CN107493245B - Board card of switch and data stream forwarding method - Google Patents
Board card of switch and data stream forwarding method Download PDFInfo
- Publication number
- CN107493245B CN107493245B CN201710867288.6A CN201710867288A CN107493245B CN 107493245 B CN107493245 B CN 107493245B CN 201710867288 A CN201710867288 A CN 201710867288A CN 107493245 B CN107493245 B CN 107493245B
- Authority
- CN
- China
- Prior art keywords
- data stream
- mac address
- chip
- switch
- destination
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L49/00—Packet switching elements
- H04L49/15—Interconnection of switching modules
-
- 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
- H04L45/74—Address processing for routing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L49/00—Packet switching elements
- H04L49/25—Routing or path finding in a switch fabric
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L61/00—Network arrangements, protocols or services for addressing or naming
- H04L61/09—Mapping addresses
- H04L61/10—Mapping addresses of different types
- H04L61/103—Mapping addresses of different types across network layers, e.g. resolution of network layer into physical layer addresses or address resolution protocol [ARP]
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a board card of a switch and a data stream forwarding method, wherein the board card comprises a first switching chip and a second switching chip, the first switching chip is connected with an optical fiber port of the board card and an inter-board-card inline port, the first switching chip and the second switching chip are connected through the inter-board-card inline port, the bandwidth of the first switching chip exceeds a set threshold, and the capacity of the second switching chip exceeds the set threshold. In the scheme, because the bandwidth of the first exchange chip exceeds the first set threshold and the capacity of the second exchange chip exceeds the second set threshold, the exchange board with high capacity and high bandwidth can be realized at relatively low cost, and the exchange capacity of the board is greatly improved by adopting a design of forwarding and separating two layers and three layers.
Description
Technical Field
The present invention relates to the field of communications technologies, and in particular, to a board card of a switch and a data stream forwarding method.
Background
The switch is a network device frequently used in a current network architecture, a board refers to a board on the switch for data forwarding, a switching chip on the board stores a Media Access Control (MAC) Address table and an Address Resolution Protocol (ARP) forwarding table that determine a forwarding outlet of a data stream, and a forwarding performance of the switching chip also determines a bandwidth of the switching board.
The switching capacity refers to the total number of users that can be supported on the board card, that is, the number of the MAC addresses and ARP entries of the users that can be stored, and is mainly limited by the hardware capacity of the switching chip along with the high-speed development of a Central Processing Unit (CPU) and a memory; the switching bandwidth is the maximum throughput data volume between cards.
The current switching chip derives two typical series according to different use scenes and trade-off between switching capacity and switching bandwidth: a high-capacity and bandwidth-general switching chip (referred to as a high-capacity switching chip for short) and a high-bandwidth and capacity-general switching chip (referred to as a high-bandwidth switching chip for short), which results in that the current board card cannot meet the requirements of high capacity and high bandwidth at the same time; the switch chip which can meet the requirements of high capacity and high bandwidth is expensive. Therefore, there is a need for a card that is inexpensive and meets both large capacity and high bandwidth requirements.
Disclosure of Invention
The embodiment of the invention provides a board card of a switch and a data stream forwarding method, which are used for providing a board card which is low in price and can meet the requirements of high capacity and high bandwidth.
According to an embodiment of the present invention, a board card of a switch is provided, including a first switch chip and a second switch chip, where the first switch chip is connected to an optical fiber port of the board card and an inter-board interconnection port, the first switch chip and the second switch chip are connected through the inter-board interconnection port, a bandwidth of the first switch chip exceeds a first set threshold, and a capacity of the second switch chip exceeds a second set threshold, where:
the first switching chip is configured to determine whether to send a data stream to the second switching chip according to a destination Media Access Control (MAC) address of the data stream after receiving the data stream, and forward the data stream according to the destination MAC address of the data stream and an MAC address table if it is determined that the data stream is not sent to the second switching chip; if the data stream is determined to be sent to the second switching chip, sending the data stream to the second switching chip;
and the second switching chip is used for forwarding the data stream according to an Address Resolution Protocol (ARP) forwarding table, a destination Internet Protocol (IP) address of the data stream and a destination MAC address after receiving the data stream sent by the first switching chip.
Specifically, the first switching chip is specifically configured to:
determining whether a destination MAC address of the data flow is a MAC address of the switch;
if the destination MAC address of the data flow is the MAC address of the switch, forwarding the data flow to the second switching chip;
if the destination MAC address of the data flow is not the MAC address of the switch, searching the outlet of the data flow from an MAC address list according to the destination MAC address of the data flow, and forwarding the data flow through the outlet of the data flow.
Specifically, the second switch chip is specifically configured to:
receiving the data stream sent by the first switching chip;
acquiring a destination IP address and a destination MAC address of the data stream;
searching an outlet of the data flow from an ARP forwarding table according to the destination IP address and the destination MAC address of the data flow;
forwarding the data flow through an egress of the data flow.
Optionally, the first switch chip is further configured to update the MAC address table according to the learned MAC address;
and the second switching chip is also used for updating the ARP forwarding table according to the learned ARP table entry.
Specifically, if the number of the second switch chips is greater than one, the first switch chip and the board card inline port between the second switch chips form an aggregation port, and the first switch chip is specifically configured to:
and if the data stream is determined to be forwarded to the second switching chip, sending the data stream to one second switching chip according to a flow balance principle.
According to an embodiment of the present invention, there is also provided a data stream forwarding method applied to a first switch chip of a board card of the switch, where the method includes:
receiving a data stream;
determining whether to send the data stream to the second switching chip according to the destination Media Access Control (MAC) address of the data stream;
if the data stream is determined not to be sent to the second exchange chip, forwarding the data stream according to a destination MAC address and an MAC address table of the data stream;
and if the data stream is determined to be sent to the second switching chip, sending the data stream to the second switching chip, so that the second switching chip forwards the data stream according to an Address Resolution Protocol (ARP) forwarding table, a destination Internet Protocol (IP) address of the data stream and a destination MAC address after receiving the data stream sent by the first switching chip.
Specifically, determining whether to send the data stream to the second switch chip according to the destination MAC address of the data stream includes:
determining whether a destination MAC address of the data flow is a MAC address of the switch;
if the destination MAC address of the data flow is determined to be the MAC address of the switch, determining to forward the data flow to the second switching chip;
if the destination MAC address of the data stream is determined not to be the MAC address of the switch, determining not to send the data stream to the second switch chip;
forwarding the data stream according to the destination MAC address and the MAC address table of the data stream, specifically including:
searching an outlet of the data flow from an MAC address list according to the destination MAC address of the data flow;
forwarding the data flow through an egress of the data flow.
Optionally, the method further includes:
and updating the MAC address table according to the learned MAC address.
Specifically, if the number of the second switch chips is greater than one, the board card inline ports between the first switch chip and the second switch chip form an aggregation port, and the data stream is sent to the second switch chip, which specifically includes:
and sending the data stream to one second switching chip according to a flow balance principle.
According to an embodiment of the present invention, there is further provided a data stream forwarding method applied to a second switch chip of the board card of the switch, where the method includes:
receiving a data stream sent by the first switching chip, wherein the data stream is sent after the first switching chip receives the data stream and the data stream is determined to be sent to the second switching chip according to a destination Media Access Control (MAC) address of the data stream;
and forwarding the data stream according to an Address Resolution Protocol (ARP) forwarding table, a destination Internet Protocol (IP) address and a destination MAC address of the data stream.
Specifically, forwarding the data stream according to an ARP forwarding table, a destination IP address of the data stream, and a destination MAC address includes:
acquiring a destination IP address and a destination MAC address of the data stream;
searching an outlet of the data flow from an ARP forwarding table according to the destination IP address and the destination MAC address of the data flow;
forwarding the data flow through an egress of the data flow.
Optionally, the method further includes:
and updating the ARP forwarding table according to the learned ARP table entry.
The invention has the following beneficial effects:
the embodiment of the invention provides a board card of a switch and a data stream forwarding method, wherein the board card comprises a first switching chip and a second switching chip, the first switching chip is connected with an optical fiber port of the board card and an inter-board-card inline port, the first switching chip and the second switching chip are connected through the inter-board-card inline port, the bandwidth of the first switching chip exceeds a set threshold, the capacity of the second switching chip exceeds the set threshold, and the method comprises the following steps: the first switching chip is configured to determine whether to send a data stream to the second switching chip according to a destination Media Access Control (MAC) address of the data stream after receiving the data stream, and forward the data stream according to the destination MAC address of the data stream and an MAC address table if it is determined that the data stream is not sent to the second switching chip; if the data stream is determined to be sent to the second switching chip, sending the data stream to the second switching chip; and the second switching chip is used for forwarding the data stream according to an Address Resolution Protocol (ARP) forwarding table, a destination Internet Protocol (IP) address of the data stream and a destination MAC address after receiving the data stream sent by the first switching chip. In the scheme, because the bandwidth of the first exchange chip exceeds the first set threshold and the capacity of the second exchange chip exceeds the second set threshold, the exchange board with high capacity and high bandwidth can be realized at relatively low cost, and the exchange capacity of the board is greatly improved by adopting a design of forwarding and separating two layers and three layers.
Drawings
Fig. 1 is a schematic structural diagram of a board card of a switch in an embodiment of the present invention;
fig. 2 is a flowchart of a forwarding method of a data stream applied in a first switch chip according to an embodiment of the present invention;
fig. 3 is a flowchart of a forwarding method of a data stream applied in a second switch chip according to an embodiment of the present invention;
fig. 4 is a schematic diagram of an application scenario in the embodiment of the present invention.
Detailed Description
In order to provide a board card which is cheap and meets requirements of large capacity and high bandwidth at the same time, an embodiment of the present invention provides a board card of a switch, where the structure of the board card is shown in fig. 1, and the board card includes a first switch chip 11 and a second switch chip 12, the first switch chip connects an optical fiber port of the board card and an inter-board inline port, the first switch chip and the second switch chip are connected through the inter-board inline port, a bandwidth of the first switch chip exceeds a first set threshold, and a capacity of the second switch chip exceeds a second set threshold. Wherein:
the first switching chip is used for determining whether to send the data stream to the second switching chip according to the destination MAC address of the data stream after receiving the data stream, and forwarding the data stream according to the destination MAC address of the data stream and the MAC address table if determining not to send the data stream to the second switching chip; and if the data stream is determined to be sent to the second switching chip, sending the data stream to the second switching chip.
And the second switching chip is used for forwarding the data stream according to an Address Resolution Protocol (ARP) forwarding table, a destination Internet Protocol (IP) address of the data stream and a destination MAC address after receiving the data stream sent by the first switching chip.
The number of the second switching chips may be at least one, and the case of two is shown in fig. 1; the first set threshold and the second set threshold may be set according to actual needs, for example, the first set threshold may be set to 300G, and the second set threshold may be set to 1000. The inter-board interconnection port can be not limited to a cross-network HG port, and the inter-board interconnection port can be not limited to a bypass HG port.
And for the data flow of the second layer, the MAC address table is directly searched on the first exchange chip for forwarding, and for the data flow of the third layer, the data flow is forcibly guided to the second exchange chip for searching the ARP forwarding table for three-layer forwarding, so that the two-layer and three-layer separated forwarding is realized.
In the scheme, because the bandwidth of the first exchange chip exceeds the first set threshold and the capacity of the second exchange chip exceeds the second set threshold, the exchange board with high capacity and high bandwidth can be realized at relatively low cost, and the exchange capacity of the board is greatly improved by adopting a design of forwarding and separating two layers and three layers.
Specifically, the first switch chip 11 is specifically configured to:
determining whether a destination MAC address of the data flow is a MAC address of the switch;
if the destination MAC address of the data flow is the MAC address of the switch, forwarding the data flow to a second switching chip;
if the destination MAC address of the data flow is not the MAC address of the switch, searching the outlet of the data flow from the MAC address list according to the destination MAC address of the data flow, and forwarding the data flow through the outlet of the data flow.
Specifically, the second switch chip 12 is specifically configured to:
receiving a data stream sent by a first switching chip;
acquiring a destination IP address and a destination MAC address of a data stream;
searching an outlet of the data stream from an ARP forwarding table according to a destination IP address and a destination MAC address of the data stream;
the data flow is forwarded through its egress.
Optionally, the first switch chip 11 is further configured to update the MAC address table according to the learned MAC address;
the second switch chip 12 is further configured to update the ARP forwarding table according to the learned ARP entry.
Specifically, if the number of the second switching chips is greater than one, the board card inline port between the first switching chip and the second switching chip forms an aggregation port, and the first switching chip 11 is specifically configured to:
and if the data stream is determined to be forwarded to the second switching chip, the data stream is sent to one second switching chip according to the flow balance principle.
In terms of bandwidth, for the first switch chip, all the bypass HG ports form an aggregation port, the flow is balanced to the plurality of second switch chips, and meanwhile, the second switch chips only make forwarding decisions and do not participate in path selection, so that the cross-board HG ports do not need to be led out, and all the bandwidth is distributed to the bypass HG ports, so that the overall bandwidth is improved. Assuming that the total bandwidth of the first switch chip is 300G, and the total bandwidth of the second switch chip is 50G, according to the existing board card architecture, the bandwidth of one switch chip is equally divided into two parts (a fiber port and a HG port across a board card), the bandwidth of the fiber port of the first switch chip can reach 150G, and the bandwidth of the fiber port of the second switch chip can only reach 25G. According to the board card architecture, the bandwidth is averagely distributed to the three parts of the optical fiber port, the bypass HG port and the cross-board HG port, the bandwidth of the optical fiber port can reach 1/3 (namely 100G) of the bandwidth of the first switching chip, and the bandwidth of the board card is improved by 3 times on the basis of the bandwidth of the second switching chip and is reduced by 33% on the basis of the first switching chip.
From the capacity, because the MAC address table on the board card and the table entry resources of the ARP forwarding table are shared, the MAC address table can be freely allocated to a plurality of points of the table entries of the MAC address table or a plurality of points of the table entries of the ARP forwarding table, wherein the resources occupied by one MAC table entry are about 1/2 of the resources occupied by one ARP table entry. In the existing architecture, it is assumed that the capacity of the first switch chip is 1/2 of the second switch chip, the table entry resources of the first switching chip are all allocated to the MAC address table for use, the table entry resources of the second switching chip are all allocated to the ARP forwarding for use, thus, the capacity of the MAC address table and the ARP forwarding table are consistent, and the whole capacity of the board card is improved by 50% compared with that of a single second switching chip (when the second switching chip is used independently, the table entry resource of the MAC address table is 1/3, the table entry resource of the ARP forwarding table is 2/3 (assumed to be 1000), after all the table entries are used by the ARP forwarding table (which can reach 1500), therefore, the capacity of the first switching chip is increased by 50% and is increased by 2 times compared with the capacity of a single first switching chip (assuming that the original capacity is 500 entries of the MAC address table and 500 entries of the ARP forwarding table, 1500 entries can be installed after all the entries of the MAC address table are installed).
Based on the same inventive concept, an embodiment of the present invention provides a method for forwarding a data stream, which is applied to a first switch chip of a board card of the switch, and a flow of the method is shown in fig. 2, and the method includes the following steps:
s21: a data stream is received.
The data stream is received from a fiber port.
S22: determining whether to transmit the data stream to the second switch chip according to the destination MAC address of the data stream, and if it is determined that the data stream is not transmitted to the second switch chip, performing S23; if it is determined to transmit the data stream to the second switch chip, S24 is performed.
The step determines whether the data flow needs to be forwarded by the second layer or the third layer.
S23: and forwarding the data flow according to the destination MAC address and the MAC address table of the data flow.
And determining that the data stream is not sent to the second switching chip and the data stream needs to be subjected to two-layer forwarding.
S24: and sending the data stream to a second switching chip so that the second switching chip forwards the data stream according to the ARP forwarding table, the destination IP address and the destination MAC address of the data stream after receiving the data stream sent by the first switching chip.
And sending the data stream to a second exchange chip, thereby realizing three-layer forwarding of the data stream.
In the scheme, because the bandwidth of the first exchange chip exceeds the first set threshold and the capacity of the second exchange chip exceeds the second set threshold, the exchange board with high capacity and high bandwidth can be realized at relatively low cost, and the exchange capacity of the board is greatly improved by adopting a design of forwarding and separating two layers and three layers.
Specifically, the implementation process of determining whether to send the data stream to the second switch chip according to the destination MAC address of the data stream in S22 specifically includes: determining whether a destination MAC address of the data flow is a MAC address of the switch; if the destination MAC address of the data flow is determined to be the MAC address of the switch, determining to forward the data flow to the second switching chip; and if the destination MAC address of the data flow is not determined to be the MAC address of the switch, determining not to send the data flow to the second switch chip.
If the destination MAC address of the data stream is the MAC address of the switch, the data stream is continuously forwarded, namely the data stream is handed to a second switch chip for forwarding; and if the destination MAC address of the data flow is not the MAC address of the switch, the data flow does not need to be forwarded continuously and is not forwarded to the second switching chip for forwarding.
Correspondingly, the implementation process of forwarding the data stream according to the destination MAC address and the MAC address table of the data stream in S23 specifically includes: searching an outlet of the data flow from the MAC address list according to the destination MAC address of the data flow; the data flow is forwarded through its egress.
The egress of the data flow may be determined from the MAC address table and then forwarded through the egress.
Optionally, the method further includes: and updating the MAC address table according to the learned MAC address. Thereby ensuring that the data stream can be accurately forwarded.
Specifically, if the number of the second switch chip is greater than one, the inline ports of the board card between the first switch chip and the second switch chip form an aggregation port, and the data stream is sent to the second switch chip, which specifically includes: and sending the data stream to a second switching chip according to the flow balance principle.
According to an embodiment of the present invention, there is further provided a data stream forwarding method applied to the second switch chip of the board card of the switch, where a flow of the method is shown in fig. 3, and the method includes the following steps:
s31: and receiving the data stream sent by the first switching chip, wherein the data stream is sent after the first switching chip receives the data stream and the data stream is sent to the second switching chip according to the destination MAC address of the data stream.
S32: and forwarding the data stream according to the ARP forwarding table, the destination IP address and the destination MAC address of the data stream.
In the scheme, because the bandwidth of the first exchange chip exceeds the first set threshold and the capacity of the second exchange chip exceeds the second set threshold, the exchange board with high capacity and high bandwidth can be realized at relatively low cost, and the exchange capacity of the board is greatly improved by adopting a design of forwarding and separating two layers and three layers.
Specifically, the implementation process of forwarding the data stream according to the ARP forwarding table, the destination IP address of the data stream, and the destination MAC address in S32 specifically includes: acquiring a destination IP address and a destination MAC address of a data stream; searching an outlet of the data stream from an ARP forwarding table according to a destination IP address and a destination MAC address of the data stream; the data flow is forwarded through its egress.
Optionally, the method further includes: and updating the ARP forwarding table according to the learned ARP table entry.
A specific example is described below, which is applied to the network architecture shown in fig. 4, and the data stream forwarding in the board 1 is taken as an example for description:
the MAC address table in the first switching chip 11 is shown in table 1:
| serial number | Destination MAC address | VLAN | An |
| 1 | MAC A | 1 | |
| 2 | |
1 | |
| 3 | |
2 | |
| 4 | |
1 | |
| 5 | |
2 | |
| 6 | |
1 | |
| 7 | |
2 | |
TABLE 1
Entry of ARP forwarding table in the second switching chip 2:
TABLE 2
The ARP table items of the opposite side can be learned among the PCs in the same network segment, so that direct two-layer communication can be realized (the destination MAC address of the sent message is directly the MAC address of the opposite side during access); the ARP table entry of the opposite side cannot be learned among the PCs in different network segments, and three-layer communication needs to be carried out through the gateway (namely, the destination MAC of the message sent during access is the MAC address of the switch).
(1) In the data flow from the PC a to the PC B, the destination MAC address is the MAC address of the PC B, and the entry of the 2 nd MAC address table is directly hit in the first switch chip 1 of the board card 1 and forwarded to the PORT 1/2 through the two layers in the board.
(2) In the data flow from the PC A to the PC C, the destination MAC address is SW, the destination IP address is 192.168.2.2, the 6 th MAC table entry is hit in the first exchange spare piece of the board card 1, and the data flow is forwarded to the chip 2 through the bypass HG; then hit the 3 rd ARP list item in the chip 2, and forward to PORT 1/3 through three layers in the board (the source MAC address is modified to SW, the destination MAC address is modified to C, VLAN is modified to 2).
(3) And (3) data flow from the PC A to the PC D, wherein the target MAC address is the PC D, the 4 th MAC table entry is directly hit in the first exchange chip 1 of the board card 1, and the data flow is forwarded to the PORT 2/1 through a cross-board two-layer.
(4) In the data flow from the PC A to the PC E, the destination MAC address is SW, the destination IP address is 192.168.2.3, the 6 th MAC table entry is hit in the first switching chip of the board card 1, and the data flow is forwarded to the second switching chip through the bypass HG; then hit the 5 th ARP list item in the second exchange chip, and forward to PORT 2/2 through three layers in the board (source MAC is modified to SW, destination MAC is modified to E, VLAN is modified to 2).
The following software implementation procedures are introduced in the above architecture:
firstly, during gateway configuration, sending MAC table entries for drainage of a VLAN corresponding to the gateway to a first switching chip 1, and forwarding a data stream of which a target MAC address is an MAC address of the switch to a second switching chip, namely the 6 th table entry and the 7 th table entry; and meanwhile, sending the ARP table entry of the CPU to the second switching chip by the gateway corresponding to the VLAN for sending the message of which the destination IP address is the IP address of the gateway to the CPU, so that other terminals can communicate with the gateway.
Secondly, for MAC address learning, for the local board, the MAC address learning is only performed on the first switching chip, and the address learning function is closed on the bypass HG port. If other board cards learn that the new MAC address is synchronized to the board card, the MAC address is only added to the first switching chip and is not added to the second switching chip.
And thirdly, for ARP table item learning, the second switching chip does not directly learn, the engine needs to learn and then send the ARP table items to each board card, and the ARP table items are only added to the second switching chip and not added to the first switching chip when being sent to the board cards.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While alternative embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following appended claims be interpreted as including alternative embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various modifications and variations can be made in the embodiments of the present invention without departing from the spirit or scope of the embodiments of the invention. Thus, if such modifications and variations of the embodiments of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to encompass such modifications and variations.
Claims (12)
1. The utility model provides a board card of switch, its characterized in that includes first exchange chip and second exchange chip, first exchange chip is connected the inline port between the optic fibre port of board card and the board card, connect through the inline port in the board card between first exchange chip and the second exchange chip, the bandwidth of first exchange chip exceeds first threshold value of setting for, the capacity of second exchange chip exceeds the second threshold value of setting for, wherein:
the first switching chip is used for determining whether to send the data stream to the second switching chip according to a destination Media Access Control (MAC) address of the data stream after receiving the data stream, and determining whether the destination MAC address of the data stream is the MAC address of the switch; if the destination MAC address of the data flow is the MAC address of the switch, forwarding the data flow to the second switching chip; if the data stream is determined not to be sent to the second exchange chip, forwarding the data stream according to a destination MAC address and an MAC address table of the data stream; if the data stream is determined to be sent to the second switching chip, sending the data stream to the second switching chip;
and the second switching chip is used for forwarding the data stream according to an Address Resolution Protocol (ARP) forwarding table, a destination Internet Protocol (IP) address of the data stream and a destination MAC address after receiving the data stream sent by the first switching chip.
2. The board card of claim 1, wherein the first switch chip is specifically configured to:
if the destination MAC address of the data flow is not the MAC address of the switch, searching the outlet of the data flow from an MAC address list according to the destination MAC address of the data flow, and forwarding the data flow through the outlet of the data flow.
3. The board card of claim 1, wherein the second switch chip is specifically configured to:
receiving the data stream sent by the first switching chip;
acquiring a destination IP address and a destination MAC address of the data stream;
searching an outlet of the data flow from an ARP forwarding table according to the destination IP address and the destination MAC address of the data flow;
forwarding the data flow through an egress of the data flow.
4. The board card of claim 1, wherein the first switch chip is further configured to update the MAC address table according to the learned MAC address;
and the second switching chip is also used for updating the ARP forwarding table according to the learned ARP table entry.
5. The board card according to any one of claims 1 to 4, wherein if the number of the second switch chips is greater than one, an inline port of the board card between the first switch chip and the second switch chip forms an aggregation port, and the first switch chip is specifically configured to:
and if the data stream is determined to be forwarded to the second switching chip, sending the data stream to one second switching chip according to a flow balance principle.
6. A data stream forwarding method applied in a first switching chip of a board of a switch according to any of claims 1 to 5, the method comprising:
receiving a data stream;
determining whether to send the data stream to the second switching chip according to the destination Media Access Control (MAC) address of the data stream;
if the data stream is determined not to be sent to the second exchange chip, forwarding the data stream according to a destination MAC address and an MAC address table of the data stream;
if the data stream is determined to be sent to the second switching chip, the data stream is sent to the second switching chip, so that the second switching chip forwards the data stream according to an Address Resolution Protocol (ARP) forwarding table, a destination Internet Protocol (IP) address of the data stream and a destination MAC address after receiving the data stream sent by the first switching chip; wherein the content of the first and second substances,
determining whether to send the data stream to the second switch chip according to the destination MAC address of the data stream, which specifically includes:
determining whether a destination MAC address of the data flow is a MAC address of the switch;
and if the destination MAC address of the data flow is determined to be the MAC address of the switch, determining to forward the data flow to the second switching chip.
7. The method of claim 6, wherein determining whether to send the data flow to the second switch chip according to the destination MAC address of the data flow specifically comprises:
if the destination MAC address of the data stream is determined not to be the MAC address of the switch, determining not to send the data stream to the second switch chip;
forwarding the data stream according to the destination MAC address and the MAC address table of the data stream, specifically including:
searching an outlet of the data flow from an MAC address list according to the destination MAC address of the data flow;
forwarding the data flow through an egress of the data flow.
8. The method of claim 6, further comprising:
and updating the MAC address table according to the learned MAC address.
9. The method according to any one of claims 6 to 8, wherein if the number of the second switch chips is greater than one, an aggregation port is formed by an inline port of the board card between the first switch chip and the second switch chip, and the sending of the data stream to the second switch chip specifically includes:
and sending the data stream to one second switching chip according to a flow balance principle.
10. A data stream forwarding method applied in a second switching chip of a board of a switch according to any of claims 1 to 5, the method comprising:
receiving a data stream sent by the first switching chip, wherein the data stream is sent after the first switching chip receives the data stream and the data stream is determined to be sent to the second switching chip according to a destination Media Access Control (MAC) address of the data stream;
and forwarding the data stream according to an Address Resolution Protocol (ARP) forwarding table, a destination Internet Protocol (IP) address and a destination MAC address of the data stream.
11. The method of claim 10, wherein forwarding the data flow according to an ARP forwarding table, a destination IP address and a destination MAC address of the data flow, specifically comprises:
acquiring a destination Internet Protocol (IP) address and a destination Media Access Control (MAC) address of the data stream;
searching an outlet of the data flow from an ARP forwarding table according to the destination IP address and the destination MAC address of the data flow;
forwarding the data flow through an egress of the data flow.
12. The method of claim 10 or 11, further comprising:
and updating the ARP forwarding table according to the learned ARP table entry.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710867288.6A CN107493245B (en) | 2017-09-22 | 2017-09-22 | Board card of switch and data stream forwarding method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710867288.6A CN107493245B (en) | 2017-09-22 | 2017-09-22 | Board card of switch and data stream forwarding method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107493245A CN107493245A (en) | 2017-12-19 |
| CN107493245B true CN107493245B (en) | 2020-04-24 |
Family
ID=60652859
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710867288.6A Active CN107493245B (en) | 2017-09-22 | 2017-09-22 | Board card of switch and data stream forwarding method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107493245B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110324265B (en) * | 2018-03-29 | 2021-09-07 | 阿里巴巴集团控股有限公司 | Traffic distribution method, routing method, equipment and network system |
| CN115766334A (en) * | 2022-12-20 | 2023-03-07 | 瑞斯康达科技发展股份有限公司 | Three-layer switch, network system and data transmission method |
| CN116684506B (en) * | 2023-08-02 | 2023-11-07 | 浪潮电子信息产业股份有限公司 | Data processing method, system, electronic device and computer readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101110721A (en) * | 2006-07-18 | 2008-01-23 | 中兴通讯股份有限公司 | Method for accessing into control address table spacing using Ethernet switch medium |
| CN101399779A (en) * | 2008-10-30 | 2009-04-01 | 北京星网锐捷网络技术有限公司 | Multi-chip switch and method for extending medium access control address table |
| CN101895471A (en) * | 2010-07-15 | 2010-11-24 | 中兴通讯股份有限公司 | Network equipment and data processing method for same |
| US9124495B2 (en) * | 2013-03-11 | 2015-09-01 | Dell Products L.P. | System and method for automatic provisioning of stacked switches |
| CN106506408A (en) * | 2016-11-18 | 2017-03-15 | 济南浪潮高新科技投资发展有限公司 | A kind of implementation method of 96+6 interface switchboards |
-
2017
- 2017-09-22 CN CN201710867288.6A patent/CN107493245B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101110721A (en) * | 2006-07-18 | 2008-01-23 | 中兴通讯股份有限公司 | Method for accessing into control address table spacing using Ethernet switch medium |
| CN101399779A (en) * | 2008-10-30 | 2009-04-01 | 北京星网锐捷网络技术有限公司 | Multi-chip switch and method for extending medium access control address table |
| CN101895471A (en) * | 2010-07-15 | 2010-11-24 | 中兴通讯股份有限公司 | Network equipment and data processing method for same |
| US9124495B2 (en) * | 2013-03-11 | 2015-09-01 | Dell Products L.P. | System and method for automatic provisioning of stacked switches |
| CN106506408A (en) * | 2016-11-18 | 2017-03-15 | 济南浪潮高新科技投资发展有限公司 | A kind of implementation method of 96+6 interface switchboards |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107493245A (en) | 2017-12-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10728176B2 (en) | Ruled-based network traffic interception and distribution scheme | |
| US10374952B2 (en) | Method for increasing layer-3 longest prefix match scale | |
| CN107819663B (en) | Method and device for realizing virtual network function service chain | |
| US10333845B2 (en) | Forwarding data packets | |
| US10404621B2 (en) | Scalable InfiniBand packet-routing technique | |
| US9215172B2 (en) | Hashing-based routing table management | |
| US8619796B2 (en) | Forwarding data frames with a distributed fiber channel forwarder | |
| US11233737B2 (en) | Stateless distributed load-balancing | |
| CN106878194B (en) | Message processing method and device | |
| CN107493245B (en) | Board card of switch and data stream forwarding method | |
| CN103477593A (en) | Network system, switch, and connection terminal detection method | |
| US20160308772A1 (en) | Systems and methods for load balancing in a data center | |
| JP6618610B2 (en) | Routing management | |
| US9397952B2 (en) | Segment based switching architecture with hybrid control in SDN | |
| CN103795644A (en) | Strategy table entry collocation method, device and system | |
| US9112796B2 (en) | System guided surrogating control in broadcast and multicast | |
| CN104601467A (en) | Method and device for sending messages | |
| US11126249B1 (en) | Power reduction methods for variable sized tables | |
| CN110768917B (en) | Message transmission method and device | |
| US20240195749A1 (en) | Path selection for packet transmission | |
| US9853891B2 (en) | System and method for facilitating communication | |
| US10110474B2 (en) | Updating interface list of multi-link group | |
| CN104410588A (en) | Method of implementing virtual switching on router equipment and router equipment | |
| US9473389B2 (en) | Excluding a data frame from a link aggregation group | |
| US20240146652A1 (en) | Optimizing hash table selection for packet processing driven by machine learning |
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 |