WO2015196494A1

WO2015196494A1 - Path calculation method and apparatus

Info

Publication number: WO2015196494A1
Application number: PCT/CN2014/081071
Authority: WO
Inventors: 王巧灵
Original assignee: 华为技术有限公司
Priority date: 2014-06-28
Filing date: 2014-06-28
Publication date: 2015-12-30
Also published as: CN105723667B; CN105723667A

Abstract

The present invention relates to the field of network communications. Specifically disclosed is a path calculation method. The method comprises: after it is detected that a fault occurs on a network, determining all affected services; acquiring traffics, allocated on each link in the network, of a largest stream between a source node and a destination node of each service affected by the fault; acquiring a cost value of each link, wherein the cost value of any link is a rounded-up value of a result obtained by dividing a traffic of the any link by a remaining bandwidth of the any link, and a sum of the traffics of the any link is a sum of traffics, allocated on the any link, of largest streams between source nodes and destination nodes of all affected services; and calculating, for a service affected by the fault, a shortest path satisfying bandwidth requirements according to the cost value of each link. Also disclosed is a path calculation apparatus.

Description

Method and device for path calculation

The present invention relates to network communication technologies, and in particular, to a method and apparatus for path calculation. Background technique

With the advent of new technologies such as Software Defined Network (SDN) and Network Function Virtualization (NFV), centralized control applications are becoming more widespread.

Centralized control requires centralized controllers to have strong scheduling capabilities for network-wide resources, especially when the network fails, requiring centralized controllers to respond quickly and recover as many of the damaged services as possible. In the prior art, when the network fails, the centralized controller still uses the distributed Constrained Shorest Path Tree (CSPF) path calculation method to separately calculate the traffic for each service affected by the fault. In the case of high network utilization and tight network resources, this CSPF path calculation method is likely to cause resource competition, resulting in failure of the calculation and low success rate. Summary of the invention

The embodiment of the invention provides a method and a device for calculating a path, which solves the problem that the existing path calculation cannot effectively utilize the resources of the whole network and the success rate of the calculation path is low.

Embodiments of the present invention use the following technical solutions:

A first aspect of the present invention provides a method for path calculation, including:

After detecting a network failure, determine all services affected by the failure;

Obtaining, by each of the source-sink nodes of the service affected by the fault, a traffic that is allocated on each link in the network;

Obtaining a value of the cost of each link, where the cost of any link is an upward rounding value of the traffic of any one of the links and the remaining bandwidth of the any of the links, the any link And the sum of the traffic aggregated on any of the links for the maximum flow between the source and sink nodes of all of the services affected by the failure;

Calculating, according to the cost value of each link, the shortest path that satisfies the bandwidth requirement of the service affected by the fault.

In a first possible implementation manner, before the detecting that the network is faulty, the method further includes:

Calculating a maximum flow between source and sink nodes of each service in the network according to a remaining bandwidth of the link in the network, determining that a maximum flow between the source and sink nodes of each service is on each of the links The traffic on the distribution.

With reference to the first possible implementation manner of the first aspect, in a second possible implementation manner, the determining, by using the maximum flow between the source and sink nodes of each service, is allocated on each link Traffic, including:

If the link carrying the largest flow between the source and sink nodes of any service is not unique, the maximum flow between the source and sink nodes of any of the services is allocated on multiple links carrying the largest flow; The maximum flow between source and sink nodes of a service is allocated traffic on each link.

In conjunction with the second possible implementation of the first aspect, in a third possible implementation, the maximum flow between the source and sink nodes of the any service is allocated to multiple links that carry the largest flow. On, specifically include:

The maximum flow between the source and sink nodes of any of the services is allocated on the link with the least remaining bandwidth among the plurality of links carrying the largest flow.

With reference to the first possible implementation manner of the first aspect, the second possible implementation manner, or the third possible implementation manner, in a fourth possible implementation manner, before the detecting that the network is faulty, The method also includes:

If the remaining bandwidth of the link in the network changes, the maximum flow between the source and sink nodes of each service is recalculated.

