CN111865795A

CN111865795A - Control method and device

Info

Publication number: CN111865795A
Application number: CN202010520470.6A
Authority: CN
Inventors: 宋小恒
Original assignee: Hangzhou H3C Technologies Co Ltd
Current assignee: New H3C Information Technologies Co Ltd
Priority date: 2020-06-10
Filing date: 2020-06-10
Publication date: 2020-10-30
Anticipated expiration: 2040-06-10
Also published as: CN111865795B

Abstract

The application provides a control method and a device, the method is applied to a first SR node in MPLS SR networking, and the method comprises the following steps: receiving a user message which is sent by a source host and comprises address information; acquiring a congestion tag and a SID tag matched with the address information according to the address information; packaging the user message to obtain a first network message; and according to the SID label, sending a first network message to a second SR node in the forwarding path, so that when the second SR node determines that the traffic congestion occurs, the EXP field included in the congestion label is set, and sending a second network message to a third SR node in the path, so that the third SR node sends the copied second network message to the controller, and the controller adjusts the path attribute of the path when determining that the traffic congestion occurs.

Description

Control method and device

Technical Field

The present application relates to the field of communications technologies, and in particular, to a control method and apparatus.

Background

Software Defined Networking (SDN) is a novel Network innovation architecture, and the core idea is to separate the control plane and the forwarding plane of a Network device to realize flexible control of Network traffic, thereby providing a good platform for innovation of a core Network and application. Segment Routing (SR) employs a source path selection mechanism, and a Segment Identifier (SID) of an SR node through which a path passes is pre-encapsulated at a source node. And when the network message passes through the SR node, the SR node forwards the network message according to the SID included in the network message. The other SR nodes on the path need not maintain the path state except for the source SR node.

The multi-protocol Label Switching (MPLS) Segment Routing (MPLS) refers to deploying an SR mechanism in an MPLS network, and using an MPLS Label as an SID of an SR node to forward a network packet. In the forwarding process, when a source SR node receives a network message of a user, the Label information of all SR nodes on a forwarding Path is encapsulated for the network message, the network message is forwarded to a tail SR node through a Label switching route (SR LSP) based on a Segment route, after the tail SR node receives the network message, all labels in the network message are stripped, and the network message is forwarded through a destination address of the original message.

However, in the current MPLS SR networking, the congestion control policy of the SR LSP is the same as that of the MPLS LSP, and the priority scheduling is still performed based on the EXP field in the MPLS label. When the SR node is congested and loses packets, the data integrity is ensured by relying on a retransmission mechanism, or detection means such as NQA/BFD/OAM are configured in MPLS SR networking to carry out congestion prevention or path switching in advance. These approaches do not truly reflect the state of the SR node and the quality of the link.

Disclosure of Invention

In view of this, the present application provides a control method and apparatus, so as to adjust a bandwidth in time and reduce packet loss caused by congestion.

In a first aspect, the present application provides a control method, where the method is applied to a first SR node in an MPLS SR networking, and the method includes:

receiving a user message sent by a source host, wherein the user message comprises address information;

acquiring a congestion tag and a SID tag matched with the address information according to the address information;

packaging the user message to obtain a first network message, wherein the first network message comprises the congestion label and the SID label;

and according to the SID label, sending the first network message to a second SR node in a forwarding path, so that when the second SR node determines that the traffic congestion occurs, the second SR node sets an EXP field included in the congestion label, and sends a second network message to a third SR node in the path, wherein the second network message includes the congestion label with the set EXP field and the SID label, so that the third SR node sends a copied second network message to a controller, and the controller adjusts the path attribute of the path when determining that the traffic congestion occurs.

In a second aspect, the present application provides a control method, which is applied to a controller in an MPLS SR networking, and the method includes:

receiving a first network message sent by a first SR node, wherein the first network message comprises a congestion label;

when the EXP field included by the congestion label is set, judging whether the first SR node is the SR node which sends the congestion label including the set EXP field in the forwarding path or not;

and if so, determining that traffic congestion occurs between the first SR node and a second SR node in the path, and adjusting the path attribute of the path.

In a third aspect, the present application provides a control apparatus, where the apparatus is applied to a first SR node in an MPLS SR networking, and the apparatus includes:

a receiving unit, configured to receive a user packet sent by a source host, where the user packet includes address information;

the acquisition unit is used for acquiring a congestion tag and an SID tag which are matched with the address information according to the address information;

an encapsulating unit, configured to perform encapsulation processing on the user packet to obtain a first network packet, where the first network packet includes the congestion tag and the SID tag;

A sending unit, configured to send the first network packet to a second SR node in a forwarding path according to the SID tag, so that the second SR node sets an EXP field included in the congestion tag when it is determined that traffic congestion occurs in the second SR node, and sends a second network packet to a third SR node in the path, where the second network packet includes the congestion tag with the set EXP field and the SID tag, so that the third SR node sends the copied second network packet to a controller, and the controller adjusts a path attribute of the path when it is determined that traffic congestion occurs.

In a fourth aspect, the present application provides a control apparatus, where the apparatus is applied to a controller in an MPLS SR networking, and the apparatus includes:

a receiving unit, configured to receive a first network packet sent by a first SR node, where the first network packet includes a congestion tag;

a determining unit, configured to determine, when an EXP field included in the congestion tag is set, whether the first SR node is an SR node that sends the congestion tag including the EXP field set in a forwarding path;

and if so, determining that traffic congestion occurs between the first SR node and a second SR node in the path, and adjusting a path attribute of the path.

In a fifth aspect, the present application provides a network device comprising a processor and a machine-readable storage medium storing machine-executable instructions executable by the processor, the processor being caused by the machine-executable instructions to perform the method provided by the first aspect of the present application.

In a sixth aspect, the present application provides a network device comprising a processor and a machine-readable storage medium storing machine-executable instructions executable by the processor, the processor being caused by the machine-executable instructions to perform the method provided by the second aspect of the present application.

Therefore, by applying the control method and the control device provided by the application, the first SR node receives the user packet including the address information, which is sent by the source host. And according to the address information, the first SR node acquires a congestion label and a SID label matched with the address information. And the first SR node packages the user message to obtain a first network message. According to the SID label, the first SR node sends a first network message to a second SR node in the forwarding path, so that when the second SR node determines that the traffic congestion occurs, the EXP field included in the congestion label is set, and the second network message is sent to a third SR node in the path, so that the third SR node sends the copied second network message to the controller, and the controller adjusts the path attribute of the path when determining that the traffic congestion occurs.

By the mode, the SR node information with the flow congestion state in the path is fed back to the controller, the controller is used for monitoring the congestion state of the SR node link and then adjusting the path bandwidth in time, and packet loss caused by congestion is reduced.

Drawings

Fig. 1 is a flowchart of a control method according to an embodiment of the present application;

fig. 2 is a schematic diagram of a message format of a route advertisement message according to an embodiment of the present application;

fig. 3 is a schematic diagram of a message format of a network message according to an embodiment of the present application;

FIG. 4 is a flow chart of another control method provided by the embodiments of the present application;

fig. 5 is a schematic diagram of a packet forwarding networking provided in an embodiment of the present application;

fig. 6 is a structural diagram of a control device according to an embodiment of the present application;

fig. 7 is a structural diagram of another control device provided in the embodiment of the present application;

fig. 8 is a hardware structure diagram of a network device according to an embodiment of the present application.

Detailed Description

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the corresponding listed items.

It is to be understood that although the terms first, second, third, etc. may be used herein to describe various information, such information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present application. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.

The control method provided in the embodiments of the present application is explained in detail below. Referring to fig. 1, fig. 1 is a flowchart illustrating a control method according to an embodiment of the present application. The method is applied to a first SR node in an MPLS SR network. The control method provided by the embodiment of the application can comprise the following steps.

Step 110, receiving a user message sent by a source host, where the user message includes address information.

Specifically, in the present embodiment, the source host prepares to access the destination host. The first SR node is specifically a source SR node. The source host accesses the source SR node. And the destination host accesses the destination SR node. And the SR nodes except the source SR node and the destination SR node in the path for forwarding the network message are intermediate SR nodes.

The source host generates a first network packet, which includes address information. It should be noted that the address information may specifically be an IP address of the source host or an IP address of the destination host.

And step 120, acquiring a congestion tag and a SID tag matched with the address information according to the address information.

Specifically, according to the address information obtained in step 110, the first SR node obtains the congestion label matching the address information and the SID label matching the address information from the label forwarding table.

In the embodiment of the application, the host accessing each SR node may be assigned a SID tag by the controller, and the controller notifies the SR node accessed by the host. The controller sends an address list message to the SR node, wherein the address list message comprises the host address information, a congestion tag corresponding to the host address information and an SID tag corresponding to the host address information. The address list message is used for enabling the SR node to determine that the host corresponding to the host address needs to perform traffic congestion monitoring.

Further, before step 110 in this embodiment of the present application, the first SR node receives an address list message sent by the controller, where the address list message includes host address information, a congestion tag corresponding to the host address information, and a SID tag corresponding to the host address information.

And after the first SR node acquires the information, establishing a label forwarding table. The label forwarding table comprises a plurality of label forwarding table entries, wherein each label forwarding table entry comprises host address information, a congestion label corresponding to the host address information and an SID label corresponding to the host address information.

Meanwhile, the first SR node also generates a route notification message and broadcasts the route notification message in the SR domain. The route notification message includes host address information, a congestion tag corresponding to the host address information, and a SID tag corresponding to the host address information. Thus, the SR node in the SR domain which receives the route notification message also establishes a label forwarding table according to the host address information, the congestion label corresponding to the host address information and the SID label corresponding to the host address information.

It can be understood that the SID label specifically refers to a label for identifying each network device in the segment routing domain, and through the SID label, each network device matches the label in the local label forwarding table and determines the next hop network device for forwarding the network packet, thereby implementing forwarding of the network packet.

For example, in the prior art, first, a network device (e.g., an SR node) floods an index value of a locally allocated prefix SID (prefix SID) in a segmented routing domain through an Interior Gateway Protocol (IGP), and other SR devices in the segmented routing domain calculate a local SID label according to received information and establish a local label forwarding table. Then, each SR node in the segmented routing domain dynamically establishes SR LSP according to IGP/Border Gateway Protocol (BGP). The SR node collects prefix SID information in the MPLS SR network through IGP/BGP protocol, calculates the shortest path to each SR node in the MPLS SR network according to the information and the topology information of the IGP/BGP protocol network, and establishes SR LSP on the path.

It should be noted that, in this embodiment of the present application, after each SR node receives a SID tag corresponding to host address information, the SID tag of the SR node itself may be calculated according to an existing manner of calculating a local SID tag. In the process of establishing the SR LSP, each SR node acquires SID labels of other SR nodes. In this way, each SR node also stores the label of the next-hop SR node of the SR node in the label forwarding table entry.

Further, as shown in fig. 2, fig. 2 is a schematic diagram of a message format of a route advertisement message provided in the embodiment of the present application. Taking an Open Shortest Path First (OSPF) protocol as an example, in the embodiment of the present application, an OSPF Extended Prefix Range TLV packet is used to perform flooding in an SR domain. Certainly, the messages of other IGP and IBGP protocols may also be selected for flooding.

The message includes a Type (Type) field, a Length (Length) field, a Prefix Length (Prefix Length) field, an AF field, a Range Size (Range Size) field, a Flag (Flag) field, a congestion Flag (ECN) field, a Reserved (Reserved) field, an Address Prefix (Address Prefix) field, which is a variable field, and a Sub-TLV (Sub-TLVs) field, which is a variable field.

The Address Prefix (Address Prefix) field is used for storing host Address information, namely a host Address which needs to be monitored for traffic congestion; a Flag field is used for storing a routing tag, in the prior art, only an IA tag is specified, in the embodiment of the present application, an congestion tag (ECN) field is added for identifying that an advertised host address has an ECN traffic congestion control attribute, and when the ECN is set, a routing advertisement message carries a congestion tag (ECN SID) field, which is divided from a Reserved (Reserved) field; the Sub-TLV (Sub-TLVs) field is used to store the SID tag corresponding to the host address.

Step 130, performing encapsulation processing on the user packet to obtain a first network packet, where the first network packet includes the congestion tag and the SID tag.

Specifically, according to the description of step 120, after obtaining the congestion tag and the SID tag, the first SR node performs encapsulation processing on the user packet to obtain a first network packet. The first network packet includes a congestion tag and a SID tag.

As shown in fig. 3, fig. 3 is a schematic diagram of a message format of a network message provided in the embodiment of the present application. The network message comprises an outer MAC (media access control) head, an outer congestion tag head, an outer SID (security identification) tag head and a user message. And the outer layer congestion tag head stores the congestion tag which is acquired by the first SR node and corresponds to the host address. Similar values of 1, 14 may be used for the congestion tag, in the present embodiment, 17 is used (it will be understood that the congestion tag does not conflict with the reserved value specified by the protocol). And the outer SID label head stores the SID label which is acquired by the first SR node and corresponds to the host address.

Step 140, according to the SID label, sending the first network packet to a second SR node in a forwarding path, so that when the second SR node determines that traffic congestion occurs in itself, the EXP field included in the congestion label is set, and sending a second network packet to a third SR node in the path, where the second network packet includes the congestion label with the set EXP field and the SID label, so that the third SR node sends a copied second network packet to a controller, and the controller adjusts a path attribute of the path when determining that traffic congestion occurs.

Specifically, the first SR node searches for the label of the next-hop SR node from its own label forwarding table according to the SID label, for example, the first SR node determines that the next-hop SR node is the second SR node. The first SR node sends a first network message to the second SR node.

After the second SR node receives the first network message, if the second SR node determines that the traffic congestion occurs, the second SR node sets the EXP field included in the congestion label to obtain a second network message. The second network packet includes a congestion tag and a SID tag set in the EXP field. Meanwhile, after receiving the first network packet, the second SR node searches for a label of the next-hop SR node from its own label forwarding table according to the SID label, for example, the second SR node determines that the next-hop SR node is the third SR node. And the second SR node sends a second network message to the third SR node.

And after receiving the second network message, the third SR node acquires the congestion label and the SID label. The EXP field is determined to be set by the congestion tag. And the third SR node copies the second network message to obtain a copied second network message. And the third SR node sends the copied second network message to the controller.

And after receiving the copied second network message, the controller acquires the congestion label and the SID label from the copied second network message. The EXP field is determined to be set by the congestion tag. The controller judges whether a third SR node sending the second network message is the SR node which sends the congestion label including the EXP field set at the first in the path for forwarding the second network message.

If the third SR node is the first SR node in the path that sends the congestion tag including the EXP field set, the controller determines that traffic congestion occurs between the third SR node and the SR node of the last hop of the third SR node, that is, between the second SR nodes in the path. The controller may obtain a traffic adjustment policy previously configured by the user according to the SID tag, and adjust traffic on the path according to the policy, for example, increase forwarding bandwidth of the path. If the third SR node is an SR node that does not send the congestion tag including the EXP field setting for the first time in the path, that is, the controller has previously received the congestion tag including the EXP field setting sent by other SR nodes in the path, the controller determines that traffic congestion does not occur at the third node. The controller discards the second network packet.

It should be noted that, if the third SR node is a non-destination SR node in the path (that is, the third SR node is an intermediate node in the path), the third SR node further searches the label of the next-hop SR node from its own label forwarding table according to the SID label, for example, the third SR node determines that the next-hop SR node is the fourth SR node. The third SR node sends the second network packet to the fourth SR node, and the fourth SR node continues to forward the second network packet, which is not described herein again.

And if the third SR node is the destination SR node in the path, the third SR node searches the next hop as the destination host matched with the SID label from the self label forwarding table according to the SID label. At this time, the third SR node pops up all the labels included in the second network packet, acquires the user packet, and sets the congestion flag field of the IP header included in the user packet to a first value (e.g., 3). And the third SR node sends the set user message to the destination host. And after receiving the user message, the target host determines that the traffic congestion occurs in the path according to the congestion mark. The destination host starts the TCP congestion mechanism and informs the source host to reduce the number of user messages sent.

It can be understood that, if the second SR node determines that traffic congestion does not occur, the second SR node does not set the EXP field included in the congestion label, and the second SR node directly forwards the second network packet to the third SR node. In the path, only the SR node that determines that the self-sent traffic is congested sets the EXP field included in the congestion tag.

Therefore, by applying the control method provided by the embodiment of the present application, the first SR node receives the user packet including the address information, which is sent by the source host. And according to the address information, the first SR node acquires a congestion label and a SID label matched with the address information. And the first SR node packages the user message to obtain a first network message. According to the SID label, the first SR node sends a first network message to a second SR node in the forwarding path, so that when the second SR node determines that the traffic congestion occurs, the EXP field included in the congestion label is set, and the second network message is sent to a third SR node in the path, so that the third SR node sends the copied second network message to the controller, and the controller adjusts the path attribute of the path when determining that the traffic congestion occurs.

