Service instance addressing method, device and equipment and readable storage medium

Abstract

The invention discloses a service instance addressing method, device and equipment and a readable storage medium. The method comprises the steps that each ETR registers a target address list including service addresses of computing power service instances connected with the ETR to an LISP mapping system; when the ITR does not retrieve the RLOC corresponding to the target service address, each ETR retrieves whether a first RLOC corresponding to the target service address exists or not through an LISP mapping system and a target address list; if the ETR retrieves the first RLOC, sending the first RLOC to the ITR; the ITR screens out a target RLOC from the first RLOC to package the original request service message carrying the target service address, and sends the generated target request service message to a target ETR corresponding to the target RLOC; and after the target ETR analyzes the target request service message, the original request service message is sent to the target computing power service instance corresponding to the target service address so as to prevent the core network from generating routing table dramatic increase.

Description

Technical Field

[0001] This application relates to the field of communication technologies, and particularly to a service instance addressing method, apparatus, device, and readable storage medium. Background Art

[0002] A distributed computing power service instance is a specific form of distributed computing, which connects multiple computing nodes through a network to form a unified computing resource pool. Currently, anycast addresses are often used to identify distributed computing power service instances, that is, all instances of the same computing power service use the same anycast address for identification. Therefore, if a user wants to access a computing power service instance, they need to obtain the route of the anycast address that identifies the computing power service instance.

[0003] In related technologies, the routing information of anycast addresses is often transmitted through BGP (Border Gateway Protocol); however, since the use of anycast addresses may cause the same IP address to be used at different network locations, in order to accurately implement the addressing of computing power services, the BGP router needs to abandon route aggregation, that is, the BGP router cannot perform prefix aggregation as usual. Then, once the computing power service is deployed on a large scale, it will cause the BGP routing table to increase sharply, resulting in an overload of the routers in the core network.

[0004] It can be seen that when implementing the addressing of computing power services, how to avoid a sharp increase in the routing table in the core network is an urgent problem to be solved currently. Summary of the Invention

[0005] This application provides a service instance addressing method, apparatus, device, and readable storage medium, which can avoid the transfer of a large number of computing power service instance routes in the core network to prevent a sharp increase in the routing table in the core network.

[0006] In a first aspect, an embodiment of this application provides a service instance addressing method, including the following steps:

[0007] Each egress tunnel router (ETR) registers the target address list corresponding to it to the Locator / ID Separation Protocol (LISP) mapping system, where the target address list includes the service addresses corresponding to the computing power service instances connected to the ETR, and the service addresses of all computing power service instances corresponding to the same service are the same;

[0008] When the ingress tunnel router (ITR) does not retrieve the route locator (RLOC) corresponding to the destination service address in the preset mapping cache, each ETR is enabled to retrieve whether there is a first RLOC corresponding to the destination service address based on the preset mapping database corresponding to it through the LISP mapping system and the target address list;

[0009] If the ETR retrieves the first RLOC, it sends the first RLOC to the ITR;

[0010] The ITR filters out the target RLOC from all the received first RLOCs, encapsulates the original request service message carrying the destination service address sent by the user, generates a target request service message, and sends it to the target ETR corresponding to the target RLOC;

[0011] The target ETR parses the received target request service message and sends the parsed original request service message to the target computing power service instance corresponding to the destination service address.

[0012] Combined with the first aspect, in an implementation, the process of enabling each ETR to retrieve whether there is a first RLOC corresponding to the destination service address based on the preset mapping database corresponding to it through the LISP mapping system and the target address list includes:

[0013] The ITR sends a target mapping request message encapsulated with a LISP header to the LISP mapping system, and the target mapping request message includes a mapping message requesting the mapping between the destination service address and the RLOC;

[0014] When the LISP mapping system retrieves the mapping relationship between the destination service address and the RLOC from the target address list, it sends the target mapping request message to all ETRs respectively;

[0015] For each ETR, the ETR retrieves the preset mapping database corresponding to it based on the target mapping request message to determine whether there is a first RLOC corresponding to the destination service address.

[0016] Combined with the first aspect, in an implementation, before the step of sending the first RLOC to the ITR, it further includes:

[0017] The ETR obtains the target parameter corresponding to the destination service address according to the preset traffic diversion strategy, where the traffic diversion strategy includes one of the minimum routing cost strategy, the minimum number of access flows strategy, and the minimum access flow bandwidth strategy, and the target parameter includes the default value corresponding to the minimum routing cost strategy, the number of access flows corresponding to the minimum number of access flows strategy, and the access flow rate corresponding to the minimum access flow bandwidth strategy;

[0018] The ETR filters out the target priority value corresponding to the target parameter from the preset priority value mapping relationship, so as to execute the step of sending the first RLOC to the ITR based on the first RLOC and the target priority value, and the target priority value is used as the screening condition for the ITR to screen the target RLOC.

[0019] In combination with the first aspect, in one embodiment, the step of sending the first RLOC to the ITR includes:

[0020] The ETR writes the first RLOC and its corresponding target priority value into the target mapping response message;

[0021] The ETR sends the target mapping response message to the ITR for the ITR to perform the step of encapsulating the original request service message carrying the destination service address sent by the user by screening out the target RLOC from all the received first RLOCs based on the target mapping response message.

[0022] In combination with the first aspect, in one embodiment, the step of the ITR screening out the target RLOC from all the received first RLOCs to encapsulate the original request service message carrying the destination service address sent by the user includes:

[0023] The ITR parses all the received target mapping response messages respectively to obtain a plurality of first RLOCs and their corresponding target priority values;

[0024] The ITR screens out the smallest target priority value from all the target priority values and uses the first RLOC corresponding to the smallest target priority value as the target RLOC;

[0025] The ITR encapsulates the original request service message carrying the destination service address sent by the user based on the target RLOC to obtain the target request service message.

[0026] In combination with the first aspect, in one embodiment, after the step of the ITR parsing all the received target mapping response messages respectively to obtain a plurality of first RLOCs and their corresponding target priority values, the method further includes:

[0027] The ITR constructs a target mapping relationship between the destination service address and each first RLOC and its corresponding target priority value;

[0028] The ITR updates the preset mapping cache based on the target mapping relationship.

[0029] In combination with the first aspect, in one embodiment, after the step of using the first RLOC corresponding to the smallest target priority value as the target RLOC, the method further includes:

[0030] The ITR obtains the source node identifier EID corresponding to the user;

[0031] The ITR constructs a target mapping relationship among the source EID, the destination service address, and the target RLOC, so that the access flows of users with the same source EID accessing the same service are directed to the computing power service instances with the destination service address connected to the same target RLOC.

