CN119892695A

CN119892695A - Time delay measurement method, time delay measurement device, forwarding node and storage medium

Info

Publication number: CN119892695A
Application number: CN202510058716.5A
Authority: CN
Inventors: 赵赛远
Original assignee: New H3C Technologies Co Ltd
Current assignee: New H3C Technologies Co Ltd
Priority date: 2025-01-14
Filing date: 2025-01-14
Publication date: 2025-04-25

Abstract

The embodiment of the application provides a time delay measuring method, a time delay measuring device, a forwarding node and a storage medium, which relate to the technical field of communication and are applied to the forwarding node; the method comprises the steps of obtaining a first message, obtaining a second message by forwarding the first message if the forwarding node is an input node or an intermediate node, copying the second message to obtain a second number of third messages if the second message is a delay dyeing message in the current statistics period and the service flow corresponds to a plurality of output interfaces, forwarding the second message and the first number of third messages through the plurality of output interfaces, sending a first time stamp and a second time stamp corresponding to each output interface to an analyzer, and measuring the delay index of a link where the forwarding node is located according to the first time stamp and the second time stamp corresponding to each output interface by the analyzer. The scheme can solve the problem of missing time delay measurement results caused by missing time stamp information on a plurality of links in a load sharing scene.

Description

Time delay measurement method, time delay measurement device, forwarding node and storage medium

Technical Field

The present application relates to the field of communications technologies, and in particular, to a delay measurement method, a delay measurement device, a forwarding node, and a storage medium.

Background

Currently, in-band flow information measurement (in-situ Flow Information Telemetry, iFIT) is generally adopted to measure performance indexes such as packet loss (PacketLoss) and Delay (D). Taking a time delay index as an example, an Ingress node (Ingress) performs time delay dyeing on a first iFIT message in each statistical period to obtain a time delay dyed message, and forwards the time delay dyed message to an intermediate node (Transit) or an Egress node (Egress), a time stamp of receiving and forwarding the time delay dyed message is recorded at a measurement point (Measurement Point, MP) on each forwarding node and is reported to an Analyzer, and the Analyzer measures time delay measurement results among the measurement points based on the time stamps.

In the load sharing scene, a plurality of links exist between the input node and the output node, in each statistical period, the input node randomly selects one link for each iFIT message to forward the iFIT message, and the link selection has certain randomness. In each statistical period, only one time delay dyeing message is needed, and correspondingly, the time delay dyeing message can be forwarded through only one link, so that only the time stamp information on the link can be obtained, and the time stamp information of other links can not be obtained. Due to the missing time stamp information for the other links, the delay measurements on the other links are missing.

Disclosure of Invention

The embodiment of the application aims to provide a time delay measurement method, a time delay measurement device, a forwarding node and a storage medium, so as to solve the problem of time stamp information loss on a plurality of links to cause loss of time delay measurement results in a load sharing scene. The specific technical scheme is as follows:

In a first aspect, an embodiment of the present application provides a delay measurement method, applied to a forwarding node, where the method includes:

Receiving a first message of a service flow through a first access interface;

If the forwarding node is an ingress node or an intermediate node, forwarding the first message to obtain a second message;

if the second message is a delay dyeing message of a current statistical period and the service flow corresponds to a plurality of output interfaces, copying the second message to obtain a first number of third messages, wherein the first number is the number of the plurality of output interfaces minus 1;

Forwarding the second message and the first number of third messages through the plurality of outgoing interfaces, and sending a first timestamp and a second timestamp corresponding to each outgoing interface to an analyzer, so that the analyzer measures a time delay index of a link where the forwarding node is located according to the first timestamp and the second timestamp corresponding to each outgoing interface, wherein the first timestamp is a timestamp of receiving the first message through the first incoming interface, and the second timestamp corresponding to each outgoing interface is a timestamp of forwarding the second message or the third message through each outgoing interface.

In a second aspect, an embodiment of the present application provides a delay measurement apparatus applied to a forwarding node, where the apparatus includes:

the receiving module is used for receiving a first message of the service flow through the first inlet interface;

the processing module is used for forwarding the first message to obtain a second message if the forwarding node is an ingress node or an intermediate node;

the copying module is used for copying the second message to obtain a first number of third messages if the second message is a delay dyeing message of a current statistical period and the service flow corresponds to a plurality of output interfaces, wherein the first number is the number of the plurality of output interfaces minus 1;

And the sending module is used for forwarding the second message and the first number of third messages through the plurality of outgoing interfaces, and sending a first timestamp and a second timestamp corresponding to each outgoing interface to the analyzer, so that the analyzer measures the time delay index of the link where the forwarding node is located according to the first timestamp and the second timestamp corresponding to each outgoing interface, wherein the first timestamp is a timestamp for receiving the first message through the first incoming interface, and the second timestamp corresponding to each outgoing interface is a timestamp for forwarding the second message or the third message through each outgoing interface.

In a third aspect, an embodiment of the present application provides a forwarding node, including 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 implement any of the above-described delay measurement methods.

In a fourth aspect, embodiments of the present application provide a computer readable storage medium having a computer program stored therein, which when executed by a processor implements any of the above-described time delay measurement methods.

In a fifth aspect, embodiments of the present application also provide a computer program product comprising instructions which, when run on a computer, cause the computer to perform any of the above-described time delay measurement methods.

The embodiment of the application has the beneficial effects that:

In the technical scheme provided by the embodiment of the application, after receiving the message of the service flow, the forwarding node copies the delay dyeing message to obtain a plurality of delay dyeing messages if the service flow corresponds to a plurality of output interfaces, and forwards one delay dyeing message through each output interface, so that the delay dyeing message is forwarded on the link corresponding to each output interface. Furthermore, the forwarding node can obtain the time stamp information on the plurality of links and report the time stamp information to the analyzer, and the analyzer can measure the time delay index on the plurality of links based on the time stamp information on the plurality of links, so that the problem of time delay measurement result deletion caused by the time stamp information deletion on the plurality of links under the load sharing scene is solved.

Of course, it is not necessary for any one product or method of practicing the application to achieve all of the advantages set forth above at the same time.

Drawings

In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the application, and other embodiments may be obtained according to these drawings to those skilled in the art.

FIG. 1 is a schematic diagram of iFIT network models;

fig. 2 is a schematic diagram of a iFIT packet loss measurement mechanism;

FIG. 3 is a schematic diagram of a iFIT delay measurement mechanism;

FIG. 4 is a schematic diagram of iFIT network model in a load sharing scenario;

fig. 5 is a schematic diagram of a packet loss and delay measurement mechanism of iFIT in a load sharing scenario;

fig. 6 is a schematic flow chart of a first method for measuring a time delay according to an embodiment of the present application;

Fig. 7 is a diagram of a format of a iFIT message in an MPLS network according to an embodiment of the present application;

fig. 8 is a iFIT message format diagram based on SRH encapsulation in SRv network according to an embodiment of the present application;

Fig. 9 is a diagram of iFIT message format based on DOH encapsulation in SRv network according to an embodiment of the present application;

fig. 10 is a schematic diagram of a second flow of a delay measurement method according to an embodiment of the present application;

fig. 11 is a schematic diagram of iFIT delay measurement mechanism according to an embodiment of the present application;

Fig. 12 is a third flowchart of a delay measurement method according to an embodiment of the present application;

FIG. 13 is a schematic diagram of a first flow of delay measurement according to an embodiment of the present application;

fig. 14 is a schematic diagram of an intermediate node in a load sharing scenario provided in an embodiment of the present application;

FIG. 15 is a schematic diagram of a second flow of delay measurement according to an embodiment of the present application;

Fig. 16 is a schematic diagram of a iFIT network model in a load sharing scenario provided by an embodiment of the present application;

fig. 17 is a schematic structural diagram of a delay measurement device according to an embodiment of the present application;

Fig. 18 is a schematic structural diagram of a forwarding node according to an embodiment of the present application.

Detailed Description

The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. Based on the embodiments of the present application, all other embodiments obtained by the person skilled in the art based on the present application are included in the scope of protection of the present application.

Current fifth generation mobile communication technology (5th Generation Mobile Communication Technology,5G) networks are evolving vigorously. Three major traffic scenarios for 5G networks include enhanced mobile broadband (Enhanced Mobile Broadband, eMBB) traffic, mass machine class Communication (MASSIVE MACHINE TYPE of Communication, mMTC) traffic, and (Ultra-reliable and Low Latency Communication, uRLLC) traffic. The three business scenes put higher requirements on network operation and performance monitoring of the bearing network, and iFIT and other flow performance detection schemes are generated.

IFIT is a flow-following operation, administration and maintenance (Operations Administration AND MAINTENANCE, OAM) detection technique, which is applied to a multiprotocol label switching (Multiprotocol Label Switching, MPLS) network, a segment routing (Segment Routing over MPLS, SR-MPLS) network based on an MPLS forwarding plane, and a segment routing (Segment Routing over IPv, SRv) network based on an internet protocol 6 th edition (Internet Protocol Version 6, ipv 6) forwarding plane by directly measuring a service packet to obtain performance indexes such as a real packet loss rate, a delay, etc. of an internet protocol (Internet Protocol, IP) network.

IFIT have the following functions and advantages. 1) iFIT has high detection precision, simple deployment and good expandability. 2) The rapid fault positioning function iFIT provides a stream following detection function, and can truly detect the packet loss, time delay and jitter of the service stream in real time. 3) And the visual function iFIT can display performance data through a visual interface and has the capability of quickly finding out fault points.

IFIT support two measurement types, end-to-end measurement and point-by-point measurement. These two measurement types are applicable to different traffic scenarios. When the user wishes to measure the performance index of the entire network, iFIT of the end-to-end measurement type may be selected. The point-by-point measurement type iFIT may be selected when the user wishes to accurately locate the performance index of each forwarding node in the network. When the measurement result shows that the performance index does not meet the service requirement in the end-to-end statistical scene, the network between the end and the end can be divided into a plurality of smaller measurement sections, the performance index between every two forwarding nodes is measured, and the positions of the forwarding nodes affecting the network performance are further positioned.

The iFIT network model measures performance indexes by using a multipoint collecting and centralized computing mode, as shown in fig. 1, taking a forwarding node in the iFIT network model as a Router (R) as an example, and the iFIT network model comprises the following elements:

the traffic flow iFIT is the data flow in the network which accords with the specified matching rule. A network administrator may define a traffic flow by a combination of parameters such as source IP address or network segment, destination IP address or network segment, protocol type, source port number and destination port number.

Ingress node-traffic flows enter the device of the measurement network, support iFIT, as R1 in fig. 1. The ingress node is responsible for screening the service flow, encapsulates iFIT the header of the service flow as a message, obtains iFIT the packet, collects the statistics of the service flow, and reports the statistics to the analyzer, as shown by the dotted line in fig. 1. The ingress node also forwards the traffic flow to the intermediate node.

Intermediate node-a device supporting iFIT through which traffic flows, such as R2 in fig. 1. And the intermediate node automatically identifies the service flow according to the iFIT message header contained in the received iFIT message and forwards the service flow to the next-hop equipment. When iFIT of point-by-point measurement type is adopted, the intermediate node can collect the statistical data of the service flow according to the measurement type carried by the iFIT message header and report the statistical data to the analyzer, and the service flow is forwarded to the next hop device.

Egress node-traffic leaves the device measuring the network, support iFIT, as R4 in fig. 1. The output node automatically identifies the service flow according to iFIT message header contained in the received iFIT message, collects the statistical data of the service flow according to the measurement type carried by iFIT message header and reports the statistical data to the analyzer, then removes iFIT message header and forwards the service flow to the next hop device.

And the analyzer is responsible for collecting the statistical data sent by the input node, the intermediate node and the output node, and completing the summarization and calculation of the data to obtain the performance indexes such as packet loss, time delay and the like of the corresponding service flow.

And the measuring point is bound with three layers of physical interfaces on the forwarding node and is responsible for executing measuring actions and generating statistical data. According to the responsibilities, MPs are classified into an ingress MP (i.e., a flow inlet measurement point), an egress MP (i.e., a flow outlet measurement point), and an intermediate MP. In FIG. 1, the incoming MP is MP1 on R1, the outgoing MP is MP6 on R4, and the intermediate MP is MP2 on R1, MP3 on R2, and MP5 on MP4 and R4.

Also included in the iFIT network model shown in fig. 1 are devices that do not support or do not turn on iFIT, such as R3, that forward traffic but do not collect statistics. In fig. 1, links forwarding traffic are R1-R2-R3-R4, MP1 to MP6 are measured end-to-end, MP1 to MP2, MP2 to MP3, MP3 to MP4, MP4 to MP5, and MP5 to MP6 are measured point by point.

To facilitate network administrators in knowing network conditions in time, iFIT measures performance metrics according to iFIT statistical cycles. For measurement of packet loss index, in order to distinguish two adjacent iFIT statistic periodic messages, a periodic alternate dyeing technology is adopted, and a specific measurement mechanism is as follows.

(1) And the incoming MP performs packet loss dyeing on the message of the service flow.

IFIT uses a packet Loss (Loss, L) field in a iFIT packet header as a packet Loss measurement dyeing bit, where the bit is set to 1 to indicate packet Loss dyeing, is set to 0 to indicate packet Loss non-dyeing, and subsequently refers to a packet Loss measurement dyeing position 1 as a packet Loss dyeing packet and refers to a packet Loss measurement dyeing position 0 as a packet Loss non-dyeing packet. MP performs packet loss dyeing treatment and packet loss non-dyeing treatment alternately on the messages of the service flow according to iFIT statistical periods to distinguish iFIT messages of two adjacent iFIT statistical periods.

As shown in fig. 2, a diagram of iFIT packet loss measurement mechanism is shown, 1 represents a packet loss dyeing message, and 0 represents a packet loss non-dyeing message. The transmitting (Tx) end performs packet loss dyeing processing in a dyeing message packet transmission statistical period (such as an ith iFIT statistical period and an ith+ iFIT statistical period), transmits a packet loss dyeing message to the receiving (Rx) end, performs packet loss non-dyeing processing in a non-dyeing message packet transmission statistical period (such as an ith+ iFIT statistical period), and transmits a packet loss non-dyeing message to the receiving end.

(2) And each MP counts the number of the received or forwarded messages according to iFIT counting periods.

Each MP counts the received or forwarded packet loss dyeing messages and packet loss non-dyeing messages. iFIT, the packet receiving statistical period of the receiving end is larger than the packet sending statistical period of the sending end, so as to avoid adverse effects of network delay and transmission disorder on statistical results to the greatest extent. As shown in fig. 2, a transmitting end firstly transmits a packet loss dyeing message X to a receiving end, then transmits a packet loss non-dyeing message Y, and the packet loss dyeing message X arrives in a delayed manner, the receiving end firstly receives the packet loss non-dyeing message Y and then receives the packet loss dyeing message X, and at this time, the receiving end still counts the packet loss dyeing message X in the ith iFIT statistical period.

That is, at the transmitting end, the time length of the packet counting period of the dyed packet=the time length of the packet counting period of the undyed packet=the time length of the iFIT counting period, the time length of the iFIT counting period can be configured according to practical situations, and at the receiving end, the time length of the packet counting period of the dyed packet=the time length of the packet counting period of the undyed packet = (1+1/3) × iFIT counting period.

According to the law of Wen Shouheng, in the ith iFIT statistics period, the difference in the number of iFIT messages received or forwarded by any two MPs is the packet loss number of the service flow between the two MPs, the packet loss number between the sending end and the receiving end in the ith iFIT statistics period in fig. 2 is PacketLoss [ i ] = Tx [ i ] -Rx [ i ], tx [ i ] represents the number of packet loss dyeing messages counted by the sending end in the ith iFIT statistics period, and Rx [ i ] represents the number of packet loss dyeing messages counted by the receiving end in the ith iFIT statistics period. Similarly, the number of lost packets between the sending end and the receiving end in the ith+ iFIT statistical period is PacketLoss [ i+1] =Tx [ i+1] -Rx [ i+1], tx [ i+1] represents the number of lost packet non-dyed messages counted by the sending end in the ith+ iFIT statistical period, and Rx [ i+1] represents the number of lost packet non-dyed messages counted by the receiving end in the ith+ iFIT statistical period.

(3) After the MP is removed iFIT by decapsulation, the MP forwards the message to the next hop device.

For the measurement of the time delay index, the measurement of the packet loss index and the dyeing and counting are carried out at the same iFIT counting period, and the specific measurement mechanism is as follows.

(1) And the incoming MP performs delay dyeing on the message of the service flow.

IFIT uses the D field in the iFIT header as a delay measurement dyeing bit, where the bit is set to 1 to indicate delay dyeing, and set to 0 to indicate delay non-dyeing, and then the message at the delay measurement dyeing position 1 is called a delay dyeing message, and the message at the delay measurement dyeing position 0 is called a delay non-dyeing message. The incoming MP performs delay dyeing only on the first message of the traffic stream received in each iFIT statistical period.

As shown in the iFIT time delay measurement mechanism schematic diagram in fig. 3, 11 represents a packet loss dyeing+time delay dyeing message, 10 represents a packet loss dyeing+time delay non-dyeing message, 01 represents a packet loss non-dyeing+time delay dyeing message, and 00 represents a packet loss non-dyeing+time delay non-dyeing message.

(2) Each MP records the time stamp of the delay dye message passing through the book MP.

In the ith iFIT statistics period, the difference value of the time stamps recorded by any two MPs is the transmission Delay of the service flow between the two MPs, and the transmission Delay between the sending end and the receiving end of the ith iFIT statistics period in fig. 3 is Delay [ i ] = t '[ i ] -ti ], t [ i ] represents the time stamp recorded by the sending end of the ith iFIT statistics period, and t' [ i ] represents the time stamp recorded by the receiving end of the ith iFIT statistics period. Similarly, the transmission Delay between the i+1st iFIT statistical period transmitting end and the receiving end is Delay [ i+1] = t '[ i+1] -t [ i+1], t [ i+1] represents the timestamp recorded by the i+1st iFIT statistical period transmitting end, and t' [ i+1] represents the timestamp recorded by the i+1st iFIT statistical period receiving end.

In the load sharing scenario, there are multiple links between the ingress node and the egress node, as shown in iFIT network model in fig. 4 (the analyzer is omitted in fig. 4), the ingress node is R1, the egress node is R5, there are 3 links between R1-R2-R5, R1-R3-R5 and R1-R4-R5, and load sharing is formed between these 3 links when the traffic flows are forwarded from R1 to R5.

In each statistical period, for each iFIT message, the ingress node randomly selects a link to forward the iFIT message, and the link selection has a certain randomness, as shown in fig. 5, the iFIT message can be forwarded to R5 through different links, and t [ i+2] represents the timestamp recorded at the sending end of the i+2nd iFIT statistical period. Taking the i iFIT th statistical period as an example, the MP1 sends the 1 st, 2 nd and 5 th iFIT messages in the present period through the links where the MP2, MP5, MP8 and MP11 are located, sends the 4 th iFIT message in the present period through the links where the MP3, MP6, MP9 and MP12 are located, sends the 3 rd and 6 th iFIT messages in the present period through the links where the MP4, MP7, MP10 and MP13 are located, and the iFIT message passes through the corresponding MP in the forwarding process, fig. 5 may show the case that the iFIT message passes through the MP2, MP3 and MP4, or may show the case that the iFIT message passes through the MP5, MP6 and MP7, that is, fig. 5 may show the case that the iFIT message passes through any one of the MPs 2 to MP 13.

For the measurement of the packet loss index, the packet receiving quantity can be accurately counted in MP 2-MP 13 no matter in the counting period of the dyed packet receiving or the counting period of the undyed packet receiving, so that the packet loss quantity in any interval from MP2 to MP5, MP8 or MP11 can be accurately calculated, and the packet loss quantity in any interval from MP3 to MP6, MP9 or MP12 and the packet loss quantity in any interval from MP4 to MP7, MP10 or MP13 can be accurately calculated. The 3 intervals of MP1 and MP2, MP3 or MP4 belong to the interior of R1, and the total packet loss in the interior of R1 can be accurately calculated.

For measurement of the time delay index, because only one time delay dyeing message exists in each statistical period, correspondingly, the time delay dyeing message can only be forwarded through one link, and further, only the time stamp information on the link can be obtained, and the time stamp information of other links can not be obtained. Due to the missing time stamp information for the other links, the delay measurements on the other links are missing.

In fig. 5, the i iFIT th statistical period delay dyeing message is forwarded through the links R1-R2-R5, the delay dyeing message can only be received by MP2, MP5, MP8 and MP11, the i+1th and i+2nd iFIT th statistical period delay dyeing message is forwarded through the links R1-R3-R5, the delay dyeing message can only be received by MP3, MP6, MP9 and MP12, and MP4, MP7, MP10 and MP13 can not receive any delay dyeing message. Furthermore, only MP2, MP5, MP8, and MP11 can record the time stamp t ' [ i ] of the ith iFIT th statistical period, and only MP3, MP6, MP9, and MP12 can record the time stamp t ' [ i+1] of the (i+1) th iFIT th statistical period and the time stamp t ' [ i+2] of the (i+2) th iFIT th statistical period.

Due to the lack of the timestamp information recorded by the receiving end, any interval from MP1 to MP2, MP5, MP8 or MP11 can only count the timestamp information of the ith iFIT statistic period, any interval from MP1 to MP3, MP6, MP9 or MP12 can only count the timestamp information of the (i+1) th and (i+2) th iFIT statistic periods, and any interval from MP1 to MP4, MP7, MP10 or MP13 can not count the timestamp information of the 3 iFIT statistic periods, thereby further resulting in the lack of the delay measurement result on the link.

In order to solve the above problems, the embodiment of the present application provides a delay measurement method, which is applied to a forwarding node. The forwarding node may be a network device such as a router, a switch, etc. supporting iFIT, and may be divided into an ingress node, an intermediate node, and an egress node, where the ingress node may be understood as a head node, and the egress node may be understood as a tail node, which are described by taking the ingress node and the egress node as examples for convenience of description, and are not limited. The link on which the forwarding node is located may also include a device that is not supported or turned on iFIT, which is not limited.

Referring to fig. 6, a first flow chart of a delay measurement method provided by an embodiment of the present application is applied to a forwarding node, and the delay measurement method includes the following steps.

Step S61, through the first incoming interface, a first message of the service flow is received.

Step S62, if the forwarding node is an ingress node or an intermediate node, forwarding the first message to obtain a second message.

Step S63, if the second message is a delay dyeing message of the current statistics period and the service flow corresponds to a plurality of output interfaces, the second message is duplicated to obtain a first number of third messages, wherein the first number is the number of the plurality of output interfaces minus 1.

Step S64, forwarding a second message and a first number of third messages through a plurality of outgoing interfaces, and sending a first timestamp and a second timestamp corresponding to each outgoing interface to an analyzer, so that the analyzer measures a time delay index of a link where a forwarding node is located according to the first timestamp and the second timestamp corresponding to each outgoing interface, wherein the first timestamp is a timestamp of receiving the first message through a first incoming interface, and the second timestamp corresponding to each outgoing interface is a timestamp of forwarding the second message or the third message through each outgoing interface.

In the technical scheme provided by the embodiment of the application, after receiving the delay dyeing message of the service flow, if the service flow corresponds to a plurality of outgoing interfaces, the forwarding node copies the delay dyeing message after forwarding processing to obtain a plurality of delay dyeing messages, and forwards one delay dyeing message through each outgoing interface, so that the delay dyeing message is forwarded on the link corresponding to each outgoing interface. Furthermore, the forwarding node can obtain the time stamp information on the plurality of links and report the time stamp information to the analyzer, and the analyzer can measure the time delay index on the plurality of links based on the time stamp information on the plurality of links, so that the problem of time delay measurement result deletion caused by the time stamp information deletion on the plurality of links under the load sharing scene is solved.

In the above step S61, the traffic flow is any data flow that uses iFIT to measure the performance index. The first message is any message of the service flow received by the forwarding node in the current statistical period, and the first input interface is the input interface corresponding to the service flow on the forwarding node and used for receiving the first message.

In the embodiment of the application, the forwarding node receives the message of the service flow in the current statistical period through the first input interface, and the received iFIT message is the first message.

In the embodiment of the application, when the forwarding node is an ingress node, the first message does not carry iFIT message header, the first message is an original message, and when the forwarding node is an intermediate node or an egress node, the first message carries iFIT message header, and the first message is iFIT message.

In the step S62, when the forwarding node is an ingress node or an intermediate node, the forwarding node may perform corresponding forwarding processing on the first packet after receiving the first packet, to obtain a packet after forwarding processing, where the packet is the second packet. For example, in an MPLS network, a forwarding node may modify an MPLS Label (Label) or the like in a first message. For another example, in the SRv network, the forwarding node may modify the segment routing header (Segment Routing Header, SRH) and destination IPv6 address, etc. in the first message. The forwarding processing method of the forwarding node is not limited here. The case where the forwarding node is an egress node will be described in detail later, and will not be described in detail here.

In the embodiment of the present application, the second message carries iFIT message header, and the second message is iFIT message. When the forwarding node is an intermediate node, the first message is iFIT messages, the second message obtained by the forwarding node is iFIT messages, when the forwarding node is an incoming node, the first message is an original message, the forwarding node can encapsulate a iFIT message header for the first message, perform delay dyeing and/or packet loss dyeing and other processes to obtain iFIT messages (namely the second message), and the process of forwarding the first message by the incoming node to obtain the second message is described in detail later and is not described in detail herein.

After the second message is obtained, the forwarding node can judge whether the second message is a delay dyeing message according to the value of a D field (i.e. a delay measurement dyeing bit) in a iFIT message header carried by the second message. When the value of the D field is not the first preset value, the second message is not the delay dyeing message (namely, the second message is the delay non-dyeing message). The first preset value may be 1 or 0, etc., and for convenience of description, the following description will take the first preset value as 1 as an example, which is not meant to be limiting.

If the value of the D field is 1, the forwarding node determines that the second message is a delay dyeing message, and the forwarding node records a timestamp (i.e., a first timestamp) of receiving the first message. The first timestamp corresponds to the first ingress interface, and is a timestamp recorded by the forwarding node at the MP corresponding to the first ingress interface.

In the embodiment of the present application, the second message is the first delay dyeing message processed by the forwarding node in the current statistical period, and the forwarding node may record a time stamp (i.e., a second time stamp) for forwarding the second message.

After determining that the second packet is a delay dyed packet, the forwarding node may further determine whether the number of egress interfaces (denoted as N) corresponding to the service flow is greater than 1. When N >1, the traffic flow corresponds to a plurality of outgoing interfaces, and the forwarding node performs step S63.

In the above step S63, the first number is the number of outgoing interfaces corresponding to the traffic flow minus 1, i.e., the first number is N-1. The third message is a copied message of the second message, that is, the third message is a delay dyeing message and is a copied message (for convenience of description, hereinafter simply referred to as a delay dyeing copy message), and the value of the D field of the third message is a first preset value.

The forwarding node replicates the first number of second messages to obtain replicated messages of the first number of second messages, and each replicated message is a third message. After the forwarding node replicates the second message, a number of delay dyed messages (including 1 second message and N-1 third messages) of the outgoing interface can be obtained.

In the embodiment of the present application, the iFIT header may include a copy (Dup) field. The length of the Dup field may be 1bit (bit), 2 bits, etc., and for convenience of description, the length of the Dup field is 1bit will be described hereinafter, which is not limited.

The Dup field carries a replication identifier, which indicates that the message is a replicated message. The Dup field may be located in a reserved bit field of iFIT header, such as iFIT messages in different networks as shown in fig. 7-9.

The iFIT packets in MPLS network are shown in fig. 7, iFIT packets include destination Address (Destination Address, DA)/Source Address (SA)/virtual local area network (Virtual Local Area Network, VLAN), segment Routing (SR)/MPLS header, iFIT packet header, and Payload. The iFIT header includes a guide tag, a base portion, and an extension portion, as indicated on the right side of the iFIT header.

The bootstrap tag includes a stream instruction identification tag (Flow Instruction Indicator Label, FII Label) field (value 12), a reserved bit (EXP) field, and a Time To Live (TTL) field.

The basic header includes a Flow Identity (Flow ID) field, an L field, a D field, a reserved bit (R) field, a non-stack bottom/stack bottom (S/R) field, an extension header (NextHeader) field (value 9), a Flow Identity extension (Extended, ext) field, a statistics pattern (E) field, a mismatch (P) field, a forward Flow Identity (F) field, a reserved bit (R) field, an extension length (Len) field (value 6), a reserved bit (Rsv) field, a Metadata (Metadata) indication bit (bitmap) (TRACE TYPE (bitmap)) field.

The extension header includes bits (Bit) 0, bit1, bit2, bit3.Bit0 is used to measure packet-by-packet delay and includes a reserved Bit (Rsv)/Timestamp (seconds (s)) field and a reserved Bit (Rsv)/Timestamp (nanoseconds (ns)) field. Bit1 is a control field, and includes a Destination IP (DIP) Mask field, a Source IP (SIP) Mask field, a protocol (Proto)/Ports field, a reverse flow (V) field, a Differential Service Code Point (DSCP) field, a Tunnel (T) field, and a synchronous report Period(s) field. Bit2 is used to measure out-of-order detection and includes a Sequence (Sequence) field. Bit3 is used to implement packet-change detection through verification, including a verification (Checksum) field.

IFIT packets encapsulated based on SRH in SRv network as shown in fig. 8, iFIT packets include ethernet Header (ETHERNET HEADER, ETH), IPv6 Basic Header (IPv 6 Basic Header), segment routing Header (Segment Routing Header, SRH), and payload, SRH includes SRH Basic Header (SRH Basic Header), segment list (SEGMENT LIST), and iFIT packet Header (optional type length Value) (Optional TYPE LENGTH Value, optional TLV). The iFIT message header includes a boot label, a base portion, and an extension portion.

The bootstrap tag includes a Type (Type) field (value 130), a Length (Length) field, and a reserved bit (Rsv) field. The basic part and the extension part are the same as those in the iFIT header in the MPLS network, and are not described in detail herein.

The iFIT message encapsulated based on the destination option Header (Destination Options Header, DOH) in SRv network is shown in fig. 9, and the iFIT message includes ETH, IPv6 basic Header, DOH1, routing Header (RH)/SRH, other Header (Other Headers) and load, or ETH, IPv6 basic Header, RH/SRH, DOH2, other Header and load. The DOH may be encapsulated in two locations, either in an alternative relationship.

The iFIT header includes an optional identification Type (Option Type) field, an optional identification Type Data length (Option Data Len) field, a traffic flow identification (Flow Monitor Identity, flowMonID) field, an L field, a D field, a Reserved bit (R) field, an identification extension header Type (HEADER TYPE Indication, HTI) field (value 16), a device node identification (Node Monitor Identity, nodeMonID) field, a traffic flow direction identification (F) field, a measurement period (P) field, a measurement Type (T) field, a Reserved bit (Rsv) field, an extension flow detection Type identification (bitmap) (Ext Flow Measurement Type, ext FM Type) (bitmap) field, a Reserved bit (Reserved) field.

Based on the encapsulation format of iFIT message header under different networks, the forwarding node can use the 1-bit reserved bit (R) field next to the D field as the Dup field to bear the copy identification. The forwarding node may also use a bit with a corresponding length (e.g., 1 bit) in other reserved bit (e.g., R, rsv, etc.) fields as the Dup field, where the location of the Dup field is not limited.

The copy identifier may be a second preset value, and the second preset value may be 0 or 1. For example, when the second preset value is 1, a value of 1 in the Dup field indicates that the message carries a copy identifier, and the message is a copied message, and a value of 0 in the Dup field indicates that the message does not carry a copy identifier, and the message is not a copied message. For convenience of description, the second preset value is taken as1 as an example, and the description is not limited.

Because the forwarding node only copies the delay dyed message, the copy identifier may also indicate that the message is a delay dyed copy message. That is, when the value of the Dup field is 1, the message carries the copy identifier, and the message is a delay dyeing copy message, and the value of the D field is 1.

In the embodiment of the application, the forwarding node can copy the first number of second messages and add the copy identifier in the copied messages, that is, set the Dup field in the iFIT message header carried by the copied messages to a second preset value (e.g. 1) to obtain the first number of third messages carrying the copy identifier.

In the embodiment of the present application, the second message obtained by the forwarding node in step S62 may carry a replication identifier, that is, the Dup field in the iFIT message header carried by the second message may have a value of 1, in this case, the second message is a delay dyeing replication message, or the second message may not carry a replication identifier, that is, the Dup field in the iFIT message header carried by the second message may have a value of 0, in this case, the second message is an original message of the delay dyeing message (for convenience of description, the subsequent is simply referred to as a delay dyeing original message).

In the embodiment of the present application, the forwarding node may record a time stamp (i.e., a second time stamp) for forwarding each third message, so as to obtain a first number (i.e., N-1) of second time stamps, which are then abbreviated as second time stamps corresponding to the third messages for convenience of description. Because the forwarding node also records the second time stamp corresponding to the second message before executing step S63, the forwarding node records N second time stamps in total. The forwarding node may record the time stamp information when the copying is completed as the second time stamp corresponding to each third message, which is not limited.

In the step S64, the forwarding node forwards a message through each outgoing interface, where the message may be the second message or the third message. The forwarding node may determine one output interface (abbreviated as a third output interface) from the multiple output interfaces corresponding to the service flow, forward the second message through the third output interface, and forward a third message through each other output interface except the third output interface. The forwarding node may randomly determine one output interface from the multiple output interfaces as the third output interface, or may determine the third output interface according to a link of the forwarding delay dyed original message, which is not limited.

The second timestamp corresponding to each message (the second message or the third message) corresponds to an outgoing interface for forwarding the message, and is a timestamp recorded by the forwarding node at the MP corresponding to the outgoing interface. For example, the second timestamp corresponding to the second message corresponds to the third outgoing interface, which is a timestamp recorded by the forwarding node at the MP corresponding to the third outgoing interface. And the forwarding node determines the time stamp of each outgoing interface forwarding message by recording the second time stamp.

In the embodiment of the application, after the current statistics period is ended, the forwarding node reports the recorded first timestamp and the plurality of second timestamps to the analyzer so as to report the timestamp corresponding to the first input interface and the timestamp corresponding to the plurality of output interfaces corresponding to the service flow to the analyzer, and further, the analyzer can measure the time delay index between the first input interface and the plurality of output interfaces to obtain the time delay in the forwarding node. For example, for each second timestamp, the analyzer may calculate a difference between the second timestamp and the first timestamp, where the obtained difference is a time delay between the ingress interface and the egress interface corresponding to the second timestamp.

In the embodiment of the application, the upstream forwarding node can forward the second message or the third message to the downstream forwarding node, and the downstream forwarding node can receive the second message or the third message forwarded by the upstream forwarding node as the first message. Each forwarding node (ingress node or intermediate node) may record and report to the analyzer a second timestamp of forwarding the second or third message and a first timestamp of receiving the first message. The analyzer may measure the time delay index between the forwarding nodes according to the first time stamp and the second time stamp reported by the current forwarding node and the first time stamp and the second time stamp reported by other forwarding nodes on the link where the current forwarding node is located, by integrating the first time stamp and the second time stamp recorded by the plurality of forwarding nodes.

When the current forwarding node is an ingress node or an intermediate node, the analyzer may measure a delay indicator between an ingress interface (i.e., a first ingress interface) on the next-hop device that receives the first packet and an egress interface on the current forwarding node that forwards the second packet or the third packet according to a first timestamp reported by a device (for convenience of description, hereinafter referred to as a next-hop device for short) of the next-hop support iFIT of the current forwarding node and in combination with a second timestamp reported by the current forwarding node.

When the current forwarding node is an intermediate node, the analyzer may measure a time delay index between the first input interface on the current forwarding node and the output interface on the previous hop device for forwarding the corresponding second message or the third message according to the second timestamp reported by the device (for convenience of description, the device is simply referred to as the previous hop device) of the previous hop support iFIT of the current forwarding node and in combination with the first timestamp reported by the current forwarding node.

In some embodiments, when the forwarding node is an ingress node, the first message received by the forwarding node through the first ingress interface is an original message, and the step S62 may be to encapsulate iFIT the header of the first message, and delay dye the encapsulated first message to obtain the second message.

In the embodiment of the application, the ingress node encapsulates the iFIT message header on the first message, and the encapsulated message is iFIT message. And then, performing delay dyeing on iFIT messages by the ingress node to obtain a second message.

For the first original message of the service flow received in the current statistical period, after the first original message is the message header of the message package iFIT, the ingress node sets the D field in the iFIT message header carried by the message to be 1 to obtain a time delay dyeing message, while for the other original messages of the service flow received in the current statistical period, after the second original message is the message header of the message package iFIT, the ingress node sets the D field in the iFIT message header carried by the message to be any value (e.g. 0) which is not 1 to obtain a time delay dyeing-free message. That is, the second message obtained by the ingress node may be a delay dyed message or a delay undyed message.

In the embodiment of the application, after the ingress node encapsulates iFIT the header of the first packet, the ingress node may further perform packet loss dyeing to measure a packet loss index. By applying the technical scheme of the embodiment of the application, the ingress node encapsulates the original message by adopting the iFIT message header, constructs the iFIT message, and reports the timestamp of the received original message as the first timestamp to the analyzer so as to realize the measurement of the time delay index.

In some embodiments, when the forwarding node is an ingress node or an intermediate node, after determining that the second packet is a delay dyeing packet, the forwarding node only needs to measure a delay index of a link where the second packet is located if it is determined that the traffic flow corresponds to only one egress interface, that is, if n=1 is determined, the forwarding node only needs to measure the delay index of the link where the second packet is located, does not need to copy the second packet, directly forwards the second packet through the egress interface corresponding to the traffic flow, and sends a first timestamp and a second timestamp corresponding to the egress interface to the analyzer, where the analyzer measures the delay index according to the first timestamp and the second timestamp. The manner in which the forwarding node sends the first timestamp and the second timestamp to the analyzer and the manner in which the analyzer measures the delay indicators can be seen in particular from the relevant description of the above section S64.

A second flow diagram of a delay measurement method, as shown in fig. 10, may include the following steps.

Step S101, through a first incoming interface, a first message of a service flow is received. The same as in step S61 described above.

Step S102, if the forwarding node is an ingress node or an intermediate node, forwarding the first message to obtain a second message. The same as in step S62 described above. After the forwarding node executes step S102, it continues to execute step S103 or step S105.

Step S103, if the second message is a delay dyeing message of the current statistics period and the service flow corresponds to a plurality of output interfaces, the second message is duplicated to obtain a first number of third messages, wherein the first number is the number of the plurality of output interfaces minus 1. The same as in step S63 described above. After the forwarding node performs step S103, it continues to perform step S104.

Step S104, forwarding a second message and a first number of third messages through a plurality of outgoing interfaces, and sending a first timestamp and a second timestamp corresponding to each outgoing interface to an analyzer, so that the analyzer measures a time delay index of a link where a forwarding node is located according to the first timestamp and the second timestamp corresponding to each outgoing interface, wherein the first timestamp is a timestamp of receiving the first message through a first incoming interface, and the second timestamp corresponding to each outgoing interface is a timestamp of forwarding the second message or the third message through each outgoing interface.

Step 105, if the second message is a delay dyeing message in the current statistics period and the service flow corresponds to an output interface, forwarding the second message through the output interface, and sending a first timestamp and a second timestamp corresponding to the output interface to the analyzer.

In the technical scheme provided by the embodiment of the application, under the condition that the service flow corresponds to one output interface, the forwarding node forwards the second message through the one output interface, so that the delay index of the link can be measured, the message forwarding speed is improved, and the message processing resources are saved.

Take R1 in the network model shown in fig. 4 as the current forwarding node as an example. R1 includes 1 input interface (corresponding to MP 1) and 3 output interfaces (corresponding to MP2, MP3 and MP4 respectively). R1 receives an original message (i.e. a first message) of a service flow sent by a previous hop device through an ingress interface (i.e. a first ingress interface), encapsulates iFIT message heads, and performs delay dyeing and packet loss dyeing.

Such as iFIT delay measurement mechanism shown in fig. 11. In fig. 11, 110 represents a packet loss dyeing+delay dyeing original message, 010 represents a packet loss non-dyeing+delay dyeing original message, 000 represents a packet loss non-dyeing+delay non-dyeing message, 100 represents a packet loss dyeing+delay non-dyeing message, 111 represents a packet loss dyeing+delay dyeing copy message, and 011 represents a packet loss non-dyeing+delay dyeing copy message. For convenience of description, the case that iFIT messages forwarded by MP1 pass through MP2, MP3 and MP4 will be described as an example.

In the ith statistical period, R1 records a first timestamp t [ i ] of the received original message at MP1, forwards the corresponding delay dyeing message from the corresponding output interface of MP2 to R2, and records a second timestamp t' [ i ] of the forwarded delay dyeing message at MP 2. Because the R1 also comprises the corresponding outgoing interfaces of the MP3 and the MP4, the R1 replicates 2 time delay dyeing messages, and forwards one time delay dyeing replication message from the corresponding outgoing interface of the MP3 to the R3, and records a second time stamp t '' i for forwarding the time delay dyeing replication message at the MP 3. Similarly, R1 forwards another delay dyeing replication message from the output interface corresponding to MP4 to R4, and records a second timestamp t ' ' ' [ i ] for forwarding the other delay dyeing replication message at MP 4.

R1 reports time stamps t [ i ], t ' ' [ i ] and t ' ' ' [ i ] to an analyzer, the analyzer calculates t ' [ i ] -t [ i ] to obtain the time delay between MP1 and MP2 in the ith statistical period, calculates t ' ' [ i ] -t [ i ] to obtain the time delay between MP1 and MP3 in the ith statistical period, and calculates t ' ' ' [ i ] -t [ i ] to obtain the time delay between MP1 and MP4 in the ith statistical period.

Because R1 forwards delay dyeing replication messages to R3 and R4 respectively, R3 and R4 can also receive delay dyeing messages and record a first time stamp of the received delay dyeing messages and a second time stamp of the forwarding delay dyeing messages, and the internal delay of the equipment and the delay between the delay dyeing messages and R1 and R5 can be measured respectively based on the received delay dyeing messages.

Similarly, in the i+1th and i+2th statistical periods, R1 may record time stamps t [ i+1], t '' [ i+1] and t '' '[ i+1], and t [ i+2], t' '[ i+2] and t' '' [ i+2], respectively, and report to the analyzer, which calculates the time delay between each MP in the i+1th and i+2th statistical periods.

Based on this, 2 delay dyeing replication messages are newly added in each statistics period, so that delay dyeing messages (i.e. 1 delay dyeing original message+2 delay dyeing replication messages) exist on 3 load sharing links in each statistics period, so as to record timestamp information on each link, and further calculate a delay index.

In the embodiment of the application, if the value of the D field in the iFIT message header carried by the second message is 0, the forwarding node determines that the second message is a delay non-dyeing message, does not record a timestamp, and forwards the second message directly through the output interface corresponding to the service flow.

In some embodiments, when the forwarding node is an egress node, the first packet received by the forwarding node is iFIT packets, which carries a iFIT packet header. In this case, the forwarding node does not perform step S62, that is, does not perform forwarding processing on the first packet, and obtains the second packet. Referring to fig. 12, a third flowchart of a delay measurement method according to an embodiment of the present application may include the following steps:

Step S121, receiving a first message of a service flow through a first ingress interface. The same as in step S61 described above. After the forwarding node performs step S121, it continues to perform step S122, step S126, or step S127.

Step S122, if the forwarding node is an ingress node or an intermediate node, forwarding the first message to obtain a second message. The same as in step S62 described above. After the forwarding node performs step S122, it continues to perform step S123 or step S125.

Step S123, if the second message is a delay dyeing message of the current statistics period and the service flow corresponds to a plurality of output interfaces, the second message is duplicated to obtain a first number of third messages, wherein the first number is the number of the plurality of output interfaces minus 1. The same as in step S63 described above. After the forwarding node performs step S123, it continues to perform step S124.

Step S124, forwarding the second message and the first number of third messages through the plurality of outgoing interfaces, and sending a first timestamp and a second timestamp corresponding to each outgoing interface to the analyzer, so that the analyzer measures a time delay index of a link where the forwarding node is located according to the first timestamp and the second timestamp corresponding to each outgoing interface, wherein the first timestamp is a timestamp of receiving the first message through the first incoming interface, and the second timestamp corresponding to each outgoing interface is a timestamp of forwarding the second message or the third message through each outgoing interface.

Step S125, if the second message is a delay dyeing message of the current statistics period and the service flow corresponds to an output interface, forwarding the second message through the output interface, and sending a first timestamp and a second timestamp corresponding to the output interface to the analyzer. The same as in step S115 described above.

In step S126, if the forwarding node is an outbound node, the first message is a delay dyeing message in the current statistical period, and the first message does not carry a duplication mark, then the iFIT message header carried by the first message is stripped to obtain a fifth message, the duplication mark indicates that the message is a duplicated message, the fifth message is forwarded through a second outbound interface corresponding to the service flow, and a first timestamp and a sixth timestamp are sent to the analyzer, so that the analyzer measures the delay index of the link where the forwarding node is located according to the first timestamp and the sixth timestamp, and the sixth timestamp is a timestamp for forwarding the fifth message through the second outbound interface.

Step S127, if the forwarding node is an egress node, the first message is a delay dyeing message in the current statistical period, and the first message carries a duplication identifier, the first message is discarded, and a first timestamp is sent to the analyzer.

By applying the technical scheme provided by the embodiment of the application, when the forwarding node is the outbound node, judging whether the delay dyeing message in the current statistical period is a copied message or not, and reducing the number of messages which need to be processed by the outbound node by discarding redundant messages, thereby reducing the influence on the forwarding of subsequent messages.

In the embodiment of the application, after the output node receives the first message, whether the first message is a delay dyeing message can be judged. If the output node determines that the first message is a delay dyeing message, it is determined whether the first message carries a duplication identifier (i.e., whether the value of the Dup field in the carried iFIT message header is a second preset value), that is, whether the first message is a delay dyeing duplication message is determined.

If the first message does not carry the duplication mark, the output node determines that the value of the Dup field in the carried iFIT message header is not the second preset value, and the first message is not the delay dyeing duplication message (namely, the delay dyeing original message), step S126 is executed, if the first message carries the duplication mark, the output node determines that the value of the Dup field in the carried iFIT message header is the second preset value, and if the first message is the delay dyeing duplication message, step S127 is executed.

In the step S126, the second outgoing interface is an outgoing interface corresponding to the traffic flow on the outgoing node. The node stripping the iFIT message header carried by the first message to obtain a corresponding original message, wherein the original message is the fifth message. The outbound node may record a first timestamp of receiving the first packet, and record a timestamp of forwarding the fifth packet (i.e., a sixth timestamp), where the sixth timestamp corresponds to an outbound interface (i.e., a second outbound interface) forwarding the fifth packet, and is a timestamp recorded by the outbound node at an MP corresponding to the second outbound interface. And the output node forwards the fifth message to the next hop device through the second output interface.

In the embodiment of the application, after the current statistical period is ended, the node is sent out to the analyzer by reporting the recorded first time stamp and sixth time stamp, and the analyzer measures the time delay index of the link where the node is located. The analyzer can measure the time delay index between the first input interface and the second output interface according to the first time stamp and the sixth time stamp to obtain the time delay inside the forwarding node.

In the embodiment of the application, the analyzer can measure the time delay index between the forwarding nodes according to the second time stamps reported by other forwarding nodes on the link where the exit node is located. For example, the analyzer may measure a time delay index between the first input interface on the node and the output interface on the last hop device that forwards the corresponding second message or third message according to the second timestamp reported by the last hop device of the output node and in combination with the first timestamp reported by the output node. The process of measuring the time delay indicator by the analyzer based on the first time stamp and the sixth time stamp is similar to the process of measuring the time delay indicator based on the first time stamp and the second time stamp, and the description of the step S63 is specifically referred to.

In the step S127, the output node determines that the first message is not the time delay dyeing original message, discards the first message, records a first timestamp of the received first message, reports the first timestamp to the analyzer, and the analyzer measures the time delay index according to the first timestamp.

In the embodiment of the application, after determining that the first message is a delay dyeing message, the node can record a first time stamp for receiving the first message, and the time for recording the first time stamp is not limited.

In the embodiment of the application, when the output node determines that the first message is not the delay dyeing message, the output node strips the iFIT message header carried by the first message to obtain the corresponding original message, and forwards the corresponding original message to the next hop device through the second output interface.

In some embodiments, after receiving the first packet, the forwarding node may continue to receive other packets of the current statistical period traffic flow through an ingress interface on the forwarding node. When the forwarding node is an intermediate node or an outgoing node, the other messages received by the forwarding node may be iFIT messages, and in this case, the delay measurement method further includes the step of receiving a fourth message of the service flow through the first ingress interface or the second ingress interface.

In the embodiment of the present application, the second ingress interface is any ingress interface on the forwarding node except the first ingress interface, and the number of the second ingress interfaces is not limited here. The fourth message is any message of the service flow received by the forwarding node in the current statistical period, and carries iFIT message header, that is, the fourth message is iFIT message.

After receiving the first message, the forwarding node can continue to receive the message of the service flow through any one of the interfaces on the forwarding node. In the embodiment of the application, iFIT messages received by the forwarding node before receiving the first time delay dyeing message are first messages, and iFIT messages received by the forwarding node after receiving the first time delay dyeing message are fourth messages.

After receiving the fourth message, the forwarding node may parse the received fourth message, and determine whether the fourth message is a delay dyeing message based on the value of the D field in the iFIT message header carried by the fourth message. If the value of the D field is 1, the forwarding node determines that the fourth message is a delay dyeing message, that is, the fourth message is another delay dyeing message processed by the forwarding node in the current statistical period (that is, not the received first delay dyeing message), and the fourth message may be a delay dyeing original message or a delay dyeing copy message.

In the embodiment of the application, the forwarding node can determine whether the current delay dyed message is the first delay dyed message or not, that is, determine whether the current delay dyed message is the first message or the fourth message.

In the mode 1, the forwarding node may count the number of delay dyed messages received in the current counting period, and determine whether the current delay dyed message is the first delay dyed message according to the counted number. If the counted number of the forwarding nodes is 0, the forwarding nodes can determine that the current delay dyed message is the second message and add 1 to the counted number, and if the counted number of the forwarding nodes is greater than 0 (such as 1,2 and the like), the forwarding nodes can determine that the current delay dyed message is the fourth message and add 1 to the counted number.

In mode 2, the forwarding node may record an identification value, which indicates whether a delay dyeing packet has been received in the current statistical period. If the identification value is 0, the forwarding node determines that the delay dyeing message is not received in the current statistical period, the current delay dyeing message is a second message, the identification value is set to be 1, and if the identification value is 1, the forwarding node determines that the delay dyeing message is received in the current statistical period, and the current delay dyeing message is a fourth message.

In the mode 3, the forwarding node may record each delay dyeing message received in the current statistics period, and record the type of each message and the ingress interface for receiving the message. For example, when the forwarding node receives the delay dyeing replication message through the first ingress interface and then receives the delay dyeing replication message through the second ingress interface, the forwarding node may record that the first delay dyeing message is the delay dyeing replication message, the received ingress interface is the first ingress interface, and record that the second delay dyeing message is the delay dyeing replication message, and the received ingress interface is the second ingress interface; in this case, if the forwarding node receives the current delay dyeing message through the first ingress interface, the same second ingress interface or another second ingress interface, the forwarding node determines that the delay dyeing message has been received in the current statistical period, the current delay dyeing message is a fourth message, records that the current delay dyeing message is a third delay dyeing message, and records the type of the message and the ingress interface of the received message.

If the delay dyeing message is not recorded in the forwarding node, the forwarding node determines that the delay dyeing message is not received in the current statistical period, the current delay dyeing message is a second message, the current delay dyeing message is recorded as a first delay dyeing message, and the type of the message and the input interface of the received message are recorded.

According to the difference of the ingress interfaces of the forwarding node for receiving the fourth message, the case that the forwarding node records the timestamp of receiving the fourth message can be specifically divided into the following two cases.

In case 1, the ingress interface of the fourth packet is a second ingress interface, i.e. the forwarding node receives the fourth packet through the second ingress interface. In this case, the forwarding node sends a third timestamp to the analyzer, so that the analyzer measures the delay index of the link where the forwarding node is located according to the first timestamp, the second timestamp (or the sixth timestamp) and the third timestamp, where the third timestamp is a timestamp of receiving the fourth message through the second ingress interface.

In the embodiment of the present application, the forwarding node records a timestamp (i.e., a third timestamp) of receiving the fourth message, where the third timestamp corresponds to the second ingress interface, and is a timestamp recorded by the forwarding node at an MP corresponding to the second ingress interface. And after the current statistical period is finished, the forwarding node reports the recorded first time stamp, a plurality of second time stamps (or a sixth time stamp corresponding to the second output interface) and the third time stamp to the analyzer. Furthermore, the analyzer may measure the delay index between the first ingress interface, the second ingress interface, and the plurality of egress interfaces, to obtain the delay inside the forwarding node.

The downstream forwarding node may also receive the second packet forwarded by the upstream forwarding node as a fourth packet. The analyzer may measure the time delay index between forwarding nodes according to time stamps reported by other forwarding nodes on the link where the current forwarding node is located. For example, the analyzer may measure a time delay index between the second ingress interface on the fourth packet and the egress interface on the previous hop device that forwards the corresponding second packet according to the third timestamp reported by the current forwarding node and the second timestamp reported by the previous hop device of the current forwarding node. Similar to the above procedure for measuring the delay index based on the first timestamp and the second timestamp (or the sixth timestamp), see in particular the relevant description of the above section S63.

In case 2, the ingress interface of the fourth packet is the first ingress interface, that is, the forwarding node receives the fourth packet through the first ingress interface. In this case, if the fourth packet does not carry the replication identifier, the forwarding node updates the first timestamp to a fourth timestamp, where the fourth timestamp is a timestamp of the fourth packet received through the first ingress interface.

In the embodiment of the application, the forwarding node judges whether the fourth message carries the copy identifier, that is, judges whether the first message is a delay dyeing copy message. When the forwarding node determines that the fourth message does not carry the replication identifier, the fourth message is a time-delay dyeing original message, that is, the first message is a time-delay dyeing replication message, and the forwarding node updates the first timestamp corresponding to the first input interface to a timestamp (that is, a fourth timestamp) of receiving the fourth message, that is, updates the first timestamp to a timestamp corresponding to the time-delay dyeing original message.

After the current statistics period is finished, the forwarding node reports the updated first time stamp and the second time stamp corresponding to each output interface (or the sixth time stamp corresponding to the second output interface) to the analyzer. Furthermore, the analyzer may measure the delay index of the link where the forwarding node is located, and see the description of the step S63.

In the embodiment of the application, when the service flow corresponds to one output interface, the forwarding node can report the updated first timestamp and the second timestamp (or the sixth timestamp) corresponding to one output interface to the analyzer after the current statistics period is finished.

In the case 1 and the case 2, after receiving the fourth message, the forwarding node may determine whether the fourth message carries the copy identifier.

When the forwarding node determines that the fourth message carries the copy identifier, the fourth message is a delay dyeing copy message, and the forwarding node can discard the fourth message and does not process and forward the fourth message so as to save the processing resources of the forwarding node.

When the forwarding node determines that the fourth message does not carry the copy identification, the fourth message is a time delay dyeing original message, and the forwarding node can forward the fourth message to obtain the processed fourth message. When the forwarding node is an intermediate node, the forwarding node may forward the processed fourth packet through a first output interface corresponding to the service flow, where the first output interface is any output interface corresponding to the service flow on the forwarding node, and a process of forwarding the fourth packet by the forwarding node may be specifically described in the above step S62. When the forwarding node is an egress node, the forwarding node may strip the iFIT message header carried by the fourth message to obtain a fifth message, forward the fifth message through the second egress interface corresponding to the service flow, and send the updated first timestamp and the updated sixth timestamp (or the first timestamp, the third timestamp and the sixth timestamp) to the analyzer after the current statistics period is finished, which can be specifically described in the above step S126, the related description of the case 1 and the case 2.

When the forwarding node is an intermediate node, before forwarding the fourth message, the forwarding node may update the second timestamp corresponding to the first outgoing interface to a fifth timestamp, where the fifth timestamp is a timestamp for forwarding the fourth message through the first outgoing interface, that is, update the corresponding second timestamp to a timestamp corresponding to the delay dyeing original message.

In case 1, after the current statistics period is over, the forwarding node may send the first timestamp, the updated second timestamp corresponding to the first outgoing interface, and the second timestamps corresponding to other outgoing interfaces except the first outgoing interface to the analyzer, so that the analyzer measures the delay index of the link where the forwarding node is located according to the timestamps reported by the forwarding node.

Under the condition 2, after the current statistics period is finished, the forwarding node can send the updated first timestamp, the updated second timestamp corresponding to the first outgoing interface and the second timestamps corresponding to other outgoing interfaces except the first outgoing interface to the analyzer, so that the analyzer measures the time delay index of the link where the forwarding node is located according to the timestamps reported by the forwarding node. The process of measuring the delay index by the analyzer is described in detail in the above-mentioned related description.

In the embodiment of the application, when the service flow corresponds to one output interface, the forwarding node can forward the fourth message after processing through the one output interface, update the second timestamp corresponding to the one output interface to the timestamp for forwarding the fourth message through the one output interface, and send the first timestamp and the updated second timestamp corresponding to the one output interface to the analyzer.

In the embodiment of the application, after determining that the fourth message is the delay dyeing message of the current statistical period, the forwarding node can process the fourth message as the first message without discarding the fourth message after the fourth message carries the replication identification, record a plurality of time stamps, and report the recorded time stamps to the analyzer, so that the analyzer measures the delay index according to the plurality of time stamps.

In the embodiment of the application, when the service flow corresponds to a plurality of output interfaces, the forwarding node can copy the fourth message, forward the original fourth message and the copied fourth message through the plurality of output interfaces, so as to record the time stamp of forwarding the fourth message through the plurality of output interfaces, and further the analyzer can measure the time delay index between the input interface for receiving the fourth message and the plurality of output interfaces.

In the embodiment of the present application, after receiving the fourth message, the forwarding node may further receive the fourth message through the first ingress interface, the same second ingress interface, or another second ingress interface, and perform the foregoing processing on the fourth message, which is not described herein again.

In the technical scheme provided by the embodiment of the application, when a plurality of input interfaces of the forwarding node are provided, as the delay dyeing messages are forwarded on a plurality of links, the forwarding node can receive the delay dyeing messages, and before receiving the fourth message, the forwarding node already receives the first message and forwards the second message, that is, the delay dyeing messages are forwarded once through each output interface corresponding to the service flow, and the delay index of the link where each output interface is located can be measured. On the basis, the forwarding node can judge whether other received delay dyed messages are duplicate messages or not, and only forwards delay dyed messages which are not duplicate messages, so that equipment processing and forwarding resources are further saved.

In some embodiments, the forwarding node may further measure a packet loss indicator, and the delay measurement method may further include counting a second number and a third number in a current statistics period, where the second number is a number of sixth packets of the received service flow, the third number is a number of forwarded sixth packets, the sixth packets do not carry a duplication identifier, the duplication identifier indicates that the packets are duplicated, and sending the second number and the third number to the analyzer, so that the analyzer measures the packet loss indicator of the link where the forwarding node is located according to the second number and the third number.

In the embodiment of the present application, the sixth message is any iFIT message of the service flow, and according to the current statistical period, the sixth message is a packet loss dyeing message or a packet loss non-dyeing message. And if the current counting period is a counting period of the non-dyeing message, the sixth message is a packet loss non-dyeing message. The sixth message does not carry the duplicate identity, i.e., the sixth message is not a duplicate message. The forwarding node may count the number of the sixth packets (e.g., the second number) received in the current statistics period, count the number of the sixth packets (e.g., the third number) forwarded in the current statistics period, and report the second number and the third number to the analyzer after the current statistics period ends.

In the embodiment of the application, the second number and the third number can be counted by other forwarding nodes on the link where the forwarding nodes are located, and the second number and the third number are respectively reported to the analyzer, and the analyzer calculates the packet loss number and the packet loss rate among the forwarding nodes according to the second number and the third number reported by the forwarding nodes.

In the technical scheme provided by the embodiment of the application, the forwarding node only counts iFIT message quantity of the message which is not duplicated, so as to accurately calculate the packet loss index, and ensure the accuracy of the packet loss index while measuring the time delay index under a plurality of links.

The delay measurement method provided by the embodiment of the application is described in detail below with reference to fig. 13 to 16.

Fig. 13 is a first flowchart of delay measurement according to an embodiment of the present application, applied to an ingress node, including the following steps:

in step S131, the traffic flow arrives at the ingress node in the statistics period.

In the embodiment of the application, the ingress node receives the message of the service flow in the statistical period.

And S132, packaging according to the original flow to generate a time delay dyeing original message.

In the embodiment of the application, the ingress node encapsulates iFIT the header of the received service flow, performs delay dyeing and packet loss dyeing, i.e., performs delay dyeing on the first received message, generates a delay dyed original message (e.g., the first message), and records timestamp information (e.g., a first timestamp and a second timestamp) of the received and forwarded message.

Step S133, judging whether the number N of interfaces is larger than 1, if so, executing step S134-step S136, and if not, executing step S137.

In step S134, the delay dyeing original message is duplicated by N-1, and the Dup field of the duplicated message is set to be 1.

In the embodiment of the application, an ingress node replicates a time-delay dyed original message to obtain N-1 time-delay dyed duplicate messages, and records time stamp information when replication is completed or records time stamp information (such as a second time stamp) for forwarding each time-delay dyed duplicate message.

Step S135, the original message is dyed according to the original flow forwarding delay and the output interface is recorded.

In the embodiment of the application, the ingress node determines an egress interface (such as a third egress interface) corresponding to the service flow, and forwards the delay dyeing original message from the egress interface.

And step S136, forwarding the delay dyeing replication messages from other N-1 output interfaces respectively.

Step S137, the original message is dyed according to the original flow forwarding delay.

The steps S131 to S137 can be specifically described with reference to the portions of FIGS. 6 to 12.

After encapsulating iFIT the header and forwarding the delay dyed message to the intermediate node, the intermediate node processes the delay dyed message, as shown in fig. 14, for the intermediate node in the load sharing scenario. The intermediate node comprises M input interfaces and N output interfaces. The M ingress interfaces correspond to M intermediate MPs in the iFIT traffic ingress direction, denoted MP i (i=1, 2,., M-1, M), namely MP 1, MP 2,..mpm), the intermediate node can receive at least one delay dye message from each ingress interface. N output interfaces correspond to N intermediate MPs in the iFIT traffic output direction, and are respectively denoted as MP j (i=m+1, m+2,..m+n-1, m+n), (i.e., MP m+1, MP m+2,..mp m+n), where the N output interfaces are in a load sharing relationship.

In the load sharing scene, the processing principle of the intermediate node on all delay dyeing messages received in the same statistical period is that the first delay dyeing message is necessarily forwarded and copied (when the number of outgoing interfaces is more than 1), the delay dyeing original message is necessarily forwarded, and other delay dyeing messages are discarded. The second flow chart of the delay measurement shown in fig. 15 is applied to the intermediate node, and includes the following steps:

Step S151, a1 st time delay dyeing message is received in a statistical period.

In the embodiment of the application, the intermediate node receives the message of the service flow in the statistical period, processes the received 1 st time delay dyeing message (such as the first message) in the statistical period as follows, and records the timestamp information (such as the first timestamp and the second timestamp) of the received and forwarded message.

Step S152, judging whether the number N of interfaces is larger than 1, if so, executing step S153 to step S155, and if not, executing step S156.

In step S153, the 1 st delay dyeing message is duplicated by N-1, and the Dup field of the duplicated message is set to be 1.

In the embodiment of the application, an intermediate node replicates delay dyeing messages to obtain N-1 delay dyeing replication messages, and records time stamp information when replication is completed or records time stamp information (such as a second time stamp) for forwarding each delay dyeing replication message.

And step S154, forwarding the 1 st time delay dyeing message according to the original flow and recording an output interface of the 1 st time delay dyeing message.

In the embodiment of the application, the intermediate node determines an output interface (such as a third output interface) corresponding to the service flow, and forwards the 1st time delay dyeing message from the output interface.

Step S155, forwarding the delay dyeing replication messages from other N-1 output interfaces, and executing step S157.

Step S156, forwarding the delay dyed original message according to the original procedure, and executing step S157.

Step S157, determine whether other delay dyeing messages are received in the statistical period. If yes, go to step S158, otherwise go to step S1511.

In the embodiment of the application, the intermediate node continues to receive the message of the service flow in the statistics period, processes the received other delay dyeing messages (such as the fourth message) as follows, and records the timestamp information (such as the third timestamp or the fourth timestamp) of the received message.

Step S158, judging whether the delay dyeing message is a delay dyeing original message. If not, step S159 is executed, and if yes, step S1510 is executed.

In the embodiment of the application, the intermediate node judges whether the message carries the copy identifier. If the copy mark is carried, determining that the message is a time delay dyeing copy message, namely, not a time delay dyeing original message, and if the copy mark is not carried, determining that the message is a time delay dyeing original message

Step S159, discard the delay dyeing message, and return to step S157.

Step S1510, the time delay dyeing original message is forwarded according to the original procedure, and step S157 is executed back.

In the embodiment of the application, the intermediate node determines an output interface (such as a first output interface) corresponding to the service flow, updates the timestamp information corresponding to the output interface to the timestamp information (such as a fifth timestamp) for forwarding the delay dyeing message, and forwards the delay dyeing message from the output interface.

Step S1511, it is determined whether the statistical period is ended. If not, the step S157 is executed if the statistical period is not ended, and if yes, the step S1512 is executed if the statistical period is ended.

In the embodiment of the application, under the condition that the current statistical period is not ended, the intermediate node always executes the judgment of the step S157, executes the steps S158-S1511 until the current statistical period is ended, and uploads the recorded time stamp information to the analyzer. When the next statistics period starts, the intermediate node starts from step S151, and continues to process the packets of the traffic flow in the new statistics period.

Step S1512, determining that all delay dyeing messages in the statistical period are processed.

The above steps S151 to S1512 can be specifically described with reference to the above FIG. 6 to FIG. 11.

The processing mechanism of the time-lapse dyeing message is described below by taking iFIT network model shown in fig. 16 as an example, and the iFIT network model includes 10 forwarding nodes, i.e., R1 to R10. For ease of description, the delay dye duplicate message is denoted as 1 and the delay dye original message is denoted as 0 in fig. 16.

According to the number of the input interfaces and the output interfaces on each forwarding node, the four cases of single input single output, single input N output (N > 1), M input single output (M > 1) and M input N output (M >1 and N > 1) can be divided.

R5 belongs to the single-in single-out situation. When the time delay dyeing copy message is received (R5), the forwarded message is also the time delay dyeing copy message, and when the time delay dyeing original message is received, the forwarded message is also the time delay dyeing original message.

R2, R3 and R4 are in the single-in N-out case. When the time delay dyeing original message is received (such as R2), the forwarded message is 1 time delay dyeing original message and N-1 (1) time delay dyeing copy messages, and when the time delay dyeing copy messages are received (such as R3 and R4), the forwarded message is N (2) time delay dyeing copy messages, namely, each message forwarded on an output interface is 1 time delay dyeing copy message.

R8 and R9 belong to the M single entry and single exit case. When the 1 st time delay dyeing copying message is received firstly, then the 2 nd time delay dyeing original message is received (as R8), the 1 st time delay dyeing copying message is forwarded firstly, then the 1 st time delay dyeing original message is forwarded, when the 1 st time delay dyeing copying message is received firstly, then the 2 nd time delay dyeing copying message is received (as R9), the forwarded message is the 1 st time delay dyeing copying message, and the received 2 nd time delay dyeing copying message is discarded, and when the 1 st time delay dyeing original message is received firstly, then the 2 nd time delay dyeing copying message is received, the forwarded message is the 1 time delay dyeing original message. That is, if the received message contains 1 delay dyeing original message, the forwarded message is 1 delay dyeing copy message and 1 delay dyeing original message (the received 1 st delay dyeing message is delay dyeing copy message), or is only 1 delay dyeing original message (the received 1 st delay dyeing message is delay dyeing original message), if the received message is delay dyeing copy message, the forwarded message is 1 delay dyeing copy message.

R6 and R7 belong to the M in-N out case. When the 1 st time delay dyeing original message is received firstly, then the 2 nd time delay dyeing copy message is received (R6, for example), the forwarded message is the 1 st time delay dyeing original message and N-1 (1) time delay dyeing copy messages, and the received 2 nd time delay dyeing copy message is discarded, when the 1 st time delay dyeing copy message is received firstly, then the 2 nd time delay dyeing copy message is received (R7, for example), the forwarded message is the 2 nd time delay dyeing copy message, and the received 2 nd time delay dyeing copy message is discarded, and when the 1 st time delay dyeing copy message is received firstly, then the 2 nd time delay dyeing original message is received, the 2 time delay dyeing copy messages are forwarded firstly, and then the 1 time delay dyeing original message is forwarded. That is, if the received message contains 1 delay dyeing original message, the forwarded message is N-1 delay dyeing copy message and 1 delay dyeing original message (the received 1 st delay dyeing message is a delay dyeing original message), or is N-1 delay dyeing copy message and 1 delay dyeing copy message+delay dyeing original message (the received 1 st delay dyeing message is a delay dyeing copy message), and if the received message is a delay dyeing copy message, the forwarded message on each output interface is 1 delay dyeing copy message.

And after the intermediate node processes and forwards the message, forwarding the message to the output node. On the outbound node, in order to ensure that the total number of the original messages obtained after the outbound node is unpacked is unchanged, the delay dyeing messages need to be filtered in the incoming direction of the outbound node, and the delay dyeing copy messages with the Dup field set 1 are directly discarded and are not unpacked.

In addition, when the packet loss index is measured, the delay dyeing replication message of the Dup field 1 cannot be counted in the total number of the received packets in the counting period, so that the accuracy of measuring the packet loss index is ensured.

The technical scheme provided by the embodiment of the application supports the time delay statistics on all load sharing links under the load sharing scene, and each packet receiving statistics period on each load sharing link has credible time stamp information. Meanwhile, an R field next to a D field in a iFIT message header is named as a Dup field and is used as a delay dyeing message copying identifier, and the problem of loss of timestamp information of a load sharing scene iFIT is solved by a delay dyeing message copying method in the load sharing scene. Compared with the technical scheme that each iFIT message carries the time stamp information, the scheme can save equipment resources, reduce the time delay of message forwarding and meet the requirement of 5G service on low time delay.

Corresponding to the above-mentioned delay measurement method, the embodiment of the present application further provides a delay measurement device, which is applied to a forwarding node, as shown in fig. 17, where the delay measurement device includes:

A receiving module 171, configured to receive, through a first ingress interface, a first packet of a service flow;

The processing module 172 is configured to forward the first message to obtain a second message if the forwarding node is an ingress node or an intermediate node;

The copying module 173 is configured to copy the second packet to obtain a first number of third packets if the second packet is a delay dyeing packet in a current statistics period and the service flow corresponds to a plurality of output interfaces, where the first number is a number of the plurality of output interfaces minus 1;

And the sending module 174 is configured to forward the second packet and the first number of third packets through the plurality of outgoing interfaces, and send a first timestamp and a second timestamp corresponding to each outgoing interface to the analyzer, so that the analyzer measures a delay index of a link where the forwarding node is located according to the first timestamp and the second timestamp corresponding to each outgoing interface, where the first timestamp is a timestamp of receiving the first packet through the first ingress interface, and the second timestamp corresponding to each outgoing interface is a timestamp of forwarding the second packet or the third packet through each outgoing interface.

In some embodiments, the forwarding node is an ingress node, the first message is an original message, and the processing module 172 may be specifically configured to encapsulate iFIT the header of the first message, and perform delay dyeing on the encapsulated first message to obtain the second message.

In some embodiments, the forwarding node is an intermediate node or an egress node, and the receiving module 171 may be further configured to receive, after receiving the first packet, a fourth packet of the traffic flow through the first ingress interface or the second ingress interface;

The sending module 174 may be further configured to send a third timestamp to the analyzer if the fourth packet is a delay dyed packet in the current statistics period and the ingress interface of the fourth packet is the second ingress interface, so that the analyzer measures the delay index of the link where the forwarding node is located according to the first timestamp, the second timestamp and the third timestamp corresponding to each egress interface, and the third timestamp is a timestamp for receiving the fourth packet through the second ingress interface.

In some embodiments, the sending module 174 may be further configured to update the first timestamp to a fourth timestamp if the fourth message is a delay dyeing message in the current statistics period, the input interface of the fourth message is a first input interface, the fourth message does not carry a replication identifier, the fourth timestamp is a timestamp of receiving the fourth message through the first input interface, and the replication identifier indicates that the message is a replicated message;

The sending module 174 may be specifically configured to send the updated first timestamp and the second timestamp corresponding to each outgoing interface to the analyzer.

In some embodiments, the sending module 174 may be further configured to discard the fourth message if the fourth message is a delay dyeing message in the current statistics period and the fourth message carries a duplication identifier, and forward the fourth message through a first output interface corresponding to the traffic flow if the fourth message is a delay dyeing message in the current statistics period and the fourth message does not carry a duplication identifier.

In some embodiments, the above-described transmitting module 174 may also be configured to:

If the fourth message is a delay dyeing message in the current statistical period and the fourth message does not carry a replication identification, updating a second timestamp corresponding to the first output interface into a fifth timestamp, wherein the fifth timestamp is a timestamp for forwarding the fourth message through the first output interface;

The sending module 174 may be specifically configured to send the first timestamp, the updated second timestamp corresponding to the first outgoing interface, and the second timestamps corresponding to other outgoing interfaces other than the first outgoing interface to the analyzer.

In some embodiments, the processing module 172 may be further configured to, if the forwarding node is an egress node, the first packet is a delay dyeing packet in a current statistical period, and the first packet does not carry a replication identifier, strip a iFIT packet header carried by the first packet to obtain a sixth packet, where the replication identifier indicates that the packet is a replicated packet;

The sending module 174 may be further configured to, if the forwarding node is an egress node, the first packet is a delay dyeing packet in a current statistics period, and the first packet does not carry a replication identifier, forward a sixth packet through a second egress interface corresponding to the traffic flow, and send a first timestamp and a sixth timestamp to the analyzer, so that the analyzer measures, according to the first timestamp and the sixth timestamp, a delay indicator of a link where the forwarding node is located, and the sixth timestamp is a timestamp for forwarding the sixth packet through the second egress interface;

The sending module 174 may be further configured to discard the first packet if the forwarding node is an egress node, the first packet is a delay dyeing packet in the current statistical period, and the first packet carries a replication identifier, and send a first timestamp to the analyzer.

In some embodiments, the sending module 174 may be further configured to count a second number and a third number in the current statistics period, where the second number is a number of sixth packets for receiving the traffic flow, the third number is a number of forwarding the sixth packets, the sixth packets do not carry a replication identifier, the replication identifier indicates that the packets are replicated, and send the second number and the third number to the analyzer, so that the analyzer measures the packet loss indicator of the link where the forwarding node is located according to the second number and the third number.

In some embodiments, the first message and/or the second message carries iFIT a header, and the iFIT header includes a Dup field, where the Dup field carries a replication identifier, and the replication identifier indicates that the message is a replicated message.

The embodiment of the present application further provides a forwarding node, as shown in fig. 18, including a processor 181 and a machine-readable storage medium 182, where the machine-readable storage medium 182 stores machine-executable instructions capable of being executed by the processor 181, and the processor 181 is caused by the machine-executable instructions to implement any of the delay measurement methods applied to the forwarding node.

The machine-readable storage medium 182 may include random access Memory (Random Access Memory, RAM) or may include Non-Volatile Memory (NVM), such as at least one disk Memory. Alternatively, the machine-readable storage medium 182 may also be at least one storage device located remotely from the aforementioned processor.

The Processor 181 may be a general purpose Processor including a central processing unit (Central Processing Unit, CPU), a network Processor (Network Processor, NP), etc., or may be a digital signal Processor (DIGITAL SIGNAL Processor, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), field-Programmable gate array (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware components.

In yet another embodiment of the present application, there is also provided a computer readable storage medium having stored therein a computer program which when executed by a processor implements the steps of any of the above-described delay measurement methods.

In yet another embodiment of the present application, there is also provided a computer program product containing instructions which, when run on a computer, cause the computer to perform any of the delay measurement methods of the above embodiments.

In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present application, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, by wired (e.g., coaxial cable, optical fiber, digital Subscriber Line (DSL)), or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid state disk (Solid STATE DISK, SSD)), etc.

It should be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises an element.

In this specification, each embodiment is described in a related manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for the apparatus, forwarding node, computer readable storage medium and computer program product embodiments, the description is relatively simple, as it is substantially similar to the method embodiments, as relevant see the section description of the method embodiments.

The foregoing description is only of the preferred embodiments of the present application and is not intended to limit the scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application are included in the protection scope of the present application.

Claims

1. A method of latency measurement applied to a forwarding node, the method comprising:

Receiving a first message of a service flow through a first access interface;

2. The method of claim 1, wherein the forwarding node is an ingress node, the first message is an original message, and the forwarding the first message to obtain a second message comprises:

measuring iFIT a message header for the first message encapsulation band flow information;

and performing delay dyeing on the packaged first message to obtain a second message.

3. The method of claim 1, wherein the forwarding node is an intermediate node or an egress node, and wherein after receiving the first message, the method further comprises:

Receiving a fourth message of the service flow through the first inlet interface or the second inlet interface;

And if the fourth message is the delay dyeing message of the current statistical period and the input interface of the fourth message is the second input interface, sending a third timestamp to an analyzer, so that the analyzer measures the delay index of the link where the forwarding node is located according to the first timestamp, the second timestamp corresponding to each output interface and the third timestamp, and the third timestamp is the timestamp for receiving the fourth message through the second input interface.

4. A method according to claim 3, characterized in that the method further comprises:

If the fourth message is the delay dyeing message of the current statistics period, the input interface of the fourth message is the first input interface, and the fourth message does not carry a copy identifier, updating the first timestamp to a fourth timestamp, wherein the fourth timestamp is a timestamp of receiving the fourth message through the first input interface, and the copy identifier indicates that the message is a copied message;

The step of sending the first timestamp and the second timestamp corresponding to each output interface to the analyzer comprises the following steps:

And sending the updated first time stamp and the second time stamp corresponding to each output interface to the analyzer.

5. A method according to claim 3, characterized in that the method further comprises:

if the fourth message is the delay dyeing message of the current statistical period and the fourth message carries a duplication mark, discarding the fourth message, wherein the duplication mark indicates that the message is a duplicated message;

And if the fourth message is the delay dyeing message of the current statistical period and the fourth message does not carry the replication identification, forwarding the fourth message through a first output interface corresponding to the service flow.

6. The method of claim 5, wherein the method further comprises:

If the fourth message is the delay dyeing message of the current statistics period and the fourth message does not carry the replication identification, updating a second timestamp corresponding to the first output interface into a fifth timestamp, wherein the fifth timestamp is a timestamp for forwarding the fourth message through the first output interface;

And sending the first timestamp, the updated second timestamp corresponding to the first outgoing interface and the second timestamps corresponding to other outgoing interfaces outside the first outgoing interface to an analyzer.

7. The method according to claim 1, wherein the method further comprises:

If the forwarding node is an outgoing node, the first message is a delay dyeing message in a current statistical period, and the first message does not carry a replication identification, stripping a iFIT message header carried by the first message to obtain a fifth message, wherein the replication identification indicates that the message is a replicated message; forwarding the fifth message through a second outgoing interface corresponding to the service flow, and sending a first timestamp and a sixth timestamp to an analyzer, so that the analyzer measures a time delay index of a link where the forwarding node is located according to the first timestamp and the sixth timestamp, wherein the sixth timestamp is a timestamp for forwarding the fifth message through the second outgoing interface;

And if the forwarding node is an outgoing node, the first message is a delay dyeing message of the current statistical period, and the first message carries the copy identifier, discarding the first message, and sending a first timestamp to an analyzer.

8. The method according to claim 1, wherein the method further comprises:

Counting a second number and a third number in the current counting period, wherein the second number is the number of sixth messages for receiving the service flow, the third number is the number of forwarding the sixth messages, the sixth messages do not carry a replication identification, and the replication identification indicates that the messages are replicated messages;

And sending the second quantity and the third quantity to an analyzer, so that the analyzer measures the packet loss index of the link where the forwarding node is located according to the second quantity and the third quantity.

9. The method according to any one of claims 1-8, wherein the first message and/or the second message carries iFIT a header, the iFIT header includes a duplicate Dup field, the Dup field carries a duplicate identifier, and the duplicate identifier indicates that the message is a duplicate message.

10. A delay measurement apparatus for use with a forwarding node, the apparatus comprising:

11. The apparatus of claim 10, wherein the forwarding node is an intermediate node or an egress node, and the receiving module is further configured to receive a fourth packet of the traffic flow through the first ingress interface or the second ingress interface after receiving the first packet;

and the sending module is further configured to send a third timestamp to an analyzer if the fourth packet is the delay dyeing packet in the current statistics period and the ingress interface of the fourth packet is the second ingress interface, so that the analyzer measures a delay index of a link where the forwarding node is located according to the first timestamp, the second timestamp corresponding to each egress interface, and the third timestamp is a timestamp of receiving the fourth packet through the second ingress interface.

12. The apparatus of claim 10, wherein the processing module is further configured to, if the forwarding node is an egress node, strip a iFIT header carried by the first packet to obtain a sixth packet, where the first packet is a delay dyeing packet in a current statistical period and the first packet does not carry a replication identifier, and the replication identifier indicates that the packet is a replicated packet;

The sending module is further configured to, if the forwarding node is an egress node, the first packet is a delay dyeing packet in a current statistics period, and the first packet does not carry a replication identifier, forward the sixth packet through a second egress interface corresponding to the service flow, and send a first timestamp and a sixth timestamp to an analyzer, so that the analyzer measures, according to the first timestamp and the sixth timestamp, a delay indicator of a link where the forwarding node is located, and the sixth timestamp is a timestamp for forwarding the sixth packet through the second egress interface;

The sending module is further configured to discard the first packet if the forwarding node is an egress node, the first packet is a delay dyeing packet in a current statistical period, and the first packet carries the replication identifier, and send a first timestamp to an analyzer.

13. The apparatus of claim 10, wherein the transmitting module is further configured to:

14. A forwarding node comprising a processor and a machine-readable storage medium storing machine-executable instructions executable by the processor to cause the processor to implement the method of any of claims 1-9.

15. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a computer program which, when executed by a processor, implements the method of any of claims 1-9.