CN113206794A - Forwarding speed limiting method and device - Google Patents
Forwarding speed limiting method and device Download PDFInfo
- Publication number
- CN113206794A CN113206794A CN202110347628.9A CN202110347628A CN113206794A CN 113206794 A CN113206794 A CN 113206794A CN 202110347628 A CN202110347628 A CN 202110347628A CN 113206794 A CN113206794 A CN 113206794A
- Authority
- CN
- China
- Prior art keywords
- data stream
- rate
- line card
- table entry
- queue
- 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.)
- Granted
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
-
- 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
- H04L47/30—Flow control; Congestion control in combination with information about buffer occupancy at either end or at transit nodes
Abstract
The specification provides a forwarding speed limiting method and a forwarding speed limiting device, and relates to the technical field of communication. A forwarding speed limiting method is applied to a line card board in network equipment and comprises the following steps: receiving a data stream forwarded inside the network equipment, counting the receiving rate of the received data stream, and acquiring the internal forwarding information of the data stream; acquiring a queue state of a buffer queue corresponding to a data stream and a maximum rate of a sending data outflow port; generating a state table entry, wherein the state table entry comprises internal forwarding information, a queue state, a receiving rate and a maximum rate; and sending the state table entry to other line card boards in the network equipment so that the other line card boards limit the speed of the data stream sent to the line card boards according to the state table entry. By the method, the reliability of data stream forwarding of the network equipment can be improved.
Description
Technical Field
The present disclosure relates to the field of communications technologies, and in particular, to a forwarding speed limiting method and apparatus.
Background
With the popularization of networks, more and more users access the networks, and the traffic carried by the network devices performing data stream interaction is also larger and larger. In order to expand the access bandwidth, more ports are expanded to receive and forward data streams by deploying the line card boards on the network equipment, and data interaction between the line card boards is realized through the network board between the outgoing direction and the incoming direction.
Because the data stream received by the line card board does not occupy the whole bandwidth of the port, the number of line card boards deployed in the outgoing direction of the network device is generally smaller than the number of line card boards deployed in the incoming direction based on the consideration of the cost and other factors. However, in a network, burst traffic often occurs, that is, a large amount of data flows are received in a certain period of time, and at this time, congestion occurs in the outgoing direction due to the shortage of bandwidth. However, in the incoming direction, because the line card board cannot know the situation of the line card board in the outgoing direction, the data stream is still processed and forwarded at the highest rate, and congestion of the line card board in the outgoing direction is further increased, so that the problem of packet loss of the data stream on the line card board in the outgoing direction is solved, and the reliability of forwarding the data stream by the network device is reduced.
Disclosure of Invention
To overcome the problems in the related art, the present specification provides a rate limiting method and apparatus.
In combination with the first aspect of the embodiments of the present specification, the present application provides a forwarding speed-limiting method, which is applied to a cable card board in a network device, and includes:
receiving a data stream forwarded inside the network equipment, counting the receiving rate of the received data stream, and acquiring the internal forwarding information of the data stream;
acquiring a queue state of a buffer queue corresponding to a data stream and a maximum rate of a sending data outflow port;
generating a state table entry, wherein the state table entry comprises internal forwarding information, a queue state, a receiving rate and a maximum rate;
and sending the state table entry to other line card boards in the network equipment so that the other line card boards limit the speed of the data stream sent to the line card boards according to the state table entry.
Optionally, the method further includes:
receiving and storing state table entries sent by other line card boards, wherein the queue state comprises the occupation amount of a cache queue corresponding to one data stream and the queue depth distributed to the cache queue;
according to a queue depth ratio and a rate ratio corresponding to a data flow of the state table entry, wherein the queue depth ratio is the ratio of the occupied amount to the queue depth, the rate ratio is the ratio of the receiving rate to the maximum rate of the output port, and one data flow is marked by internal forwarding information;
and if the rate ratio is smaller than the queue depth ratio, limiting the forwarding speed of the data stream according to the maximum rate and the receiving rate of the currently received data stream.
Optionally, after the queue depth ratio and the rate ratio corresponding to one data flow according to the state table entry, the method further includes:
and if the rate ratio is not less than the queue depth ratio, forwarding the data stream according to the current receiving rate.
Further, sending the status table entry to another cable card board in the network device includes:
sending the state table entry to other line card boards in the network equipment in a broadcasting mode; alternatively, the first and second electrodes may be,
and sending the state table entry to other line card boards contained in the multicast group in a multicast mode.
Optionally, the state table entry includes: a source chip identification, a destination chip identification and a port identification.
In combination with the second aspect of the embodiments of the present specification, the present application provides a forwarding speed limiting device, which is applied to a cable card board in a network device, and includes:
the analysis unit is used for receiving the data stream forwarded inside the network equipment, counting the receiving rate of the received data stream and acquiring the internal forwarding information of the data stream;
the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring the queue state of a buffer queue corresponding to a data stream and the maximum rate of a sending data outflow port;
the generating unit is used for generating a state table entry, wherein the state table entry comprises internal forwarding information, a queue state, a receiving rate and a maximum rate;
and the sending unit is used for sending the state table entry to other line card boards in the network equipment so that the other line card boards can limit the speed of the data stream sent to the line card boards according to the state table entry.
Optionally, the apparatus further includes:
the receiving unit is used for receiving and storing state table entries sent by other line card boards, wherein the queue state comprises the occupation amount of a buffer queue corresponding to one data stream and the queue depth distributed to the buffer queue;
a determining unit, configured to determine a queue depth ratio and a rate ratio according to a state table entry corresponding to a data flow of the state table entry, where the queue depth ratio is a ratio of an occupied amount to a queue depth, the rate ratio is a ratio of a receiving rate to a maximum rate of an egress port, and one data flow is marked by internal forwarding information;
and the speed limiting unit is used for limiting the forwarding of the data stream according to the maximum rate and the receiving rate of the currently received data stream if the rate ratio is smaller than the queue depth ratio.
And further, the speed limiting unit is used for forwarding the data stream according to the current receiving rate if the rate ratio is not less than the queue depth ratio.
Optionally, the sending unit includes:
the broadcasting module is used for sending the state table entry to other line card boards in the network equipment in a broadcasting mode; alternatively, the first and second electrodes may be,
and the multicast module is used for sending the state table entry to other line card boards contained in the multicast group in a multicast mode.
Optionally, the state table entry includes: a source chip identification, a destination chip identification and a port identification.
The technical scheme provided by the implementation mode of the specification can have the following beneficial effects:
in the embodiment of the present specification, the line card board obtains internal forwarding information related to a data stream, counts a receiving rate of a data stream and a queue depth and an occupied amount of a cache queue associated with the data stream according to the internal forwarding information, generates a state entry, and sends the state entry to other line card boards in the network device, so that the other line card boards determine a forwarding condition of the line card board sending the state entry according to a rate and a queue state included in the state entry, and manages a rate of the data stream sent to the line card by the other line card boards, thereby avoiding congestion and even packet loss of the data stream on one line card board, and improving reliability of forwarding the data stream by the network device.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the specification.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present specification and together with the description, serve to explain the principles of the specification.
Fig. 1 is a flowchart of a forwarding speed limiting method according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a network device according to an embodiment of the present application;
fig. 3 is a schematic diagram of a network device according to an embodiment of the present application forwarding a data flow;
fig. 4 is a schematic configuration diagram of a transfer governor according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present specification.
The application provides a forwarding speed-limiting method, which is applied to a cable card board in network equipment, and as shown in fig. 1, the forwarding speed-limiting method includes:
s100, receiving the data stream forwarded inside the network equipment, counting the receiving rate of the received data stream, and acquiring the internal forwarding information of the data stream.
The network device as shown in fig. 2 comprises at least two cable card boards, and the cable card boards can be directly connected or connected through a network board. The on-line card board can be provided with a forwarding chip, a processor, a memory and other devices, wherein the forwarding chip, the processor and the memory are connected with each other, and the connection among the line card boards and the screen board are realized through the forwarding chip. Of course, the devices included in the network device and the cable card board are not limited to the above-mentioned devices, and may include others, and will not be described herein.
For example, as shown in fig. 2, in the network device, three wire-clamping boards, namely a wire-clamping board 1, a wire-clamping board 2, and a wire-clamping board 3, may be provided, where the three wire-clamping boards are connected to the network board respectively, and perform interaction of data streams through the network board.
A plurality of buffer queues are formed in the memory, each buffer queue is allocated with a preset storage space, and the forwarding chip can record the queue depth of the buffer queue and the current occupancy of each buffer queue. The occupied amount refers to the size of a storage space occupied by the forwarding chip when writing the received message in the data stream into the buffer queue. A cache queue may cache packets in multiple data flows, and a specific cache rule may be to bind an egress port to a cache queue, or to correspond a processor core of a processor to a cache queue, which is not limited to this. The buffer queue may be configured as a FIFO (First in First out), or in other forms.
After the network equipment operates, the data stream is received from the line card board on one side and is forwarded out from the line card board on the other side. In the network device, after one cable card board receives the data stream, the data stream can be matched according to a forwarding table issued by a processor to a forwarding chip, and a port is determined according to a matching result. And after receiving the message with the internal forwarding head, the network board sends the message to the line card board connected with the output port so as to realize external message forwarding.
When the data stream flows into the network device, the line card board may receive the data stream through the forwarding chip and analyze the data stream to determine a forwarding path of the data stream inside the network device.
For example, after the forwarding chips (i.e. forwarding chip 1 and forwarding chip 2) of the line card board 1 and the line card board 2 receive the data stream, the forwarding information is parsed by the header message of the data stream, and the forwarding information may include a source IP address, a destination IP address, a source MAC address, a destination MAC address, an applied network protocol, and the like. Based on the forwarding information, forwarding chip 1 and forwarding chip 2 can determine from which egress port on the network device the data stream needs to be sent, for example, the egress port is determined as being connected to cable card board 3. Thereafter, the forwarding chip may encapsulate an internal forwarding header for a packet in the data flow, and within the network device, the data flow may be guided to the corresponding egress port through the internal forwarding header.
In this way, the forwarding chip 1 and the forwarding chip 2 can encapsulate the received data stream, and the internal forwarding header may include information such as a source chip identifier, a destination chip identifier, a source port, and a destination port, but the information carried by the internal forwarding header is not limited thereto. Thereafter, the line card board 1 and the line card board 2 may transmit the data stream to the screen board so that the screen board forwards the data stream to the line card board 3.
When the forwarding chip 3 of the online card 3 receives the data stream forwarded from the inside of the network device (i.e. the data stream forwarded by the network board), the forwarding chip 3 counts the data stream, obtains the receiving rate of the data stream, can analyze the message in the data stream, determines that the target chip identifier is the chip identifier of itself, strips off the internal forwarding header, and writes the internal forwarding header into the corresponding cache queue.
In the embodiment shown in fig. 3, the forwarding chip 3 receives the data stream 1 and the data stream 2 sent by the forwarding chip 1 and the forwarding chip 2, respectively, so that the forwarding chip 3 can analyze the source chip identifier 1 (the chip identifier of the forwarding chip 1) and the source chip identifier 2 (the chip identifier of the forwarding chip 2) in the internal forwarding header, and the destination chip identifiers of the data stream 1 and the data stream 2 are consistent and are both the chip identifiers of the forwarding chip 3. The forwarding chip 3 can count that the receiving rate of the data stream 1 is 60Gbps (gigabits per second), and the receiving rate of the data stream 2 is 70 Gbps.
S101, acquiring a queue state of a buffer queue corresponding to a data stream and a maximum rate of a sending data outflow port.
After the forwarding chip analyzes the packet of the data flow, the output port of the data flow can be determined, and then the maximum rate of the output port when the data flow is forwarded can be determined according to the identifier of the output port. And the forwarding chip can also determine the queue state of the buffer queue corresponding to the egress port, including the queue depth of the buffer queue and the current occupancy in the buffer queue. The occupancy monitoring may be periodically or in real time, which is not limited herein. Data flow 3 may determine that the queue depth of the buffer queue is 10000 bytes and the maximum rate of the egress port is 100 Gbps.
And S102, generating a state table entry.
And the forwarding chip 3 generates a state table entry according to the acquired source chip identifier, destination chip identifier, receiving rate of the data stream, maximum rate of the output port, queue depth of the cache queue and current occupancy of the cache queue.
The internal forwarding information may include a source chip identifier and a destination chip identifier, and the queue state of the buffer queue may include an occupancy amount and a queue depth. It should be noted that the internal forwarding information may further include a port identifier, that is, may include a port identifier of an egress port and/or a port identifier of an ingress port.
The accuracy of speed limit can be further divided by port identification, because the data streams can be more accurately distinguished by four dimensions of source chip identification, destination chip identification, port identification of an ingress port and port identification of an egress port. The following description will be given only by taking the state table entry containing the source chip identifier and the destination chip identifier as an example.
The status table entry may be used to indicate the status of the currently received data flow on the line card board and the application status of the resource involved in forwarding the data flow.
S103, sending the state table entry to other line card boards in the network equipment so that the other line card boards can limit the speed of the data stream sent to the line card boards according to the state table entry.
After the forwarding chip generates the state table entry according to the data stream, the forwarding chip may send the state table entry to other line card boards in the network device, for example, the forwarding chip 3 may send the state table entry to the forwarding chip 1 and the forwarding chip 2.
When the forwarding chip 3 sends the status table entry to another line card board, the status table entry may be sent in a broadcast mode or a multicast mode.
If the broadcast is sent in a broadcast manner, a broadcast identifier needs to be set on the network device. When the forwarding chip 3 determines that the status table entry needs to be sent, in the internal message containing the status table entry, the destination chip identifier of the internal forwarding header is set as the broadcast identifier. Then, the internal message is sent to the network board, and the network board transmits the internal message to each line card board (i.e. other line card boards) except for the transmission status table entry in the network device, where the internal transmission header of the internal message is analyzed by the network board to carry the broadcast identifier.
If the multicast is sent by the multicast mode, the multicast identifier needs to be set on the network device, and the multicast group is set, and the line card board that needs to acquire the state table entry is added into the multicast group, which can also be understood as adding the chip identifier of the forwarding chip on the line card board into the multicast group. When the forwarding chip 3 determines that the state table entry needs to be sent, in the internal message containing the state table entry, the destination chip identifier of the internal forwarding header is set as the multicast identifier. Then, the internal packet is sent to the network board, and the network board forwards the internal packet to the line card board (i.e. other line card boards) included in the multicast group, where the internal forwarding header of the internal packet carries the multicast identifier.
And the forwarding chip 1 and the forwarding chip 2 store the state table entry sent by the forwarding chip 3 after receiving the state table entry. At this time, the forwarding chip 1 or the forwarding chip 2 may limit the data stream received by itself based on the information included in the status table entry.
Specifically, for a forwarding chip, the method further includes:
and S104, receiving and storing the state table items sent by other line card boards.
The queue state includes an occupation amount of a buffer queue corresponding to a data flow and a queue depth allocated to the buffer queue.
After the forwarding chip receives the status table entry, the status table entry may be stored in a storage space preset in the line card, such as a memory or a separately configured flash memory. The state table entries stored in the state table are shown in table 1 below, and it should be noted that in this embodiment, only one data stream of the line card board 1 and the line card board 2 is received by the line card board 3, as an example, and when the data stream is actually applied, relevant information of all data streams currently received and forwarded by the line card board 3 may be recorded in the table.
| Source chip identification | Destination chip identification | Receiving rate | Occupancy of buffer queue | Maximum rate | Queue depth |
| Forwarding chip 1 | Forwarding chip 3 | 60Gbps | 8000Byte | 100Gbps | 10000Byte |
| Forwarding chip 2 | Forwarding chip 3 | 70Gbps | 8000Byte | 100Gbps | 10000Byte |
TABLE 1
And S105, according to the queue depth ratio and the rate ratio corresponding to one data flow of the state table entry.
Taking the forwarding chip 1 as an example, after the table 1 is stored, a data stream received and forwarded by itself may be determined according to the source chip identifier and the destination chip identifier, that is, a data stream is marked by the internal forwarding information. Based on the state table entry corresponding to the data flow, the receiving and forwarding conditions of the data flow on the line card board 3 can be determined, that is, the queue depth ratio and the rate ratio are determined.
The queue depth ratio is the ratio of the occupied quantity to the queue depth, and the rate ratio is the ratio of the receiving rate to the maximum rate of the output port.
Based on table 1, the queue depth ratio of data flow 1 is 8000Byte/10000Byte 4/5, the rate ratio is 60Gbps/100Gbps 3/5, the queue depth ratio of data flow 2 is 8000Byte/10000Byte 4/5, and the rate ratio is 70Gbps/100Gbps 7/10.
And S106, if the rate ratio is smaller than the queue depth ratio, limiting the forwarding speed of the data stream according to the maximum rate and the receiving rate of the currently received data stream.
The forwarding chip 1 may compare the rate ratio of the data stream 1 with the queue depth ratio, and since the buffer queue may continuously perform reading and writing, when a packet is written into the buffer queue, the packet will be sent to the egress port to complete forwarding. When the occupied amount in the buffer queue increases, it indicates that the egress port cannot send out the data stream received by the line card board 3, that is, a congestion phenomenon occurs on the line card board 3, at this time, if the rate ratio is smaller than the queue depth ratio, it may indicate that other data streams, that is, data stream 2, are carried on the egress port in addition to data stream 1, and based on that the rate ratio 3/5 of data stream 1 determined in step S105 is smaller than the queue depth ratio 4/5, the sum of the two data streams exceeds the forwarding capability of the egress port.
Then, the line card board 1 and the line card board 2 can determine that the data stream sent to the line card board 3 by themselves needs to be limited in speed, so as to avoid the problem that the packet is lost in the cache queue due to the fact that the line card board 3 continues to accumulate the messages in the cache queue under the condition of congestion.
Specifically, the speed limit of the line card board may be based on the receiving rate of the multiple data streams and the maximum rate of the output port included in the status table entry. Taking the data stream 1 as an example for description, the line card board 1 determines that the receiving rates of the data stream 1 and the data stream 2 contained in the state table entry on the line card board 3 are 60Gbps and 70Gbps, and the maximum rates of the output ports corresponding to the two data streams are 100 Gbps. Then, the reception rates of the data stream 1 and the data stream 2, respectively, can be determined as the ratio of the sum of the two, i.e., 60/(60+70) and 70/(60+ 70). Thus, the ratio of data stream 1 is 6/13 and the ratio of data stream 2 is 7/13.
After determining the ratio between the data streams, the specific value of the speed limit can be determined by the maximum rate of the output port, i.e. data stream 1 will be limited to 100 × (6/13) 46Gbps and data stream 2 will be limited to 100 × (7/13) 53 Gbps. After the speed-limited rate is determined, the line card board 1 and the line card board 2 can limit the speed of the message forwarded by the line card board 1 and the line card board 2.
The specific speed limit may be implemented by adjusting the total amount of the token buckets, for example, adjusting the number of token buckets generated in one second to the speed limit rate, or may be implemented by other speed limit manners, which is not limited to this. Therefore, the wire clamping plate 1 and the wire clamping plate 2 can buffer the message exceeding the speed limiting rate part into the memory of the wire clamping plate 2, so that the occupied amount in the buffer queue on the wire clamping plate 3 is reduced, the exceeding part is ensured not to be concentrated on the wire clamping plate 3, and the problem of packet loss caused by continuous accumulation of congestion of a plurality of data streams on the wire clamping plate 3 is avoided.
In addition, after step S105, according to the queue depth ratio and the rate ratio corresponding to one data flow of the state table entry, the method further includes:
and S107, if the rate ratio is not less than the queue depth ratio, forwarding the data stream according to the current receiving rate.
If the line card board can determine that the rate ratio is greater than the queue depth ratio, it can be determined that the data stream has not accumulated on the line card board, so that the forwarding of the data stream can be continued at the current receiving rate.
It should be noted that, in the above embodiment, only by taking the case that the line card board 1 and the line card board 2 send the received data stream 1 and the data stream 2 to the outside through the output port of the line card board 3, in practical application, each line card board may perform the steps S100 to S107, that is, one line card board may be used as a line card board that sends data streams to the outside, generates the status table entry to send to other line card boards in the network device, and may also be used to receive data streams sent from the outside, and limits the speed of the data streams received by itself according to the status table entry sent from other line card boards.
Correspondingly, the present application provides a rate limiting apparatus, which is applied to a cable card board in a network device, as shown in fig. 3, and includes:
the analysis unit is used for receiving the data stream forwarded inside the network equipment, counting the receiving rate of the received data stream and acquiring the internal forwarding information of the data stream;
the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring the queue state of a buffer queue corresponding to a data stream and the maximum rate of a sending data outflow port;
the generating unit is used for generating a state table entry, wherein the state table entry comprises internal forwarding information, a queue state, a receiving rate and a maximum rate;
and the sending unit is used for sending the state table entry to other line card boards in the network equipment so that the other line card boards can limit the speed of the data stream sent to the line card boards according to the state table entry.
Optionally, the apparatus further includes:
the receiving unit is used for receiving and storing state table entries sent by other line card boards, wherein the queue state comprises the occupation amount of a cache queue corresponding to one data stream and the queue depth distributed for the cache queue;
a determining unit, configured to determine a queue depth ratio and a rate ratio according to a state table entry corresponding to a data flow of the state table entry, where the queue depth ratio is a ratio of an occupied amount to a queue depth, the rate ratio is a ratio of a receiving rate to a maximum rate of an egress port, and one data flow is marked by internal forwarding information;
and the speed limiting unit is used for limiting the forwarding of the data stream according to the maximum rate and the receiving rate of the currently received data stream if the rate ratio is not less than the queue depth ratio.
Further, the speed limiting unit is configured to forward the data stream according to the current receiving rate if the rate ratio is smaller than the queue depth ratio.
Optionally, the sending unit includes:
the broadcasting module is used for sending the state table entry to other line card boards in the network equipment in a broadcasting mode; alternatively, the first and second electrodes may be,
and the multicast module is used for sending the state table entry to other line card boards contained in the multicast group in a multicast mode.
Optionally, the internal forwarding information includes: a source chip identification, a destination chip identification, and an egress port identification.
In the embodiment of the present specification, the line card board obtains internal forwarding information related to a data stream, counts a receiving rate of a data stream and a queue depth and an occupied amount of a cache queue associated with the data stream according to the internal forwarding information, generates a state entry, and sends the state entry to other line card boards in the network device, so that the other line card boards determine a forwarding condition of the line card board sending the state entry according to a rate and a queue state included in the state entry, and manages a rate of the data stream sent to the line card by the other line card boards, thereby avoiding congestion and even packet loss of the data stream on one line card board, and improving reliability of forwarding the data stream by the network device.
It will be understood that the present description 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 above description is only for the purpose of illustrating the preferred embodiments of the present disclosure and is not to be construed as limiting the present disclosure, and any modifications, equivalents, improvements, etc. made within the spirit and principle of the present disclosure are intended to be included within the scope of the present disclosure.
Claims (10)
1. A forwarding speed limiting method is characterized in that the method is applied to a line card board in network equipment and comprises the following steps:
receiving a data stream forwarded inside network equipment, counting the receiving rate of the data stream, and acquiring the internal forwarding information of the data stream;
acquiring a queue state of a buffer queue corresponding to the data stream and sending the maximum rate of the data outflow port;
generating a state table entry, wherein the state table entry comprises internal forwarding information, the queue state, the receiving rate and the maximum rate;
and sending the state table entry to other line card boards in the network equipment so that the other line card boards carry out speed limitation on the data stream sent to the line card boards according to the state table entry.
2. The method of claim 1, further comprising:
receiving and storing state table entries sent by other line card boards, wherein the queue state comprises the occupation amount of a cache queue corresponding to a data stream and the queue depth distributed to the cache queue;
according to a queue depth ratio and a rate ratio corresponding to one data flow of the state table entry, wherein the queue depth ratio is the ratio of occupancy to queue depth, the rate ratio is the ratio of a receiving rate to a maximum rate of an output port, and the data flow is marked by the internal forwarding information;
and if the rate ratio is smaller than the queue depth ratio, limiting the forwarding speed of the data stream according to the maximum rate and the receiving rate of the currently received data stream.
3. The method of claim 2, further comprising, after determining a queue depth ratio and a rate ratio for a data flow based on the state table entry:
and if the rate ratio is not less than the queue depth ratio, forwarding the data stream according to the current receiving rate.
4. The method of claim 1, wherein the sending the status table entry to other cable cards in the network device comprises:
sending the state table entry to other line card boards in the network equipment in a broadcasting mode; alternatively, the first and second electrodes may be,
and sending the state table entry to other line card boards contained in the multicast group in a multicast mode.
5. The method of claim 1, wherein the status table entry comprises: a source chip identification, a destination chip identification and a port identification.
6. The utility model provides a forwardding speed-limiting device which characterized in that, is applied to the line cardboard in network equipment, includes:
the analysis unit is used for receiving the data stream forwarded inside the network equipment, counting the receiving rate of the received data stream and acquiring the internal forwarding information of the data stream;
an obtaining unit, configured to obtain a queue state of a buffer queue corresponding to the data stream and a maximum rate of sending the data egress port;
a generating unit, configured to generate a status table entry, where the status table entry includes internal forwarding information, the queue status, the receiving rate, and the maximum rate;
and the sending unit is used for sending the state table entry to other line card boards in the network equipment so that the other line card boards carry out speed limitation on the data stream sent to the line card boards according to the state table entry.
7. The apparatus of claim 6, further comprising:
the receiving unit is used for receiving and storing state table entries sent by other line card boards, wherein the queue state comprises the occupation amount of a buffer queue corresponding to one data stream and the queue depth distributed to the buffer queue;
a determining unit, configured to determine a queue depth ratio and a rate ratio according to a state table entry corresponding to one data flow of the state table entries, where the queue depth ratio is a ratio of an occupied amount to a queue depth, the rate ratio is a ratio of a receiving rate to a maximum rate of an egress port, and the one data flow is marked by the internal forwarding information;
and the speed limiting unit is used for limiting the forwarding of the data stream according to the maximum rate and the receiving rate of the currently received data stream if the rate ratio is smaller than the queue depth ratio.
8. The apparatus of claim 7, wherein the rate limiting unit is configured to forward the data stream according to a current receiving rate if the rate ratio is smaller than the queue depth ratio.
9. The apparatus of claim 6, wherein the sending unit comprises:
the broadcast module is used for sending the state table entry to other line card boards in the network equipment in a broadcast mode; alternatively, the first and second electrodes may be,
and the multicast module is used for sending the state table entry to other line card boards in the multicast group in a multicast mode.
10. The apparatus of claim 6, wherein the status table entry comprises: a source chip identification, a destination chip identification and a port identification.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110347628.9A CN113206794B (en) | 2021-03-31 | 2021-03-31 | Forwarding speed limiting method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110347628.9A CN113206794B (en) | 2021-03-31 | 2021-03-31 | Forwarding speed limiting method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113206794A true CN113206794A (en) | 2021-08-03 |
| CN113206794B CN113206794B (en) | 2022-05-27 |
Family
ID=77025954
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110347628.9A Active CN113206794B (en) | 2021-03-31 | 2021-03-31 | Forwarding speed limiting method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113206794B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113783789A (en) * | 2021-09-29 | 2021-12-10 | 新华三信息安全技术有限公司 | Message speed limiting method and device |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6170042B1 (en) * | 1998-02-24 | 2001-01-02 | Seagate Technology Llc | Disc drive data storage system and method for dynamically scheduling queued commands |
| US6192029B1 (en) * | 1998-01-29 | 2001-02-20 | Motorola, Inc. | Method and apparatus for performing flow control in a wireless communications system |
| CN1819577A (en) * | 2005-01-24 | 2006-08-16 | 阿尔卡特公司 | Communication traffic management systems and methods |
| US7599292B1 (en) * | 2002-08-05 | 2009-10-06 | Extreme Networks | Method and apparatus for providing quality of service across a switched backplane between egress and ingress queue managers |
| CN101984594A (en) * | 2010-10-25 | 2011-03-09 | 华为技术有限公司 | Switching network flow control method and device |
| CN101997772A (en) * | 2010-10-13 | 2011-03-30 | 福建星网锐捷网络有限公司 | Flow control method, device, system and network equipment |
| CN102611620A (en) * | 2012-02-23 | 2012-07-25 | 福建星网锐捷网络有限公司 | Congestion control method and message processing device |
| CN103546271A (en) * | 2013-10-28 | 2014-01-29 | 陕西高新实业有限公司 | Synchronous transmission system of resilient packet ring asynchronous network |
| CN107579921A (en) * | 2017-09-26 | 2018-01-12 | 锐捷网络股份有限公司 | Flow control methods and device |
| CN107979544A (en) * | 2016-10-25 | 2018-05-01 | 华为技术有限公司 | A kind of retransmission method of IP packet, equipment and system |
| CN108667739A (en) * | 2017-03-27 | 2018-10-16 | 华为技术有限公司 | Jamming control method, apparatus and system |
| CN110290072A (en) * | 2018-03-19 | 2019-09-27 | 华为技术有限公司 | Flow control methods, device, the network equipment and storage medium |
| CN111385223A (en) * | 2018-12-28 | 2020-07-07 | 阿里巴巴集团控股有限公司 | Flow control method, device, system and storage medium |
| US20200280518A1 (en) * | 2020-01-28 | 2020-09-03 | Intel Corporation | Congestion management techniques |
| CN111786890A (en) * | 2020-06-29 | 2020-10-16 | 新华三信息安全技术有限公司 | Multicast message sending method, related device and network equipment |
| CN112311685A (en) * | 2019-07-24 | 2021-02-02 | 华为技术有限公司 | Method and related device for processing network congestion |
-
2021
- 2021-03-31 CN CN202110347628.9A patent/CN113206794B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6192029B1 (en) * | 1998-01-29 | 2001-02-20 | Motorola, Inc. | Method and apparatus for performing flow control in a wireless communications system |
| US6170042B1 (en) * | 1998-02-24 | 2001-01-02 | Seagate Technology Llc | Disc drive data storage system and method for dynamically scheduling queued commands |
| US7599292B1 (en) * | 2002-08-05 | 2009-10-06 | Extreme Networks | Method and apparatus for providing quality of service across a switched backplane between egress and ingress queue managers |
| CN1819577A (en) * | 2005-01-24 | 2006-08-16 | 阿尔卡特公司 | Communication traffic management systems and methods |
| CN101997772A (en) * | 2010-10-13 | 2011-03-30 | 福建星网锐捷网络有限公司 | Flow control method, device, system and network equipment |
| CN101984594A (en) * | 2010-10-25 | 2011-03-09 | 华为技术有限公司 | Switching network flow control method and device |
| CN102611620A (en) * | 2012-02-23 | 2012-07-25 | 福建星网锐捷网络有限公司 | Congestion control method and message processing device |
| CN103546271A (en) * | 2013-10-28 | 2014-01-29 | 陕西高新实业有限公司 | Synchronous transmission system of resilient packet ring asynchronous network |
| CN107979544A (en) * | 2016-10-25 | 2018-05-01 | 华为技术有限公司 | A kind of retransmission method of IP packet, equipment and system |
| CN108667739A (en) * | 2017-03-27 | 2018-10-16 | 华为技术有限公司 | Jamming control method, apparatus and system |
| CN107579921A (en) * | 2017-09-26 | 2018-01-12 | 锐捷网络股份有限公司 | Flow control methods and device |
| CN110290072A (en) * | 2018-03-19 | 2019-09-27 | 华为技术有限公司 | Flow control methods, device, the network equipment and storage medium |
| CN111385223A (en) * | 2018-12-28 | 2020-07-07 | 阿里巴巴集团控股有限公司 | Flow control method, device, system and storage medium |
| CN112311685A (en) * | 2019-07-24 | 2021-02-02 | 华为技术有限公司 | Method and related device for processing network congestion |
| US20200280518A1 (en) * | 2020-01-28 | 2020-09-03 | Intel Corporation | Congestion management techniques |
| CN111786890A (en) * | 2020-06-29 | 2020-10-16 | 新华三信息安全技术有限公司 | Multicast message sending method, related device and network equipment |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113783789A (en) * | 2021-09-29 | 2021-12-10 | 新华三信息安全技术有限公司 | Message speed limiting method and device |
| CN113783789B (en) * | 2021-09-29 | 2023-03-31 | 新华三信息安全技术有限公司 | Message speed limiting method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113206794B (en) | 2022-05-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8139576B2 (en) | Network routing apparatus | |
| US8699490B2 (en) | Data transmission method, network node, and data transmission system | |
| JP4046704B2 (en) | Packet transmission apparatus and method for communication system | |
| US6643292B2 (en) | Efficient packet data transport mechanism and an interface therefor | |
| US20080196033A1 (en) | Method and device for processing network data | |
| US7583735B2 (en) | Methods and systems for handling underflow and overflow in a software defined radio | |
| CN108777646B (en) | Flow monitoring method and device | |
| CN100553199C (en) | Method of realizing group broadcasting, system and equipment based on the PCIE switching network | |
| US8553708B2 (en) | Bandwith allocation method and routing device | |
| US6636510B1 (en) | Multicast methodology and apparatus for backpressure-based switching fabric | |
| US20030223442A1 (en) | Buffer memory reservation | |
| CN107770085B (en) | Network load balancing method, equipment and system | |
| CN103475542A (en) | Network equipment handling capacity performance testing system and method | |
| CN113225196B (en) | Service level configuration method and device | |
| CN110138610A (en) | A kind of sending method and device of service message | |
| EP3188419B1 (en) | Packet storing and forwarding method and circuit, and device | |
| CN112383450A (en) | Network congestion detection method and device | |
| CN113206794B (en) | Forwarding speed limiting method and device | |
| CN113162855B (en) | Multicast message detection method, network equipment and system | |
| US20150195039A1 (en) | System and method for interchanging data in a hybrid ethernet-based passive optical network | |
| US20030072268A1 (en) | Ring network system | |
| US20220086107A1 (en) | Data traffic control device, a residential router, an operator network device and a telecommunication system | |
| US7855967B1 (en) | Method and apparatus for providing line rate netflow statistics gathering | |
| CN110336759B (en) | RDMA (remote direct memory Access) -based protocol message forwarding method and device | |
| CN113037651B (en) | Method, device, equipment and storage medium for improving QoS (quality of service) of traffic forwarding |
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 |