[0032] In a second aspect, an embodiment of the present application provides a service instance addressing device, including: an egress tunnel router (ETR), a locator / identifier separation protocol (LISP) mapping system, and an ingress tunnel router (ITR);

[0033] Each ETR registers the corresponding target address list to the LISP mapping system, and the target address list includes the service addresses corresponding to the computing power service instances connected to the ETR, where the service addresses of all computing power service instances corresponding to the same service are the same;

[0034] When the ITR does not retrieve the routing locator (RLOC) corresponding to the destination service address in the preset mapping cache, each ETR is enabled to retrieve whether there is a first RLOC corresponding to the destination service address based on the corresponding preset mapping database through the LISP mapping system and the target address list;

[0035] If the ETR retrieves the first RLOC, it sends the first RLOC to the ITR;

[0036] The ITR filters out the target RLOC from all the received first RLOCs, encapsulates the original request service message carrying the destination service address sent by the user, generates a target request service message, and sends it to the target ETR corresponding to the target RLOC;

[0037] The target ETR parses the received target request service message, and sends the parsed original request service message to the target computing power service instance corresponding to the destination service address.

[0038] In a third aspect, an embodiment of the present application provides a service instance addressing device. The service instance addressing device includes a processor, a memory, and a service instance addressing program stored on the memory and executable by the processor. When the service instance addressing program is executed by the processor, the steps of the service instance addressing method as described above are implemented.

[0039] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium. A service instance addressing program is stored on the computer-readable storage medium. When the service instance addressing program is executed by a processor, the steps of the service instance addressing method as described above are implemented.

[0040] The beneficial effects brought by the technical solutions provided by the embodiments of the present application at least include:

[0041] By using the service address as the unique identifier of the service, the service addresses of all computing power service instances corresponding to the same service are the same; each ETR registers a target address list including the service addresses corresponding to the computing power service instances connected to it with the LISP mapping system; when the ITR fails to retrieve the RLOC corresponding to the destination service address from the preset mapping cache, the LISP mapping system and the target address list are used to enable each ETR to retrieve whether there is a first RLOC corresponding to the destination service address based on the preset mapping database corresponding to it, so as to determine whether there is a computing power service instance corresponding to the destination service address connected to it; if the ETR retrieves the mapping relationship between the destination service address and the first RLOC, it means that there is a computing power service instance corresponding to the destination service address connected to it, and then the first RLOC is sent to the ITR; the ITR filters out the target RLOC from all the received first RLOCs to encapsulate the original request service message carrying the destination service address sent by the user, generates a target request service message and sends it to the target ETR corresponding to the target RLOC; the target ETR parses the received target request service message and sends the parsed original request service message to the target computing power service instance corresponding to the destination service address, so as to realize the addressing of the computing power service instance, without the need to transmit the routing information of the anycast address through BGP, thereby avoiding the routing of a large number of distributed computing power service instances from being transmitted in the core network, and thus preventing the problem of the core network routing table increasing sharply. Brief Description of the Drawings

[0042] Figure 1 It is a schematic flowchart of an embodiment of the service instance addressing method of the present application;

[0043] Figure 2 It is a schematic diagram of the LISP architecture involved in the solution of the embodiment of the present application;

[0044] Figure 3 It is a schematic diagram of the SID-to-RLOC mapping involved in the solution of the embodiment of the present application;

[0045] Figure 4 It is a schematic diagram of the deployment of distributed computing power service instances based on LISP involved in the solution of the embodiment of the present application;

[0046] Figure 5 It is a schematic diagram of the traffic statistics involved in the solution of the embodiment of the present application;

[0047] Figure 6 It is a schematic diagram of the hardware structure of the service instance addressing device involved in the solution of the embodiment of the present application. Detailed Description of the Embodiment

[0048] To enable those skilled in the art to better understand the solution of this application, the following will clearly and completely describe the technical solution in the embodiments of this application in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of this application.

[0049] First, some technical terms in this application are explained to facilitate understanding by those skilled in the art.

[0050] LISP: Locator / Identifier Separation Protocol, the Locator and Identifier Separation Protocol.

[0051] EID: Endpoint Identifier, the node identifier, which is used to uniquely identify the address of a node and is independent of its topological location, usually for routing within a domain.

[0052] RLOC: Routing Locator, the routing locator, which is the address assigned to a network access point topologically and is usually for routing between domains.

[0053] ITR: Ingress Tunnel Router, the ingress tunnel router, which is a router supporting LISP and encapsulates packets from LISP sites into the core network.

[0054] ETR: Egress Tunnel Router, the egress tunnel router, which is a router supporting LISP and decapsulates packets in the core network and sends them to LISP sites; among them, the address of the ETR is the RLOC.

[0055] xTR: Tunnel Router, the tunnel router, which is a router that can simultaneously implement the functions of ITR and ETR.

[0056] Map-Cache: Mapping Cache, which contains the mapping from EID to RLOC.

[0057] Map-Server: Mapping Server, a network infrastructure component that learns mappings from ETRs and publishes them to the LISP mapping system.

[0058] Map-Request: Control Plane Message, which is used to query the mapping system to resolve the EID.

[0059] Map-Reply: A control plane message that is returned as a response to a Map-Request sent to the mapping system to resolve an EID.

[0060] ECM: Encapsulated Control Message, an encapsulated control message that is used to encapsulate control packets sent between xTRs, between an xTR and a mapping database system, or within a mapping database system.

[0061] Encapsulated Map-Request: A LISP Map-Request carried in an ECM, preceded by an additional LISP header, sent to the UDP destination port 4342; its "outer" address is a routable IP address, also known as an RLOC, which is used by an ITR when sending to a Map-Resolver and by a Map-Server when forwarding a Map-Request to an ETR.

[0062] Map-Resolver: A mapping resolver, which is a network infrastructure component that accepts LISP-encapsulated (ECM) Map-Requests, typically from an ITR, and determines whether the destination IP address belongs to an EID namespace; if not, it returns a negative Map-Reply, and if so, the Map-Resolver finds the appropriate EID-to-RLOC mapping by querying a mapping database system; among them, the Map-Resolver and the Map-Server constitute a LISP mapping system.

[0063] Negative Map-Reply: A negative Map-Reply that contains a LISP Map-Reply with an empty Locator-Set; this type of Map-Reply is returned if the destination EID is not registered in the mapping system, is policy-rejected, or authentication fails.

[0064] Map-Register: A LISP message sent by an ETR to a Map-Server to register its associated EID prefix; in addition to the set of EID prefixes to be registered, this message includes one or more RLOCs to reach the ETR, which are used by the Map-Server when forwarding Map-Requests (reformatted as encapsulated Map-Requests); the ETR can request the Map-Server to answer Map-Requests on its behalf by setting the "proxy Map-Reply" flag (P-bit) in the message.

[0065] Map-Notify: A LISP message sent by the Map-Server to the ETR to confirm that the Map-Register has been received and processed. The ETR requests the return of Map-Notify by setting the "want-map-notify" flag (M-bit) in the Map-Register message. Different from Map-Reply, Map-Notify uses UDP port 4342 for both the source and the destination. When the RLOC-Set changes, the Map-Server also sends Map-Notify messages to the ITR.

[0066] To make the objectives, technical solutions, and advantages of the present application clearer, the following will further describe the embodiments of the present application in detail with reference to the accompanying drawings.

[0067] In a first aspect, an embodiment of the present application provides a service instance addressing method.

[0068] In one embodiment, refer to Figure 1 , Figure 1 which is a schematic flowchart of an embodiment of the service instance addressing method of the present application. As Figure 1 shown, the service instance addressing method includes:

[0069] Step S10: Each egress tunnel router (ETR) registers the target address list corresponding to it with the Locator / ID Separation Protocol (LISP) mapping system. The target address list includes the service addresses corresponding to the computing power service instances connected to the ETR. Among them, the service addresses of all computing power service instances corresponding to the same service are the same.

[0070] Exemplarily, in this embodiment, LISP is used to implement the addressing of multiple computing power service instances of the same computing power service identified by the same anycast address, so as to avoid transmitting the routing information of the anycast address through BGP. Furthermore, the routing of a large number of computing power service instances does not need to be transmitted in the core network, thereby preventing the problem of a sharp increase in the routing table in the core network. Among them, in this embodiment, an ingress tunnel router (ITR) and an egress tunnel router (ETR) that support the LISP function are deployed between the core network and the site where the distributed computing power service instances are deployed to implement the message processing, forwarding, etc. in the process of addressing the computing power service instances. It should be noted that a router xTR that can implement both the ITR and ETR functions can be preferably used to replace the ITR and ETR, so that the node where the xTR is located can determine whether it is a tunnel entrance or a tunnel exit according to the actual scenario requirements. However, for the sake of simplicity of description, in the subsequent embodiments, the router corresponding to the tunnel entrance is referred to as the ITR and the router corresponding to the tunnel exit is referred to as the ETR. Therefore, refer to Figure 2As shown in the figure, the LISP architecture in this embodiment includes user nodes, ITR nodes, a mapping resolver Map-Resolver, a mapping server Map-Server, ETR nodes, and computing power service instances, and realizes the addressing of computing power service instances through data interaction between the above nodes.

[0071] It should be understood that for each service, a unique address will be assigned to it, and this address can be an anycast address or an extended SID (Service ID); it should be noted that in this embodiment, the SID will be preferably used as the service address to avoid the limitations and constraints of anycast, that is, a new SID space is added in LISP, and the form of this SID is the same as that of the EID, 32-bit (IPv4) or 128-bit (IPv6) IP address, that is, a service is uniquely identified by the SID. It should be noted that although a service can have multiple distributed computing power service instances, all computing power service instances use the same SID address; for example, if the SID corresponding to Service 1 is X and Service 1 includes computing power service instances 11, 12, 13, and 14, then the SIDs corresponding to computing power service instances 11 to 14 are all X. For the sake of simplicity of description, the subsequent embodiments will take the service address as the SID as an example to explain the addressing of computing power service instances.

[0072] It can be understood that for each ETR, there may be computing power service instances corresponding to different services connected to it. Therefore, in this embodiment, the mapping relationship between the SID of the computing power service instance and the address RLOC of the ETR will be created according to the creation mechanism of the EID-to-RLOC mapping relationship in the original LISP, that is, the SID-to-RLOC mapping relationship is configured in the ETR. Of course, it is also possible to make the computing power service instance identify itself as a computing power service instance when advertising its SID address by extending internal gateway protocols such as ISIS or OSPF. For example, assume that the RLOC of ETR1 is Y, and on ETR1, there are computing power service instance 11 corresponding to Service 1 with SID X, computing power service instance 21 corresponding to Service 2 with SID Z, and computing power service instance 31 corresponding to Service 3 with SID M. Then, in the ETR, the mapping relationships between the prefix of X and Y, the prefix of Z and Y, and the prefix of M and Y are respectively configured to form a target address list corresponding to ETR1, that is, the target address list of ETR1 includes the mapping relationships between the prefix of X and Y, the prefix of Z and Y, and the prefix of M and Y.

[0073] For each ETR, it registers its target address list to the LISP mapping system by sending a Map-Register message to the Map-Server, so as to inform the Map-Server of the SIDs of the computing power service instances that it allows users to access, enabling the Map-Server to determine whether the computing power service instance accessed by the user is within the permitted range according to the mapping relationship between the SID and the RLOC, that is, to determine whether the computing power service instance accessed by the user is reachable. Among them, after the Map-Server completes the registration of the target address list, it will send a Map-Notify to the ETR to inform the ETR that it has received and processed the Map-Register message.

[0074] Among them, in this embodiment, the transmission of the SID can be implemented by extending the original ETR registration mechanism, that is, carrying the SID information in the Map-Reply and Map-Register messages. It should be understood that in order to be compatible with the original LISP and be more easily deployed and promoted in practice, this embodiment does not modify the Map-Reply and Map-Register message formats defined in RFC 9301, but only places the SID-Prefix-AFI and SID-Prefix in the EID-Prefix-AFI and EID-Prefix fields of the Map-Reply and Map-Register messages, so that the ETR passes the SID address in the EID address to the ITR in this way, and the ITR does not need to distinguish between the SID and the EID.

[0075] Step S20: When the ingress tunnel router ITR fails to retrieve the routing locator RLOC corresponding to the destination service address from the preset mapping cache, each ETR is enabled to retrieve whether there is a first RLOC corresponding to the destination service address based on the preset mapping database corresponding to it through the LISP mapping system and the target address list.

[0076] Exemplarily, referring to Figure 3 As shown, the preset mapping cache Map-Cache on the ITR stores a SID-to-RLOC mapping table, which contains the mapping relationship between the SIDs of the computing power service instances that have been accessed and the RLOCs of all the ETRs connected to them. Referring to Figure 4As shown, when a user needs to use a certain service 1, a service request will be sent to the ITR, that is, the original request service message carrying the destination SID corresponding to the requested service 1 will be sent to the ITR; after receiving the original request service message sent by the user, the ITR first performs a routing table lookup on the destination SID. If the lookup is successful, it will directly forward according to the routing; if the lookup fails, it will perform the longest prefix match query of the SID in its internal Map-Cache with the destination SID as the key value pair to determine whether there is a SID-to-RLOC mapping in the Map-Cache; if it exists, it means that a user has accessed the computing power service instance corresponding to the destination SID before, and the target RLOC will be determined through the mapping relationship stored in the Map-Cache, so as to transmit the service request message to the computing power service instance corresponding to the destination SID through the ETR corresponding to the target RLOC.

[0077] If there is no mapping relationship between the destination SID and the RLOC in the Map-Cache, that is, no RLOC is retrieved to have a mapping relationship with the destination SID. At this time, the RLOC set for reaching the destination EID will be obtained through the LISP mapping system, that is, it will be determined whether the destination SID is reachable through the registered target address list in the LISP mapping system. If it is reachable, an Encapsulated Map-Request encapsulated with an additional LISP header will be sent to all ETRs, so that each ETR can learn that the ITR is requesting the mapping of the destination SID to the RLOC; therefore, each ETR will view the destination SID in the received Encapsulated Map-Request and match the destination SID with the prefix in the preset mapping database of the SID-to-RLOC configured internally or learned from the IGP to determine whether there is an RLOC (i.e., the first RLOC) having a mapping relationship with the destination SID.

[0078] Further, in one embodiment, the process of enabling each ETR to retrieve whether there is a first RLOC corresponding to the destination service address based on the preset mapping database corresponding to it through the LISP mapping system and the target address list includes:

[0079] The ITR sends a target mapping request message encapsulated with a LISP header to the LISP mapping system, and the target mapping request message includes a mapping message requesting the destination service address and the RLOC.

[0080] When the LISP mapping system retrieves that there is a mapping relationship between the destination service address and the RLOC from the target address list, the target mapping request message will be sent to all ETRs respectively.

[0081] For each ETR, the ETR retrieves the corresponding preset mapping database based on the target mapping request message to determine whether there is a first RLOC corresponding to the destination service address.

[0082] Exemplarily, in this embodiment, when the ITR does not find any RLOC with a mapping relationship with the destination SID in the Map-Cache, it will send an Encapsulated Map-Request (i.e., a target mapping request message encapsulated with a LISP header) to the Map-Resolver in the LISP mapping system to request the mapping of the destination SID to the RLOC, that is, to obtain the set of RLOCs reaching the destination SID; the Map-Resolver unpacks the received Encapsulated Map-Request to obtain the parsed message content (for example, the message content is that the ITR cannot find the mapping of the destination SID to the RLOC and is not sure whether the destination SID exists), and then transmits the parsed message content to the Map-Server in the form of a Map-Request; after receiving the Map-Request, the Map-Server will determine whether the destination SID is within the permitted range according to the registered target address list thereon. If there is no mapping relationship between the destination SID and the RLOC in the target address list, it means that the destination SID is not within the permitted range, and the Map-Server will reply to the ITR that the destination SID is unreachable through a Negative Map-Reply.

[0083] If there is a mapping relationship between the destination SID and the RLOC stored in the target address list, it means that the destination SID is within the permitted range, that is, the destination SID is reachable. Then, the Encapsulated Map-Request is forwarded to all ETRs so that each ETR retrieves the destination SID from the corresponding preset mapping database based on the Encapsulated Map-Request to determine whether there is a first RLOC corresponding to the destination SID.

[0084] It should be noted that if the ETR enables the Map-Server proxy reply, after the Map-Server finds an RLOC with a mapping relationship with the destination SID, it will directly return all the found RLOCs to the ITR for the ITR to select a target RLOC from them for transmitting the service request message; if the ETR does not enable the Map-Server proxy reply, it is necessary to forward the Encapsulated Map-Request to all ETRs to implement the transmission of the RLOC through the ETR.

[0085] Step S30: If the ETR retrieves the first RLOC, it sends the first RLOC to the ITR.

[0086] Exemplarily, in this embodiment, for each ETR, if the ETR does not find a matching entry for the destination SID in the preset mapping system, the Encapsulated Map-Request is discarded. If a first RLOC having a mapping relationship with the destination SID is found, the first RLOC is sent to the ITR through a Map-Reply, so that the ITR receives a set of RLOCs corresponding to the destination SID, that is, the RLOC set contains all the first RLOCs it receives.

[0087] Step S40: The ITR filters out a target RLOC from all the first RLOCs received, encapsulates the original request service message carrying the destination service address sent by the user, generates a target request service message, and sends it to a target ETR corresponding to the target RLOC.

[0088] Exemplarily, in this embodiment, after the ITR receives the first RLOCs sent by different ETRs, it can randomly select one from all the first RLOCs as the target RLOC. Of course, it can also select one as the target RLOC according to a preset traffic diversion strategy (such as the minimum routing cost). This is not limited herein. Then, the target RLOC is used as the destination service address of the LISP header to encapsulate the LISP header, that is, the LISP header is added to the original request service message carrying the destination SID sent by the user based on the target RLOC and the message is encapsulated to obtain a target request service message. The ITR then sends the target request service message to the target ETR with the address of the target RLOC, so as to direct the user's service request to the computing power service instance having the destination SID connected thereto through the target ETR.

[0089] Further, in one embodiment, before the step of sending the first RLOC to the ITR, it further includes:

[0090] The ETR obtains target parameters corresponding to the destination service address according to a preset traffic diversion strategy, where the traffic diversion strategy includes one of a minimum routing cost strategy, a minimum access flow number strategy, and a minimum access flow bandwidth strategy, and the target parameters include a default value corresponding to the minimum routing cost strategy, an access flow number corresponding to the minimum access flow number strategy, and an access flow rate corresponding to the minimum access flow bandwidth strategy;

[0091] The ETR filters out a target priority value corresponding to the target parameters from a preset priority value mapping relationship, so as to perform the step of sending the first RLOC to the ITR based on the first RLOC and the target priority value, and the target priority value is used as a screening condition for the ITR to screen the target RLOC.

[0092] Exemplarily, in this embodiment, in order to direct traffic to the optimal computing power service instance, traffic diversion strategies such as the strategy of minimizing routing cost, the strategy of minimizing the number of access flows, and the strategy of minimizing the bandwidth of access flows will be provided. The ITR can pre-select one of them as the preset traffic diversion strategy according to the scenario requirements and inform the ETR; the ETR needs to monitor the load conditions of each computing power service instance in real time and set the Priority value (i.e., the priority value) for the computing power service instance it is connected to according to the preset traffic diversion strategy, so that the ITR can select an optimal computing power service instance according to the magnitude of the received Priority value.

[0093] Among them, when the ETR monitors all access flows of the SID, the following method can be used for flow information statistics: when a new access flow is received, the statistical counts of the number and bandwidth of the access flow are increased, and when no access flow is received for a certain time interval, the statistical counts of the number and bandwidth of the access flow are decreased; for example, when a new access flow is received, the flow count statistic is incremented by 1, the flow bandwidth statistic is incremented by the current flow bandwidth, and the current access flow starts a timeout timer; if no access flow is received again when the current access flow timer times out, the flow information is deleted, and at the same time the flow count statistic is decremented by 1 and the flow bandwidth statistic is decremented by the current timeout flow bandwidth. Based on this, the ETR can establish a traffic statistics table with the SID as the key value as shown in Figure 5 to record and store the flow information table, the flow count statistic, and the flow bandwidth statistic for accessing this SID. Among them, in the flow information table, the source EID (i.e., the address corresponding to the user node) and the source RLOC (i.e., the address of the ITR) are used as key values to record and store the flow bandwidth information and the flow timeout timer for different users to access the SID through the ITR.

[0094] It should be noted that in order to be compatible with the original LISP and be more easily deployed and promoted in practice, this embodiment will not change the LISP message structure, but enable the ETR to generate an appropriate Priority value according to the configured traffic diversion strategy (i.e., the preset traffic diversion strategy) and the Priority mapping rule and in combination with the monitored load status of the computing power service instance; among them, each ETR should be configured with the same traffic diversion strategy and Priority mapping rule to ensure fair access to the computing power service instance.

[0095] In this embodiment, the ETR needs to map the statistics of the number of access service streams and the statistics of stream bandwidth (i.e., stream rate) collected into the Priority field of the Map-Reply and Map-Register messages in RFC 9301. Among them, according to the provisions in RFC 9301, the valid values of Priority are 1 to 254, 255 is not used for unicast, and 0 is the initial value. For the minimum routing cost strategy, the Priority value of the computing power service instance will be set to 0. For the strategy of the least number of access streams, it needs to be determined according to the statistical results of the number of streams. For the strategy of the least access stream bandwidth, it needs to be determined according to the statistical results of the stream bandwidth.

[0096] It should be understood that the ETR will pre-build different Priority mapping relationships for different traffic steering strategies. Among them, for the minimum routing cost strategy, its corresponding Priority mapping rule is that the Priority value is set to 0. Then the preset Priority value mapping relationship is the corresponding relationship between the default value and 0. This default value can be any self-defined value as long as it does not conflict with other parameters. For the strategy of the least number of access streams, its corresponding Priority mapping rule is that the higher the number of access streams, the larger the Priority value. Then the preset Priority value mapping relationship can include that when the number of access streams is 0 - 10, the Priority value is set to 1; when the number of access streams is 11 - 20, the Priority value is set to 2; when the number of access streams is 21 - 30, the Priority value is set to 3, and so on. For the strategy of the least access stream bandwidth, its corresponding Priority mapping rule is that the larger the access stream bandwidth, the larger the Priority value. Then the preset Priority value mapping relationship can include that when the access stream bandwidth is 0 - 10KB, the Priority value is set to 1; when the access stream bandwidth is 11 - 20KB, the Priority value is set to 2; when the access stream bandwidth is 21 - 30KB, the Priority value is set to 3, and so on. It should be noted that the setting of the above Priority value mapping relationship is only a presentation of the embodiment and can be adjusted adaptively according to actual needs.

[0097] Therefore, the ETR will obtain the target parameter corresponding to the first RLOC according to the traffic steering strategy preset by the ITR. Among them, if the preset traffic steering strategy is the minimum routing cost strategy, the target parameter is the default value. If the preset traffic steering strategy is the strategy of the least number of access streams, the target parameter is the number of access streams of the computing power service instance corresponding to the destination SID. If the preset traffic steering strategy is the strategy of the least access stream bandwidth, the target parameter is the access stream bandwidth of the computing power service instance corresponding to the destination SID.

[0098] After obtaining the target parameter, the ETR will screen out the target priority value corresponding to the target parameter from the priority value mapping relationship corresponding to the target parameter as the priority value of the computing power server instance corresponding to the destination SID. For example, assume that the target parameter obtained by the ETR is the default value. Then, according to the Priority value mapping relationship corresponding to the default value, the Priority value can be determined to be 0. Thus, the ETR sets the target priority value of the computing power server instance with the destination SID connected to it to 0. Assume that the target parameter obtained by the ETR is the access stream bandwidth and the access stream bandwidth is 18KB. Then, according to the Priority value mapping relationship corresponding to the access stream bandwidth, the Priority value can be determined to be 2. Thus, the ETR sets the target priority value of the computing power server instance with the destination SID connected to it to 2. Assume further that the target parameter obtained by the ETR is the number of access streams and the number of access streams is 7. Then, according to the Priority value mapping relationship corresponding to the number of access streams, the Priority value can be determined to be 1. Thus, the ETR sets the target priority value of the computing power server instance with the destination SID connected to it to 1.

[0099] After determining the target priority value of the computing power server instance with the destination SID connected to it, the ETR will send its own RLOC (i.e., the first RLOC) and the target priority value of the computing power server instance corresponding to the destination SID to the ITR, so that the ITR can screen out the target ETR where the optimal computing power service instance is located based on the magnitude of the target priority value.

[0100] Further, in one embodiment, the sending the first RLOC to the ITR includes:

[0101] The ETR writes the first RLOC and its corresponding target priority value into the target mapping response message.

[0102] The ETR sends the target mapping response message to the ITR for the ITR to perform the step of screening out the target RLOC from all the received first RLOCs and encapsulating the original request service message carrying the destination service address sent by the user based on the target mapping response message.

[0103] Exemplarily, in this embodiment, the ETR writes the first RLOC and its corresponding target priority value into the target mapping response message; for example, assume that the target parameter obtained by the ETR1 with the first RLOC being Y1 is the number of access flows and the number of access flows is 7, then the target priority value of the computing power server instance with the destination SID connected to the ETR1 will be set to 1; assume that the target parameter obtained by the ETR2 with the first RLOC being Y2 is the number of access flows and the number of access flows is 15, then the target priority value of the computing power server instance with the destination SID connected to the ETR2 will be set to 2; assume that the target parameter obtained by the ETR1 with the first RLOC being Y3 is the number of access flows and the number of access flows is 23, then the target priority value of the computing power server instance with the destination SID connected to the ETR3 will be set to 3; based on this, after the ETR1 writes Y1 and the target priority value "1" into the target mapping response message, the ETR2 writes Y2 and the target priority value "2" into the target mapping response message, and the ETR3 writes Y3 and the target priority value "3" into the target mapping response message, it is replied to the ITR through Map-Reply as a response to the Encapsulated Map-Request; and the ITR can filter the target ETR where the optimal computing power service instance is located according to the target priority value carried in each received target mapping response message.

[0104] Further, in one embodiment, the ITR filters out the target RLOC from all the received first RLOCs and encapsulates the original request service message carried by the user with the destination service address, including:

[0105] The ITR parses each of the received target mapping response messages to obtain multiple first RLOCs and their corresponding target priority values;

[0106] The ITR filters out the smallest target priority value from all the target priority values, and uses the first RLOC corresponding to the smallest target priority value as the target RLOC;

[0107] The ITR encapsulates the original request service message carried by the user with the destination service address based on the target RLOC to obtain the target request service message.

[0108] Exemplarily, in this embodiment, after the ITR parses all the received target mapping response messages respectively, a plurality of first RLOCs and their corresponding target priority values can be obtained; for example, parsing the target mapping response message sent by ETR1 can obtain Y1 and its corresponding target priority value "1", parsing the target mapping response message sent by ETR2 can obtain Y2 and its corresponding target priority value "2", and parsing the target mapping response message sent by ETR3 can obtain Y3 and its corresponding target priority value "3"; then, the ITR filters out the smallest target priority value from all the target priority values, and uses the first RLOC corresponding to the smallest target priority value as the target RLOC, that is, among the three target priority values parsed by the ITR, the priority value of the computing power service instance connected to ITR1 corresponding to the destination service address is the smallest, so the computing power service instance connected to ITR1 corresponding to the destination service address is used as the optimal computing power service instance; therefore, the first RLOC corresponding to ITR1 (i.e., Y1) is used as the target RLOC to be used to send the data packet to the topological location of the SID, that is, to direct the user's service request to the appropriate computing power service instance; then, based on the target RLOC (i.e., Y1), the original request service message carrying the destination service address sent by the user is encapsulated to obtain the target request service message. It should be noted that when the minimum value of all the target priority values is 0, the ITR will select the first RLOC with the smallest cost in the local routing table as the target RLOC for guidance.

[0109] Further, in one embodiment, after the step in which the ITR parses all the received target mapping response messages respectively to obtain a plurality of first RLOCs and their corresponding target priority values, the method further includes:

[0110] The ITR constructs a target mapping relationship between the destination service address and each first RLOC and its corresponding target priority value;

[0111] The ITR updates a preset mapping cache based on the target mapping relationship.

[0112] Exemplarily, as shown in Figure 3 After the ITR parses all the received target mapping response messages to obtain all the first RLOCs and their corresponding target priority values, the ITR also stores each first RLOC and its corresponding target priority value Priority into the RLOC table corresponding to the destination SID, so as to construct a target mapping relationship between the destination SID and each first RLOC, thereby realizing the update of the SID-to-RLOC mapping table, so that when the ITR receives a new service request corresponding to the destination SID, it can immediately find all the first RLOCs having a mapping relationship with the destination SID from the SID-to-RLOC mapping table.

[0113] Further, in one embodiment, after the step of using the first RLOC corresponding to the smallest target priority value as the target RLOC, the method further includes:

[0114] The ITR obtains the source node identifier EID corresponding to the user;

[0115] The ITR constructs a target mapping relationship among the source EID, the destination service address, and the target RLOC, so that the access flows of users with the same source EID accessing the same service are directed to the computing power service instances with the destination service address connected to the same target RLOC.

[0116] Exemplarily, referring to Figure 3 As shown, the ITR will add a flow information table for each SID in the SID-to-RLOC mapping table, and the flow information table stores, with the source EID as the key value, the RLOC corresponding to the ETR where the computing power service instance used by the user corresponding to the source EID when accessing the service corresponding to the SID before is located, so that the access flows of users with the same source EID accessing the same service can be directed to the computing power service instances with the destination SID connected to the same RLOC, that is, direct the flows of the same user accessing the same SID to the same computing power service instance, thereby avoiding the same user accessing multiple computing power service instances of the same service at the same time, and thus preventing data transmission blockage. For example, when the user with the source EID of N accesses Service 1 with the destination SID of X, the target RLOC selected by the ITR for it is Y1, then Y1 is stored with N as the key value in the flow information table corresponding to X. Then, when the subsequent user N accesses Service 1 again, the ITR will direct the request for Service 1 to the computing power service instance with the destination SID of X connected to Y1.

[0117] Specifically, after the ITR receives a service request with the source EID of user N and the destination SID of X, it can first query the SID record in the SID-to-RLOC mapping table with X as the key value. If the X record exists, it continues to query the flow information table in the X record with the user's source EID (i.e., N) as the key value. If a record with the source EID of N exists in the flow information table, it selects the RLOC in the source EID record as the target RLOC and uses the target RLOC as the LISP outer destination service address. If a record with the source EID of N does not exist in the flow information table, it filters out the RLOC with the smallest priority value from the RLOC table stored in the X record as the target RLOC. After determining the target RLOC, it is necessary to add the flow record to the flow information table in the X record of the SID-to-RLOC mapping table, that is, record the mapping relationship between the just determined target RLOC and X into the flow information table. It should be noted that if the X record does not exist, an Encapsulated Map-Request is sent to the Map-Resolver in the LISP mapping system to request the mapping of SID to RLOC.

[0118] Step S50: The target ETR parses the received target request service message and sends the parsed original request service message to the target computing power service instance corresponding to the destination service address.

[0119] Exemplarily, in this embodiment, the target ETR directly receives the target request service message sent by the ITR (because the destination service address of the target request service message is one of the IP addresses it allocates), checks the validity of its address, and if valid, strips the LISP header to obtain the original request service message and then forwards it to the target computing power service instance with the destination SID connected to it. At the same time, it also updates the flow information table, the flow count statistics, and the flow bandwidth statistics in the traffic statistics table according to the target request service message.

[0120] In summary, this embodiment realizes the registration and addressing of distributed computing power service instances based on LISP, avoiding the transmission of a large number of computing power service instance routes in the core network and solving the problem of the sharp increase in the core network routing table. Secondly, the ETR detects and counts the traffic accessing the computing power service instance, and transmits the traffic statistics information of the computing power service instance to the ITR, enabling the ITR to direct the user's service request to a suitable computing power service instance according to different guiding strategies (such as the minimum routing cost, the least number of accessing users, and the least occupied access bandwidth). In addition, when the ITR detects the traffic accessing the computing power service instance, the traffic of the same user accessing the same SID will be directed to the same computing power service instance, which is particularly important for protocols such as TCP. Finally, the computing power service instances in this embodiment can be deployed more flexibly. For example, they can be deployed at different sites simultaneously or at different nodes of the same site, etc. Moreover, this embodiment is fully compatible with LISP, enabling the deployment of computing power service instances in an incremental manner (such as first deploying computing power service instances on 3 of the nodes, and then choosing to deploy on 5 nodes as resources become richer), which is easy to promote.

[0121] In a second aspect, an embodiment of the present application further provides a service instance addressing device.

[0122] In one embodiment, the service instance addressing device includes: an egress tunnel router (ETR), a locator / identifier separation protocol (LISP) mapping system, and an ingress tunnel router (ITR);

[0123] Each ETR registers the corresponding target address list to the LISP mapping system, and the target address list includes the service addresses corresponding to the computing power service instances connected to the ETR. Among them, the service addresses of all computing power service instances corresponding to the same service are the same;

[0124] When the ITR fails to retrieve the routing locator (RLOC) corresponding to the destination service address in the preset mapping cache, each ETR is enabled to retrieve whether there is a first RLOC corresponding to the destination service address based on the corresponding preset mapping database through the LISP mapping system and the target address list;

[0125] If the ETR retrieves the first RLOC, it sends the first RLOC to the ITR;

[0126] The ITR filters out the target RLOC from all the received first RLOCs, encapsulates the original request service message carrying the destination service address sent by the user, generates a target request service message, and sends it to the target ETR corresponding to the target RLOC;

[0127] The target ETR parses the received target request service message and sends the parsed original request service message to the target computing power service instance corresponding to the destination service address.

[0128] Further, in one embodiment, the ITR sends a target mapping request message encapsulated with a LISP header to the LISP mapping system. The target mapping request message includes a mapping message of the requested destination service address and the RLOC. When the LISP mapping system retrieves a mapping relationship between the destination service address and the RLOC from the target address list, it sends the target mapping request message to all ETRs respectively. For each ETR, the ETR retrieves its corresponding preset mapping database based on the target mapping request message to determine whether there is a first RLOC corresponding to the destination service address.

[0129] Further, in one embodiment, the ETR obtains target parameters corresponding to the destination service address according to a preset traffic steering policy. The traffic steering policy includes one of the minimum routing cost policy, the minimum access flow number policy, and the minimum access flow bandwidth policy. The target parameters include the default value corresponding to the minimum routing cost policy, the access flow number corresponding to the minimum access flow number policy, and the access flow rate corresponding to the minimum access flow bandwidth policy. The ETR filters out the target priority value corresponding to the target parameter from the preset priority value mapping relationship to perform the step of sending the first RLOC to the ITR based on the first RLOC and the target priority value. The target priority value is used as a filtering condition for the ITR to filter the target RLOC.

[0130] Further, in one embodiment, the ETR writes the first RLOC and its corresponding target priority value into the target mapping response message. The ETR sends the target mapping response message to the ITR for the ITR to perform the step of filtering out the target RLOC from all the received first RLOCs and encapsulating the original request service message carried by the user with the destination service address based on the target mapping response message.

[0131] Further, in one embodiment, the ITR parses all the received target mapping response messages respectively to obtain a plurality of first RLOCs and their corresponding target priority values. The ITR filters out the minimum target priority value from all the target priority values and uses the first RLOC corresponding to the minimum target priority value as the target RLOC. The ITR encapsulates the original request service message carried by the user with the destination service address based on the target RLOC to obtain the target request service message.

[0132] Further, in one embodiment, the ITR constructs a target mapping relationship between the destination service address and each first RLOC and its corresponding target priority value; the ITR updates a preset mapping cache based on the target mapping relationship.

[0133] Further, in one embodiment, the ITR obtains a source node identifier EID corresponding to a user; the ITR constructs a target mapping relationship among the source EID, the destination service address, and the target RLOC, so that access flows of users with the same source EID accessing the same service are directed to a computing power service instance with the destination service address connected to the same target RLOC.

[0134] Among them, the function implementation of each module in the above service instance addressing device corresponds to each step in the above service instance addressing method embodiment, and its function and implementation process will not be elaborated here one by one.

[0135] In a third aspect, an embodiment of the present application provides a service instance addressing device, and the service instance addressing device may be a device with data processing functions such as a personal computer (PC), a laptop computer, a server, etc.

[0136] Refer to Figure 6 , Figure 6 which is a schematic hardware structure diagram of the service instance addressing device involved in the solution of the embodiment of the present application. In the embodiment of the present application, the service instance addressing device may include a processor, a memory, a communication interface, and a communication bus.

[0137] Among them, the communication bus may be of any type and is used to interconnect the processor, the memory, and the communication interface.

[0138] The communication interface includes input / output (I / O) interfaces, physical interfaces, and logical interfaces, etc., which are used to implement the interconnection of components inside the service instance addressing device, and interfaces for implementing the interconnection of the service instance addressing device with other devices (such as other computing devices or user devices). The physical interface may be an Ethernet interface, an optical fiber interface, an ATM (Asynchronous Transfer Mode) interface, etc.; the user device may be a display, a keyboard, etc.

[0139] The memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical memory, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0140] The processor can be a general-purpose processor, which can call the service instance addressing program stored in the memory and execute the service instance addressing method provided by the embodiments of the present application. For example, the general-purpose processor can be a central processing unit (CPU). Among them, the method executed when the service instance addressing program is called can refer to the various embodiments of the service instance addressing method of the present application, which will not be elaborated here.

[0141] Those skilled in the art can understand that Figure 6 the hardware structure shown in

[0142] does not constitute a limitation to the present application, and may include more or fewer components than shown in the figure, or combine some components, or arrange different components.

[0143] A computer-readable storage medium is further provided in the embodiments of the present application.

[0144] A service instance addressing program is stored on the readable storage medium of the present application. When the service instance addressing program is executed by a processor, the steps of the service instance addressing method as described above are implemented.

[0145] It should be noted that the serial numbers of the above embodiments of the present application are only for description and do not represent the advantages and disadvantages of the embodiments.

[0146] In the description of the specification, claims and the above-mentioned drawings of this application, the terms "comprising", "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally further include steps or units not listed, or may optionally further include other steps or units inherent to these processes, methods, products or devices. Descriptions such as "first", "second" and "third" are used to distinguish different objects, etc., and do not represent a sequence, nor do they limit that "first", "second" and "third" are different types.

[0147] In the description of the embodiments of this application, terms such as "exemplary", "for example" or "for instance" are used to indicate examples, illustrations or explanations. Any embodiment or design solution described as "exemplary", "for example" or "for instance" in the embodiments of this application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of words such as "exemplary", "for example" or "for instance" is intended to present relevant concepts in a specific manner.

[0148] In the description of the embodiments of this application, unless otherwise specified, " / " means "or". For example, A / B may mean A or B; "and / or" in the text is merely a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B may mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of this application, "a plurality of" means two or more than two.

[0149] In some processes described in the embodiments of this application, there are multiple operations or steps that appear in a specific order. However, it should be understood that these operations or steps may not be executed in the order in which they appear in the embodiments of this application or may be executed in parallel. The serial numbers of the operations are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed in sequence or in parallel, and these operations or steps may be combined.

[0150] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disc) as described above and includes several instructions to enable a terminal device to execute the methods described in the various embodiments of this application.

[0151] The above are only the preferred embodiments of the present application, and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present application.

Claims

1. A service instance addressing method, characterized in that: The following steps are involved: Each egress tunnel router ETR registers a target address list corresponding to it to the locator and identifier separation protocol LISP mapping system, wherein the target address list includes a service address corresponding to the computing service instance connected to the ETR, wherein the service addresses of all computing service instances corresponding to the same service are the same; When the ingress tunnel router ITR fails to retrieve the route locator RLOC corresponding to the destination service address in the preset mapping cache, each ETR is enabled to search whether there is a first RLOC corresponding to the destination service address based on the preset mapping database corresponding thereto through the LISP mapping system and the target address list; If the ETR retrieves the first RLOC, the first RLOC is sent to the ITR; The ITR selects the target RLOC from all the received first RLOCs, encapsulates the original service request message carrying the destination service address sent by the user, generates a target service request message and sends it to the target ETR corresponding to the target RLOC; The target ETR parses the received target request service message and sends the parsed original request service message to the target computing power service instance corresponding to the destination service address.

2. The service instance addressing method according to claim 1, characterized in that: The method of enabling each ETR to search for a first RLOC corresponding to the destination service address based on a preset mapping database corresponding to the ETR through the LISP mapping system and the target address list includes: The ITR sends a target mapping request message encapsulated with a LISP header to the LISP mapping system, wherein the target mapping request message includes a mapping message requesting a destination service address and a RLOC; When the LISP mapping system retrieves a mapping relationship between the destination service address and the RLOC from the target address list, the target mapping request message is sent to all ETRs respectively; For each ETR, the ETR searches the preset mapping database corresponding to it based on the target mapping request message to determine whether there is a first RLOC corresponding to the destination service address.

3. The service instance addressing method according to claim 1, characterized in that: Before the step of sending the first RLOC to the ITR, the method further includes: The ETR obtains the target parameters corresponding to the destination service address according to the preset diversion strategy, the diversion strategy includes one of the minimum routing cost strategy, the minimum number of access flows strategy and the minimum access flow bandwidth strategy, and the target parameters include the default value corresponding to the minimum routing cost strategy, the number of access flows corresponding to the minimum number of access flows strategy, and the access flow rate corresponding to the minimum access flow bandwidth strategy; The ETR selects a target priority value corresponding to the target parameter from a preset priority value mapping relationship to perform the step of sending the first RLOC to the ITR based on the first RLOC and the target priority value, and the target priority value is used as a screening condition for the ITR to screen the target RLOC.

4. The service instance addressing method according to claim 3, characterized in that: The sending the first RLOC to the ITR comprises: The ETR writes the first RLOC and its corresponding target priority value into a target mapping response message; The ETR sends the target mapping response message to the ITR, so that the ITR performs the step of selecting the target RLOC from all received first RLOCs to encapsulate the original service request message carrying the destination service address sent by the user based on the target mapping response message.

5. The service instance addressing method according to claim 4, characterized in that: The ITR selects a target RLOC from all received first RLOCs to encapsulate an original service request message sent by a user and carrying a destination service address, including: The ITR parses all received target mapping response messages respectively to obtain multiple first RLOCs and their corresponding target priority values; ITR selects the minimum target priority value from all target priority values, and uses the first RLOC corresponding to the minimum target priority value as the target RLOC; The ITR encapsulates the original service request message carrying the destination service address sent by the user based on the target RLOC to obtain a target service request message.

6. The service instance addressing method according to claim 5, characterized in that: After the ITR parses all received target mapping response messages respectively to obtain a plurality of first RLOCs and their corresponding target priority values, the method further includes: The ITR constructs a target mapping relationship between the destination service address and each first RLOC and its corresponding target priority value; The ITR updates the preset mapping cache based on the target mapping relationship.

7. The service instance addressing method according to claim 5, characterized in that: After the step of taking the first RLOC corresponding to the minimum target priority value as the target RLOC, the method further includes: ITR obtains the source node identifier EID corresponding to the user; ITR constructs a target mapping relationship among the source EID, the destination service address and the target RLOC, so that the access flow corresponding to the same service accessed by users with the same source EID is directed to the computing service instance with the destination service address connected to the same target RLOC.

8. A service instance addressing device, characterized in that: include: Egress tunnel router ETR, locator and identifier separation protocol LISP mapping system, ingress tunnel router ITR; Each ETR registers its corresponding target address list to the LISP mapping system, where the target address list includes the service address corresponding to the computing service instance connected to the ETR, where the service addresses of all computing service instances corresponding to the same service are the same; When the ITR fails to retrieve the route locator RLOC corresponding to the destination service address in the preset mapping cache, each ETR is enabled to search whether there is a first RLOC corresponding to the destination service address based on the preset mapping database corresponding thereto through the LISP mapping system and the target address list; If the ETR retrieves the first RLOC, the first RLOC is sent to the ITR; The ITR selects the target RLOC from all the received first RLOCs, encapsulates the original service request message carrying the destination service address sent by the user, generates a target service request message and sends it to the target ETR corresponding to the target RLOC; The target ETR parses the received target request service message and sends the parsed original request service message to the target computing power service instance corresponding to the destination service address.

9. A service instance addressing device, characterized in that: The service instance addressing device includes a processor, a memory, and a service instance addressing program stored in the memory and executable by the processor, wherein when the service instance addressing program is executed by the processor, the steps of the service instance addressing method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a service instance addressing program, wherein when the service instance addressing program is executed by a processor, the steps of the service instance addressing method according to any one of claims 1 to 7 are implemented.

Images