WO2016150020A1

WO2016150020A1 - Scheduling flow identifier-based packet scheduling method and device

Info

Publication number: WO2016150020A1
Application number: PCT/CN2015/082100
Authority: WO
Inventors: 徐春松; 钟炜; 张树冲; 蔡广平
Original assignee: 中兴通讯股份有限公司
Priority date: 2015-03-20
Filing date: 2015-06-23
Publication date: 2016-09-29
Also published as: CN106034089A

Abstract

A scheduling flow identifier-based packet scheduling method and device, the method comprising: during forwarding processing of a received packet, a forwarding device obtains a corresponding scheduling flow identifier of a next forwarding device of a packet in a forwarding path; the forwarding device adds the scheduling flow identifier to the packet; the forwarding device sends the packet comprising the scheduling flow identifier to the next forwarding device. The present technical solution reduces the time wherein the next forwarding device analyses packet feature information once again so as to obtain the corresponding scheduling flow identifier of the packet, thereby increasing information processing efficiency, and reducing hardware consumption.

Description

Message scheduling method and device based on scheduling flow identifier

Technical field

This document relates to the field of communications, and in particular, to a message scheduling method and apparatus based on a scheduling flow identifier.

Background technique

QoS (Quality of Service) is a technology used to solve problems such as network delay and congestion, which provides better service capabilities for designated network communications. QoS features include traffic classification, access control, traffic policing, traffic shaping, congestion management, and congestion avoidance. The traffic classification uses certain rules to identify packets that meet certain characteristics. It is the premise and basis for differentiated services. The traffic classification rule can use the priority bits of the ToS (Type of Service) field in the IP packet header to identify traffic with different priority characteristics. The network administrator can also set the traffic classification policy, for example, through the integration. The source address, the destination address, the MAC (Media Access Control) address, the IP protocol, or the port number of the application are classified. The purpose of traffic classification is to provide services in a differentiated manner. The traffic classification is associated with the flow control or resource allocation actions to complete the Qos function.

Regarding flow classification, the current QoS technology usually processes incoming messages, and then extracts message information that needs to be processed by TCAM (Ternary Content Addressable Memory) device or software algorithm. After the classification, traffic policing, traffic shaping, congestion management, and congestion avoidance are further processed, and such processing is required for each incoming message. This way is very wasteful of system resources and performance. For example, a device that is classified on a medium or high-end router or a packet forwarding device is usually a TCAM. The classification of QoS requires a large key value, and the TCAM performance and space are limited. Each message comes in one or more TCAMs. Lookups can cause a drop in forwarding performance. On some low- and medium-end devices, software algorithms are usually used to classify messages. However, there are many key values, and search also requires a certain amount of performance, which affects the performance of the entire system.

Therefore, how to simplify the processing complexity of stream classification is an urgent problem to be solved.

Summary of the invention

The embodiment of the invention provides a packet scheduling method and device based on a scheduling flow identifier, and the technical problem to be solved is how to simplify the processing complexity of the traffic classification.

In order to solve the above technical problem, the embodiment of the present invention provides the following technical solutions:

A packet scheduling method based on a scheduling flow identifier includes:

The forwarding device obtains the scheduling flow identifier corresponding to the next forwarding device of the packet in the forwarding path, in the process of forwarding the received packet.

The forwarding device adds the scheduling flow identifier to the packet;

The forwarding device sends a packet including the scheduling flow identifier to the next forwarding device.

In an implementation manner of the foregoing method, the forwarding device acquires a scheduling flow identifier corresponding to the next forwarding device of the packet on the forwarding path, including:

The forwarding device acquires packet feature information of the packet;

And the forwarding device searches for the scheduling flow identifier of the next forwarding device corresponding to the packet feature information of the packet according to the correspondence between the local pre-stored packet feature information and the scheduling flow identifier of the next forwarding device;

If found, the forwarding device uses the found result as the scheduling flow identifier corresponding to the packet;

If not found, the forwarding device sends a query request to the next forwarding device, where the query request includes packet feature information of the packet; and receives a query response fed back by the next forwarding device, The query response includes scheduling flow identification information of the packet.

In an implementation manner of the foregoing method, the forwarding device adds the scheduling flow identifier to the packet, including:

The forwarding device adds a field after the Layer 2 protocol header of the packet, and adds the scheduling flow identifier to the added field.

A packet scheduling method based on a scheduling flow identifier includes:

After receiving the packet including the scheduling flow identifier, the forwarding device acquires the scheduling flow in the packet. Identification

The forwarding device performs a scheduling operation on the packet according to the scheduling flow identifier.

In an embodiment of the above method, the method further includes:

The forwarding device acquires a scheduling flow identifier corresponding to the next forwarding device of the packet on the forwarding path;

The forwarding device replaces the forwarding identifier in the packet with the scheduling stream identifier corresponding to the next forwarding device;

The forwarding device sends the packet that has been replaced by the scheduled flow identifier.

A message scheduling device based on a scheduling flow identifier, comprising:

The first obtaining module is configured to: in the process of scheduling the received packet, obtain the scheduling flow identifier corresponding to the next forwarding device of the packet in the forwarding path;

Adding a module, configured to add the scheduling flow identifier to the packet;

The first sending module is configured to send a packet including the scheduling flow identifier to the next forwarding device.

In an implementation manner of the foregoing apparatus, the first acquiring module includes:

An obtaining unit, configured to obtain message feature information of the packet;

The search unit is configured to search for a scheduling flow identifier of the next forwarding device corresponding to the packet feature information of the packet according to the correspondence between the local pre-stored packet feature information and the scheduling flow identifier of the next forwarding device;

a first determining unit, configured to: if found, the forwarding device uses the found result as a scheduling flow identifier corresponding to the packet;

a sending unit, configured to send a query request to the next forwarding device if not found, where the query request includes message feature information of the packet;

The receiving unit is configured to receive a query response fed back by the next forwarding device, where the query response includes scheduling flow identification information of the packet.

In an implementation manner of the foregoing apparatus, the adding module is configured to: add a field after the Layer 2 protocol header of the packet, and add the scheduling flow identifier to the added field.

A message scheduling device based on a scheduling flow identifier, comprising:

The second obtaining module is configured to: after receiving the packet that includes the scheduling flow identifier, obtain the scheduling flow identifier in the packet;

The scheduling module is configured to perform a scheduling operation on the packet according to the scheduling flow identifier.

In an embodiment of the above apparatus, the apparatus further includes:

a third acquiring module, configured to obtain a scheduling flow identifier corresponding to a next forwarding device of the packet on the forwarding path;

The replacement module is configured to replace the forwarding identifier in the packet with the scheduling flow identifier corresponding to the next forwarding device;

The second sending module is configured to send the packet after the completion of the scheduling flow identifier is replaced.

A computer storage medium having stored therein computer executable instructions for performing the methods described above.

In the embodiment of the present invention, the forwarding device adds the scheduling flow identifier of the packet on the next forwarding device in the forwarding path to the next forwarding device, and reduces the feature information of the next forwarding device to parse the packet again. Obtaining the time of the scheduling flow identifier corresponding to the packet improves the information processing efficiency and reduces the hardware consumption.

BRIEF abstract

FIG. 1 is a flowchart of a packet scheduling method based on a scheduling flow identifier according to an embodiment of the present disclosure;

FIG. 2 is a flowchart of another method for scheduling a packet based on a scheduling flow identifier according to an embodiment of the present disclosure;

FIG. 3 is a schematic structural diagram of a header of a packet in a scheduling flow identifier request distribution protocol according to an embodiment of the present disclosure;

4 is a structural diagram of a message body of a message in a scheduling flow identifier request distribution protocol according to an embodiment of the present invention;

FIG. 5 is a schematic diagram of comparison of packet formats according to an embodiment of the present invention;

FIG. 6 is a schematic structural diagram of a scheduling flow identifier field according to an embodiment of the present disclosure;

FIG. 7 is a schematic diagram of an Ethernet network according to an embodiment of the present invention;

FIG. 8 is a schematic diagram of a packet format change in a packet process based on a scheduling flow identifier in an Ethernet network according to an embodiment of the present disclosure;

FIG. 9 is a schematic diagram of a format of a packet encapsulated by a forwarding device R1 according to an embodiment of the present disclosure;

FIG. 10 is a structural diagram of a packet scheduling apparatus based on a scheduling flow identifier according to an embodiment of the present disclosure;

FIG. 11 is a structural diagram of another packet scheduling apparatus based on a scheduling flow identifier according to an embodiment of the present invention.

Preferred embodiment of the invention

The invention will be further described in detail below with reference to the drawings and specific embodiments. It should be noted that, in the case of no conflict, the features in the embodiments and the embodiments in the present application may be arbitrarily combined with each other.

FIG. 1 is a flowchart of a packet scheduling method based on a scheduling flow identifier according to an embodiment of the present invention. The method shown in Figure 1 includes:

Step 101: The forwarding device acquires a scheduling flow identifier corresponding to the next forwarding device of the packet in the forwarding path, in the process of scheduling the received packet.

Step 102: The forwarding device adds the scheduling flow identifier to the packet.

Step 103: The forwarding device sends a packet including the scheduling flow identifier to the next forwarding device.

According to the method provided by the embodiment of the present invention, in the process of processing the packet, the forwarding device obtains the scheduling flow identifier of the next forwarding device on the forwarding path by using the result of the local processing, and the scheduling is performed. The flow identifier is carried to the next forwarding device, which reduces the time for the next forwarding device to parse the packet feature information again to obtain the scheduling flow identifier corresponding to the packet, thereby improving information processing efficiency and reducing hardware consumption.

FIG. 2 is a flowchart of another method for scheduling a message based on a scheduling flow identifier according to an embodiment of the present invention. The method shown in Figure 2 includes:

Step 201: After receiving the packet including the scheduling flow identifier, the forwarding device acquires the scheduling flow identifier in the packet.

Step 202: The forwarding device performs a scheduling operation on the packet according to the scheduling flow identifier.

According to the method provided by the embodiment of the present invention, the forwarding device uses the scheduling flow identifier in the packet to schedule the packet, and does not need to parse the feature information of the packet again to obtain the scheduling flow identifier, so that the packet scheduling can be completed, thereby saving local The scheduling time improves the efficiency of information processing and reduces hardware consumption.

The method provided by the embodiment of the present invention is further described below:

First, the packet scheduling on the forwarding device side is described:

The forwarding device obtains the scheduling flow identifier corresponding to the next forwarding device of the packet on the forwarding path, including:

The forwarding device acquires packet feature information of the packet;

And the forwarding device searches for the scheduling flow identifier corresponding to the packet feature information of the packet according to the correspondence between the locally stored packet feature information and the scheduling flow identifier;

It should be noted that the packet feature information may be information such as an integrated source address, a destination address, a MAC address, a label exp, an IP protocol, or an application port number.

The correspondence between the packet feature information and the scheduling flow identifier is obtained by:

The forwarding device requests the next forwarding device to obtain the corresponding scheduling flow identifier of the packet feature information on the next forwarding device;

After receiving the request, the next forwarding device feeds back the information of the local traffic classification, and feeds back the scheduling flow identifier corresponding to the feature information to the forwarding device.

After the forwarding device obtains the packet flow information corresponding to the scheduling flow identifier corresponding to the next forwarding device, the corresponding relationship between the two is saved for subsequent use.

The scheduling flow identifier request distribution protocol is based on the TCP protocol (the port number is a temporary port number of 1024-5000), and the scheduling flow identifier request distribution protocol is divided into a scheduling flow identifier request packet and a scheduling flow identifier response packet, and the packet header is sent by the header. The department and the message body are composed of two parts.

FIG. 3 is a schematic structural diagram of a header of a message in a scheduling flow identifier request distribution protocol according to an embodiment of the present invention. The protocol header shown in Figure 3 has a total of 8 bytes, each of which is described as follows:

Version: 1 byte, used to identify the version of the dispatch stream identifier request distribution protocol.

1:1 bytes are reserved for subsequent expansion.

Protocol payload length: 2 bytes, the total length of the protocol payload, excluding the protocol header length.

Message Type: Identifies the packet type. The request is 0 and the response is 1.

Request number: 3 bytes are used to identify the request. (The attachment protocol format has been modified)

FIG. 4 is a structural diagram of a message body of a message in a scheduling flow identifier request distribution protocol according to an embodiment of the present invention. The message body shown in Figure 4 consists of a type, length, and value (Type, Length, Value, TLV) format. The description of each of these fields is as follows:

Type: Type field, indicating the content of the following fields, such as source IP, destination IP, source port number, destination port, and so on.

Length: A length field that identifies the length of a group of TLVs.

Value: Value, Type corresponds to the value of the attribute. The specific length is determined according to the attribute. For example, Type is an IP address, then Value is 4 bytes. If Type is the destination mac, then it is 6 bytes, and the attribute is less than one byte. One byte indicates that the value of exp is 1 byte.

The value of Type in the request message and the corresponding attribute:

0: Purpose mac

1: source mac

3:802.1p value

4: Source IP

5: Destination IP

6: Protocol number in the IP header

7: source port

8: destination port

9: label

10:exp

Other: Reserved for extended use.

The value of the response message Type and the corresponding attribute:

0: The value of the scheduled flow identifier to be returned. Currently, the specific value of the scheduled flow identifier is 2 bytes.

The forwarding device adds the scheduling flow identifier to the packet, including:

The Ethernet packet is used as an example. The added field is located between the packet header field and the IP header field of the Ethernet packet. The IP packet is used as an example. The added field is located between the IP header field and the data segment field.

FIG. 5 is a schematic diagram of comparison of packet formats according to an embodiment of the present invention. As shown in Figure 5, the first packet format is the original packet format, and the second packet format is the processed packet format. In the format of the processed packet, the "Scheduled Flow Identifier" field is inserted between the Layer 2 Ethernet Header and the Layer 3 IP, so that the next forwarding device can directly search for the corresponding schedule according to the value of the "Scheduled Flow Identifier" field. Information, perform scheduling actions.

In order to identify such a packet, a corresponding protocol field is added in the Ethernet header to identify a packet with a scheduling flow identifier, and a flow identifier value may be added in the scheduling flow identifier field to increase the upper protocol type. Value, which is convenient for the device to parse the message.

FIG. 6 is a schematic structural diagram of a scheduling flow identifier field according to an embodiment of the present invention. The schematic diagram shown in FIG. 6 includes a scheduling flow identifier and upper layer protocol number information. The upper layer protocol number information is used to indicate data protocol information corresponding to the data of the subsequent field.

The following describes the packet scheduling of the next forwarding device:

The forwarding device of the next forwarding device acquires the scheduling flow identifier corresponding to the next forwarding device of the packet on the forwarding path;

FIG. 7 is a schematic diagram of an Ethernet network according to an embodiment of the present invention. In the network shown in Figure 7, R1, R2, and R3 are three forwarding devices on the forwarding path. The packets are forwarded from R1 to R2, and R2 forwards them to R3. R3 forwards them again. When QoS processing is performed on R1, R2, and R3, it is classified according to information such as source address, destination address, MAC address, label exp, IP protocol, or application port number, and then scheduled.

In the embodiment of the present invention, the packets are forwarded through R1, R2, and R3, and the three forwarding devices perform protocol interaction and negotiation in advance, so that the output packet format on the forwarding device changes. .

FIG. 8 is a schematic diagram of a packet format change in a packet process based on a scheduling flow identifier in an Ethernet network according to an embodiment of the present invention. The packet forwarding path is R1->R2->R3, then R1 is the upstream device of R2, and R2 is the downstream device of R1. Others are similar. The following figure illustrates the process of scheduling flow identification request and distribution, and requests are distributed from upstream to downstream.

As shown in Figure 8, when the original message is sent to R2 through the R1 forwarding process, the message format becomes the "processed message" in the figure (that is, the output message of R1), and after R2 processing, Replace the "scheduling flow identifier" in the input message with the corresponding local "scheduling flow identifier" (R3 assigned to R2), and then send it to R3, and R3 performs a similar action on R2. R2, R3, and subsequent forwarding devices do not need to be classified according to information such as source address, destination address, MAC address, label exp, IP protocol, or application port number, but can be directly based on the pre-allocated scheduling stream identifier. Perform the correct scheduling action.

The processing method in the related art is that the forwarding device needs to be identified according to the characteristics of the message, and this operation step is very cost-effective. In addition, it is considered that the same type of packets on the network are always persistent for a certain period of time. In the related art, even if the packets of the same type are received, the forwarding device repeatedly recognizes the packets according to the characteristics of the packets. The action of classification. Different from the related art, the embodiment of the present invention identifies the flow in advance through the interaction on the control plane protocol, and the upstream forwarding device The scheduling flow identifier is sent to the downstream forwarding device. Therefore, after obtaining the scheduling flow identifier, the downstream forwarding device does not need to perform the classification action by using the scheduling flow identification information, and does not need to identify each packet one by one when it is the same type of packet for a period of time. Because the scheduled flow identifier requested by the upstream device is a preparatory action for triggering the downstream device to perform the corresponding scheduling mode of the device, the prepared action avoids the persistent classification action that is originally necessary.

That is, if the forwarding device detects that the scheduling identifier carried in the received packet changes, the packet is scheduled according to the newly obtained scheduling flow identifier in a preset time.

For example, if the scheduled flow identifier of the previously obtained packet is A, and the currently received scheduling flow identifier becomes B, according to the law of data transmission in the network, the received packet is received in the next one end time. The packet feature information is the same. Therefore, the scheduling flow identifier of the subsequent packets is also B. Therefore, the forwarding device does not need to identify the packet characteristics one by one, which reduces the processing pressure of the forwarding device and reduces hardware consumption.

The communication between the forwarding device R1 and the forwarding device R2 is taken as an example for description:

Steps A01 and R1 enable the functions of the embodiment of the present invention, and configure the entry quintuple information such as: the destination IP address is 200.1.1.10, the source IP address is 210.1.1.10, the protocol number is UDP, the source port number is 1000, and the destination port number is It is 1000.

Steps A02 and R1 process the message to obtain the characteristics of the output message. For example, if the quintuple information remains unchanged and a layer of tag information is added, then R1 puts the quintuple information and the tag value (for example, 1200) and exp (for example, 1) into the request message of the scheduling flow identification request distribution protocol. , sent to the next hop device R2.

Steps A03 and R2 receive the received packet feature information, obtain an index of the corresponding local scheduling classification entry according to the actual forwarding process, and send the index as a scheduling flow identifier in the response packet of the scheduling flow identifier request distribution protocol. R1 is L2 in the above figure, and the specific value is, for example, 0x1200.

Step A04, R1 receives the scheduling flow identifier (L2=0x1200), and stores it in the local classification result entry (the destination IP of the corresponding quintuple information is 200.1.1.10, the source IP is 210.1.1.10, and the protocol number is UDP. The source port number is 1000 and the destination port number is 1000). This classification is the same as the normal classification implementation (eg using TCAM).

Step A05: When R1 receives the feature traffic from the interface (the destination IP address of the quintuple information is 200.1.1.10, the source IP address is 210.1.1.10, the protocol number is UDP, the source port number is 1000, and the destination port number is 1000. When the classification is performed, the scheduling flow identifier in the classification table is obtained, and then encapsulated into the packet. .

FIG. 9 is a schematic diagram of a format of a packet encapsulated by a forwarding device R1 according to an embodiment of the present invention. In the diagram shown in FIG. 9, 0x1200 is the scheduling flow identifier of the downstream branch, and 0x0800 is the protocol number of the upper layer protocol.

Steps A06 and R1 send the message.

The embodiment of the invention implements a method for distributing a scheduling flow identifier in a network, and performing QoS scheduling based on the distributed scheduling flow identifier. The main implementation steps are as follows:

Embodiment 1:

Step 1: Enable the function of distributing the scheduling flow identifier and performing the QoS scheduling based on the distributed scheduling flow identifier on each forwarding device.

Step 2: Configure the stream characteristics to be processed, such as the source address, the destination address, the MAC address, the label exp, the IP protocol, or the port number of the application, on the entire forwarding path upstream device R1. It can be either an entry or an outgoing message feature.

Step 3: If it is an inbound packet feature, the upstream device R1 processes the packet characteristics of the egress, and then carries the packet feature field to send a request to the downstream device R2 to request distribution of the scheduling flow identifier. If the egress message feature is configured, the downstream device is directly requested to distribute the scheduling flow identifier.

Step 4: R1 downstream device R2 receives the request of the upstream device, generates a scheduling flow identifier L2 as a response and sends it to the upstream device R1, and obtains the egress packet feature of the device according to the ingress packet processing, and then sends the egress packet feature of the device to the downstream device R3. The request to dispatch the flow identifier is distributed, and R3 responds to the request, so that R2 also obtains the dispatch flow identifier L3 allocated by R3, and R2 associates the dispatch flow identifier L3 with the dispatch flow identifier L2 that is sent to R1 by itself. That is, L3 can be found according to L2. And each device associates the scheduling flow identifier assigned to the upstream device with its own scheduling action, that is, the scheduling action can be found according to the scheduling flow identifier.

Step 5: The devices on the forwarding path perform similar functions until the last forwarding device, and the scheduling flow identifier is distributed.

Step 6: Receive a packet on R1 to find out whether it is a configured flow feature. If yes, the L2 scheduling flow identifier is encapsulated in the normal forwarding process, and then forwarded to R2. R2 parses the packet according to the protocol number, and then finds the associated scheduling action according to L2, performs scheduling, and sends the packet. When you replace L2 with an L3 tag, send it to R2.

Step 7: R3 performs an R2-like action until the message is forwarded to the destination.

In this manner, the devices dynamically negotiate the allocation of the scheduling flow identifiers through the protocol, and perform scheduling according to the scheduling flow identifier.

Embodiment 2:

Different from the first embodiment, the present embodiment is such that the manner is completed by static configuration. The specific instructions are as follows:

Step 1: Each forwarding device enables distribution of the scheduling flow identifier, and performs QoS scheduling based on the distributed scheduling flow identifier.

Step 2: Configure flow characteristics on each device and specify the dispatch flow identifier to be distributed to the upstream device. For device R1 that forwards the path entry, the outbound encapsulated scheduling flow identifier L1 is specified for the particular flow. For the case of R2, such as the upstream device and the downstream device, the scheduled flow identifier L1 of the ingress and the scheduled flow identifier L2 of the egress are configured, and the ingress scheduling flow identifier L2 is configured on R3. R2 and R3 associate the scheduling action with the ingress scheduling flow identifier.

Step 3: The packet enters R1, and R1 encapsulates the configured scheduling flow identifier L1 when forwarding the packet according to the flow characteristics and configuration.

Step 4: Relevant scheduling is performed according to L1 on R2, and L2 is sent to R3 on the egress package.

Step 5: R3 receives the packet, similar to R2 for related scheduling, forwarding, and the like.

In summary, the forwarding device performs the interaction, assigns a specific identifier to a specific flow, and sends a request message of the scheduling flow identifier requesting the distribution protocol to the downstream device. After receiving the request, the downstream device convects the flow according to the processing of the device. Assigning a specific identifier, and then notifying the upstream forwarding device by sending a response packet of the scheduling distribution identifier requesting the distribution protocol, so that the upstream forwarding device encapsulates the specific scheduling flow identifier into the packet when processing the packet. In the text, the downstream forwarding device is sent to the downstream forwarding device, and the downstream forwarding device can directly perform related action processing and scheduling according to the scheduling flow identifier, without performing classification processing, thereby improving processing performance and even saving hardware devices such as TCAM.

FIG. 10 is a structural diagram of a message scheduling apparatus based on a scheduling flow identifier according to an embodiment of the present invention. The device shown in Figure 10 includes:

The first obtaining module 1001 is configured to: in the process of processing the received packet, obtain a scheduling flow identifier corresponding to the next forwarding device of the packet in the forwarding path;

The adding module 1002 is configured to add the scheduling flow identifier to the packet.

The first sending module 1003 is configured to send a packet including the scheduling flow identifier to the next forwarding device.

The first obtaining module 1001 includes:

The searching unit searches for the scheduling flow identifier of the next forwarding device corresponding to the packet feature information of the packet according to the correspondence between the local pre-stored packet feature information and the scheduling flow identifier of the next forwarding device;

The receiving unit is configured to receive a query response fed back by the next forwarding device, where the query response includes message feature information of the packet.

The adding module 1002 is configured to: add a field after the Layer 2 protocol header of the packet, and add the scheduling flow identifier to the added field.

The device provided by the embodiment of the present invention obtains the scheduling flow identifier of the next forwarding device on the forwarding path by using the result of the local scheduling process in the process of scheduling the packet, and identifies the scheduling flow identifier. The notification is sent to the next forwarding device, which reduces the time for the next forwarding device to parse the packet feature information again to obtain the scheduling flow identifier corresponding to the packet, which improves the information processing efficiency and reduces the hardware consumption.

FIG. 11 is another packet scheduling device based on a scheduling flow identifier according to an embodiment of the present invention. Structure diagram. The device shown in Figure 11 includes:

The second obtaining module 1101 is configured to: after receiving the packet that includes the scheduling flow identifier, obtain the scheduling flow identifier in the packet;

The scheduling module 1102 is configured to perform a scheduling operation on the packet according to the scheduling flow identifier.

Wherein, the device further comprises:

The device provided by the embodiment of the present invention, in the process of processing the packet, obtains the scheduling flow identifier of the next forwarding device on the forwarding path by using the result of the local processing, and carries the scheduling flow identifier The next forwarding device is used to reduce the time when the next forwarding device parses the packet feature information to obtain the scheduling flow identifier corresponding to the packet, which improves information processing efficiency and reduces hardware consumption.

One of ordinary skill in the art will appreciate that all or a portion of the steps of the above-described embodiments can be implemented using a computer program flow, which can be stored in a computer readable storage medium, such as on a corresponding hardware platform (eg, The system, device, device, device, etc. are executed, and when executed, include one or a combination of the steps of the method embodiments.

Alternatively, all or part of the steps of the above embodiments may also be implemented by using an integrated circuit. These steps may be separately fabricated into individual integrated circuit modules, or multiple modules or steps may be fabricated into a single integrated circuit module. achieve. Thus, the invention is not limited to any specific combination of hardware and software.

The devices/function modules/functional units in the above embodiments may be implemented by a general-purpose computing device, which may be centralized on a single computing device or distributed over a network of multiple computing devices.

When each device/function module/functional unit in the above embodiment is implemented in the form of a software function module and sold or used as a stand-alone product, it can be stored in a computer readable storage medium. The above mentioned computer readable storage medium may be a read only memory, a magnetic disk or an optical disk or the like.

The above is only a specific embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily think of changes or substitutions within the technical scope of the present invention. It should be covered by the scope of the present invention. Therefore, the scope of the invention should be determined by the scope of the claims.

Industrial applicability

The foregoing technical solution reduces the time for the next forwarding device to parse the packet feature information again to obtain the scheduling flow identifier corresponding to the packet, thereby improving information processing efficiency and reducing hardware consumption.

Claims

A packet scheduling method based on a scheduling flow identifier includes:

The forwarding device obtains the scheduling flow identifier corresponding to the next forwarding device of the packet in the forwarding path, in the process of forwarding the received packet.

The forwarding device adds the scheduling flow identifier to the packet;

The forwarding device sends a packet including the scheduling flow identifier to the next forwarding device.
The method of claim 1, wherein the forwarding device obtains the scheduling flow identifier corresponding to the next forwarding device of the packet on the forwarding path, including:

The forwarding device acquires packet feature information of the packet;

And the forwarding device searches for the scheduling flow identifier of the next forwarding device corresponding to the packet feature information of the packet according to the correspondence between the local pre-stored packet feature information and the scheduling flow identifier of the next forwarding device;

If found, the forwarding device uses the found result as the scheduling flow identifier corresponding to the packet;

If not found, the forwarding device sends a query request to the next forwarding device, where the query request includes packet feature information of the packet; and receives a query response fed back by the next forwarding device, The query response includes scheduling flow identification information of the packet.
The method according to claim 1 or 2, wherein the forwarding device adds the scheduling flow identifier to the packet, including:

The forwarding device adds a field after the Layer 2 protocol header of the packet, and adds the scheduling flow identifier to the added field.
A packet scheduling method based on a scheduling flow identifier includes:

After receiving the packet including the scheduling flow identifier, the forwarding device acquires the scheduling flow identifier in the packet.

The forwarding device performs a scheduling operation on the packet according to the scheduling flow identifier.
The method of claim 4, further comprising:

The forwarding device acquires a scheduling flow identifier corresponding to the next forwarding device of the packet on the forwarding path;

The forwarding device replaces the forwarding identifier in the packet with the scheduling stream identifier corresponding to the next forwarding device;

The forwarding device sends the packet that has been replaced by the scheduled flow identifier.
A message scheduling device based on a scheduling flow identifier, comprising:

The first obtaining module is configured to: in the process of scheduling the received packet, obtain the scheduling flow identifier corresponding to the next forwarding device of the packet in the forwarding path;

Adding a module, configured to add the scheduling flow identifier to the packet;

The first sending module is configured to send a packet including the scheduling flow identifier to the next forwarding device.
The apparatus of claim 6, wherein the first obtaining module comprises:

An obtaining unit, configured to obtain message feature information of the packet;

The search unit is configured to search for a scheduling flow identifier of the next forwarding device corresponding to the packet feature information of the packet according to the correspondence between the local pre-stored packet feature information and the scheduling flow identifier of the next forwarding device;

a first determining unit, configured to: if found, the forwarding device uses the found result as a scheduling flow identifier corresponding to the packet;

a sending unit, configured to send a query request to the next forwarding device if not found, where the query request includes message feature information of the packet;

The receiving unit is configured to receive a query response fed back by the next forwarding device, where the query response includes scheduling flow identification information of the packet.
The apparatus according to claim 6 or 7, wherein the adding module is configured to: add a field after the layer 2 protocol header of the message, and add the scheduling stream identifier in the added field.
A message scheduling device based on a scheduling flow identifier, comprising:

The second obtaining module is configured to: after receiving the packet that includes the scheduling flow identifier, obtain the scheduling flow identifier in the packet;

The scheduling module is configured to perform a scheduling operation on the packet according to the scheduling flow identifier.
The apparatus of claim 9 further comprising:

a third acquiring module, configured to obtain a scheduling flow identifier corresponding to a next forwarding device of the packet on the forwarding path;

The replacement module is configured to replace the forwarding identifier in the packet with the scheduling flow identifier corresponding to the next forwarding device;

The second sending module is configured to send the packet after the completion of the scheduling flow identifier is replaced.
A computer storage medium having stored therein computer executable instructions for performing the method of any one of claims 1 to 3.
A computer storage medium having stored therein computer executable instructions for performing the method of any one of claims 4-5.