WO2016019763A1 - Extension method and apparatus for address resolution protocol table and storage medium - Google Patents

Extension method and apparatus for address resolution protocol table and storage medium Download PDF

Info

Publication number
WO2016019763A1
WO2016019763A1 PCT/CN2015/081700 CN2015081700W WO2016019763A1 WO 2016019763 A1 WO2016019763 A1 WO 2016019763A1 CN 2015081700 W CN2015081700 W CN 2015081700W WO 2016019763 A1 WO2016019763 A1 WO 2016019763A1
Authority
WO
WIPO (PCT)
Prior art keywords
address
arp
routing table
cpu
host
Prior art date
Application number
PCT/CN2015/081700
Other languages
French (fr)
Chinese (zh)
Inventor
焦赵云
Original Assignee
中兴通讯股份有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 中兴通讯股份有限公司 filed Critical 中兴通讯股份有限公司
Publication of WO2016019763A1 publication Critical patent/WO2016019763A1/en

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L61/00Network arrangements, protocols or services for addressing or naming

Definitions

  • the present invention relates to network routing technologies, and in particular, to an extended method and apparatus for an address resolution protocol (ARP) table, and a storage medium.
  • ARP address resolution protocol
  • the access mode also has Layer 3 (L3) access.
  • L3 access mode access devices such as DSLAMs, PONs, and MAN switches need to use switch chips for data aggregation and L3 forwarding. Due to the increasing number of access users, the capacity of the switch chip to store ARP tables cannot meet this requirement. The current practice is generally to replace the switch chip with a larger ARP table capacity, but this method is limited by two conditions: First, whether the chip manufacturer can provide such a product in time, and second, the cost of the chip will be high.
  • the present invention mainly provides an extended method and device for an address resolution protocol table, and a storage medium.
  • the present invention provides an extended method of an ARP table, the method comprising:
  • the CPU obtains the ARP table, and sets the networking protocol (IP) address of the ARP table to the host routing table of the switch chip;
  • IP networking protocol
  • the CPU sets the IP address of the hash conflicting ARP table to the subnet routing table of the switching chip.
  • the obtaining the ARP table by the CPU includes: the CPU receiving the ARP packet, The ARP learning is performed.
  • the ARP learning is to establish an ARP table by establishing a mapping relationship between the IP address, the next hop information, and the interface.
  • the method further includes: after the CPU sets the IP address of the hash conflicting ARP table to the subnet routing table of the switch chip, and further sets a fully matched subnet mask for the IP address, where the subnet
  • the lookup table of the routing table uses a three-state content addressing memory (TCAM) lookup table.
  • the method further includes: setting, by the CPU, a threshold, when the number of IP addresses of the ARP table set to the subnet routing table reaches the threshold, the other IP addresses of the ARP table are no longer set to the subnet routing table. in.
  • the method further includes: the CPU marking the flag of the IP address of the ARP table set to the host routing table as a host; setting a flag of the IP address of the ARP table set to the subnet routing table For subnets.
  • the method further includes: when performing a host route lookup on the data packet, the switch chip preferentially searches for the IP address of the host routing table, and if found, directly forwards the data packet according to the found IP address, if If not found, the subnet routing table is matched with the longest IP mask. If it is found, the packet is directly forwarded according to the found IP address. If not found, the packet is discarded or sent to the CPU. .
  • the method further includes: when the ARP entry is aged or deleted, the CPU first checks the flag of the IP address of the aging or deleted ARP entry, and if it is the host, searches for and deletes the host routing table from the switch chip. IP address entry of the IP address; if it is subnet, find and delete the IP address of the IP address from the subnet routing table of the switch chip.
  • the present invention provides an extension device of an address resolution protocol table, which includes: a CPU and a switch chip;
  • the CPU is configured to obtain an ARP table, and set an IP address of the ARP table to a host routing table of the switch chip; when a hash collision occurs in the host routing table, set an IP address of the ARP table of the hash conflict to the sub-switch of the switch chip.
  • the network routing table In the network routing table;
  • a switch chip configured to provide a host routing table and a subnet routing table.
  • the CPU is further configured to set a threshold. After the number of IP addresses of the ARP table set to the subnet routing table reaches the threshold, the other IP addresses of the ARP table are no longer set to the subnet route. In the table.
  • the CPU is further configured to mark the flag of the IP address of the ARP table set to the host routing table as host; and mark the IP address of the ARP table set to the subnet routing table as subnet.
  • a storage medium having stored therein a computer program configured to perform the aforementioned method of extending an Address Resolution Protocol (ARP) table.
  • ARP Address Resolution Protocol
  • the embodiment of the present invention provides an extended method and device for an address resolution protocol table, and a storage medium.
  • the CPU obtains an ARP table, and sets an IP address of the ARP table to a host routing table of the switch chip; when the host routing table occurs When the hash conflicts, the IP address of the ARP table of the hash conflict is set to the subnet routing table of the switch chip. In this way, the capacity of the IP address of the ARP table stored in the switch chip can be greatly improved, and the problem that the network failure of the host host routing IP address hash conflict is solved.
  • FIG. 1 is a schematic flowchart 1 of a method for implementing an address resolution protocol table according to an embodiment of the present invention
  • FIG. 2 is a schematic flowchart of aging or manually deleting an ARP entry according to an embodiment of the present invention
  • FIG. 3 is a schematic structural diagram of an apparatus for implementing an address resolution protocol table according to an embodiment of the present invention.
  • FIG. 4 is a second schematic flowchart of a method for implementing an address resolution protocol table according to an embodiment of the present invention.
  • the switch chip generally has a host routing table and a subnet routing table.
  • the host routing table is used to store the IP address and the next hop index of the ARP table, and the subnet routing table is used to store the subnet IP address prefix and the next hop. index.
  • the host routing table generally uses the hash algorithm, and the subnet routing table generally uses the Ternary Content Addressable Memory (TCAM) because it needs to preferentially perform the longest route matching.
  • TCAM Ternary Content Addressable Memory
  • the TCAM has the advantages of fast searching speed and simple operation. But at the same time it also has obvious shortcomings: high cost, high power consumption and complex routing updates.
  • the host routing table in the switch chip is relatively large, it is easy to conflict by using the hash algorithm; although the subnet routing table is relatively small, the search is accurate. According to the characteristics of these two tables, an extension method and device of the address resolution protocol table are proposed.
  • the CPU obtains the ARP table, and sets the IP address of the ARP table to the host routing table of the switch chip.
  • the host routing table has a hash conflict
  • the IP address of the ARP table of the hash conflict is set to the exchange.
  • the subnet routing table of the chip In this way, the capacity of the IP address of the ARP table stored in the switch chip can be greatly increased.
  • An embodiment of the present invention implements an extension method of an address resolution protocol table. As shown in FIG. 1 , the method mainly includes the following steps:
  • Step 101 The CPU obtains an ARP table.
  • Step 102 The CPU sets an IP address of the ARP table to a host routing table of the switch chip.
  • Step 103 When a hash collision occurs in the host routing table, the CPU sets the IP address of the ARP table of the hash conflict to the subnet routing table of the switching chip.
  • the setting of the host routing table by the CPU or the setting of the subnet routing table by the CPU may be: the CPU writes the register of the host chip routing table or the subnet routing table of the switching chip through the PCI bus. operating.
  • the CPU obtains an ARP table by using an ARP protocol or a Dynamic Host Configuration Protocol (DHCP), where the ARP table includes an IP address, a next hop information, and a mapping relationship between the interfaces.
  • the CPU receives an ARP packet and performs ARP learning.
  • the ARP learning is to establish an IP address and a next hop.
  • the mapping relationship between the information and the interface forms an ARP table.
  • the CPU determines that a hash collision occurs in the host routing table according to the received setup failure message, and the setting failure message is that the number of IP addresses having the same hash index in the host routing table exceeds the hash bucket depth.
  • the hash bucket depth may generally be 8.
  • the CPU sets the IP address of the hash conflicting ARP table to the subnet routing table of the switch chip, it is also required to set a fully matched subnet mask for the IP address, and the subnet mask.
  • IPV4 32-bit
  • IPV6 128-bit
  • the look-up table of the subnet routing table adopts the TCAM lookup table.
  • the subnet routing table cannot be used to store the IP address of the ARP table. Therefore, you need to set a threshold. When the number of IP addresses in the ARP table of the subnet routing table reaches the threshold. The other IP addresses of the ARP table are no longer set to the subnet routing table.
  • the CPU marks the flag of each IP address as a host; for the IP address of the ARP table set to the subnet routing table, The CPU marks the flag of each IP address as a subnet.
  • the switch chip When performing a host route lookup on a data packet, the switch chip preferentially searches for the IP address of the host routing table. If it finds, it directly forwards the data packet according to the found IP address. If not, the subnet route is obtained. The table performs a matching lookup of the longest IP mask. If it finds, it forwards the packet directly according to the found IP address. If it is not found, the packet is discarded or sent to the CPU.
  • the steps for aging or deleting an ARP entry include:
  • Step 201 The ARP entry is aged or deleted.
  • Step 202 The CPU first checks the flag of the IP address of the aging or deleted ARP entry, and if it is the host, searches for and deletes the IP entry of the IP address from the host routing table of the switch chip, and returns a success message;
  • Step 203 If it is a subnet, find and delete an IP entry of the IP address from the subnet routing table of the switch chip, and return a success message;
  • Step 204 If both types are not, a failure message is returned.
  • the present invention further provides an apparatus for extending an address resolution protocol table.
  • the apparatus includes: a CPU 31 and a switch chip 32;
  • the CPU 31 is configured to obtain an ARP table, and set an IP address of the ARP table to a host routing table of the switch chip. When a hash collision occurs in the host routing table, set an IP address of the ARP table of the hash conflict to the switch chip. Subnet routing table;
  • the switch chip 32 is configured to provide a host routing table and a subnet routing table.
  • the ARP table is obtained by the CPU 31.
  • the CPU 31 receives the ARP packet and performs ARP learning.
  • the ARP learning is to establish an ARP table by establishing an mapping relationship between the IP address, the next hop information, and the interface.
  • the CPU 31 is further configured to set a fully matched subnet mask for the IP address set in the subnet routing table, the subnet mask being 32 bits (IPV4) or 128 bits (IPV6)
  • IPV4 32 bits
  • IPV6 128 bits
  • the CPU 31 is further configured to set a threshold. After the number of IP addresses of the ARP table set to the subnet routing table reaches the threshold, the other IP addresses of the ARP table are no longer set to the sub-address. In the network routing table.
  • the CPU 31 is further configured to mark the IP address of each ARP table as the IP address of the ARP table set to the host routing table, and the IP address of the ARP table set to the subnet routing table. Mark the flag of each IP address as subnet.
  • the switch chip 32 is further configured to perform an IP address matching search on the host routing table preferentially when performing host route lookup on the data packet. If found, the data packet is directly forwarded according to the found IP address, if not found. To, the matching lookup of the longest IP mask is performed on the subnet routing table. If found, the data packet is directly forwarded according to the found IP address, if not If found, the packet is discarded or sent to the CPU 31;
  • the CPU 31 is further configured to: when the ARP entry is aged or manually deleted, first check the flag of the IP address of the aging or deleted ARP entry, and if it is the host, look up and delete the packet from the host routing table of the switch chip. IP address entry of the IP address; if it is subnet, it searches for and deletes the IP address of the IP address from the subnet routing table of the switch chip; if neither type is true, it returns a failure.
  • FIG. 4 is a specific example of an extension method of an address resolution protocol table according to the present invention, which includes the following steps:
  • Step 401 The CPU receives the ARP packet, performs ARP learning, and obtains an ARP table.
  • Step 402 The CPU sets the IP address of the ARP table to the host routing table of the switch chip.
  • Step 403 The CPU determines whether the host routing table has a hash conflict, if yes, step 404 is performed, if no, step 407 is performed;
  • Step 404 The CPU sets the IP address of the ARP table of the hash conflict to the subnet routing table of the switch chip.
  • Step 405 The CPU determines whether the setting is successful. If yes, step 406 is performed, and if not, a failure message is returned;
  • Step 406 The CPU marks the IP address of the ARP table set to the host routing table as host, and marks the IP address of the ARP table set to the subnet routing table as subnet, and returns a success message;
  • Step 407 The CPU marks the IP address of the ARP table set to the host routing table as host, and returns a success message.
  • the capacity of the IP address of the ARP table stored in the switch chip is improved, and the host host routing IP address hash can be solved.
  • the problem of network failure after the conflict is improved.
  • Embodiments of the present invention also describe a storage medium in which a computer is stored A program configured to perform an extension method of an Address Resolution Protocol (ARP) table described in the foregoing embodiments.
  • ARP Address Resolution Protocol
  • the ARP table is obtained by the CPU, and the IP address of the ARP table is set in the host routing table of the switch chip; when a hash collision occurs in the host routing table, the IP address of the ARP table in which the hash conflicts is set. Set to the subnet routing table of the switch chip. In this way, the capacity of the IP address of the ARP table stored in the switch chip can be greatly improved, and the problem that the network failure of the host host routing IP address hash conflict is solved.

Landscapes

  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

Disclosed is an extension method for an address resolution protocol (ARP) table. A CPU obtains an ARP table and provides an IP address of the ARP table in a host routing table of a switching chip; and when a hash conflict happens to the host routing table, the IP address of the ARP table having the hash conflict is provided in a sub-network routing table of the switching chip. Also disclosed at the same time are an extension apparatus for an address resolution protocol table and a storage medium.

Description

一种地址解析协议表的扩展方法和装置、存储介质Method and device for expanding address resolution protocol table, storage medium 技术领域Technical field
本发明涉及网络路由技术,尤其涉及一种地址解析协议(ARP)表的扩展方法和装置、存储介质。The present invention relates to network routing technologies, and in particular, to an extended method and apparatus for an address resolution protocol (ARP) table, and a storage medium.
背景技术Background technique
随着城域网的快速发展,接入和汇聚网络设备的带宽越来越大,同时运营商要求一个设备接入的用户越来越多。接入模式除了层2(L2)接入以外,还有层3(L3)接入。对于L3接入模式,接入设备如DSLAM、PON、城域网交换机等,需要使用交换芯片进行数据汇聚和L3转发。由于接入用户越来越多,所以交换芯片存储ARP表的容量无法满足这一需求。现有的做法一般是更换更大ARP表容量的交换芯片,但这种方法受限于两个条件:一是芯片厂家是否能及时提供这样的产品,二是芯片的成本会很高。With the rapid development of metropolitan area networks, the bandwidth of access and aggregation network equipment is increasing, and operators are demanding more and more users accessing one device. In addition to Layer 2 (L2) access, the access mode also has Layer 3 (L3) access. For the L3 access mode, access devices such as DSLAMs, PONs, and MAN switches need to use switch chips for data aggregation and L3 forwarding. Due to the increasing number of access users, the capacity of the switch chip to store ARP tables cannot meet this requirement. The current practice is generally to replace the switch chip with a larger ARP table capacity, but this method is limited by two conditions: First, whether the chip manufacturer can provide such a product in time, and second, the cost of the chip will be high.
发明内容Summary of the invention
为解决现有存在的技术问题,本发明主要提供一种地址解析协议表的扩展方法和装置、存储介质。In order to solve the existing technical problems, the present invention mainly provides an extended method and device for an address resolution protocol table, and a storage medium.
本发明的技术方案是这样实现的:The technical solution of the present invention is implemented as follows:
本发明提供一种ARP表的扩展方法,该方法包括:The present invention provides an extended method of an ARP table, the method comprising:
CPU获得ARP表,将ARP表的联网协议(IP)地址设置到交换芯片的主机路由表中;The CPU obtains the ARP table, and sets the networking protocol (IP) address of the ARP table to the host routing table of the switch chip;
当所述主机路由表发生哈希(hash)冲突时,CPU将hash冲突的ARP表的IP地址设置到交换芯片的子网路由表中。When a hash collision occurs in the host routing table, the CPU sets the IP address of the hash conflicting ARP table to the subnet routing table of the switching chip.
上述方案中,所述CPU获得ARP表包括:所述CPU接收ARP报文, 进行ARP学习,所述ARP学习为建立IP地址、下一跳信息、接口三者之间的映射关系,形成ARP表。In the above solution, the obtaining the ARP table by the CPU includes: the CPU receiving the ARP packet, The ARP learning is performed. The ARP learning is to establish an ARP table by establishing a mapping relationship between the IP address, the next hop information, and the interface.
上述方案中,该方法还包括:CPU将hash冲突的ARP表的IP地址设置到交换芯片的子网路由表中后,还对所述IP地址设置全匹配的子网掩码,所述子网路由表的查表方式采用三态内容寻址存储器(TCAM)查表方式。In the above solution, the method further includes: after the CPU sets the IP address of the hash conflicting ARP table to the subnet routing table of the switch chip, and further sets a fully matched subnet mask for the IP address, where the subnet The lookup table of the routing table uses a three-state content addressing memory (TCAM) lookup table.
上述方案中,该方法还包括:CPU设置一个门限,当设置到子网路由表的ARP表的IP地址个数达到所述门限后,不再将ARP表的其他IP地址设置到子网路由表中。In the above solution, the method further includes: setting, by the CPU, a threshold, when the number of IP addresses of the ARP table set to the subnet routing table reaches the threshold, the other IP addresses of the ARP table are no longer set to the subnet routing table. in.
上述方案中,该方法还包括:CPU将设置到主机路由表的ARP表的IP地址的标志(flag)标记为主机(host);将设置到子网路由表的ARP表的IP地址的flag标记为子网(subnet)。In the above solution, the method further includes: the CPU marking the flag of the IP address of the ARP table set to the host routing table as a host; setting a flag of the IP address of the ARP table set to the subnet routing table For subnets.
上述方案中,该方法还包括:交换芯片在对数据包进行主机路由查找时,优先对主机路由表进行IP地址的匹配查找,如果查找到,则按照查找到的IP地址直接转发数据包,如果没有查找到,则对子网路由表进行最长IP掩码的匹配查找,如果查找到,则按照查找到的IP地址直接转发数据包,如果没有查到,则将数据包丢弃或发送到CPU。In the above solution, the method further includes: when performing a host route lookup on the data packet, the switch chip preferentially searches for the IP address of the host routing table, and if found, directly forwards the data packet according to the found IP address, if If not found, the subnet routing table is matched with the longest IP mask. If it is found, the packet is directly forwarded according to the found IP address. If not found, the packet is discarded or sent to the CPU. .
上述方案中,该方法还包括:当ARP条目老化或被删除时,CPU先检查老化或删除的ARP条目的IP地址的flag,如果为host,从交换芯片的主机路由表中查找并删除所述IP地址的IP表项;如果为subnet,从交换芯片的子网路由表中查找并删除所述IP地址的IP表项。In the foregoing solution, the method further includes: when the ARP entry is aged or deleted, the CPU first checks the flag of the IP address of the aging or deleted ARP entry, and if it is the host, searches for and deletes the host routing table from the switch chip. IP address entry of the IP address; if it is subnet, find and delete the IP address of the IP address from the subnet routing table of the switch chip.
本发明提供一种地址解析协议表的扩展装置,该装置包括:CPU、交换芯片;其中,The present invention provides an extension device of an address resolution protocol table, which includes: a CPU and a switch chip;
CPU,配置为获得ARP表,将ARP表的IP地址设置到交换芯片的主机路由表中;当所述主机路由表发生hash冲突时,将hash冲突的ARP表的IP地址设置到交换芯片的子网路由表中; The CPU is configured to obtain an ARP table, and set an IP address of the ARP table to a host routing table of the switch chip; when a hash collision occurs in the host routing table, set an IP address of the ARP table of the hash conflict to the sub-switch of the switch chip. In the network routing table;
交换芯片,配置为提供主机路由表和子网路由表。A switch chip configured to provide a host routing table and a subnet routing table.
上述方案中,所述CPU,还配置为设置一个门限,当设置到子网路由表的ARP表的IP地址个数达到所述门限后,不再将ARP表的其他IP地址设置到子网路由表中。In the above solution, the CPU is further configured to set a threshold. After the number of IP addresses of the ARP table set to the subnet routing table reaches the threshold, the other IP addresses of the ARP table are no longer set to the subnet route. In the table.
上述方案中,所述CPU,还配置为将设置到主机路由表的ARP表的IP地址的flag标记为host;将设置到子网路由表的ARP表的IP地址的flag标记为subnet。In the above solution, the CPU is further configured to mark the flag of the IP address of the ARP table set to the host routing table as host; and mark the IP address of the ARP table set to the subnet routing table as subnet.
一种存储介质,所述存储介质中存储有计算机程序,所述计算机程序配置为执行前述的地址解析协议(ARP)表的扩展方法。A storage medium having stored therein a computer program configured to perform the aforementioned method of extending an Address Resolution Protocol (ARP) table.
本发明实施例提供了一种地址解析协议表的扩展方法和装置、存储介质,CPU获得ARP表,将ARP表的IP地址设置到交换芯片的主机路由表中;当所述主机路由表发生哈希(hash)冲突时,将hash冲突的ARP表的IP地址设置到交换芯片的子网路由表中。如此,可以大大提高交换芯片存储ARP表的IP地址的容量,解决用户主机路由IP地址hash冲突后导致网络不通的问题。The embodiment of the present invention provides an extended method and device for an address resolution protocol table, and a storage medium. The CPU obtains an ARP table, and sets an IP address of the ARP table to a host routing table of the switch chip; when the host routing table occurs When the hash conflicts, the IP address of the ARP table of the hash conflict is set to the subnet routing table of the switch chip. In this way, the capacity of the IP address of the ARP table stored in the switch chip can be greatly improved, and the problem that the network failure of the host host routing IP address hash conflict is solved.
附图说明DRAWINGS
图1为本发明实施例实现地址解析协议表的扩展方法的流程示意图一;1 is a schematic flowchart 1 of a method for implementing an address resolution protocol table according to an embodiment of the present invention;
图2为本发明实施例提供的ARP条目老化或手工被删除的流程示意图;2 is a schematic flowchart of aging or manually deleting an ARP entry according to an embodiment of the present invention;
图3为本发明实施例实现地址解析协议表的扩展装置的结构示意图;3 is a schematic structural diagram of an apparatus for implementing an address resolution protocol table according to an embodiment of the present invention;
图4为本发明实施例实现地址解析协议表的扩展方法的流程示意图二。FIG. 4 is a second schematic flowchart of a method for implementing an address resolution protocol table according to an embodiment of the present invention.
具体实施方式detailed description
交换芯片一般有主机路由表和子网路由表,主机路由表用于存储ARP表的IP地址和下一跳索引,子网路由表用于存储子网IP地址前缀和下一跳 索引。主机路由表一般使用hash算法,而子网路由表由于需要优先进行最长路由匹配,所以一般使用三态内容寻址存储器(TCAM,Ternary Content Addressable Memory),TCAM具有查找速度快、操作简单的优点,但同时它也具有明显的缺点:成本高、功耗大和路由更新复杂。交换芯片中主机路由表虽然比较大,但使用hash算法,容易冲突;子网路由表虽然比较小,但查找精确。根据这两个表的特点,提出一种地址解析协议表的扩展方法和装置。The switch chip generally has a host routing table and a subnet routing table. The host routing table is used to store the IP address and the next hop index of the ARP table, and the subnet routing table is used to store the subnet IP address prefix and the next hop. index. The host routing table generally uses the hash algorithm, and the subnet routing table generally uses the Ternary Content Addressable Memory (TCAM) because it needs to preferentially perform the longest route matching. The TCAM has the advantages of fast searching speed and simple operation. But at the same time it also has obvious shortcomings: high cost, high power consumption and complex routing updates. Although the host routing table in the switch chip is relatively large, it is easy to conflict by using the hash algorithm; although the subnet routing table is relatively small, the search is accurate. According to the characteristics of these two tables, an extension method and device of the address resolution protocol table are proposed.
本发明实施例中,CPU获得ARP表,将ARP表的IP地址设置到交换芯片的主机路由表中;当所述主机路由表发生hash冲突时,将hash冲突的ARP表的IP地址设置到交换芯片的子网路由表中。这样,可以使得交换芯片存储ARP表的IP地址的容量大大提高。In the embodiment of the present invention, the CPU obtains the ARP table, and sets the IP address of the ARP table to the host routing table of the switch chip. When the host routing table has a hash conflict, the IP address of the ARP table of the hash conflict is set to the exchange. The subnet routing table of the chip. In this way, the capacity of the IP address of the ARP table stored in the switch chip can be greatly increased.
下面通过附图及具体实施例对本发明做进一步的详细说明。The invention will be further described in detail below with reference to the drawings and specific embodiments.
本发明实施例实现一种地址解析协议表的扩展方法,如图1所示,该方法主要包括以下几个步骤:An embodiment of the present invention implements an extension method of an address resolution protocol table. As shown in FIG. 1 , the method mainly includes the following steps:
步骤101:CPU获得ARP表;Step 101: The CPU obtains an ARP table.
步骤102:CPU将ARP表的IP地址设置到交换芯片的主机路由表中;Step 102: The CPU sets an IP address of the ARP table to a host routing table of the switch chip.
步骤103:当所述主机路由表发生hash冲突时,CPU将hash冲突的ARP表的IP地址设置到交换芯片的子网路由表中。Step 103: When a hash collision occurs in the host routing table, the CPU sets the IP address of the ARP table of the hash conflict to the subnet routing table of the switching chip.
上述步骤中,CPU对所述主机路由表的设置或CPU对所述子网路由表的设置,均可以是:CPU通过PCI总线对交换芯片的主机路由表或子网路由表所在的寄存器进行写操作。In the above steps, the setting of the host routing table by the CPU or the setting of the subnet routing table by the CPU may be: the CPU writes the register of the host chip routing table or the subnet routing table of the switching chip through the PCI bus. operating.
所述步骤101中,CPU通过ARP协议或动态主机配置协议(DHCP,Dynamic Host Configuration Protocol)获得ARP表,所述ARP表包括IP地址、下一跳信息、接口三者之间的映射关系;在步骤101中,所述CPU接收ARP报文,进行ARP学习,所述ARP学习就是建立IP地址、下一跳信 息、接口三者之间的映射关系,形成ARP表。In the step 101, the CPU obtains an ARP table by using an ARP protocol or a Dynamic Host Configuration Protocol (DHCP), where the ARP table includes an IP address, a next hop information, and a mapping relationship between the interfaces. In step 101, the CPU receives an ARP packet and performs ARP learning. The ARP learning is to establish an IP address and a next hop. The mapping relationship between the information and the interface forms an ARP table.
所述步骤103中,所述CPU根据收到的设置失败消息确定所述主机路由表发生hash冲突,所述设置失败消息为主机路由表中具有相同hash索引的IP地址的个数超出hash桶深时交换芯片反馈的消息,所述hash桶深一般可以为8。In the step 103, the CPU determines that a hash collision occurs in the host routing table according to the received setup failure message, and the setting failure message is that the number of IP addresses having the same hash index in the host routing table exceeds the hash bucket depth. When the chip feeds back the message, the hash bucket depth may generally be 8.
作为一种实现方式,CPU将hash冲突的ARP表的IP地址设置到交换芯片的子网路由表中后,还需要对所述IP地址设置全匹配的子网掩码,所述子网掩码为32位(IPV4)或128位(IPV6),所述子网路由表的查表方式采用TCAM查表方式。As an implementation manner, after the CPU sets the IP address of the hash conflicting ARP table to the subnet routing table of the switch chip, it is also required to set a fully matched subnet mask for the IP address, and the subnet mask. For 32-bit (IPV4) or 128-bit (IPV6), the look-up table of the subnet routing table adopts the TCAM lookup table.
考虑到子网路由的需要,子网路由表不能全部用于存储ARP表的IP地址,因此,需要设置一个门限,当设置到子网路由表的ARP表的IP地址个数达到所述门限后,不再将ARP表的其他IP地址设置到子网路由表中。The subnet routing table cannot be used to store the IP address of the ARP table. Therefore, you need to set a threshold. When the number of IP addresses in the ARP table of the subnet routing table reaches the threshold. The other IP addresses of the ARP table are no longer set to the subnet routing table.
作为一种实现方式,对于设置到主机路由表的ARP表的IP地址,CPU将各IP地址的标志(flag)标记为主机(host);对于设置到子网路由表的ARP表的IP地址,CPU将各IP地址的flag标记为子网(subnet)。As an implementation manner, for the IP address of the ARP table set to the host routing table, the CPU marks the flag of each IP address as a host; for the IP address of the ARP table set to the subnet routing table, The CPU marks the flag of each IP address as a subnet.
交换芯片在对数据包进行主机路由查找时,优先对主机路由表进行IP地址的匹配查找,如果查找到,则按照查找到的IP地址直接转发数据包,如果没有查找到,则对子网路由表进行最长IP掩码的匹配查找,如果查找到,则按照查找到的IP地址直接转发数据包,如果没有查到,则将数据包丢弃或发送到CPU。When performing a host route lookup on a data packet, the switch chip preferentially searches for the IP address of the host routing table. If it finds, it directly forwards the data packet according to the found IP address. If not, the subnet route is obtained. The table performs a matching lookup of the longest IP mask. If it finds, it forwards the packet directly according to the found IP address. If it is not found, the packet is discarded or sent to the CPU.
如图2所示,ARP条目老化或被删除的步骤包括:As shown in Figure 2, the steps for aging or deleting an ARP entry include:
步骤201:ARP条目老化或被删除;Step 201: The ARP entry is aged or deleted.
步骤202:CPU先检查老化或删除的ARP条目的IP地址的flag,如果为host,就从交换芯片的主机路由表中查找并删除所述IP地址的IP表项,返回成功消息; Step 202: The CPU first checks the flag of the IP address of the aging or deleted ARP entry, and if it is the host, searches for and deletes the IP entry of the IP address from the host routing table of the switch chip, and returns a success message;
步骤203:如果为subnet,就从交换芯片的子网路由表中查找并删除所述IP地址的IP表项,返回成功消息;Step 203: If it is a subnet, find and delete an IP entry of the IP address from the subnet routing table of the switch chip, and return a success message;
步骤204:如果两个类型都不是的话,就返回失败消息。Step 204: If both types are not, a failure message is returned.
为了实现上述方法,本发明还提供一种地址解析协议表的扩展装置,如图3所示,该装置包括:CPU 31、交换芯片32;其中,In order to achieve the above method, the present invention further provides an apparatus for extending an address resolution protocol table. As shown in FIG. 3, the apparatus includes: a CPU 31 and a switch chip 32;
CPU 31,配置为获得ARP表,将ARP表的IP地址设置到交换芯片的主机路由表中;当所述主机路由表发生hash冲突时,将hash冲突的ARP表的IP地址设置到交换芯片的子网路由表中;The CPU 31 is configured to obtain an ARP table, and set an IP address of the ARP table to a host routing table of the switch chip. When a hash collision occurs in the host routing table, set an IP address of the ARP table of the hash conflict to the switch chip. Subnet routing table;
交换芯片32,配置为提供主机路由表和子网路由表。The switch chip 32 is configured to provide a host routing table and a subnet routing table.
所述CPU 31获得ARP表包括:所述CPU 31接收ARP报文,进行ARP学习,所述ARP学习就是建立IP地址、下一跳信息、接口三者之间的映射关系,形成ARP表。The ARP table is obtained by the CPU 31. The CPU 31 receives the ARP packet and performs ARP learning. The ARP learning is to establish an ARP table by establishing an mapping relationship between the IP address, the next hop information, and the interface.
作为一种实现方式,所述CPU 31还配置为对设置到子网路由表中的IP地址设置全匹配的子网掩码,所述子网掩码为32位(IPV4)或128位(IPV6),所述子网路由表的查表方式采用TCAM查表方式。As an implementation, the CPU 31 is further configured to set a fully matched subnet mask for the IP address set in the subnet routing table, the subnet mask being 32 bits (IPV4) or 128 bits (IPV6) The manner of checking the subnet routing table adopts the TCAM lookup table.
作为一种实现方式,所述CPU 31还配置为设置一个门限,当设置到子网路由表的ARP表的IP地址个数达到所述门限后,不再将ARP表的其他IP地址设置到子网路由表中。As an implementation manner, the CPU 31 is further configured to set a threshold. After the number of IP addresses of the ARP table set to the subnet routing table reaches the threshold, the other IP addresses of the ARP table are no longer set to the sub-address. In the network routing table.
作为一种实现方式,所述CPU 31还配置为对设置到主机路由表的ARP表的IP地址,将各IP地址的flag标记为host;对设置到子网路由表的ARP表的IP地址,将各IP地址的flag标记为subnet。As an implementation manner, the CPU 31 is further configured to mark the IP address of each ARP table as the IP address of the ARP table set to the host routing table, and the IP address of the ARP table set to the subnet routing table. Mark the flag of each IP address as subnet.
所述交换芯片32,还配置为在对数据包进行主机路由查找时,优先对主机路由表进行IP地址的匹配查找,如果查找到,则按照查找到的IP地址直接转发数据包,如果没有查找到,则对子网路由表进行最长IP掩码的匹配查找,如果查找到,则按照查找到的IP地址直接转发数据包,如果没有 查到,则将数据包丢弃或发送到CPU 31;The switch chip 32 is further configured to perform an IP address matching search on the host routing table preferentially when performing host route lookup on the data packet. If found, the data packet is directly forwarded according to the found IP address, if not found. To, the matching lookup of the longest IP mask is performed on the subnet routing table. If found, the data packet is directly forwarded according to the found IP address, if not If found, the packet is discarded or sent to the CPU 31;
所述CPU 31,还配置为当ARP条目老化或手工被删除时,先检查老化或删除的ARP条目的IP地址的flag,如果为host,就从交换芯片的主机路由表中查找并删除所述IP地址的IP表项;如果为subnet,就从交换芯片的子网路由表中查找并删除所述IP地址的IP表项;如果两个类型都不是的话,就返回失败。The CPU 31 is further configured to: when the ARP entry is aged or manually deleted, first check the flag of the IP address of the aging or deleted ARP entry, and if it is the host, look up and delete the packet from the host routing table of the switch chip. IP address entry of the IP address; if it is subnet, it searches for and deletes the IP address of the IP address from the subnet routing table of the switch chip; if neither type is true, it returns a failure.
图4为本发明的地址解析协议表的扩展方法的具体实例,包括以下几个步骤:FIG. 4 is a specific example of an extension method of an address resolution protocol table according to the present invention, which includes the following steps:
步骤401:CPU接收ARP报文,进行ARP学习,获得ARP表;Step 401: The CPU receives the ARP packet, performs ARP learning, and obtains an ARP table.
步骤402:CPU将ARP表的IP地址设置到交换芯片的主机路由表中;Step 402: The CPU sets the IP address of the ARP table to the host routing table of the switch chip.
步骤403:CPU判断所述主机路由表是否发生hash冲突,如果是,则执行步骤404,如果否,则执行步骤407;Step 403: The CPU determines whether the host routing table has a hash conflict, if yes, step 404 is performed, if no, step 407 is performed;
步骤404:CPU将hash冲突的ARP表的IP地址设置到交换芯片的子网路由表中;Step 404: The CPU sets the IP address of the ARP table of the hash conflict to the subnet routing table of the switch chip.
步骤405:CPU判断是否设置成功,如果是,执行步骤406,如果否,返回失败消息;Step 405: The CPU determines whether the setting is successful. If yes, step 406 is performed, and if not, a failure message is returned;
步骤406:CPU将设置到主机路由表的ARP表的IP地址的flag标记为host,将设置到子网路由表的ARP表的IP地址的flag标记为subnet,返回成功消息;Step 406: The CPU marks the IP address of the ARP table set to the host routing table as host, and marks the IP address of the ARP table set to the subnet routing table as subnet, and returns a success message;
步骤407:CPU将设置到主机路由表的ARP表的IP地址的flag标记为host,返回成功消息。Step 407: The CPU marks the IP address of the ARP table set to the host routing table as host, and returns a success message.
综合本发明的各实施例,通过将ARP表的IP地址设置到交换芯片的主机路由表和子网路由表中,提高了交换芯片存储ARP表的IP地址的容量,能够解决用户主机路由IP地址hash冲突后导致网络不通的问题。In the embodiment of the present invention, by setting the IP address of the ARP table to the host routing table and the subnet routing table of the switch chip, the capacity of the IP address of the ARP table stored in the switch chip is improved, and the host host routing IP address hash can be solved. The problem of network failure after the conflict.
本发明实施例还记载了一种存储介质,所述存储介质中存储有计算机 程序,所述计算机程序配置为执行前述各实施例所述的地址解析协议(ARP)表的扩展方法。Embodiments of the present invention also describe a storage medium in which a computer is stored A program configured to perform an extension method of an Address Resolution Protocol (ARP) table described in the foregoing embodiments.
以上所述,仅为本发明的较佳实施例而已,并非用于限定本发明的保护范围,凡在本发明的精神和原则之内所作的任何修改、等同替换和改进等,均应包含在本发明的保护范围之内。The above is only the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in Within the scope of protection of the present invention.
工业实用性Industrial applicability
本发明中,由CPU获得ARP表,将ARP表的IP地址设置到交换芯片的主机路由表中;当所述主机路由表发生哈希(hash)冲突时,将hash冲突的ARP表的IP地址设置到交换芯片的子网路由表中。如此,可以大大提高交换芯片存储ARP表的IP地址的容量,解决用户主机路由IP地址hash冲突后导致网络不通的问题。 In the present invention, the ARP table is obtained by the CPU, and the IP address of the ARP table is set in the host routing table of the switch chip; when a hash collision occurs in the host routing table, the IP address of the ARP table in which the hash conflicts is set. Set to the subnet routing table of the switch chip. In this way, the capacity of the IP address of the ARP table stored in the switch chip can be greatly improved, and the problem that the network failure of the host host routing IP address hash conflict is solved.

Claims (11)

  1. 一种地址解析协议(ARP)表的扩展方法,该方法包括:An extended method of an Address Resolution Protocol (ARP) table, the method comprising:
    CPU获得ARP表,将ARP表的联网协议(IP)地址设置到交换芯片的主机路由表中;The CPU obtains the ARP table, and sets the networking protocol (IP) address of the ARP table to the host routing table of the switch chip;
    当所述主机路由表发生哈希(hash)冲突时,CPU将hash冲突的ARP表的IP地址设置到交换芯片的子网路由表中。When a hash collision occurs in the host routing table, the CPU sets the IP address of the hash conflicting ARP table to the subnet routing table of the switching chip.
  2. 根据权利要求1所述的扩展方法,其中,所述CPU获得ARP表包括:所述CPU接收ARP报文,进行ARP学习,所述ARP学习为建立IP地址、下一跳信息、接口三者之间的映射关系,形成ARP表。The method of claim 1 , wherein the obtaining the ARP table by the CPU comprises: the CPU receiving an ARP packet, and performing ARP learning, where the ARP learning is to establish an IP address, a next hop information, and an interface. The mapping relationship between the two forms an ARP table.
  3. 根据权利要求1所述的扩展方法,其中,该方法还包括:CPU将hash冲突的ARP表的IP地址设置到交换芯片的子网路由表中后,还对所述IP地址设置全匹配的子网掩码,所述子网路由表的查表方式采用三态内容寻址存储器(TCAM)查表方式。The expansion method according to claim 1, wherein the method further comprises: after the CPU sets the IP address of the hash conflicting ARP table to the subnet routing table of the switch chip, and further sets a fully matched sub-portion to the IP address. The netmask, the lookup mode of the subnet routing table adopts a three-state content addressing memory (TCAM) lookup table.
  4. 根据权利要求1所述的扩展方法,其中,该方法还包括:CPU设置一个门限,当设置到子网路由表的ARP表的IP地址个数达到所述门限后,不再将ARP表的其他IP地址设置到子网路由表中。The expansion method according to claim 1, wherein the method further comprises: the CPU setting a threshold, and after the number of IP addresses of the ARP table set to the subnet routing table reaches the threshold, the other ARP table is no longer used. The IP address is set to the subnet routing table.
  5. 根据权利要求1所述的扩展方法,其中,该方法还包括:CPU将设置到主机路由表的ARP表的IP地址的标志(flag)标记为主机(host);将设置到子网路由表的ARP表的IP地址的flag标记为子网(subnet)。The expansion method according to claim 1, wherein the method further comprises: the CPU marking a flag of an IP address set to an ARP table of the host routing table as a host; setting the packet to the subnet routing table The flag of the IP address of the ARP table is marked as a subnet.
  6. 根据权利要求1所述的扩展方法,其中,该方法还包括:交换芯片在对数据包进行主机路由查找时,优先对主机路由表进行IP地址的匹配查找,如果查找到,则按照查找到的IP地址直接转发数据包,如果没有查找到,则对子网路由表进行最长IP掩码的匹配查找,如果查找到,则按照查找到的IP地址直接转发数据包,如果没有查到,则将数据包丢弃或发送到CPU。 The expansion method according to claim 1, wherein the method further comprises: when the host performs route lookup on the data packet, the switch chip preferentially searches for the IP address of the host routing table, and if found, searches according to the search result. The IP address directly forwards the data packet. If not found, the longest IP mask matching search is performed on the subnet routing table. If found, the data packet is directly forwarded according to the found IP address. If not, the packet is not directly found. Drop or send the packet to the CPU.
  7. 根据权利要求5所述的扩展方法,其中,该方法还包括:当ARP条目老化或被删除时,CPU先检查老化或删除的ARP条目的IP地址的flag,如果为host,从交换芯片的主机路由表中查找并删除所述IP地址的IP表项;如果为subnet,从交换芯片的子网路由表中查找并删除所述IP地址的IP表项。The expansion method according to claim 5, wherein the method further comprises: when the ARP entry is aged or deleted, the CPU first checks the flag of the IP address of the aged or deleted ARP entry, and if it is the host, the host from the switch chip The IP address of the IP address is searched for and deleted in the routing table. If it is a subnet, the IP address of the IP address is searched for and deleted from the subnet routing table of the switch chip.
  8. 一种地址解析协议表的扩展装置,该装置包括:CPU、交换芯片;其中,An expansion device of an address resolution protocol table, the device comprising: a CPU and a switch chip; wherein
    CPU,配置为获得ARP表,将ARP表的IP地址设置到交换芯片的主机路由表中;当所述主机路由表发生hash冲突时,将hash冲突的ARP表的IP地址设置到交换芯片的子网路由表中;The CPU is configured to obtain an ARP table, and set an IP address of the ARP table to a host routing table of the switch chip; when a hash collision occurs in the host routing table, set an IP address of the ARP table of the hash conflict to the sub-switch of the switch chip. In the network routing table;
    交换芯片,配置为提供主机路由表和子网路由表。A switch chip configured to provide a host routing table and a subnet routing table.
  9. 根据权利要求8所述的扩展装置,其中,所述CPU,还配置为设置一个门限,当设置到子网路由表的ARP表的IP地址个数达到所述门限后,不再将ARP表的其他IP地址设置到子网路由表中。The expansion device according to claim 8, wherein the CPU is further configured to set a threshold, and when the number of IP addresses of the ARP table set to the subnet routing table reaches the threshold, the ARP table is no longer The other IP addresses are set to the subnet routing table.
  10. 根据权利要求8所述的扩展装置,其中,所述CPU,还配置为将设置到主机路由表的ARP表的IP地址的flag标记为host;将设置到子网路由表的ARP表的IP地址的flag标记为subnet。The expansion apparatus according to claim 8, wherein said CPU is further configured to mark a flag of an IP address of an ARP table set to a host routing table as host; an IP address of an ARP table to be set to a subnet routing table The flag is marked as subnet.
  11. 一种存储介质,所述存储介质中存储有计算机程序,所述计算机程序配置为执行权利要求1至7任一项所述的地址解析协议(ARP)表的扩展方法。 A storage medium storing a computer program configured to execute the method of extending an address resolution protocol (ARP) table according to any one of claims 1 to 7.
PCT/CN2015/081700 2014-08-05 2015-06-17 Extension method and apparatus for address resolution protocol table and storage medium WO2016019763A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201410381822.9A CN105323175A (en) 2014-08-05 2014-08-05 Method and device for expanding address resolution protocol table
CN201410381822.9 2014-08-05

Publications (1)

Publication Number Publication Date
WO2016019763A1 true WO2016019763A1 (en) 2016-02-11

Family

ID=55249791

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/081700 WO2016019763A1 (en) 2014-08-05 2015-06-17 Extension method and apparatus for address resolution protocol table and storage medium

Country Status (2)

Country Link
CN (1) CN105323175A (en)
WO (1) WO2016019763A1 (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107770076B (en) * 2016-08-23 2020-12-04 中兴通讯股份有限公司 Hash collision processing method and device and switching equipment
CN109639581B (en) * 2019-02-21 2021-05-28 杭州迪普科技股份有限公司 Table entry maintenance method and device of switch chip
CN115118662A (en) * 2022-06-16 2022-09-27 浪潮思科网络科技有限公司 Hash collision processing method, system, equipment and medium based on ARP table

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080192754A1 (en) * 2007-02-12 2008-08-14 Yoon-Jin Ku Routing system and method for managing rule entries of ternary content addressable memory in the same
CN101325554A (en) * 2008-08-04 2008-12-17 北京星网锐捷网络技术有限公司 Method for establishing route, forwarding chip and three-layer switchboard
CN101540731A (en) * 2009-04-30 2009-09-23 杭州华三通信技术有限公司 Three-tier message retransmission method and device
CN101741737A (en) * 2009-12-08 2010-06-16 中兴通讯股份有限公司 Maintenance method and device of route table
CN103166858A (en) * 2013-03-26 2013-06-19 杭州华三通信技术有限公司 Message transmission method and device

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103577564A (en) * 2013-10-25 2014-02-12 盛科网络(苏州)有限公司 Method and device for reducing HASH collision through software shift
CN103560962A (en) * 2013-11-04 2014-02-05 神州数码网络(北京)有限公司 Method for automatically updating host routing table entries of Ethernet switch and switch

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080192754A1 (en) * 2007-02-12 2008-08-14 Yoon-Jin Ku Routing system and method for managing rule entries of ternary content addressable memory in the same
CN101325554A (en) * 2008-08-04 2008-12-17 北京星网锐捷网络技术有限公司 Method for establishing route, forwarding chip and three-layer switchboard
CN101540731A (en) * 2009-04-30 2009-09-23 杭州华三通信技术有限公司 Three-tier message retransmission method and device
CN101741737A (en) * 2009-12-08 2010-06-16 中兴通讯股份有限公司 Maintenance method and device of route table
CN103166858A (en) * 2013-03-26 2013-06-19 杭州华三通信技术有限公司 Message transmission method and device

Also Published As

Publication number Publication date
CN105323175A (en) 2016-02-10

Similar Documents

Publication Publication Date Title
US9240944B2 (en) Overlay services in communication networks
ES2826388T3 (en) Procedure and gateway to acquire a route as required
US9258699B2 (en) Method for route transmission based on single IPv6 address prefix, and wireless device
US8879555B2 (en) Method and apparatus for forwarding packets by obtaining addresses of the packets using a preset forwarding information base entry
US9325616B2 (en) Packet sending method and network device
US20060098644A1 (en) Translating native medium access control (MAC) addresses to hierarchical MAC addresses and their use
WO2016192686A1 (en) Data packet forwarding
CN107547407B (en) Message transmission method, device and implementation device
WO2011088657A1 (en) Method, device and internet system for processing internet address information
CN108494686B (en) Route processing method and device
US9960995B2 (en) Packet forwarding using a physical unit and a virtual forwarding unit
CN109921995B (en) Method for configuring address table, FPGA and network equipment applying FPGA
US9183322B2 (en) Increasing internet protocol version 6 host table scalability in top of rack switches for data center deployments
WO2016019763A1 (en) Extension method and apparatus for address resolution protocol table and storage medium
JP2014150364A (en) Address generation device
CN102291472A (en) Network address lookup method and device
CN107147581B (en) Maintenance method and device for routing table entry
US10897422B2 (en) Hybrid routing table for routing network traffic
US7948916B2 (en) Method and apparatus for discovering topology information in a network
CN108306825B (en) Equivalent forwarding table item generation method and VTEP device
US20230041395A1 (en) Method and Device for Processing Routing Table Entries
CN108768845B (en) Multi-homing host routing synchronization method and device
US9025604B2 (en) Scaling IPV4 at large datacenters with device level aggregation
CN104394081B (en) A kind of data processing method and device
CN101616159A (en) The data forwarding method and the device that are used for three-tier switch

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 15829841

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 15829841

Country of ref document: EP

Kind code of ref document: A1