CN112152865B

CN112152865B - Network performance measuring device and method

Info

Publication number: CN112152865B
Application number: CN201910564926.6A
Authority: CN
Inventors: 周先涛
Original assignee: ZTE Corp
Current assignee: ZTE Corp
Priority date: 2019-06-27
Filing date: 2019-06-27
Publication date: 2023-06-27
Anticipated expiration: 2039-06-27
Also published as: CN112152865A; WO2020259113A1

Abstract

The embodiment of the invention discloses a network performance measuring device and a method, wherein one of the network performance measuring devices comprises: the processor and 2N counters, wherein the 2N counters comprise N counter Count An and N counter Count Bn, N is An even multiple of 2, and N takes a natural number from 0 to N-1; the coloring mark of the message is N, and a counter Count An and a counter Count Bn correspondingly calculate the number of the coloring mark message; the coloring period is T, and the reading period is N x T; the processor is used for sequentially counting N corresponding Count An according to the coloring mark of the message in An odd number of N x T periods; and in an even number of N T periods, sequentially counting N corresponding Count Bns according to the coloring marks of the message. The validity and reliability of the test performance data based on RFC8321 are improved.

Description

Network performance measuring device and method

Technical Field

Embodiments of the present invention relate to the field of, but are not limited to, PTN (Packet Transport Network )/IP ran (IP Radio Access Network, IP radio access network), and more particularly to a network performance measurement apparatus and method.

Background

Today, most service provider networks carry content that is highly sensitive to packet loss, delay and jitter. In view of this, service providers need methods and tools to monitor and measure network performance, continuously enhancing customer experience. On the other hand, providing useful information management (e.g., quarantine network problems, troubleshooting, etc.) for improving network quality.

A number of operations, administration and maintenance (OAM, operation Administration and Maintenance), including performance monitoring techniques, are performed by standard deviation organizations (SDOs, standards Organization). The IPPM (IP Performance Metrics, IP performance index) working group is always dedicated to standard formulation of network traffic measurement analysis, and proposes multiple RFCs (Request For Comments, request documents) and internet protocols, which relate to various aspects of network traffic measurement analysis, including connectivity, unidirectional delay and packet loss, bidirectional delay and packet loss, delay jitter, and the like. The main focus of this work group is active (active) measurement techniques, which have some limitations in application. Such as unidirectional traffic, probe messages with different paths than the actual traffic, etc.

The RFC8321 provides an alternative coloring method for passive (passive) performance monitoring, as shown in fig. 1, where the method does not use any additional probe message, directly performs periodic coloring on a user message at a source node, recovers coloring at a destination node, and can monitor the number of service message sending and receiving packets on the whole forwarding path. For each traffic packet loss performance, the router needs to provide two counters, counter a and Counter B. Counter A counts messages carrying color A and Counter B counts messages carrying color B. During the coloring B period, the stable count of the coloring Counter A of the last round can be read; while during the coloring A period, the stable count of the last round of coloring Counter B can be read. The end-to-end packet loss performance or the packet loss performance of a certain section of the forwarding path can be calculated by comparing the performance values of the source, the sink and the intermediate nodes in the same period.

However, based on the packet loss performance monitoring realized by RFC8321, each router to be monitored is distributed with two counters Count A and Count B according to different coloring. In order to obtain stable Count, when reading the Count of the A period, the Count of the Count A is required to be stable, and the Count A can only be read near the middle time point of the B period, and the message of the A period before the reading is likely not ended, and the message of the next A period after the reading is started to Count again. For long periods, e.g. 10s, 30s or more, stable counting time points are relatively easy to obtain; however, for a shorter period, such as a 1s or millisecond monitoring period, the interval between counter stabilization is short and difficult to acquire.

Among them, RFC8321 also provides a coloring scheme for delay measurement, where a source node colors for the first message of each cycle, records the coloring time point, and resumes coloring at a destination node. The coloring message can be extracted and the time point can be recorded on the whole forwarding path. Under the condition that all routers on the path are time-synchronized, the time delay from end to end or the time delay performance of a certain section on the forwarding path can be calculated by comparing the time values of the same period of the source, the sink and the intermediate node.

However, delay performance monitoring based on RFC8321 also has the problem of acquiring a stable time point as the packet loss performance. In addition, for a scene with serious packet loss, as only one coloring time delay message exists in each period, the coloring time delay messages in a plurality of periods are possibly discarded, so that no time delay data exists for a long time. And for a long-period monitoring scene, as the number of colored time delay message samples is small, the performance data such as the maximum time delay, the minimum time delay, the average time delay, the jitter and the like obtained by statistics have larger deviation from the actual service condition.

Disclosure of Invention

In view of this, an embodiment of the present invention provides a network performance measurement device, including:

The processor and 2N counters, wherein the 2N counters comprise N counter Count An and N counter Count Bn, N is An even multiple of 2, and N takes a natural number from 0 to N-1; the coloring mark of the message is N, and a counter Count An and a counter Count Bn correspondingly calculate the number of the coloring mark message; the coloring period is T, and the reading period is N x T;

the processor is used for sequentially counting N corresponding Count An according to the coloring mark of the message in An odd number of N x T periods; and in an even number of N T periods, sequentially counting N corresponding Count Bns according to the coloring marks of the message.

The embodiment of the invention also provides a network performance measuring device, which comprises:

the processor and 2N counters, wherein the 2N counters comprise N counter Count An and N counter Count Bn, N is An even multiple of 2, and N takes a natural number from 0 to N-1; the coloring mark of the message comprises two types A and B; the coloring period is T, and the reading period is N x T; a counter Count An and a counter Count Bn correspondingly calculate the number of coloring marking messages in a 2T period;

the processor is used for counting the message colored as A in-T/2-3T/2 time into a corresponding counter Count A0 in an odd number of N x T periods; counting the message colored as B in the time of T/2-5T/2 into a corresponding counter Count A1; counting the message colored as A in 3T/2-7T/2 time into a corresponding counter Count A2; counting the message colored as B in the time of 5T/2-9T/2 into a corresponding counter Count A3; and so on until the reading period is finished;

In an even number of N-T periods, counting the messages colored as A in the time of-T/2-3T/2 into a corresponding counter Count B0; counting the message colored as B in the time of T/2-5T/2 into a corresponding counter Count B1; counting the message colored as A in 3T/2-7T/2 time into a corresponding counter Count B2; counting the message colored as B in the time of 5T/2-9T/2 into a corresponding counter Count B3; and so on until the end of the read cycle.

the coloring period is T, and the delay coloring messages in one period T are expanded into N; the N is 2 or even times of 2; the coloring marks of the message are N types; a counter Count is used for correspondingly marking the coloring time of a coloring marking message;

and the processor is used for coloring the first message started every T/N cycles in the T cycles, and counting the coloring time of the message into a corresponding counter Count.

the coloring period is T, and the delay coloring messages in one period T are expanded into N; the N is 2 or even times of 2; the coloring marks of the message are N types; a counter Count sequentially arranges the receiving time of a coloring mark message correspondingly marked according to a period T;

The processor is used for writing the receiving time of a coloring message into (receiving time/reading period)/the coloring period when the coloring period is lower than the reading period, then rounding downwards to obtain a corresponding counter, and counting the receiving time of the coloring message into the corresponding counter; when the coloring period is consistent with the reading period, writing the receiving time of a coloring message into (receiving time/reading period) N/coloring period, then rounding downwards to obtain a corresponding counter, and counting the receiving time of the coloring message into the corresponding counter.

The embodiment of the invention also provides a network performance measuring method which is applied to the network performance measuring device,

the network performance measurement apparatus includes: the processor and 2N counters, wherein the 2N counters comprise N counter Count An and N counter Count Bn, N is An even multiple of 2, and N takes a natural number from 0 to N-1; the coloring mark of the message is N, and a counter Count An and a counter Count Bn correspondingly calculate the number of the coloring mark message; the coloring period is T, and the reading period is N x T;

the processor sequentially counts N corresponding Count An according to the coloring marks of the message in An odd number of N x T periods; and in an even number of N T periods, sequentially counting N corresponding Count Bns according to the coloring marks of the message.

the network performance measurement apparatus includes: the processor and 2N counters, wherein the 2N counters comprise N counter Count An and N counter Count Bn, N is An even multiple of 2, and N takes a natural number from 0 to N-1; the coloring mark of the message comprises two types A and B; the coloring period is T, and the reading period is N x T; a counter Count An and a counter Count Bn correspondingly calculate the number of coloring marking messages in a 2T period;

the processor counts the message colored as A in-T/2-3T/2 time into a corresponding counter Count A0 in an odd number of N x T periods; counting the message colored as B in the time of T/2-5T/2 into a corresponding counter Count A1; counting the message colored as A in 3T/2-7T/2 time into a corresponding counter Count A2; counting the message colored as B in the time of 5T/2-9T/2 into a corresponding counter Count A3; and so on until the reading period is finished;

the network performance measurement apparatus includes: the coloring period is T, and the delay coloring messages in one period T are expanded into N; the N is 2 or even times of 2; a counter Count is used for correspondingly marking the coloring time of a coloring marking message;

and the processor colors the first message started every T/N cycles in the T cycle, and counts the coloring time of the message into a corresponding counter Count.

the network performance measurement apparatus includes: the coloring period is T, and the delay coloring messages in one period T are expanded into N; the N is 2 or even times of 2; a counter Count sequentially arranges the receiving time of a coloring mark message correspondingly marked according to a period T;

when the coloring period is lower than the reading period, the processor writes the receiving time of a coloring message into (receiving time/reading period)/the coloring period, then rounds down to obtain a corresponding counter, and the receiving time of the coloring message is counted into the corresponding counter; when the coloring period is consistent with the reading period, the processor writes the receiving time of a coloring message into (receiving time/reading period) N/coloring period, then rounds down to obtain a corresponding counter, and the receiving time of the coloring message is counted into the corresponding counter.

The technical scheme provided by the embodiment of the invention improves the validity and reliability of the test performance data based on RFC8321, and solves the problems of unstable short period test count, large calculation deviation caused by insufficient long period sample number and the like in the prior art.

Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.

Drawings

The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate and do not limit the invention.

FIG. 1 is a schematic diagram of an alternate coloring scheme of RFC 8321;

FIG. 2 is a schematic diagram of a network performance measurement apparatus according to an embodiment of the present invention;

FIG. 3 is a schematic diagram of a network performance measurement apparatus according to another embodiment of the present invention;

FIG. 4 is a schematic diagram of a network performance measurement system according to an embodiment of the present invention;

FIG. 5 is a diagram illustrating coloring of a message according to another embodiment of the present invention;

FIG. 6 is a diagram illustrating coloring of a message according to another embodiment of the present invention;

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

FIG. 8 is a schematic diagram of a network performance measurement apparatus according to an embodiment of the present invention;

FIG. 9 is a schematic diagram of a network performance measurement system according to an embodiment of the present invention;

FIG. 10 is a diagram illustrating coloring of messages according to another embodiment of the present invention;

fig. 11 is a flowchart of a network performance measurement method according to an embodiment of the present invention;

fig. 12 is a flowchart of a network performance measurement method according to another embodiment of the present invention;

fig. 13 is a flowchart of a network performance measurement method according to another embodiment of the present invention;

fig. 14 is a flowchart of a network performance measurement method according to another embodiment of the present invention;

fig. 15 is a flowchart of a network performance measurement method according to another embodiment of the present invention;

fig. 16 is a flowchart of a network performance measurement method according to another embodiment of the present invention.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail hereinafter with reference to the accompanying drawings. It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be arbitrarily combined with each other.

The steps illustrated in the flowchart of the figures may be performed in a computer system, such as a set of computer-executable instructions. Also, while a logical order is depicted in the flowchart, in some cases, the steps depicted or described may be performed in a different order than presented herein.

The main idea of the embodiment of the invention is to overcome the problems of larger calculation deviation and the like caused by unstable short period test count and insufficient long period sample number in the prior art by expanding the number of coloring marks and the number of counters, thereby improving the validity and the reliability of test performance data based on RFC 8321.

Fig. 2 is a schematic structural diagram of a network performance measurement device according to an embodiment of the present invention, and as shown in fig. 2, the network performance measurement device includes:

The network performance measuring device can be arranged in a router, a gateway, a switch and other equipment.

Fig. 3 is a schematic structural diagram of a network performance measurement device according to another embodiment of the present invention, and as shown in fig. 3, the network performance measurement device includes:

Wherein, the mark A is 0 and the mark B is 1.

Fig. 4 is a schematic structural diagram of a network performance measurement system according to an embodiment of the present invention, as shown in fig. 4, where the system includes:

the network manager and the source node and the destination node or the intermediate node for transmitting the message,

the source node comprises: a first processor and 2N counters;

the sink node or intermediate node comprises: a second processor and 2N counters;

the 2N counters comprise N counter Count An and N counter Count Bn, wherein N is An even multiple of 2, and N is a natural number from 0 to N-1; the coloring mark of the message is N, and a counter Count An and a counter Count Bn correspondingly calculate the number of the coloring mark message; the coloring period is T, and the reading period is N x T;

The first processor is used for coloring and sending the message; in An odd number of N-T periods, sequentially counting N corresponding Count An according to the coloring marks of the message; in an even number of N T periods, sequentially counting N corresponding Count Bns according to the coloring marks of the message;

the second processor is used for receiving the message; in An odd number of N-T periods, sequentially counting N corresponding Count An according to the coloring marks of the message; in an even number of N T periods, sequentially counting N corresponding Count Bns according to the coloring marks of the message;

and the network manager is used for reading the data of the counters in the source node and the sink node or the intermediate node at the intermediate point of every N x T periods and calculating the packet loss rate.

Wherein the network performance measuring device may be provided in the above-mentioned node.

Fig. 5 is a schematic diagram illustrating message coloring in another embodiment of the present invention. In this embodiment, the coloring period is T, the reading period is 4T, and each node transmitting data may be provided with a network performance measurement device, and each network performance measurement device is provided with 8 counters (CountA 0 to CountA3, countB0 to CountB 3).

As shown in fig. 5, in this embodiment, the coloring marks are of four types: 0000, 1111, 2222, 3333.

At the source node transmitting the data, the data blocks B (blocks) 1 to 16 are colored according to a coloring cycle, for example, the data Block B1 is colored 0000, the data Block B2 is colored 1111, the data Block B3 is colored 2222, the data Block B4 is colored 3333, and so on. In the odd number of 4T periods, the messages are respectively put into a Count A (Count A0-Count A3) according to coloring; in an even number of 4T cycles, messages are placed into Count B (CountB 0-CountB 3) according to coloring, respectively.

Similarly, in the sink node or the intermediate node for transmitting data, in an odd number of 4T periods, the messages are respectively put into Count a (Count a0 to Count a 3) according to coloring; in an even number of 4T cycles, messages are placed into CountB (CountB 0-CountB 3) according to the coloring.

Specifically, for a scenario supporting coloring number extension, the message coloring value is (current time/reading period)/coloring period, then the corresponding counter is determined by rounding down, and the message is counted into the corresponding counter according to the coloring value and parity period.

The network manager can read 4 groups of performance data of last 4T of each node on the transmission path at the middle time point of each 4T period, so as to calculate the packet loss rate. For example, data in the Count a (Count a0 to Count a 3) in the source node and data in the Count a (Count a0 to Count a 3) in the sink node may be in one-to-one correspondence to obtain four groups of packet loss numbers, and an average value, a maximum value or a minimum value may be taken as the packet loss rate.

In another embodiment of the present invention, the read cycle ratio can be further extended for a shorter coloring cycle T based on the above embodiment, for example, 10T, 100T, etc., and the number of coloring marks and the number of counters corresponding thereto need to be correspondingly extended.

Fig. 6 is a schematic diagram illustrating message coloring in another embodiment of the present invention. In this embodiment, the coloring period is T, the reading period is 4T, and each node transmitting data may be provided with a network performance measurement device, and each network performance measurement device is provided with 8 counters (CountA 0 to CountA3, countB0 to CountB 3).

Message coloring mainly marks certain specific fields of service messages, and the number of different service messages which can be marked is limited. The extreme case is that only 1 bit is available for marking, and only 0 and 1 can be colored, i.e. the marking pattern provided by RFC 8321. In such a scenario, the extended coloring flag number scheme provided by the above embodiments is not feasible.

To this end, the present embodiment provides an enhanced alternate coloring scheme. As shown in fig. 6, in this embodiment, there are two types of coloring marks: 0000, 1111,

at the source node transmitting the data, the data blocks B (blocks) 1 to 16 are colored in accordance with a coloring cycle, for example, the data Block B1 is colored 0000, the data Block B2 is colored 1111, the data Block B3 is colored 0000, the data Block B4 is colored 1111, and so on. Wherein, in the odd number of 4T periods, -T/2-3T/2 time, the message with the coloring of 0 is counted into CountA0; in the time of T/2-5T/2, counting the message with the coloring of 1 into CountA1; counting the message with the coloring value of 0 into CountA2 in the time of 3T/2-7T/2; in the time of 5T/2-9T/2, the message with the coloring of 1 is counted into CountA3. In an even number of 4T cycles, the count is similar to the odd number, except that the messages count into CountB 0-CountB 3.

Similarly, in the sink node or intermediate node transmitting data, in an odd number of 4T cycles, -T/2-3T/2 time, a message colored to 0 counts into CountA0; in the time of T/2-5T/2, counting the message with the coloring of 1 into CountA1; counting the message with the coloring value of 0 into CountA2 in the time of 3T/2-7T/2; in the time of 5T/2-9T/2, the message with the coloring of 1 is counted into CountA3. In an even number of 4T cycles, the count is similar to the odd number, except that the messages count into CountB 0-CountB 3.

Specifically, for a scene that does not support the expansion of the number of coloring marks, a message in the range from T/2 before the start of the current coloring period T to T/2 after the end of the current coloring period T is counted into a counter corresponding to the period.

In another embodiment of the present invention, the read period can be expanded by expanding the number of counters for a shorter coloring period T as well, on the basis of the above embodiment.

Fig. 7 is a schematic structural diagram of a network performance measurement device according to an embodiment of the present invention, and as shown in fig. 7, the network performance measurement device includes:

Fig. 8 is a schematic structural diagram of a network performance measurement device according to an embodiment of the present invention, and as shown in fig. 8, the network performance measurement device includes:

Fig. 9 is a schematic structural diagram of a network performance measurement system according to an embodiment of the present invention, as shown in fig. 9, the system includes:

the source node comprises: the method comprises the steps of a first processor and N counters, wherein a counter Count in a router source node sequentially arranges coloring time of a coloring marking message correspondingly according to a period T;

the sink node or intermediate node comprises: the second processor and the N counters, wherein a counter Count in the router sink node is used for sequentially arranging the receiving time of a coloring mark message correspondingly marked according to a period T;

The coloring period is T, and the delay coloring messages in one period T are expanded into N; the coloring marks of the message are N types; the N is 2 or even times of 2;

the first processor is configured to send a message, color a first message started in every T/N periods in a T period, and Count a coloring time of the message into a corresponding counter Count;

the second processor is configured to receive a packet, write a receiving time of receiving a coloring packet into (receiving time/reading period)/the coloring period when the coloring period is lower than the reading period, then round down to obtain a corresponding counter, and count the receiving time of receiving the coloring packet into the corresponding counter; when the coloring period is consistent with the reading period, writing the receiving time of a coloring message into (receiving time/reading period) N/coloring period, then rounding downwards to obtain a corresponding counter, and counting the receiving time of the coloring message into the corresponding counter;

and the network manager is used for reading the data of the counters in the source node and the sink node or the intermediate node at the intermediate point of each T periods and calculating network time delay.

Fig. 5 is a schematic diagram of message coloring in another embodiment of the invention. In this embodiment, the coloring period is T, the reading period is 4T, and each node transmitting data may be provided with a network performance measurement device, and each network performance measurement device is provided with 8 counters (CountA 0 to CountA3, countB0 to CountB 3).

At the source node transmitting the data, the data blocks B (blocks) 1 to 16 are colored according to a coloring cycle, for example, the data Block B1 is colored 0000, the data Block B2 is colored 1111, the data Block B3 is colored 2222, the data Block B4 is colored 3333, and so on. Wherein, in the odd number of 4T periods, the message respectively counts the coloring time of the message into Count A (Count A0-Count A3) according to coloring; in an even number of 4T periods, the message counts the coloring time of the message into Count B (Count B0-Count B3) according to coloring.

Specifically, for a scene supporting coloring mark number extension, the message coloring value is (current time/reading period)/coloring period, then the corresponding counter is determined by rounding down, and the coloring time of the message is counted into the corresponding counter. For example, in a scenario where the coloring period is lower than the reading period, the coloring time of the message is written into (receiving time/reading period)/the coloring period, then the coloring time of the message is rounded down to obtain a corresponding counter, and the coloring time of the message is counted into the corresponding counter. In the scene that the coloring period is consistent with the reading period, N time delay coloring messages can be inserted in each period, namely, the first service message is time delay colored every 1/N period.

Similarly, in the sink node or the intermediate node transmitting data, in an odd number of 4T periods, the message counts the receiving time of the message into Count a (Count a0 to Count a 3) respectively according to coloring; in an even number of 4T periods, the messages respectively count the receiving time of the messages into CountB (CountB 0 to CountB 3) according to coloring.

Specifically, the coloring period is lower than the reading period, the time of receiving the message is written (current time/reading period)/the coloring period, and then the coloring period is rounded down to obtain the corresponding counter. And (3) writing the time of receiving the message (current time/coloring period) N/coloring period in a scene with the coloring period consistent with the reading period, and then rounding downwards to obtain a corresponding counter. And counting the receiving time of the message into the corresponding counter.

The network manager can read 4 groups of performance data of last 4T of each node on the transmission path at an intermediate time point of every 4T period, so as to calculate the time delay. For example, data in the Count a (Count a0 to Count a 3) in the source node and data in the Count a (Count a0 to Count a 3) in the sink node may be in one-to-one correspondence to obtain four sets of time, and an average value, a maximum value, or a minimum value may be taken as the delay value.

Fig. 6 is a schematic diagram of message coloring in another embodiment of the invention. In this embodiment, the coloring period is T, the reading period is 4T, and each node transmitting data may be provided with a network performance measurement device, and each network performance measurement device is provided with 8 counters (CountA 0 to CountA3, countB0 to CountB 3).

at the source node transmitting the data, the data blocks B (blocks) 1 to 16 are colored in accordance with a coloring cycle, for example, the data Block B1 is colored 0000, the data Block B2 is colored 1111, the data Block B3 is colored 0000, the data Block B4 is colored 1111, and so on. Wherein, in the odd number of 4T periods, -T/2-3T/2 time, the message coloring time with coloring 0 is counted into CountA0; in the time of T/2-5T/2, counting the message coloring time with the coloring of 1 into CountA1; in the time of 3T/2-7T/2, counting the message coloring time with the coloring value of 0 into CountA2; in the time of 5T/2-9T/2, the message coloring time with the coloring value of 1 is counted into CountA3. In an even number of 4T cycles, the count is similar to the odd number, except that the message coloring time counts into CountB 0-CountB 3.

Similarly, in the sink node or the intermediate node for transmitting data, the message receiving time colored to 0 is counted into CountA0 in-T/2-3T/2 time in an odd number of 4T periods; in the time of T/2-5T/2, counting the message receiving time with the coloring of 1 into CountA1; counting the message receiving time with coloring 0 into CountA2 in the time of 3T/2-7T/2; the message receiving time with the coloring of 1 is counted into CountA3 within the time of 5T/2-9T/2. In an even number of 4T cycles, the count is similar to the odd number, except that the message reception time counts into CountB 0-CountB 3.

Specifically, for the scene which does not support the expansion of the coloring mark number, the coloring or receiving time of the message in the period range from T/2 before the current coloring period T starts to T/2 after the current coloring period T ends is counted into the counter corresponding to the period.

The network manager can read 4 groups of performance data of last 4T of each node on the transmission path at an intermediate time point of every 4T period, so as to calculate the time delay. For example, data in the Count a (Count a0 to Count a 3) in the source node and data in the Count a (Count a0 to Count a 3) in the sink node may be in one-to-one correspondence, so as to obtain four groups of time, and an average value, a maximum value or a minimum value may be taken as the time delay.

Fig. 10 is a schematic diagram of message coloring in another embodiment of the invention. In this embodiment, the coloring period is T1, the delay coloring message is extended to N, and each node for transmitting data may be provided with a network performance measurement device, and each network performance measurement device is provided with N counters.

At the source node transmitting the data, the amount of delay coloring may be increased per cycle. RFC8321 provides a way to color the first message that starts every cycle. In this embodiment, the number of delay coloring messages can be increased as required according to actual situations by extending the counter. For example, the coloring period is T, and the delay coloring message is extended to N. The first message starting every T/N cycles is colored, and the coloring time is counted into the corresponding counter.

Similarly, in a sink node or an intermediate node for transmitting data, the coloring period is lower than the reading period scene, the time for receiving the coloring message is written in (current time/reading period)/the coloring period, and then the coloring period is rounded down to obtain a corresponding expansion counter; and (3) writing the time of receiving the coloring message into (the current time/the coloring period) N/the coloring period in a scene with the coloring period consistent with the reading period, and then rounding downwards to obtain a corresponding expansion counter. The reception time is counted in a corresponding counter.

The network manager can read N groups of performance data of last T of each node on the transmission path at the middle time point of each T period, so as to calculate the time delay. For example, the data in N counters in the source node and the data in N counters in the destination node may be in one-to-one correspondence, so as to obtain N groups of time, and an average value, a maximum value, or a minimum value may be taken as the time delay.

Fig. 11 is a flowchart of a network performance measurement method according to an embodiment of the present invention, where the method is applied to a network performance measurement device,

as shown in fig. 11, includes:

step 1101, the processor counts N counts An corresponding to the coloring mark of the message in An odd number of n×t periods; and in an even number of N T periods, sequentially counting N corresponding Count Bns according to the coloring marks of the message.

Fig. 12 is a flowchart of a network performance measurement method according to another embodiment of the present invention, where the method is applied to a network performance measurement device,

as shown in fig. 12, includes:

step 1201, the processor counts the message colored as a in-T/2-3T/2 time into the corresponding counter Count A0 in an odd number of n×t periods; counting the message colored as B in the time of T/2-5T/2 into a corresponding counter Count A1; counting the message colored as A in 3T/2-7T/2 time into a corresponding counter Count A2; counting the message colored as B in the time of 5T/2-9T/2 into a corresponding counter Count A3; and so on until the reading period is finished;

Wherein, the mark A is 0 and the mark B is 1.

Fig. 13 is a flowchart of a network performance measurement method according to another embodiment of the present invention, where the method is applied to a network performance measurement system, and the system includes: the network manager and the source node and the destination node or the intermediate node for transmitting the message,

the source node comprises: a first processor and 2N counters;

As shown in fig. 13, includes:

step 1301, the first processor colors and sends a message; in An odd number of N-T periods, sequentially counting N corresponding Count An according to the coloring marks of the message; in an even number of N T periods, sequentially counting N corresponding Count Bns according to the coloring marks of the message;

step 1302, the second processor receives a message; in An odd number of N-T periods, sequentially counting N corresponding Count An according to the coloring marks of the message; in an even number of N T periods, sequentially counting N corresponding Count Bns according to the coloring marks of the message;

in step 1303, the network manager reads the data of the counters in the source node and the sink node or the intermediate node at the intermediate point of every n×t periods, and calculates the packet loss rate.

Fig. 14 is a flowchart of a network performance measurement method according to another embodiment of the present invention, where the method is applied to a network performance measurement device, and the network performance measurement device includes: the coloring period is T, and the delay coloring messages in one period T are expanded into N; the N is 2 or even times of 2; a counter Count is used for correspondingly marking the coloring time of a coloring marking message;

As shown in fig. 14, includes:

in step 1401, the processor performs coloring on the first message started every T/N cycles in the T cycles, and counts the coloring time of the message into the corresponding counter Count.

Fig. 15 is a flowchart of a network performance measurement method according to another embodiment of the present invention, where the method is applied to a network performance measurement device, and the network performance measurement device includes: the coloring period is T, and the delay coloring messages in one period T are expanded into N; the N is 2 or even times of 2; a counter Count sequentially arranges the receiving time of a coloring mark message correspondingly marked according to a period T;

as shown in fig. 15, includes:

step 1501, when the coloring period is lower than the reading period, the processor writes the receiving time of a coloring message into (receiving time/reading period)/the coloring period, then rounds down to obtain a corresponding counter, and counts the receiving time of the coloring message into the corresponding counter; when the coloring period is consistent with the reading period, the processor writes the receiving time of a coloring message into (receiving time/reading period) N/coloring period, then rounds down to obtain a corresponding counter, and the receiving time of the coloring message is counted into the corresponding counter.

FIG. 16 is a flowchart of a network performance measurement method according to another embodiment of the present invention, which is applied to a network performance measurement system;

the network performance measurement system includes: the network manager and the source node and the destination node or the intermediate node for transmitting the message,

the coloring period is T, and the delay coloring messages in one period T are expanded into N; the N is 2 or even times of 2;

as shown in fig. 16, the method includes:

step 1601, the first processor sends a message, and in a T period, colors a first message started every T/N periods, and counts the coloring time of the message into a corresponding counter Count;

step 1602, the second processor receives the message, when the coloring period is lower than the reading period, writes the receiving time of receiving a coloring message into (receiving time/reading period)/coloring period, then rounds down to obtain a corresponding counter, and counts the receiving time of receiving the coloring message into the corresponding counter; when the coloring period is consistent with the reading period, writing the receiving time of a coloring message into (receiving time/reading period) N/coloring period, then rounding downwards to obtain a corresponding counter, and counting the receiving time of the coloring message into the corresponding counter;

In step 1603, the network manager reads the data of the counters in the source node and the sink node or the intermediate node at the intermediate point of each T periods, and calculates the network delay.

Those of ordinary skill in the art will appreciate that all or some of the steps, systems, functional modules/units in the apparatus, and methods disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. In a hardware implementation, the division between the functional modules/units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be performed cooperatively by several physical components. Some or all of the components may be implemented as software executed by a processor, such as a digital signal processor or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as known to those skilled in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer. Furthermore, as is well known to those of ordinary skill in the art, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media.

Claims

1. A network performance measurement apparatus, comprising:

2. A network performance measurement apparatus, comprising:

3. The network performance measurement apparatus of claim 2, wherein,

the mark A is 0, and the mark B is 1.

4. A network performance measuring method is characterized by being applied to a network performance measuring device,

5. A network performance measuring method is characterized by being applied to a network performance measuring device,

6. The method of claim 5, wherein the step of determining the position of the probe is performed,

the mark A is 0, and the mark B is 1.