WO2018040916A1 - 一种转发报文的方法及装置 - Google Patents

一种转发报文的方法及装置 Download PDF

Info

Publication number
WO2018040916A1
WO2018040916A1 PCT/CN2017/097679 CN2017097679W WO2018040916A1 WO 2018040916 A1 WO2018040916 A1 WO 2018040916A1 CN 2017097679 W CN2017097679 W CN 2017097679W WO 2018040916 A1 WO2018040916 A1 WO 2018040916A1
Authority
WO
WIPO (PCT)
Prior art keywords
link
network device
link group
group
links
Prior art date
Application number
PCT/CN2017/097679
Other languages
English (en)
French (fr)
Inventor
庹波
钱慧
付嘉
Original Assignee
华为技术有限公司
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 华为技术有限公司 filed Critical 华为技术有限公司
Publication of WO2018040916A1 publication Critical patent/WO2018040916A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/10—Flow control; Congestion control
    • H04L47/12—Avoiding congestion; Recovering from congestion
    • H04L47/125—Avoiding congestion; Recovering from congestion by balancing the load, e.g. traffic engineering
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/10—Flow control; Congestion control
    • H04L47/33—Flow control; Congestion control using forward notification
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/10—Flow control; Congestion control
    • H04L47/34—Flow control; Congestion control ensuring sequence integrity, e.g. using sequence numbers

Definitions

  • the present application relates to the field of communications technologies, and in particular, to a method and an apparatus for forwarding a message.
  • Load sharing is based on the existing network structure.
  • the packet is dynamically distributed based on links or interfaces through a specific algorithm to extend the bandwidth and increase the throughput of network devices and servers.
  • the min active links are concepts proposed for the load balancing scenario. The purpose is to ensure the minimum bandwidth for normal traffic forwarding.
  • the load sharing technology is used to expand the bandwidth.
  • the carrier needs to be in the load sharing technology.
  • the minimum activation link is added to ensure that switching is required when the minimum number of active links is not met.
  • link detection is usually performed to ensure the accuracy of data packet exchange.
  • the communication device finds that the communication link is abnormal in the detection, the communication link is stopped, and the number of available links in the load sharing is less than the minimum number of active links.
  • the communication device cannot continue. Load balancing is performed, causing traffic interruption.
  • the embodiments of the present invention provide a method and an apparatus for forwarding a message, which helps reduce traffic interruption.
  • a method of forwarding a message is provided.
  • the method is applied to a first network device that communicates with a second network device via a first link group.
  • the method includes:
  • the first network device Determining, by the first network device, that the number of member links in the first link group is less than the minimum number of active links, and the first link group includes the first member link, where the first The member link is in a partially available state;
  • the member link in the available state refers to a member link with a normal signal, and the first member link is in a partially available state, which means that the first member link has signal degraded (SD).
  • the member link in the partially available state in which the signal degradation SD occurs is used to avoid the link group from being deactivated.
  • traffic interruption can be reduced, and network resource utilization and network bandwidth can be further improved.
  • the first link group further includes a second member link, where the second member link is in an available state, and the first network device sends the second network to the second network. And sending, by the first network device, the data packet sequence to be forwarded to the first member link and the second member link to be sent to the device Said second network device. Therefore, load balancing is further performed between the member link in the available state and the member link in the partially available state, thereby further improving network resource utilization.
  • the first link group further includes a second member link, the second member link is in a partially available state, and the first network device sends the second link to the second
  • the sending, by the network device, the data packet sequence to be forwarded includes: the first network device loading, to the first member link and the second member link, the load of the data packet sequence to be forwarded to the first member link The second network device. Therefore, network resource utilization is further improved by performing load sharing between a plurality of member links in a partially available state.
  • the first link group further includes a second member link, the second member link is in an unavailable state, and the first network device sends the second link group to the second
  • the sending, by the network device, the data packet sequence to be forwarded includes: sending, by the first network device, the sequence of data packets to be forwarded to the second network device by using the first member link;
  • the fact that the two-member link is in an unavailable state means that the second member link has a signal failure (SF).
  • SF signal failure
  • the first network device further communicates with the second network device by using the second link group
  • the method further includes: the first network device determining that the second link group is in an available state The number of member links is greater than or equal to the minimum number of active links; the first network device loads the data packet sequence to be forwarded to the first link group and the second link group to be sent to The second network device. Therefore, load balancing is further performed between the link group in which the number of member links in the available state is insufficient and the link group in which the number of member links in the available state is sufficient, thereby further increasing the available network bandwidth and network resource utilization.
  • the first network device further communicates with the second network device by using the second link group
  • the method further includes: the first network device determining that the second link group is in an available state The number of member links is less than the minimum number of active links, and the second link group includes a third member link, and the third member link is in a partially available state; the first network device will be in the The forwarded data packet sequence load is distributed to the first link group and the second link group to be sent to the second network device; the third member link is in a partially available state, which refers to the third A signal degradation SD occurs on the member link. Therefore, load balancing is performed between two link groups in which the number of member links in the available state is insufficient, thereby reducing traffic interruption and further increasing network bandwidth and network resource utilization.
  • the first network device further communicates with the second network device by using the second link group
  • the method further includes: the first network device determining that the second link group is in an available state The number of member links is less than the minimum number of active links, and is greater than zero; the first network device loads the data packet sequence to be forwarded to the first link group and the second link group Sent to the second network device. Therefore, by performing load sharing between two link groups with insufficient number of member links in an available state, traffic interruption is reduced, and further Steps increase network bandwidth and network resource utilization.
  • an apparatus for forwarding a message is provided.
  • the apparatus is applied to a first network device that communicates with a second network device via a first set of links.
  • the apparatus includes a receiving unit, a determining unit, and a transmitting unit.
  • the receiving unit is configured to receive a sequence of data packets to be forwarded, where the determining unit is configured to determine that the number of member links in the first link group that are in an available state is less than a minimum number of active links, and The first link group includes a first member link, the first member link is in a partially available state, and the sending unit is configured to send, by using the first link group, the second network device
  • the sequence of data packets to be forwarded; the member link in the available state refers to a member link with a normal signal, and the first member link is in a partially available state, indicating that the first member link is degraded by SD. .
  • the first link group further includes a second member link, where the second member link is in an available state, and the sending unit is specifically configured to load the data packet sequence to be forwarded to the The first member link and the second member link are sent to the second network device.
  • the first link group further includes a second member link, where the second member link is in a partially available state, and the sending unit is specifically configured to load balance the data packet sequence to be forwarded.
  • the first member link and the second member link are sent to the second network device.
  • the first link group further includes a second member link, where the second member link is in an unavailable state, and the sending unit is specifically configured to use the first member link to The forwarded data packet sequence is sent to the second network device; the second member link is in an unavailable state, and the second member link generates a signal failure SF.
  • the first network device is further configured to communicate with the second network device by using a second link group, where the determining unit is further configured to determine a member link that is in an available state in the second link group. The number is greater than or equal to the minimum number of activated links; the sending unit is further configured to load the data packet sequence to be forwarded to the first link group and the second link group to be sent to the Second network device.
  • the first network device is further configured to communicate with the second network device by using a second link group, where the determining unit is further configured to determine a member link that is in an available state in the second link group. The number is smaller than the minimum number of active links, and the second link group includes a third member link, and the third member link is in a partially available state; the sending unit is further configured to use the to-be-forwarded Data packet sequence load sharing to the first link group and the second link group is sent to the second network device; the third member link is in a partially available state, and the third member chain is The road occurrence signal deteriorates SD.
  • the first network device is further configured to communicate with the second network device by using a second link group, where the determining unit is further configured to determine a member link that is in an available state in the second link group. The number is smaller than the minimum number of active links, and is greater than zero.
  • the sending unit is further configured to load the data packet sequence to be forwarded to the first link group and the second link group to be sent to The second network device.
  • an apparatus for forwarding a message for use in a first network device, the first network device communicating with a second network device via a first link group, the device comprising a processor, a network interface, and a memory.
  • the memory is configured to store a program instruction code.
  • the processor is configured to read a program instruction code in the memory, and control the first network device to perform a method for forwarding a message provided by the first aspect.
  • the network interface is used in Under the control of the processor, the received operation and the sent operation in the method for forwarding a message provided by the first aspect are performed.
  • FIG. 1 is a schematic diagram of a possible application scenario of the present invention
  • FIG. 2 is a schematic diagram of another possible application scenario of the present invention.
  • FIG. 3 is a schematic diagram of packet forwarding according to an embodiment of the present invention.
  • FIG. 4 is a schematic diagram of another packet forwarding according to an embodiment of the present invention.
  • FIG. 5 is a schematic diagram of another packet forwarding according to an embodiment of the present invention.
  • FIG. 6 is a flowchart of a method for forwarding a message according to an embodiment of the present invention.
  • FIG. 7 is a schematic diagram of another packet forwarding according to an embodiment of the present invention.
  • FIG. 8 is a schematic diagram of another packet forwarding according to an embodiment of the present invention.
  • FIG. 9 is a schematic diagram of another packet forwarding according to an embodiment of the present invention.
  • FIG. 10 is a schematic structural diagram of an apparatus for forwarding a message according to an embodiment of the present disclosure.
  • FIG. 11 is a schematic structural diagram of another apparatus for forwarding a message according to an embodiment of the present invention.
  • network element In the present application, "network element”, “network device”, “forwarding device” and “node” are often used interchangeably, and those skilled in the art can know their usual meanings.
  • the above devices may include switches, routers, packet transport network devices, and the like.
  • the communication link involved in the present application may be a physical link, such as an optical fiber at a physical level, or a logical link, such as any one or more of a pseudo-line or a tunnel in a logical plane.
  • the application is collectively referred to as a communication link or link.
  • FIG. 1 is a schematic diagram of a possible application scenario of the present invention.
  • the network element (NE) NE1 may communicate with the network element NE2 via each of the multiple communication links, or may form part or all of the multiple communication links.
  • a plurality of communication links in the link group may form a load sharing relationship, and the network element NE1 may use the link group as a load sharing group, and send a datagram to the network element NE2 through the load sharing group.
  • Sequence of text Each communication link that constitutes a link group can be used as a member link of the load sharing group.
  • the network element NE1 sends the received data packet sequence to the NE NE2 after the load balancing is performed between the multiple member links in the load balancing group.
  • the load balancing group can perform load balancing by using a communication protocol that implements a load sharing mechanism, such as equal-cost multipath (ECMP) or weight-cost multipath (WCMP).
  • ECMP equal-cost multipath
  • WCMP weight-cost multipath
  • FIG. 2 is a schematic diagram of another possible application scenario of the present invention.
  • a plurality of link groups may be included between NE1 and NE2, for example, including a first link group and a second link group.
  • the first link group may include one or more communication links, and the NE1 communicates with the NE2 via the first link group to send a sequence of data messages to the NE2.
  • the plurality of communication links may further form a load sharing relationship, and the first link group may be used as the first load sharing group.
  • Each of the plurality of communication links in the first link group can be used as a member link in the first load sharing group.
  • the second link group may also include one or more communication links via which the NE1 may also communicate with the NE2.
  • Each of the plurality of communication links in the second optional link group may be used as a member link in the second load sharing group.
  • more than two link groups may be included in FIG. 2 and both serve as load sharing groups.
  • each load sharing group may also include more than 2 member links.
  • NE1 can load the received data packets between the multiple load balancing groups.
  • the NE1 may further perform the load balancing in the load sharing group by using the data packet sequence that is allocated to each load sharing group. For example, NE1 can load the load to the data packet sequence of the first load balancing group, and load balancing is performed again between multiple member links in the first load balancing group.
  • the data packet sequence allocation manner in the prior art may be adopted.
  • flow-by-flow load sharing the data packet sequence is differentiated according to the flow to which the data packet sequence belongs, and the data packet sequence of the same stream is sent through the same link; for example, packet-by-packet load sharing, the packet-by-packet load
  • the data packets are distributed to the links that participate in the load balancing according to the sequence of the data packet sequence. For example, the data packets of the same destination address are sent to the same load balancing member link and the data packets are sent. Equally allocates between multiple load-sharing member links, distributes data packets proportionally among multiple member links according to the proportion of member link bandwidth, and so on.
  • the bit error status of the communication link in the error detection includes: signal degradation SD and signal failure SF.
  • the signal degradation SD and the signal failure SF correspond to different error rate thresholds, wherein the signal failure SF threshold is greater than the signal degradation SD threshold.
  • the error detection when the error rate on the link is greater than or equal to the signal degradation SD threshold but less than the signal failure SF threshold, the link is in the signal degradation SD state, and the error rate on the link is greater than When the signal failure SF threshold is equal to or equal to, the link is in the SF state.
  • the state in which the link group member link is located in the embodiment of the present invention includes: an available state, a partially available state, an unavailable state, the available state, and a partially usable state.
  • the unavailable status can be represented by UP, POK, and DOWN, respectively.
  • the member link in the available state UP refers to the member link with the normal signal.
  • the member link in the partially available state POK refers to the member link where the signal degradation occurs.
  • the member link in the unavailable state DOWN refers to the communication.
  • the state in which the link group is located in the embodiment of the present invention may include: an available state, a partially available state, and an unavailable state, and the available state, the partially available state, and the unavailable state may be represented by UP, POK, and DOWN, respectively.
  • the link group is in the available state, that is, the number of member links in the link group that are in the available state is greater than or equal to the minimum number of active links; the link group in the partially available state refers to the member link in the link group that is in the available state.
  • the number is less than the minimum number of active links, and the link group includes member links in an available state or a partially available state; the link group in an unavailable state refers to a member link in the link group that is not in an available state, There are no member links in the partially available state.
  • the number of the member links in the above link group is an arbitrary number, and the number of the minimum active links may be any number less than or equal to the number of link members of the link group.
  • the example number is given in the following scenario description. It will be appreciated by those skilled in the art that other numbers of cases are within the scope of the embodiments of the invention.
  • FIG. 3 is a schematic diagram of packet forwarding according to an embodiment of the present invention. It is assumed that the first link group is used for communication between NE1 and NE2.
  • the first link group includes member link 1 and member link 2, and the number of minimum active links of the link group is 2.
  • the member link 1 is in the UP state and the member link 2 is in the POK state
  • the number of member links in the UP state in the link group is 1, which is less than the minimum number of active links 2, but there is a member link in the POK state. 2, then the best effort forwarding mode can be enabled without deactivating the first link group.
  • the link resource utilization can be improved, the link bandwidth can be increased, and the traffic interruption caused by the link group deactivation can be reduced.
  • the best-effort forwarding mode try to use the member link 1 in the UP state and the member link 2 in the POK state in the link group to sequence the data packet to be sent on the member link 1 and the member. Load-sharing is performed between the two links, so that the forwarding requirements are fulfilled on the link group, and best-effort forwarding is implemented.
  • FIG. 4 is a schematic diagram of another packet forwarding according to an embodiment of the present invention. It is assumed that the first link group is used for communication between NE1 and NE2.
  • the first link group includes member link 1 and member link 2, and the number of minimum active links of the link group is 2.
  • the member link 1 is in the POK state and the member link 2 is in the POK state
  • the number of member links in the UP state in the link group is 0, which is less than the minimum number of active links 2, but there is a member link in the POK state. 1 and member link 2
  • the best effort forwarding mode try to use the member link 1 and the member link 2 in the POK state in the link group, and the data packet sequence to be sent is between member link 1 and member link 2. Perform load sharing and forwarding to achieve best-effort forwarding.
  • FIG. 5 is a schematic diagram of another packet forwarding according to an embodiment of the present invention. It is assumed that the first link group is used for communication between NE1 and NE2.
  • the first link group includes member link 1 and member link 2, and the number of minimum active links of the link group is 2.
  • member link 1 is in the POK state and member link 2 is in the DOWN state
  • the number of member links in the UP state in the link group is 0, which is less than the minimum number of active links 2, but there is a member link in the POK state. 1, then enable the best effort forwarding mode.
  • the member link 1 in the POK state in the link group is used as much as possible, and the data packet sequence to be sent is forwarded through the member link 1 to implement best-effort forwarding.
  • the number of member links in the UP state in the link group is smaller than the minimum number of active links, and the link group includes N member links, where N is greater than or equal to 1.
  • N is greater than or equal to 1.
  • each of the N member links is in an UP state or a POK state, and one or more member links of the N member links are used to transmit a sequence of data packets to implement best-effort forwarding. If N>1, NE1 can load the data packet sequence to the NE2 after load balancing between the N member links.
  • the NE1 may perform load sharing between the plurality of member links in the POK state and then send the data packet sequence to the NE2.
  • FIG. 6 is a flowchart of a method for forwarding a packet according to an embodiment of the present invention.
  • the method is applied to a first network device, where the first network device is a packet forwarding device, such as a router, a switch, etc., the first network.
  • the device communicates with the second network device via the first set of links.
  • the method may be applicable to the scenario as shown in FIG. 1 and FIG. 2, the first network device may be NE1 in FIG. 1 and FIG. 2, and the second network device may be NE2 in FIG.
  • the method can implement forwarding as described in Figures 3 through 5.
  • the method specifically includes:
  • Operation 601 The first network device receives a sequence of data packets to be forwarded.
  • the first network device receives a sequence of data packets to be forwarded from an upstream network device of the first network device.
  • the first network device determines that the number of member links in the first link group that is in an available state is less than the minimum number of active links, and the first link group includes the first member link.
  • the first member link is in a partially available state.
  • the first network device determines a number of member links in the first link group that are in an available state, and compares with a minimum number of active links of the first link group.
  • the minimum number of active links can be specified by a user, an operator, or a device vendor based on traffic bandwidth and the like.
  • the first network device selects an available member link that is greater than or equal to the minimum number of active links to perform load sharing forwarding; when the member is in an available state When the number of links is equal to the minimum number of active links, the first network device selects all available member links to perform load sharing forwarding; when the number of member links in the available state is less than the minimum number of active links, the first link is determined. There are still member links in the group that are in a partially available state. For example, there is a first member link in a partially available state, and the link group can still be utilized, so that the link group is not stopped, but is under Continue to use the link group for forwarding in one step.
  • the first network device sends the to the second network device by using the first link group. Sequence of data packets to be forwarded.
  • the first network device determines that the number of member links in the available state in the first link group is less than the minimum number of active links, and the member chain in the first link group still exists in a partially available state. After the path is, for example, the first member link, the first network device uses the link group to forward the data message sequence to the second network device in operation 603.
  • the first link group further includes a second member link, and the second link is in an UP state.
  • the first network device sends the data message sequence to the first member link and the second link. The load between the member links is transferred to the second network device.
  • the first link group may further include N member links, where N is a natural number greater than or equal to 1, and each of the N member links is in a POK state or an UP state, and the first network The device may forward the received data packet sequence to the second network device after the load sharing of the first member link and the N member links.
  • the first link group further includes a second member link, and the second member link is in a POK state.
  • the first network device sends the data packet sequence to the first member link and the first The load between the two member links is forwarded to the second network device.
  • the first link group includes multiple member links in a POK state
  • load balancing is performed between multiple member links in a POK state, where the multiple member links in the POK state include the First member link.
  • the first link group further includes a second member link, and the second link is in a DOWN state.
  • the first network device forwards the data message sequence to the first member link to the Second network device.
  • the first link group may further include N member links, where N is a natural number greater than or equal to 1, and each of the N member links is in a POK state or a DOWN state, in the first chain.
  • the first network device sends a data packet sequence through the first member link, except for the first member link, and does not include other member links in the POK state; In the member link of the POK state, load balancing is performed between multiple member links in the POK state, and the plurality of member links in the POK state include the first member link.
  • the first network device further communicates with the second network device via a second link group.
  • the second link group is in an available state or a partially available state, and the first network device loads the data message sequence between the first link group and the second link group in operation 603 to be forwarded to the second network. device.
  • the second link group when the second link group is in an available state or a partially available state, the second link group includes N member links, and N is a natural number greater than or equal to 1, each of the N member links All of them are in the UP state or the POK state.
  • N is equal to 1
  • the first network device sends a data packet sequence that is load-balanced to the second link group to the second network device through the one member link.
  • the first network device distributes the load to the data packet sequence of the second link group, and then performs load sharing between the N member links and sends the data packet to the second network device.
  • FIGS. 7-9 are schematic diagrams of another packet forwarding according to an embodiment of the present invention, showing an example in which a first network device communicates with a second network device by using the first and second link groups, including a first chain.
  • the path group is in the POK state, and the second link group is in the UP state.
  • the link group minimum active link number is set to 2.
  • the first link group member link 1 is in the UP state, and the member link 2 is in the POK state, the first link.
  • the member link in the UP state is less than 2, the first link group is in the POK state, the member links 1 and 2 in the second link group are in the UP state, and the second link group is in the UP state.
  • the first network device forwards the received data packet sequence after the load sharing between the first link group and the second link group, if more than one of the first link groups are in an available state or part
  • the member link of the available state may further load and share the data packet sequence entering the first link group between the member links in the available state or the partially available state, and then send the data packet sequence to the second network.
  • NE1 can load the data packet sequence that is load-balanced to the first link group and perform load sharing between member links 1 and 2 and send it to NE2. Similarly, if there are more than one member links in the available or partially available state within the second link group, then further access may be made between more than one member link in an available state or a partially available state.
  • the data packet sequence of the second link group is load-balanced and sent to the second network device. For example, in Figure 7, the data packet sequence that the NE1 can load to the second link group is on the member links 3 and 4. After load balancing is performed again, it is sent to NE2.
  • the first link group member links 1 and 2 are in the POK state, the member links in the UP state in the first link group are less than 2, the first link group is in the POK state, and the second link group is in the second link group.
  • the member links 1 and 2 are in the UP state, and the second link group is in the UP state.
  • the first network device performs load sharing between the first link group and the second link group, and further Load sharing is performed between member links 1 and 2 in the first link group, and load sharing is performed between member links 3 and 4 in the second link group.
  • the first link group member link 1 is in the POK state and the member link 2 is in the DOWN state.
  • the member link in the UP state in the first link group is less than 2, and the first link group is in the POK state.
  • the member links 1 and 2 are in the UP state, and the second link group is in the UP state.
  • the first network device loads between the first link group and the second link group. The load is forwarded by the member link 1 in the first link group, and the load sharing is further performed between the member links 3 and 4 in the second link group.
  • the first network device may also use more than two link groups to send the data message sequence to the second network device, and perform load sharing processing between more than two link groups with the above in the first and the The load balancing between the two link groups is similar.
  • the use of the member link in the UP state and the member link in the POK state are similar, and are not described here.
  • the first network device includes corresponding hardware structures and/or software modules for performing respective functions.
  • the present invention can be implemented in a combination of hardware or hardware and computer software in combination with the elements and method steps of the various examples described in the embodiments disclosed herein. Whether a function is implemented in hardware or computer software to drive hardware depends on the specific application and design constraints of the solution. A person skilled in the art can use different methods for implementing the described functions for each particular application, but such implementation should not be considered to be beyond the scope of the present invention.
  • FIG. 10 is a schematic structural diagram of an apparatus for forwarding a packet according to an embodiment of the present disclosure, where the apparatus is used to run a method for forwarding a packet in the scenario shown in FIG. 1-9.
  • the device for forwarding a message is applied to a first network device, where the first network device communicates with a second network device by using a first link group, where the device includes:
  • a receiving unit configured to receive a sequence of data packets to be forwarded
  • a determining unit configured to determine that the number of member links in the first link group that is in an available state is less than a minimum number of active links, and the first link group includes a first member link, the first member The link is partially available state;
  • a sending unit configured to send, by using the first link group, the data packet sequence to be forwarded to the second network device
  • the member link in the available state refers to a member link with a normal signal, and the first member link is in a partially available state, that is, the first member link generates a signal degradation SD.
  • the first link group further includes a second member link, where the second member link is in an available state, and the sending unit is specifically configured to load the data packet sequence to be forwarded to the The first member link and the second member link are forwarded to the second network device.
  • the first link group further includes a second member link, where the second member link is in a partially available state, and the sending unit is specifically configured to load balance the data packet sequence to be forwarded. Forwarding to the second member device to the first member link and the second member link.
  • the first link group further includes a second member link, where the second member link is in an unavailable state, and the sending unit is specifically configured to use the first member link to The forwarded data packet sequence is forwarded to the second network device; the second member link is in an unavailable state, indicating that the second member link generates a signal failure SF.
  • the first network device is further configured to communicate with the second network device by using a second link group, where the determining unit is further configured to determine a member link that is in an available state in the second link group. The number is greater than or equal to the minimum number of active links; the sending unit is further configured to forward the data packet sequence to be forwarded to the first link group and the second link group to be forwarded to the Second network device.
  • the first network device is further configured to communicate with the second network device by using a second link group, where the determining unit is further configured to determine a member link that is in an available state in the second link group. The number is smaller than the minimum number of active links, and the second link group includes a third member link, and the third member link is in a partially available state; the sending unit is further configured to use the to-be-forwarded Data packet sequence load sharing to the first link group and the second link group is forwarded to the second network device; the third member link is in a partially available state, and the third member chain is The road occurrence signal deteriorates SD.
  • the first network device is further configured to communicate with the second network device by using a second link group, where the determining unit is further configured to determine a member link that is in an available state in the second link group. The number is smaller than the minimum number of active links, and is greater than zero.
  • the sending unit is further configured to load the data packet sequence to be forwarded to the first link group and the second link group to be sent to The second network device.
  • FIG. 11 is a schematic structural diagram of an apparatus for forwarding a packet according to an embodiment of the present disclosure, where the apparatus is used to run a method for forwarding a packet in the scenario shown in FIG. 1-9.
  • the device for forwarding a message is applied to a first network device, where the first network device communicates with a second network device by using a first link group, where the device includes:
  • a memory for storing program instruction code
  • a processor configured to read a program instruction code in the memory, to control a method for the first network device to perform forwarding of the message in the scenario of FIG. 1-9;
  • a network interface configured to perform the operation and the sending operation in the method of forwarding a message in the scenario of FIG. 1-9 under the control of the processor;
  • the first network device and the second network device may be various types of network devices with forwarding functions, such as routers, switches, and the like.
  • the processor can be, for example, a central processing unit (CPU), A digital signal processor (DSP) or the like
  • the memory may be a random access memory (RAM), a read-only memory (ROM), an erasable programmable read only memory ( Erasable programmable ROM (EPROM), compact disc ROM (CD-ROM), hard disk, etc.
  • the network interface can be, for example, fiber distributed data interface (FDDI), gigabit ethernet (gigabit ethernet) , GE) interface, etc.
  • FDDI fiber distributed data interface
  • gigabit ethernet gigabit ethernet
  • GE gigabit ethernet
  • the processor can read the program instruction code in the memory, control the first network device, and perform the method of forwarding the message in the scenario of FIG. 1-9.
  • the processor may be further configured to: send a detection packet, such as an OAM packet, to the second network device to perform error detection, and determine that the member link of the first network device to the second network device is located.
  • a detection packet such as an OAM packet
  • the state is, for example, in a signal degradation SD state, a signal failure SF state, or the like.
  • the apparatus shown in FIG. 11 can also be used to implement the apparatus for forwarding a message as shown in the scenario of FIG. 10, and the network interface can be used to implement the receiving unit and the sending unit shown in the scenario of FIG. Means for implementing the determining unit in the scenario of FIG. 10, thereby implementing the forwarding of the message shown in the scenario of FIG.
  • the device for forwarding a message provided by the foregoing embodiment is only illustrated by the division of each functional unit.
  • the function allocation may be performed by different functional units as needed, that is, the internal structure of the device is divided into different Functional unit to perform all or part of the functions described above.
  • traffic forwarding method and apparatus described in connection with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the solution. Different methods may be used to implement the described functionality for each particular application, but such implementation should not be considered to be beyond the scope of the present invention.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Computer Security & Cryptography (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

本申请涉及通信技术领域，尤其涉及一种转发报文的方法及装置。在一种转发报文的方法中，第一网络设备接收待转发的数据报文序列，确定转发链路组中处于可用状态的成员链路数小于最小激活链路数，且链路组中包括发生信号劣化SD的处于部分可用状态的的成员链路，第一网络设备经由所述链路组发送待转发的数据报文序列。通过本申请提供的方案，在链路组中处于可用状态的成员链路数不足时，利用发生信号劣化SD的处于部分可用状态的成员链路，避免链路组停用，在面对对误码率要求不苛刻的通信业务时，可以减少流量中断，进一步提升网络资源利用率和网络带宽。

Description

一种转发报文的方法及装置
本申请要求于2016年8月30日提交中国专利局、申请号为201610776997.9、申请名称为“一种转发报文的方法及装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及涉及通信技术领域，尤其涉及一种转发报文的方法及装置。
背景技术
负载分担就是一种建立在现有网络结构之上，通过某种特定算法对报文进行基于链路或接口的动态均衡分发，以便扩展网络设备和服务器的带宽、增加吞吐量。最小激活链路(min active links)是针对负载分担场景而提出的概念，目的是为了保证流量正常转发的最小带宽。现网中当下游用户逐步增多时，会同时使用多条链路，运用负载分担技术来拓展带宽，对于运营商而言，为了满足下游用户的正常的流量需求，那么就需要在负载分担技术中加入最小激活链路来保证，当不满足最小激活链路数目时，需要进行倒换。
现有数据转发中，为确保数据报文交换的准确性，通常会进行链路检测。当通信设备在检测中发现通信链路发生信号异常时，停止使用该通信链路，进而导致负载分担中可用链路数小于最小激活链路数，在没有多余链路进行进行倒换时，无法继续进行负载分担转发，导致流量中断。
发明内容
有鉴于此，本发明实施例提供了一种转发报文的方法及装置，有助于减少流量中断。
本发明实施例提供的技术方案如下：
第一方面，提供了一种转发报文的方法。该方法应用于第一网络设备，该第一网络设备经由第一链路组与第二网络设备通信。该方法包括：
所述第一网络设备接收待转发的数据报文序列；
所述第一网络设备确定所述第一链路组中处于可用状态的成员链路数小于最小激活链路数，且所述第一链路组中包括第一成员链路，所述第一成员链路处于部分可用状态；
所述第一网络设备经由所述第一链路组向所述第二网络设备发送所述待转发的数据报文序列；
所述处于可用状态的成员链路是指信号正常的成员链路，所述第一成员链路处于部分可用状态是指所述第一成员链路发生信号劣化(signal degrade，SD)。
通过上述方案，在链路组中处于可用状态的成员链路数不足时，利用发生信号劣化SD的处于部分可用状态的成员链路，避免链路组停用。在面对对误码率要求不苛刻的通信业务时，可以减少流量中断，进一步提升网络资源利用率和网络带宽。
可选的，所述第一链路组还包括第二成员链路，所述第二成员链路处于可用状态，所述第一网络设备经由所述第一链路组向所述第二网络设备发送所述待转发的数据报文序列包括：所述第一网络设备将所述待转发的数据报文序列负载分担到所述第一成员链路和所述第二成员链路发送到所述第二网络设备。由此，进一步将流量在处于可用状态的成员链路和处于部分可用状态的成员链路之间进行负载分担，进一步提高了网络资源利用率。
可选的，所述第一链路组还包括第二成员链路，所述第二成员链路处于部分可用状态，所述第一网络设备经由所述第一链路组向所述第二网络设备发送所述待转发的数据报文序列包括：所述第一网络设备将所述待转发的数据报文序列负载分担到所述第一成员链路和所述第二成员链路发送到所述第二网络设备。由此，通过将流量在多条处于部分可用状态的成员链路之间进行负载分担，进一步提高了网络资源利用率。
可选的，所述第一链路组还包括第二成员链路，所述第二成员链路处于不可用状态，所述第一网络设备经由所述第一链路组向所述第二网络设备发送所述待转发的数据报文序列包括：所述第一网络设备使用所述第一成员链路将所述待转发的数据报文序列发送到所述第二网络设备；所述第二成员链路处于不可用状态是指所述第二成员链路发生信号故障(signal failure，SF)。由此，通过使用处于部分可用状态的成员链路，减少流量中断，提高可靠性和网络资源利用率。
可选的，所述第一网络设备还经由第二链路组与所述第二网络设备通信，所述方法还包括：所述第一网络设备确定所述第二链路组中处于可用状态的成员链路数大于或等于最小激活链路数；所述第一网络设备将所述待转发的数据报文序列负载分担到所述第一链路组和所述第二链路组发送到所述第二网络设备。由此，通过在处于可用状态的成员链路数不足的链路组与处于可用状态的成员链路数充足的链路组之间进行负载分担，进一步增加可用的网络带宽和网络资源利用率。
可选的，所述第一网络设备还经由第二链路组与所述第二网络设备通信，所述方法还包括：所述第一网络设备确定所述第二链路组中处于可用状态的成员链路数小于最小激活链路数，且所述第二链路组中包括第三成员链路，所述第三成员链路处于部分可用状态；所述第一网络设备将所述待转发的数据报文序列负载分担到所述第一链路组和所述第二链路组发送到所述第二网络设备；所述第三成员链路处于部分可用状态是指所述第三成员链路发生信号劣化SD。由此，通过在两个处于可用状态的成员链路数不足的链路组之间进行负载分担，减少流量中断，还进一步增加网络带宽和网络资源利用率。
可选的，所述第一网络设备还经由第二链路组与所述第二网络设备通信，所述方法还包括：所述第一网络设备确定所述第二链路组中处于可用状态的成员链路数小于最小激活链路数，且大于零；所述第一网络设备将所述待转发的数据报文序列负载分担到所述第一链路组和所述第二链路组发送到所述第二网络设备。由此，通过在两个处于可用状态的成员链路数不足的链路组之间进行负载分担，减少流量中断，还进一 步增加网络带宽和网络资源利用率。
第二方面，提供了一种转发报文的装置。该装置应用于第一网络设备，该第一网络设备经由第一链路组与第二网络设备通信。该装置包括接收单元、确定单元和发送单元。所述接收单元，用于接收待转发的数据报文序列；所述确定单元，用于确定所述第一链路组中处于可用状态的成员链路数小于最小激活链路数，且所述第一链路组中包括第一成员链路，所述第一成员链路处于部分可用状态；所述发送单元，用于经由所述第一链路组向所述第二网络设备发送所述待转发的数据报文序列；所述处于可用状态的成员链路是指信号正常的成员链路，所述第一成员链路处于部分可用状态是指所述第一成员链路发生信号劣化SD。
可选的，所述第一链路组还包括第二成员链路，所述第二成员链路处于可用状态，所述发送单元具体用于将所述待转发的数据报文序列负载分担到所述第一成员链路和所述第二成员链路发送到所述第二网络设备。
可选的，所述第一链路组还包括第二成员链路，所述第二成员链路处于部分可用状态，所述发送单元具体用于将所述待转发的数据报文序列负载分担到所述第一成员链路和所述第二成员链路发送到所述第二网络设备。
可选的，所述第一链路组还包括第二成员链路，所述第二成员链路处于不可用状态，所述发送单元具体用于使用所述第一成员链路将所述待转发的数据报文序列发送到所述第二网络设备；所述第二成员链路处于不可用状态是指所述第二成员链路发生信号故障SF。
可选的，所述第一网络设备还经由第二链路组与所述第二网络设备通信，所述确定单元，还用于确定所述第二链路组中处于可用状态的成员链路数大于或等于最小激活链路数；所述发送单元，还用于将所述待转发的数据报文序列负载分担到所述第一链路组和所述第二链路组发送到所述第二网络设备。
可选的，所述第一网络设备还经由第二链路组与所述第二网络设备通信，所述确定单元，还用于确定所述第二链路组中处于可用状态的成员链路数小于最小激活链路数，且所述第二链路组中包括第三成员链路，所述第三成员链路处于部分可用状态；所述发送单元，还用于将所述待转发的数据报文序列负载分担到所述第一链路组和所述第二链路组发送到所述第二网络设备；所述第三成员链路处于部分可用状态是指所述第三成员链路发生信号劣化SD。
可选的，所述第一网络设备还经由第二链路组与所述第二网络设备通信，所述确定单元，还用于确定所述第二链路组中处于可用状态的成员链路数小于最小激活链路数，且大于零；所述发送单元，还用于将所述待转发的数据报文序列负载分担到所述第一链路组和所述第二链路组发送到所述第二网络设备。
第二方面的上述方案与第一方面描述内容中使用相同手段的对应方案具有相同的技术效果。
第三方面，提供了一种转发报文的装置，应用于第一网络设备，该第一网络设备经由第一链路组与第二网络设备通信，该装置包括处理器、网络接口和存储器。所述存储器，用于存储程序指令代码。所述处理器，用于读取存储器中的程序指令代码，控制所述第一网络设备执行第一方面提供的转发报文的方法。所述网络接口，用于在 处理器控制下，执行第一方面提供的转发报文的方法中所述接收的操作和所述发送的操作。
第三方面的上述方案与第一方面描述内容中使用相同手段的对应方案具有相同的技术效果。
附图说明
图1为本发明的一种可能的应用场景示意图；
图2为本发明的另一种可能的应用场景示意图；
图3为本发明实施例提供的一种报文转发示意图；
图4为本发明实施例提供的另一种报文转发示意图；
图5为本发明实施例提供的另一种报文转发示意图；
图6为本发明实施例提供的一种转发报文的方法流程图；
图7为本发明实施例提供的另一种报文转发示意图；
图8为本发明实施例提供的另一种报文转发示意图；
图9为本发明实施例提供的另一种报文转发示意图；
图10为本发明实施例提供的一种转发报文的装置的结构示意图；
图11为本发明实施例提供的另一种转发报文的装置的结构示意图。
具体实施方式
为使本申请的目的、技术方案和优点更加清楚，下面将结合附图对本申请实施方式做出进一步地详细描述。对于本领域普通技术人员在没有付出创造性劳动的前提下所获得的其它所有实施例，都属于本申请保护的范围。
本申请实施例描述的应用场景是为了更加清楚的说明本申请实施例的技术方案，并不构成对于本申请实施例提供的技术方案的限定，本领域普通技术人员可知，随着网络架构的演变和新业务场景的出现，本申请实施例提供的技术方案对于类似的技术问题，同样适用。
本申请中，“网元”、“网络设备”、“转发设备”和“节点”经常交替使用，本领域技术人员可以知晓其通常含义。可选的，以上设备可以包括交换机、路由器、分组传送网设备等。本申请涉及到的通信链路可以是物理链路，如物理层面的光纤，也可以是逻辑链路，如逻辑层面的伪线、隧道中的任意一种或多种等，为方便描述，本申请中统称为通信链路或链路。
图1为本发明的一种可能的应用场景示意图。在该场景下网元(network element，NE)NE1可以分别经由多条通信链路中的每一条与网元NE2通信，也可以将该多条通信链路中的部分链路或全部链路组成一个链路组，使用该链路组进行通信。进一步可选的，在该链路组内的多条通信链路可以形成负载分担关系，网元NE1可以将该链路组做为负载分担组，通过该负载分担组向网元NE2发送数据报文序列。其中，组成链路组的每条通信链路可以做为该负载分担组的一个成员链路。网元NE1将收到的数据报文序列在负载分担组内的多个成员链路之间进行负载分担后发送到网元NE2。所述 负载分担组内可以采用各种能够实现负载分担机制的通信协议执行负载分担，例如等价多路径(equal-cost multipath，ECMP)或权重多路径(weight-cost multipath，WCMP)等。
图2为本发明的另一种可能的应用场景示意图。在该场景下NE1与NE2之间可以包括多个链路组，比如包括第一链路组、第二链路组。第一链路组可以包括一条或多条通信链路，NE1经由该第一链路组与NE2通信，向NE2发送数据报文序列。第一链路组包括多条通信链路时，进一步可选的该多条通信链路可以形成负载分担关系，第一链路组可以作为第一负载分担组使用。第一链路组内的多条通信链路中的每条都可以做为第一负载分担组中的一个成员链路。类似地，第二链路组也可以包括一条或多条通信链路，NE1也可以经由该第二链路组与NE2通信。进一步可选的第二链路组中的多条通信链路中的每条都可以做为第二负载分担组中的一个成员链路。当然，图2中还可以包括多于2个链路组并都作为负载分担组。同样可选的，每个负载分担组还可以包括多于2个成员链路。由于图2所示的场景中，NE1和NE2之间存在多个负载分担组，NE1可以将收到的数据报文在该多个负载分担组之间进行负载分担。可选的，NE1还可以进一步将分配到每个负载分担组的数据报文序列，在该负载分担组内再进行负载分担。比如，NE1可以将负载分担到第一负载分担组的数据报文序列，在第一负载分担组内的多个成员链路之间再次进行负载分担。
本发明实施例使用负载分担组内成员链路进行负载分担转发时，可以采用现有技术中的各种数据报文序列分配方式。例如逐流负载分担，该逐流负载分担将数据报文序列根据所属的流进行区分，同一条流的数据报文序列将通过同一条链路发送；又例如逐包负载分担，该逐包负载分担按数据报文序列到来的次序，将数据报文分摊到参与负载分担的各条链路上；还例如将相同目的地址的数据报文发送给同一个负载分担成员链路、将数据报文在多个负载分担成员链路间进行等比例分配、按照成员链路带宽比例将数据报文按比例在多个成员链路间分配等等。
图1和图2所示场景中，NE1在与NE2间进行数据转发的过程中，为确保数据报文交换的准确性，通常会进行通信链路上的误码检测。这种误码检测可以利用操作管理维护(operation admini stration and maintenance，OAM)报文等。当NE1发现到NE2的通信链路处于误码状态时，停止使用该通信链路。而当运营商或用户对链路组的流量有特定要求时，会设定最小激活链路数，由此当从NE1到NE2的通信链路组中的信号正常的链路数小于最小激活链路数要求时，将停用该链路组，进而导致流量中断。
误码检测中通信链路处于误码状态包括：信号劣化SD和信号故障SF。信号劣化SD和信号故障SF对应不同的误码率门限值，其中信号故障SF门限值要大于信号劣化SD门限值。误码检测中当链路上的误码率大于或等于信号劣化SD门限值，但小于信号故障SF门限值时，该链路处于信号劣化SD状态，当链路上的误码率大于或等于信号故障SF门限值时，该链路处于SF状态。
现有通信传输中不同的通信业务有着不同的服务质量要求(quality of service，QoS)，不同的服务质量要求QoS中也有着不同的误码率要求，实际上发生信号劣化SD的通信链路在对一些对误码率要求不苛刻的通信业务中仍然是可用的，例如语音、 图像、视频数据的传输中，可以容忍一定程度的误码。因此可以在通信业务的数据报文序列转发中对通信链路的误码状态进行区分，对发生信号劣化的这部分通信链路加以利用，以提升网络资源利用率，加大通信带宽。特别是在链路组具有最小激活链路数要求时，增加使用信号劣化的通信链路，将会增加链路组中能够使用的链路数，在面对对信号质量要求不高的通信业务时，在该链路组上尽力满足转发需求，减少链路组停用而导致的流量中断，实现尽力而为的转发。
为充分利用通信链路处于信号劣化SD状态的情况，本发明实施例定义链路组成员链路所处的状态包括：可用状态、部分可用状态、不可用状态，所述可用状态、部分可用状态、不可用状态可以分别用UP、POK、DOWN来表示。其中处于可用状态UP的成员链路是指信号正常的成员链路，处于部分可用状态POK的成员链路是指发生信号劣化SD的成员链路，处于不可用状态DOWN的成员链路是指通信信号无法满足质量要求的成员链路，例如发生信号故障SF的成员链路。
本发明实施例中链路组所处的状态可以包括：可用状态、部分可用状态、不可用状态，所述可用状态、部分可用状态、不可用状态可以分别用UP、POK、DOWN来表示。其中链路组处于可用状态是指链路组中处于可用状态的成员链路数大于或等于最小激活链路数；链路组处于部分可用状态是指链路组中处于可用状态的成员链路数小于最小激活链路数，且该链路组中包括处于可用状态或部分可用状态的成员链路；链路组处于不可用状态是指链路组中没有处于可用状态的成员链路，也没有处于部分可用状态的成员链路。
以上链路组内成员链路数量为任意数目，最小激活链路数可以是小于或等于链路组成员链路数量的任意数目，为便于描述，后续场景描述仅给出举例数目，本领域技术人员能够理解，其他数目的情况均落入本发明实施例的范围内。
图3为本发明实施例提供的一种报文转发示意图。假设NE1与NE2之间采用第一链路组进行通信，该第一链路组中包括成员链路1和成员链路2，假设该链路组的最小激活链路数为2。当成员链路1处于UP状态，成员链路2处于POK状态时，链路组内处于UP状态的成员链路数是1，小于最小激活链路数2，但存在处于POK状态的成员链路2，于是可以不停用该第一链路组，启用尽力而为的转发模式。这在对于对误码率要求不苛刻的通信业务中，可以提高链路资源利用率，加大链路带宽，也可以减少链路组停用导致的流量中断。在该尽力而为的转发模式下，尽力使用链路组内的处于UP状态的成员链路1和处于POK状态的成员链路2，将待发送的数据报文序列在成员链路1和成员链路2间进行负载分担转发，从而在该链路组上尽力满足转发需求，实现尽力而为的转发。
图4为本发明实施例提供的另一种报文转发示意图。假设NE1与NE2之间采用第一链路组进行通信，该第一链路组中包括成员链路1和成员链路2，假设该链路组的最小激活链路数为2。当成员链路1处于POK状态，成员链路2处于POK状态时，链路组内处于UP状态的成员链路数是0，小于最小激活链路数2，但存在处于POK状态的成员链路1和成员链路2，于是启用尽力而为的转发模式。在该尽力而为的转发模式下，尽力使用链路组内的处于POK状态的成员链路1和成员链路2，将待发送的数据报文序列在成员链路1和成员链路2间进行负载分担转发，实现尽力而为的转发。
图5为本发明实施例提供的另一种报文转发示意图。假设NE1与NE2之间采用第一链路组进行通信，该第一链路组中包括成员链路1和成员链路2，假设该链路组的最小激活链路数为2。当成员链路1处于POK状态，成员链路2处于DOWN状态时，链路组内处于UP状态的成员链路数是0，小于最小激活链路数2，但存在处于POK状态的成员链路1，于是启用尽力而为的转发模式。在该尽力而为的转发模式下，尽力使用链路组内的处于POK状态的成员链路1，将待发送的数据报文序列经由成员链路1进行转发，实现尽力而为的转发。
可选的，在尽力而为的转发中，链路组内处于UP状态的成员链路数小于最小激活链路数，且链路组内包括N条成员链路，N为大于或等于1的自然数，该N条成员链路中的每一条处于UP状态或POK状态，使用该N条成员链路的一条或多条成员链路传输数据报文序列，实现尽力而为的转发。如果N>1，则NE1可以将数据报文序列在N条成员链路之间进行负载分担后发送到NE2。
可选的，在尽力而为的转发中，链路组内不存在处于UP状态的成员链路数，且链路组内存在一条或多条处于POK状态的成员链路时，使用该一条或多条处于POK状态的成员链路中的一条或多条成员链路实现尽力而为的转发。在处于POK状态的成员链路为多条时，则NE1可以将数据报文序列在该多条处于POK状态的成员链路之间进行负载分担后发送到NE2。
图6为本发明实施例提供的一种转发报文的方法流程图，该方法应用于第一网络设备，该第一网络设备是各类报文转发设备例如路由器、交换机等，该第一网络设备经由第一链路组与第二网络设备通信。该方法可以适用于如图1、2所述场景，该第一网络设备可以是图1、2中的NE1，该第二网络设备可以是图1、2中的NE2。该方法可以实现如图3至图5所述的转发。该方法具体包括：
操作601、所述第一网络设备接收待转发的数据报文序列。
所述第一网络设备从所述第一网络设备的上游网络设备接收待转发的数据报文序列。
操作602、所述第一网络设备确定所述第一链路组中处于可用状态的成员链路数小于最小激活链路数，且所述第一链路组中包括第一成员链路，所述第一成员链路处于部分可用状态。
所述第一网络设备确定所述第一链路组中处于可用状态的成员链路数量，并与所述第一链路组的最小激活链路数进行比较。该最小激活链路数可以由用户、运营商或设备商等基于流量带宽等需要来进行指定。
当处于可用状态的成员链路数大于最小激活链路数时，第一网络设备选用任意大于或等于最小激活链路数的数量的可用成员链路来执行负载分担转发；当处于可用状态的成员链路数等于最小激活链路数时，第一网络设备选用全部可用成员链路来执行负载分担转发；当处于可用状态的成员链路数小于最小激活链路数时，确定该第一链路组中仍存在处于部分可用状态的成员链路，例如存在处于部分可用状态的第一成员链路，属于仍然可以利用该链路组的情况，从而并不停止使用该链路组，而是在下一步继续使用该链路组进行转发。
操作603、所述第一网络设备经由所述第一链路组向所述第二网络设备发送所述 待转发的数据报文序列。
所述第一网络设备在操作602后确定所述第一链路组内处于可用状态的成员链路数小于最小激活链路数，且第一链路组中还存在处于部分可用状态的成员链路例如第一成员链路后，在操作603中第一网络设备使用该链路组向第二网络设备进行数据报文序列的转发。
可选的，所述第一链路组还包括第二成员链路，第二链路处于UP状态，在操作603中，第一网络设备将数据报文序列在第一成员链路和第二成员链路间进行负载负担从而转发到第二网络设备。
可选的，所述第一链路组还可以包括N个成员链路，N为大于或等于1的自然数，该N个成员链路中的每一个都处于POK状态或UP状态，第一网络设备可以将收到的数据报文序列在所述第一成员链路及该N个成员链路负载分担后转发到所述第二网络设备。
可选的，所述第一链路组还包括第二成员链路，第二成员链路处于POK状态，在操作603中，第一网络设备将数据报文序列在第一成员链路和第二成员链路间进行负载负担从而转发到第二网络设备。
可选的，在第一链路组包括多个处于POK状态的成员链路时，在多个处于POK状态的成员链路间进行负载分担，该多个处于POK状态的成员链路包括所述第一成员链路。
可选的，所述第一链路组还包括第二成员链路，第二链路处于DOWN状态，在操作603中，第一网络设备将数据报文序列经由该第一成员链路转发到第二网络设备。
可选的，在第一链路组还可以包括N个成员链路，N为大于或等于1的自然数，该N个成员链路中的每一个都处于POK状态或DOWN状态，在第一链路组中除第一成员链路外，不包含其他处于POK状态的成员链路时，第一网络设备通过第一成员链路发送数据报文序列；在第一链路组中包含多个处于POK状态的成员链路时，在多个处于POK状态的成员链路间进行负载分担，该多个处于POK状态的成员链路包括所述第一成员链路。
可选的，所述第一网络设备还经由第二链路组与所述第二网络设备通信。所述第二链路组处于可用状态或部分可用状态，第一网络设备在操作603中将数据报文序列在第一链路组和第二链路组间进行负载负担从而转发到第二网络设备。具体来说，当第二链路组处于可用状态或部分可用状态时，第二链路组包括N个成员链路，N为大于或等于1的自然数，该N个成员链路中的每一个都处于UP状态或POK状态，当N等于1时，第一网络设备将负载分担到第二链路组的数据报文序列经该1个成员链路发送到所述第二网络设备，当N大于1时，第一网络设备将负载分担到第二链路组的数据报文序列，在该N个成员链路间再次负载分担后发送到所述第二网络设备。
图7-9是本发明实施例提供的另一种报文转发示意图，给出了第一网络设备使用第一和第二链路组与第二网络设备进行通信的示例，其中包括第一链路组处于POK状态，第二链路组处于UP状态下的三种情况，这几个示例中链路组最小激活链路数均设定为2。
图7中第一链路组成员链路1处于UP状态、成员链路2处于POK状态，第一链路 组内处于UP状态的成员链路小于2，第一链路组处于POK状态，第二链路组内成员链路1、2均处于UP状态，第二链路组处于UP状态。第一网络设备在将收到的数据报文序列在第一链路组和第二链路组之间负载分担后转发时，如果第一链路组内有多于1条处于可用状态或者部分可用状态的成员链路，则可以在多于1条处于可用状态或者部分可用状态的成员链路之间进一步对进入该第一链路组的数据报文序列进行负载分担后发送到第二网络设备，比如图7中，NE1可以将负载分担到第一链路组的数据报文序列在成员链路1和2之间再次进行负载分担后发送到NE2。类似地，如果第二链路组内有多于1条处于可用状态或者部分可用状态的成员链路，则可以在多于1条处于可用状态或者部分可用状态的成员链路之间进一步对进入该第二链路组的数据报文序列进行负载分担后发送到第二网络设备，比如图7中，NE1可以将负载分担到第二链路组的数据报文序列在成员链路3和4之间再次进行负载分担后发送到NE2。
图8中第一链路组成员链路1、2均处于POK状态，第一链路组内处于UP状态的成员链路小于2，第一链路组处于POK状态，第二链路组内成员链路1和2均处于UP状态，第二链路组处于UP状态，在该情况下，第一网络设备在第一链路组和第二链路组之间进行负载分担，且进一步在第一链路组内的成员链路1和2间进行负载分担，以及在第二链路组内成员链路3和4间进行负载分担。
图9中第一链路组成员链路1处于POK状态、成员链路2处于DOWN状态，第一链路组内处于UP状态的成员链路小于2，第一链路组处于POK状态，第二链路组内成员链路1和2均处于UP状态，第二链路组处于UP状态，在该情况下，第一网络设备在第一链路组和第二链路组之间进行负载分担，在第一链路组内经成员链路1转发，进一步在第二链路组内的成员链路3和4间进行负载分担。
当然，第一网络设备还可以使用多于2个链路组来将数据报文序列发送到第二网络设备，在多于2个链路组间进行负载分担的处理与以上在第一和第二两个链路组间进行负载分担的处理类似，对链路组内处于UP状态的成员链路和处于POK状态的成员链路的使用也类似，这里不再赘述。
上述内容主要从第一网络设备接收数据报文序列并利用成员链路向第二网络设备进行转发的角度对本发明实施例提供的方案进行了介绍。可以理解的是，为了实现上述功能，所述第一网络设备包含了执行各个功能相应的硬件结构和/或软件模块。本领域技术人员应该很容易意识到，结合本文中所公开的实施例描述的各示例的单元及方法步骤，本发明能够以硬件或硬件和计算机软件的结合形式来实现。某个功能究竟以硬件还是计算机软件驱动硬件的方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本发明的范围。
图10为本发明实施例提供的一种的转发报文的装置结构示意图，该装置用于运行如图1-9场景中的转发报文的方法。所述转发报文的装置应用于第一网络设备，该第一网络设备经由第一链路组与第二网络设备通信，该装置包括：
接收单元，用于接收待转发的数据报文序列；
确定单元，用于确定所述第一链路组中处于可用状态的成员链路数小于最小激活链路数，且所述第一链路组中包括第一成员链路，所述第一成员链路处于部分可用状 态；
发送单元，用于经由所述第一链路组向所述第二网络设备发送所述待转发的数据报文序列；
所述处于可用状态的成员链路是指信号正常的成员链路，所述第一成员链路处于部分可用状态是指所述第一成员链路发生信号劣化SD。
可选的，所述第一链路组还包括第二成员链路，所述第二成员链路处于可用状态，所述发送单元具体用于将所述待转发的数据报文序列负载分担到所述第一成员链路和所述第二成员链路转发到所述第二网络设备。
可选的，所述第一链路组还包括第二成员链路，所述第二成员链路处于部分可用状态，所述发送单元具体用于将所述待转发的数据报文序列负载分担到所述第一成员链路和所述第二成员链路转发到所述第二网络设备。
可选的，所述第一链路组还包括第二成员链路，所述第二成员链路处于不可用状态，所述发送单元具体用于使用所述第一成员链路将所述待转发的数据报文序列转发到所述第二网络设备；所述第二成员链路处于不可用状态是指所述第二成员链路发生信号故障SF。
可选的，所述第一网络设备还经由第二链路组与所述第二网络设备通信，所述确定单元，还用于确定所述第二链路组中处于可用状态的成员链路数大于或等于最小激活链路数；所述发送单元，还用于将所述待转发的数据报文序列负载分担到所述第一链路组和所述第二链路组转发到所述第二网络设备。
可选的，所述第一网络设备还经由第二链路组与所述第二网络设备通信，所述确定单元，还用于确定所述第二链路组中处于可用状态的成员链路数小于最小激活链路数，且所述第二链路组中包括第三成员链路，所述第三成员链路处于部分可用状态；所述发送单元，还用于将所述待转发的数据报文序列负载分担到所述第一链路组和所述第二链路组转发到所述第二网络设备；所述第三成员链路处于部分可用状态是指所述第三成员链路发生信号劣化SD。
可选的，所述第一网络设备还经由第二链路组与所述第二网络设备通信，所述确定单元，还用于确定所述第二链路组中处于可用状态的成员链路数小于最小激活链路数，且大于零；所述发送单元，还用于将所述待转发的数据报文序列负载分担到所述第一链路组和所述第二链路组发送到所述第二网络设备。
图11为本发明实施例提供的一种的转发报文的装置结构示意图，该装置用于运行如图1-9场景中的转发报文的方法。所述转发报文的装置应用于第一网络设备，该第一网络设备经由第一链路组与第二网络设备通信，该装置包括：
存储器，用于存储程序指令代码；
处理器，用于读取存储器中的程序指令代码，控制第一网络设备执行如图1-9场景中的转发报文的方法；
网络接口，用于在处理器控制下，执行如图1-9场景中的转发报文的方法中所述接收的操作和所述发送的操作；
所述第一网络设备和第二网络设备可以是具有转发功能的各类网络设备，例如路由器、交换机等。处理器可以是例如中央处理器(central processing unit，CPU)、 数字信号处理器(digital signal processor，DSP)等，存储器可以是随机存取存储器(random-access memory，RAM)、只读存储器(read-only memory，ROM)、可擦除可编程只读存储器(erasable programmable ROM，EPROM)、光盘只读存储器(compact disc ROM，CD-ROM)、硬盘等，网络接口可以是例如光纤分布式数据接口(fiber distributed data interface，FDDI)，千兆以太网(gigabit ethernet，GE)接口等。
所述处理器可以读取存储器中的程序指令代码，控制第一网络设备，执行如图1-9场景中的转发报文的方法。
可选地，所述处理器还可以用于控制网络接口向第二网络设备发送检测报文例如OAM报文等进行误码检测，确定第一网络设备到第二网络设备的成员链路所处的状态，例如处于信号劣化SD状态、信号故障SF状态等。
图11所述装置也可以用于实现如图10场景中所示的转发报文的装置，所述网络接口可以用于实现图10场景中所示的接收单元和发送单元，所述处理器可以用于实现图10场景中的确定单元，由此实现图10场景中所示的转发报文的装置。
上述实施例提供的转发报文的装置，仅以上述各功能单元的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能单元完成，即将设备的内部结构划分成不同的功能单元，以完成以上描述的全部或者部分功能。
本说明书中的各个实施例均采用递进的方式描述，各个实施例之间相同相似的部分互相参见即可，每个实施例重点说明的都是与其他实施例的不同之处。尤其，对于系统实施例而言，由于其基本相似于方法实施例，所以描述的比较简单，相关之处参见方法实施例的部分说明即可。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的流量转发方法和设备，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。本领域的普通技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本发明的范围。

Claims (15)

  1. 一种转发报文的方法，应用于第一网络设备，该第一网络设备经由第一链路组与第二网络设备通信，其特征在于，该方法包括：
    所述第一网络设备接收待转发的数据报文序列；
    所述第一网络设备确定所述第一链路组中处于可用状态的成员链路数小于最小激活链路数，且所述第一链路组中包括第一成员链路，所述第一成员链路处于部分可用状态；
    所述第一网络设备经由所述第一链路组向所述第二网络设备发送所述待转发的数据报文序列；
    所述处于可用状态的成员链路是指信号正常的成员链路，所述第一成员链路处于部分可用状态是指所述第一成员链路发生信号劣化SD。
  2. 如权利要求1所述的方法，其特征在于，所述第一链路组还包括第二成员链路，所述第二成员链路处于可用状态，所述第一网络设备经由所述第一链路组向所述第二网络设备发送所述待转发的数据报文序列包括：
    所述第一网络设备将所述待转发的数据报文序列负载分担到所述第一成员链路和所述第二成员链路发送到所述第二网络设备。
  3. 如权利要求1所述的方法，其特征在于，所述第一链路组还包括第二成员链路，所述第二成员链路处于部分可用状态，所述第一网络设备经由所述第一链路组向所述第二网络设备发送所述待转发的数据报文序列包括：
    所述第一网络设备将所述待转发的数据报文序列负载分担到所述第一成员链路和所述第二成员链路发送到所述第二网络设备。
  4. 如权利要求1所述的方法，其特征在于，所述第一链路组还包括第二成员链路，所述第二成员链路处于不可用状态，所述第一网络设备经由所述第一链路组向所述第二网络设备发送所述待转发的数据报文序列包括：
    所述第一网络设备使用所述第一成员链路将所述待转发的数据报文序列发送到所述第二网络设备；
    所述第二成员链路处于不可用状态是指所述第二成员链路发生信号故障SF。
  5. 如权利要求1-4任意一项所述的方法，其特征在于，所述第一网络设备还经由第二链路组与所述第二网络设备通信，所述方法还包括：
    所述第一网络设备确定所述第二链路组中处于可用状态的成员链路数大于或等于最小激活链路数；
    所述第一网络设备将所述待转发的数据报文序列负载分担到所述第一链路组和所述第二链路组发送到所述第二网络设备。
  6. 如权利要求1-4任意一项所述的方法，其特征在于，所述第一网络设备还经由 第二链路组与所述第二网络设备通信，所述方法还包括：
    所述第一网络设备确定所述第二链路组中处于可用状态的成员链路数小于最小激活链路数，且所述第二链路组中包括第三成员链路，所述第三成员链路处于部分可用状态；
    所述第一网络设备将所述待转发的数据报文序列负载分担到所述第一链路组和所述第二链路组发送到所述第二网络设备；
    所述第三成员链路处于部分可用状态是指所述第三成员链路发生信号劣化SD。
  7. 如权利要求1-4任意一项所述的方法，其特征在于，所述第一网络设备还经由第二链路组与所述第二网络设备通信，所述方法还包括：
    所述第一网络设备确定所述第二链路组中处于可用状态的成员链路数小于最小激活链路数，且大于零；
    所述第一网络设备将所述待转发的数据报文序列负载分担到所述第一链路组和所述第二链路组发送到所述第二网络设备。
  8. 一种转发报文的装置，应用于第一网络设备，该第一网络设备经由第一链路组与第二网络设备通信，其特征在于，该装置包括：
    接收单元，用于接收待转发的数据报文序列；
    确定单元，用于确定所述第一链路组中处于可用状态的成员链路数小于最小激活链路数，且所述第一链路组中包括第一成员链路，所述第一成员链路处于部分可用状态；
    发送单元，用于经由所述第一链路组向所述第二网络设备发送所述待转发的数据报文序列；
    所述处于可用状态的成员链路是指信号正常的成员链路，所述第一成员链路处于部分可用状态是指所述第一成员链路发生信号劣化SD。
  9. 如权利要求8所述的装置，其特征在于，所述第一链路组还包括第二成员链路，所述第二成员链路处于可用状态，所述发送单元具体用于将所述待转发的数据报文序列负载分担到所述第一成员链路和所述第二成员链路发送到所述第二网络设备。
  10. 如权利要求8所述的装置，其特征在于，所述第一链路组还包括第二成员链路，所述第二成员链路处于部分可用状态，所述发送单元具体用于将所述待转发的数据报文序列负载分担到所述第一成员链路和所述第二成员链路发送到所述第二网络设备。
  11. 如权利要求8所述的装置，其特征在于，所述第一链路组还包括第二成员链路，所述第二成员链路处于不可用状态，所述发送单元具体用于使用所述第一成员链路将所述待转发的数据报文序列发送到所述第二网络设备；
    所述第二成员链路处于不可用状态是指所述第二成员链路发生信号故障SF。
  12. 如权利要求8-11任意一项所述的装置，其特征在于，所述第一网络设备还经由第二链路组与所述第二网络设备通信，
    所述确定单元，还用于确定所述第二链路组中处于可用状态的成员链路数大于或等于最小激活链路数；
    所述发送单元，还用于将所述待转发的数据报文序列负载分担到所述第一链路组和所述第二链路组发送到所述第二网络设备。
  13. 如权利要求8-11任意一项所述的装置，其特征在于，所述第一网络设备还经由第二链路组与所述第二网络设备通信，
    所述确定单元，还用于确定所述第二链路组中处于可用状态的成员链路数小于最小激活链路数，且所述第二链路组中包括第三成员链路，所述第三成员链路处于部分可用状态；
    所述发送单元，还用于将所述待转发的数据报文序列负载分担到所述第一链路组和所述第二链路组发送到所述第二网络设备；
    所述第三成员链路处于部分可用状态是指所述第三成员链路发生信号劣化SD。
  14. 如权利要求8-11任意一项所述的装置，其特征在于，所述第一网络设备还经由第二链路组与所述第二网络设备通信，
    所述确定单元，还用于确定所述第二链路组中处于可用状态的成员链路数小于最小激活链路数，且大于零；
    所述发送单元，还用于将所述待转发的数据报文序列负载分担到所述第一链路组和所述第二链路组发送到所述第二网络设备。
  15. 一种转发报文的装置，应用于第一网络设备，该第一网络设备经由第一链路组与第二网络设备通信，其特征在于，该装置包括：
    存储器，用于存储程序指令代码；
    处理器，用于读取所述存储器中的程序指令代码，控制所述第一网络设备执行权利要求1-7中任意一项所述的转发报文方法。
PCT/CN2017/097679 2016-08-30 2017-08-16 一种转发报文的方法及装置 WO2018040916A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610776997.9A CN106302215A (zh) 2016-08-30 2016-08-30 一种转发报文的方法及装置
CN201610776997.9 2016-08-30

Publications (1)

Publication Number Publication Date
WO2018040916A1 true WO2018040916A1 (zh) 2018-03-08

Family

ID=57672579

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/097679 WO2018040916A1 (zh) 2016-08-30 2017-08-16 一种转发报文的方法及装置

Country Status (2)

Country Link
CN (1) CN106302215A (zh)
WO (1) WO2018040916A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106302215A (zh) * 2016-08-30 2017-01-04 华为技术有限公司 一种转发报文的方法及装置
WO2023145006A1 (ja) * 2022-01-28 2023-08-03 日本電信電話株式会社 無線装置及び無線通信方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101854396A (zh) * 2010-05-31 2010-10-06 中兴通讯股份有限公司 Mlppp组带宽容量的处理方法和装置
US20110194562A1 (en) * 2010-02-10 2011-08-11 Fujitsu Network Communications, Inc. Systems and Methods for Communication of Management Traffic Over Link Aggregation Group Interface for a Network Element with Distributed Architecture
CN102364892A (zh) * 2011-10-12 2012-02-29 华为技术有限公司 一种lacp链路切换、数据传输方法与装置
CN102882805A (zh) * 2012-09-24 2013-01-16 华为技术有限公司 避免链路聚合组状态震荡的方法及装置
CN106302215A (zh) * 2016-08-30 2017-01-04 华为技术有限公司 一种转发报文的方法及装置

Family Cites Families (27)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
MY140438A (en) * 2003-06-04 2009-12-31 Basf Ag Preparation of catalytically active multielement oxide materials which contain at least one of the elements nb and w and the elements mo, v and cu
US7542761B2 (en) * 2004-10-06 2009-06-02 At&T Mobility Ii Llc Voice quality on a communication link based on customer feedback
CN100542137C (zh) * 2006-06-09 2009-09-16 华为技术有限公司 移动ip快速切换系统及快速切换方法
CN101048012A (zh) * 2006-06-22 2007-10-03 华为技术有限公司 一种在无线网状网络中确定路由的方法
CN101512978B (zh) * 2006-07-04 2013-02-13 夏普株式会社 通信装置、设备、通信装置控制方法
JP4904994B2 (ja) * 2006-08-25 2012-03-28 富士通東芝モバイルコミュニケーションズ株式会社 移動無線端末装置
CN100555997C (zh) * 2007-01-31 2009-10-28 华为技术有限公司 异步传输模式反向复用组重新激活的方法、系统和装置
JP4835499B2 (ja) * 2007-04-18 2011-12-14 株式会社日立製作所 異システム間ハンドオフ方法および無線通信端末
CN101369962B (zh) * 2007-08-13 2011-06-08 华为技术有限公司 转发报文的方法和网络设备
CN101299716B (zh) * 2008-04-25 2011-04-06 华为技术有限公司 业务数据发送的方法、装置及系统
CN101621347B (zh) * 2008-06-30 2013-01-30 华为技术有限公司 倒换处理方法及装置
CN101345675B (zh) * 2008-08-15 2011-02-09 哈尔滨工业大学 一种协同通信中的中继节点选择方法
CN101707788B (zh) * 2009-10-27 2014-04-02 北京邮电大学 基于差异化定价策略的多层网络业务动态规划方法
CN102387559B (zh) * 2010-09-03 2015-06-03 中兴通讯股份有限公司 无线Mesh网络的跨层路由优化的方法及装置
US8798077B2 (en) * 2010-12-29 2014-08-05 Juniper Networks, Inc. Methods and apparatus for standard protocol validation mechanisms deployed over a switch fabric system
CN103947166A (zh) * 2011-11-16 2014-07-23 瑞典爱立信有限公司 条件路由技术
CN102638407B (zh) * 2012-04-17 2014-10-29 北京星网锐捷网络技术有限公司 报文转发方法、装置及网络设备
CN103023804B (zh) * 2012-12-18 2015-08-19 北京星网锐捷网络技术有限公司 一种聚合链路自适应流量负载均衡方法、装置及网络设备
CN104010332B (zh) * 2013-02-21 2019-03-15 中兴通讯股份有限公司 承载绑定方法及系统
CN104113488A (zh) * 2013-04-16 2014-10-22 中兴通讯股份有限公司 接口切换方法和装置
US20140369329A1 (en) * 2013-06-18 2014-12-18 Qualcomm Incorporated Lte and external wifi bandwidth aggregation
CN103428101A (zh) * 2013-08-01 2013-12-04 华为技术有限公司 负载分担的方法和装置
CN103441945B (zh) * 2013-08-30 2016-08-24 华为技术有限公司 一种控制链路负载的方法、设备及数据转发设备
JP6295137B2 (ja) * 2014-04-28 2018-03-14 ＡＰＲＥＳＩＡ Ｓｙｓｔｅｍｓ株式会社 中継システムおよびスイッチ装置
CN105281926B (zh) * 2014-05-27 2019-03-12 中兴通讯股份有限公司 一种链路聚合端口的信号劣化触发保护切换的方法及装置
CN105471736B (zh) * 2014-09-02 2020-09-11 中兴通讯股份有限公司 一种隧道信号劣化通知及切换方法、装置
CN105049150B (zh) * 2015-06-26 2018-09-25 大唐移动通信设备有限公司 一种自适应速率的信号处理方法和装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110194562A1 (en) * 2010-02-10 2011-08-11 Fujitsu Network Communications, Inc. Systems and Methods for Communication of Management Traffic Over Link Aggregation Group Interface for a Network Element with Distributed Architecture
CN101854396A (zh) * 2010-05-31 2010-10-06 中兴通讯股份有限公司 Mlppp组带宽容量的处理方法和装置
CN102364892A (zh) * 2011-10-12 2012-02-29 华为技术有限公司 一种lacp链路切换、数据传输方法与装置
CN102882805A (zh) * 2012-09-24 2013-01-16 华为技术有限公司 避免链路聚合组状态震荡的方法及装置
CN106302215A (zh) * 2016-08-30 2017-01-04 华为技术有限公司 一种转发报文的方法及装置

Also Published As

Publication number Publication date
CN106302215A (zh) 2017-01-04

Similar Documents

Publication Publication Date Title
US9705735B2 (en) System and method using RSVP hello suppression for graceful restart capable neighbors
WO2018077238A1 (zh) 一种基于交换机的负载均衡系统及方法
US9485181B2 (en) Dynamic bandwidth adjustment in packet transport network
EP2667548B1 (en) Network traffic volume distribution method, network node, and system
US9634925B2 (en) Technique for network routing
EP3949293A1 (en) Slice-based routing
US20090296572A1 (en) Tunnel establishing method, network node device and network system
WO2011022998A1 (zh) 自动保护倒换方法、设备和系统
EP3029883B1 (en) Network protection method and apparatus, next-ring node, and system
WO2018113294A1 (zh) 一种转发报文的方法、设备及系统
CN109088822B (zh) 数据流量转发方法、装置、系统、计算机设备及存储介质
WO2018040916A1 (zh) 一种转发报文的方法及装置
KR20180122513A (ko) Sdn 기반 네트워크 가상화 플랫폼의 네트워크 하이퍼바이저에서 트래픽 엔지니어링 방법 및 프레임워크
CN107426099B (zh) 多机箱链路聚合流量重分布时的报文保序方法及系统
CN110892687B (zh) 多级资源预留
US20240080238A1 (en) Communication Resilience in a Network
US20240080237A1 (en) Communication Resilience in a Network
US20240154861A1 (en) Communication Resilience in a Network
US20220311694A1 (en) Communication Resilience in a Network
JP2009017230A (ja) 通信システム、冗長化ノードおよび冗長化ノード用プログラム
Han et al. A Novel Multipath Load Balancing Algorithm in Fat-Tree Data Center

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: 17845218

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: 17845218

Country of ref document: EP

Kind code of ref document: A1