Optionally, in this embodiment of the application, when the first SR node is an intermediate SR node in the path, the foregoing method further includes the following steps:

specifically, the first SR node receives a third network packet sent by a fourth SR node (taking the fourth SR node as a previous-hop node of the first SR node in the path for explanation, and the previous-hop node is not limited in practical application), where the third network packet includes a congestion tag and an SID tag, and the congestion tag includes an EXP field. The fourth SR node may be a source SR node, an intermediate SR node, and the like. The process of the fourth SR node sending the third network packet may refer to the description of the foregoing embodiments.

When the first SR node determines that the traffic congestion occurs in itself, the first SR node sets the EXP field included in the congestion tag. And the first SR node generates a fourth network message, wherein the fourth network message comprises a congestion label and an SID label which are set in an EXP field. According to the SID label, the first SR node searches for a label of the next-hop SR node from its own label forwarding table, for example, the first SR node determines that the next-hop SR node is the fifth SR node. And the first SR node sends a fourth network message to a fifth SR node in the path. It will be appreciated that the fifth SR node is the next hop node of the first SR node in the path.

Optionally, in this embodiment of the application, when the first SR node is a tail SR node in the path, the foregoing method further includes the following steps:

specifically, the first SR node receives a third network packet sent by a fourth SR node (taking the fourth SR node as a previous-hop node of the first SR node in the path for explanation, and the previous-hop node is not limited in practical application), where the third network packet includes a congestion tag and an SID tag, and the congestion tag includes an EXP field. And the fourth SR node is an intermediate SR node. The process of the fourth SR node sending the third network packet may refer to the description of the foregoing embodiments.

When the first SR node determines that the first SR node generates traffic congestion and is a tail SR node in the path, the first SR node sets an EXP field included by the congestion label. And the first SR node generates a fourth network message, wherein the fourth network message comprises a congestion label and an SID label which are set in an EXP field. Meanwhile, the first SR node sends a fourth network message to the controller.

And after receiving the fourth network message, the controller acquires the congestion label and the SID label. The EXP field is determined to be set by the congestion tag.

The controller determines whether the first SR node that sends the fourth network packet is the SR node that sends the congestion tag including the EXP field set in the first path.

If the first SR node is the first SR node in the path that sends the congestion tag including the EXP field set, the controller determines that traffic congestion occurs between the first SR node and the SR node of the last hop of the first SR node, that is, between the fourth SR node in the path. The controller may obtain a traffic adjustment policy previously configured by the user according to the SID tag, and adjust traffic on the path according to the policy, for example, increase forwarding bandwidth of the path.

If the first SR node is an SR node that does not send the congestion tag including the EXP field setting for the first time in the path, that is, the controller has previously received the congestion tag including the EXP field setting sent by other SR nodes in the path, the controller determines that traffic congestion does not occur at the first node. The controller discards the fourth network packet.

By way of example and not limitation, the SR node determines that traffic congestion may occur on its own by determining whether traffic is forwarded from a configured non-fixed port. For example, in the path of R1-R2-R3, there are two ports between R2 and R1 (e.g., port1, port 2); there are also two ports (e.g., port3, port4) between R2 and R3. If all the R1 traffic received by R2 is forwarded from port3, it is determined that there is a possibility of traffic congestion at port 3.

Further, the third network message further includes a user message, and the user message includes an ECN congestion flag.

When the first SR node is the tail node in the path, the first SR node determines that the first SR node sends traffic congestion, and sends a congestion label set by the EXP field to the controller, and meanwhile, the first SR node searches the next hop from a label forwarding table of the first SR node according to the SID label, wherein the next hop is a target host matched with the SID label. And the first SR node pops up all the labels included in the third network message and acquires the user message. The first SR node sets the congestion flag of the IP header included in the user packet to a first value (e.g., 3), and obtains the set user packet. And the first SR node sends the set user message to the destination host. And after receiving the user message, the target host determines that the traffic congestion occurs in the path according to the congestion mark. The destination host starts the TCP congestion mechanism and informs the source host to reduce the number of network messages sent.

specifically, the first SR node receives a fifth network packet sent by a sixth SR node (taking the sixth SR node as a previous-hop node of the first SR node in the path for explanation, and the previous-hop node is not limited in practical application), where the fifth network packet includes a congestion tag and an SID tag set in an EXP field.

And the first SR node determines that a link between the sixth SR node and the first SR node may have a traffic congestion state according to the EXP field, and at this time, the first SR node copies the fifth network packet. And the first SR node sends the copied fifth network message to the controller. And after receiving the copied fifth network message, the controller acquires the congestion label and the SID label from the fifth network message. The EXP field is determined to be set by the congestion tag.

The controller determines whether the first SR node that transmits the fifth network packet is the SR node that transmits the congestion tag including the EXP field set in the first path.

If the first SR node is the first SR node in the path that sends the congestion tag including the EXP field set, the controller determines that traffic congestion occurs between the first SR node and the SR node of the last hop of the first SR node, that is, between the sixth SR node in the path. The controller may obtain a traffic adjustment policy previously configured by the user according to the SID tag, and adjust traffic on the path according to the policy, for example, increase forwarding bandwidth of the path.

If the first SR node is an SR node that does not send the congestion tag including the EXP field setting for the first time in the path, that is, the controller has previously received the congestion tag including the EXP field setting sent by other SR nodes in the path, the controller determines that traffic congestion does not occur at the first node. The controller discards the fifth network packet.

Further, when the first SR node is the intermediate SR node in the path, after the first SR node copies the fifth network packet, according to the SID label, the first SR node searches for the label of the next-hop SR node from its own label forwarding table, for example, the first SR node determines that the next-hop SR node is the seventh SR node. And the first SR node sends a fifth network message to a seventh SR node in the path, wherein the fifth network message comprises a congestion label set in an EXP field and the SID label. The seventh SR node may be a middle SR node and a tail SR node. The seventh SR node may refer to the description of the foregoing embodiment for a process of processing the fifth network packet.

specifically, the fifth network message further includes a user message, and the user message includes an ECN congestion flag.

When the first SR node is used as the tail SR node in the path, the first SR node searches the next hop from the self label forwarding table according to the SID label as the destination host matched with the SID label. And popping up all labels included in the fifth network message by the first SR node, and acquiring the user message. The first SR node sets the congestion flag of the IP header included in the user packet to a first value (e.g., 3), and obtains the set user packet. And the first SR node sends the set user message to the destination host. And after receiving the user message, the target host determines that the traffic congestion occurs in the path according to the congestion mark. The destination host starts the TCP congestion mechanism and informs the source host to reduce the number of network messages sent.

The control method provided in the embodiments of the present application is explained in detail below. Referring to fig. 4, fig. 4 is a flowchart illustrating another control method according to an embodiment of the present application. The method is applied to a controller in an MPLS SR networking. The control method provided by the embodiment of the application can comprise the following steps.

Step 410, receiving a first network packet sent by a first SR node, where the first network packet includes a congestion tag. Specifically, when a second SR node included in a path for forwarding the network packet determines that traffic congestion occurs in itself, the second SR node sets an EXP field included in a congestion tag, and obtains the first network packet. The first network packet includes a congestion tag and a SID tag set in the EXP field.

Meanwhile, after receiving the first network packet, the second SR node searches for the next-hop SR node from its own label forwarding table according to the SID label, for example, the second SR node determines that the next-hop SR node is the first SR node. And the second SR node sends the first network message to the first SR node.

And after receiving the first network message, the first SR node acquires the congestion label and the SID label. The EXP field is determined to be set by the congestion tag. And the first SR node copies the first network message to obtain a copied first network message. And the first SR node sends the copied first network message to the controller, wherein the copied first network message comprises a congestion label, and an EXP field included in the congestion label is set.

Step 420, when the EXP field included in the congestion label is set, determining whether the first SR node is the first SR node that sends the congestion label including the set EXP field in the forwarding path.

Specifically, after receiving the copied first network packet, the controller obtains a congestion tag and an SID tag from the copied first network packet. The controller checks whether the EXP field included in the congestion tag is set.

If the EXP field included in the congestion tag is set, the controller determines whether the first SR node that transmits the first network packet is the SR node that transmits the congestion tag including the EXP field set in the first path used for forwarding the first network packet.

If yes, go to step 430.

And 430, if so, determining that traffic congestion occurs between the first SR node and a second SR node in the path, and adjusting a path attribute of the path.

Specifically, if the first SR node is the SR node that sends the congestion tag including the EXP field set for the first in the path, the controller determines that traffic congestion occurs between the first SR node and the SR node of the last hop of the first SR node, that is, between the second SR nodes in the path. The controller may obtain a traffic adjustment policy previously configured by the user according to the SID tag, and adjust traffic on the path according to the policy, for example, increase forwarding bandwidth of the path.

Further, if the first SR node is an SR node that does not send the congestion tag including the EXP field setting for the first time in the path, that is, the controller has previously received the congestion tag including the EXP field setting sent by other SR nodes in the path, the controller determines that traffic congestion does not occur at the first node. The controller discards the first network packet.

It should be noted that, if the first SR node is a non-destination SR node in the path (that is, the first SR node is an intermediate node in the path), the first SR node further searches the label of the next-hop SR node from its own label forwarding table according to the SID label, for example, the first SR node determines that the next-hop SR node is a third SR node. The first SR node sends the first network packet to the third SR node, and the third SR node continues to forward the first network packet, which is not described herein again.

And if the first SR node is the target SR node in the path, the first SR node searches the next hop from the self label forwarding table as the target host matched with the SID label according to the SID label. At this time, the first SR node pops up all the labels included in the first network packet, acquires the user packet, and sets the congestion flag field of the IP header included in the user packet to a first value (e.g., 3). And the first SR node sends the set user message to the destination host.

And after receiving the user message, the target host determines that the traffic congestion occurs in the path according to the congestion mark. The destination host starts the TCP congestion mechanism and informs the source host to reduce the number of network messages sent.

Therefore, by applying the control device provided by the present application, the controller receives the first network packet including the congestion tag sent by the first SR node. When the EXP field included in the congestion label is set, the controller judges whether the first SR node is the SR node which sends the congestion label including the set EXP field in the forwarding path. If yes, the controller determines that traffic congestion occurs between the first SR node and a second SR node in the path, and adjusts the path attribute of the path.

Optionally, in this embodiment of the present application, before performing step 410, the controller further performs the following process:

specifically, the controller obtains host address information, and the host corresponding to the host address information is the host to be controlled. And according to the host address information, the controller allocates corresponding congestion tags and SID tags to the host address information. The controller generates an address list message including host address information and a congestion tag, SID tag corresponding to the host address information.

And the controller sends the address list message to a third SR node accessed by the host corresponding to the host address information. And the third SR node establishes a label forwarding table according to the host address information, the congestion label corresponding to the host address information and the SID label. The label forwarding table comprises a plurality of label forwarding table entries, and each label forwarding table entry comprises host address information and a congestion label and a SID label corresponding to the host address information. It is understood that the label forwarding table entry further includes a label of the next-hop SR node.

Therefore, after receiving the user message sent by the source host, the third SR node acquires the congestion tag and SID tag corresponding to the host from the tag forwarding table, encapsulates the acquired congestion tag and SID tag corresponding to the host in the outer header of the user message, and generates and forwards the network message to the destination host. Or after the third SR node receives the network packet of the SR node of the previous hop, the third SR node searches for the label of the SR node of the next hop according to the label forwarding table, and forwards the network packet.

Further, the controller acquiring the host address information may be obtained by: 1) the controller receives a configuration instruction input by a user, wherein the configuration instruction comprises host address information. 2) The application type of the data stream is identified through an intelligent engine version, such as a web application, an audio and video application and the like. And sending the application data stream to the controller, and extracting the host address from the data stream by the controller.

The following is a detailed description by way of an example. As shown in fig. 5, fig. 5 is a schematic diagram of packet forwarding networking provided in the embodiment of the present application. As shown in fig. 5, R1, R2, R3, R4 are routers. Host10, Host11 … Host19 are user hosts and are all accessed under R1. Host40, Host41 … Host49 are user hosts and are all accessed under R4. The controller is an SDN controller. The user statically designates Host10 as the VIP Host, i.e., the Host needs to be traffic congestion monitored.

The following description will take an example in which Host40 accesses Host 10.

The Host40 sends a first user message to the R4, where the first user message may specifically be a TCP request message. R4 receives the first user message, and obtains the destination IP address as Host 10. R4 obtains the congestion label and SID label matching with Host10 from the local label forwarding table. And the R4 encapsulates the acquired congestion label and SID label on the outer layer of the first user message to obtain a first network message. Meanwhile, R4 obtains the label (e.g., R3) of the next-hop SR node from the label forwarding table, and R4 sends the first network packet to R3.

And after receiving the first network message, the R3 acquires the congestion label and the SID label from the first network message. And determining that the traffic congestion monitoring needs to be performed on the Host10 corresponding to the SID label according to the congestion label and the SID label. According to the SID label, the label (e.g., R2) of the next-hop SR node is obtained from the local label forwarding table. R3 sends the first network message to R2.

Similarly, R2 performs the same procedure as R3 and sends the first network packet to R1.

And after receiving the first network message, the R1 acquires the congestion label and the SID label from the first network message. And determining that the traffic congestion monitoring needs to be performed on the Host10 corresponding to the SID label according to the congestion label and the SID label. And acquiring the next hop from a local label forwarding table as Host10 according to the SID label. And the R1 pops up an outer layer label included in the first network message to obtain the first user message. R1 sends the first user message to Host 10.

After receiving the first user message, the Host10 generates a second user message, which may specifically be a TCP response message. The Host10 sends a second user message to R1.

And R1 receives the second user message, and acquires the source IP from the second user message as Host 10. R1 obtains the congestion label and SID label matching with Host10 from the local label forwarding table. And the R1 encapsulates the acquired congestion label and SID label on the outer layer of the second user message to obtain a second network message. Meanwhile, R1 obtains the label (e.g., R2) of the next-hop SR node from the label forwarding table, and R1 sends the second network packet to R2.

Similarly, R2, R3, R4 perform similar operations as described above in turn, and will not be repeated here.

If in the network message interaction process between the Host10 and the Host40, in a message forwarding path from the Host10 to the Host40, traffic congestion occurs in R2. At this time, before the R2 forwards the second network packet, the R2 sets the EXP field included in the congestion tag to obtain the third network packet. Then, R2 sends a third network message to R3.

And after receiving the third network message, the R3 sends the third network message to the R4. Meanwhile, R3 obtains the congestion tag from the third network message, and determines that the EXP field included in the congestion tag is set. At this time, R3 copies the third network packet and sends the copied third network packet to the controller. And the controller receives the third network message copied by the R3, determines that traffic congestion occurs on the last hop R2 of the R3 according to the SR LSP, and a traffic congestion link exists between the R2 and the R3. And the controller acquires the flow adjustment strategy configured on line by the user according to the SID label. In accordance with the traffic adjustment policy, the controller adjusts traffic on the SR LSP, e.g., increasing the forwarding bandwidth of the path.

And after receiving the third network message, the R4 obtains the congestion tag from the third network message, and determines that the EXP field included in the congestion tag is also set. At this time, R4 copies the third network packet and sends the copied third network packet to the controller. Meanwhile, according to the SID label, R4 obtains the next hop from the local label forwarding table as Host 40. And the R4 pops up the outer layer label included in the third network message to obtain the second user message. Since the EXP field included in the congestion tag is set, R4 sets 3 the ECN of the IP header included in the second user packet, and sends the second user packet to Host 40.

After receiving the third network message sent by the R4, the controller determines that the previous hop R3 of the R4 has no traffic congestion according to the SR LSP path, and discards the third network message sent by the R4.

And after receiving the second user message, the Host40 acquires the ECN of the IP header from the second user message, and determines that the path between the Host10 and the ECN is congested. Host40 initiates the TCP congestion mechanism and informs Host10 to reduce the number of user messages sent.

Through the method, the controller can monitor and control the traffic congestion of any VIP host in the SR-based intelligent network, and timely adjust the path bandwidth of the service on the VIP host.

Based on the same inventive concept, the embodiment of the application also provides a control device corresponding to the control method. Referring to fig. 6, fig. 6 is a structural diagram of a control apparatus according to an embodiment of the present application, where the apparatus is applied to a first SR node in an MPLS SR networking, and the apparatus includes:

a receiving unit 610, configured to receive a user packet sent by a source host, where the user packet includes address information;

an obtaining unit 620, configured to obtain, according to the address information, a congestion tag and an SID tag that are matched with the address information;

an encapsulating unit 630, configured to perform encapsulation processing on the user packet to obtain a first network packet, where the first network packet includes the congestion tag and the SID tag;

A sending unit 640, configured to send the first network packet to a second SR node in a forwarding path according to the SID tag, so that when the second SR node determines that traffic congestion occurs in itself, the second SR node sets an EXP field included in the congestion tag, and sends a second network packet to a third SR node in the path, where the second network packet includes the congestion tag with the set EXP field and the SID tag, so that the third SR node sends the copied second network packet to a controller, and the controller adjusts a path attribute of the path when traffic congestion is determined.

Optionally, the receiving unit 610 is further configured to receive an address list message sent by the controller, where the address list message includes host address information, a congestion tag corresponding to the host address information, and a SID tag corresponding to the host address information;

the device further comprises: an establishing unit (not shown in the figure), configured to establish a label forwarding table, where the label forwarding table includes a plurality of label forwarding entries, and each label forwarding entry includes the host address information, a congestion label corresponding to the host address information, and an SID label;

The sending unit 640 is further configured to broadcast a route notification packet in an SR domain, where the route notification packet includes the host address information and a congestion tag and an SID tag corresponding to the host address information, so that an SR node receiving the route notification packet establishes a tag forwarding table according to the host address information and the congestion tag and the SID tag corresponding to the host address information.

Optionally, the receiving unit 610 is further configured to receive a third network packet sent by a fourth SR node, where the third network packet includes the congestion tag and the SID tag, and the congestion tag includes an EXP field;

the device further comprises: a setting unit (not shown in the figure), configured to set the EXP field when it is determined that traffic congestion occurs in the network, to obtain a fourth network packet, where the fourth network packet includes a congestion tag with the set EXP field and the SID tag;

the sending unit 640 is further configured to send the fourth network packet to a fifth SR node in the path according to the SID label when the first SR node is the middle SR node in the path.

Optionally, when the first SR node is a tail SR node, the sending unit 640 is further configured to send the fourth network packet to a controller, so that when the controller determines that the first SR node is an SR node that sends a congestion tag including the EXP field set to the first in the path, the controller determines that traffic congestion occurs between an SR node of a previous hop of the first SR node and the first SR node; the controller adjusts the path attribute of the path;

Alternatively, the first and second electrodes may be,

and when the controller determines that the first SR node is the SR node which does not send the congestion label in the path first, the controller determines that the first SR node has no traffic congestion and discards the fourth network packet.

Optionally, the receiving unit 610 is further configured to receive a fifth network packet sent by a sixth SR node, where the fifth network packet includes a congestion tag in which the EXP field is set;

the device further comprises: a copying unit (not shown in the figure) configured to copy the fifth network packet according to the EXP field;

the sending unit 640 is further configured to send the copied fifth network packet to a controller, so that when the controller determines that the first SR node is the SR node that sends the congestion tag including the EXP field set in the first path, the controller determines that traffic congestion occurs between the SR node of the previous hop of the first SR node and the first SR node; the controller adjusts the path attribute of the path; or, when the controller determines that the first SR node is the SR node that transmits the congestion label but not the first SR node in the path, the controller determines that traffic congestion does not occur in the first SR node, and discards the fifth network packet.

Optionally, the fifth network packet further includes the SID label;

when the first SR node is an intermediate SR node, the sending unit 640 is further configured to send the fifth network packet to a seventh SR node in the path according to the SID label, where the fifth network packet includes a congestion label set in an EXP field and the SID label.

Optionally, the network packet further includes the user packet, and the user packet includes a congestion flag;

when the first SR node is a tail SR node, the apparatus further includes: a pop-up unit (not shown in the figure), configured to pop up all tags included in the network packet, and set the congestion flag to a first value, so as to obtain a set user packet;

the sending unit 640 is further configured to send the set user packet to a destination host corresponding to the SID label according to the SID label, so that the destination host starts a TCP congestion mechanism, and notifies the source host to reduce the number of the sent user packets.

Therefore, by applying the control device provided by the present application, the first SR node receives the user packet including the address information sent by the source host. And according to the address information, the first SR node acquires a congestion label and a SID label matched with the address information. And the first SR node packages the user message to obtain a first network message. According to the SID label, the first SR node sends a first network message to a second SR node in the forwarding path, so that when the second SR node determines that the traffic congestion occurs, the EXP field included in the congestion label is set, and the second network message is sent to a third SR node in the path, so that the third SR node sends the copied second network message to the controller, and the controller adjusts the path attribute of the path when determining that the traffic congestion occurs.

Based on the same inventive concept, the embodiment of the application also provides a control device corresponding to the control method. Referring to fig. 7, fig. 7 is a structural diagram of another control apparatus provided in the embodiment of the present application, where the apparatus is applied to a controller in an MPLS SR networking, and the apparatus includes:

a receiving unit 710, configured to receive a first network packet sent by a first SR node, where the first network packet includes a congestion tag;

a determining unit 720, configured to determine, when the EXP field included in the congestion tag is set, whether the first SR node is an SR node that sends the congestion tag including the EXP field set in a forwarding path;

a determining and adjusting unit 730, configured to determine that traffic congestion occurs between the first SR node and a second SR node in the path if the first SR node is determined to be a target SR node, and adjust a path attribute of the path.

Optionally, the determining and adjusting unit 730 is further configured to, if not, determine that no traffic congestion occurs in the first SR node;

The device further comprises: a discarding unit (not shown in the figure) configured to discard the first network packet.

Optionally, the apparatus further comprises: an obtaining unit (not shown in the figure) configured to obtain host address information, where a host corresponding to the host address information is a host to be controlled by flow;

an allocating unit (not shown in the figure) configured to allocate a corresponding congestion tag and SID tag to the host address information according to the host address information;

a sending unit (not shown in the figure), configured to send an address list message to a third SR node to which the host is accessed, where the address list message includes host address information and a congestion tag and a SID tag corresponding to the host address information, so that the third SR node establishes a tag forwarding table, where the tag forwarding table includes a plurality of tag forwarding entries, and each tag forwarding entry includes the host address information and a congestion tag and a SID tag corresponding to the host address information.

Based on the same inventive concept, the embodiment of the present application further provides a network device, as shown in fig. 8, including a processor 810, a transceiver 820 and a machine-readable storage medium 830, where the machine-readable storage medium 830 stores machine-executable instructions capable of being executed by the processor 810, and the processor 810 is caused by the machine-executable instructions to execute the control method provided by the embodiment of the present application. The control devices shown in fig. 6 and 7 can be implemented by using a hardware structure of a network device as shown in fig. 8.

The computer-readable storage medium 830 may include a Random Access Memory (RAM) and a Non-volatile Memory (NVM), such as at least one disk Memory. Alternatively, the computer-readable storage medium 830 may be at least one memory device located remotely from the processor 810.

The Processor 810 may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; the Integrated Circuit can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components.

In the embodiment of the present application, the processor 810 is caused by machine executable instructions by reading the machine executable instructions stored in the machine readable storage medium 830 to enable the processor 810 itself and the call transceiver 820 to execute the control method described in the embodiment of the present application.

Additionally, embodiments of the present application provide a machine-readable storage medium 830, the machine-readable storage medium 830 storing machine-executable instructions that, when invoked and executed by the processor 810, cause the processor 810 itself and the invoking transceiver 820 to perform the control methods described in embodiments of the present application.

The implementation process of the functions and actions of each unit in the above device is specifically described in the implementation process of the corresponding step in the above method, and is not described herein again.

For the device embodiments, since they substantially correspond to the method embodiments, reference may be made to the partial description of the method embodiments for relevant points. The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of the application. One of ordinary skill in the art can understand and implement it without inventive effort.

As for the control device and the machine-readable storage medium embodiment, since the contents of the related methods are substantially similar to those of the foregoing method embodiments, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiments.

The above description is only exemplary of the present application and should not be taken as limiting the present application, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the scope of protection of the present application.

Claims

1. A control method applied to a first SR node in an MPLS SR networking, the method comprising:

2. The method according to claim 1, wherein before receiving the user message sent by the source host, the method further comprises:

receiving an address list message sent by a controller, wherein the address list message comprises host address information, a congestion tag corresponding to the host address information and an SID tag corresponding to the host address information;

establishing a label forwarding table, wherein the label forwarding table comprises a plurality of label forwarding table entries, and each label forwarding table entry comprises the host address information, a congestion label corresponding to the host address information and an SID label;

and broadcasting a route notification message in an SR domain, wherein the route notification message comprises the host address information and a congestion label and an SID label corresponding to the host address information, so that an SR node receiving the route notification message establishes a label forwarding table according to the host address information and the congestion label and the SID label corresponding to the host address information.

3. The method of claim 1, further comprising:

receiving a third network message sent by a fourth SR node, wherein the third network message comprises the congestion label and the SID label, and the congestion label comprises an EXP field;

When the traffic congestion of the network node is determined, setting the EXP field to obtain a fourth network message, wherein the fourth network message comprises a congestion label with the set EXP field and the SID label;

and when the first SR node is the middle SR node in the path, sending the fourth network message to a fifth SR node in the path according to the SID label.

4. The method of claim 3, wherein after obtaining the fourth network packet when the first SR node is a tail SR node, the method further comprises:

sending the fourth network packet to a controller, so that when the controller determines that the first SR node is the SR node that sends the congestion tag including the EXP field set to the first SR node in the path, the controller determines that traffic congestion occurs between the SR node of the last hop of the first SR node and the first SR node; the controller adjusts the path attribute of the path;

alternatively, the first and second electrodes may be,

5. The method of claim 1, further comprising:

receiving a fifth network message sent by a sixth SR node, wherein the fifth network message comprises a congestion tag set by the EXP field;

copying the fifth network message according to the EXP field;

sending the copied fifth network message to a controller, so that when the controller determines that the first SR node is the SR node in the first path that sends the congestion tag including the EXP field set, the controller determines that traffic congestion occurs between the SR node of the last hop of the first SR node and the first SR node; the controller adjusts the path attribute of the path; or, when the controller determines that the first SR node is the SR node that transmits the congestion label but not the first SR node in the path, the controller determines that traffic congestion does not occur in the first SR node, and discards the fifth network packet.

6. The method of claim 5, wherein the fifth network packet further comprises the SID tag;

when the first SR node is an intermediate SR node, after the fifth network packet is copied, the method further includes:

And sending the fifth network message to a seventh SR node in the path according to the SID label, wherein the fifth network message comprises a congestion label with an EXP field set and the SID label.

7. The method according to claim 4 or 6, wherein the network message further comprises the user message, and the user message comprises a congestion flag;

when the first SR node is a tail SR node, the method further includes:

popping up all labels included in the network message, and setting the congestion mark as a first value to obtain a set user message;

and sending the set user message to a target host corresponding to the SID label according to the SID label, so that the target host starts a TCP congestion mechanism and informs the source host of reducing the number of the sent user messages.

8. A control method, applied to a controller in MPLS SR networking, the method comprising:

9. The method of claim 8, further comprising:

if not, determining that the first SR node has no traffic congestion;

and discarding the first network message.

10. The method according to claim 8, wherein before receiving the first network packet sent by the first SR node, the method further comprises:

acquiring host address information, wherein a host corresponding to the host address information is a host to be controlled;

distributing corresponding congestion labels and SID labels to the host address information according to the host address information;

and sending an address list message to a third SR node accessed by the host, wherein the address list message comprises host address information and congestion labels and SID labels corresponding to the host address information, so that the third SR node establishes a label forwarding table, the label forwarding table comprises a plurality of label forwarding table entries, and each label forwarding table entry comprises the host address information and the congestion labels and SID labels corresponding to the host address information.

11. A control apparatus, applied to a first SR node in an MPLS SR networking, the apparatus comprising:

12. A control apparatus, wherein the apparatus is applied to a controller in MPLS SR networking, the apparatus comprising: