[go: up one dir, main page]

WO2020259113A1 - Network performance measurement device and method - Google Patents

Network performance measurement device and method Download PDF

Info

Publication number
WO2020259113A1
WO2020259113A1 PCT/CN2020/090077 CN2020090077W WO2020259113A1 WO 2020259113 A1 WO2020259113 A1 WO 2020259113A1 CN 2020090077 W CN2020090077 W CN 2020090077W WO 2020259113 A1 WO2020259113 A1 WO 2020259113A1
Authority
WO
WIPO (PCT)
Prior art keywords
coloring
message
count
period
colored
Prior art date
Application number
PCT/CN2020/090077
Other languages
French (fr)
Chinese (zh)
Inventor
周先涛
Original Assignee
中兴通讯股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 中兴通讯股份有限公司 filed Critical 中兴通讯股份有限公司
Publication of WO2020259113A1 publication Critical patent/WO2020259113A1/en

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00Arrangements for monitoring or testing data switching networks
    • H04L43/18Protocol analysers
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00Arrangements for monitoring or testing data switching networks
    • H04L43/50Testing arrangements
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W24/00Supervisory, monitoring or testing arrangements
    • H04W24/08Testing, supervising or monitoring using real traffic
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00Arrangements for monitoring or testing data switching networks
    • H04L43/08Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
    • H04L43/0823Errors, e.g. transmission errors
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00Arrangements for monitoring or testing data switching networks
    • H04L43/08Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
    • H04L43/0823Errors, e.g. transmission errors
    • H04L43/0829Packet loss
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00Arrangements for monitoring or testing data switching networks
    • H04L43/08Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
    • H04L43/0852Delays
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02DCLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00Reducing energy consumption in communication networks
    • Y02D30/50Reducing energy consumption in communication networks in wire-line communication networks, e.g. low power modes or reduced link rate

Definitions

  • the embodiments of this application relate to but are not limited to the field of PTN (Packet Transport Network)/IPRAN (IP Radio Access Network, IP radio access network), and more specifically to a network performance measurement device and method.
  • PTN Packet Transport Network
  • IPRAN IP Radio Access Network, IP radio access network
  • IPPM IP Performance Metrics
  • RFCs Request For Comments
  • Internet drafts involving all aspects of network traffic measurement and analysis.
  • connectivity one-way delay and packet loss, two-way delay and packet loss, delay jitter, etc.
  • active measurement technology which has some limitations in application. For example, one-way services, different paths between detection packets and actual services, and so on.
  • RFC8321 provides an alternate coloring method for passive performance monitoring. As shown in Figure 1, this method does not use additional probe messages and directly colorizes user messages periodically at the source node. The destination node resumes coloring, and the number of business packets sent and received can be monitored on the entire forwarding path. For each service packet loss performance, the router needs to provide two counters, Counter A and Counter B. Counter A counts the packets carrying color A, and Counter B counts the packets carrying color B. In the coloring cycle B, the stable count of the previous coloring Counter A can be read; while in the coloring A cycle, the stable count of the previous coloring Counter B can be read. By comparing the performance values of the source, sink, and intermediate nodes in the same cycle, the end-to-end packet loss performance or the packet loss performance of a certain segment of the forwarding path can be calculated.
  • each router that needs to be monitored is allocated two counters Count A and Count B.
  • Count A count needs to be stable, and it can only be read around the middle time point of the B cycle.
  • the A cycle message may not be over too early, and the next A cycle too late The messages start counting again.
  • stable counting time points are easier to obtain; but for shorter periods, such as 1s or millisecond monitoring periods, the counter stable interval is very short, which is difficult Obtain.
  • RFC8321 also provides a coloring scheme for delay measurement.
  • the source node colorizes the first packet of each cycle, records the coloring time point, and restores coloring at the destination node.
  • colored packets can be extracted and time points can be recorded.
  • the end-to-end delay or the delay performance of a certain segment of the forwarding path can be calculated by comparing the time values of the source, sink, and intermediate nodes in the same cycle.
  • the delay performance monitoring based on RFC8321 also has the same problem of obtaining stable time points as the packet loss performance.
  • the delay performance monitoring based on RFC8321 also has the same problem of obtaining stable time points as the packet loss performance.
  • the delay performance monitoring based on RFC8321 since there is only one colored delay packet per cycle, it is possible that colored delay packets in multiple cycles are discarded, resulting in no delay data for a long time.
  • performance data such as the maximum delay, minimum delay, average delay, and jitter obtained by statistics have large deviations from actual business conditions.
  • an embodiment of the present application provides a network performance measurement device, including: a processor and 2N counters, the 2N counters include N counters Count An and N counters Count Bn, where N is 2. Even times, the value of n is a natural number from 0 to N-1; there are N kinds of coloring marks for the message, a counter Count An and a counter Count Bn corresponding to calculate the number of a kind of coloring mark message; the coloring cycle is T, read Take the cycle as N*T; the processor is used to count the corresponding N Count An according to the coloring mark of the message in an odd number of N*T cycles; in an even number of N*T cycles, according to the report The coloring marks of the text are counted in the corresponding N Count Bn in turn.
  • An embodiment of the present application also provides a network performance measurement device, including: a processor and 2N counters, the 2N counters include N counters Count An and N counters Count Bn, where N is an even multiple of 2.
  • the value of n is a natural number from 0 to N-1; there are two types of coloring tags for the message: A and B; the coloring cycle is T, and the reading cycle is N*T; a counter Count An and a counter Count Bn are corresponding to a 2T
  • the processor is configured to count the messages colored as A in the period -T/2—3T/2 into the corresponding counter Count in an odd number of N*T cycles A0; the packets colored as B within T/2 ⁇ 5T/2 are counted into the corresponding counter Count A1; the packets colored as A within the time 3T/2 ⁇ 7T/2 count into the corresponding counter Count A2; 5T/ Packets colored as B within 2-9T/2 are counted into the corresponding counter
  • An embodiment of the present application also provides a network performance measurement device, including: a processor and N counters, the coloring period is T, and the delay coloring packets within a period T are expanded to N; where N is 2 or 2. Even times; there are N kinds of coloring marks for the message; a counter Count corresponds to marking the coloring time of a coloring mark message; the processor is used for the first one at the beginning of every T/N cycle in the T period The message is colored, and the coloring time of the message is counted into the corresponding counter Count.
  • An embodiment of the present application also provides a network performance measurement device, including: a processor and N counters, the coloring period is T, and the delay coloring packets within a period T are expanded to N; where N is 2 or 2. Even times; there are N kinds of coloring marks for the message; a counter Count is arranged according to the period T in order to mark the receiving time of a coloring mark message; the processor is used for receiving when the coloring period is lower than the reading period When the receiving time of a colored message is written (receiving time/reading period)/coloring cycle, then round down to obtain the corresponding counter, and the receiving time of receiving the colored message is counted into the corresponding counter; When the coloring period is the same as the reading period, write the receiving time of a coloring message (receiving time/reading period)*N/coloring period, and then round down to get the corresponding counter, which will receive the The receiving time of the colored message is included in the corresponding counter.
  • the embodiment of the present application also provides a network performance measurement method, which is applied to a network performance measurement device.
  • the network performance measurement device includes a processor and 2N counters.
  • the 2N counters include N counters Count An and N counters.
  • the counter Count Bn the N is an even multiple of 2, and n is a natural number from 0 to N-1; there are N types of coloring tags for the message, and a counter Count An and a counter Count Bn respectively calculate a coloring tag report
  • the embodiment of the present application also provides a network performance measurement method, which is applied to a network performance measurement device.
  • the network performance measurement device includes a processor and 2N counters.
  • the 2N counters include N counters Count An and N counters.
  • the counter Count Bn the N is an even multiple of 2, and the value of n is a natural number from 0 to N-1;
  • the coloring flag of the message has two types: A and B; the coloring period is T, and the reading period is N*T;
  • a counter Count An and a counter Count Bn correspondingly calculate the number of a coloring flag message in a 2T cycle;
  • the processor colorizes -T/2—3T/2 within an odd number of N*T cycles as
  • the message of A is counted into the corresponding counter Count A0; the message colored as B within T/2 ⁇ 5T/2 counts into the corresponding counter Count A1; the message colored as A within 3T/2 ⁇ 7T/2 Count into the corresponding counter Count A2;
  • the embodiment of the present application also provides a network performance measurement method, which is applied to a network performance measurement device,
  • the network performance measurement device includes: a processor and N counters, the coloring period is T, and the delay coloring message is expanded to N in a period T; the N is 2 or an even multiple of 2; a counter Count corresponds to a mark The coloring time of a coloring flag message; the processor colorizes the first message starting every T/N cycle within T cycles, and counts the coloring time of the message into the corresponding counter Count .
  • the embodiment of the present application also provides a network performance measurement method, which is applied to a network performance measurement device.
  • the network performance measurement device includes a processor and N counters, the coloring period is T, and the coloring message is delayed within a period T. Expanded to N; the N is 2 or an even multiple of 2; a counter Count is arranged in sequence according to the period T to mark the receiving time of a coloring flag message; when the coloring period is lower than the reading period, the processor will The receiving time of receiving a coloring message is written (receiving time/reading period)/coloring period, and then rounding down to get the corresponding counter, and the receiving time of receiving the coloring message is counted into the corresponding counter ; When the coloring cycle is consistent with the read cycle, the processor writes the receiving time of a coloring message (receiving time/reading cycle)*N/coloring cycle, and then rounds down to get the corresponding counter Calculate the receiving time of receiving the colored message into the corresponding counter.
  • Figure 1 is a schematic diagram of the existing RFC8321 alternate coloring
  • FIG. 2 is a schematic structural diagram of a network performance measurement device provided by an embodiment of this application.
  • FIG. 3 is a schematic structural diagram of a network performance measurement device provided by another embodiment of this application.
  • FIG. 4 is a schematic structural diagram of a network performance measurement system provided by an embodiment of this application.
  • 5 is a schematic diagram of packet coloring in another embodiment of the application.
  • FIG. 6 is a schematic diagram of packet coloring in another embodiment of the application.
  • FIG. 7 is a schematic structural diagram of a network performance measurement device provided by an embodiment of this application.
  • FIG. 8 is a schematic structural diagram of a network performance measurement device provided by an embodiment of this application.
  • FIG. 9 is a schematic structural diagram of a network performance measurement system provided by an embodiment of this application.
  • FIG. 10 is a schematic diagram of packet coloring in another embodiment of the application.
  • FIG. 11 is a schematic flowchart of a network performance measurement method provided by an embodiment of this application.
  • FIG. 12 is a schematic flowchart of a network performance measurement method provided by another embodiment of this application.
  • FIG. 13 is a schematic flowchart of a network performance measurement method provided by another embodiment of this application.
  • FIG. 14 is a schematic flowchart of a network performance measurement method provided by another embodiment of this application.
  • 15 is a schematic flowchart of a method for measuring network performance according to another embodiment of this application.
  • FIG. 16 is a schematic flowchart of a method for measuring network performance according to another embodiment of this application.
  • the main idea of the embodiments of this application is to overcome the instability of short-period test counting in the prior art by expanding the number of coloring marks and the number of counters, and the insufficient number of long-period samples leads to large calculation deviations, etc., thereby improving the performance data based on RFC8321 Effectiveness and reliability.
  • FIG. 2 is a schematic structural diagram of a network performance measurement device provided by an embodiment of the application. As shown in FIG. 2, the network performance measurement device includes:
  • the 2N counters include N counters Count An and N counters Count Bn, where N is an even multiple of 2, and n is a natural number from 0 to N-1; coloring of packets There are N types of tags, a counter Count An and a counter Count Bn correspondingly calculate the number of a coloring tag message; the coloring cycle is T, and the reading cycle is N*T;
  • the processor is configured to sequentially count the corresponding N Count An according to the coloring mark of the message in an odd number of N*T cycles; and sequentially count the corresponding N Count An according to the coloring mark of the message in an even number of N*T cycles The corresponding N Count Bn.
  • the network performance measurement device can be set in routers, gateways, switches and other equipment.
  • FIG. 3 is a schematic structural diagram of a network performance measurement device provided by another embodiment of the application. As shown in FIG. 3, the network performance measurement device includes:
  • the 2N counters include N counters Count An and N counters Count Bn, where N is an even multiple of 2, and n is a natural number from 0 to N-1; coloring of packets There are two types of markers: A and B; the coloring cycle is T, and the reading cycle is N*T; a counter Count An and a counter Count Bn correspondingly count the number of a coloring tag message in a 2T cycle;
  • the processor is configured to count the packets colored as A within the period of -T/2—3T/2 into the corresponding counter Count A0 within an odd number of N*T cycles; within the period of T/2—5T/2 Messages colored as B are counted in the corresponding counter Count A1; messages colored as A within 3T/2 ⁇ 7T/2 are counted into the corresponding counter Count A2; messages colored as B within 5T/2 ⁇ 9T/2 The message is counted into the corresponding counter Count A3; and so on until the end of the reading cycle;
  • the packets colored as A within -T/2—3T/2 are counted into the corresponding counter Count B0; the packets colored as B within T/2 ⁇ 5T/2 are counted Enter the corresponding counter Count B1; the packets colored as A within 3T/2 ⁇ 7T/2 are counted into the corresponding counter Count B2; the packets colored as B within 5T/2 ⁇ 9T/2 are counted into the corresponding counter Count B3; and so on until the end of the read cycle.
  • the mark A is 0, and the mark B is 1.
  • the network performance measurement device can be set in routers, gateways, switches and other equipment.
  • FIG. 4 is a schematic structural diagram of a network performance measurement system provided by an embodiment of the application. As shown in FIG. 4, the system includes:
  • the source node and sink node or intermediate node of network management and transmission message are The source node and sink node or intermediate node of network management and transmission message
  • the source node includes: a first processor and 2N counters;
  • the sink node or intermediate node includes: a second processor and 2N counters;
  • the 2N counters include N counters Count An and N counters Count Bn, where N is an even multiple of 2, and n is a natural number from 0 to N-1; there are N types of coloring tags for packets, one counter Count An and a counter Count Bn respectively calculate the number of a coloring mark message; the coloring cycle is T, and the reading cycle is N*T;
  • the first processor is configured to color and send the message; in an odd number of N*T cycles, the corresponding N Count An are counted in sequence according to the coloring flag of the message; in an even number of N*T cycles , Count the corresponding N Count Bn in turn according to the coloring mark of the message;
  • the second processor is configured to receive a message; in an odd number of N*T cycles, the corresponding N Count An is counted in sequence according to the coloring flag of the message; in an even number of N*T cycles, according to the message The colored marks of are counted in the corresponding N Count Bn in turn;
  • the network management system is configured to read the counter data of the source node and the sink node or the intermediate node at an intermediate point of every N*T cycles, and calculate the packet loss rate.
  • the network performance measurement device may be provided in the above-mentioned node.
  • FIG. 5 is a schematic diagram of packet coloring in another embodiment of the application.
  • the coloring period is T and the reading period is 4T.
  • Each node that transmits data can be equipped with a network performance measurement device, and each network performance measurement device is provided with 8 counters (CountA0 ⁇ CountA3, CountB0 ⁇ CountB3).
  • the data block B (Block) 1-16 is colored according to the coloring cycle, for example, data block B1 is colored 0000, data block B2 is colored 1111, data block B3 is colored 2222, and data block B4 is colored It is 3333, and so on.
  • the message is put into Count A (CountA0 ⁇ CountA3) according to the coloring; in the even number of 4T cycles, the message is put into Count B (CountB0 ⁇ CountB3) according to the coloring.
  • the coloring value of the message is (current time/read cycle)/coloring cycle, and then rounded down to determine the corresponding counter.
  • the message is counted into the corresponding counter according to the coloring value and parity cycle. counter.
  • the network manager can read the last 4T performance data of each node in the transmission path at the intermediate time of the 4T cycle to calculate the packet loss rate.
  • the data in Count A (CountA0 ⁇ CountA3) in the source node can be one-to-one corresponding to the data in Count A (CountA0 ⁇ CountA3) in the sink node to obtain the number of lost packets in four groups, which can be the average, maximum, or The minimum value is used as the packet loss rate.
  • the reading period ratio can be further expanded, such as 10T, 100T, etc., and the corresponding coloring mark number and counter The quantity needs to be expanded accordingly.
  • FIG. 6 is a schematic diagram of packet coloring in another embodiment of the application.
  • the coloring period is T and the reading period is 4T.
  • Each node that transmits data can be equipped with a network performance measurement device, and each network performance measurement device is provided with 8 counters (CountA0 ⁇ CountA3, CountB0 ⁇ CountB3).
  • Message coloring is mainly to mark certain specific fields of business messages, and the number of different business messages that can be marked is limited. In the extreme case, only 1 bit is available for marking and can only be colored as 0 and 1, which is the marking method provided by RFC8321. In this scenario, the solution for expanding the number of colored marks provided in the above embodiment is not feasible.
  • this embodiment provides an enhanced alternate coloring scheme.
  • the data block B (Block) 1-16 is colored according to the coloring cycle, for example, data block B1 is colored 0000, data block B2 is colored 1111, data block B3 is colored 0000, and data block B4 is colored 1111, and so on.
  • packets colored as 0 are included in CountA0; within T/2 ⁇ 5T/2, packets colored as 1 are included in CountA1; Within 3T/2 ⁇ 7T/2, packets colored as 0 are counted as CountA2; within 5T/2 ⁇ 9T/2, packets colored as 1 are counted as CountA3.
  • counting is similar to an odd number cycle, except that the message is counted into CountB0 ⁇ CountB3.
  • the network manager can read the last 4T performance data of each node on the transmission path at the intermediate time of the 4T cycle to calculate the packet loss rate.
  • the data in Count A (CountA0 ⁇ CountA3) in the source node can be one-to-one corresponding to the data in Count A (CountA0 ⁇ CountA3) in the sink node to obtain the number of lost packets in four groups, which can be the average, maximum, or The minimum value is used as the packet loss rate.
  • the reading period can also be enlarged by expanding the number of counters.
  • FIG. 7 is a schematic structural diagram of a network performance measurement device provided by an embodiment of the application. As shown in FIG. 7, the network performance measurement device includes:
  • the processor and N counters, the coloring period is T, and the delay coloring message within a period T is expanded to N; the N is 2 or an even multiple of 2; there are N kinds of coloring marks for the message; a counter Count corresponds Mark the coloring time of a coloring tag message;
  • the processor is configured to color the first message starting every T/N cycle in the T period, and count the coloring time of the message into the corresponding counter Count.
  • the network performance measurement device can be set in routers, gateways, switches and other equipment.
  • FIG. 8 is a schematic structural diagram of a network performance measurement device provided by an embodiment of the application. As shown in FIG. 8, the network performance measurement device includes:
  • the coloring cycle is T, and the delay coloring message in a cycle T is expanded to N; the N is 2 or an even multiple of 2; there are N kinds of coloring marks for the message; a counter Count according to The period T sequentially arranges the receiving time of correspondingly marked a colored marked message;
  • the processor is used to write the receiving time (receiving time/reading period)/coloring period of a coloring message when the coloring period is lower than the reading period, and then round down to obtain the corresponding counter , The receiving time of receiving the coloring message is counted into the corresponding counter; when the coloring period is consistent with the reading period, the receiving time of receiving a coloring message is written (receiving time/reading period)* N/coloring period, then round down to obtain a corresponding counter, and count the receiving time of receiving the coloring message into the corresponding counter.
  • the network performance measurement device can be set in routers, gateways, switches and other equipment.
  • Fig. 9 is a schematic structural diagram of a network performance measurement system provided by an embodiment of the application. As shown in Fig. 9, the system includes: a network management and a source node and a sink node or intermediate nodes for transmitting packets.
  • the source node includes: a first processor and N counters, and a counter Count in the router source node sequentially arranges the coloring time corresponding to a coloring flag packet according to the period T.
  • the sink node or intermediate node includes: a second processor and N counters, and a counter Count in the router sink node sequentially arranges the receiving time corresponding to a colored marking message according to the period T.
  • the coloring period is T, and the time-delay coloring message is expanded to N in a period T; there are N kinds of coloring marks for the message; the N is 2 or an even multiple of 2.
  • the first processor is configured to send a message, and in the T cycle, color the first message starting every T/N cycle, and count the coloring time of the message into the corresponding counter Count.
  • the second processor is configured to receive a message, and when the coloring period is lower than the reading period, write the receiving time of a coloring message into (receiving time/reading period)/coloring period, and then down Round to get the corresponding counter, and count the receiving time of the coloring message into the corresponding counter; when the coloring period is the same as the reading period, write the receiving time of a coloring message (receive time /Reading period)*N/coloring period, then round down to obtain the corresponding counter, and count the receiving time of receiving the coloring message into the corresponding counter.
  • the network management system is configured to read the counter data of the source node and the sink node or the intermediate node at an intermediate point of every T period, and calculate the network delay.
  • FIG. 5 is also a schematic diagram of packet coloring in another embodiment of the application.
  • the coloring period is T and the reading period is 4T.
  • Each node that transmits data can be equipped with a network performance measurement device, and each network performance measurement device is provided with 8 counters (CountA0 ⁇ CountA3, CountB0 ⁇ CountB3).
  • the data block B (Block) 1-16 is colored according to the coloring cycle, for example, data block B1 is colored 0000, data block B2 is colored 1111, data block B3 is colored 2222, and data block B4 is colored It is 3333, and so on.
  • the coloring time of the message is included in Count A (CountA0 ⁇ CountA3) according to the coloring; in the even number of 4T cycles, the coloring time of the message is included in the coloring time of the message.
  • Count B (CountB0 ⁇ CountB3) the coloring time of the message is included in the coloring time of the message.
  • the coloring value of the message is (current time/read cycle)/coloring cycle, then round down to determine the corresponding counter, and the coloring time of the message is included in the corresponding counter. For example, if the coloring cycle is lower than the reading cycle, write the coloring time of the message (receiving time/reading cycle)/coloring cycle, then round down to get the corresponding counter, and count the coloring time of the message The corresponding counter.
  • N delay coloring messages can be inserted in each cycle, that is, the first service message is delayed coloring every 1/N cycle.
  • the message counts the message reception time into Count A (CountA0 ⁇ CountA3) according to the coloring; in even 4T cycles, the message According to the coloring, the receiving time of the message is counted into CountB (CountB0 ⁇ CountB3).
  • the time of receiving the message is written (current time/reading cycle)/coloring cycle, and then rounded down to get the corresponding counter.
  • the time of receiving the message is written (current time/coloring cycle)*N/coloring cycle, and then rounded down to get the corresponding counter.
  • the message receiving time is counted into the corresponding counter.
  • the network manager can read the last 4T performance data of each node in the transmission path at the intermediate time of the 4T cycle to calculate the delay.
  • the data in Count A (CountA0 ⁇ CountA3) in the source node can be one-to-one corresponding to the data in Count A (CountA0 ⁇ CountA3) in the sink node to obtain four sets of times, which can be the average, maximum, or minimum. As the delay value.
  • the reading period ratio can be further expanded, such as 10T, 100T, etc., and the corresponding coloring mark number and counter The quantity needs to be expanded accordingly.
  • FIG. 6 is also a schematic diagram of packet coloring in another embodiment of the application.
  • the coloring period is T and the reading period is 4T.
  • Each node that transmits data can be equipped with a network performance measurement device, and each network performance measurement device is provided with 8 counters (CountA0 ⁇ CountA3, CountB0 ⁇ CountB3).
  • Message coloring is mainly to mark certain specific fields of business messages, and the number of different business messages that can be marked is limited. In the extreme case, only 1 bit is available for marking and can only be colored as 0 and 1, which is the marking method provided by RFC8321. In this scenario, the solution for expanding the number of colored marks provided in the above embodiment is not feasible.
  • this embodiment provides an enhanced alternate coloring scheme.
  • the data block B (Block) 1-16 is colored according to the coloring cycle, for example, data block B1 is colored 0000, data block B2 is colored 1111, data block B3 is colored 0000, and data block B4 is colored 1111, and so on.
  • the coloring time of packets colored as 0 is included in CountA0; within T/2 ⁇ 5T/2, the coloring time of packets colored as 1 CountA1; within 3T/2 ⁇ 7T/2, the coloring time of the message colored 0 is included in CountA2; within 5T/2 ⁇ 9T/2, the coloring time of the message colored 1 is included in CountA3.
  • counting is similar to odd cycles, except that the message coloring time is included in CountB0 ⁇ CountB3.
  • the packet reception time colored 0 is included in CountA0; T/2 ⁇ 5T/2 Within the time, the receiving time of the message colored 1 is counted into CountA1; within 3T/2 ⁇ 7T/2, the receiving time of the message colored 0 is counted into CountA2; within 5T/2 ⁇ 9T/2, the coloring is 1
  • the received time of the message is included in CountA3.
  • counting is similar to odd cycles, except that the message reception time is included in CountB0 ⁇ CountB3.
  • the coloring or receiving time of packets in the range of T/2 before the start of the current coloring period T to T/2 after the end of the current coloring period T is included in the counter corresponding to the period in.
  • the network manager can read the last 4T performance data of each node in the transmission path at the intermediate time of the 4T cycle to calculate the delay.
  • the data in Count A (CountA0 ⁇ CountA3) in the source node can be one-to-one corresponding to the data in Count A (CountA0 ⁇ CountA3) in the sink node to obtain four sets of times, which can be the average, maximum, or minimum. As a delay.
  • the reading period can also be enlarged by expanding the number of counters.
  • FIG. 10 is also a schematic diagram of packet coloring in another embodiment of the application.
  • the coloring period is T1
  • the delayed coloring message is expanded to N.
  • Each node that transmits data can be provided with a network performance measurement device, and each network performance measurement device is provided with N counters.
  • the number of delay coloring can be increased during each week.
  • the method provided by RFC8321 is to color the first message at the beginning of each cycle.
  • the number of delay colored packets can be increased as needed according to actual conditions.
  • the coloring period is T
  • the delayed coloring message is expanded to N. Color the first message at the beginning of every T/N cycle, and count the coloring time into the corresponding counter.
  • the coloring cycle is lower than the read cycle scenario, the time of receiving the coloring message is written (current time/read cycle)/coloring cycle, and then rounded down to get the corresponding
  • the time of receiving the coloring message is written (current time/coloring cycle)*N/coloring cycle, and then rounded down to get the corresponding extended counter. Count the receiving time into the corresponding counter.
  • the network manager can read the N sets of performance data of the last T in each node on the transmission path at the intermediate time point of every T cycle, so as to calculate the time delay.
  • the data in the N counters in the source node can be one-to-one corresponding to the data in the N counters in the sink node to obtain N sets of time, and the average value, maximum value, or minimum value can be taken as the delay.
  • the reading period can also be enlarged by expanding the number of counters.
  • FIG. 11 is a schematic flowchart of a network performance measurement method provided by an embodiment of this application, and the method is applied to a network performance measurement device.
  • the network performance measurement device includes: a processor and 2N counters.
  • the 2N counters include N counters CountAn and N counters CountBn, where N is an even multiple of 2, and n takes a value from 0 to N- A natural number of 1; there are N types of coloring tags for messages, a counter CountAn and a counter CountBn corresponding to calculate the number of a coloring tag message; the coloring cycle is T, and the reading cycle is N*T;
  • Step 1101 The processor counts the corresponding N Count An in the odd number N*T cycles according to the coloring flag of the message; in the even N*T cycles, counts it sequentially according to the coloring tag of the message The corresponding N Count Bn.
  • the network performance measurement device can be set in routers, gateways, switches and other equipment.
  • FIG. 12 is a schematic flowchart of a network performance measurement method provided by another embodiment of this application, and the method is applied to a network performance measurement device.
  • the network performance measurement device includes: a processor and 2N counters.
  • the 2N counters include N counters CountAn and N counters CountBn, where N is an even multiple of 2, and n takes a value from 0 to N- A natural number of 1; there are two types of coloring tags for the message: A and B; the coloring cycle is T, and the reading cycle is N*T; a counter Count An and a counter Count Bn correspond to a coloring tag message in a 2T cycle quantity;
  • Step 1201 The processor counts the packets colored as A within the period of -T/2—3T/2 into the corresponding counter Count A0 within an odd number of N*T cycles; within the period of T/2—5T/2 Messages colored as B are counted in the corresponding counter Count A1; messages colored as A within 3T/2 ⁇ 7T/2 are counted into the corresponding counter Count A2; messages colored as B within 5T/2 ⁇ 9T/2 The message is counted into the corresponding counter Count A3; and so on until the end of the reading cycle;
  • the packets colored as A within -T/2—3T/2 are counted into the corresponding counter Count B0; the packets colored as B within T/2 ⁇ 5T/2 are counted Enter the corresponding counter Count B1; the packets colored as A within 3T/2 ⁇ 7T/2 are counted into the corresponding counter Count B2; the packets colored as B within 5T/2 ⁇ 9T/2 are counted into the corresponding counter Count B3; and so on until the end of the read cycle.
  • the mark A is 0, and the mark B is 1.
  • the network performance measurement device can be set in routers, gateways, switches and other equipment.
  • FIG. 13 is a schematic flowchart of a network performance measurement method according to another embodiment of the application. The method is applied to a network performance measurement system.
  • the system includes: a network management system and a source node and a sink node or an intermediate node for transmitting packets;
  • the source node includes: a first processor and 2N counters;
  • the sink node or intermediate node includes: a second processor and 2N counters;
  • the 2N counters include N counters Count An and N counters Count Bn, where N is an even multiple of 2, and n is a natural number from 0 to N-1; there are N types of coloring tags for packets, one counter Count An and a counter Count Bn respectively calculate the number of a coloring mark message; the coloring cycle is T, and the reading cycle is N*T;
  • Step 1301 The first processor colorizes and sends the message; in the odd number of N*T cycles, count the corresponding N Count An according to the coloring flag of the message in turn; in the even number of N*T cycles , Count the corresponding N Count Bn in turn according to the coloring mark of the message;
  • Step 1302 the second processor receives the message; in the odd number of N*T cycles, count the corresponding N Count An according to the coloring flag of the message; in the even number of N*T cycles, according to the message The colored marks of are counted in the corresponding N Count Bn in turn;
  • Step 1303 The network manager reads the data of the counters in the source node and the sink node or the intermediate node at an intermediate point of every N*T cycles, and calculates the packet loss rate.
  • the network performance measurement device may be provided in the above-mentioned node.
  • the 14 is a schematic flowchart of a network performance measurement method provided by another embodiment of the application.
  • the method is applied to a network performance measurement device.
  • the network performance measurement device includes a processor and N counters, and the coloring period is T.
  • the delay coloring message is expanded to N in a period T; the N is 2 or an even multiple of 2; a counter Count corresponds to marking the coloring time of a coloring mark message;
  • Step 1401 The processor colorizes the first message that starts every T/N cycle in T cycles, and counts the coloring time of the message into the corresponding counter Count.
  • the network performance measurement device includes a processor and N counters, and the coloring period is T.
  • the delay coloring message is expanded to N; the N is 2 or an even multiple of 2; a counter Count is arranged in sequence according to the period T to mark the receiving time of a coloring mark message;
  • Step 1501 When the coloring period is lower than the reading period, the processor writes (receiving time/reading period)/coloring period of the receiving time of a colored message received, and then rounds down to obtain the corresponding counter , The receiving time of receiving the colored 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 colored message (receiving time/reading Take period)*N/coloring period, then round down to obtain the corresponding counter, and count the receiving time of receiving the coloring message into the corresponding counter.
  • FIG. 16 is a schematic flowchart of a network performance measurement method provided by another embodiment of this application, and the method is applied to a network performance measurement system.
  • the network performance measurement system includes: a network management and a source node and a sink node or intermediate nodes for transmitting messages.
  • the source node includes: a first processor and N counters, and a counter Count in the router source node sequentially arranges the coloring time corresponding to a coloring flag packet according to the period T.
  • the sink node or the intermediate node includes: a second processor and N counters, and a counter Count in the router sink node sequentially arranges the receiving time of a colored marking message corresponding to the period T.
  • the coloring period is T, and the delayed coloring message is expanded to N in a period T; the N is 2 or an even multiple of 2.
  • the method includes:
  • Step 1601 The first processor sends a message, and in the T period, colorizes the first message that starts every T/N period, and counts the coloring time of the message into the corresponding counter Count;
  • Step 1602 the second processor receives the message, and when the coloring period is lower than the reading period, writes the receiving time of a coloring message into (receiving time/reading period)/coloring period, and then down Round to get the corresponding counter, and count the receiving time of the coloring message into the corresponding counter; when the coloring period is the same as the reading period, write the receiving time of a coloring message (receive time /Reading period)*N/coloring period, then round down to obtain the corresponding counter, and count the receiving time of receiving the coloring message into the corresponding counter;
  • 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 every T cycles, and calculates the network delay.
  • the network performance measurement device may be provided in the above-mentioned node.
  • Such software may be distributed on a computer-readable medium, and the computer-readable medium may include a computer storage medium (or a non-transitory medium) and a communication medium (or a transitory medium).
  • the term computer storage medium includes volatile and non-volatile memory implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Sexual, removable and non-removable media.
  • Computer storage media include but are not limited to RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cassette, tape, magnetic disk storage or other magnetic storage device, or Any other medium used to store desired information and that can be accessed by a computer.
  • communication media usually contain computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as carrier waves or other transmission mechanisms, and may include any information delivery media .

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

Disclosed in embodiments of the present application are a network performance measurement device and method. One type of network performance measurement device comprises: a processor and 2N counters. The 2N counters comprise N counters count An and N counters Count Bn, N being an even multiple of 2 and n being a natural number ranging from 0 to N-1. There are N coloring markings for packets. One counter Count An and one counter Count Bn correspondingly calculate the number of packets with one coloring marking. A coloring period is T and a reading period is N*T. The processor is used for including the packets into the corresponding N Count An according to the coloring markings of the packets in an odd number of periods N*T, and for including the packets into the corresponding N Count Bn according to the coloring markings of the packets in an even number of periods N*T.

Description

一种网络性能测量装置及方法Network performance measuring device and method
相关申请的交叉引用Cross references to related applications
本申请基于申请号为201910564926.6、申请日为2019年6月27日的中国专利申请提出,并要求该中国专利申请的优先权,该中国专利申请的全部内容在此以引入方式并入本申请。This application is filed based on the Chinese patent application with the application number 201910564926.6 and the filing date on June 27, 2019, and claims the priority of the Chinese patent application. The entire content of the Chinese patent application is hereby incorporated into this application by way of introduction.
技术领域Technical field
本申请实施例涉及但不限于PTN(Packet Transport Network,分组传送网)/IPRAN(IP Radio Access Network,IP无线接入网)领域,更具体地涉及一种网络性能测量装置及方法。The embodiments of this application relate to but are not limited to the field of PTN (Packet Transport Network)/IPRAN (IP Radio Access Network, IP radio access network), and more specifically to a network performance measurement device and method.
背景技术Background technique
如今,大多数服务提供商的网络都带有对丢包率、时延和抖动高度敏感的内容。鉴于这种情况,服务提供商需要有方法和工具来监控和测量网络性能,不断提升客户体验。另一方面,为改善网络质量提供有用的信息管理(例如,隔离网络问题,故障排除等等)。Today, most service provider networks carry content that is highly sensitive to packet loss, delay, and jitter. In view of this situation, service providers need methods and tools to monitor and measure network performance to continuously improve customer experience. On the other hand, it provides useful information management for improving network quality (for example, isolating network problems, troubleshooting, etc.).
大量与运营、管理和维护(OAM,Operation Administration and Maintenance),包括性能监控技术等相关的工作都是由标准制定组织(SDO,Standards Organization)完成的。其中IPPM(IP Performance Metrics,IP性能指标)工作组一直致力于网络流量测量分析的标准制定,提出了多个RFC(Request For Comments,请求文档)和互联网草案,涉及到网络流量测量分析的各个方面,包括连接性、单向时延和丢包、双向时延和丢包、时延抖动等。该工作组主要关注的是主动(active)测量技术,在应用上存在一些局限性。例如单向的业务、探测报文与实际业务不同路径等等。A large amount of work related to operation, management and maintenance (OAM, Operation Administration and Maintenance), including performance monitoring technology, is completed by the Standards Organization (SDO, Standards Organization). Among them, the IPPM (IP Performance Metrics) working group has been committed to the formulation of standards for network traffic measurement and analysis, and has proposed multiple RFCs (Request For Comments) and Internet drafts, involving all aspects of network traffic measurement and analysis. , Including connectivity, one-way delay and packet loss, two-way delay and packet loss, delay jitter, etc. The main focus of this working group is active measurement technology, which has some limitations in application. For example, one-way services, different paths between detection packets and actual services, and so on.
其中,RFC8321提供了一种交替着色方法用于被动(passive)的性能监测, 如图1所示,该方法不额外使用探测报文,直接在源节点对用户报文进行周期性的着色,在目的节点恢复着色,在整个转发路径上都可以对业务报文收发包数进行监测。针对每个业务丢包性能,路由器需要提供两个计数器,Counter A和Counter B。Counter A对携带颜色A的报文进行计数,Counter B对携带颜色B的报文进行计数。在着色B周期时,可以读取上一轮着色Counter A的稳定计数;而在着色A周期时,可以读取上一轮着色Counter B的稳定计数。通过比较源、宿和中间节点同一周期的性能值就可以计算端到端的丢包性能或是转发路径上某一段的丢包性能。Among them, RFC8321 provides an alternate coloring method for passive performance monitoring. As shown in Figure 1, this method does not use additional probe messages and directly colorizes user messages periodically at the source node. The destination node resumes coloring, and the number of business packets sent and received can be monitored on the entire forwarding path. For each service packet loss performance, the router needs to provide two counters, Counter A and Counter B. Counter A counts the packets carrying color A, and Counter B counts the packets carrying color B. In the coloring cycle B, the stable count of the previous coloring Counter A can be read; while in the coloring A cycle, the stable count of the previous coloring Counter B can be read. By comparing the performance values of the source, sink, and intermediate nodes in the same cycle, the end-to-end packet loss performance or the packet loss performance of a certain segment of the forwarding path can be calculated.
但是,基于RFC8321实现的丢包性能监控,根据着色不同,需要监测的每路由器分配两个计数器Count A和Count B。为了获取稳定的计数,读取A周期计数时,需要Count A计数稳定,只能在B周期中间时间点附近读取,太靠前A周期报文可能还没有结束,太靠后下一A周期的报文又开始计数了。对于长周期,例如10s、30s或是更高的周期,稳定的计数时间点比较容易获取;但对于较短的周期,例如1s或是毫秒级的监控周期,计数器稳定的间隔很短,很难获取。However, based on the packet loss performance monitoring implemented by RFC8321, depending on the coloring, each router that needs to be monitored is allocated two counters Count A and Count B. In order to obtain a stable count, when reading the A cycle count, the Count A count needs to be stable, and it can only be read around the middle time point of the B cycle. The A cycle message may not be over too early, and the next A cycle too late The messages start counting again. For long periods, such as 10s, 30s or higher periods, stable counting time points are easier to obtain; but for shorter periods, such as 1s or millisecond monitoring periods, the counter stable interval is very short, which is difficult Obtain.
其中,RFC8321同样提供用于时延测量的着色方案,源节点针对每周期的第一个报文进行着色,并记录着色的时间点,在目的节点恢复着色。在整个转发路径上都可以提取着色报文并记录时间点。在路径上所有路由器都时间同步的情况下,通过比较源、宿和中间节点同一周期的时间值就可以计算端到端的时延或是转发路径上某一段的时延性能。Among them, RFC8321 also provides a coloring scheme for delay measurement. The source node colorizes the first packet of each cycle, records the coloring time point, and restores coloring at the destination node. On the entire forwarding path, colored packets can be extracted and time points can be recorded. When all routers on the path are time synchronized, the end-to-end delay or the delay performance of a certain segment of the forwarding path can be calculated by comparing the time values of the source, sink, and intermediate nodes in the same cycle.
但是,基于RFC8321实现的时延性能监控,也存在同丢包性能一样的获取稳定时间点的问题。另外对于丢包比较严重的场景,由于每周期只有一个着色的时延报文,有可能多个周期都存在着色的时延报文被丢弃,导致长时间都没有时延数据。并且对于长周期监控场景,由于着色的时延报文样本数比较少,统计得到的最大时延、最小时延、平均时延、抖动等性能数据与实际业务情况存在较大的偏差。However, the delay performance monitoring based on RFC8321 also has the same problem of obtaining stable time points as the packet loss performance. In addition, for scenarios with severe packet loss, since there is only one colored delay packet per cycle, it is possible that colored delay packets in multiple cycles are discarded, resulting in no delay data for a long time. And for long-period monitoring scenarios, because the number of colored delay message samples is relatively small, performance data such as the maximum delay, minimum delay, average delay, and jitter obtained by statistics have large deviations from actual business conditions.
发明内容Summary of the invention
有鉴于此,本申请实施例提供了一种网络性能测量装置,包括:处理器和2N个计数器,所述2N个计数器包括N个计数器Count An和N个计数器Count  Bn,所述N为2的偶数倍,n取值为0到N-1的自然数;报文的着色标记有N种,一个计数器Count An和一个计数器Count Bn对应计算一种着色标记报文的数量;着色周期为T,读取周期为N*T;所述处理器,用于在奇数个N*T周期内,根据报文的着色标记依次计入对应的N个Count An;在偶数个N*T周期内,根据报文的着色标记依次计入对应的N个Count Bn。In view of this, an embodiment of the present application provides a network performance measurement device, including: a processor and 2N counters, the 2N counters include N counters Count An and N counters Count Bn, where N is 2. Even times, the value of n is a natural number from 0 to N-1; there are N kinds of coloring marks for the message, a counter Count An and a counter Count Bn corresponding to calculate the number of a kind of coloring mark message; the coloring cycle is T, read Take the cycle as N*T; the processor is used to count the corresponding N Count An according to the coloring mark of the message in an odd number of N*T cycles; in an even number of N*T cycles, according to the report The coloring marks of the text are counted in the corresponding N Count Bn in turn.
本申请实施例还提供了一种网络性能测量装置,包括:处理器和2N个计数器,所述2N个计数器包括N个计数器Count An和N个计数器Count Bn,所述N为2的偶数倍,n取值为0到N-1的自然数;报文的着色标记有A和B两种;着色周期为T,读取周期为N*T;一个计数器Count An和一个计数器Count Bn对应计算一个2T周期内一种着色标记报文的数量;所述处理器,用于在奇数个N*T周期内,将-T/2—3T/2时间内着色为A的报文计入对应的计数器Count A0;T/2~5T/2时间内着色为B的报文计入对应的计数器Count A1;3T/2~7T/2时间内着色为A的报文计入对应的计数器Count A2;5T/2~9T/2时间内着色为B的报文计入对应的计数器Count A3;依次类推直到读取周期结束;在偶数个N*T周期内,将-T/2—3T/2时间内着色为A的报文计入对应的计数器Count B0;T/2~5T/2时间内着色为B的报文计入对应的计数器Count B1;3T/2~7T/2时间内着色为A的报文计入对应的计数器Count B2;5T/2~9T/2时间内着色为B的报文计入对应的计数器Count B3;依次类推直到读取周期结束。An embodiment of the present application also provides a network performance measurement device, including: a processor and 2N counters, the 2N counters include N counters Count An and N counters Count Bn, where N is an even multiple of 2. The value of n is a natural number from 0 to N-1; there are two types of coloring tags for the message: A and B; the coloring cycle is T, and the reading cycle is N*T; a counter Count An and a counter Count Bn are corresponding to a 2T The number of colored marking messages in a cycle; the processor is configured to count the messages colored as A in the period -T/2—3T/2 into the corresponding counter Count in an odd number of N*T cycles A0; the packets colored as B within T/2~5T/2 are counted into the corresponding counter Count A1; the packets colored as A within the time 3T/2~7T/2 count into the corresponding counter Count A2; 5T/ Packets colored as B within 2-9T/2 are counted into the corresponding counter Count A3; and so on until the end of the reading cycle; within an even number of N*T cycles, colored within -T/2-3T/2 The message that is A is counted in the corresponding counter Count B0; the message that is colored as B within T/2~5T/2 is counted into the corresponding counter Count B1; the message that is colored as A within 3T/2~7T/2 The message is counted into the corresponding counter Count B2; the message colored as B within 5T/2 to 9T/2 is counted into the corresponding counter Count B3; and so on until the end of the reading cycle.
本申请实施例还提供了一种网络性能测量装置,包括:处理器和N个计数器,着色周期为T,一个周期T内时延着色报文扩展为N个;所述N为2或者2的偶数倍;报文的着色标记有N种;一个计数器Count对应标记一个着色标记报文的着色时间;所述处理器,用于在T周期内,对每T/N个周期开始的第一个报文进行着色,并将所述报文的着色时间计入对应的计数器Count。An embodiment of the present application also provides a network performance measurement device, including: a processor and N counters, the coloring period is T, and the delay coloring packets within a period T are expanded to N; where N is 2 or 2. Even times; there are N kinds of coloring marks for the message; a counter Count corresponds to marking the coloring time of a coloring mark message; the processor is used for the first one at the beginning of every T/N cycle in the T period The message is colored, and the coloring time of the message is counted into the corresponding counter Count.
本申请实施例还提供了一种网络性能测量装置,包括:处理器和N个计数器,着色周期为T,一个周期T内时延着色报文扩展为N个;所述N为2或者2的偶数倍;报文的着色标记有N种;一个计数器Count按照周期T依次排列对应标记一个着色标记报文的接收时间;所述处理器,用于当着色周期低于读取周期时,将接收到一个着色报文的接收时间写入(接收时间/读取周期)/着色周期,然后向下取整得到对应的计数器,将接收所述着色报文的接收时间计入所述对应的计数器;当着色周期与读取周期一致时,将接收到一个着色报文的 接收时间写入(接收时间/读取周期)*N/着色周期,然后向下取整得到对应的计数器,将接收所述着色报文的接收时间计入所述对应的计数器。An embodiment of the present application also provides a network performance measurement device, including: a processor and N counters, the coloring period is T, and the delay coloring packets within a period T are expanded to N; where N is 2 or 2. Even times; there are N kinds of coloring marks for the message; a counter Count is arranged according to the period T in order to mark the receiving time of a coloring mark message; the processor is used for receiving when the coloring period is lower than the reading period When the receiving time of a colored message is written (receiving time/reading period)/coloring cycle, then round down to obtain the corresponding counter, and the receiving time of receiving the colored message is counted into the corresponding counter; When the coloring period is the same as the reading period, write the receiving time of a coloring message (receiving time/reading period)*N/coloring period, and then round down to get the corresponding counter, which will receive the The receiving time of the colored message is included in the corresponding counter.
本申请实施例还提供了一种网络性能测量方法,应用于网络性能测量装置,所述网络性能测量装置包括:处理器和2N个计数器,所述2N个计数器包括N个计数器Count An和N个计数器Count Bn,所述N为2的偶数倍,n取值为0到N-1的自然数;报文的着色标记有N种,一个计数器Count An和一个计数器Count Bn对应计算一种着色标记报文的数量;着色周期为T,读取周期为N*T;所述处理器在奇数个N*T周期内,根据报文的着色标记依次计入对应的N个Count An;在偶数个N*T周期内,根据报文的着色标记依次计入对应的N个Count Bn。The embodiment of the present application also provides a network performance measurement method, which is applied to a network performance measurement device. The network performance measurement device includes a processor and 2N counters. The 2N counters include N counters Count An and N counters. The counter Count Bn, the N is an even multiple of 2, and n is a natural number from 0 to N-1; there are N types of coloring tags for the message, and a counter Count An and a counter Count Bn respectively calculate a coloring tag report The number of messages; the coloring cycle is T, and the reading cycle is N*T; the processor counts the corresponding N Count An according to the coloring flag of the message in an odd number of N*T cycles; in an even number of N *In the T period, the corresponding N Count Bn are counted in sequence according to the coloring mark of the message.
本申请实施例还提供了一种网络性能测量方法,应用于网络性能测量装置,所述网络性能测量装置包括:处理器和2N个计数器,所述2N个计数器包括N个计数器Count An和N个计数器Count Bn,所述N为2的偶数倍,n取值为0到N-1的自然数;报文的着色标记有A和B两种;着色周期为T,读取周期为N*T;一个计数器Count An和一个计数器Count Bn对应计算一个2T周期内一种着色标记报文的数量;所述处理器在奇数个N*T周期内,将-T/2—3T/2时间内着色为A的报文计入对应的计数器Count A0;T/2~5T/2时间内着色为B的报文计入对应的计数器Count A1;3T/2~7T/2时间内着色为A的报文计入对应的计数器Count A2;5T/2~9T/2时间内着色为B的报文计入对应的计数器Count A3;依次类推直到读取周期结束;在偶数个N*T周期内,将-T/2—3T/2时间内着色为A的报文计入对应的计数器Count B0;T/2~5T/2时间内着色为B的报文计入对应的计数器Count B1;3T/2~7T/2时间内着色为A的报文计入对应的计数器Count B2;5T/2~9T/2时间内着色为B的报文计入对应的计数器Count B3;依次类推直到读取周期结束。The embodiment of the present application also provides a network performance measurement method, which is applied to a network performance measurement device. The network performance measurement device includes a processor and 2N counters. The 2N counters include N counters Count An and N counters. The counter Count Bn, the N is an even multiple of 2, and the value of n is a natural number from 0 to N-1; the coloring flag of the message has two types: A and B; the coloring period is T, and the reading period is N*T; A counter Count An and a counter Count Bn correspondingly calculate the number of a coloring flag message in a 2T cycle; the processor colorizes -T/2—3T/2 within an odd number of N*T cycles as The message of A is counted into the corresponding counter Count A0; the message colored as B within T/2~5T/2 counts into the corresponding counter Count A1; the message colored as A within 3T/2~7T/2 Count into the corresponding counter Count A2; messages colored as B within 5T/2 to 9T/2 are counted into the corresponding counter Count A3; and so on until the end of the reading cycle; in an even number of N*T cycles, the- The messages colored as A within T/2—3T/2 are counted into the corresponding counter Count B0; the messages colored as B within T/2~5T/2 are counted into the corresponding counter Count B1; 3T/2~ Messages colored as A within 7T/2 are counted into the corresponding counter Count B2; messages colored as B within 5T/2 to 9T/2 are counted into the corresponding counter Count B3; and so on until the end of the reading cycle.
本申请实施例还提供了一种网络性能测量方法,应用于网络性能测量装置,The embodiment of the present application also provides a network performance measurement method, which is applied to a network performance measurement device,
所述网络性能测量装置包括:处理器和N个计数器,着色周期为T,一个周期T内时延着色报文扩展为N个;所述N为2或者2的偶数倍;一个计数器Count对应标记一个着色标记报文的着色时间;所述处理器在T周期内,对每T/N个周期开始的第一个报文进行着色,并将所述报文的着色时间计入对应的计数器Count。The network performance measurement device includes: a processor and N counters, the coloring period is T, and the delay coloring message is expanded to N in a period T; the N is 2 or an even multiple of 2; a counter Count corresponds to a mark The coloring time of a coloring flag message; the processor colorizes the first message starting every T/N cycle within T cycles, and counts the coloring time of the message into the corresponding counter Count .
本申请实施例还提供了一种网络性能测量方法,应用于网络性能测量装置,所述网络性能测量装置包括:处理器和N个计数器,着色周期为T,一个周期T内时延着色报文扩展为N个;所述N为2或者2的偶数倍;一个计数器Count按照周期T依次排列对应标记一个着色标记报文的接收时间;当着色周期低于读取周期时,所述处理器将接收到一个着色报文的接收时间写入(接收时间/读取周期)/着色周期,然后向下取整得到对应的计数器,将接收所述着色报文的接收时间计入所述对应的计数器;当着色周期与读取周期一致时,所述处理器将接收到一个着色报文的接收时间写入(接收时间/读取周期)*N/着色周期,然后向下取整得到对应的计数器,将接收所述着色报文的接收时间计入所述对应的计数器。The embodiment of the present application also provides a network performance measurement method, which is applied to a network performance measurement device. The network performance measurement device includes a processor and N counters, the coloring period is T, and the coloring message is delayed within a period T. Expanded to N; the N is 2 or an even multiple of 2; a counter Count is arranged in sequence according to the period T to mark the receiving time of a coloring flag message; when the coloring period is lower than the reading period, the processor will The receiving time of receiving a coloring message is written (receiving time/reading period)/coloring period, and then rounding down to get the corresponding counter, and the receiving time of receiving the coloring message is counted into the corresponding counter ; When the coloring cycle is consistent with the read cycle, the processor writes the receiving time of a coloring message (receiving time/reading cycle)*N/coloring cycle, and then rounds down to get the corresponding counter Calculate the receiving time of receiving the colored message into the corresponding counter.
本申请的其它特征和优点将在随后的说明书中阐述,并且,部分地从说明书中变得显而易见,或者通过实施本申请而了解。本申请的目的和其他优点可通过在说明书、权利要求书以及附图中所特别指出的结构来实现和获得。Other features and advantages of the present application will be described in the following description, and partly become obvious from the description, or understood by implementing the present application. The purpose and other advantages of the application can be realized and obtained through the structures specifically pointed out in the description, claims and drawings.
附图说明Description of the drawings
附图用来提供对本申请技术方案的进一步理解,并且构成说明书的一部分,与本申请的实施例一起用于解释本申请的技术方案,并不构成对本申请技术方案的限制。The accompanying drawings are used to provide a further understanding of the technical solution of the present application, and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the technical solution of the present application, and do not constitute a limitation to the technical solution of the present application.
图1为现有RFC8321交替着色示意图;Figure 1 is a schematic diagram of the existing RFC8321 alternate coloring;
图2为本申请一实施例提供的一种网络性能测量装置的结构示意图;2 is a schematic structural diagram of a network performance measurement device provided by an embodiment of this application;
图3为本申请另一实施例提供的一种网络性能测量装置的结构示意图;3 is a schematic structural diagram of a network performance measurement device provided by another embodiment of this application;
图4为本申请一实施例提供的一种网络性能测量系统的结构示意图;4 is a schematic structural diagram of a network performance measurement system provided by an embodiment of this application;
图5为本申请另一实施例中的报文着色示意图;5 is a schematic diagram of packet coloring in another embodiment of the application;
图6为本申请另一实施例中的报文着色示意图;FIG. 6 is a schematic diagram of packet coloring in another embodiment of the application;
图7为本申请一实施例提供的一种网络性能测量装置的结构示意图;FIG. 7 is a schematic structural diagram of a network performance measurement device provided by an embodiment of this application;
图8为本申请一实施例提供的一种网络性能测量装置的结构示意图;FIG. 8 is a schematic structural diagram of a network performance measurement device provided by an embodiment of this application;
图9为本申请一实施例提供的一种网络性能测量系统的结构示意图;FIG. 9 is a schematic structural diagram of a network performance measurement system provided by an embodiment of this application;
图10为本申请另一实施例中的报文着色示意图;10 is a schematic diagram of packet coloring in another embodiment of the application;
图11为本申请一实施例提供的一种网络性能测量方法的流程示意图;FIG. 11 is a schematic flowchart of a network performance measurement method provided by an embodiment of this application;
图12为本申请另一实施例提供的一种网络性能测量方法的流程示意图;FIG. 12 is a schematic flowchart of a network performance measurement method provided by another embodiment of this application;
图13为本申请另一实施例提供的一种网络性能测量方法的流程示意图;FIG. 13 is a schematic flowchart of a network performance measurement method provided by another embodiment of this application;
图14为本申请另一实施例提供的一种网络性能测量方法的流程示意图;FIG. 14 is a schematic flowchart of a network performance measurement method provided by another embodiment of this application;
图15为本申请另一实施例提供的一种网络性能测量方法的流程示意图;15 is a schematic flowchart of a method for measuring network performance according to another embodiment of this application;
图16为本申请另一实施例提供的一种网络性能测量方法的流程示意图。FIG. 16 is a schematic flowchart of a method for measuring network performance according to another embodiment of this application.
具体实施方式Detailed ways
为使本申请的目的、技术方案和优点更加清楚明白,下文中将结合附图对本申请的实施例进行详细说明。需要说明的是,在不冲突的情况下,本申请中的实施例及实施例中的特征可以相互任意组合。In order to make the purpose, technical solutions, and advantages of the present application clearer, the embodiments of the present application will be described in detail below in conjunction with the accompanying drawings. It should be noted that the embodiments in this application and the features in the embodiments can be combined with each other arbitrarily if there is no conflict.
在附图的流程图示出的步骤可以在诸如一组计算机可执行指令的计算机系统中执行。并且,虽然在流程图中示出了逻辑顺序,但是在某些情况下,可以以不同于此处的顺序执行所示出或描述的步骤。The steps shown in the flowchart of the drawings may be executed in a computer system such as a set of computer-executable instructions. And, although a logical sequence is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than here.
本申请实施例的主要思想是通过扩展着色标记数量和计数器数量,克服现有技术中短周期测试计数不稳定,长周期样本数不足导致计算偏差较大等问题,从而提升基于RFC8321测试性能数据的有效性和可靠性。The main idea of the embodiments of this application is to overcome the instability of short-period test counting in the prior art by expanding the number of coloring marks and the number of counters, and the insufficient number of long-period samples leads to large calculation deviations, etc., thereby improving the performance data based on RFC8321 Effectiveness and reliability.
图2为本申请一实施例提供的一种网络性能测量装置的结构示意图,如图2所示,该网络性能测量装置包括:FIG. 2 is a schematic structural diagram of a network performance measurement device provided by an embodiment of the application. As shown in FIG. 2, the network performance measurement device includes:
处理器和2N个计数器,所述2N个计数器包括N个计数器Count An和N个计数器Count Bn,所述N为2的偶数倍,n取值为0到N-1的自然数;报文的着色标记有N种,一个计数器Count An和一个计数器Count Bn对应计算一种着色标记报文的数量;着色周期为T,读取周期为N*T;Processor and 2N counters, the 2N counters include N counters Count An and N counters Count Bn, where N is an even multiple of 2, and n is a natural number from 0 to N-1; coloring of packets There are N types of tags, a counter Count An and a counter Count Bn correspondingly calculate the number of a coloring tag message; the coloring cycle is T, and the reading cycle is N*T;
所述处理器,用于在奇数个N*T周期内,根据报文的着色标记依次计入对应的N个Count An;在偶数个N*T周期内,根据报文的着色标记依次计入对应的N个Count Bn。The processor is configured to sequentially count the corresponding N Count An according to the coloring mark of the message in an odd number of N*T cycles; and sequentially count the corresponding N Count An according to the coloring mark of the message in an even number of N*T cycles The corresponding N Count Bn.
其中,该网络性能测量装置可以设置在路由器、网关、交换机等设备中。Among them, the network performance measurement device can be set in routers, gateways, switches and other equipment.
图3为本申请另一实施例提供的一种网络性能测量装置的结构示意图,如图3所示,该网络性能测量装置包括:FIG. 3 is a schematic structural diagram of a network performance measurement device provided by another embodiment of the application. As shown in FIG. 3, the network performance measurement device includes:
处理器和2N个计数器,所述2N个计数器包括N个计数器Count An和N个计数器Count Bn,所述N为2的偶数倍,n取值为0到N-1的自然数;报文的着色标记有A和B两种;着色周期为T,读取周期为N*T;一个计数器Count An和一个计数器Count Bn对应计算一个2T周期内一种着色标记报文的数量;Processor and 2N counters, the 2N counters include N counters Count An and N counters Count Bn, where N is an even multiple of 2, and n is a natural number from 0 to N-1; coloring of packets There are two types of markers: A and B; the coloring cycle is T, and the reading cycle is N*T; a counter Count An and a counter Count Bn correspondingly count the number of a coloring tag message in a 2T cycle;
所述处理器,用于在奇数个N*T周期内,将-T/2—3T/2时间内着色为A的报文计入对应的计数器Count A0;T/2~5T/2时间内着色为B的报文计入对应的计数器Count A1;3T/2~7T/2时间内着色为A的报文计入对应的计数器Count A2;5T/2~9T/2时间内着色为B的报文计入对应的计数器Count A3;依次类推直到读取周期结束;The processor is configured to count the packets colored as A within the period of -T/2—3T/2 into the corresponding counter Count A0 within an odd number of N*T cycles; within the period of T/2—5T/2 Messages colored as B are counted in the corresponding counter Count A1; messages colored as A within 3T/2~7T/2 are counted into the corresponding counter Count A2; messages colored as B within 5T/2~9T/2 The message is counted into the corresponding counter Count A3; and so on until the end of the reading cycle;
在偶数个N*T周期内,将-T/2—3T/2时间内着色为A的报文计入对应的计数器Count B0;T/2~5T/2时间内着色为B的报文计入对应的计数器Count B1;3T/2~7T/2时间内着色为A的报文计入对应的计数器Count B2;5T/2~9T/2时间内着色为B的报文计入对应的计数器Count B3;依次类推直到读取周期结束。In an even number of N*T cycles, the packets colored as A within -T/2—3T/2 are counted into the corresponding counter Count B0; the packets colored as B within T/2~5T/2 are counted Enter the corresponding counter Count B1; the packets colored as A within 3T/2~7T/2 are counted into the corresponding counter Count B2; the packets colored as B within 5T/2~9T/2 are counted into the corresponding counter Count B3; and so on until the end of the read cycle.
其中,所述标记A为0,所述标记B为1。Wherein, the mark A is 0, and the mark B is 1.
其中,该网络性能测量装置可以设置在路由器、网关、交换机等设备中。Among them, the network performance measurement device can be set in routers, gateways, switches and other equipment.
图4为本申请一实施例提供的一种网络性能测量系统的结构示意图,如图4所示,该系统包括:FIG. 4 is a schematic structural diagram of a network performance measurement system provided by an embodiment of the application. As shown in FIG. 4, the system includes:
网管和传输报文的源节点和宿节点或中间节点,The source node and sink node or intermediate node of network management and transmission message,
所述源节点,包括:第一处理器和2N个计数器;The source node includes: a first processor and 2N counters;
所述宿节点或中间节点,包括:第二处理器和2N个计数器;The sink node or intermediate node includes: a second processor and 2N counters;
所述2N个计数器包括N个计数器Count An和N个计数器Count Bn,所述N为2的偶数倍,n取值为0到N-1的自然数;报文的着色标记有N种,一个计数器Count An和一个计数器Count Bn对应计算一种着色标记报文的数量;着色周期为T,读取周期为N*T;The 2N counters include N counters Count An and N counters Count Bn, where N is an even multiple of 2, and n is a natural number from 0 to N-1; there are N types of coloring tags for packets, one counter Count An and a counter Count Bn respectively calculate the number of a coloring mark message; the coloring cycle is T, and the reading cycle is N*T;
所述第一处理器,用于对报文进行着色和发送;在奇数个N*T周期内,根据报文的着色标记依次计入对应的N个Count An;在偶数个N*T周期内,根据报文的着色标记依次计入对应的N个Count Bn;The first processor is configured to color and send the message; in an odd number of N*T cycles, the corresponding N Count An are counted in sequence according to the coloring flag of the message; in an even number of N*T cycles , Count the corresponding N Count Bn in turn according to the coloring mark of the message;
所述第二处理器,用于接收报文;在奇数个N*T周期内,根据报文的着色标记依次计入对应的N个Count An;在偶数个N*T周期内,根据报文的着色标记依次计入对应的N个Count Bn;The second processor is configured to receive a message; in an odd number of N*T cycles, the corresponding N Count An is counted in sequence according to the coloring flag of the message; in an even number of N*T cycles, according to the message The colored marks of are counted in the corresponding N Count Bn in turn;
所述网管,用于在每N*T个周期的中间点读取所述源节点和所述宿节点或中间节点中计数器的数据,计算丢包率。The network management system is configured to read the counter data of the source node and the sink node or the intermediate node at an intermediate point of every N*T cycles, and calculate the packet loss rate.
其中,上述节点中可以设置所述网络性能测量装置。Wherein, the network performance measurement device may be provided in the above-mentioned node.
图5为本申请另一实施例中的报文着色示意图。本实施例中,着色周期为T,读取周期为4T,传输数据的每一个节点中都可以设置网络性能测量装置,每一个网络性能测量装置中都设置8个计数器(CountA0~CountA3,CountB0~CountB3)。FIG. 5 is a schematic diagram of packet coloring in another embodiment of the application. In this embodiment, the coloring period is T and the reading period is 4T. Each node that transmits data can be equipped with a network performance measurement device, and each network performance measurement device is provided with 8 counters (CountA0~CountA3, CountB0~ CountB3).
如图5所示,本实施例中,着色标记有四种:0000,1111,2222,3333。As shown in FIG. 5, in this embodiment, there are four kinds of colored marks: 0000, 1111, 2222, and 3333.
在传输数据的源节点,对于数据块B(Block)1-16,按照着色周期进行着色,例如数据块B1着色为0000,数据块B2着色为1111,数据块B3着色为2222,数据块B4着色为3333,依次类推。其中,在奇数个4T周期内,报文根据着色分别放入Count A(CountA0~CountA3);在偶数个4T周期内,报文根据着色分别放入Count B(CountB0~CountB3)。At the source node of the transmission data, the data block B (Block) 1-16 is colored according to the coloring cycle, for example, data block B1 is colored 0000, data block B2 is colored 1111, data block B3 is colored 2222, and data block B4 is colored It is 3333, and so on. Among them, in the odd number of 4T cycles, the message is put into Count A (CountA0~CountA3) according to the coloring; in the even number of 4T cycles, the message is put into Count B (CountB0~CountB3) according to the coloring.
同样地,在传输数据的宿节点或中间节点,在奇数个4T周期内,报文根据着色分别放入Count A(CountA0~CountA3);在偶数个4T周期内,报文根据着色分别放入CountB(CountB0~CountB3)。Similarly, at the sink node or intermediate node that transmits data, in odd 4T cycles, packets are put into CountA (CountA0~CountA3) according to their coloring; in even 4T cycles, packets are put into CountB according to their coloring (CountB0~CountB3).
具体而言,对于支持着色数量扩展场景,报文着色值为(当前时间/读取周期)/着色周期,然后向下取整确定对应的计数器,报文根据着色值和奇偶周期计入对应的计数器。Specifically, for scenarios that support the expansion of the number of coloring, the coloring value of the message is (current time/read cycle)/coloring cycle, and then rounded down to determine the corresponding counter. The message is counted into the corresponding counter according to the coloring value and parity cycle. counter.
网管可以每4T周期的中间时间点读取传输路径上各个节点中上一次4T的 4组性能数据,从而计算丢包率。例如可以将源节点中Count A(CountA0~CountA3)中的数据与宿节点中的Count A(CountA0~CountA3)中的数据一一对应,得到四组丢包数量,可以取平均值、最大值或者最小值作为丢包率。The network manager can read the last 4T performance data of each node in the transmission path at the intermediate time of the 4T cycle to calculate the packet loss rate. For example, the data in Count A (CountA0 ~ CountA3) in the source node can be one-to-one corresponding to the data in Count A (CountA0 ~ CountA3) in the sink node to obtain the number of lost packets in four groups, which can be the average, maximum, or The minimum value is used as the packet loss rate.
在本申请的另一实施例中,在上一实施例的基础上,对于更短的着色周期T,读取周期比率可以进一步扩展,例如10T、100T等,与之对应的着色标记数量和计数器数量也需要相应的进行扩充。In another embodiment of the present application, on the basis of the previous embodiment, for a shorter coloring period T, the reading period ratio can be further expanded, such as 10T, 100T, etc., and the corresponding coloring mark number and counter The quantity needs to be expanded accordingly.
图6为本申请另一实施例中的报文着色示意图。本实施例中,着色周期为T,读取周期为4T,传输数据的每一个节点中都可以设置网络性能测量装置,每一个网络性能测量装置中都设置8个计数器(CountA0~CountA3,CountB0~CountB3)。FIG. 6 is a schematic diagram of packet coloring in another embodiment of the application. In this embodiment, the coloring period is T and the reading period is 4T. Each node that transmits data can be equipped with a network performance measurement device, and each network performance measurement device is provided with 8 counters (CountA0~CountA3, CountB0~ CountB3).
报文着色主要是对业务报文某些特定字段进行标记,不同的业务报文可以标记的数量是有限制的。极端情况就只有1比特可供标记,只能着色为0和1,即RFC8321提供的标记方式。这种场景里,上面实施例提供的扩展着色标记数量方案不可行。Message coloring is mainly to mark certain specific fields of business messages, and the number of different business messages that can be marked is limited. In the extreme case, only 1 bit is available for marking and can only be colored as 0 and 1, which is the marking method provided by RFC8321. In this scenario, the solution for expanding the number of colored marks provided in the above embodiment is not feasible.
为此,本实施例提供了一种增强的交替着色方案。如图6所示,本实施例中,着色标记有两种:0000,1111,To this end, this embodiment provides an enhanced alternate coloring scheme. As shown in Figure 6, in this embodiment, there are two types of colored marks: 0000, 1111,
在传输数据的源节点,对于数据块B(Block)1-16,按照着色周期进行着色,例如数据块B1着色为0000,数据块B2着色为1111,数据块B3着色为0000,数据块B4着色为1111,依次类推。其中,在奇数个4T周期内,-T/2~3T/2时间内,着色为0的报文计入CountA0;T/2~5T/2时间内,着色为1的报文计入CountA1;3T/2~7T/2时间内,着色为0的报文计入CountA2;5T/2~9T/2时间内,着色为1的报文计入CountA3。在偶数个4T周期内,计数与奇数周期类似,只是报文计入到CountB0~CountB3。At the source node of the transmission data, the data block B (Block) 1-16 is colored according to the coloring cycle, for example, data block B1 is colored 0000, data block B2 is colored 1111, data block B3 is colored 0000, and data block B4 is colored 1111, and so on. Among them, in an odd number of 4T cycles, within -T/2~3T/2, packets colored as 0 are included in CountA0; within T/2~5T/2, packets colored as 1 are included in CountA1; Within 3T/2~7T/2, packets colored as 0 are counted as CountA2; within 5T/2~9T/2, packets colored as 1 are counted as CountA3. In an even number of 4T cycles, counting is similar to an odd number cycle, except that the message is counted into CountB0~CountB3.
同样地,在传输数据的宿节点或中间节点,在奇数个4T周期内,-T/2~3T/2时间内,着色为0的报文计入CountA0;T/2~5T/2时间内,着色为1的报文计入CountA1;3T/2~7T/2时间内,着色为0的报文计入CountA2;5T/2~9T/2时 间内,着色为1的报文计入CountA3。在偶数个4T周期内,计数与奇数周期类似,只是报文计入到CountB0~CountB3。Similarly, at the sink node or intermediate node that transmits data, within an odd number of 4T cycles, within -T/2~3T/2, packets colored as 0 are included in CountA0; within T/2~5T/2 , The message colored 1 is counted into CountA1; within 3T/2~7T/2, the message colored 0 is counted into CountA2; within 5T/2~9T/2, the message colored 1 is counted into CountA3 . In an even number of 4T cycles, counting is similar to an odd number cycle, except that the message is counted into CountB0~CountB3.
具体而言,对于不支持着色标记数量扩展场景,在当前着色周期T开始前T/2到当前着色周期T结束后T/2周期范围内的报文计入该周期对应的计数器中。Specifically, for scenes that do not support the expansion of the number of coloring marks, packets in the range of T/2 before the start of the current coloring period T to T/2 after the end of the current coloring period T are counted in the counter corresponding to the period.
网管可以每4T周期的中间时间点读取传输路径上各个节点中上一次4T的4组性能数据,从而计算丢包率。例如可以将源节点中Count A(CountA0~CountA3)中的数据与宿节点中的Count A(CountA0~CountA3)中的数据一一对应,得到四组丢包数量,可以取平均值、最大值或者最小值作为丢包率。The network manager can read the last 4T performance data of each node on the transmission path at the intermediate time of the 4T cycle to calculate the packet loss rate. For example, the data in Count A (CountA0 ~ CountA3) in the source node can be one-to-one corresponding to the data in Count A (CountA0 ~ CountA3) in the sink node to obtain the number of lost packets in four groups, which can be the average, maximum, or The minimum value is used as the packet loss rate.
在本申请的另一实施例中,在上一实施例的基础上,对于更短的着色周期T,同样可以通过扩展计数器的数量来扩大读取周期。In another embodiment of the present application, based on the previous embodiment, for a shorter coloring period T, the reading period can also be enlarged by expanding the number of counters.
图7为本申请一实施例提供的一种网络性能测量装置的结构示意图,如图7所示,该网络性能测量装置包括:FIG. 7 is a schematic structural diagram of a network performance measurement device provided by an embodiment of the application. As shown in FIG. 7, the network performance measurement device includes:
处理器和N个计数器,着色周期为T,一个周期T内时延着色报文扩展为N个;所述N为2或者2的偶数倍;报文的着色标记有N种;一个计数器Count对应标记一个着色标记报文的着色时间;The processor and N counters, the coloring period is T, and the delay coloring message within a period T is expanded to N; the N is 2 or an even multiple of 2; there are N kinds of coloring marks for the message; a counter Count corresponds Mark the coloring time of a coloring tag message;
所述处理器,用于在T周期内,对每T/N个周期开始的第一个报文进行着色,并将所述报文的着色时间计入对应的计数器Count。The processor is configured to color the first message starting every T/N cycle in the T period, and count the coloring time of the message into the corresponding counter Count.
其中,该网络性能测量装置可以设置在路由器、网关、交换机等设备中。Among them, the network performance measurement device can be set in routers, gateways, switches and other equipment.
图8为本申请一实施例提供的一种网络性能测量装置的结构示意图,如图8所示,该网络性能测量装置包括:FIG. 8 is a schematic structural diagram of a network performance measurement device provided by an embodiment of the application. As shown in FIG. 8, the network performance measurement device includes:
处理器和N个计数器,着色周期为T,一个周期T内时延着色报文扩展为N个;所述N为2或者2的偶数倍;报文的着色标记有N种;一个计数器Count按照周期T依次排列对应标记一个着色标记报文的接收时间;Processors and N counters, the coloring cycle is T, and the delay coloring message in a cycle T is expanded to N; the N is 2 or an even multiple of 2; there are N kinds of coloring marks for the message; a counter Count according to The period T sequentially arranges the receiving time of correspondingly marked a colored marked message;
所述处理器,用于当着色周期低于读取周期时,将接收到一个着色报文的接收时间写入(接收时间/读取周期)/着色周期,然后向下取整得到对应的计数器,将接收所述着色报文的接收时间计入所述对应的计数器;当着色周期与读取周期一致时,将接收到一个着色报文的接收时间写入(接收时间/读取周期)*N/着色周期,然后向下取整得到对应的计数器,将接收所述着色报文的接收时间计入所述对应的计数器。The processor is used to write the receiving time (receiving time/reading period)/coloring period of a coloring message when the coloring period is lower than the reading period, and then round down to obtain the corresponding counter , The receiving time of receiving the coloring message is counted into the corresponding counter; when the coloring period is consistent with the reading period, the receiving time of receiving a coloring message is written (receiving time/reading period)* N/coloring period, then round down to obtain a corresponding counter, and count the receiving time of receiving the coloring message into the corresponding counter.
其中,该网络性能测量装置可以设置在路由器、网关、交换机等设备中。Among them, the network performance measurement device can be set in routers, gateways, switches and other equipment.
图9为本申请一实施例提供的一种网络性能测量系统的结构示意图,如图9所示,该系统包括:网管和传输报文的源节点和宿节点或中间节点。Fig. 9 is a schematic structural diagram of a network performance measurement system provided by an embodiment of the application. As shown in Fig. 9, the system includes: a network management and a source node and a sink node or intermediate nodes for transmitting packets.
所述源节点,包括:第一处理器和N个计数器,所述路由器源节点中的一个计数器Count按照周期T依次排列对应标记一个着色标记报文的着色时间。The source node includes: a first processor and N counters, and a counter Count in the router source node sequentially arranges the coloring time corresponding to a coloring flag packet according to the period T.
所述宿节点或中间节点,包括:第二处理器和N个计数器,所述路由器宿节点中的一个计数器Count按照周期T依次排列对应标记一个着色标记报文的接收时间。The sink node or intermediate node includes: a second processor and N counters, and a counter Count in the router sink node sequentially arranges the receiving time corresponding to a colored marking message according to the period T.
着色周期为T,一个周期T内时延着色报文扩展为N个;报文的着色标记有N种;所述N为2或者2的偶数倍。The coloring period is T, and the time-delay coloring message is expanded to N in a period T; there are N kinds of coloring marks for the message; the N is 2 or an even multiple of 2.
所述第一处理器,用于发送报文,并在T周期内,对每T/N个周期开始的第一个报文进行着色,并将所述报文的着色时间计入对应的计数器Count。The first processor is configured to send a message, and in the T cycle, color the first message starting every T/N cycle, and count the coloring time of the message into the corresponding counter Count.
所述第二处理器,用于接收报文,当着色周期低于读取周期时,将接收到一个着色报文的接收时间写入(接收时间/读取周期)/着色周期,然后向下取整得到对应的计数器,将接收所述着色报文的接收时间计入所述对应的计数器;当着色周期与读取周期一致时,将接收到一个着色报文的接收时间写入(接收时间/读取周期)*N/着色周期,然后向下取整得到对应的计数器,将接收所述着色报文的接收时间计入所述对应的计数器。The second processor is configured to receive a message, and when the coloring period is lower than the reading period, write the receiving time of a coloring message into (receiving time/reading period)/coloring period, and then down Round to get the corresponding counter, and count the receiving time of the coloring message into the corresponding counter; when the coloring period is the same as the reading period, write the receiving time of a coloring message (receive time /Reading period)*N/coloring period, then round down to obtain the corresponding counter, and count the receiving time of receiving the coloring message into the corresponding counter.
所述网管,用于在每T个周期的中间点读取所述源节点和所述宿节点或中间节点中计数器的数据,计算网络时延。The network management system is configured to read the counter data of the source node and the sink node or the intermediate node at an intermediate point of every T period, and calculate the network delay.
图5同样为本申请另一实施例中的报文着色示意图。本实施例中,着色周期为T,读取周期为4T,传输数据的每一个节点中都可以设置网络性能测量装置,每一个网络性能测量装置中都设置8个计数器(CountA0~CountA3,CountB0~CountB3)。FIG. 5 is also a schematic diagram of packet coloring in another embodiment of the application. In this embodiment, the coloring period is T and the reading period is 4T. Each node that transmits data can be equipped with a network performance measurement device, and each network performance measurement device is provided with 8 counters (CountA0~CountA3, CountB0~ CountB3).
如图5所示,本实施例中,着色标记有四种:0000,1111,2222,3333。As shown in FIG. 5, in this embodiment, there are four kinds of colored marks: 0000, 1111, 2222, and 3333.
在传输数据的源节点,对于数据块B(Block)1-16,按照着色周期进行着色,例如数据块B1着色为0000,数据块B2着色为1111,数据块B3着色为2222,数据块B4着色为3333,依次类推。其中,在奇数个4T周期内,报文根据着色分别将报文的着色时间计入Count A(CountA0~CountA3);在偶数个4T周期内,报文根据着色分别将报文的着色时间计入Count B(CountB0~CountB3)。At the source node of the transmission data, the data block B (Block) 1-16 is colored according to the coloring cycle, for example, data block B1 is colored 0000, data block B2 is colored 1111, data block B3 is colored 2222, and data block B4 is colored It is 3333, and so on. Among them, in the odd number of 4T cycles, the coloring time of the message is included in Count A (CountA0~CountA3) according to the coloring; in the even number of 4T cycles, the coloring time of the message is included in the coloring time of the message. Count B (CountB0~CountB3).
具体而言,对于支持着色标记数量扩展场景,报文着色值为(当前时间/读取周期)/着色周期,然后向下取整确定对应的计数器,并将报文的着色时间计入对应的计数器。例如,着色周期低于读取周期的场景,将报文的着色时间写入(接收时间/读取周期)/着色周期,然后向下取整得到对应的计数器,将报文的着色时间计入所述对应的计数器。着色周期与读取周期一致的场景,可以在每周期插入N个时延着色报文,即每1/N周期对第一个业务报文进行时延着色。Specifically, for scenarios that support the expansion of the number of coloring marks, the coloring value of the message is (current time/read cycle)/coloring cycle, then round down to determine the corresponding counter, and the coloring time of the message is included in the corresponding counter. For example, if the coloring cycle is lower than the reading cycle, write the coloring time of the message (receiving time/reading cycle)/coloring cycle, then round down to get the corresponding counter, and count the coloring time of the message The corresponding counter. In a scenario where the coloring cycle is consistent with the reading cycle, N delay coloring messages can be inserted in each cycle, that is, the first service message is delayed coloring every 1/N cycle.
同样地,在传输数据的宿节点或中间节点,在奇数个4T周期内,报文根据着色分别将报文的接收时间计入Count A(CountA0~CountA3);在偶数个4T周期内,报文根据着色分别分别将报文的接收时间计入CountB(CountB0~CountB3)。Similarly, at the sink node or intermediate node that transmits data, in odd 4T cycles, the message counts the message reception time into Count A (CountA0~CountA3) according to the coloring; in even 4T cycles, the message According to the coloring, the receiving time of the message is counted into CountB (CountB0~CountB3).
具体而言,着色周期低于读取周期的场景,接收到报文的时间写入(当前时间/读取周期)/着色周期,然后向下取整得到对应的计数器中。着色周期与读取周期一致的场景,接收到报文的时间写入(当前时间/着色周期)*N/着色周期,然后向下取整得到对应的计数器中。将报文的接收时间计入所述对应的计数器。Specifically, for scenarios where the coloring cycle is lower than the reading cycle, the time of receiving the message is written (current time/reading cycle)/coloring cycle, and then rounded down to get the corresponding counter. In the scenario where the coloring cycle is consistent with the reading cycle, the time of receiving the message is written (current time/coloring cycle)*N/coloring cycle, and then rounded down to get the corresponding counter. The message receiving time is counted into the corresponding counter.
网管可以每4T周期的中间时间点读取传输路径上各个节点中上一次4T的4组性能数据,从而计算时延。例如可以将源节点中Count A(CountA0~CountA3)中的数据与宿节点中的Count A(CountA0~CountA3)中的数据一一对应,得到四组时间,可以取平均值、最大值或者最小值作为时延值。The network manager can read the last 4T performance data of each node in the transmission path at the intermediate time of the 4T cycle to calculate the delay. For example, the data in Count A (CountA0~CountA3) in the source node can be one-to-one corresponding to the data in Count A (CountA0~CountA3) in the sink node to obtain four sets of times, which can be the average, maximum, or minimum. As the delay value.
在本申请的另一实施例中,在上一实施例的基础上,对于更短的着色周期T,读取周期比率可以进一步扩展,例如10T、100T等,与之对应的着色标记数量和计数器数量也需要相应的进行扩充。In another embodiment of the present application, on the basis of the previous embodiment, for a shorter coloring period T, the reading period ratio can be further expanded, such as 10T, 100T, etc., and the corresponding coloring mark number and counter The quantity needs to be expanded accordingly.
图6同样为本申请另一实施例中的报文着色示意图。本实施例中,着色周期为T,读取周期为4T,传输数据的每一个节点中都可以设置网络性能测量装置,每一个网络性能测量装置中都设置8个计数器(CountA0~CountA3,CountB0~CountB3)。FIG. 6 is also a schematic diagram of packet coloring in another embodiment of the application. In this embodiment, the coloring period is T and the reading period is 4T. Each node that transmits data can be equipped with a network performance measurement device, and each network performance measurement device is provided with 8 counters (CountA0~CountA3, CountB0~ CountB3).
报文着色主要是对业务报文某些特定字段进行标记,不同的业务报文可以标记的数量是有限制的。极端情况就只有1比特可供标记,只能着色为0和1,即RFC8321提供的标记方式。这种场景里,上面实施例提供的扩展着色标记数量方案不可行。Message coloring is mainly to mark certain specific fields of business messages, and the number of different business messages that can be marked is limited. In the extreme case, only 1 bit is available for marking and can only be colored as 0 and 1, which is the marking method provided by RFC8321. In this scenario, the solution for expanding the number of colored marks provided in the above embodiment is not feasible.
为此,本实施例提供了一种增强的交替着色方案。如图6所示,本实施例中,着色标记有两种:0000,1111,To this end, this embodiment provides an enhanced alternate coloring scheme. As shown in Figure 6, in this embodiment, there are two types of colored marks: 0000, 1111,
在传输数据的源节点,对于数据块B(Block)1-16,按照着色周期进行着色,例如数据块B1着色为0000,数据块B2着色为1111,数据块B3着色为0000,数据块B4着色为1111,依次类推。其中,在奇数个4T周期内,-T/2~3T/2时间内,着色为0的报文着色时间计入CountA0;T/2~5T/2时间内,着色为1的报文着色时间计入CountA1;3T/2~7T/2时间内,着色为0的报文着色时间计入CountA2;5T/2~9T/2时间内,着色为1的报文着色时间计入CountA3。在偶数个4T周期内,计数与奇数周期类似,只是报文着色时间计入到CountB0~CountB3。At the source node of the transmission data, the data block B (Block) 1-16 is colored according to the coloring cycle, for example, data block B1 is colored 0000, data block B2 is colored 1111, data block B3 is colored 0000, and data block B4 is colored 1111, and so on. Among them, in an odd number of 4T cycles, within -T/2~3T/2, the coloring time of packets colored as 0 is included in CountA0; within T/2~5T/2, the coloring time of packets colored as 1 CountA1; within 3T/2~7T/2, the coloring time of the message colored 0 is included in CountA2; within 5T/2~9T/2, the coloring time of the message colored 1 is included in CountA3. In even 4T cycles, counting is similar to odd cycles, except that the message coloring time is included in CountB0~CountB3.
同样地,在传输数据的宿节点或中间节点,在奇数个4T周期内,-T/2~3T/2时间内,着色为0的报文接收时间计入CountA0;T/2~5T/2时间内,着色为1的报文接收时间计入CountA1;3T/2~7T/2时间内,着色为0的报文接收时间计入CountA2;5T/2~9T/2时间内,着色为1的报文接收时间计入CountA3。在偶数个4T周期内,计数与奇数周期类似,只是报文接收时间计入到CountB0~CountB3。Similarly, at the sink node or intermediate node that transmits data, within an odd number of 4T cycles, within -T/2~3T/2, the packet reception time colored 0 is included in CountA0; T/2~5T/2 Within the time, the receiving time of the message colored 1 is counted into CountA1; within 3T/2~7T/2, the receiving time of the message colored 0 is counted into CountA2; within 5T/2~9T/2, the coloring is 1 The received time of the message is included in CountA3. In even 4T cycles, counting is similar to odd cycles, except that the message reception time is included in CountB0~CountB3.
具体而言,对于不支持着色标记数量扩展场景,在当前着色周期T开始前T/2到当前着色周期T结束后T/2周期范围内的报文着色或接收时间计入该周期 对应的计数器中。Specifically, for scenes that do not support the expansion of the number of coloring marks, the coloring or receiving time of packets in the range of T/2 before the start of the current coloring period T to T/2 after the end of the current coloring period T is included in the counter corresponding to the period in.
网管可以每4T周期的中间时间点读取传输路径上各个节点中上一次4T的4组性能数据,从而计算时延。例如可以将源节点中Count A(CountA0~CountA3)中的数据与宿节点中的Count A(CountA0~CountA3)中的数据一一对应,得到四组时间,可以取平均值、最大值或者最小值作为时延。The network manager can read the last 4T performance data of each node in the transmission path at the intermediate time of the 4T cycle to calculate the delay. For example, the data in Count A (CountA0~CountA3) in the source node can be one-to-one corresponding to the data in Count A (CountA0~CountA3) in the sink node to obtain four sets of times, which can be the average, maximum, or minimum. As a delay.
在本申请的另一实施例中,在上一实施例的基础上,对于更短的着色周期T,同样可以通过扩展计数器的数量来扩大读取周期。In another embodiment of the present application, based on the previous embodiment, for a shorter coloring period T, the reading period can also be enlarged by expanding the number of counters.
图10同样为本申请另一实施例中的报文着色示意图。本实施例中,着色周期为T1,时延着色报文扩展为N,传输数据的每一个节点中都可以设置网络性能测量装置,每一个网络性能测量装置中都设置N个计数器。FIG. 10 is also a schematic diagram of packet coloring in another embodiment of the application. In this embodiment, the coloring period is T1, and the delayed coloring message is expanded to N. Each node that transmits data can be provided with a network performance measurement device, and each network performance measurement device is provided with N counters.
在传输数据的源节点,可以在每周期内增加时延着色数量。RFC8321提供的方式是对每周期开始的第一个报文进行着色。而本实施例中,通过计数器扩展,可以根据实际情况按需增加时延着色报文数量。例如着色周期为T,时延着色报文扩展为N。对每T/N个周期开始的第一个报文进行着色,并将着色时间计入对应的计数器。At the source node of the data transmission, the number of delay coloring can be increased during each week. The method provided by RFC8321 is to color the first message at the beginning of each cycle. However, in this embodiment, through counter expansion, the number of delay colored packets can be increased as needed according to actual conditions. For example, the coloring period is T, and the delayed coloring message is expanded to N. Color the first message at the beginning of every T/N cycle, and count the coloring time into the corresponding counter.
同样地,在传输数据的宿节点或中间节点,着色周期低于读取周期场景,接收到着色报文的时间写入(当前时间/读取周期)/着色周期,然后向下取整得到对应的扩展计数器;着色周期与读取周期一致的场景,接收到着色报文的时间写入(当前时间/着色周期)*N/着色周期,然后向下取整得到对应的扩展计数器中。将接收时间计入对应的计数器。Similarly, at the sink node or intermediate node that transmits data, the coloring cycle is lower than the read cycle scenario, the time of receiving the coloring message is written (current time/read cycle)/coloring cycle, and then rounded down to get the corresponding When the coloring cycle is the same as the read cycle, the time of receiving the coloring message is written (current time/coloring cycle)*N/coloring cycle, and then rounded down to get the corresponding extended counter. Count the receiving time into the corresponding counter.
网管可以每T周期的中间时间点读取传输路径上各个节点中上一次T的N组性能数据,从而计算时延。例如可以将源节点中N个计数器中的数据与宿节点中的N个计数器中的数据一一对应,得到N组时间,可以取平均值、最大值或者最小值作为时延。The network manager can read the N sets of performance data of the last T in each node on the transmission path at the intermediate time point of every T cycle, so as to calculate the time delay. For example, the data in the N counters in the source node can be one-to-one corresponding to the data in the N counters in the sink node to obtain N sets of time, and the average value, maximum value, or minimum value can be taken as the delay.
在本申请的另一实施例中,在上一实施例的基础上,对于更短的着色周期T,同样可以通过扩展计数器的数量来扩大读取周期。In another embodiment of the present application, based on the previous embodiment, for a shorter coloring period T, the reading period can also be enlarged by expanding the number of counters.
图11为本申请一实施例提供的一种网络性能测量方法的流程示意图,该方法应用于网络性能测量装置,FIG. 11 is a schematic flowchart of a network performance measurement method provided by an embodiment of this application, and the method is applied to a network performance measurement device.
所述网络性能测量装置包括:处理器和2N个计数器,所述2N个计数器包括N个计数器Count An和N个计数器Count Bn,所述N为2的偶数倍,n取值为0到N-1的自然数;报文的着色标记有N种,一个计数器Count An和一个计数器Count Bn对应计算一种着色标记报文的数量;着色周期为T,读取周期为N*T;The network performance measurement device includes: a processor and 2N counters. The 2N counters include N counters CountAn and N counters CountBn, where N is an even multiple of 2, and n takes a value from 0 to N- A natural number of 1; there are N types of coloring tags for messages, a counter CountAn and a counter CountBn corresponding to calculate the number of a coloring tag message; the coloring cycle is T, and the reading cycle is N*T;
如图11所示,包括:As shown in Figure 11, it includes:
步骤1101,所述处理器在奇数个N*T周期内,根据报文的着色标记依次计入对应的N个Count An;在偶数个N*T周期内,根据报文的着色标记依次计入对应的N个Count Bn。Step 1101: The processor counts the corresponding N Count An in the odd number N*T cycles according to the coloring flag of the message; in the even N*T cycles, counts it sequentially according to the coloring tag of the message The corresponding N Count Bn.
其中,该网络性能测量装置可以设置在路由器、网关、交换机等设备中。Among them, the network performance measurement device can be set in routers, gateways, switches and other equipment.
图12为本申请另一实施例提供的一种网络性能测量方法的流程示意图,该方法应用于网络性能测量装置,FIG. 12 is a schematic flowchart of a network performance measurement method provided by another embodiment of this application, and the method is applied to a network performance measurement device.
所述网络性能测量装置包括:处理器和2N个计数器,所述2N个计数器包括N个计数器Count An和N个计数器Count Bn,所述N为2的偶数倍,n取值为0到N-1的自然数;报文的着色标记有A和B两种;着色周期为T,读取周期为N*T;一个计数器Count An和一个计数器Count Bn对应计算一个2T周期内一种着色标记报文的数量;The network performance measurement device includes: a processor and 2N counters. The 2N counters include N counters CountAn and N counters CountBn, where N is an even multiple of 2, and n takes a value from 0 to N- A natural number of 1; there are two types of coloring tags for the message: A and B; the coloring cycle is T, and the reading cycle is N*T; a counter Count An and a counter Count Bn correspond to a coloring tag message in a 2T cycle quantity;
如图12所示,包括:As shown in Figure 12, it includes:
步骤1201,所述处理器在奇数个N*T周期内,将-T/2—3T/2时间内着色为A的报文计入对应的计数器Count A0;T/2~5T/2时间内着色为B的报文计入对应的计数器Count A1;3T/2~7T/2时间内着色为A的报文计入对应的计数器Count A2;5T/2~9T/2时间内着色为B的报文计入对应的计数器Count A3;依次类推直到读取周期结束;Step 1201: The processor counts the packets colored as A within the period of -T/2—3T/2 into the corresponding counter Count A0 within an odd number of N*T cycles; within the period of T/2—5T/2 Messages colored as B are counted in the corresponding counter Count A1; messages colored as A within 3T/2~7T/2 are counted into the corresponding counter Count A2; messages colored as B within 5T/2~9T/2 The message is counted into the corresponding counter Count A3; and so on until the end of the reading cycle;
在偶数个N*T周期内,将-T/2—3T/2时间内着色为A的报文计入对应的计 数器Count B0;T/2~5T/2时间内着色为B的报文计入对应的计数器Count B1;3T/2~7T/2时间内着色为A的报文计入对应的计数器Count B2;5T/2~9T/2时间内着色为B的报文计入对应的计数器Count B3;依次类推直到读取周期结束。In an even number of N*T cycles, the packets colored as A within -T/2—3T/2 are counted into the corresponding counter Count B0; the packets colored as B within T/2~5T/2 are counted Enter the corresponding counter Count B1; the packets colored as A within 3T/2~7T/2 are counted into the corresponding counter Count B2; the packets colored as B within 5T/2~9T/2 are counted into the corresponding counter Count B3; and so on until the end of the read cycle.
其中,所述标记A为0,所述标记B为1。Wherein, the mark A is 0, and the mark B is 1.
其中,该网络性能测量装置可以设置在路由器、网关、交换机等设备中。Among them, the network performance measurement device can be set in routers, gateways, switches and other equipment.
图13为本申请另一实施例提供的一种网络性能测量方法的流程示意图,该方法应用于网络性能测量系统,所述系统包括:网管和传输报文的源节点和宿节点或中间节点,FIG. 13 is a schematic flowchart of a network performance measurement method according to another embodiment of the application. The method is applied to a network performance measurement system. The system includes: a network management system and a source node and a sink node or an intermediate node for transmitting packets;
所述源节点,包括:第一处理器和2N个计数器;The source node includes: a first processor and 2N counters;
所述宿节点或中间节点,包括:第二处理器和2N个计数器;The sink node or intermediate node includes: a second processor and 2N counters;
所述2N个计数器包括N个计数器Count An和N个计数器Count Bn,所述N为2的偶数倍,n取值为0到N-1的自然数;报文的着色标记有N种,一个计数器Count An和一个计数器Count Bn对应计算一种着色标记报文的数量;着色周期为T,读取周期为N*T;The 2N counters include N counters Count An and N counters Count Bn, where N is an even multiple of 2, and n is a natural number from 0 to N-1; there are N types of coloring tags for packets, one counter Count An and a counter Count Bn respectively calculate the number of a coloring mark message; the coloring cycle is T, and the reading cycle is N*T;
如图13所示包括:As shown in Figure 13, including:
步骤1301,所述第一处理器对报文进行着色和发送;在奇数个N*T周期内,根据报文的着色标记依次计入对应的N个Count An;在偶数个N*T周期内,根据报文的着色标记依次计入对应的N个Count Bn;Step 1301: The first processor colorizes and sends the message; in the odd number of N*T cycles, count the corresponding N Count An according to the coloring flag of the message in turn; in the even number of N*T cycles , Count the corresponding N Count Bn in turn according to the coloring mark of the message;
步骤1302,所述第二处理器接收报文;在奇数个N*T周期内,根据报文的着色标记依次计入对应的N个Count An;在偶数个N*T周期内,根据报文的着色标记依次计入对应的N个Count Bn; Step 1302, the second processor receives the message; in the odd number of N*T cycles, count the corresponding N Count An according to the coloring flag of the message; in the even number of N*T cycles, according to the message The colored marks of are counted in the corresponding N Count Bn in turn;
步骤1303,所述网管在每N*T个周期的中间点读取所述源节点和所述宿节点或中间节点中计数器的数据,计算丢包率。Step 1303: The network manager reads the data of the counters in the source node and the sink node or the intermediate node at an intermediate point of every N*T cycles, and calculates the packet loss rate.
其中,上述节点中可以设置所述网络性能测量装置。Wherein, the network performance measurement device may be provided in the above-mentioned node.
图14为本申请另一实施例提供的一种网络性能测量方法的流程示意图,该 方法应用于网络性能测量装置,所述网络性能测量装置包括:处理器和N个计数器,着色周期为T,一个周期T内时延着色报文扩展为N个;所述N为2或者2的偶数倍;一个计数器Count对应标记一个着色标记报文的着色时间;14 is a schematic flowchart of a network performance measurement method provided by another embodiment of the application. The method is applied to a network performance measurement device. The network performance measurement device includes a processor and N counters, and the coloring period is T. The delay coloring message is expanded to N in a period T; the N is 2 or an even multiple of 2; a counter Count corresponds to marking the coloring time of a coloring mark message;
如图14所示,包括:As shown in Figure 14, including:
步骤1401,所述处理器在T周期内,对每T/N个周期开始的第一个报文进行着色,并将所述报文的着色时间计入对应的计数器Count。Step 1401: The processor colorizes the first message that starts every T/N cycle in T cycles, and counts the coloring time of the message into the corresponding counter Count.
图15为本申请另一实施例提供的一种网络性能测量方法的流程示意图,该方法应用于网络性能测量装置,所述网络性能测量装置包括:处理器和N个计数器,着色周期为T,一个周期T内时延着色报文扩展为N个;所述N为2或者2的偶数倍;一个计数器Count按照周期T依次排列对应标记一个着色标记报文的接收时间;15 is a schematic flow chart of a network performance measurement method provided by another embodiment of the application. The method is applied to a network performance measurement device. The network performance measurement device includes a processor and N counters, and the coloring period is T. In a period T, the delay coloring message is expanded to N; the N is 2 or an even multiple of 2; a counter Count is arranged in sequence according to the period T to mark the receiving time of a coloring mark message;
如图15所示,包括:As shown in Figure 15, including:
步骤1501,当着色周期低于读取周期时,所述处理器将接收到一个着色报文的接收时间写入(接收时间/读取周期)/着色周期,然后向下取整得到对应的计数器,将接收所述着色报文的接收时间计入所述对应的计数器;当着色周期与读取周期一致时,所述处理器将接收到一个着色报文的接收时间写入(接收时间/读取周期)*N/着色周期,然后向下取整得到对应的计数器,将接收所述着色报文的接收时间计入所述对应的计数器。Step 1501: When the coloring period is lower than the reading period, the processor writes (receiving time/reading period)/coloring period of the receiving time of a colored message received, and then rounds down to obtain the corresponding counter , The receiving time of receiving the colored 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 colored message (receiving time/reading Take period)*N/coloring period, then round down to obtain the corresponding counter, and count the receiving time of receiving the coloring message into the corresponding counter.
图16为本申请另一实施例提供的一种网络性能测量方法的流程示意图,该方法应用于网络性能测量系统。FIG. 16 is a schematic flowchart of a network performance measurement method provided by another embodiment of this application, and the method is applied to a network performance measurement system.
所述网络性能测量系统包括:网管和传输报文的源节点和宿节点或中间节点。The network performance measurement system includes: a network management and a source node and a sink node or intermediate nodes for transmitting messages.
所述源节点,包括:第一处理器和N个计数器,所述路由器源节点中的一个计数器Count按照周期T依次排列对应标记一个着色标记报文的着色时间。The source node includes: a first processor and N counters, and a counter Count in the router source node sequentially arranges the coloring time corresponding to a coloring flag packet according to the period T.
所述宿节点或中间节点,包括:第二处理器和N个计数器,所述路由器宿节点中的一个计数器Count按照周期T依次排列对应标记一个着色标记报文的 接收时间。The sink node or the intermediate node includes: a second processor and N counters, and a counter Count in the router sink node sequentially arranges the receiving time of a colored marking message corresponding to the period T.
着色周期为T,一个周期T内时延着色报文扩展为N个;所述N为2或者2的偶数倍。The coloring period is T, and the delayed coloring message is expanded to N in a period T; the N is 2 or an even multiple of 2.
如图16所示,该方法包括:As shown in Figure 16, the method includes:
步骤1601,所述第一处理器发送报文,并在T周期内,对每T/N个周期开始的第一个报文进行着色,并将所述报文的着色时间计入对应的计数器Count;Step 1601: The first processor sends a message, and in the T period, colorizes the first message that starts every T/N period, and counts the coloring time of the message into the corresponding counter Count;
步骤1602,所述第二处理器接收报文,当着色周期低于读取周期时,将接收到一个着色报文的接收时间写入(接收时间/读取周期)/着色周期,然后向下取整得到对应的计数器,将接收所述着色报文的接收时间计入所述对应的计数器;当着色周期与读取周期一致时,将接收到一个着色报文的接收时间写入(接收时间/读取周期)*N/着色周期,然后向下取整得到对应的计数器,将接收所述着色报文的接收时间计入所述对应的计数器; Step 1602, the second processor receives the message, and when the coloring period is lower than the reading period, writes the receiving time of a coloring message into (receiving time/reading period)/coloring period, and then down Round to get the corresponding counter, and count the receiving time of the coloring message into the corresponding counter; when the coloring period is the same as the reading period, write the receiving time of a coloring message (receive time /Reading period)*N/coloring period, then round down to obtain the corresponding counter, and count the receiving time of receiving the coloring message into the corresponding counter;
步骤1603,所述网管在每T个周期的中间点读取所述源节点和所述宿节点或中间节点中计数器的数据,计算网络时延。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 every T cycles, and calculates the network delay.
其中,上述节点中可以设置所述网络性能测量装置。Wherein, the network performance measurement device may be provided in the above-mentioned node.
本领域普通技术人员可以理解,上文中所公开方法中的全部或某些步骤、系统、装置中的功能模块/单元可以被实施为软件、固件、硬件及其适当的组合。在硬件实施方式中,在以上描述中提及的功能模块/单元之间的划分不一定对应于物理组件的划分;例如,一个物理组件可以具有多个功能,或者一个功能或步骤可以由若干物理组件合作执行。某些组件或所有组件可以被实施为由处理器,如数字信号处理器或微处理器执行的软件,或者被实施为硬件,或者被实施为集成电路,如专用集成电路。这样的软件可以分布在计算机可读介质上,计算机可读介质可以包括计算机存储介质(或非暂时性介质)和通信介质(或暂时性介质)。如本领域普通技术人员公知的,术语计算机存储介质包括在用于存储信息(诸如计算机可读指令、数据结构、程序模块或其他数据)的任何方法或技术中实施的易失性和非易失性、可移除和不可移除介质。计算机存储介质包括但不限于RAM、ROM、EEPROM、闪存或其他存储器技术、CD-ROM、数字多功能盘(DVD)或其他光盘存储、磁盒、磁带、磁盘存储或其他磁存储 装置、或者可以用于存储期望的信息并且可以被计算机访问的任何其他的介质。此外,本领域普通技术人员公知的是,通信介质通常包含计算机可读指令、数据结构、程序模块或者诸如载波或其他传输机制之类的调制数据信号中的其他数据,并且可包括任何信息递送介质。A person of ordinary skill in the art can understand that all or some of the steps, functional modules/units in the system, and apparatus in the methods disclosed above can be implemented as software, firmware, hardware, and appropriate combinations thereof. In hardware implementations, the division between 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 consist of several physical components. The components are executed cooperatively. Some or all components may be implemented as software executed by a processor, such as a digital signal processor or a microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on a computer-readable medium, and the computer-readable medium may include a computer storage medium (or a non-transitory medium) and a communication medium (or a transitory medium). As is well known to those of ordinary skill in the art, the term computer storage medium includes volatile and non-volatile memory implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Sexual, removable and non-removable media. Computer storage media include but are not limited to RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cassette, tape, magnetic disk storage or other magnetic storage device, or Any other medium used to store desired information and that can be accessed by a computer. In addition, as is well known to those of ordinary skill in the art, communication media usually contain computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as carrier waves or other transmission mechanisms, and may include any information delivery media .

Claims (10)

  1. 一种网络性能测量装置,包括:A network performance measurement device, including:
    处理器和2N个计数器,所述2N个计数器包括N个计数器Count An和N个计数器Count Bn,所述N为2的偶数倍,n取值为0到N-1的自然数;报文的着色标记有N种,一个计数器Count An和一个计数器Count Bn对应计算一种着色标记报文的数量;着色周期为T,读取周期为N*T;Processor and 2N counters, the 2N counters include N counters Count An and N counters Count Bn, where N is an even multiple of 2, and n is a natural number from 0 to N-1; coloring of packets There are N types of tags, a counter Count An and a counter Count Bn correspondingly calculate the number of a coloring tag message; the coloring cycle is T, and the reading cycle is N*T;
    所述处理器,用于在奇数个N*T周期内,根据报文的着色标记依次计入对应的N个Count An;在偶数个N*T周期内,根据报文的着色标记依次计入对应的N个Count Bn。The processor is configured to sequentially count the corresponding N Count An according to the coloring mark of the message in an odd number of N*T cycles; and sequentially count the corresponding N Count An according to the coloring mark of the message in an even number of N*T cycles The corresponding N Count Bn.
  2. 一种网络性能测量装置,包括:A network performance measurement device, including:
    处理器和2N个计数器,所述2N个计数器包括N个计数器Count An和N个计数器Count Bn,所述N为2的偶数倍,n取值为0到N-1的自然数;报文的着色标记有A和B两种;着色周期为T,读取周期为N*T;一个计数器Count An和一个计数器Count Bn对应计算一个2T周期内一种着色标记报文的数量;Processor and 2N counters, the 2N counters include N counters Count An and N counters Count Bn, where N is an even multiple of 2, and n is a natural number from 0 to N-1; coloring of packets There are two types of markers: A and B; the coloring cycle is T, and the reading cycle is N*T; a counter Count An and a counter Count Bn correspondingly count the number of a coloring tag message in a 2T cycle;
    所述处理器,用于在奇数个N*T周期内,将-T/2—3T/2时间内着色为A的报文计入对应的计数器Count A0;T/2~5T/2时间内着色为B的报文计入对应的计数器Count A1;3T/2~7T/2时间内着色为A的报文计入对应的计数器Count A2;5T/2~9T/2时间内着色为B的报文计入对应的计数器Count A3;依次类推直到读取周期结束;The processor is configured to count the packets colored as A within the period of -T/2—3T/2 into the corresponding counter Count A0 within an odd number of N*T cycles; within the period of T/2—5T/2 Messages colored as B are counted in the corresponding counter Count A1; messages colored as A within 3T/2~7T/2 are counted into the corresponding counter Count A2; messages colored as B within 5T/2~9T/2 The message is counted into the corresponding counter Count A3; and so on until the end of the reading cycle;
    在偶数个N*T周期内,将-T/2—3T/2时间内着色为A的报文计入对应的计数器Count B0;T/2~5T/2时间内着色为B的报文计入对应的计数器Count B1;3T/2~7T/2时间内着色为A的报文计入对应的计数器Count B2;5T/2~9T/2时间内着色为B的报文计入对应的计数器Count B3;依次类推直到读取周期结束。In an even number of N*T cycles, the packets colored as A within -T/2—3T/2 are counted into the corresponding counter Count B0; the packets colored as B within T/2~5T/2 are counted Enter the corresponding counter Count B1; the packets colored as A within 3T/2~7T/2 are counted into the corresponding counter Count B2; the packets colored as B within 5T/2~9T/2 are counted into the corresponding counter Count B3; and so on until the end of the read cycle.
  3. 根据权利要求2所述的网络性能测量装置,其中,The network performance measurement device according to claim 2, wherein:
    所述标记A为0,所述标记B为1。The mark A is 0, and the mark B is 1.
  4. 一种网络性能测量装置,包括:A network performance measurement device, including:
    处理器和N个计数器,着色周期为T,一个周期T内时延着色报文扩展为 N个;所述N为2或者2的偶数倍;报文的着色标记有N种;一个计数器Count对应标记一个着色标记报文的着色时间;The processor and N counters, the coloring period is T, and the delay coloring message within a period T is expanded to N; the N is 2 or an even multiple of 2; there are N kinds of coloring marks for the message; a counter Count corresponds Mark the coloring time of a coloring tag message;
    所述处理器,用于在T周期内,对每T/N个周期开始的第一个报文进行着色,并将所述报文的着色时间计入对应的计数器Count。The processor is configured to color the first message starting every T/N cycle in the T period, and count the coloring time of the message into the corresponding counter Count.
  5. 一种网络性能测量装置,包括:A network performance measurement device, including:
    处理器和N个计数器,着色周期为T,一个周期T内时延着色报文扩展为N个;所述N为2或者2的偶数倍;报文的着色标记有N种;一个计数器Count按照周期T依次排列对应标记一个着色标记报文的接收时间;Processors and N counters, the coloring cycle is T, and the delay coloring message in a cycle T is expanded to N; the N is 2 or an even multiple of 2; there are N kinds of coloring marks for the message; a counter Count according to The period T sequentially arranges the receiving time of correspondingly marked a colored marked message;
    所述处理器,用于当着色周期低于读取周期时,将接收到一个着色报文的接收时间写入(接收时间/读取周期)/着色周期,然后向下取整得到对应的计数器,将接收所述着色报文的接收时间计入所述对应的计数器;当着色周期与读取周期一致时,将接收到一个着色报文的接收时间写入(接收时间/读取周期)*N/着色周期,然后向下取整得到对应的计数器,将接收所述着色报文的接收时间计入所述对应的计数器。The processor is used to write the receiving time (receiving time/reading period)/coloring period of a coloring message when the coloring period is lower than the reading period, and then round down to obtain the corresponding counter , The receiving time of receiving the coloring message is counted into the corresponding counter; when the coloring period is consistent with the reading period, the receiving time of receiving a coloring message is written (receiving time/reading period)* N/coloring period, then round down to obtain a corresponding counter, and count the receiving time of receiving the coloring message into the corresponding counter.
  6. 一种网络性能测量方法,其中,应用于网络性能测量装置,A network performance measurement method, which is applied to a network performance measurement device,
    所述网络性能测量装置包括:处理器和2N个计数器,所述2N个计数器包括N个计数器Count An和N个计数器Count Bn,所述N为2的偶数倍,n取值为0到N-1的自然数;报文的着色标记有N种,一个计数器Count An和一个计数器Count Bn对应计算一种着色标记报文的数量;着色周期为T,读取周期为N*T;The network performance measurement device includes: a processor and 2N counters. The 2N counters include N counters CountAn and N counters CountBn, where N is an even multiple of 2, and n takes a value from 0 to N- A natural number of 1; there are N types of coloring tags for messages, a counter CountAn and a counter CountBn corresponding to calculate the number of a coloring tag message; the coloring cycle is T, and the reading cycle is N*T;
    所述处理器在奇数个N*T周期内,根据报文的着色标记依次计入对应的N个Count An;在偶数个N*T周期内,根据报文的着色标记依次计入对应的N个Count Bn。In an odd number of N*T cycles, the processor sequentially counts the corresponding N Count An according to the coloring mark of the message; in an even number of N*T cycles, sequentially counts the corresponding N according to the coloring mark of the message Count Bn.
  7. 一种网络性能测量方法,其中,应用于网络性能测量装置,A network performance measurement method, which is applied to a network performance measurement device,
    所述网络性能测量装置包括:处理器和2N个计数器,所述2N个计数器包括N个计数器Count An和N个计数器Count Bn,所述N为2的偶数倍,n取值为0到N-1的自然数;报文的着色标记有A和B两种;着色周期为T,读取周期为N*T;一个计数器Count An和一个计数器Count Bn对应计算一个2T周期内一种着色标记报文的数量;The network performance measurement device includes: a processor and 2N counters. The 2N counters include N counters CountAn and N counters CountBn, where N is an even multiple of 2, and n takes a value from 0 to N- A natural number of 1; there are two types of coloring tags for the message: A and B; the coloring cycle is T, and the reading cycle is N*T; a counter Count An and a counter Count Bn correspond to a coloring tag message in a 2T cycle quantity;
    所述处理器在奇数个N*T周期内,将-T/2—3T/2时间内着色为A的报文计入对应的计数器Count A0;T/2~5T/2时间内着色为B的报文计入对应的计数器Count A1;3T/2~7T/2时间内着色为A的报文计入对应的计数器Count A2;5T/2~9T/2时间内着色为B的报文计入对应的计数器Count A3;依次类推直到读取周期结束;In an odd number of N*T cycles, the processor counts the packets colored as A within -T/2—3T/2 into the corresponding counter Count A0; within T/2 to 5T/2, colored as B The messages that are colored as A are counted in the corresponding counter Count A1; the messages that are colored as A within 3T/2 to 7T/2 are counted into the corresponding counter Count A2; the packets that are colored as B within 5T/2 to 9T/2 are counted Enter the corresponding counter Count A3; and so on until the end of the reading cycle;
    在偶数个N*T周期内,将-T/2—3T/2时间内着色为A的报文计入对应的计数器Count B0;T/2~5T/2时间内着色为B的报文计入对应的计数器Count B1;3T/2~7T/2时间内着色为A的报文计入对应的计数器Count B2;5T/2~9T/2时间内着色为B的报文计入对应的计数器Count B3;依次类推直到读取周期结束。In an even number of N*T cycles, the packets colored as A within -T/2—3T/2 are counted into the corresponding counter Count B0; the packets colored as B within T/2~5T/2 are counted Enter the corresponding counter Count B1; the packets colored as A within 3T/2~7T/2 are counted into the corresponding counter Count B2; the packets colored as B within 5T/2~9T/2 are counted into the corresponding counter Count B3; and so on until the end of the read cycle.
  8. 根据权利要求7所述的方法,其中,The method according to claim 7, wherein:
    所述标记A为0,所述标记B为1。The mark A is 0, and the mark B is 1.
  9. 一种网络性能测量方法,其中,应用于网络性能测量装置,A network performance measurement method, which is applied to a network performance measurement device,
    所述网络性能测量装置包括:处理器和N个计数器,着色周期为T,一个周期T内时延着色报文扩展为N个;所述N为2或者2的偶数倍;一个计数器Count对应标记一个着色标记报文的着色时间;The network performance measurement device includes: a processor and N counters, the coloring period is T, and the delay coloring message is expanded to N in a period T; the N is 2 or an even multiple of 2; a counter Count corresponds to a mark The coloring time of a coloring tag message;
    所述处理器在T周期内,对每T/N个周期开始的第一个报文进行着色,并将所述报文的着色时间计入对应的计数器Count。The processor colorizes the first message starting every T/N cycle in the T cycle, and counts the coloring time of the message into the corresponding counter Count.
  10. 一种网络性能测量方法,其中,应用于网络性能测量装置,A network performance measurement method, which is applied to a network performance measurement device,
    所述网络性能测量装置包括:处理器和N个计数器,着色周期为T,一个周期T内时延着色报文扩展为N个;所述N为2或者2的偶数倍;一个计数器Count按照周期T依次排列对应标记一个着色标记报文的接收时间;The network performance measurement device includes: a processor and N counters, the coloring period is T, and the delay coloring message within a period T is expanded to N; the N is 2 or an even multiple of 2; a counter Count is in accordance with the cycle T sequentially arranges the receiving time corresponding to a colored tag message;
    当着色周期低于读取周期时,所述处理器将接收到一个着色报文的接收时间写入(接收时间/读取周期)/着色周期,然后向下取整得到对应的计数器,将接收所述着色报文的接收时间计入所述对应的计数器;当着色周期与读取周期一致时,所述处理器将接收到一个着色报文的接收时间写入(接收时间/读取周期)*N/着色周期,然后向下取整得到对应的计数器,将接收所述着色报文的接收时间计入所述对应的计数器。When the coloring period is lower than the reading period, the processor writes (receiving time/reading period)/coloring period of the receiving time of a colored message received, and then rounds down to get the corresponding counter, and will receive The receiving time of the colored 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 colored message received (receiving time/reading period) *N/coloring period, then round down to obtain the corresponding counter, and count the receiving time of receiving the coloring message into the corresponding counter.
PCT/CN2020/090077 2019-06-27 2020-05-13 Network performance measurement device and method WO2020259113A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910564926.6 2019-06-27
CN201910564926.6A CN112152865B (en) 2019-06-27 2019-06-27 Network performance measuring device and method

Publications (1)

Publication Number Publication Date
WO2020259113A1 true WO2020259113A1 (en) 2020-12-30

Family

ID=73868473

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/090077 WO2020259113A1 (en) 2019-06-27 2020-05-13 Network performance measurement device and method

Country Status (2)

Country Link
CN (1) CN112152865B (en)
WO (1) WO2020259113A1 (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113644998B (en) * 2021-08-23 2023-06-09 烽火通信科技股份有限公司 IOAM time delay measuring method and device for 5G network

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102014030A (en) * 2010-12-31 2011-04-13 湖南神州祥网科技有限公司 Network performance measurement diagnostic method and system based on transmission control protocol (TCP)
CN104348750A (en) * 2013-07-31 2015-02-11 中兴通讯股份有限公司 QoS realization method and apparatus in OpenFlow network
CN107996023A (en) * 2016-11-23 2018-05-04 华为技术有限公司 Method, device and virtual network system for monitoring virtual network
US20190068453A1 (en) * 2017-08-30 2019-02-28 Citrix Systems, Inc. Inferring radio type from clustering algorithms
CN109428782A (en) * 2017-08-30 2019-03-05 杭州华为数字技术有限公司 The method and apparatus of network monitoring
CN109525451A (en) * 2018-09-13 2019-03-26 中兴通讯股份有限公司 A kind of implementation method, device, the network equipment and the controller of MPLS network detection

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101026504B (en) * 2006-02-24 2011-05-11 华为技术有限公司 Network performance measuring method
KR101475347B1 (en) * 2008-12-22 2014-12-30 텔레콤 이탈리아 소시에떼 퍼 아찌오니 Measurement of data loss in a communication network
US8559331B2 (en) * 2010-09-13 2013-10-15 Alcatel Lucent Tri-colour data packet counting for tri-colour marking policies
CN103152223B (en) * 2013-03-15 2016-08-03 华为技术有限公司 network performance monitoring method and device
CN105072629B (en) * 2015-06-30 2019-04-26 华为技术有限公司 Method, device and system for measuring the quality of services running on a terminal
CN106921534A (en) * 2015-12-25 2017-07-04 北京华为朗新科技有限责任公司 Data traffic monitoring and managing method and device
US10320645B2 (en) * 2016-07-11 2019-06-11 Cisco Technology, Inc. System and method of using atomic flow counters in data center switching

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102014030A (en) * 2010-12-31 2011-04-13 湖南神州祥网科技有限公司 Network performance measurement diagnostic method and system based on transmission control protocol (TCP)
CN104348750A (en) * 2013-07-31 2015-02-11 中兴通讯股份有限公司 QoS realization method and apparatus in OpenFlow network
CN107996023A (en) * 2016-11-23 2018-05-04 华为技术有限公司 Method, device and virtual network system for monitoring virtual network
US20190068453A1 (en) * 2017-08-30 2019-02-28 Citrix Systems, Inc. Inferring radio type from clustering algorithms
CN109428782A (en) * 2017-08-30 2019-03-05 杭州华为数字技术有限公司 The method and apparatus of network monitoring
CN109525451A (en) * 2018-09-13 2019-03-26 中兴通讯股份有限公司 A kind of implementation method, device, the network equipment and the controller of MPLS network detection

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
G FIOCCOLA, A CAPELLO, M. CASTALDELLI, M, CHEN L, ZHENG HUAWEI, TECHNOLOGIES G, MIRSKY ZTE T, MIZRAHI: "Alternate-Marking Method for Passive and Hybrid Performance Monitoring", INTERNET ENGINEERING TASK FORCE (IETF) REQUEST FOR COMMENTS: 8321, 7 December 2017 (2017-12-07), XP055769269, Retrieved from the Internet <URL:https://pdfs.semanticscholar.org/ff80/7cc84463e28c3abca7b0153b462b49ddac41.pdf?_ga=2.264066444.1074271107.1611742682-1966713014.1611742682> [retrieved on 20210127] *

Also Published As

Publication number Publication date
CN112152865A (en) 2020-12-29
CN112152865B (en) 2023-06-27

Similar Documents

Publication Publication Date Title
US11405295B2 (en) Scalable distributed end-to-end performance delay measurement for segment routing policies
CN112866043B (en) Network quality detection method, device, server and computer readable medium
CN105072629B (en) Method, device and system for measuring the quality of services running on a terminal
CN113328902B (en) Network performance detection method and device and network equipment
US9985856B2 (en) Method, apparatus and system for measuring network packet loss
US20070064611A1 (en) Method for monitoring packet loss ratio
CN101272290B (en) Measuring method, measuring apparatus for route congestion state in IP network
US8130752B2 (en) Real-time network measurement
WO2021093574A1 (en) Network quality detection method and apparatus, network element device, computer device, and computer readable medium
US12088489B2 (en) Performance measurement in a packet-switched communication network
US8165011B2 (en) Real-time network measurement
US9331927B2 (en) Communication system, communication device, and communication method
US11121938B2 (en) Performance measurement in a packet-switched communication network
US20250202790A1 (en) Delay measurement method and apparatus, storage medium and program product
WO2020259113A1 (en) Network performance measurement device and method
CN113328901A (en) Message out-of-order detection method, device and system
CN115460118B (en) A network performance detection method, device and computer readable storage medium
US9432275B2 (en) Transmission monitoring method and device
WO2024055584A1 (en) Delay measurement method, electronic device, and computer-readable medium
CN112702218A (en) Method, system, network device and storage medium for detecting data transmission quality
WO2023109267A1 (en) Information measurement method and apparatus
CN117955861A (en) Flow detection method, device and system
CN114039888A (en) Time delay measuring method and device
CN118449886B (en) A cross-domain performance detection method and device
CN112688833A (en) Method and device for measuring network time delay and time delay jitter and computer storage medium

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20830520

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS (EPO FORM 1205A DATED 30.05.2022)

122 Ep: pct application non-entry in european phase

Ref document number: 20830520

Country of ref document: EP

Kind code of ref document: A1