a network service according to an embodiment of the present invention, where the access system architecture of the network service includes an access node cluster 101, a network node cluster 105, a load balancing node 104, and a switch 103, where a target node 102 is included in the target node cluster 101. One or more network nodes in network node cluster 105 provide network services to one or more target nodes in access node cluster 101 through load balancing node 104, switch 103. The IP addresses of each network node in the network node cluster 105 and the load balancing node 104 are the same, so that the load balancing node 104 proxies each network node in the network node cluster 105 to communicate outwards, speed up the network service access and simplify the network service access process. The load balancing node 104 periodically sends a heartbeat message to the network node cluster 105, so that each network node in the network node cluster 105 confirms survival of the load balancing node 104, and the load balancing node 104 is prevented from being in fault, and each network node in the network node cluster 105 still communicates outwards through the load balancing node 104, so that network service quality is reduced and errors occur; meanwhile, when the network node in the network node cluster 105 determines that the heartbeat message sent by the load balancing node 104 is not received within the preset time, an alarm is sent. The network node cluster 105 may also send a heartbeat message to the load balancing node 104 periodically, so that the load balancing node 104 confirms the survival of each network node in the network node cluster 105, thereby preventing the network node in the network node cluster 105 from failing, and the load balancing node 104 still distributes traffic for the network node in the network node cluster 105 that has failed, so as to provide network service for the network node that has failed, thereby reducing the quality of network service and causing errors; meanwhile, when the load balancing node 104 determines that the heartbeat message sent by one or more network nodes in the network node cluster 105 is not received within the preset time, an alarm is sent out, or the failed network node is directly deleted. Each network node in the network node cluster 105 may be used to improve network services, and the multiple network nodes are not distinguished by active and standby nodes, and a network node with better service quality may be determined by the load balancing node according to the use condition of the network node to provide the network services. Therefore, compared with the system architecture of the main network node and the standby network node in the prior art, the system architecture can realize flexible scheduling of network service flow, improve the bandwidth utilization rate of the network nodes and improve the network service quality.
In the system architecture, when the network nodes in the network node cluster 105 are expanded, the newly added network node sends a new request to the load balancing node 104, and after the load balancing node 104 confirms and records that the newly added network node is available for providing network services, a heartbeat packet is sent to the load balancing node 104. When the network nodes in the network node cluster 105 are subjected to capacity reduction, the deletion request sent by the network node to the load balancing node 104 is deleted, the load balancing node 104 determines that the deleted network node is not available for providing network service, and after the deleted network node is deleted, the deleted network node stops sending the heartbeat message to the load balancing node 104.
Based on the above system architecture, the target node 102 in the access node cluster 101 sends a first access request for the network service to the switch 103. The switch 103 sends the first access request to the load balancing node 104 according to the destination Mac address (which is the Mac address of the load balancing node 104) in the first access request. The load balancing node 104 determines that the first network node 106 provides network service for the target node 102 according to the operating state and Mac address of each network node in the network node cluster 105 in the network node record maintained by the load balancing node; the destination Mac address in the first access request is converted into a Mac address of the first network node 106, a second access request is generated, and the second access request is sent to the first network node 106 through the switch 103. The first network node 106 processes the second access request to generate an access result, and sends the access result to the target node 102 through the switch 103.
Based on this, an embodiment of the present application provides a flow of an access method for a network service, as shown in fig. 2, including:
In the method, the load balancing node and the plurality of network nodes are configured with the same IP address, and the load balancing node is used as the ARP agent of the plurality of network nodes, so that the load balancing node does not need to perform IP address conversion and IP management, and the processing speed of the load balancing node on the access request is increased. For the network node, after the second access request is processed to obtain the access result, the second access request does not need to be forwarded through the load balancing node, but can be directly sent to the target node through the switch, so that the response speed is improved. And because the network service of one target node can be provided by a plurality of network nodes, the reliability of the network service is increased.
The embodiment of the present application further provides a method for a first network node to obtain a Mac address of a target node, further including: the load balancing node receives a request message sent by the first network node through the switch; the request message comprises an ARP request message serving as message content, and the ARP request message is used for acquiring a target Mac of the target node; the load balancing node obtains an ARP response message by broadcasting the ARP request message; the ARP response message comprises a target Mac of the target node; and the load balancing node sends the ARP response message to the first network node through the switch, the first network node acquires the target Mac of the target node in the ARP response message, and sends the access result of the second access request to the target node through the switch. That is to say, if the first network node does not have the IP address and the Mac address of the target node, the first network node sends a request message to the load balancing node through the switch, where the message content in the request message is an ARP request message, and the ARP request message is used to obtain the IP address and the Mac address of the target node; the message content in the request message is at the transport layer or the network layer. Therefore, when the first network node sends a request message to the load balancing node through the switch, the switch only reads the Mac address of the load balancing node serving as the destination address in the network link layer, and does not acquire the ARP request message encapsulated in the transmission layer or the network layer; further, the switch cannot acquire the IP address and the Mac address of the first network node serving as the source address in the ARP request message, and the switch cannot learn that one IP address corresponds to multiple Mac addresses, so that address learning is disordered, and accuracy of message transmission is ensured. The load balancing node obtains an ARP request message from the message content of the request message, broadcasts the ARP request message to obtain an ARP response message which comprises the IP address and the Mac address of the target node and is returned by the target node, the load balancing node packages the ARP response message in a transmission layer or a network layer of the response message, the response message is sent to the first network node through the switch, further, the first network node obtains the ARP response message from the transmission layer or the network layer to obtain the IP address and the Mac address of the target node, the IP address and the Mac address of the target node are used as the destination address of the access result of the second access request, and the access result of the second access request is directly sent to the target node through the switch.
The embodiment of the present application further provides a method for maintaining an ARP table of a target node, including:
the load balancing node periodically sends a free ARP message, wherein the free ARP message is used for updating an ARP table of the target node to obtain address information of the load balancing node, and the address information comprises an IP address and a Mac address. That is, the load balancing node may periodically send a gratuitous ARP packet, and the target node may grab the gratuitous ARP packet and update its ARP table according to the address information of the load balancing node in the gratuitous ARP packet, including the IP address and the Mac address. Therefore, the accuracy of the address of the load balancing node in the ARP table maintained in the target node is ensured, the network service is further ensured to be accurately obtained, and the quality of the network service is ensured.
In addition, each network node in the above method and system architecture has one or a group of hash values, and the hash values are distributed when each network node expands to the system architecture. The load balancer can calculate to obtain a hash value according to the five-tuple source ip, the source port, the destination ip, the destination port and the protocol of the message in the received information; when forwarding information, the information is forwarded to a network node having the same hash value as the hash value obtained from the packet quintuple. For example, when the system architecture expands 3 network nodes — A, B, C, hash values of 1, 2, and 3 are respectively allocated to each network node. When a hash value obtained by calculation of a five-tuple source ip, a source port, a destination ip, a destination port and a protocol received by the load balancer is 2, information is distributed to a network node B according to the hash value 2.
The embodiment of the application further provides a method for converting a message quintuple by a network node, wherein the load balancing node receives a fourth access request sent by the first network node through the switch, and the fourth access request is generated according to a third access request of a back-end server; the first network node is used for converting the message quintuple in the third access request into a message quintuple with the same hash value as the first network node, and taking the converted message quintuple as the message quintuple in the fourth access request; the load balancing node sends the fourth access request to a target node to obtain an access result of the target node to the fourth access request; and the load balancer sends the access result of the fourth access request to the first network node through the switch, so that the first network node sends the access result of the fourth access request to the backend server. That is to say, when the hash value of the packet quintuple sent by the backend server to the first network node is different from the hash value of the first network node itself, the first network node may obtain the packet quintuple corresponding to the hash value that is the same as the hash value of the first network node by changing the original packet quintuple. For example, the backend server ip: 1.1.1.1, external machine: 2.2.2.1, the public network ip configured by the back-end server is: 2.2.2.10, network node a hash value 1 and network node B hash value 2. The back-end server initiates a request to the port 80 of the external machine through the port 10000 of the back-end server, and through the network node A, the network node A calculates the five-element group of the message: 2.2.2.10+10000+2.2.2.1+80, the hash value is 2, which is different from the hash value 1 itself, so that when the target node passes through the load balancer for the request result, the load balancer will send the request result to the network node B (hash value is 2), and the network node a cannot be reached. Thus, network node a may modify the source port to 9999, letting the computed hash value equal to 1, i.e., 2.2.2.10+9999+2.2.2.1+80 hash value equal to 1. The latter request results reach the load balancer, and the quintuple is calculated: 2.2.2.10+9999+2.2.2.1+80, which yields a hash value of 1, and sends the request result to network node a. Although the ports are changed, the network node a can maintain a connection tracking table to send the message to 10000 ports of the server. This approach is directed to scenarios where the internal backend server actively accesses the outside. That is, when the back-end server generates an access packet according to its own service and sends the access packet to the network node a, the network node a modifies the source ip into a certain public network ip according to a preset rule and sends the modified source ip to an external destination node. And after receiving the access message, the external target node generates a reply message, and the reply message reaches the load balancing server, and the load balancing server sends the reply message to the network node A.
Yet another approach is to provide a scenario of services to external clusters. That is, when the external cluster accesses the public network ip, the access packet reaches the load balancing server, the load balancing server calculates the hash value according to the packet quintuple, and the hash value points to the network node a, the access packet is sent to the network node a, and the network node a modifies the target ip of the access packet into a preset ip of a certain back-end server and then sends the ip to the back-end server; and when the back-end server finishes processing, generating a reply message and sending the reply message to the network node A, wherein the network node A modifies the source ip of the reply message into the previous public network ip and sends the modified reply message to the external cluster. The presetting refers to setting a corresponding relation between a public network ip and an intranet server ip through an NAT rule. For example, the backend server ip: 1.1.1.1, external machine: 2.2.2.1, the public network ip configured by the back-end server is: 2.2.2.10, network node a hash value 1 and network node B hash value 2. The external machine initiates a request to the port 80 of the public network ip through the port 10000 of the external machine, and calculates the quintuple through the load balancer: 2.2.2.10+10000+2.2.2.1+80, to obtain the hash value 2, and the message is sent to the network node B with hash value 2. And B, forwarding the request to a back-end server, replying a request result by the back-end server to reach a network node B, and transferring the request result to an external machine by the network node B. Based on the foregoing method, an embodiment of the present application provides a flow of an access method for a network service, as shown in fig. 3, including:
In the method, the first network node obtains the request information of the first access request of the target node by receiving the second access request of the load balancing node, generates an access result according to the second access request, and directly sends the access result to the target node through the switch. Therefore, each network node can directly send the access result to the target node, and the speed of network service access is increased. And each network node receives the access request of the target node through the load balancing node, and the load balancing node distributes flow according to the running state of each network node, so that the plurality of network nodes flexibly provide network service for the target node and ensure the quality of the network service. Wherein, the purpose Mac of the first access request is different from that of the second access request; that is, the destination Mac of the first access request sent by the first network node is the Mac address of the load balancing node, and the destination Mac of the second access request sent by the load balancing node is the first network node. That is, the destination address of the first access request sent by the target node is the Mac address of the load balancing node, so that the load balancing node receives the access request of the target node instead of each network node and distributes traffic according to the running state of each network node; the content of the access request of the target node is used as the content of the second access request, the Mac address of the first network node is used as the destination address of the second access request, and the flow is distributed to the first network node, so that the flexible scheduling of the flow is realized, and the quality of network service is improved.
The embodiment of the present application further provides a method for a first network node to obtain a Mac address of a target node, including: the first network node sends a request message to the load balancing node through the switch, wherein the request message comprises an ARP request message serving as message content, and the ARP request message is used for acquiring a target Mac of the target node; the first network node receives a response message sent by the load balancing node through the switch, wherein the response message comprises an ARP response message serving as message content; the ARP response message is obtained by the load balancing node based on broadcasting the ARP request message. That is to say, when a request message or a response message occurs between the first network node and the load balancing node, the ARP request message or the ARP response message is correspondingly encapsulated in the message content of the request message or the response message, and the message content is the content which cannot be read by the switch; therefore, the switch can learn only the Mac address of the network link layer if the switch can not acquire the address information contained in the ARP request message or the ARP response message; the address learning chaos caused by learning the same IP addresses of the load balancing node and each network node and the different Mac addresses corresponding to the load balancing node and each network node can be avoided, and further network service access errors can be avoided.
The embodiment of the application provides a method for transmitting a message between a first network node and a load balancing node, namely, the first network node and the load balancing node package an ARP message in a transmission layer or a network layer.
The embodiment of the application provides a method for expanding capacity of a network service system, which comprises the following steps: the load balancing node receives a newly-added request and a heartbeat packet sent by a newly-added network node; the load balancing node synchronizes first connection tracking information of a current network node to the newly added network node, wherein the first connection tracking information is used for sending network service data generated by the network service provided by the current network node to the newly added network node, so that the newly added network node comprises complete network service data used for providing the network service; and the load balancing node determines that the newly-added network node provides network service through the load balancing node. That is to say, the network service system can expand capacity, the newly added network node can realize the expansion capacity by sending a new request to the load balancing node, and the newly added network node can also enable the load balancing node to confirm the survival through the heartbeat packet; if the newly added network node needs to provide the network service, the first link tracking information aiming at the network service in the current network node responsible for providing the network service can be forwarded to the newly added network node through the load balancing node, so that the newly added network node comprises complete network service data for providing the network service. Therefore, the newly added network node can provide reliable and accurate network service.
The embodiment of the application provides a method for reducing the capacity of a network service system, which comprises the following steps: the load balancing node receives a deleting request sent by a deleting network node; the load balancing node synchronizes second connection tracking information of the network node to be deleted to the current network node, wherein the second connection tracking information is used for sending network service data generated by the network node to be deleted providing network service to the current network node, so that the current network node comprises complete network service data used for providing the network service; and the load balancing node determines to delete the network node and stops providing the network service. That is, the network service system can also reduce the capacity, and the deletion network node can realize the capacity reduction by sending a deletion request to the load balancing node; if the current network node needs to provide the network service which is provided by the deleted network node, the second link tracking information aiming at the network service in the deleted network node which is responsible for processing the network service can be forwarded to the current network node through the load balancing node, so that the current network node comprises complete network service data for providing the network service. In this way, the current network node can provide reliable and accurate network services. The stability and accuracy of the network service system service are ensured.
Based on the above flow, the embodiment of the present application provides a method flow for accessing a network service, as shown in fig. 4 (the flow in fig. 4 is longer, and in order to ensure the clarity of fig. 4, the applicant divides fig. 4 in the drawings of the specification into three parts, i.e. fig. 4-1, fig. 4-2, and fig. 4-3), and the flow includes:
step 401, when the network service system needs capacity expansion, adding a new network node in the network service system, setting an IP address identical to the IP address of the load balancing node for the new network node, and configuring the load balancing node corresponding to the new network node, that is, recording the Mac address of the load balancing node; and the newly added network node sends a newly added request to the switch, wherein the newly added request takes the Mac address of the load balancing node as a destination address.
Step 402, after the switch receives the new request, the switch forwards the new request to the load balancing node according to the Mac address of the load balancing node in the new request.
Step 403, after receiving the new request sent by the new network node, the load balancing node records information such as address information and operating status of the new network node according to the new request. And generating a new request response according to the new request, taking the Mac address of the new network node as the destination address of the new request response, and sending the new request response to the switch.
Step 404, the switch receives the new request response and sends the new request response to the new network node according to the Mac address of the new network node.
Step 405, when the load balancing node determines to distribute the network service provided by the first network node to the newly added network node, obtaining first connection tracking information in the first network node. And the load balancing node takes the Mac address of the newly added network node as the destination address of the first connection tracking information. The first connection trace information includes information related to the network service, and the first connection trace information may be acquired by the load balancing node from the first network node, or the load balancing node stores information related to the network service, where a specific manner of acquiring the first connection trace information is not limited.
Step 406, the load balancing node sends the first connection trace information to the switch.
Step 407, the switch sends the first connection trace information to the newly added network node according to the destination Mac address.
And step 408, when the network service system needs capacity reduction, deleting the network node in the network service system, and sending a deletion request to the load balancing node by the network node to be deleted. And taking the Mac address of the load balancing node as a destination address.
And step 409, the switch sends the deletion request to the load balancing node according to the destination address.
Step 410, after receiving the deletion request of the network node to be deleted, the load balancing node deletes the address information, the running state and other information of the network node to be deleted, and determines that the network node to be deleted is not used for providing network service. And the load balancing node acquires second connection tracking information of the network node to be deleted. And generating a deletion request response, and using the Mac address of the network node to be deleted as the destination address of the deletion request response. The second connection tracking information may be recorded in the load balancing node and may be carried by the delete request; or after the load balancing node receives the deletion request, before the address information, the running state and other information of the network node to be deleted are not deleted, the information may be obtained from the network node to be deleted, and a specific obtaining manner of the second connection tracking information is not limited.
Step 411, the load balancing node sends the delete request response to the switch.
And step 412, the switch sends the request to the network node to be deleted according to the destination address of the deletion request response.
Step 413, the load balancing node determines that the first network node is used to provide the network service provided by the network node to be deleted, and sends the second connection tracking information to the switch. And the Mac address of the first network node is used as the destination address of the second connection trace information.
Step 414, the switch sends the second connection trace information to the first network node according to the destination address of the second connection trace information.
Step 415, the target node sends a first access request to the switch according to the network service requirement, and the like, wherein the destination address of the first access request comprises the IP address and the Mac address of the load balancing node, and the source address comprises the IP address and the Mac address of the target node.
Step 416, after receiving the first access request, the switch forwards the first access request to the load balancing node according to the destination address, that is, the IP address and the Mac address of the load balancing node.
Step 417, after receiving the first access request, the load balancing node determines that the first network node provides network service for the target node, and then converts the Mac address of the load balancing node in the destination address in the first access request into the Mac address of the first network node to generate a second access request; the source address of the second access request comprises an IP address and a Mac address of the target node, and the destination address comprises the IP address of the load balancing node and the Mac address of the first network node; since the load balancing node and the corresponding network nodes (including the first network node) have the same IP address, the source address of the second access request includes the IP address and the Mac address of the target node, and the destination address includes the IP address and the Mac address of the first network node.
Step 418, the load balancing node sends the second access request to the switch.
Step 419, the switch forwards the received second access request to the first network node according to the destination Mac address in the second access request.
Step 420, after receiving the second access request, the first network node processes the second access request to generate an access result. If the address information of the target node is known by the current first network node, step 432 is directly performed, otherwise, step 421 is performed.
Step 421, if the first network node does not record the address information of the target node, a request message is generated to obtain the address information of the target node, and the first network node sends the request message to the switch by using the Mac address of the load balancing node as the destination address of the request message.
Step 422, the switch forwards the request message to the load balancing node according to the destination Mac address (Mac address of the load balancing node) in the request message.
Step 423, the load balancing node generates an ARP request message according to the request content of the request message.
Step 424, the load balancing node broadcasts the ARP request message.
Step 425, the switch broadcasts the ARP request message to the access nodes each including the target node according to the broadcasted ARP request message.
Step 426, the target node in the access node determines, according to the content of the ARP request message, that the address information that the ARP request message needs to obtain is the address information of the target node, and then generates an ARP response message, where the ARP response message includes the address information of the target node and the IP address and Mac address of the load balancing node. The target node sends the ARP response message to the switch.
And step 427, the switch sends the ARP response message to the load balancing node according to the IP address and the Mac address of the load balancing node.
Step 428, the load balancing node encapsulates the ARP response message in the transport layer or network layer of the reply message, and encapsulates the Mac address of the first network node in the data link layer.
Step 429, the load balancing node sends the response message to the switch.
Step 430, the switch sends the response message to the first network node according to the Mac address of the first network node of the data link layer.
And 431, the first network node acquires the address information of the target node according to the response message. And takes the address information of the target node as the destination address of the access result.
Step 432, the first network node sends the access result to the switch.
Step 433, the switch forwards the access result to the target node according to the address information of the target node.
And step 434, the first network node sends a heartbeat message to the switch according to the Mac address of the load balancing node.
Step 435, the switch sends the heartbeat message to the load balancing node according to the Mac address of the load balancing node in the heartbeat message.
Step 436, the load balancing node determines that the first network node can also be used to provide network service according to the heartbeat packet of the first network node, and the first network node is in a survival state. And if the heartbeat message of the first network node is not received within the preset time, determining that the first network node has a fault and cannot be used for providing network service.
And 437, the newly added network node sends a heartbeat message to the switch according to the Mac address of the load balancing node.
And step 438, the switch sends the heartbeat message to the load balancing node according to the Mac address of the load balancing node in the heartbeat message.
Step 439, the load balancing node determines that the newly added network node can be used for providing network service according to the heartbeat message of the newly added network node, and the newly added network node is in a survival state. And if the heartbeat message of the newly added network node is not received within the preset time, determining that the newly added network node has a fault and cannot be used for providing network service.
Step 440, the load balancing node sends the heartbeat packet to the first network node through the switch at regular time.
Step 441, after receiving the heartbeat message, the switch sends the heartbeat message to the first network node.
Step 442, after receiving the heartbeat packet, the first network node determines that the load balancing node is in a survival state.
And step 443, the load balancing node sends a heartbeat message to the newly added network node through the switch at regular time.
And step 444, after receiving the heartbeat message, the switch sends the heartbeat message to the newly added network node.
Step 445, after the newly added network node receives the heartbeat packet, it is determined that the load balancing node is in a survival state.
It should be noted that, for convenience of overall understanding of the scheme, the flow steps in fig. 4 are described as a set of multiple flows, for example, steps 401 to 404 are capacity expansion flows for the network service system. Steps 405 through 407 provide a possible flow of network services for the newly added network node. Steps 408 to 412 are the web services system capacity reduction process. Step 413, step 414 provide the first network node with a possible existing flow of the network service provided by the deleted network node. Steps 415 to 433 are a procedure in which the first network node provides a network service to the target node through the load balancing node, where the procedure of acquiring the target node in steps 421 to 431 may not occur, and steps 415 to 433 may occur in the procedure in which the first network node provides a network service to any access node in the access node cluster 102 through the load balancing node in fig. 1. Steps 434 through 436 are confirmation live flows for the load balancing node to the first network node. Steps 437 to 439 are confirmation survival flows of the load balancing node to the newly added network node. Step 440 to step 445 are the survival confirmation flows of the nodes to the load balancing nodes, and the flows may be that the load balancing nodes send heartbeat messages to each network node, or that the load balancing nodes broadcast heartbeat messages to each network node, and specifically, the survival confirmation flows of the network nodes to the load balancing nodes are not limited. The above processes may be executed without the process shown in fig. 4, for example, the processes from step 401 to step 404 are the capacity expansion process of the network service system; may occur before or after any of the above described process steps. The above processes may or may not occur in fig. 4, for example, the network service system capacity reduction process from step 408 to step 412 may not be sent. The above-described process steps may not be performed according to the process of fig. 4, for example, step 413 may occur before step 412. The network service flow in fig. 4 is only an embodiment of the above flows, and is not limited to the network service flow; based on the flexible scheduling of the network service flow, the effect of improving the bandwidth utilization rate of the network node can be achieved, and corresponding adjustment can be performed according to specific requirements.
Based on the same concept, an embodiment of the present invention provides an access apparatus for a network service, where the network service is provided by a plurality of network nodes through a load balancing node, and fig. 5 is a schematic diagram of the access apparatus for a network service provided in the embodiment of the present application, as shown in fig. 5, including:
a transceiver module 501, configured to receive a first access request for a network service, where the first access request is sent by a target node;
a processing module 502, configured to convert a destination Mac address of the first access request into a Mac address of a first network node, thereby generating the second access request; the first network node is one of the plurality of network nodes;
the transceiver module 501 is further configured to send the second access request to the first network node through a switch; the first network node is configured to send an access result of the second access request to the target node through the switch.
Optionally, the transceiver module 501 is further configured to: receiving a request message sent by the first network node through the switch; the request message comprises an ARP request message serving as message content, and the ARP request message is used for acquiring a target Mac of the target node; acquiring an ARP response message based on the broadcast of the ARP request message; the ARP response message comprises a target Mac of the target node; and sending the ARP response message to the first network node through the switch, wherein the first network node acquires the target Mac of the target node in the ARP response message and sends the access result of the second access request to the target node through the switch.
Optionally, the processing module 502 is specifically configured to: and encapsulating the ARP response message in a transmission layer or a network layer to obtain a response message, and sending the response message to the first network node through the switch. Optionally, the load balancing node has the same IP address as the plurality of network nodes; the transceiver module 501 is configured to receive an access request; the processing module 502 is configured to select a target network node from the plurality of network nodes as a response to the access request according to a calculation rule.
Optionally, the transceiver module 501 is further configured to: and receiving heartbeat messages of the plurality of network nodes, wherein the heartbeat messages are used for determining the working state of the network nodes.
Optionally, the transceiver module 501 is further configured to: receiving a newly-added request and a heartbeat packet sent by a newly-added network node;
the transceiver module 501 is further configured to: synchronizing first connection tracking information of a current network node to the newly added network node, wherein the first connection tracking information is used for sending network service data generated by the network service provided by the current network node to the newly added network node, so that the newly added network node comprises complete network service data used for providing the network service;
the processing module 502 is further configured to: determining that the newly added network node provides network service through the load balancing node;
if the load balancing node receives a deleting request sent by a deleting network node;
the transceiver module 501 is further configured to: synchronizing second connection tracking information of the network node to be deleted to a current network node, wherein the second connection tracking information is used for sending network service data generated by the network node to be deleted for providing network service to the current network node, so that the current network node comprises complete network service data for providing the network service;
the processing module 502 is further configured to: determining the deleted network node and stopping providing network services.
Optionally, the transceiver module 501 is further configured to: receiving, by the switch, a fourth access request sent by the first network node, where the fourth access request is generated according to a third access request of a backend server; the first network node is used for converting the message quintuple in the third access request into a message quintuple with the same hash value as the first network node, and taking the converted message quintuple as the message quintuple in the fourth access request; the transceiver module 501 is further configured to: sending the fourth access request to a target node to obtain an access result of the target node to the fourth access request; the transceiver module 501 is further configured to: and sending the access result of the fourth access request to the first network node through the switch, so that the first network node sends the access result of the fourth access request to the backend server.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.
Claims (11)
1. An access method of a network service, wherein the network service is provided by a plurality of network nodes through a load balancing node; the method comprises the following steps:
the load balancing node receives a first access request aiming at network service and sent by a target node;
translating a destination Mac address of the first access request to a Mac address of a first network node, thereby generating the second access request; the first network node is one of the plurality of network nodes;
the load balancing node sends the second access request to the first network node through a switch; the first network node is configured to send an access result of the second access request to the target node through the switch.
2. The method of claim 1, further comprising:
the load balancing node receives a request message sent by the first network node through the switch; the request message comprises an ARP request message serving as message content, and the ARP request message is used for acquiring a target Mac of the target node;
the load balancing node acquires an ARP response message based on broadcasting the ARP request message; the ARP response message comprises a target Mac of the target node;
and the load balancing node sends the ARP response message to the first network node through the switch, the first network node acquires the target Mac of the target node in the ARP response message, and sends the access result of the second access request to the target node through the switch.
3. The method of claim 2, wherein the load balancing node sending the ARP response message to the first network node through the switch, comprising:
and the load balancing node encapsulates the ARP response message in a transmission layer or a network layer to obtain a response message, and sends the response message to the first network node through the switch.
4. The method of claim 1, comprising:
the load balancing node has the same IP address as the plurality of network nodes;
and the load balancing node receives the access request and selects a target network node from the plurality of network nodes as a response of the access request according to a calculation rule.
5. The method of any one of claims 1-4, further comprising:
and the load balancing node receives heartbeat messages of the plurality of network nodes, wherein the heartbeat messages are used for determining the working state of the network nodes.
6. The method of claim 1, further comprising:
the load balancing node receives a newly-added request and a heartbeat packet sent by a newly-added network node;
the load balancing node synchronizes first connection tracking information of a current network node to the newly added network node, wherein the first connection tracking information is used for sending network service data generated by the network service provided by the current network node to the newly added network node, so that the newly added network node comprises complete network service data used for providing the network service;
and the load balancing node determines that the newly-added network node provides network service through the load balancing node.
7. The method of claim 1, further comprising:
the load balancing node receives a deleting request sent by a deleting network node;
the load balancing node synchronizes second connection tracking information of the network node to be deleted to the current network node, wherein the second connection tracking information is used for sending network service data generated by the network node to be deleted providing network service to the current network node, so that the current network node comprises complete network service data used for providing the network service;
and the load balancing node determines to delete the network node and stops providing the network service.
8. The method of claim 1, further comprising:
the load balancing node receives a fourth access request sent by the first network node through the switch, wherein the fourth access request is generated according to a third access request of a back-end server; the first network node is used for converting the message quintuple in the third access request into a message quintuple with the same hash value as the first network node, and taking the converted message quintuple as the message quintuple in the fourth access request;
the load balancing node sends the fourth access request to a target node to obtain an access result of the target node to the fourth access request;
and the load balancer sends the access result of the fourth access request to the first network node through the switch, so that the first network node sends the access result of the fourth access request to the backend server.
9. An apparatus for accessing a network service, the network service being provided by a plurality of network nodes through a load balancing node, the apparatus comprising:
the system comprises a receiving and sending module, a sending and receiving module and a processing module, wherein the receiving and sending module is used for receiving a first access request aiming at network service and sent by a target node;
a processing module, configured to convert a destination Mac address of the first access request into a Mac address of a first network node, thereby generating the second access request; the first network node is one of the plurality of network nodes;
the transceiver module is further configured to send the second access request to the first network node through a switch; the first network node is configured to send an access result of the second access request to the target node through the switch.
10. A computer-readable storage medium, characterized in that the storage medium stores a program which, when run on a computer, causes the computer to carry out the method of any one of claims 1 to 8.
11. A computer device, comprising:
a memory for storing a computer program;
a processor for calling a computer program stored in said memory to execute the method of any of claims 1 to 8 in accordance with the obtained program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110402394.3A CN113141400B (en) | 2021-04-14 | 2021-04-14 | Network service access method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110402394.3A CN113141400B (en) | 2021-04-14 | 2021-04-14 | Network service access method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113141400A true CN113141400A (en) | 2021-07-20 |
| CN113141400B CN113141400B (en) | 2023-04-07 |
Family
ID=76812542
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110402394.3A Active CN113141400B (en) | 2021-04-14 | 2021-04-14 | Network service access method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113141400B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114268630A (en) * | 2021-12-14 | 2022-04-01 | 浪潮思科网络科技有限公司 | Method, device and equipment for realizing random load balance access based on static ARP (Address resolution protocol) table entry |
| CN114584482A (en) * | 2022-02-14 | 2022-06-03 | 阿里巴巴（中国）有限公司 | Method and device for storing detection data based on memory and network card |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103166870A (en) * | 2011-12-13 | 2013-06-19 | 百度在线网络技术（北京）有限公司 | Load balancing clustered system and method for providing services by using load balancing clustered system |
| CN103200120A (en) * | 2013-04-09 | 2013-07-10 | 杭州华三通信技术有限公司 | Method and network device for message transmission under direct routing type |
| CN106230992A (en) * | 2016-09-28 | 2016-12-14 | 中国银联股份有限公司 | A kind of load-balancing method and load balancing node |
| CN107026890A (en) * | 2016-02-02 | 2017-08-08 | 华为技术有限公司 | A kind of message forming method and load equalizer based on server cluster |
| WO2017133291A1 (en) * | 2016-02-02 | 2017-08-10 | 华为技术有限公司 | Server cluster-based message generation method and load balancer |
| US20180063231A1 (en) * | 2016-08-25 | 2018-03-01 | Nhn Entertainment Corporation | Method and system for processing direct server return load balancing using loopback interface in virtual network environment |
| CN107872368A (en) * | 2017-11-22 | 2018-04-03 | 杭州华为数字技术有限公司 | Detection method, device and the terminal of gateway accessibility in a kind of network node cluster |
| CN109451084A (en) * | 2018-09-14 | 2019-03-08 | 华为技术有限公司 | A kind of service access method and device |
| CN109639589A (en) * | 2018-12-27 | 2019-04-16 | 杭州迪普科技股份有限公司 | A kind of load-balancing method and device |
| CN110753072A (en) * | 2018-07-24 | 2020-02-04 | 阿里巴巴集团控股有限公司 | Load balancing system, method, device and equipment |
| CN111866064A (en) * | 2016-12-29 | 2020-10-30 | 华为技术有限公司 | Load balancing method, device and system |
-
2021
- 2021-04-14 CN CN202110402394.3A patent/CN113141400B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103166870A (en) * | 2011-12-13 | 2013-06-19 | 百度在线网络技术（北京）有限公司 | Load balancing clustered system and method for providing services by using load balancing clustered system |
| CN103200120A (en) * | 2013-04-09 | 2013-07-10 | 杭州华三通信技术有限公司 | Method and network device for message transmission under direct routing type |
| CN107026890A (en) * | 2016-02-02 | 2017-08-08 | 华为技术有限公司 | A kind of message forming method and load equalizer based on server cluster |
| WO2017133291A1 (en) * | 2016-02-02 | 2017-08-10 | 华为技术有限公司 | Server cluster-based message generation method and load balancer |
| US20180063231A1 (en) * | 2016-08-25 | 2018-03-01 | Nhn Entertainment Corporation | Method and system for processing direct server return load balancing using loopback interface in virtual network environment |
| CN106230992A (en) * | 2016-09-28 | 2016-12-14 | 中国银联股份有限公司 | A kind of load-balancing method and load balancing node |
| CN111866064A (en) * | 2016-12-29 | 2020-10-30 | 华为技术有限公司 | Load balancing method, device and system |
| CN107872368A (en) * | 2017-11-22 | 2018-04-03 | 杭州华为数字技术有限公司 | Detection method, device and the terminal of gateway accessibility in a kind of network node cluster |
| CN110753072A (en) * | 2018-07-24 | 2020-02-04 | 阿里巴巴集团控股有限公司 | Load balancing system, method, device and equipment |
| CN109451084A (en) * | 2018-09-14 | 2019-03-08 | 华为技术有限公司 | A kind of service access method and device |
| CN109639589A (en) * | 2018-12-27 | 2019-04-16 | 杭州迪普科技股份有限公司 | A kind of load-balancing method and device |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114268630A (en) * | 2021-12-14 | 2022-04-01 | 浪潮思科网络科技有限公司 | Method, device and equipment for realizing random load balance access based on static ARP (Address resolution protocol) table entry |
| CN114268630B (en) * | 2021-12-14 | 2024-04-12 | 浪潮思科网络科技有限公司 | Method, device and equipment for realizing random load balancing access based on static ARP (Address resolution protocol) table items |
| CN114584482A (en) * | 2022-02-14 | 2022-06-03 | 阿里巴巴（中国）有限公司 | Method and device for storing detection data based on memory and network card |
| CN114584482B (en) * | 2022-02-14 | 2023-09-08 | 阿里巴巴（中国）有限公司 | Method, device and network card for storing detection data based on memory |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113141400B (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110753072B (en) | Load balancing system, method, device and equipment | |
| US10182091B2 (en) | Decentralized, hierarchical, and overlay-driven mobility support architecture for information-centric networks | |
| CN110635987B (en) | Message transmission method, device, equipment and machine readable storage medium | |
| CN113141400B (en) | Network service access method and device | |
| CN111526223B (en) | Management method of edge service server, service data processing method and device | |
| CN110213148B (en) | Data transmission method, system and device | |
| US10652142B2 (en) | SDN-based ARP implementation method and apparatus | |
| CN110474802B (en) | Equipment switching method and device and service system | |
| CN111010329B (en) | Message transmission method and device | |
| CN112968965B (en) | Metadata service method, server and storage medium for NFV network node | |
| US20230067091A1 (en) | Method and device for segment routing service processing, routing equipment, and storage medium | |
| CN113364660A (en) | Data packet processing method and device in LVS load balancing | |
| CN108574587B (en) | Capacity updating method and device for distributed equipment | |
| JP2023526843A (en) | PORT STATE SETTING METHOD, APPARATUS AND SYSTEM, AND STORAGE MEDIUM | |
| WO2023093513A1 (en) | Path sensing method, apparatus and system | |
| CN114827015B (en) | Data forwarding method and virtualized cloud network architecture | |
| CN106489252A (en) | A kind of data transmission method and device | |
| CN114157455A (en) | Data transmission method, device, equipment and storage medium | |
| CN109347851B (en) | Request response method and device | |
| CN112953858A (en) | Message transmission method in virtual network, electronic device and storage medium | |
| CN108737580B (en) | IP address configuration method and device | |
| JP2017050747A (en) | Communication system, transfer device and control device | |
| CN104363172A (en) | Data transceiving method and device | |
| WO2023185297A1 (en) | Data packet transmission method and apparatus, and device, storage medium and program product | |
| CN110505620B (en) | Communication method, management station and hotspot device |
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 |