CN112702277B - Load balancing configuration optimization method and device - Google Patents
Load balancing configuration optimization method and device Download PDFInfo
- Publication number
- CN112702277B CN112702277B CN202011478242.3A CN202011478242A CN112702277B CN 112702277 B CN112702277 B CN 112702277B CN 202011478242 A CN202011478242 A CN 202011478242A CN 112702277 B CN112702277 B CN 112702277B
- Authority
- CN
- China
- Prior art keywords
- hash
- value
- message
- hash algorithm
- algorithm
- 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
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/12—Avoiding congestion; Recovering from congestion
- H04L47/125—Avoiding congestion; Recovering from congestion by balancing the load, e.g. traffic engineering
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0803—Configuration setting
- H04L41/0823—Configuration setting characterised by the purposes of a change of settings, e.g. optimising configuration for enhancing reliability
Abstract
The invention provides a method and a device for optimizing load balancing configuration, wherein the method comprises the following steps: receiving a message flow and storing messages in the message flow; calculating the discrete degree value of each tuple in the quintuple in the message according to the number of the message; saving at least one HASH algorithm; sorting the discrete degree values of each tuple; selecting a balance factor corresponding to the maximum discrete degree value; selecting a HASH algorithm from the HASH algorithms according to the balance factor of each message to calculate a HASH value, offsetting the HASH value by using an offset to obtain a first HASH value, and obtaining a message output port of each message according to the first HASH value; counting the number of messages of each output port; calculating the balance error of each output port according to the number of the messages of each output port; and when the equalization error of any outlet is not larger than the expected error input by the user, sending the selected HASH algorithm, the offset and the equalization factor to the client. And optimizing the load balancing effect of the switch equipment according to the expected balancing effect specified by the user.
Description
Technical Field
The invention relates to the field of data communication, in particular to a method and a device for optimizing load balancing configuration.
Background
The Ethernet link aggregation is called link aggregation for short, and a plurality of Ethernet physical links are bound together to form a logical link, so that the aim of increasing the link bandwidth is fulfilled. Meanwhile, the reliability of the links can be effectively improved through mutual dynamic backup of the bound links. In the same aggregation group, the problem of load balancing among member links is involved.
In a network environment where ECMP (Equal-cost multi-routing) exists in which multiple different links reach the same destination address, if a conventional routing technology is used, a packet sent to the destination address can only use one of the links, and other links are in a backup state or an invalid state, and a certain time is required for mutual switching in a dynamic routing environment, whereas an Equal-cost multi-path routing protocol can use multiple links simultaneously in the network environment, which not only increases transmission bandwidth, but also can back up data transmission of a failed link without delay or packet loss. Load balancing of traffic is involved between different ECMP transmission links.
The default balancing configuration of the switch has a certain difference in the balancing effect of different service flows, and when the switch needs to deploy a specific service, if the load balancing effect is not ideal, the load balancing related configuration needs to be readjusted. Because different equalization configurations which may be needed by different flow sets can achieve an ideal equalization effect, and at present, an equalization configuration which meets an expected equalization deviation cannot be found at one time according to flow information, so that the equalization configuration which meets the expectation can be found only by adjusting the configuration blindly and needing to be adjusted for many times, and the equalization effect which needs to be observed again after the adjustment is finished every time. Therefore, the service deployment time can be delayed, and if the service is online, the forwarding of service traffic can be influenced in the process of debugging the balanced configuration.
Disclosure of Invention
In order to solve the technical problem, the embodiment of the invention adopts the following technical scheme:
a method of load balancing configuration optimization, comprising:
the method comprises the following steps: receiving a message flow and storing messages in the message flow;
step two: calculating the discrete degree value of each tuple in the quintuple in the message according to the number of the message;
step three: saving at least one HASH algorithm;
step four: sorting the discrete degree value of each tuple;
step five: selecting the balance factor corresponding to the maximum discrete degree value;
step six: selecting an HASH algorithm from the HASH algorithms according to the balance factor of each message to calculate an HASH value, offsetting the HASH value by using an offset to obtain a first HASH value, and obtaining a message output port of each message according to the first HASH value; counting the number of messages of each output port;
step seven: calculating the balance error of each output port according to the number of the messages of each output port;
step eight: and when the equalization error of any outlet is not greater than the expected error input by the user, sending the selected HASH algorithm, the offset and the equalization factor to a client.
Optionally, the method further includes:
step nine: and when the equalization error of any one outlet is larger than the expected error input by the user and the currently used discrete degree value is not the minimum discrete degree value, adding the tuple corresponding to the next discrete degree value according to the sequence on the basis of the tuple corresponding to the currently used equalization factor to serve as a new equalization factor, and re-executing the step six.
Optionally, the method further includes:
and when the equalization errors of all outlets are larger than the expected error input by the user and the currently used discrete magnitude value is the minimum discrete magnitude value, determining whether the at least one HASH algorithm has an unselected HASH algorithm, and when the at least one HASH algorithm has an unselected HASH algorithm, re-executing the step six by using the unselected HASH algorithm.
Optionally, the method further includes:
and when the unselected HASH algorithm does not exist, adding 1 to the offset, and if the offset is equal to a preset value, sending the equilibrium configuration which does not meet the condition to the client.
Optionally, the method further includes:
and re-executing the step five to the step eight.
Another aspect of the embodiments of the present invention provides a device for optimizing load balancing configuration, including:
the receiving module is used for receiving the message flow and storing the messages in the message flow;
the calculation module is used for calculating the discrete degree value of each tuple in the quintuple in the message according to the number of the message;
the storage module is used for storing at least one HASH algorithm;
the sorting module is used for sorting the discrete degree value of each tuple;
the selection module is used for selecting the balance factor corresponding to the maximum discrete degree value;
the processing module is used for selecting an HASH algorithm from the HASH algorithms according to the balance factors of each message to calculate an HASH value, offsetting the HASH value by using an offset to obtain a first HASH value, and obtaining a message outlet port of each message according to the first HASH value; counting the number of messages of each output port;
the calculation module is further configured to calculate a balance error of each egress port according to the number of the packets at each egress port;
and the sending module is used for sending the selected HASH algorithm, the offset and the equalization factor to a client when the equalization error of any one outlet is not larger than the expected error input by a user.
Optionally, the processing module is further configured to:
when the equalization error of any one outlet is larger than the expected error input by a user and the currently used discrete degree value is not the minimum discrete degree value, adding a tuple corresponding to the next discrete degree value according to the sequence on the basis of the tuple corresponding to the currently used equalization factor as a new equalization factor, selecting an HASH algorithm from the HASH algorithm according to the equalization factor of each message to calculate an HASH value, offsetting the HASH value by using an offset to obtain a first HASH value, and obtaining a message outlet port of each message according to the first HASH value; and counting the number of messages of each output port.
Optionally, the processing module is further configured to:
when the balance errors of all outlets are larger than the expected errors input by a user and the currently used discrete degree value is the minimum discrete degree value, determining whether at least one HASH algorithm has an unselected HASH algorithm, when the at least one HASH algorithm has the unselected HASH algorithm, calculating the HASH value from the HASH algorithm by using the unselected HASH algorithm according to the balance factor of each message, offsetting the HASH value by using an offset to obtain a first HASH value, and obtaining a message outlet port of each message according to the first HASH value; and counting the number of messages of each egress port.
Alternatively to this, the first and second parts may,
the sending module is further configured to add 1 to the offset when there is no unselected HASH algorithm, and send the equalization configuration that does not satisfy the condition to the client if the offset is equal to a preset value.
Alternatively to this, the first and second parts may,
the HASH algorithm is as follows: a CRC-16 algorithm, an XOR-16 algorithm, a CRC-32 algorithm, or a CRC-CCITT algorithm.
The embodiment of the invention has the advantage that the load balancing effect of the switch equipment can be optimized according to the expected balancing effect specified by a user under the condition of not influencing the original service forwarding.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flowchart of a method provided by an embodiment of the present invention;
fig. 2 is a diagram illustrating a structure of an apparatus according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
An embodiment of the present invention provides a method for optimizing load balancing configuration, as shown in fig. 1, including:
step S101, receiving a message flow and storing messages in the message flow;
step S103, calculating the discrete degree value of each tuple in the quintuple in the message according to the number of the message;
step S105, storing at least one HASH algorithm;
step S107, sorting the discrete degree value of each tuple;
step S109, selecting the balance factor corresponding to the maximum discrete degree value;
step S111, selecting a HASH algorithm from the HASH algorithms according to the balance factor of each message to calculate a HASH value, offsetting the HASH value by using an offset to obtain a first HASH value, and obtaining a message output port of each message according to the first HASH value; counting the number of messages of each output port;
step S113, calculating the balance error of each output port according to the message quantity of each output port;
and step S115, when the equalization error of any outlet is not larger than the expected error input by the user, sending the selected HASH algorithm, the offset and the equalization factor to the client.
Optionally, the method further includes:
and when the equalization error of any one outlet is greater than the expected error input by the user and the currently used discrete degree value is not the minimum discrete degree value, adding the tuple corresponding to the next discrete degree value as a new equalization factor according to the sorting on the basis of the tuple corresponding to the currently used equalization factor, and re-executing the step S111.
Optionally, the method further includes:
and when the equalization errors of all outlets are larger than the expected error input by the user and the currently used discrete magnitude value is the minimum discrete magnitude value, determining whether the at least one HASH algorithm has an unselected HASH algorithm, and when the at least one HASH algorithm has an unselected HASH algorithm, re-executing the step six by using the unselected HASH algorithm.
Optionally, the method further includes:
and when the unselected HASH algorithm does not exist, adding 1 to the offset, and if the offset is equal to a preset value, sending the equilibrium configuration which does not meet the condition to the client.
Optionally, the method further includes:
step S109 to step S115 are re-executed.
The embodiment of the invention has the advantage that the load balancing effect of the switch equipment can be optimized according to the expected balancing effect specified by the user under the condition of not influencing the forwarding of the original service.
Another aspect of the embodiments of the present invention is to provide an apparatus for optimizing load balancing configuration, as shown in fig. 2, including:
a receiving module 201, configured to receive a message stream and store a message in the message stream;
a calculating module 203, configured to calculate a discrete degree value of each tuple in the quintuple in the message according to the number of the message;
a storage module 205 for storing at least one HASH algorithm;
a sorting module 207, configured to sort the discrete degree value of each tuple;
a selecting module 209, configured to select a balance factor corresponding to the largest discrete degree value;
a processing module 211, configured to select a HASH algorithm from the HASH algorithms according to the balance factor of each packet to calculate a HASH value, offset the HASH value by using an offset to obtain a first HASH value, and obtain a packet egress port of each packet according to the first HASH value; counting the number of messages of each output port;
the calculating module 203 is further configured to calculate a balance error of each egress port according to the number of the packets of each egress port;
a sending module 213, configured to send the selected HASH algorithm, the offset, and the equalization factor to the client when the equalization error of any one of the outlets is not greater than the expected error input by the user.
Optionally, the processing module is further configured to:
when the balance error of any one outlet is larger than the expected error input by a user and the currently used discrete degree value is not the minimum discrete degree value, adding a tuple corresponding to the next discrete degree value according to the sequence on the basis of the tuple corresponding to the currently used balanced factor as a new balanced factor, selecting a HASH algorithm from the HASH algorithm according to the balanced factor of each message to calculate a HASH value, offsetting the HASH value by using an offset to obtain a first HASH value, and obtaining a message outlet port of each message according to the first HASH value; and counting the number of messages of each output port.
Optionally, the processing module is further configured to:
when the balance errors of all outlets are larger than the expected errors input by a user and the currently used discrete degree value is the minimum discrete degree value, determining whether at least one HASH algorithm has an unselected HASH algorithm, when the at least one HASH algorithm has the unselected HASH algorithm, calculating the HASH value from the HASH algorithm by using the unselected HASH algorithm according to the balance factor of each message, offsetting the HASH value by using an offset to obtain a first HASH value, and obtaining a message outlet port of each message according to the first HASH value; and counting the number of messages of each output port.
Alternatively to this, the first and second parts may,
the sending module is further configured to add 1 to the offset when there is no unselected HASH algorithm, and send the equalization configuration that does not satisfy the condition to the client if the offset is equal to a preset value.
Alternatively to this, the first and second parts may,
the HASH algorithm is as follows: a CRC-16 algorithm, an XOR-16 algorithm, a CRC-32 algorithm, or a CRC-CCITT algorithm.
The embodiment of the invention has the advantage that the load balancing effect of the switch equipment can be optimized according to the expected balancing effect specified by the user under the condition of not influencing the forwarding of the original service.
The embodiments of the present invention are further described below with reference to specific application scenarios.
The method comprises the following steps: flow collection and introduction
The flow set in this step is the flow set that needs load balancing optimization. When the flow enters the switch equipment, the message information of the input flow is stored locally in a file writing mode, so that reading and analysis of subsequent processing are facilitated. Thus, before the optimized configuration is calculated, the flow is forwarded according to the original load balancing configuration.
Step two: flow set analysis
Analyzing the discrete degree of the corresponding message header of the input flow set. Assuming that the total number of the packets is n, the discrete degree is represented by D, and the discrete degree of the packet five-tuple is calculated respectively, taking the discrete degree of the source IP address header as an example for explanation, the quantization formula is as follows:
wherein D is sip Represents the discrete quantized value, count, of the source IP sip The number of the source IP, the total number of the messages and the respective counts of the quintuple are obtained by statistics after the flow set import is finished.
According to the above, the value of the discrete degree of each quintuple can be obtained, the value is equal to 1, namely the complete discrete state, and the more the value approaches to 0, the lower the discrete degree is.
Step three: HASH algorithm import
Since the HASH algorithms supported by different switches may be different, it is necessary to read the HASH algorithm list supported by the switch device and perform adaptation import into the system, so that the algorithms supported by the system are consistent with those supported by the device.
Commonly used HASH algorithms are: CRC-16, XOR-16, CRC-32, CRC-CCITT, etc.
For convenience of description, three algorithms are assumed in this embodiment, which are respectively denoted as al _1, al _2, and al _3.
Step four: optimizing information input
This embodiment provides a CLI command interacting with a user, who needs to input the number m of traffic forwarding outlets, the load balancing error index epsilon that the user wants to optimize (i.e., the output objective of this embodiment, when the calculated error is smaller than the error, it is considered that the optimal configuration is found), and whether the optimal configuration needs to be directly applied to the device.
Step five: HASH simulation calculation
Through the above steps, the preparation information required by the present embodiment is already completed, and in this step, the calculation is started, and the specific calculation flow is as follows:
a: and sorting according to the discrete degree value of the quintuple calculated in the step two, wherein the five tuples are respectively arranged into 5 discrete levels: d1 > D2 > D3 > D4 > D5;
b: selecting a balance algorithm, and selecting an al _1HASH algorithm by default if the balance algorithm is not specified;
c: selecting the balance factor, and selecting the balance factor corresponding to the D1 by default if the balance factor is not specified;
d: reading the message headers of the corresponding balance factors of each message one by one to perform HASH calculation to obtain a HASH value (HASH _ key, length 16 bit), updating the HASH _ key according to cyclic offset shift setting (offset), obtaining a value obtained by the HASH _ key by adding m as a simulated forwarding outlet of the message, and adding 1 to the message count corresponding to the outlet.
E: after all messages are calculated, the message counts of all exits can be obtained. The equalization error is found for all outlets according to the following equation:
i∈[1,m]
wherein epsilon i Indicating the equalization error of the ith egress link; count i Counting the messages of the ith outlet of the table entry; x represents the average of the packet counts for all the outlets.
When the condition is satisfied
If the equalization error is smaller than the expected value, namely the equalization errors of all outlets are not larger than the expected error input by the user, the method jumps to the step six with the current equalization configuration (hash algorithm, equalization factor and offset value), and if the equalization error is not larger than the expected error input by the user, the jump is carried outTo F.
F: if the condition is not met, judging whether the equalization factor of the D5 level discrete degree is used or not, if so, skipping to G, otherwise, increasing the equalization factor of the next level discrete degree as input, skipping to E for calculation again.
G: and judging whether HASH algorithms which do not participate in calculation exist, if so, replacing the HASH algorithms as input, skipping to B for recalculation, and otherwise, skipping to H.
H: setting an equalization key to add 1 to the cyclic shift value offset (the offset defaults to 0), if the offset is equal to 16, jumping to the step six without equalization parameters, then jumping to the step B without specifying any parameters and re-calculating.
Step six: output equalization configuration
If no input parameter exists, the print output does not meet the condition balance configuration;
if the input parameters exist, the balance configuration is printed and displayed on the CLI interface according to the input balance parameters (hash algorithm, balance factor and offset value), and if the step four specifies direct application to the equipment, the balance configuration of the equipment is directly updated to the configuration and is immediately effective.
The embodiment of the invention has the advantage that the load balancing effect of the switch equipment can be optimized according to the expected balancing effect specified by the user under the condition of not influencing the forwarding of the original service.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, and not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for load balancing configuration optimization, comprising:
the method comprises the following steps: receiving a message flow and storing messages in the message flow;
step two: calculating the discrete degree value of each tuple in the quintuple in the message according to the number of the message;
step three: saving at least one HASH algorithm;
step four: sorting the discrete degree value of each tuple;
step five: selecting a balance factor corresponding to the tuple corresponding to the maximum discrete degree value;
step six: selecting an HASH algorithm from the HASH algorithms according to the balance factors of each message to calculate an HASH value, offsetting the HASH value by using an offset to obtain a first HASH value, and obtaining a message outlet port of each message according to the first HASH value; counting the number of messages of each output port;
step seven: calculating the balance error of each output port according to the number of the messages of each output port;
step eight: and when the equalization error of any egress port is not greater than the expected error input by the user, sending the selected HASH algorithm, the offset and the equalization factor to a client.
2. The method of claim 1, further comprising:
step nine: and when the equalization error of any output port is larger than the expected error input by the user and the currently used discrete degree value is not the minimum discrete degree value, adding the tuple corresponding to the next discrete degree value as a new equalization factor according to the sequence on the basis of the tuple corresponding to the currently used equalization factor, and re-executing the step six.
3. The method of claim 1, further comprising:
and when the equalization errors of all the egress ports are larger than the expected error input by the user and the currently used discrete magnitude value is the minimum discrete magnitude value, determining whether the at least one HASH algorithm has an unselected HASH algorithm, and when the unselected HASH algorithm has the unselected HASH algorithm, re-executing the step six by using the unselected HASH algorithm.
4. The method of claim 3, further comprising:
and when the unselected HASH algorithm does not exist, adding 1 to the offset, and if the offset is equal to a preset value, sending the equilibrium configuration which does not meet the condition to the client.
5. The method of claim 4, further comprising:
and when the unselected HASH algorithm does not exist, adding 1 to the offset, and if the offset is equal to a preset value, re-executing the steps from the fifth step to the eighth step.
6. An apparatus for load balancing configuration optimization, comprising:
the receiving module is used for receiving the message flow and storing the messages in the message flow;
the calculation module is used for calculating the discrete degree value of each tuple in the quintuple in the message according to the number of the message;
the storage module is used for storing at least one HASH algorithm;
the sorting module is used for sorting the discrete degree value of each tuple;
the selection module is used for selecting the balance factor corresponding to the maximum discrete degree value;
the processing module is used for selecting an HASH algorithm from the HASH algorithms according to the balance factor of each message to calculate an HASH value, offsetting the HASH value by using an offset to obtain a first HASH value, and obtaining a message output port of each message according to the first HASH value; counting the number of messages of each output port;
the calculation module is further configured to calculate a balance error of each egress port according to the number of the packets at each egress port;
and the sending module is used for sending the selected HASH algorithm, the offset and the equalization factor to a client when the equalization error of any one egress port is not larger than the expected error input by a user.
7. The apparatus of claim 6, wherein the processing module is further to:
when the balance error of any output port is larger than the expected error input by a user and the currently used discrete degree value is not the minimum discrete degree value, adding a tuple corresponding to the next discrete degree value according to the sequence on the basis of a tuple corresponding to the currently used balanced factor as a new balanced factor, selecting a HASH algorithm from the HASH algorithm according to the balanced factor of each message to calculate a HASH value, offsetting the HASH value by using an offset to obtain a first HASH value, and obtaining the message output port of each message according to the first HASH value; and counting the number of messages of each egress port.
8. The apparatus of claim 6, wherein the processing module is further to:
when the equalization errors of all egress ports are larger than the expected errors input by a user and the currently used discrete degree value is the minimum discrete degree value, determining whether at least one HASH algorithm has an unselected HASH algorithm, when the at least one HASH algorithm has the unselected HASH algorithm, calculating the HASH value by using the unselected HASH algorithm in the HASH algorithm according to the equalization factor of each message, shifting the HASH value by using an offset to obtain a first HASH value, and obtaining the message egress port of each message according to the first HASH value; and counting the number of messages of each output port.
9. The apparatus of claim 8,
the sending module is further configured to add 1 to the offset when there is no unselected HASH algorithm, and send the equalization configuration that does not satisfy the condition to the client if the offset is equal to a preset value.
10. The apparatus of claim 9,
the HASH algorithm is as follows: a CRC-16 algorithm, an XOR-16 algorithm, a CRC-32 algorithm, or a CRC-CCITT algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011478242.3A CN112702277B (en) | 2020-12-15 | 2020-12-15 | Load balancing configuration optimization method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011478242.3A CN112702277B (en) | 2020-12-15 | 2020-12-15 | Load balancing configuration optimization method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112702277A CN112702277A (en) | 2021-04-23 |
| CN112702277B true CN112702277B (en) | 2023-01-10 |
Family
ID=75508126
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011478242.3A Active CN112702277B (en) | 2020-12-15 | 2020-12-15 | Load balancing configuration optimization method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112702277B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101330433A (en) * | 2007-06-20 | 2008-12-24 | 中兴通讯股份有限公司 | Method and apparatus for managing Ethernet equipment sharing buffer area base on transmission network |
| CN101499957A (en) * | 2008-01-29 | 2009-08-05 | 中国电信股份有限公司 | Multipath load balance implementing method and data forwarding apparatus |
| CN101686235A (en) * | 2008-09-26 | 2010-03-31 | 中联绿盟信息技术(北京)有限公司 | Device and method for analyzing abnormal network flow |
| CN102098224A (en) * | 2011-02-16 | 2011-06-15 | 中兴通讯股份有限公司 | Method and device for sharing data stream loads |
| CN102143074A (en) * | 2011-03-25 | 2011-08-03 | 中兴通讯股份有限公司 | Method and system for sharing network load and network processor |
| CN102413053A (en) * | 2011-12-12 | 2012-04-11 | 盛科网络（苏州）有限公司 | Method and device for realizing load balance of trunk port |
| CN102469006A (en) * | 2010-11-01 | 2012-05-23 | 杭州华三通信技术有限公司 | Method and device for quickly forwarding data report |
| CN102761479A (en) * | 2012-06-28 | 2012-10-31 | 华为技术有限公司 | Method for selecting link and device therefore |
| CN102857391A (en) * | 2012-08-21 | 2013-01-02 | 北京星网锐捷网络技术有限公司 | Method, device and network device for detecting IP (internet protocol) scanning action |
| CN102868631A (en) * | 2012-09-28 | 2013-01-09 | 华为技术有限公司 | Load sharing method and device |
| CN103414701A (en) * | 2013-07-25 | 2013-11-27 | 华为技术有限公司 | Rule matching method and device |
| CN104182393A (en) * | 2013-05-21 | 2014-12-03 | 中兴通讯股份有限公司 | Processing method and processing device for keyword mapping based on hash table |
| CN107623640A (en) * | 2017-11-07 | 2018-01-23 | 北京锐安科技有限公司 | A kind of method and device for strengthening hash algorithm |
| CN110191109A (en) * | 2019-05-17 | 2019-08-30 | 杭州迪普信息技术有限公司 | A kind of packet sampling method and device |
| CN110784378A (en) * | 2019-11-04 | 2020-02-11 | 盛科网络（苏州）有限公司 | Method and device for realizing accurate flow balance by using TWAMP (two way operational amplifier) |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9237103B2 (en) * | 2012-03-30 | 2016-01-12 | Cisco Technology, Inc. | Congestion alleviation in network systems |
| US9577939B2 (en) * | 2013-11-07 | 2017-02-21 | Cisco Technology, Inc. | Method and apparatus for distributing EtherChannel load based on variance |
| CN109067664B (en) * | 2018-08-29 | 2022-06-10 | 迈普通信技术股份有限公司 | Load balancing method and device |
| CN111726299B (en) * | 2019-03-18 | 2023-05-09 | 华为技术有限公司 | Flow balancing method and device |
| CN110912832A (en) * | 2019-10-15 | 2020-03-24 | 深圳市恒扬数据股份有限公司 | Processing method and device for flow load balancing, electronic equipment and storage medium |
| CN111711577B (en) * | 2020-07-24 | 2022-07-22 | 杭州迪普信息技术有限公司 | Message forwarding method and device of flow control equipment |
-
2020
- 2020-12-15 CN CN202011478242.3A patent/CN112702277B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101330433A (en) * | 2007-06-20 | 2008-12-24 | 中兴通讯股份有限公司 | Method and apparatus for managing Ethernet equipment sharing buffer area base on transmission network |
| CN101499957A (en) * | 2008-01-29 | 2009-08-05 | 中国电信股份有限公司 | Multipath load balance implementing method and data forwarding apparatus |
| CN101686235A (en) * | 2008-09-26 | 2010-03-31 | 中联绿盟信息技术(北京)有限公司 | Device and method for analyzing abnormal network flow |
| CN102469006A (en) * | 2010-11-01 | 2012-05-23 | 杭州华三通信技术有限公司 | Method and device for quickly forwarding data report |
| CN102098224A (en) * | 2011-02-16 | 2011-06-15 | 中兴通讯股份有限公司 | Method and device for sharing data stream loads |
| CN102143074A (en) * | 2011-03-25 | 2011-08-03 | 中兴通讯股份有限公司 | Method and system for sharing network load and network processor |
| CN102413053A (en) * | 2011-12-12 | 2012-04-11 | 盛科网络（苏州）有限公司 | Method and device for realizing load balance of trunk port |
| CN102761479A (en) * | 2012-06-28 | 2012-10-31 | 华为技术有限公司 | Method for selecting link and device therefore |
| CN102857391A (en) * | 2012-08-21 | 2013-01-02 | 北京星网锐捷网络技术有限公司 | Method, device and network device for detecting IP (internet protocol) scanning action |
| CN102868631A (en) * | 2012-09-28 | 2013-01-09 | 华为技术有限公司 | Load sharing method and device |
| CN104182393A (en) * | 2013-05-21 | 2014-12-03 | 中兴通讯股份有限公司 | Processing method and processing device for keyword mapping based on hash table |
| CN103414701A (en) * | 2013-07-25 | 2013-11-27 | 华为技术有限公司 | Rule matching method and device |
| CN107623640A (en) * | 2017-11-07 | 2018-01-23 | 北京锐安科技有限公司 | A kind of method and device for strengthening hash algorithm |
| CN110191109A (en) * | 2019-05-17 | 2019-08-30 | 杭州迪普信息技术有限公司 | A kind of packet sampling method and device |
| CN110784378A (en) * | 2019-11-04 | 2020-02-11 | 盛科网络（苏州）有限公司 | Method and device for realizing accurate flow balance by using TWAMP (two way operational amplifier) |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112702277A (en) | 2021-04-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11736388B1 (en) | Load balancing path assignments techniques | |
| US9654419B2 (en) | Fabric channel control apparatus and method | |
| CN107580769B (en) | Method and apparatus for load balancing in a network switch | |
| US9270601B2 (en) | Path resolution for hierarchical load distribution | |
| Xu et al. | Real-time update with joint optimization of route selection and update scheduling for SDNs | |
| CN112350949A (en) | Rerouting congestion control method and system based on flow scheduling in software defined network | |
| CN116055415A (en) | Data packet transmission control method and device | |
| US10686616B2 (en) | System and method to control latency of serially-replicated multi-destination flows | |
| US8867408B2 (en) | Fast convergence on child link failures and weighted load balancing of aggregate ethernet/sonet bundles | |
| US10305787B2 (en) | Dropping cells of a same packet sent among multiple paths within a packet switching device | |
| CN114500354A (en) | Switch control method, device, control equipment and storage medium | |
| CN112702277B (en) | Load balancing configuration optimization method and device | |
| CN111865789B (en) | SR path constraint method based on segment routing | |
| CN115883469B (en) | Data stream load balancing method and device and data center | |
| CN110324255B (en) | Data center network coding oriented switch/router cache queue management method | |
| Dou et al. | ProgrammabilityMedic: Predictable path programmability recovery under multiple controller failures in SD-WANs | |
| US10887237B2 (en) | Advanced load balancing based on bandwidth estimation | |
| CN112187642B (en) | Weighted bandwidth allocation for adaptive routing | |
| CN113890855A (en) | Message forwarding method, system, equipment and medium | |
| Nithin et al. | Efficient load balancing for multicast traffic in data center networks using SDN | |
| Huang et al. | Updating data-center network with ultra-low latency data plane | |
| CN115037667A (en) | Fine-grained network situation awareness and source routing intelligent optimization method and device | |
| US20140040659A1 (en) | Selection of one of first and second links between first and second network devices | |
| Duan et al. | GLIB: A Global and Local Integrated Load Balancing Scheme for Datacenter Network | |
| CN113824781B (en) | Data center network source routing method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | 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 |