A second aspect of the present invention provides an apparatus for path calculation, including: a service determining unit, configured to determine, after detecting a network failure, all services affected by the fault;

An acquiring unit, configured to acquire, by the service determining unit, a traffic that is allocated on each link in the network by a maximum flow between source and sink nodes of each of the services affected by the fault; acquiring each of the The cost of the link, where the cost of any link is the rounded up value of the traffic of any of the links and the remaining bandwidth of the link; the traffic of any of the links is The sum of the traffic of the maximum flow between the source and sink nodes of the service affected by the fault on the any of the links;

The path calculation unit calculates, according to the cost value of each link acquired by the acquiring unit, the shortest path that satisfies the bandwidth requirement of the service affected by the fault.

In a first possible implementation, the device further includes:

a maximum flow calculation unit, configured to calculate, after the service determining unit detects a network failure, a maximum flow between source and sink nodes of each service in the network according to a remaining bandwidth of the link in the network;

And a traffic determining unit, configured to determine, according to the maximum flow between the source and sink nodes of each service that is calculated by the maximum flow calculation unit, the traffic that is allocated on each link.

With reference to the first possible implementation manner of the second aspect, in a second possible implementation manner, the traffic determining unit is specifically configured to: if the link carrying the maximum flow between the source and sink nodes of any service is not unique And allocating a maximum flow between the source and sink nodes of the any service on the multiple links carrying the maximum flow; calculating a maximum flow between the source and sink nodes of the any service on each of the links The traffic on the distribution.

With the second possible implementation of the second aspect, in a third possible implementation, the traffic determining unit specifically includes:

a first sub-unit, configured to allocate, if the link between the source and sink nodes of the any service is the only one, the maximum flow between the source and sink nodes of the any service On the link; And a second subunit, configured to calculate a traffic that is allocated by the maximum flow between the source and sink nodes of the any service on each link.

With reference to the third possible implementation manner of the second aspect, in a fourth possible implementation, the first sub-unit is specifically configured to: if the source and sink nodes of any service carry a maximum flow chain The path is not unique, and the maximum flow between the source and sink nodes of any of the services is allocated on the link with the least remaining bandwidth among the multiple links carrying the largest flow.

With reference to any one of the possible implementations of the first to fourth possible implementations of the second aspect, in a fifth possible implementation, the maximum flow calculation unit is further used by the service determining unit Before detecting a network failure, if the remaining bandwidth of the link in the network changes, the maximum flow between the source and sink nodes of each service is recalculated.

A method and a device for calculating a path provided by an embodiment of the present invention, comprehensively considering the traffic that is allocated to each link in the network by the maximum flow between the source and sink nodes of the service affected by the fault, and is a service affected by the fault. Calculate the path, effectively use the resources of the whole network, and calculate the success rate of the road. DRAWINGS

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the embodiments will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the present invention. One of ordinary skill in the art can also obtain other drawings based on these drawings without paying for inventive labor.

FIG. 1 is a flowchart of a method for path calculation according to an embodiment of the present invention;

2 is a schematic diagram of a network networking provided by an embodiment of the present invention;

FIG. 3 is a schematic diagram of traffic flow allocated by each node between a node A and a node C according to an embodiment of the present invention;

FIG. 4 is a schematic diagram of traffic flow allocated by each node between a node A and a node D according to an embodiment of the present invention;

FIG. 5 is a structural block diagram of an apparatus for path calculation according to an embodiment of the present invention; FIG. 6 is another structural block diagram of an apparatus for path calculation according to an embodiment of the present invention. FIG. 7 is a structural block diagram of another apparatus for path calculation according to an embodiment of the present invention. detailed description

Embodiments of the present invention provide a method and apparatus for path calculation. For a better understanding of the technical solutions of the present invention, the embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

It should be understood that the described embodiments are only a part of the embodiments of the invention, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present invention without creative efforts are within the scope of the present invention.

The embodiment of the present invention provides a process for calculating a path as shown in FIG. 1 , and the method includes the following steps:

Step S101: After detecting a network failure, determine all services affected by the fault.

Step S102: Acquire a traffic that is allocated on each link in the network by the maximum flow between the source and sink nodes of each service affected by the fault.

Step S103: Obtain a value of each link, where the cost value of any link is an upward rounding value of the traffic of the any link and the remaining bandwidth of the link, and the traffic sum of the link is all The sum of the traffic that the maximum flow between the source and sink nodes of the service affected by the failure is spread over any of the links.

Step S104: Calculate, according to the cost value of each link, a shortest path that satisfies the bandwidth requirement for the service affected by the fault.

Further, before detecting that the network is faulty, the method may further include the step S100: calculating a maximum flow between the source and sink nodes of each service in the network according to the remaining bandwidth of the link in the network, and determining a source and sink node of each service. The maximum flow between the traffic on each link.

Specifically, determining the traffic that the maximum flow between the source and sink nodes of each service is allocated on each link may specifically include: if the link carrying the largest flow between the source and sink nodes of any service is not unique, The maximum flow between the source and sink nodes of any service is allocated on multiple links carrying the largest flow; Calculate the traffic that the maximum flow between the source and sink nodes of any service is allocated on each link. Specifically, the maximum flow between the source and sink nodes of any service is allocated on the multiple links that carry the maximum flow, and the specific flow includes: maximizing the maximum flow between the source and sink nodes of any service. On the links with the fewest remaining bandwidth among the multiple links of the flow.

Further, step S100 may further include: recalculating the maximum flow between the source and sink nodes of each service if the remaining bandwidth of the link in the network changes. A method and apparatus for path calculation according to an embodiment of the present invention are described in detail below with reference to the accompanying drawings.

The executor in the embodiment of the present invention may be a centralized control device, and the centralized control device may be a centralized controller, such as a network management system, a path calculation unit, a network controller, an SDN controller, etc., and the centralized control device may also be A device built into the above centralized controller.

The embodiment of the invention provides a method for path calculation, and the execution subject takes a centralized controller as an example. As shown in Figure 2, there are five nodes A, B, C, D, and E in the network, which are controlled by a centralized controller. The services in the network are: service 1, whose route is A-E-D-C; service 2, whose route is A-E-D; service 3, whose route is A-B.

The remaining bandwidth of each link in the network shown in Figure 2 is:

The remaining bandwidth of link A-B is 3 bandwidth units;

The remaining bandwidth of the link A-D is 3 bandwidth units;

The remaining bandwidth of link A-E is 6 bandwidth units;

The remaining bandwidth of the link E-D is 6 bandwidth units;

The remaining bandwidth of the link D-C is 3 bandwidth units;

The remaining bandwidth of the link BC is 3 bandwidth units. The remaining bandwidth of the link is a relative value, indicating how many bandwidth units. For example, the remaining bandwidth value is 3, which represents 3 bandwidth units; the remaining bandwidth value is 6, representing 6 bandwidth units. It can represent 3MHz bandwidth and 6MHz bandwidth, respectively, and can also represent 30MHz bandwidth and 60MHz bandwidth respectively.

The method for calculating the path specifically includes the following steps:

Step S201: After detecting a network failure, determine all services affected by the fault.

In this embodiment, after detecting that the link A-E in the network is faulty, it is determined that the service affected by the fault is service 1 and service 2.

Step S202: Acquire, according to the maximum flow between each source and sink node of the service affected by the fault, traffic allocated on each link in the network, where the maximum flow is the maximum traffic that can be carried between the source node and the sink node. .

In this embodiment, the maximum flow between the source and sink nodes of service 1 and service 2 is obtained on each link in the network. The source and sink nodes of service 1 are node A and node C, respectively, and the source and sink nodes of service 2 are node A and node D, respectively.

The traffic that the maximum flow between the source and sink nodes of each service in the network is allocated on each link may be pre-configured before the network fails, or may be pre-calculated before the network fails. This embodiment does not ^1 is limited.

Therefore, in this embodiment, the maximum flow between the node A and the node C can be directly obtained from the traffic that is allocated on each link in the maximum flow between the source and sink nodes of each service in the network obtained in advance. The traffic that is allocated on each link, and the traffic that is spread across each link, and the maximum flow between node A and node D.

The maximum flow between node A and node C is allocated on each link, as shown in Figure 3. The traffic on link A-B is 3 bandwidth units.

The traffic allocated on link A-D is 3 bandwidth units.

The traffic allocated on link A-E is 0 bandwidth units.

The traffic allocated on the link ED is 0 bandwidth units. The traffic allocated on the link DC is 3 bandwidth units.

The traffic allocated on link B-C is 3 bandwidth units.

The maximum flow between node A and node D is allocated on each link, as shown in Figure 4: The traffic on link A-B is 0 bandwidth units.

The traffic allocated on link A-D is 3 bandwidth units.

The traffic allocated on link A-E is 6 bandwidth units.

The traffic allocated on the link E-D is 6 bandwidth units.

The traffic allocated on the link D-C is 0 bandwidth units.

The traffic on the link B-C is 0 bandwidth units.

Step S203: Obtain a cost (Metric) value of each link.

For any link in the network, the Metric value of the link is the rounded up value of the traffic of the link and the remaining bandwidth of the link; the traffic of the link and the source of all services affected by the fault The sum of the traffic spread by the maximum flow between the sink nodes on the link.

In this embodiment, the link AB is taken as an example. The traffic of the maximum flow between the source and sink nodes A and C of the service 1 on the link AB is 3 bandwidth units, and the source and sink nodes A and D of the service 2 The sum of the traffic of the maximum flow on the link AB is 0, and the sum of the traffic flowed by the maximum flow between the service 1 and the source and sink nodes of the service 2 on the link AB is 3 bandwidth units. That is, the traffic of the link AB is 3 bandwidth units.

The other links are similar to the link A-B. The maximum flow between the service 1 and the source and sink nodes of the service 2 is the sum of the traffic allocated on each link, that is, the traffic of each link is:

The traffic sum of link A-B is 3 bandwidth units;

The traffic of the link A-D is 6 bandwidth units;

The traffic of link A-E is 6 bandwidth units;

The traffic of the link E-D is 6 bandwidth units;

The traffic of the link D-C is 3 bandwidth units;

The traffic of the link BC is 3 bandwidth units. Take link AB as an example. The traffic sum of link AB is 3 bandwidth units, and the remaining bandwidth value is 3 bandwidth units. Then, the cost of link AB is the round-up value of the result of dividing by 3 and 3, that is, 1 .

The other links are similar to the link AB. According to the traffic of each link and the remaining bandwidth value of each link, the value of each link is obtained: the cost value of the link AB is 1; the cost value of the link AD is 2. The cost value of the link AE is 1, the cost of the link ED is 1, the cost of the link DC is 1, and the cost of the link BC is 1.

Step S204: Calculate, according to the cost value of each link, the shortest path that satisfies the bandwidth requirement for the service affected by the fault.

In this embodiment, the shortest path that satisfies the bandwidth requirement is calculated for the service 1 and service 2 affected by the failure according to the cost value of each link acquired in step S203.

The method of calculating the shortest path according to the value of the link may use a method such as a dijkstra algorithm, a Bellman-Ford algorithm or a Floyd-Warshall algorithm, which is not limited in this embodiment.

After the link A-E is faulty, the path from node A to node C is A-B-C. After the link A-E is faulty, the path from node A to node D is A-D. In another embodiment, before the step S201 of the foregoing embodiment, that is, before the network is detected to be faulty, the method may further include:

Step S200: Calculate a maximum flow between source and sink nodes of each service in the network according to remaining bandwidth of the link in the network, and determine that a maximum flow between source and sink nodes of each service is allocated on each link. flow.

In this embodiment, according to the remaining bandwidth value of each link, the maximum flow between the source and sink nodes A and C of service 1 is 6 bandwidth units, and the maximum flow between source and sink nodes A and D of service 2 is The maximum bandwidth between the 9 bandwidth units and the source and sink nodes A and B of service 3 is 3 bandwidth units. The calculation method of the maximum flow is the prior art, and details are not described in this embodiment.

Then, determine the traffic that the maximum flow between the source and sink nodes of each service is allocated on each link. Specifically, if the link carrying the largest flow between the source and sink nodes of the service is not unique, the service is The maximum flow between the source and sink nodes is allocated on multiple links carrying the largest flow, and the maximum flow between the source and sink nodes of the service is calculated on each link; if the source and sink nodes of the service The maximum flow between the source and sink nodes of the service is directly allocated on the link, and the maximum flow between the source and sink nodes of the service is calculated and allocated on each link. Traffic.

Specifically, the maximum flow between the source and sink nodes of the service is allocated on multiple links carrying the largest flow, and the maximum flow between the source and sink nodes of the service may be allocated to multiple links carrying the largest flow. In the link with the least remaining bandwidth, other allocation modes may be used, for example, the maximum flow is evenly distributed on multiple links, or the maximum flow is allocated on the link with the most remaining bandwidth. No restrictions.

In this embodiment, the traffic of the maximum flow between the source and sink nodes of service 1, service 2, and service 3 is allocated on each link.

The maximum flow between the source and sink nodes A and C of service 1 is 6 bandwidth units, and the link carrying the largest flow between node A and node C is not unique, and link AD and link AE and ED can replace each other. That is, the link AD can replace the links AE and ED, and the links AE and ED can replace the link AD.

In this embodiment, the maximum flow between the source and sink nodes of the service is allocated to the link with the smallest remaining bandwidth among the multiple links carrying the largest flow. The maximum flow between the node A and the node C is allocated on the link with the smallest remaining bandwidth among the multiple links carrying the largest flow, and the remaining bandwidth of the link AD is 3 bandwidth units, and the remaining bandwidth of the link AE and the ED are both 6 bandwidth units, between which the link AD with less remaining bandwidth is selected as the link carrying the largest flow. The traffic with the maximum flow between the node A and the node C as shown in Figure 3 is allocated on each link, and the traffic on the links A-E and E-D is 0.

The maximum flow between the source and sink nodes A and D of service 2 is 9 bandwidth units. The link carrying the largest flow between node A and node D is unique. The traffic allocated on each link is shown in Figure 4.

The maximum flow between the source and sink nodes A and B of service 3 is 3 bandwidth units, and the link carrying the largest flow between node A and node B is unique, and the traffic allocated on link AB is 3 bandwidth units. The traffic allocated on other links is 0.

A large number of services are often present in the actual application network, and each node in the network may go up and down. In this case, calculate the maximum flow between the source and sink nodes of each service in the network, and determine the traffic that the maximum flow between the source and sink nodes of each service is allocated on each link, which is equivalent to calculating the network. The maximum flow between any two nodes, determining the traffic that the maximum flow between any two nodes is allocated on each link.

Further, before detecting a network failure, if the remaining bandwidth of the link in the network changes, recalculating the maximum flow between the source and sink nodes of each service, and then re-determining the source and sink nodes of each service. The maximum flow between each link is allocated to each link, so that after the network fails, the shortest path that meets the bandwidth requirement is calculated for the service affected by the failure. In the prior art, when a link A-E failure is detected, the CSPF is used to recalculate the path. Because CSPF does not make effective use of the entire network resources, it is a separate way for each business affected by the failure. If service 1 calculates the path first, according to the shortest path rule, the calculated path is A-D-C, then service 2 fails and service 2 cannot be recovered.

A path calculation method provided by an embodiment of the present invention comprehensively considers the traffic that is allocated by each of the source and sink nodes of the service affected by the fault in each link in the network, and calculates the path for the service affected by the fault. , Effective use of the entire network resources, high success rate of calculation.

In addition, the path calculation method provided by the embodiment of the present invention may further calculate, before the network failure, pre-calculate the traffic that the maximum flow between the source and sink nodes of each service is allocated on each link, and according to the link. The change of the remaining bandwidth and the real-time refresh of the allocated traffic make the path calculation more accurate and effective. The embodiment of the present invention provides a device 500 for path calculation. As shown in FIG. 5, the device includes a service determining unit 510, an obtaining unit 520, and a path calculating unit 530:

The service determining unit 510 is configured to: after detecting that the network is faulty, determine all affected by the fault. Business

The obtaining unit 520 is configured to acquire, by the service determining unit 510, the traffic that is allocated on each link in the network by the maximum flow between the source and sink nodes of each service affected by the fault; acquire the cost value of each link, Wherein the cost of any link is an upward rounding value of the traffic of any of the links and the remaining bandwidth of the link; the traffic of any of the links is between the source and sink nodes of all services affected by the fault The sum of the traffic that the maximum flow distributes on any of the links;

The path calculation unit 530 calculates a shortest path that satisfies the bandwidth requirement according to the cost of each link acquired by the acquisition unit 520.

Further, as shown in FIG. 6, the device 500 for calculating the path may further include:

The maximum flow calculation unit 540 is configured to calculate, according to the remaining bandwidth of the link in the network, the maximum flow between the source and sink nodes of each service in the network before the service determining unit 510 detects that the network is faulty; the traffic determining unit 550 is configured to: The flow rate of the maximum flow between the source and sink nodes of each service calculated by the maximum flow calculation unit 540 on each link is determined.

Further, the traffic determining unit 550 may be specifically configured to: if the link carrying the largest flow between the source and sink nodes of any service is not unique, allocate the maximum flow between the source and sink nodes of any service to the maximum flow of the bearer. On multiple links; calculate the traffic that the maximum flow between the source and sink nodes of any service is allocated on each link.

Further, the traffic determining unit 550 may specifically include:

The first sub-unit 551 is configured to allocate, if the link that carries the largest flow between the source and sink nodes of any service is not unique, allocate the maximum flow between the source and sink nodes of any service to multiple chains that carry the largest flow. On the road

The second sub-unit 552 is configured to calculate the traffic that the maximum flow between the source and sink nodes of the any service is allocated on each link.

Further, the first sub-unit 552 may be specifically configured to: if the link carrying the largest flow between the source and sink nodes of any service is not unique, the maximum flow between the source and sink nodes of any service is allocated to the maximum bearer. On the links with the fewest remaining bandwidth among the multiple links of the flow. Further, the maximum flow calculation unit 540 is further configured to: before the service determining unit 510 detects that the network has a fault, if the remaining bandwidth of the link in the network changes, recalculate the maximum flow between the source and sink nodes of each service. Another embodiment of the present invention provides a path calculation device 700, as shown in FIG. 7, including a transmitter 710, a memory 720, and a processor 730:

a transmitter 710, configured to send a shortest path that meets a bandwidth requirement for a service affected by the fault; and a memory 720, configured to store information including a program routine;

The processor 730 is coupled to the memory 720 and the transmitter 710 for controlling the execution of the program routine, and specifically includes:

Obtaining the traffic that the maximum flow between the source and sink nodes of each service affected by the fault is allocated on each link in the network;

Obtaining the cost value of each link, where the cost of any link is the rounded up value of the traffic of any link and the remaining bandwidth of the link, and the traffic of any link is affected by all the faults. The sum of the traffic of the maximum flow between the source and sink nodes of the service on the any of the links;

Calculate the shortest path that meets the bandwidth requirement based on the cost of each link.

Further, before detecting a network failure, the processor 730 can also be used to control the execution of the program routine:

Calculate the maximum flow between the source and sink nodes of each service in the network according to the remaining bandwidth of the link in the network, and determine the traffic that the maximum flow between the source and sink nodes of each service is allocated on each link.

The traffic that is allocated by the maximum flow between the source and sink nodes of each service on each link may include: if the link carrying the largest flow between the source and sink nodes of any service is not unique, The maximum flow between source and sink nodes of any service is allocated on multiple links carrying the largest flow; The traffic that the maximum flow between the source and sink nodes of any service is allocated on each link.

The maximum flow between the source and sink nodes of any service is allocated on the multiple links that carry the maximum flow, and the specific flow includes: the maximum flow between the source and sink nodes of any service is allocated in the maximum flow of the bearer. On the links with the fewest remaining bandwidth among the multiple links.

If the remaining bandwidth of the link in the network changes, recalculate the maximum flow between the source and sink nodes of each service. The device for calculating the path in the above embodiment may be a centralized control device, and the centralized control device may be a centralized controller, such as a network management system, a path calculation unit, a network controller, an SDN controller, etc., and the centralized control device may also be It is a device built into the above centralized controller.

In the foregoing embodiment, the information interaction, the execution process, and the like between the units in the path calculation device are based on the same concept as the method embodiment of the present invention. For details, refer to the description in the method embodiment of the present invention. I will not repeat them here.

The device for calculating a path provided by the embodiment of the present invention comprehensively considers the traffic that is allocated to each link in the network by the maximum flow between the source and sink nodes of the service affected by the fault, and is the service affected by the fault. Calculate the path, effectively use the resources of the whole network, and calculate the success rate of the road. A person skilled in the art can understand that all or part of the steps of the foregoing embodiment can be implemented by a computer program to instruct related hardware, and the program can be stored in a computer readable storage medium. In execution, the flow of an embodiment of the methods as described above may be included. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

The above is only a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto, and any person skilled in the art can easily within the technical scope disclosed by the present invention. All changes or substitutions contemplated are intended to be included within the scope of the invention. Therefore, the scope of the invention should be determined by the scope of the claims.

Claims

Claim

A method for path calculation, comprising:

Obtaining the cost value of each link, where the cost value of any link is an upward rounding value of the traffic of any one of the links and the remaining bandwidth of the any link, and the traffic of the any link is The sum of the traffic aggregated on any of the links for the maximum flow between the source and sink nodes of all of the fault-affected services;

The method according to claim 1, wherein the method further comprises: before the detecting that the network is faulty, the method further comprises:

The method according to claim 2, wherein the determining the traffic that the maximum flow between the source and sink nodes of each service is allocated on each link includes:

The method according to claim 3, wherein the allocating the maximum flow between the source and sink nodes of the any service on the multiple links that carry the maximum flow includes:

The method according to claim 2, 3 or 4, wherein the detecting the network transmission Before the failure, the method further includes:

6. A device for path calculation, comprising:

a service determining unit, configured to determine, after detecting a network failure, a service that is affected by the fault; and an acquiring unit, configured to acquire, between the source and sink nodes of each of the services affected by the fault determined by the service determining unit The maximum flow is the traffic that is distributed on each link in the network; the cost of each link is obtained, where the cost of any link is the traffic of any of the links and the remainder of any of the links The rounded up value of the result of the bandwidth; the sum of the traffic of any one of the links and the traffic of the maximum flow between the source and sink nodes of all the services affected by the fault on any of the links; a path calculation unit, Calculating, according to the cost of each link acquired by the acquiring unit, a shortest path that satisfies a bandwidth requirement by the service affected by the fault.

The device according to claim 6, wherein the device further comprises:

a maximum flow calculation unit, configured to calculate, according to a remaining bandwidth of the link in the network, a maximum flow between source and sink nodes of each service in the network, before the service determining unit detects that the network is faulty;

The traffic determining unit is configured to determine, according to the maximum flow between the source and sink nodes of each service that is calculated by the maximum flow computing unit, the traffic that is allocated on each link.

The device according to claim 7, wherein the traffic determining unit is specifically configured to: if the link carrying the largest flow between the source and sink nodes of any service is not unique, the service of any one of the services The maximum flow between the source and sink nodes is allocated on multiple links carrying the largest flow; and the traffic that the maximum flow between the source and sink nodes of any of the services is allocated on each link is calculated.

The device according to claim 8, wherein the traffic determining unit specifically includes: a first subunit, configured to: if the link between the source and sink nodes of the any service carries the largest flow, the link is not unique Allocating a maximum flow between source and sink nodes of any of the services on multiple links carrying the largest flow; And a second subunit, configured to calculate a traffic that is allocated by the maximum flow between the source and sink nodes of the any service on each link.

The device according to claim 9, wherein the first sub-unit is specifically configured to: if the link carrying the largest flow between the source and sink nodes of the any service is not unique, The maximum flow between the source and sink nodes of a service is allocated on the link with the least bandwidth remaining among the multiple links carrying the largest flow.

The device according to any one of claims 7 to 10, wherein the maximum flow calculation unit is further configured to: before the service determining unit detects that the network is faulty, if the link in the network The remaining bandwidth changes, and the maximum flow between the source and sink nodes of each service is recalculated.