CN106230654B - Method for rapidly realizing maximum throughput rate of RFC2544 under background flow - Google Patents
Method for rapidly realizing maximum throughput rate of RFC2544 under background flow Download PDFInfo
- Publication number
- CN106230654B CN106230654B CN201610585553.7A CN201610585553A CN106230654B CN 106230654 B CN106230654 B CN 106230654B CN 201610585553 A CN201610585553 A CN 201610585553A CN 106230654 B CN106230654 B CN 106230654B
- Authority
- CN
- China
- Prior art keywords
- rate
- packet loss
- ratehigh
- ratelow
- currate
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0876—Network utilisation, e.g. volume of load or congestion level
- H04L43/0888—Throughput
Landscapes
- Engineering & Computer Science (AREA)
- Environmental & Geological Engineering (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention relates to a network communication technology, in particular to a method for rapidly realizing the maximum throughput rate of RFC2544 under a background flow. At present, the maximum throughput rate between test points of RFC2544 is the maximum rate under the condition of no packet loss, and when the network has a flow burst, the maximum throughput difference of the actual network is relatively large by using the method for measurement. The method for rapidly realizing the maximum throughput rate of the RFC2544 under the background flow can realize the point-to-point maximum throughput rate statistics under the background flow condition, and change the situation that the RFC2544 can only count the throughput rate under the stable condition at present.
Description
Technical Field
The invention relates to a network communication technology, in particular to a method for rapidly realizing the maximum throughput rate of RFC2544 under a background flow.
Technical Field
The RFC2544 protocol is an international standard proposed by the RFC organization for evaluating network-connected devices (firewalls, IDS, Switch, etc.). The test under the RFC2544 standard mainly comprises the following steps: throughput, delay, packet loss, back-to-back.
(1) Throughput rate (Throughput)
Defining: the maximum data flow which can be forwarded by the tested device under the condition of no packet loss. The maximum number of packets or bytes passed per second is typically used as a measure (MB/s).
The function is as follows: reflecting the maximum data traffic that the device under test can handle (without losing packets).
(2) Packet loss Rate (Lost Rate)
Defining: under a certain load, packets that fail to be forwarded due to lack of resources account for the percentage of the number of packets that should be forwarded.
The function is as follows: reflecting the ability of the device under test to withstand a particular load.
(3) Time delay (Latency)
Defining: sending a certain amount of data packets, recording the time T1 when the intermediate data packets are sent out and the time T2 when the intermediate data packets arrive at a receiving port after being forwarded by the testing equipment, and then calculating according to the following formula:
for store/bit forwarding devices: latency ═ T2-T1
T2: the time of arrival of the first bit of the output frame at the output port;
t1: the time at which the last bit of the input frame arrives at the input port.
The function is as follows: reflecting the speed of the device under test processing the data packets.
(4) Back-to-Back (Back-to-Back)
Defining: and sending data packets with a certain length at the maximum rate which can be generated, and continuously changing the number of the data packets sent at one time until the tested device can completely forward all the sent data packets, wherein the number of the data packets is the back-to-back value of the device.
At present, the maximum throughput rate between test points and a point of RFC2544 is the maximum rate under the condition of no packet loss, for example, under the condition of no background traffic between the points, the maximum throughput rate of a test bandwidth can reach 1Gbps, and in an actual network, the condition of a background stream between the points is often encountered, at this time, the RFC2544 tests the maximum throughput through the bisection method (shown in fig. 2), and then a relatively large error may be encountered, for example, when 1Gbps is sent, the packet loss condition exists, the next test flow is 500Mbps, at this time, a traffic burst exists in the network, which may result in that 500Mbps cannot completely pass, a small amount of packet loss exists, the next test flow is 250Mbps, and thus, the maximum throughput difference from the actual network may be relatively large.
Disclosure of Invention
The invention aims to provide a method for quickly realizing the maximum throughput rate of RFC2544 under a background flow. The technical scheme of the invention is as follows: a method for rapidly realizing maximum throughput rate under RFC2544 background flow comprises the following steps:
1. the control plane sets the content of the sending message, the maximum rate RateHigh, the minimum rate RateLow and the time duration.
The content of the sent message is the message content transmitted on the network, RateHigh is the rate of sending the message for the first time, the lowest rate is the rate used for calculating the next sending rate, and duration is the duration of sending the message.
2. The control plane sets the allowed packet loss rate PermitLost, i.e. the case below this value falls within the normal range or is considered as no packet loss.
3. The control plane sets a flow repetition time, that is, after a certain rate is sent, when a counted packet loss rate Lost is greater than a permitted packet loss rate (PermitLost), the rate repeats sending the repetition time. And if the lowest packet loss rate is lower than the allowable packet loss rate in the set repeat times test result, the rate is considered to pass.
4. And the control plane acquires the multiple packet loss rate Lost, and if the multiple packet loss rates in the statistics are all larger than the allowable packet loss rate. And considering that the rate is too large, continuously adjusting downwards through a dichotomy, and calculating the next sending rate. Otherwise, the next sending rate is calculated by upward adjustment through a bisection method. Until the maximum throughput rate below the allowable packet loss rate is calculated.
5. The rate is calculated by bisection, and the control plane sets the initial RateHigh and RateLow values, i.e., the highest and lowest rates, so that the first sent rate currrate is equal to RateHigh. If the sending rate is curRate, if the lot is not greater than the PermitLost, curRate is the maximum throughput rate of the current RFC2544, otherwise, the dichotomous curRate calculates the next sending rate downwards, RateHigh ═ curRate, RateLow ═ RateLow, and curRate ═ RateHigh + RateLow)/2. According to the rate of the currrate transmitted at this time, if the low is not greater than the PermitLost, the dichotomous currrate calculates the next transmission rate upward, RateHigh ═ RateHigh, RateLow ═ currrate, currrate ═ RateHigh + RateLow)/2, the dichotomous currrate calculates the next transmission rate downward, RateHigh ═ currrate, RateLow ═ RateLow, currrate ═ RateHigh + RateLow)/2. Until (RateHigh-RateLow) <2, currrate is the maximum throughput.
6. The forwarding plane is responsible for analyzing the message content and delivering the message content to a specific output interface according to a target IP or a label.
Compared with the prior art, the method for rapidly realizing the maximum throughput rate of the RFC2544 under the background flow can realize the statistics of the maximum throughput rate from point to point under the condition of the background flow, and change the situation that the RFC2544 can only count the throughput rate under the stable condition at present.
Description of the drawings:
FIG. 1 is a diagram of RFC2544 test data flow networking;
FIG. 2 is a flow of RFC2544 bisection to calculate the next transmission rate;
FIG. 3 is a flow chart of RFC2544 data testing in the present invention.
The specific implementation mode is as follows:
the following describes a method for rapidly realizing the maximum throughput rate under the RFC2544 background flow according to the present invention with reference to the accompanying drawings.
Firstly, as shown in a test data stream networking diagram of fig. 1, two test devices are set up to access a public network or a network set up by the test devices, and the two test devices are respectively RFC2544 test devices and remote loopback devices. The RFC2544 device specially sends the message to the far-end loopback device, and the far-end loopback device loops the processed message back to the RFC2544 device so that the RFC2544 device can count the packet loss rate, the time delay, the throughput rate and the like.
According to the relevant configuration of the user, the parameters are sent to the control plane and the forwarding plane, and when the test starts, the configured maximum rate is first used as the currently sent initial rate, as shown in fig. 3. (1) After the message is sent out from the RFC2544 test device, the message passes through the intermediate network, and reaches the far-end loopback device as shown in fig. 1, and the far-end loopback device sends the processed message back to the RFC2544 test device. At this time, the RFC2544 device performs packet reception statistics to calculate a packet loss rate.
(2) If the packet loss rate is greater than the allowable packet loss rate, continuing to transmit the rate according to the configured repeated transmission times, and if the packet loss rate is still greater than the allowable packet loss rate within the repeated transmission times, considering that the rate is large and the transmission rate needs to be reduced, otherwise, considering that the rate passes, and calculating the next rate according to the bisection method shown in fig. 2.
(3) If the packet loss rate is not greater than the allowable packet loss rate, the rate is considered to pass, but the rate needs to be increased if the packet loss rate is smaller, and the next sending rate is calculated by bisection.
(4) The next transmission rate calculated by the bisection method is compared with the current transmission rate, and if the current transmission rate is not equal to the next transmission rate, the next transmission is performed, and the steps are as above. If the current transmission rate is equal to the next transmission rate, the current rate is considered to be the maximum throughput rate, and so on.
Claims (1)
1. A method for rapidly realizing maximum throughput rate under RFC2544 background flow is characterized in that: the method comprises the following steps:
(1) the control plane sets the content of the sending message, the maximum rate RateHigh, the minimum rate RateLow and the time duration; the content of the sent message is the message content transmitted on the network, RateHigh is the rate of sending the message for the first time, the lowest rate is the rate used for calculating the next sending rate, and duration is the duration of sending the message;
(2) the control plane sets the allowable packet loss rate PermitLost, that is, the packet loss rate PermitLost falls into a normal range or is considered to be a case of no packet loss when the allowable packet loss rate PermitLost is lower than the value;
(3) the control plane sets a flow repetition time, that is, after a certain rate is sent, when a counted packet loss rate Lost is greater than a permitted packet loss rate (PermitLost), the rate repeats the sending of the flow repetition time; if the lowest packet loss rate is lower than the allowable packet loss rate in the set repeat times test result, the rate is considered to pass;
(4) the control plane obtains a multiple packet loss rate Lost, if the multiple packet loss rates in the statistics are all larger than the allowable packet loss rate; if the rate is too large, continuing to downwards adjust by the dichotomy, and calculating the next sending rate; otherwise, upwards adjusting through bisection, and calculating the next sending rate until the maximum throughput rate lower than the allowable packet loss rate is calculated;
(5) calculating the speed by bisection, wherein the control plane sets initial RateHigh and RateLow values, namely the highest speed and the lowest speed; the rate currrate of the first transmission is equal to RateHigh; if the sending rate is curRate, if the Lost is not greater than PermitLost, the curRate is the maximum throughput rate of the current RFC2544, otherwise, the next sending rate is calculated downwards by bisection, RateHigh = curRate, RateLow = RateLow, curRate = (RateHigh + RateLow)/2; as a result of the currrate transmitted at this time, if the low is not greater than the PermitLost, then the next transmission rate is calculated by bisection method, RateHigh = RateHigh, RateLow = curRate, curRate = (RateHigh + RateLow)/2, otherwise, the next transmission rate is calculated by bisection method, RateHigh = curRate, RateLow = RateLow, curRate = (RateHigh + RateLow)/2, until (RateHigh-RateLow) <2, the curRate is the maximum throughput rate;
(6) the forwarding plane is responsible for analyzing the message content and delivering the message content to a specific output interface according to a target IP or a label.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610585553.7A CN106230654B (en) | 2016-07-22 | 2016-07-22 | Method for rapidly realizing maximum throughput rate of RFC2544 under background flow |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610585553.7A CN106230654B (en) | 2016-07-22 | 2016-07-22 | Method for rapidly realizing maximum throughput rate of RFC2544 under background flow |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106230654A CN106230654A (en) | 2016-12-14 |
| CN106230654B true CN106230654B (en) | 2019-12-24 |
Family
ID=57531589
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610585553.7A Active CN106230654B (en) | 2016-07-22 | 2016-07-22 | Method for rapidly realizing maximum throughput rate of RFC2544 under background flow |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106230654B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107453944B (en) * | 2017-07-07 | 2021-04-02 | 台州市吉吉知识产权运营有限公司 | Method and system for determining optimal test connection number of network throughput test |
| CN111049704A (en) * | 2019-12-23 | 2020-04-21 | 安徽皖通邮电股份有限公司 | Method for calculating switching and back-switching time in protection environment through RFC2544 |
| CN111030890A (en) * | 2019-12-23 | 2020-04-17 | 安徽皖通邮电股份有限公司 | Network interconnection equipment evaluation method based on EOS service |
| CN114363217B (en) * | 2021-12-23 | 2024-10-29 | 北京六方云信息技术有限公司 | RFC2544 throughput performance test method, system, device and medium |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8009696B2 (en) * | 2004-08-06 | 2011-08-30 | Ipeak Networks Incorporated | System and method for achieving accelerated throughput |
| CN104378307B (en) * | 2014-10-27 | 2017-11-21 | 北京华夏创新科技有限公司 | Optimization method and system based on throughput and packet loss control CWND |
| CN104486168A (en) * | 2014-12-31 | 2015-04-01 | 北京奇虎科技有限公司 | Router wireless performance evaluation system and method |
| CN104618183B (en) * | 2015-01-22 | 2017-12-19 | 北京奥普维尔科技有限公司 | A kind of RFC2544 throughput testing approach |
-
2016
- 2016-07-22 CN CN201610585553.7A patent/CN106230654B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN106230654A (en) | 2016-12-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210006482A1 (en) | Broadband communication link performance monitoring method for communication devices | |
| EP3259888B1 (en) | High-precision packet train generation | |
| CN105306888B (en) | Mobile video monitor bandwidth self-adaption method based on packet loss differentiating | |
| Zats et al. | DeTail: Reducing the flow completion time tail in datacenter networks | |
| CN106230654B (en) | Method for rapidly realizing maximum throughput rate of RFC2544 under background flow | |
| US20100008248A1 (en) | Network tester for real-time measuring of tcp throughput | |
| WO2016058279A1 (en) | Multi-path data transmission method based on quality evaluation | |
| EP1382219A2 (en) | Method and device for robust real-time estimation of bottleneck bandwidth | |
| KR20160036878A (en) | Apparatus and method for controlling data flow in a communication system | |
| WO2010033059A1 (en) | Method, arrangement and system for monitoring a data path in a communication network | |
| KR20100051537A (en) | Automatic detection and re-configuration of priority status in telecommunications networks | |
| KR101924740B1 (en) | Probing a network | |
| US20150229575A1 (en) | Flow control in a network | |
| Nguyen et al. | Performance evaluation of TCP congestion control algorithms in data center networks | |
| Kachan et al. | Available bandwidth measurement for 10 Gbps networks | |
| WO2012071851A1 (en) | Method and apparatus for adjusting bidirectional forwarding detection transmission interval according to network jitter | |
| Gokhale et al. | Opportunistic adaptive haptic sampling on forward channel in telehaptic communication | |
| CN102185732B (en) | Method and system for testing active queue management parameters of communication equipment | |
| Kuhn et al. | Less-than-best-effort capacity sharing over high BDP networks with LEDBAT | |
| Park et al. | Minimizing application-level delay of multi-path TCP in wireless networks: A receiver-centric approach | |
| Delphinanto et al. | Path capacity estimation in heterogeneous, best-effort, small-scale IP networks | |
| Singh et al. | Circuit breakers for multimedia congestion control | |
| Xie et al. | AProbing: Estimating available bandwidth using ACK pair probing | |
| RU2687040C1 (en) | Method and apparatus for monitoring a backbone network | |
| CN111049704A (en) | Method for calculating switching and back-switching time in protection environment through RFC2544 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |