CN114070797A - Method and system for controlling data transmission - Google Patents
Method and system for controlling data transmission Download PDFInfo
- Publication number
- CN114070797A CN114070797A CN202111153892.5A CN202111153892A CN114070797A CN 114070797 A CN114070797 A CN 114070797A CN 202111153892 A CN202111153892 A CN 202111153892A CN 114070797 A CN114070797 A CN 114070797A
- Authority
- CN
- China
- Prior art keywords
- layer
- hash algorithm
- variance
- hash
- data
- 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.)
- Pending
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
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/24—Multipath
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L49/00—Packet switching elements
- H04L49/15—Interconnection of switching modules
Abstract
The application relates to a method and a system for controlling data transmission, in particular to the technical field of network communication. The method is used for any one of a first layer switch and a second layer switch which are cascaded, and comprises the following steps: determining the minimum flow variance in a variance mapping table, and determining a target hash algorithm currently adopted by the flow variance in a first layer hash algorithm and a second layer hash algorithm mapped by the minimum flow variance; and performing hash calculation on the target data based on a target hash algorithm, and forwarding the target data according to the obtained hash value. Through the Hash algorithm of the switch determined by the scheme, the variance value of the data traffic forwarded by each port of the second layer of equipment in the cascade equivalent routing network is minimum, the data traffic forwarded by each port of the second layer of equipment is more balanced, and the condition that the link is blocked due to the fact that data is polarized to a certain link is avoided as far as possible.
Description
Technical Field
The invention relates to the technical field of network communication, in particular to a method and a system for controlling signal transmission.
Background
There are often multiple paths in the network with the same destination and the same cost. At present, a load balancing strategy based on a hash algorithm is generally adopted to control data transmission of an equivalent multipath.
In practical applications, a cascading networking mode of equivalent routes occurs, that is, a first-level device and a second-level device have a first-layer equivalent route, and a second-level device and a third-level device have a second-layer equivalent route, but when the hash algorithm of the first-layer equivalent route and the hash algorithm of the second-layer equivalent route are the same, data flowing into the second-layer equivalent route from the first-layer equivalent route will be caused, and the calculated hash values are the same, so that traffic flows into a certain link in a centralized manner. In order to solve the above problem, at present, a hash algorithm is finely tuned on the second layer equivalent route in a manual manner, for example, an xor bit is added in a port selection algorithm, so that it is ensured that a load balance can be realized for a finely tuned hash value.
However, in the above scheme, when the input data traffic changes, the load balancing effect of the trimmed hash algorithm also changes, which results in an unstable load balancing effect.
Disclosure of Invention
The application provides a method and a system for controlling data transmission, which enable link loads in an equivalent multi-routing path to be more balanced.
In one aspect, a method for controlling data transmission is provided, where the method is used for any one of a first layer switch and a second layer switch in cascade connection, where the first layer switch and the second layer switch both have equivalent multi-routing paths pointing to a same destination address, and the variance mapping table is used to represent a mapping relationship between a traffic variance of each output port of the second layer switch and a first layer hash algorithm used by the first layer switch and a second layer hash algorithm used by the second layer switch;
the method comprises the following steps:
determining the minimum flow variance in a variance mapping table, and determining a target hash algorithm currently adopted by the flow variance in a first layer hash algorithm and a second layer hash algorithm mapped by the minimum flow variance;
and performing hash calculation on the target data based on the target hash algorithm, and forwarding the target data according to the obtained hash value.
In another aspect, a system for controlling data transmission is provided, where the system is applied to any one of a first layer switch and a second layer switch in cascade connection, and both the first layer switch and the second layer switch have equivalent multi-routing paths pointing to a same destination address;
the system comprises:
the hash algorithm determining unit is used for determining the minimum flow variance in the variance mapping table and determining a target hash algorithm currently adopted by the hash algorithm determining unit in a first layer of hash algorithm and a second layer of hash algorithm mapped by the minimum flow variance; the variance mapping table is used for representing the mapping relation between the flow variance of each output port of the second-layer switch and a first-layer hash algorithm adopted by the first-layer switch and a second-layer hash algorithm adopted by the second-layer switch;
and the data forwarding unit is used for carrying out hash calculation on the target data based on the target hash algorithm and forwarding the target data according to the obtained hash value.
In a possible implementation, the hash algorithm determination unit is further configured to,
when the switch device is a first-layer device, determining a first-layer hash algorithm corresponding to the minimum value of the traffic variance as the target hash algorithm in the variance mapping table;
alternatively, the first and second electrodes may be,
and when the switch equipment is second-layer equipment, determining a second-layer hash algorithm corresponding to the minimum value of the flow variance as a target hash algorithm in the variance mapping table.
In a possible implementation, the hash algorithm determination unit is further configured to,
receiving an algorithm message issued by the first layer of equipment, and determining a second layer of hash algorithm in the algorithm message as the target hash algorithm; the algorithm message is generated by the first layer device according to the minimum value of the flow variance in the variance mapping table.
In one possible implementation, the variance mapping table is constructed by the first layer device; when the switch device is a first tier device, the system further comprises:
a first message sending unit, configured to send a first message to a second layer device; the first message comprises a hash algorithm identifier applied by the first layer device;
a second packet receiving unit, configured to receive a second packet sent by a second layer of equipment, where the second packet is used to indicate a mapping relationship between the first layer of hash algorithm, the second layer of hash algorithm, and a traffic variance;
and the variance mapping table constructing unit is used for constructing the variance mapping table according to the second message sent by the second layer equipment.
In a possible implementation manner, the first packet includes a destination address of an equivalent multi-routing path of the first layer device, a first hash identifier, and a data five-tuple; the first hash mark is used for indicating a first layer hash algorithm adopted by the first layer device.
The second message comprises the first hash identification, the second hash identification and the first flow variance; the second hash mark is used for indicating a second layer hash algorithm adopted by a second layer device; the first traffic variance is obtained by the second layer device calculating the data quintuple through a second layer hash algorithm indicated by the second hash identifier, determining a forwarding port of the data quintuple in the second layer device, and calculating a variance value of data traffic corresponding to each forwarding port.
In a possible implementation manner, the first packet includes a destination address and a first hash identifier of an equivalent multi-routing path of the first layer device; the first hash mark is used for indicating the first layer hash algorithm adopted by the first layer equipment for forwarding;
the system further comprises:
and the first data forwarding unit is used for forwarding the first data to the second layer device through a first layer hash algorithm indicated by the first hash identifier.
In a possible implementation manner, the second packet includes the first hash identifier, the second hash identifier, and the first traffic variance; the second hash mark is used for indicating a second layer hash algorithm adopted by a second layer device; the first traffic variance is obtained by the second-layer device calculating the first data through the second-layer hash algorithm, determining forwarding ports of the first data in the second-layer device, and calculating variance values of data traffic corresponding to the forwarding ports.
In a possible implementation manner, when the switch device is a first layer device, the system further includes:
a timer starting unit for starting the multi-route detection timer;
and the variance mapping table constructing unit is used for sending a first message to the second layer device when detecting that the time indicated by the multi-route detection timer meets a specified condition, so as to update the variance mapping table according to a received second message sent by the second device.
In still another aspect, a switch device is provided, where the switch device includes a processor and a memory, where the memory stores at least one instruction, at least one program, a set of codes, or a set of instructions, and the at least one instruction, the at least one program, the set of codes, or the set of instructions is loaded and executed by the processor to implement the method for controlling data transmission described above.
In yet another aspect, a computer-readable storage medium is provided, in which a computer program is stored, the computer program being adapted to be executed by a processor to implement the above-mentioned method for controlling data transmission.
In yet another aspect, a computer program product or computer program is provided, the computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the computer device to execute the method for controlling data transmission provided in the various alternative implementations described above.
The technical scheme provided by the application can comprise the following beneficial effects:
when the first layer device and the second layer device have equivalent routing networks with the same destination addresses in the cascade equivalent routing network, before the hash algorithm of the first layer device and the second layer device needs to be selected, the variance mapping table can be read first, and the adopted first layer hash algorithm and the second layer hash algorithm are determined according to the corresponding relation between the first layer hash algorithm and the second layer hash algorithm and the minimum value of the flow variance of each port of the second layer device, so that the switch can conveniently adopt and forward data. When the first-layer equipment adopts a first-layer hash algorithm corresponding to the minimum value of the flow variance, and the second-layer equipment adopts a second-layer hash algorithm corresponding to the minimum value of the flow variance, the variance value of data flow forwarded by each port of the second-layer equipment in the cascade equivalent routing network is the minimum, the data flow forwarded by each port of the second-layer equipment is more balanced, and the condition that data polarization to a certain link causes link blockage is avoided as far as possible.
Drawings
In order to more clearly illustrate the detailed description of the present application or the technical solutions in the prior art, the drawings needed to be used in the detailed description of the present application or the prior art description will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a schematic diagram illustrating a cascaded equivalent routing network in accordance with an exemplary embodiment.
Fig. 2 is a flow chart illustrating a method of controlling data transmission according to an example embodiment.
FIG. 3 is a flowchart illustrating a method of construction of a variance map, according to an example embodiment.
FIG. 4 is a flowchart illustrating a method of construction of a variance map, according to an example embodiment.
Fig. 5 is a flowchart illustrating a method of controlling data transmission according to an example embodiment.
Fig. 6 is a flowchart illustrating a method of controlling data transmission according to an example embodiment.
Fig. 7 is a block diagram illustrating a structure of a system for controlling data transmission according to an exemplary embodiment.
Fig. 8 is a schematic diagram of a communication device provided in accordance with an exemplary embodiment of the present application.
Detailed Description
The technical solutions of the present application will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are only some embodiments of the present application, but not all 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 application.
It should be understood that "indication" mentioned in the embodiments of the present application may be a direct indication, an indirect indication, or an indication of an association relationship. For example, a indicates B, which may mean that a directly indicates B, e.g., B may be obtained by a; it may also mean that a indicates B indirectly, for example, a indicates C, and B may be obtained by C; it can also mean that there is an association between a and B.
In the description of the embodiments of the present application, the term "correspond" may indicate that there is a direct correspondence or an indirect correspondence between the two, may also indicate that there is an association between the two, and may also indicate and be indicated, configure and configured, and so on.
In the embodiment of the present application, "predefining" may be implemented by saving a corresponding code, table, or other manners that may be used to indicate related information in advance in a device (for example, including a terminal device and a network device), and the present application is not limited to a specific implementation manner thereof.
Fig. 1 is a schematic diagram illustrating a cascaded equivalent routing network in accordance with an exemplary embodiment. As shown in fig. 1, the cascaded equivalent routing network includes a first layer device 101, a second layer device 102, a second layer device 103, and other switch devices.
The first layer device 101, the second layer device 102, and the second layer device 103 are all switch devices.
In the embodiment of the present application, the first layer device 101 and the second layer device 102, and the first layer device 102 and the second layer device 103 form an equal cost multi-path route. That is, in the process of the first layer device 101 reaching a certain destination address, the path overhead from the first layer device 101 to the second layer device 102 and from the first layer device 101 to the second layer device 103 is the same.
In the embodiment of the present application, the second tier device 102 and other switch devices connected thereto also form equivalent multi-path routes, so as to form a cascaded equivalent routing network.
In the cascade equivalent routing network as shown in fig. 1, assuming that hash algorithms adopted by the first layer device 101 and the second layer device 102 are the same when load balancing is implemented, at this time, the first layer device 101 selectively transmits a plurality of data packets to the second layer device 102 through the hash algorithms, and at this time, the second layer device may further calculate the plurality of data packets through the same hash algorithms. Because the algorithms are the same, each data packet arriving at the second layer device is calculated through the hash algorithm, and the obtained values are the same or meet the same selection condition, so that the second layer device transmits a plurality of data through a certain link, and the load balancing strategy fails.
To avoid the above situation, different hash algorithm combinations are usually adopted in the first layer device and the second layer device of the cascaded equivalent routing network shown in fig. 1, but the load balancing effect of adopting the hash algorithm combination is also unstable for different data flow situations.
In one possible implementation, there are several hash algorithms in the first layer of devices, such as hash algorithm 1, hash algorithm 2, and hash algorithm 3; there are also several hash algorithms in the second tier device, such as hash algorithm 4, hash algorithm 5, and hash algorithm 6. Therefore, 9 hash algorithm combinations can be formed between the first layer device and the second layer device.
Fig. 2 is a flow chart illustrating a method of controlling data transmission according to an example embodiment. This is performed by a first tier device in a cascaded equal cost routing network as shown in figure 1. As shown in fig. 2, the method for controlling data transmission may include the steps of:
The variance mapping table is used for representing the mapping relation between the flow variance of each output port of the second-layer switch and a first-layer hash algorithm adopted by the first-layer switch and a second-layer hash algorithm adopted by the second-layer switch; the flow variance is used for indicating the variance value of the flow of each port of the second layer device when the first layer device adopts the first layer hash algorithm and the second layer device adopts the second layer hash algorithm.
For example, the variance mapping table may be as shown in table 1.
| First hash mark | Second floor equipment | Variance (variance) | Second layer hash algorithm |
| hash 1 | C | S1 | hash 4 |
| hash 1 | C | S2 | hash 5 |
| hash 1 | C | S3 | hash 6 |
| hash 2 | C | S4 | hash 4 |
| hash 2 | C | S5 | hash 5 |
| hash 2 | C | S6 | hash 6 |
| hash 3 | C | S7 | hash 4 |
| hash 3 | C | S8 | hash 5 |
| hash 3 | C | S9 | hash 6 |
TABLE 1
According to table 1, the identifier of the first layer hash algorithm corresponding to the minimum variance and the identifier of the second layer hash algorithm can be read out, so as to determine the target first layer hash algorithm and the target second layer hash algorithm, and at this time, when data is forwarded through the target first layer hash algorithm and the target second layer hash algorithm, the load balancing effect is the best.
In a possible implementation manner, the variance mapping table may be obtained by traversing a first layer hash algorithm adopted by the first layer device and a second layer hash algorithm adopted by the second layer device, and then obtaining a traffic variance value between each port of the second layer device.
In a possible implementation manner, when the switch device is a first-layer device, in the variance mapping table, determining a first-layer hash algorithm corresponding to the minimum value of the traffic variance as the target hash algorithm;
alternatively, the first and second electrodes may be,
and when the switch equipment is second-layer equipment, determining a second-layer hash algorithm corresponding to the minimum value of the flow variance as a target hash algorithm in the variance mapping table.
After the target hash algorithm corresponding to the switch device is determined, the characteristic values of the target data, such as the data quintuple, can be calculated according to the target hash algorithm to obtain the corresponding hash value, and the corresponding hash table is inquired in the switch device to obtain the forwarding port corresponding to the target data, so as to forward the target data.
In a possible implementation manner, when the switch device is a second layer device, receiving an algorithm message issued by the first layer device, and determining a second layer hash algorithm in the algorithm message as the target hash algorithm; the algorithm message is generated by the first layer device according to the minimum value of the flow variance in the variance mapping table.
In summary, when the first layer device and the second layer device in the cascaded equivalent routing network have equivalent routing networks with the same destination address, before the hash algorithm of the first layer device and the second layer device needs to be selected, the variance mapping table may be read first, and the first layer hash algorithm and the second layer hash algorithm used may be determined according to the correspondence between the first layer hash algorithm and the second layer hash algorithm and the minimum value of the traffic variance of each port of the second layer device, so that the switch may use and forward data. When the first-layer equipment adopts a first-layer hash algorithm corresponding to the minimum value of the flow variance, and the second-layer equipment adopts a second-layer hash algorithm corresponding to the minimum value of the flow variance, the variance value of data flow forwarded by each port of the second-layer equipment in the cascade equivalent routing network is the minimum, the data flow forwarded by each port of the second-layer equipment is more balanced, and the condition that data polarization to a certain link causes link blockage is avoided as far as possible.
FIG. 3 is a flowchart illustrating a method of construction of a variance map, according to an example embodiment. The method is performed by a first tier device in a cascaded equal cost routing network as shown in fig. 1. As shown in fig. 2, the method for controlling data transmission may include the steps of:
When the first layer device needs to construct the variance mapping table, a first message may be sent to the second layer device to inform the second layer device of the first layer hash algorithm adopted by the first layer device at this time.
In a possible implementation manner of the embodiment of the present application, the second packet includes a first hash identifier corresponding to a first layer hash algorithm and a hash identifier corresponding to a second layer hash algorithm.
In a possible implementation manner, the traffic variance corresponding to the first hash identifier and each second-layer hash algorithm is obtained by traversing each second-layer hash algorithm by the second-layer device, calculating a data five-tuple through the second-layer hash algorithm corresponding to the second-layer device, determining a forwarding port of the data five-tuple in the second-layer device, and calculating a variance value of data traffic corresponding to each forwarding port.
That is, when the second layer device receives the hash identifier, the second layer device performs data processing on the issued data quintuple through each second layer hash algorithm corresponding to the second layer device, and determines a forwarding port of the data indicated by the data quintuple through the second layer hash algorithm.
Taking one of the second-layer hash algorithms as an example, when the second-layer hash algorithm is used to perform data processing on the delivered data quintuple, the forwarding condition of the data, which is calculated by the second-layer hash algorithm and is required to be indicated by each port for the data quintuple, can be determined within a certain period of time, and the variance value of the data volume sent by each port is obtained.
As shown in table 2 below, traversing the second-layer hash algorithms, that is, after the second-layer device receives the first hash identifier, the variance value corresponding to each second-layer hash algorithm is obtained, that is, the traffic variance corresponding to the first hash identifier and each second-layer hash algorithm is obtained.
Step 303, constructing the variance mapping table according to the second packet sent by the second layer device.
After the first layer device receives each second packet sent by the second layer device, a variance mapping table used for indicating the flow variance and used between the first layer hash algorithm and the second layer hash algorithm can be constructed according to the second packet.
In summary, when the first layer device and the second layer device in the cascaded equivalent routing network have equivalent routing networks with the same destination address, before the hash algorithm of the first layer device and the second layer device needs to be selected, the variance mapping table may be read first, and the first layer hash algorithm and the second layer hash algorithm used may be determined according to the correspondence between the first layer hash algorithm and the second layer hash algorithm and the minimum value of the traffic variance of each port of the second layer device, so that the switch may use and forward data. When the first-layer equipment adopts a first-layer hash algorithm corresponding to the minimum value of the flow variance, and the second-layer equipment adopts a second-layer hash algorithm corresponding to the minimum value of the flow variance, the variance value of data flow forwarded by each port of the second-layer equipment in the cascade equivalent routing network is the minimum, the data flow forwarded by each port of the second-layer equipment is more balanced, and the condition that data polarization to a certain link causes link blockage is avoided as far as possible.
FIG. 4 is a flowchart illustrating a method of construction of a variance map, according to an example embodiment. The method is performed by a first tier device in a cascaded equal cost routing network as shown in fig. 1. As shown in fig. 4, the method for controlling data transmission may include the steps of:
In a possible implementation manner, after the second layer device receives the first packet, the hash identifier corresponding to the first layer hash algorithm stored in the second layer device is updated according to the hash identifier corresponding to the first layer hash algorithm in the first packet.
That is, the first layer device continuously issues the hash identifier corresponding to each first layer hash algorithm in the process of traversing the first layer hash algorithm, and at this time, the second layer device should update the hash identifier stored therein according to the traversal of the first layer device, so as to ensure that the hash identifier accurately corresponds to the flow variance in the subsequently uploaded first message.
The flow variance calculation method in step 402 may be similar to that in step 302, and is not described here again.
That is, the first packet includes the first hash identifier, the second hash identifier and the traffic variance value, and at this time, the first packet indicates the corresponding relationship among the first layer hash algorithm, the second layer hash algorithm and the traffic variance value.
In summary, when the first layer device and the second layer device in the cascaded equivalent routing network have equivalent routing networks with the same destination address, before the hash algorithm of the first layer device and the second layer device needs to be selected, the variance mapping table may be read first, and the first layer hash algorithm and the second layer hash algorithm used may be determined according to the correspondence between the first layer hash algorithm and the second layer hash algorithm and the minimum value of the traffic variance of each port of the second layer device, so that the switch may use and forward data. When the first-layer equipment adopts a first-layer hash algorithm corresponding to the minimum value of the flow variance, and the second-layer equipment adopts a second-layer hash algorithm corresponding to the minimum value of the flow variance, the variance value of data flow forwarded by each port of the second-layer equipment in the cascade equivalent routing network is the minimum, the data flow forwarded by each port of the second-layer equipment is more balanced, and the condition that data polarization to a certain link causes link blockage is avoided as far as possible.
Fig. 5 is a flowchart illustrating a method of controlling data transmission according to an example embodiment. The method is performed by a first layer device and a second layer device in a cascaded equal cost routing network as shown in fig. 1. As shown in fig. 5, the method for controlling data transmission may include the steps of:
When the first layer device includes the equivalent multi-routing path, the first layer device needs to process a data quintuple of a data packet to be sent through a first layer hash algorithm stored in the first layer device in advance, so that the data packet is determined to be forwarded through one path in the equivalent multi-routing path.
When the first layer of equipment has the equivalent multi-routing path, the first layer of equipment still needs to forward the data packet through the equivalent multi-routing path, so that the first layer of equipment can perform data processing on the five-tuple in the first data according to a preset first layer of hash algorithm, thereby determining a forwarding port and a forwarding path of the first data. (for example, comparing the hash value obtained after the data processing with the hash table corresponding to the first-layer hash algorithm, and determining the forwarding port and the forwarding path of the first data).
In a possible implementation manner of the embodiment of the present application, the first packet includes a destination address and a first hash identifier of an equivalent multi-routing path of the first layer device; the first hash mark is used for indicating the first layer hash algorithm adopted by the first layer equipment for forwarding.
And for the first layer device, forwarding the first data to the second layer device through the first layer hash algorithm indicated by the first hash identifier.
The first hash identifier is used for indicating a first layer hash algorithm adopted by the first layer device for forwarding the data corresponding to the data quintuple. The data quintuple is a source IP address, a source port, a destination IP address, a destination port and a transport layer protocol.
In one possible implementation, the first packet may be a first protocol packet.
While the first data is forwarded, the first layer device may also send, through the first protocol packet, through each interface of the equivalent multi-routing path, to each second layer device connected to the first layer device.
The first protocol message includes a destination address and a first hash identifier of an equivalent multi-routing path of the first layer device. For example, the first protocol packet may be as shown in table 3.
TABLE 3
As shown in table 3, the first protocol message further includes a multicast protocol address, a protocol type, and a source address. The destination address is a multicast protocol address M to support and establish a hash variance table of the first layer device, that is, each second layer device can forward the variance table to the first layer device according to the multicast protocol address M and the corresponding source address. The protocol type is used to indicate the processing manner when the second layer device receives the first protocol packet (e.g., how to decode the protocol packet and how to perform an action according to the data in the protocol packet).
When the second layer device detects that the destination address of the equivalent multi-routing path in the second layer device matches the destination address of the equivalent multi-routing path sent in the first protocol packet, it indicates that the second layer device and the first layer device have the cascaded equivalent routing as shown in the embodiment shown in fig. 1.
In order to avoid port load imbalance in the second layer device, the hash algorithm of the first layer device and the second layer device needs to be adjusted.
For example, after the second layer device receives the first protocol packet, the data packet received within a certain period of time may be respectively forwarded through each second layer hash algorithm, and the data traffic of the port of the second layer device when the data packet is forwarded by each second layer hash algorithm is recorded.
And when the second layer equipment performs data processing on the data quintuple through a second layer hash algorithm, obtaining a forwarding port corresponding to the data message, forwarding each data message through the forwarding port, and recording the forwarding flow of each port through the second layer hash algorithm within a period of time.
After the data distribution condition of each port is determined, the variance value of the data traffic of each port when the data traffic is sent by the second-layer hash algorithm can be calculated, and the variance formula is as follows:
The variance may reflect a port load balancing condition among the ports, where the greater the variance is, the more unbalanced the port load of each port is, and the smaller the variance is, the more balanced the port load of each port is.
The second packet is used for indicating a mapping relation among the first layer of hash algorithm, the second layer of hash algorithm and the flow variance.
The second message comprises the first hash identification, the second hash identification and the first flow variance; the second hash mark is used for indicating a second layer hash algorithm adopted by a second layer device; the first traffic variance is obtained by the second-layer device calculating the first data through the second-layer hash algorithm, determining forwarding ports of the first data in the second-layer device, and calculating variance values of data traffic corresponding to the forwarding ports.
That is, when the second layer device can forward each data packet including the first data according to the second layer hash algorithm, the forwarding port corresponding to each data packet including the first data is calculated, and the traffic variance value of each port is obtained as the first traffic variance.
In one possible implementation, the second message may be as shown in table 4 below.
Protocol message 2
The second message further includes a second hash identifier, and the second hash identifier is used for indicating a second layer hash algorithm adopted by the second layer device when the variance is calculated, so that a mapping relationship among the first layer hash algorithm, the second layer hash algorithm, and the traffic variance can be determined according to the table. At this time, the first layer device may construct a correspondence table among the first hash identifier, the second hash identifier, and the traffic variance according to the first hash identifier, the second hash identifier, and the traffic variance sequentially uploaded by the second layer device, so as to indicate a correspondence relationship among the first hash identifier, the second hash identifier, and the traffic variance (i.e., a correspondence relationship among the first layer hash algorithm, the second layer hash algorithm, and the traffic variance).
And 505, the first layer device constructs the variance mapping table according to the second message sent by the second layer device.
After the first layer device acquires each second packet sent by the second layer device, a variance mapping table shown in the table can be constructed according to the first layer hash algorithm, the second layer hash algorithm and the relation among the traffic variance values indicated in the second packet.
When the first-layer device obtains the flow variance that each hash identifier corresponds to each second-layer hash algorithm, that is, when the first-layer device constructs the variance mapping table among each hash identifier, each second-layer hash algorithm, and the flow variance value as shown in table 2, the minimum value among the flow variances can be determined as the target flow variance by reading the variance mapping table.
In step 507, the first layer device determines the first layer hash algorithm indicated by the hash identifier corresponding to the target flow variance as the target first layer hash algorithm, and determines the second layer hash algorithm corresponding to the target flow variance as the target second layer hash algorithm.
After the first layer device determines the minimum value in the flow variance as the target flow variance, the first hash identifier and the second hash identifier corresponding to the target flow variance can be read according to the corresponding relationship among the flow variance, the first hash identifier and the second hash identifier, so that the target first layer hash algorithm and the target second layer hash algorithm are determined.
In one possible implementation, the algorithm message may be as shown in table 5.
TABLE 5
In summary, when the first layer device and the second layer device in the cascaded equivalent routing network have equivalent routing networks with the same destination address, before the hash algorithm of the first layer device and the second layer device needs to be selected, the variance mapping table may be read first, and the first layer hash algorithm and the second layer hash algorithm used may be determined according to the correspondence between the first layer hash algorithm and the second layer hash algorithm and the minimum value of the traffic variance of each port of the second layer device, so that the switch may use and forward data. When the first-layer equipment adopts a first-layer hash algorithm corresponding to the minimum value of the flow variance, and the second-layer equipment adopts a second-layer hash algorithm corresponding to the minimum value of the flow variance, the variance value of data flow forwarded by each port of the second-layer equipment in the cascade equivalent routing network is the minimum, the data flow forwarded by each port of the second-layer equipment is more balanced, and the condition that data polarization to a certain link causes link blockage is avoided as far as possible.
Fig. 6 is a flowchart illustrating a method of controlling data transmission according to an example embodiment. The method is performed by a first layer device and a second layer device in a cascaded equal cost routing network as shown in fig. 1. As shown in fig. 6, the method for controlling data transmission may include the steps of:
In one possible implementation, the first packet may be a second protocol packet.
At this time, the first message includes a destination address of an equivalent multi-routing path of the first layer device, a first hash identifier and a data quintuple; the first hash mark is used for indicating a first layer hash algorithm adopted by the first layer device.
In this embodiment of the present application, the first layer device may write a data quintuple of data to be transmitted in a second protocol packet, and send the second protocol packet to the second layer device. For example, the second protocol packet may be as shown in table 6.
TABLE 6
In a possible implementation manner of the embodiment of the present application, the traffic forwarding value of each port is calculated according to a data quintuple sent in the second protocol packet.
After the second layer device calculates the forwarding ports according to the quintuple sent by the second protocol message, the second layer device does not perform data forwarding according to the forwarding ports, but directly counts the times calculated by each forwarding port, thereby determining that each forwarding port calculates the quintuple according to the second layer hash algorithm, and simulating the data traffic required to be forwarded by each forwarding port.
Therefore, optionally, the quantity value of the forwarding data quintuple of each forwarding port is the number of times of occurrence of each forwarding port calculated according to each data quintuple.
In addition, in a possible implementation manner of the embodiment of the present application, the first layer device and the second layer device may still perform normal data transmission through the original first layer hash algorithm and the second layer hash algorithm while simulating data traffic that needs to be forwarded by each forwarding port through the second protocol packet. That is, the second layer device may receive the data packet sent by the first layer device, receive the sent second protocol packet, and call a certain computing resource to perform a simulation corresponding to forwarding of the data quintuple sent in the second protocol packet.
After the data traffic that needs to be forwarded by each forwarding port is calculated according to the data quintuple, the calculation process of the traffic variance is similar to that in step 503, and is not described here again.
And step 604, the first layer device constructs the variance mapping table according to the second message sent by the second layer device.
In step 607, the first layer device sends an algorithm packet indicating the target second layer hash algorithm to the second layer device. Correspondingly, the second layer device receives the algorithm message issued by the first layer device, and performs data forwarding of equal cost multiple paths in the second layer device according to the target second layer hash algorithm indicated in the algorithm message.
Step 603 to step 607 are similar to step 504 to step 508 in the embodiment shown in fig. 5, and are not described here again.
In summary, when the first layer device and the second layer device in the cascaded equivalent routing network have equivalent routing networks with the same destination address, before the hash algorithm of the first layer device and the second layer device needs to be selected, the variance mapping table may be read first, and the first layer hash algorithm and the second layer hash algorithm used may be determined according to the correspondence between the first layer hash algorithm and the second layer hash algorithm and the minimum value of the traffic variance of each port of the second layer device, so that the switch may use and forward data. When the first-layer equipment adopts a first-layer hash algorithm corresponding to the minimum value of the flow variance, and the second-layer equipment adopts a second-layer hash algorithm corresponding to the minimum value of the flow variance, the variance value of data flow forwarded by each port of the second-layer equipment in the cascade equivalent routing network is the minimum, the data flow forwarded by each port of the second-layer equipment is more balanced, and the condition that data polarization to a certain link causes link blockage is avoided as far as possible.
Fig. 7 is a block diagram illustrating a structure of a system for controlling data transmission according to an exemplary embodiment. The system is applied to any one of a first layer switch and a second layer switch which are cascaded, and the first layer switch and the second layer switch are both provided with equivalent multi-routing paths pointing to the same destination address;
the system comprises:
a hash algorithm determining unit 701, configured to determine a minimum flow variance in the variance mapping table, and determine a target hash algorithm currently used by the hash algorithm determining unit in a first layer hash algorithm and a second layer hash algorithm mapped by the minimum flow variance; the variance mapping table is used for representing the mapping relation between the flow variance of each output port of the second-layer switch and a first-layer hash algorithm adopted by the first-layer switch and a second-layer hash algorithm adopted by the second-layer switch;
a data forwarding unit 702, configured to perform hash calculation on the target data based on the target hash algorithm, and forward the target data according to the obtained hash value.
In a possible implementation, the hash algorithm determination unit is further configured to,
when the switch device is a first-layer device, determining a first-layer hash algorithm corresponding to the minimum value of the traffic variance as the target hash algorithm in the variance mapping table;
alternatively, the first and second electrodes may be,
and when the switch equipment is second-layer equipment, determining a second-layer hash algorithm corresponding to the minimum value of the flow variance as a target hash algorithm in the variance mapping table.
In a possible implementation, the hash algorithm determination unit is further configured to,
receiving an algorithm message issued by the first layer of equipment, and determining a second layer of hash algorithm in the algorithm message as the target hash algorithm; the algorithm message is generated by the first layer device according to the minimum value of the flow variance in the variance mapping table.
In one possible implementation, the variance mapping table is constructed by the first layer device; when the switch device is a first tier device, the system further comprises:
a first message sending unit, configured to send a first message to a second layer device; the first message comprises a hash algorithm identifier applied by the first layer device;
a second packet receiving unit, configured to receive a second packet sent by a second layer of equipment, where the second packet is used to indicate a mapping relationship between the first layer of hash algorithm, the second layer of hash algorithm, and a traffic variance;
and the variance mapping table constructing unit is used for constructing the variance mapping table according to the second message sent by the second layer equipment.
In a possible implementation manner, the first packet includes a destination address of an equivalent multi-routing path of the first layer device, a first hash identifier, and a data five-tuple; the first hash mark is used for indicating a first layer hash algorithm adopted by the first layer device.
The second message comprises the first hash identification, the second hash identification and the first flow variance; the second hash mark is used for indicating a second layer hash algorithm adopted by a second layer device; the first traffic variance is obtained by the second layer device calculating the data quintuple through a second layer hash algorithm indicated by the second hash identifier, determining a forwarding port of the data quintuple in the second layer device, and calculating a variance value of data traffic corresponding to each forwarding port.
In a possible implementation manner, the first packet includes a destination address and a first hash identifier of an equivalent multi-routing path of the first layer device; the first hash mark is used for indicating the first layer hash algorithm adopted by the first layer equipment for forwarding;
the system further comprises:
and the first data forwarding unit is used for forwarding the first data to the second layer device through a first layer hash algorithm indicated by the first hash identifier.
In a possible implementation manner, the second packet includes the first hash identifier, the second hash identifier, and the first traffic variance; the second hash mark is used for indicating a second layer hash algorithm adopted by a second layer device; the first traffic variance is obtained by the second-layer device calculating the first data through the second-layer hash algorithm, determining forwarding ports of the first data in the second-layer device, and calculating variance values of data traffic corresponding to the forwarding ports.
In a possible implementation manner, when the switch device is a first layer device, the system further includes:
a timer starting unit for starting the multi-route detection timer;
and the variance mapping table constructing unit is used for sending a first message to the second layer device when detecting that the time indicated by the multi-route detection timer meets a specified condition, so as to update the variance mapping table according to a received second message sent by the second device.
In summary, in the cascade equal-cost routing network, the first layer device may issue a data quintuple and a hash identifier corresponding to a hash algorithm currently used by the first layer device to the second layer device, and when the first layer device and the second layer device both have equal-cost multiple routing paths with the same destination address, the second layer device determines a forwarding port of the data quintuple through the second layer hash algorithm, thereby determining a forwarding condition of each forwarding port in the second layer device. The first-layer hash algorithm and the second-layer hash algorithm are traversed, namely, when each first-layer hash algorithm is combined with each second-layer hash algorithm, the first-layer hash algorithm and the second-layer hash algorithm with the minimum variance value are selected from the variance values of all ports of the second-layer equipment and are used as algorithms for data forwarding, so that the load of links in the equivalent multi-routing path is more balanced, and the condition that the links are blocked due to the fact that data are polarized to a certain link is avoided as far as possible.
Refer to fig. 8, which is a schematic diagram of a communication device according to an exemplary embodiment of the present application, the communication device including a memory and a processor, the memory storing a computer program, and the computer program when executed by the processor implementing the method.
The processor may be a Central Processing Unit (CPU). The Processor may also be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, or a combination thereof.
The memory, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules corresponding to the methods of the embodiments of the present invention. The processor executes various functional applications and data processing of the processor by executing non-transitory software programs, instructions and modules stored in the memory, that is, the method in the above method embodiment is realized.
The memory may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created by the processor, and the like. Further, the memory may include high speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory optionally includes memory located remotely from the processor, and such remote memory may be coupled to the processor via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
In an exemplary embodiment, a computer readable storage medium is also provided for storing at least one computer program, which is loaded and executed by a processor to implement all or part of the steps of the above method. For example, the computer-readable storage medium may be a Read-Only Memory (ROM), a Random Access Memory (RAM), a Compact Disc Read-Only Memory (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, and the like.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It will be understood that the present application is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.
Claims (10)
1. A method for controlling data transmission is characterized in that the method is used for any one of a first layer switch and a second layer switch which are cascaded, and the first layer switch and the second layer switch are both provided with equivalent multi-routing paths pointing to the same destination address;
the method comprises the following steps:
determining the minimum flow variance in a variance mapping table, and determining a target hash algorithm currently adopted by the flow variance in a first layer hash algorithm and a second layer hash algorithm mapped by the minimum flow variance; the variance mapping table is used for representing the mapping relationship between the flow variance of each output port of the second layer switch and the first layer hash algorithm adopted by the first layer switch and the second layer hash algorithm adopted by the second layer switch
And performing hash calculation on the target data based on the target hash algorithm, and forwarding the target data according to the obtained hash value.
2. The method according to claim 1, wherein the determining a target hash algorithm currently adopted by the first layer hash algorithm and the second layer hash algorithm mapped by the minimum traffic variance comprises:
when the switch device is a first-layer device, determining a first-layer hash algorithm corresponding to the minimum value of the traffic variance as the target hash algorithm in the variance mapping table;
alternatively, the first and second electrodes may be,
and when the switch equipment is second-layer equipment, determining a second-layer hash algorithm corresponding to the minimum value of the flow variance as a target hash algorithm in the variance mapping table.
3. The method according to claim 2, wherein the determining, in the variance mapping table, a second-layer hash algorithm corresponding to the minimum value of the traffic variance as a target hash algorithm comprises:
receiving an algorithm message issued by the first layer of equipment, and determining a second layer of hash algorithm in the algorithm message as the target hash algorithm; the algorithm message is generated by the first layer device according to the minimum value of the flow variance in the variance mapping table.
4. The method of any of claims 1 to 3, wherein the variance map is constructed by the first tier device;
when the switch device is a first tier device, the method further comprises:
sending a first message to a second layer device; the first message comprises a hash identifier used for indicating a first layer hash algorithm applied by the first layer equipment;
receiving a second message sent by a second layer device, wherein the second message is used for indicating a mapping relation among the first layer hash algorithm, the second layer hash algorithm and the flow variance;
and constructing the variance mapping table according to a second message sent by the second layer equipment.
5. The method of claim 4, wherein the first packet comprises a destination address of an equivalent multi-routing path of the first layer device, a first hash identifier, and a data quintuple; the first hash mark is used for indicating a first layer hash algorithm adopted by the first layer device.
The second message comprises the first hash identification, the second hash identification and the first flow variance; the second hash mark is used for indicating a second layer hash algorithm adopted by a second layer device; the first traffic variance is obtained by the second layer device calculating the data quintuple through a second layer hash algorithm indicated by the second hash identifier, determining a forwarding port of the data quintuple in the second layer device, and calculating a variance value of data traffic corresponding to each forwarding port.
6. The method of claim 4, wherein the first packet includes a destination address of an equivalent multi-routing path of the first layer device, the first hash identifier; the first hash mark is used for indicating the first layer hash algorithm adopted by the first layer equipment for forwarding;
when the switch device is a first tier device, the method further comprises:
and forwarding the first data to the second layer device through the first layer hash algorithm indicated by the first hash identifier.
7. The method according to claim 6, wherein the second packet includes the first hash identifier, a second hash identifier and a first traffic variance; the second hash mark is used for indicating a second layer hash algorithm adopted by a second layer device; the first traffic variance is obtained by the second-layer device calculating the first data through the second-layer hash algorithm, determining forwarding ports of the first data in the second-layer device, and calculating variance values of data traffic corresponding to the forwarding ports.
8. The method of claim 4, wherein when the switch device is a first tier device, the method further comprises:
starting a multi-route detection timer;
and when detecting that the time indicated by the multi-route detection timer meets a specified condition, sending a first message to second-layer equipment so as to update the variance mapping table according to a received second message sent by the second equipment.
9. A system for controlling data transmission is characterized in that the system is applied to any one of a first layer switch and a second layer switch which are cascaded, and the first layer switch and the second layer switch are both provided with equivalent multi-routing paths pointing to the same destination address;
the system comprises:
the hash algorithm determining unit is used for determining the minimum flow variance in the variance mapping table and determining a target hash algorithm currently adopted by the hash algorithm determining unit in a first layer of hash algorithm and a second layer of hash algorithm mapped by the minimum flow variance; the variance mapping table is used for representing the mapping relation between the flow variance of each output port of the second-layer switch and a first-layer hash algorithm adopted by the first-layer switch and a second-layer hash algorithm adopted by the second-layer switch;
and the data forwarding unit is used for carrying out hash calculation on the target data based on the target hash algorithm and forwarding the target data according to the obtained hash value.
10. A switch device, characterized in that it comprises a processor and a memory in which at least one instruction, at least one program, set of codes or set of instructions is stored, which is loaded and executed by the processor to implement the method of controlling data transmission according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111153892.5A CN114070797A (en) | 2021-09-29 | 2021-09-29 | Method and system for controlling data transmission |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111153892.5A CN114070797A (en) | 2021-09-29 | 2021-09-29 | Method and system for controlling data transmission |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114070797A true CN114070797A (en) | 2022-02-18 |
Family
ID=80233899
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111153892.5A Pending CN114070797A (en) | 2021-09-29 | 2021-09-29 | Method and system for controlling data transmission |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114070797A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023011153A1 (en) * | 2021-08-03 | 2023-02-09 | 华为技术有限公司 | Method and apparatus for determining hash algorithm information for load balancing, and storage medium |
| CN115883469A (en) * | 2023-01-04 | 2023-03-31 | 苏州浪潮智能科技有限公司 | Data flow load balancing method and device, network topology and data center |
-
2021
- 2021-09-29 CN CN202111153892.5A patent/CN114070797A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023011153A1 (en) * | 2021-08-03 | 2023-02-09 | 华为技术有限公司 | Method and apparatus for determining hash algorithm information for load balancing, and storage medium |
| CN115883469A (en) * | 2023-01-04 | 2023-03-31 | 苏州浪潮智能科技有限公司 | Data flow load balancing method and device, network topology and data center |
| CN115883469B (en) * | 2023-01-04 | 2023-06-02 | 苏州浪潮智能科技有限公司 | Data stream load balancing method and device and data center |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10728173B1 (en) | Equal cost multiple path group failover for multicast | |
| US8259585B1 (en) | Dynamic link load balancing | |
| US9503374B2 (en) | Apparatus for hybrid routing in SDN networks to avoid congestion and achieve good load balancing under fluctuating traffic load | |
| US10193810B2 (en) | Congestion-aware load balancing | |
| US9246818B2 (en) | Congestion notification in leaf and spine networks | |
| CN114070797A (en) | Method and system for controlling data transmission | |
| US20060133282A1 (en) | Systems and methods for multipath routing | |
| CN107078963B (en) | Route tracing in virtual extensible local area networks | |
| CN106713182B (en) | Method and device for processing flow table | |
| EP3186928B1 (en) | Bandwidth-weighted equal cost multi-path routing | |
| US11336577B2 (en) | Method and apparatus for implementing load sharing | |
| US9647925B2 (en) | System and method for data path validation and verification | |
| US10122627B2 (en) | Network routing through an overlay network | |
| JP2003338835A (en) | Packet switch and method | |
| US10536368B2 (en) | Network-aware routing in information centric networking | |
| CN112039772A (en) | Transmission path determining method and node | |
| KR101707355B1 (en) | Communication node, communication system, control device, packet transfer method, and program | |
| US20090296725A1 (en) | Router device for efficient routing with congestion minimized | |
| US20150381775A1 (en) | Communication system, communication method, control apparatus, control apparatus control method, and program | |
| US20170070473A1 (en) | A switching fabric including a virtual switch | |
| US20220217179A1 (en) | Methods and devices for measuring reputation in a communication network | |
| CN105530189B (en) | Method for forwarding message in TRILL network and routing bridge | |
| TWI492587B (en) | Network system and routing method | |
| CN114567679B (en) | Data transmission method and device | |
| US20220217092A1 (en) | Packet flow out-of-order detection method, packet processing method, and apparatus |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |