CN103491021A - Method and device for sharing traffic load - Google Patents
Method and device for sharing traffic load Download PDFInfo
- Publication number
- CN103491021A CN103491021A CN201310476090.7A CN201310476090A CN103491021A CN 103491021 A CN103491021 A CN 103491021A CN 201310476090 A CN201310476090 A CN 201310476090A CN 103491021 A CN103491021 A CN 103491021A
- Authority
- CN
- China
- Prior art keywords
- table item
- hardware table
- flow
- load sharing
- outgoing interface
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The embodiment of the invention provides a method and a device for sharing traffic load. The method comprises the following steps: determining that whether a current traffic load sharing difference value among interconnected links is more than or equal to a preset difference value or not; starting a traffic load sharing optimization mechanism to adjust first hardware entries if the current traffic load sharing difference value among the interconnected links is more than or equal to the preset difference value, acquiring second hardware entries, and reducing the traffic load sharing difference value through the second hardware entries; outputting traffic to be output from an exit interface corresponding to the second hardware entries after the traffic to be output passes through the second hardware entries, wherein the preset difference value is determined according to user requirements or the actual traffic of the exit interface, the number of the second hardware entries is an integral multiple of that of the first hardware entries. According to the embodiment of the invention, the problem of traffic sharing disparity among a plurality of interconnected links shared by traffic load can be solved, the traffic load sharing difference value is reduced, and the load sharing effect of the plurality of interconnected links can be optimized.
Description
Technical field
The embodiment of the present invention relates to the communication technology, relates in particular to a kind of flow load sharing method and apparatus.
Background technology
Along with the development of the Internet, the rapid growth of the bandwidth of user's request, need the interconnected link between router to provide larger bandwidth to meet the demand of user bandwidth.A kind of mode commonly used is by the quantity of interconnected link between increase equipment and forms load balancing and increase bandwidth.But this mode there will be the part of links flow very large, thereby congestion packet loss affects service quality, and the part of links flow is smaller, bandwidth does not have situation about effectively utilizing, and causes the problem of traffic sharing great disparity between the multilink of flow load sharing.
In order to address the above problem, in prior art by flow is carried out to Hash operation, thereby obtain the outgoing interface that flow is corresponding, flow is exported at corresponding outgoing interface, yet this method is the business model under applicable part scene only, the business model between the existing network business model in the large and consolidated network of difference along with the variation of time also in the situation that change, the problems referred to above still can not solve, and can't accomplish Precise control to flow load sharing.
Summary of the invention
The embodiment of the present invention provides a kind of flow load sharing method and apparatus, with the problem of traffic sharing great disparity between many interconnected links that solve flow load sharing.
First aspect, the embodiment of the present invention provides a kind of flow load sharing method, comprising:
Determine whether flow load sharing difference current between interconnected link is more than or equal to preset difference value;
If determine, between described interconnected link, current flow load sharing difference is more than or equal to preset difference value, starting the flow load sharing Optimization Mechanism is adjusted the first hardware table item, obtain the second hardware table item, by described the second hardware table item, to reduce described flow load sharing difference;
The outgoing interface output corresponding from described the second hardware table item will be passed through until output flow after described the second hardware table item;
Wherein, described preset difference value is determined according to the flow of user's request or described outgoing interface reality, the integral multiple of the number that the number of described the second hardware table item is described the first hardware table item.
In the first of first aspect, in possible implementation, described startup flow load sharing Optimization Mechanism is adjusted the first hardware table item, obtains the second hardware table item, comprising:
Obtain described the second hardware table item by spreading described the first hardware table item.
The possible implementation according to the first of first aspect or first aspect, at the second in possible implementation, described will be after output flow passes through described the second hardware table item the corresponding outgoing interface output from described the second hardware table item, comprising:
Treat that by described output flow carries out Hash operation according to the number of described the second hardware table item, to obtain the Hash operation result of mating with described the second hardware table item;
According to described Hash operation result, determine the described corresponding relation for the treatment of output flow and described the second hardware table item;
According to described corresponding relation, by the described corresponding outgoing interface output from described the second hardware table item after output flow passes through described the second hardware table item.
The possible implementation according to the second of first aspect, at the third in possible implementation,
Described, according to described corresponding relation, by described, after passing through described the second hardware table item, output flow, after the output of corresponding outgoing interface, also comprises from described the second hardware table item:
Statistics is by the flow of each described the second hardware table item;
To carry out order according to uninterrupted by the flow of each described the second hardware table item arranges;
According to putting in order of uninterrupted, obtain the 3rd hardware table item by adjusting the position of the outgoing interface corresponding with described the second hardware table item in described the second hardware table item, to reduce described flow load sharing difference;
Outgoing interface output that will be corresponding from described the 3rd hardware table item by the flow of described the 3rd hardware table item.
The possible implementation according to the second of first aspect, in the 4th kind of possible implementation, described, according to described corresponding relation, by described, after passing through described the second hardware table item, output flow, after the output of corresponding outgoing interface, also comprises from described the second hardware table item:
According to the regulation rule of setting, obtain the 4th hardware table item by adjusting the position of the outgoing interface corresponding with described the second hardware table item in described the second hardware table item, to reduce described flow load sharing difference;
Outgoing interface output that will be corresponding from described the 4th hardware table item by the flow of described the 4th hardware table item.
The 4th kind of possible implementation according to first aspect, in the 5th kind of possible implementation, at the described regulation rule according to setting, after adjusting position acquisition four hardware table item of the outgoing interface corresponding with described the second hardware table item in described the second hardware table item, also comprise:
Statistics is by the flow of each described the 4th hardware table item;
To carry out order according to uninterrupted by the flow of each described the 4th hardware table item arranges;
Issue five stiffness part list item according to putting in order of uninterrupted, with outgoing interface output that will be corresponding from described five stiffness part list item by the flow of described five stiffness part list item, reduce described flow load sharing difference, wherein, described five stiffness part list item is the list item that puts in order and obtain by adjusting the position of the outgoing interface corresponding with described the 4th hardware table item in described the 4th hardware table item according to described uninterrupted.
According to any one of five kinds of possible implementations of the first to the of first aspect, first aspect, in the 6th kind of possible implementation, described, will be after output flow passes through described the second hardware table item from described the second hardware table item, after corresponding outgoing interface output, also comprise:
Between the definite interconnected link of execution, whether current flow load sharing difference is more than or equal to the step of preset difference value;
If determine, between described interconnected link, current flow load sharing difference is more than or equal to preset difference value, increase the multiple of described the first hardware table item of diffusion, and start described flow load sharing Optimization Mechanism described the first hardware table item is adjusted, to reduce described flow load sharing difference.
Second aspect, the embodiment of the present invention provides a kind of flow load sharing device, comprising:
The difference determination module, for determining between interconnected link, whether current flow load sharing difference is more than or equal to preset difference value;
Hardware table item obtains module, if for determining that between described interconnected link, current flow load sharing difference is more than or equal to preset difference value, starting the flow load sharing Optimization Mechanism is adjusted the first hardware table item, obtain the second hardware table item, by described the second hardware table item, to reduce described flow load sharing difference;
The flow output module, for will be after output flow passes through described the second hardware table item the corresponding outgoing interface output from described the second hardware table item;
Wherein, described preset difference value is determined according to the flow of user's request or described outgoing interface reality, the integral multiple of the number that the number of described the second hardware table item is described the first hardware table item.
In the first of second aspect, in possible implementation, described hardware table item obtains module, specifically for by spreading described the first hardware table item, obtaining described the second hardware table item.
The possible implementation according to the first of second aspect or second aspect, at the second in possible implementation, described flow output module, treat that by described output flow carries out Hash operation specifically for the number according to described the second hardware table item, to obtain the Hash operation result of mating with described the second hardware table item; According to described Hash operation result, determine the described corresponding relation for the treatment of output flow and described the second hardware table item; According to described corresponding relation, by the described corresponding outgoing interface output from described the second hardware table item after output flow passes through described the second hardware table item.
The possible implementation according to the second of second aspect, at the third in possible implementation, described hardware table item obtains module, also for described according to described corresponding relation, by described after output flow passes through described the second hardware table item from described the second hardware table item after the output of corresponding outgoing interface, statistics is by the flow of each described the second hardware table item; To carry out order according to uninterrupted by the flow of each described the second hardware table item arranges; According to putting in order of uninterrupted, obtain the 3rd hardware table item by adjusting the position of the outgoing interface corresponding with described the second hardware table item in described the second hardware table item, to reduce described flow load sharing difference;
Described flow output module, also export for outgoing interface that will be corresponding from described the 3rd hardware table item by the flow of described the 3rd hardware table item.
The possible implementation according to the second of second aspect, in the 4th kind of possible implementation, described hardware table item obtains module, also for described according to described corresponding relation, by described after output flow passes through described the second hardware table item from described the second hardware table item after the output of corresponding outgoing interface, according to the regulation rule of setting, obtain the 4th hardware table item by adjusting the position of the outgoing interface corresponding with described the second hardware table item in described the second hardware table item, to reduce described flow load sharing difference;
Described flow output module, also export for outgoing interface that will be corresponding from described the 4th hardware table item by the flow of described the 4th hardware table item.
The 4th kind of possible implementation according to second aspect, in the 5th kind of possible implementation, described flow output module, also at the described regulation rule according to setting, after adjusting position acquisition four hardware table item of the outgoing interface corresponding with described the second hardware table item in described the second hardware table item, statistics is by the flow of each described the 4th hardware table item; To carry out order according to uninterrupted by the flow of each described the 4th hardware table item arranges; Issue five stiffness part list item according to putting in order of uninterrupted, with outgoing interface output that will be corresponding from described five stiffness part list item by the flow of described five stiffness part list item, reduce described flow load sharing difference, wherein, described five stiffness part list item is the list item that puts in order and obtain by adjusting the position of the outgoing interface corresponding with described the 4th hardware table item in described the 4th hardware table item according to described uninterrupted.
According to any one in five kinds of possible implementations of the first to the of second aspect, second aspect, in the 6th kind of possible implementation, described difference determination module, also for described, will be after output flow passes through described the second hardware table item from described the second hardware table item, after corresponding outgoing interface output, carry out and determine between interconnected link, whether current flow load sharing difference is more than or equal to preset difference value;
Described hardware table item obtains module, if also for determining that between described interconnected link, current flow load sharing difference is more than or equal to preset difference value, increase the multiple of described the first hardware table item of diffusion, and start described flow load sharing Optimization Mechanism described the first hardware table item is adjusted, to reduce described flow load sharing difference.
Embodiment of the present invention flow load sharing method and apparatus, starting the flow load sharing Optimization Mechanism when determining between interconnected link whether current flow load sharing difference is more than or equal to preset difference value and is more than or equal to preset difference value is adjusted the first hardware table item, obtain the second hardware table item, by described the second hardware table item, to reduce described flow load sharing difference, and will be after output flow passes through described the second hardware table item the corresponding outgoing interface output from the second hardware table item.Thereby between many interconnected links that solved flow load sharing, the problem of traffic sharing great disparity, reduced described flow load sharing difference, optimized the load balancing effect of many interconnected links.
The accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, below will the accompanying drawing of required use in embodiment or description of the Prior Art be briefly described, apparently, accompanying drawing in the following describes is some embodiments of the present invention, for those of ordinary skills, under the prerequisite of not paying creative work, can also obtain according to these accompanying drawings other accompanying drawing.
The flow chart of the flow load sharing method that Fig. 1 provides for the embodiment of the present invention one;
The flow chart of the flow load sharing method that Fig. 2 provides for the embodiment of the present invention two;
The flow chart of the flow load sharing method that Fig. 3 provides for the embodiment of the present invention three;
The flow chart of the flow load sharing method that Fig. 4 A provides for the embodiment of the present invention four;
The schematic diagram of the flow load sharing method that Fig. 4 B provides for the embodiment of the present invention four;
A kind of schematic diagram that adjusts flow and outgoing interface corresponding relation behind the position of interface in hardware table item that Fig. 4 C provides for the embodiment of the present invention four;
The another kind that Fig. 4 D provides for the embodiment of the present invention four adjusts the schematic diagram of flow and outgoing interface corresponding relation behind the position of interface in hardware table item;
The structural representation of the flow load sharing device 500 that Fig. 5 provides for the embodiment of the present invention five.
Embodiment
For the purpose, technical scheme and the advantage that make the embodiment of the present invention clearer, below in conjunction with the accompanying drawing in the embodiment of the present invention, technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is the present invention's part embodiment, rather than whole embodiment.Embodiment based in the present invention, those of ordinary skills, not making under the creative work prerequisite the every other embodiment obtained, belong to the scope of protection of the invention.
The flow chart of the flow load sharing method that Fig. 1 provides for the embodiment of the present invention one.The flow that the method for the present embodiment is applicable to that many interconnected links of formation flow load sharing are shared carries out the situation of flow equalization.The method is carried out by the flow load sharing device, and this device is realized in the mode of hardware and/or software usually.The method of the present embodiment comprises as follows:
110, determine whether flow load sharing difference current between interconnected link is more than or equal to preset difference value.
Traffic sharing great disparity between the multilink of prior art kind flow load sharing, and operator wishes that the actual flow error of flow load sharing link is controlled in a less scope, for example 20%, to bring into play as far as possible the maximum bandwidth capability of each link, from minute bandwidth availability ratio of raising link.Control the flow situation of the load balancing outgoing interface that the actual flow error of flow load sharing link can be by real-time monitor network equipment, obtain the flow load sharing difference between the link of the link of flow maximum between many interconnected links and flow minimum, and judge whether current load balancing difference is more than or equal to preset difference value, thereby determine whether to enter 120 realizations, to reduce the flow load sharing difference.Wherein, preset difference value is determined according to the flow of user's request or outgoing interface reality.
If 120 determine that between interconnected link, current flow load sharing difference is more than or equal to preset difference value, starting the flow load sharing Optimization Mechanism is adjusted the first hardware table item, obtain the second hardware table item, by the second hardware table item, to reduce the flow load sharing difference.The integral multiple of the number that wherein, the number of the second hardware table item is the first hardware table item.
Integral multiple due to the number of the second hardware table item number that is the first hardware table item, therefore can be segmented flow by the second hardware table item.If for example the first list item is 3, actual outgoing interface is outgoing interface 1, outgoing interface 2 and outgoing interface 3,6 outgoing interface list items are arranged after the first hardware table item is adjusted, but actual outgoing interface or outgoing interface 1, outgoing interface 2 and outgoing interface 3 now there are 2 the second hardware table items under each outgoing interface.Because 6 the second hardware table items can be segmented flow, therefore can reduce the flow load sharing difference, the traffic sharing of the multilink of flow load sharing is tending towards evenly more, thereby optimizes the load balancing effect.
130, will be after output flow passes through the second hardware table item the corresponding outgoing interface output from the second hardware table item.
Concrete, by determining between interconnected link, whether current flow load sharing difference is more than or equal to preset difference value, if determine, between interconnected link, current flow load sharing difference is more than or equal to preset difference value, starting the flow load sharing Optimization Mechanism is adjusted the first hardware table item, obtain the second hardware table item, by the second hardware table item, to reduce the flow load sharing difference, the outgoing interface output corresponding from the second hardware table item will be passed through until output flow after the second hardware table item.
The flow load sharing method that the present embodiment provides, adjusted the first hardware table item by starting the flow load sharing Optimization Mechanism, obtains the second hardware table item, by the second hardware table item, to reduce the flow load sharing difference.Thereby between many interconnected links that solved flow load sharing, the problem of traffic sharing great disparity, reduced the flow load sharing difference, optimized the load balancing effect of many interconnected links.
The present embodiment be take above-described embodiment one as basis, further is optimized the flow chart of the flow load sharing method that Fig. 2 provides for the embodiment of the present invention two.With reference to Fig. 2, the method for the present embodiment can comprise:
210, determine whether flow load sharing difference current between interconnected link is more than or equal to preset difference value.
If 220 determine that between interconnected link, current flow load sharing difference is more than or equal to preset difference value, by spreading the first hardware table item, obtain the second hardware table item.
230, will treat that according to the number of the second hardware table item output flow carries out Hash operation, to obtain the Hash operation result of mating with the second hardware table item.
240,, according to the Hash operation result, determine the corresponding relation for the treatment of output flow and the second hardware table item.
250,, according to corresponding relation, the outgoing interface output corresponding from the second hardware table item will be passed through until output flow after the second hardware table item.
The flow load sharing method that the present embodiment provides, obtain the second hardware table item by spreading the first hardware table item, to treat that according to the number of the second hardware table item output flow carries out Hash operation, to obtain the Hash operation result of mating with the second hardware table item, thereby determine the corresponding relation treat output flow and the second hardware table item according to the Hash operation result, then according to corresponding relation will be after output flow passes through the second hardware table item from the second hardware table item corresponding outgoing interface export.Thereby between many interconnected links that solved flow load sharing, the problem of traffic sharing great disparity, reduced the flow load sharing difference, optimized the load balancing effect of many interconnected links.
The present embodiment be take above-described embodiment two as basis, further is optimized the flow chart of the flow load sharing method that Fig. 3 provides for the embodiment of the present invention three.With reference to Fig. 3, the method for the present embodiment can comprise:
310, determine whether flow load sharing difference current between interconnected link is more than or equal to preset difference value.
If 320 determine that between interconnected link, current flow load sharing difference is more than or equal to preset difference value, by spreading the first hardware table item, obtain the second hardware table item.
330, will treat that according to the number of the second hardware table item output flow carries out Hash operation, to obtain the Hash operation result of mating with the second hardware table item.
340,, according to the Hash operation result, determine the corresponding relation for the treatment of output flow and the second hardware table item.
350,, according to corresponding relation, the outgoing interface output corresponding from the second hardware table item will be passed through until output flow after the second hardware table item.
After carrying out 310～350, the flow situation of the load balancing outgoing interface by real-time monitor network equipment, if the flow load sharing difference between many interconnected links is not still in the preset difference value scope, can further reduce the flow load sharing difference by 360～390, further to optimize the load balancing effect.
360, statistics is by the flow of each the second hardware table item.
370, will carry out order according to uninterrupted by the flow of each the second hardware table item arranges.
380, according to the putting in order of uninterrupted, by adjusting position acquisition three hardware table item of the outgoing interface corresponding with the second hardware table item in the second hardware table item, to reduce the flow load sharing difference.
For instance, if the corresponding outgoing interface 1 of the second hardware table item 0, and executing the 350 rear flow maximums of outgoing interface 1 of passing through, and difference maximum between the flow of the flow of outgoing interface 1 and outgoing interface 3, be also that between the flow of the link that the flow of link of outgoing interface 1 correspondence is corresponding with outgoing interface 3, the flow load sharing difference is maximum and not in the preset difference value scope, can adjust by the identification information of adjusting the outgoing interface of storage in the second hardware table item 0 position of interface in the second hardware table item 0 and obtain the 3rd hardware table item.For example adjust the corresponding outgoing interface 3 of the 3rd hardware table item 0 obtained after the identification information of the outgoing interface of storage in the second hardware table item 0, by the flow of the 3rd hardware table item 0, just can export from outgoing interface 3 more afterwards, thus the flow between balanced outgoing interface 1 and outgoing interface 3.
390, outgoing interface output that will be corresponding from the 3rd hardware table item by the flow of the 3rd hardware table item.
The flow load sharing method that the present embodiment provides, pass through corresponding relation, by pass through after the second hardware table item the outgoing interface output corresponding from the second hardware table item until output flow, further statistics is by the flow of each the second hardware table item, the flow of each the second hardware table item is carried out to order according to uninterrupted to be arranged and putting in order according to uninterrupted, adjust the position of the outgoing interface corresponding with the second hardware table item in the second hardware table item and obtain the 3rd hardware table item, further to reduce the flow load sharing difference.Thereby between many interconnected links that solved flow load sharing, the problem of traffic sharing great disparity, further reduced the flow load sharing difference, optimized the load balancing effect of many interconnected links.
The flow chart of the flow load sharing method that Fig. 4 A provides for the embodiment of the present invention four.With reference to Fig. 4 A, the method for the present embodiment can comprise:
401, determine whether flow load sharing difference current between interconnected link is more than or equal to preset difference value.
If 402 determine that between interconnected link, current flow load sharing difference is more than or equal to preset difference value, by spreading the first hardware table item, obtain the second hardware table item.
For instance, if carry out load balancing with 3 outgoing interfaces.Suppose that outgoing interface is respectively outgoing interface 1, outgoing interface 2 and outgoing interface 3.The first hardware table item is 3,3 first hardware table item difference corresponding outgoing interface 1, outgoing interface 2 and outgoing interfaces 3.If determine that between interconnected link, current flow load sharing difference is more than or equal to preset difference value, the number of the first hardware table item can be expanded as to original 2 times, obtain 6 the second hardware table items, so that flow is segmented.
403, will treat that according to the number of the second hardware table item output flow carries out Hash operation, to obtain the Hash operation result of mating with the second hardware table item.
For instance, for 6 the second hardware table items, treat the Hash operation result that output flow carries out after Hash operation and be respectively 0,1,2,3,4,5, Hash operation result 0,1,2,3,4,5 respectively with the second hardware table item coupling.For example, Hash operation result 0 coupling the second hardware table item 0, Hash operation result 1 coupling the second hardware table item 1, by that analogy.
404,, according to the Hash operation result, determine the corresponding relation for the treatment of output flow and the second hardware table item.
405,, according to corresponding relation, the outgoing interface output corresponding from the second hardware table item will be passed through until output flow after the second hardware table item.
Owing to having stored the outgoing interface identification information corresponding with it in each second hardware table item, therefore can obtain the outgoing interface that each the second hardware table item is corresponding according to the outgoing interface identification information, thus the output of outgoing interface that can the flow after every second hardware table item is corresponding from this second hardware table item.For example, simultaneously can be referring to Fig. 4 B, the schematic diagram of the flow load sharing method that Fig. 4 B provides for the embodiment of the present invention four, if the corresponding outgoing interface 1 of the second hardware table item 0, the flow 0 of Hash operation result 0 correspondence after the second hardware table item 0 from outgoing interface 1 output; The corresponding outgoing interface 2 of the second hardware table item 1, the flow 1 of Hash operation result 1 correspondence is being exported from outgoing interface 2 after the second hardware table item 1; The corresponding outgoing interface 3 of the second hardware table item 2, the flow 2 of Hash operation result 2 correspondences is being exported from outgoing interface 3 after the second hardware table item 2; The corresponding outgoing interface 1 of the second hardware table item 3, the flow 3 of Hash operation result 3 correspondences is being exported from outgoing interface 1 after the second hardware table item 3; The corresponding outgoing interface 2 of the second hardware table item 4, the flow 4 of Hash operation result 4 correspondences is being exported from outgoing interface 2 after the second hardware table item 4; The corresponding outgoing interface 3 of the second hardware table item 5, the flow 5 of Hash operation result 5 correspondences is being exported from outgoing interface 3 after the second hardware table item 5.
After carrying out 401 to 405, can continue by the flow situation of the load balancing outgoing interface of real-time monitor network equipment, obtain the flow load sharing difference between the link of the link of flow maximum between many interconnected links and flow minimum, and judge whether current load balancing difference is more than or equal to preset difference value.If between interconnected link, current flow load sharing difference still, not in the preset difference value scope, can further reduce the flow load sharing difference by 406 to 407.
406,, according to the regulation rule of setting, obtain the 4th hardware table item by adjusting the position of the outgoing interface corresponding with the second hardware table item in the second hardware table item, to reduce the flow load sharing difference.
Adjust according to the regulation rule of setting the position of outgoing interface in the second hardware table item that the second hardware table item is corresponding, can adjust the position of interface in the second hardware table item for the position of several groups of outgoing interfaces in hardware table item by setting in advance, also can adjust the position of each outgoing interface in the second hardware table item according to the mode of permutation and combination.For example adjust the position of outgoing interface in the second hardware table item provided in 405 as follows: adjusting the corresponding outgoing interface 1 of the second hardware table item 3 and be adjusted into the corresponding outgoing interface 3 of the second hardware table item 3, is also that the second hardware table item 3 of corresponding outgoing interface 3 is the 4th hardware table item 3; The corresponding outgoing interface 2 of the second hardware table item 5 is adjusted into the corresponding outgoing interface 1 of the second hardware table item 5, is also that the second hardware table item 5 of corresponding outgoing interface 1 is the 4th hardware table item 5.All the other do not adjust respectively corresponding corresponding the 4th hardware table item of the second hardware table item of the position of interface in the second hardware table item.The 4th hardware table item obtained after adjusting and the corresponding relation of outgoing interface can be referring to Fig. 4 C, a kind of schematic diagram that adjusts flow and outgoing interface corresponding relation behind the position of interface in hardware table item that Fig. 4 C provides for the embodiment of the present invention four, after adjustment, in conjunction with Fig. 4 B and Fig. 4 C, can find out, before adjusting, flow 3 is from outgoing interface 1 output, and after adjusting, flow 3 is exported from outgoing interface 3, thereby further optimize the flow load sharing effect.
407, outgoing interface output that will be corresponding from the 4th hardware table item by the flow of the 4th hardware table item.
Further, after carrying out 407, if between interconnected link, current flow load sharing difference is not still in the preset difference value scope, can continues to carry out 408～410 and further reduce the flow load sharing difference:
408, statistics is by the flow of each the 4th hardware table item;
409, will carry out order according to uninterrupted by the flow of each the 4th hardware table item arranges;
410, issue five stiffness part list item according to putting in order of uninterrupted, with outgoing interface output that will be corresponding from five stiffness part list item by the flow of five stiffness part list item, reduce the flow load sharing difference, wherein, five stiffness part list item is the list item that puts in order and obtain by adjusting the position of the outgoing interface corresponding with the 4th hardware table item in the 4th hardware table item according to uninterrupted.
After counting the flow that each the 4th hardware table item passes through, arranged flow is descending, for example put in order as flow 1 flow 5 flow 2 flow 0 flow 4 flow 3, then according to the uninterrupted order, issue five stiffness part list item.For example can take the little flow of a largest flow and first according to outgoing interface 1, outgoing interface 2 takies the little flow of second largest flow and second, outgoing interface 3 takies the rule of the little flow of a third-largest flow and the 3rd, readjusts the position of outgoing interface in the 4th hardware table item with this and re-issues five stiffness part list item.The corresponding relation that adjusts flow and outgoing interface behind the position of interface in the 4th hardware table item can be referring to shown in Fig. 4 D, the another kind that Fig. 4 D provides for the embodiment of the present invention four adjusts the schematic diagram of flow and outgoing interface corresponding relation behind the position of interface in hardware table item, from Fig. 4 D, can find out, after adjusting, flow 0 and flow 2 are from outgoing interface 3 outputs, flow 1 and flow 3 are from outgoing interface 1 output, flow 4 and flow 5 are exported from outgoing interface 2, thereby further optimize the flow load sharing effect.It should be noted that, also outgoing interface 2 can be taken to the little flow of a largest flow and first, other two outgoing interfaces are combined according to the uninterrupted order again.
Further, after carrying out 408～410, can further reduce flow load sharing difference current between interconnected link, optimize the load balancing effect.If determine that between interconnected link, current flow load sharing difference is more than or equal to preset difference value, can carry out again 411 and further optimize again the load balancing effect.
411, the multiple of increase diffusion the first hardware table item, and startup flow load sharing Optimization Mechanism is adjusted the first hardware table item, to reduce the flow load sharing difference.
At this, it should be noted that, owing to having increased the multiple that spreads the first hardware table item, start when the flow load sharing Optimization Mechanism is adjusted the first hardware table item and can obtain more the second hardware table item of more number, carry out thinner division to treat output flow, thereby further optimize the load balancing effect.Carry out 411 optimize after, if between interconnected link, current flow load sharing difference is not still in the preset difference value scope, can further reduce the flow load sharing difference by the technical scheme that repeats above-mentioned arbitrary embodiment and provide.If between interconnected link, current flow load sharing difference is appointed so not in the preset difference value scope, carry out again 411, continue to optimize the load balancing effect, until between interconnected link, current flow load sharing difference reaches in the preset difference value scope or the multiple that increases diffusion the first hardware table item reaches allowed maximum multiple.
The flow load sharing method that the present embodiment provides, pass through corresponding relation, by pass through after the second hardware table item the outgoing interface output corresponding from the second hardware table item until output flow, further according to the regulation rule of setting, adjust the position of the outgoing interface corresponding with the second hardware table item in the second hardware table item and obtain the 4th hardware table item, outgoing interface output that will be corresponding from the 4th hardware table item by the flow of the 4th hardware table item, further statistics is by the flow of each the 4th hardware table item, to carry out order according to uninterrupted by the flow of each the 4th hardware table item arranges, issue five stiffness part list item according to putting in order of uninterrupted, further to reduce the flow load sharing difference.Thereby between many interconnected links that solved flow load sharing, the problem of traffic sharing great disparity, reduced the flow load sharing difference, makes the flow load sharing difference in the preset difference value scope, optimized the load balancing effect of many interconnected links.
The structural representation of the flow load sharing device 500 that Fig. 5 provides for the embodiment of the present invention five.The flow that the device of the present embodiment is applicable to that many interconnected links of formation flow load sharing are shared carries out the situation of flow equalization.This device is realized in the mode of hardware and/or software usually.With reference to Fig. 5, this device comprises as lower module: difference determination module 510, hardware table item obtain module 520, flow output module 530.
Wherein, hardware table item obtains module 520 specifically for by spreading the first hardware table item, obtaining the second hardware table item.Flow output module 530 will treat that specifically for the number according to the second hardware table item output flow carries out Hash operation, to obtain the Hash operation result of mating with the second hardware table item; According to the Hash operation result, determine the corresponding relation for the treatment of output flow and the second hardware table item; According to corresponding relation, the outgoing interface output corresponding from the second hardware table item will be passed through until output flow after the second hardware table item.
Further, hardware table item obtains module 520 also for according to corresponding relation, and by pass through after the second hardware table item the outgoing interface output corresponding from the second hardware table item until output flow after, statistics is by the flow of each the second hardware table item; To carry out order according to uninterrupted by the flow of each the second hardware table item arranges; According to putting in order of uninterrupted, obtain the 3rd hardware table item by adjusting the position of the outgoing interface corresponding with the second hardware table item in the second hardware table item, to reduce the flow load sharing difference; Flow output module 530 is also exported for outgoing interface that will be corresponding from the 3rd hardware table item by the flow of the 3rd hardware table item.
Further, hardware table item obtains module 520 also for according to corresponding relation, by pass through after the second hardware table item the outgoing interface output corresponding from the second hardware table item until output flow after, according to the regulation rule of setting, obtain the 4th hardware table item by adjusting the position of the outgoing interface corresponding with the second hardware table item in the second hardware table item, to reduce the flow load sharing difference; Flow output module 530 is also exported for outgoing interface that will be corresponding from the 4th hardware table item by the flow of the 4th hardware table item.
Further, flow output module 530 is also for the regulation rule according to setting, after adjusting position acquisition four hardware table item of the outgoing interface corresponding with the second hardware table item in the second hardware table item, statistics is by the flow of each the 4th hardware table item; To carry out order according to uninterrupted by the flow of each the 4th hardware table item arranges; Issue five stiffness part list item according to putting in order of uninterrupted, with outgoing interface output that will be corresponding from five stiffness part list item by the flow of five stiffness part list item, reduce the flow load sharing difference, wherein, five stiffness part list item is the list item that puts in order and obtain by adjusting the position of the outgoing interface corresponding with the 4th hardware table item in the 4th hardware table item according to uninterrupted.
Further, difference determination module 510 is also for will be after output flow passes through the second hardware table item, carrying out and determining between interconnected link, whether current flow load sharing difference is more than or equal to preset difference value after corresponding outgoing interface output from the second hardware table item;
If hardware table item obtains module 520 also for determining that between interconnected link, current flow load sharing difference is more than or equal to preset difference value, increase the multiple of diffusion the first hardware table item, and start the flow load sharing Optimization Mechanism the first hardware table item is adjusted, to reduce the flow load sharing difference.
The flow load sharing device that the present embodiment provides, adjusted the first hardware table item by starting the flow load sharing Optimization Mechanism, obtains the second hardware table item, by the second hardware table item, to reduce the flow load sharing difference.Thereby between many interconnected links that solved flow load sharing, the problem of traffic sharing great disparity, reduced the flow load sharing difference, optimized the load balancing effect of many interconnected links.
One of ordinary skill in the art will appreciate that: all or part of hardware that can be relevant by program command of realizing above-mentioned each embodiment of the method completes.Aforesaid program can be stored in a computer read/write memory medium.This program, when carrying out, is carried out and to be comprised above-mentioned each embodiment of the method; And aforesaid storage medium comprises: various media that can be program code stored such as ROM, RAM, magnetic disc or CDs.
Finally it should be noted that: above each embodiment, only in order to technical scheme of the present invention to be described, is not intended to limit; Although with reference to aforementioned each embodiment, the present invention is had been described in detail, those of ordinary skill in the art is to be understood that: its technical scheme that still can put down in writing aforementioned each embodiment is modified, or some or all of technical characterictic wherein is equal to replacement; And these modifications or replacement do not make the essence of appropriate technical solution break away from the scope of various embodiments of the present invention technical scheme.
Claims (14)
1. a flow load sharing method, is characterized in that, comprising:
Determine whether flow load sharing difference current between interconnected link is more than or equal to preset difference value;
If determine, between described interconnected link, current flow load sharing difference is more than or equal to preset difference value, starting the flow load sharing Optimization Mechanism is adjusted the first hardware table item, obtain the second hardware table item, by described the second hardware table item, to reduce described flow load sharing difference;
The outgoing interface output corresponding from described the second hardware table item will be passed through until output flow after described the second hardware table item;
Wherein, described preset difference value is determined according to the flow of user's request or described outgoing interface reality, the integral multiple of the number that the number of described the second hardware table item is described the first hardware table item.
2. method according to claim 1, is characterized in that, described startup flow load sharing Optimization Mechanism is adjusted the first hardware table item, obtains the second hardware table item, comprising:
Obtain described the second hardware table item by spreading described the first hardware table item.
3. method according to claim 1 and 2, is characterized in that, described will be after output flow passes through described the second hardware table item the corresponding outgoing interface output from described the second hardware table item, comprising:
Treat that by described output flow carries out Hash operation according to the number of described the second hardware table item, to obtain the Hash operation result of mating with described the second hardware table item;
According to described Hash operation result, determine the described corresponding relation for the treatment of output flow and described the second hardware table item;
According to described corresponding relation, by the described corresponding outgoing interface output from described the second hardware table item after output flow passes through described the second hardware table item.
4. method according to claim 3, is characterized in that, described, according to described corresponding relation, by described, after output flow passes through described the second hardware table item, from described the second hardware table item, after the output of corresponding outgoing interface, also comprises:
Statistics is by the flow of each described the second hardware table item;
To carry out order according to uninterrupted by the flow of each described the second hardware table item arranges;
According to putting in order of uninterrupted, obtain the 3rd hardware table item by adjusting the position of the outgoing interface corresponding with described the second hardware table item in described the second hardware table item, to reduce described flow load sharing difference;
Outgoing interface output that will be corresponding from described the 3rd hardware table item by the flow of described the 3rd hardware table item.
5. method according to claim 3, is characterized in that, described, according to described corresponding relation, by described, after output flow passes through described the second hardware table item, from described the second hardware table item, after the output of corresponding outgoing interface, also comprises:
According to the regulation rule of setting, obtain the 4th hardware table item by adjusting the position of the outgoing interface corresponding with described the second hardware table item in described the second hardware table item, to reduce described flow load sharing difference;
Outgoing interface output that will be corresponding from described the 4th hardware table item by the flow of described the 4th hardware table item.
6. method according to claim 5, is characterized in that, at the described regulation rule according to setting, after adjusting position acquisition four hardware table item of the outgoing interface corresponding with described the second hardware table item in described the second hardware table item, also comprises:
Statistics is by the flow of each described the 4th hardware table item;
To carry out order according to uninterrupted by the flow of each described the 4th hardware table item arranges;
Issue five stiffness part list item according to putting in order of uninterrupted, with outgoing interface output that will be corresponding from described five stiffness part list item by the flow of described five stiffness part list item, reduce described flow load sharing difference, wherein, described five stiffness part list item is the list item that puts in order and obtain by adjusting the position of the outgoing interface corresponding with described the 4th hardware table item in described the 4th hardware table item according to described uninterrupted.
7. according to the described method of any one in claim 1～6, it is characterized in that, will be after output flow passes through described the second hardware table item, also comprise after corresponding outgoing interface output from described the second hardware table item described:
Between the definite interconnected link of execution, whether current flow load sharing difference is more than or equal to the step of preset difference value;
If determine, between described interconnected link, current flow load sharing difference is more than or equal to preset difference value, increase the multiple of described the first hardware table item of diffusion, and start described flow load sharing Optimization Mechanism described the first hardware table item is adjusted, to reduce described flow load sharing difference.
8. a flow load sharing device, is characterized in that, comprising:
The difference determination module, for determining between interconnected link, whether current flow load sharing difference is more than or equal to preset difference value;
Hardware table item obtains module, if for determining that between described interconnected link, current flow load sharing difference is more than or equal to preset difference value, starting the flow load sharing Optimization Mechanism is adjusted the first hardware table item, obtain the second hardware table item, by described the second hardware table item, to reduce described flow load sharing difference;
The flow output module, for will be after output flow passes through described the second hardware table item the corresponding outgoing interface output from described the second hardware table item;
Wherein, described preset difference value is determined according to the flow of user's request or described outgoing interface reality, the integral multiple of the number that the number of described the second hardware table item is described the first hardware table item.
9. device according to claim 8, is characterized in that, described hardware table item obtains module, specifically for by spreading described the first hardware table item, obtaining described the second hardware table item.
10. device according to claim 8 or claim 9, it is characterized in that, described flow output module, treat that by described output flow carries out Hash operation specifically for the number according to described the second hardware table item, to obtain the Hash operation result of mating with described the second hardware table item; According to described Hash operation result, determine the described corresponding relation for the treatment of output flow and described the second hardware table item; According to described corresponding relation, by the described corresponding outgoing interface output from described the second hardware table item after output flow passes through described the second hardware table item.
11. device according to claim 10, it is characterized in that, described hardware table item obtains module, also for described according to described corresponding relation, by described after output flow passes through described the second hardware table item from described the second hardware table item after the output of corresponding outgoing interface, statistics is by the flow of each described the second hardware table item; To carry out order according to uninterrupted by the flow of each described the second hardware table item arranges; According to putting in order of uninterrupted, obtain the 3rd hardware table item by adjusting the position of the outgoing interface corresponding with described the second hardware table item in described the second hardware table item, to reduce described flow load sharing difference;
Described flow output module, also export for outgoing interface that will be corresponding from described the 3rd hardware table item by the flow of described the 3rd hardware table item.
12. device according to claim 10, it is characterized in that, described hardware table item obtains module, also for described according to described corresponding relation, by described after output flow passes through described the second hardware table item from described the second hardware table item after the output of corresponding outgoing interface, according to the regulation rule of setting, obtain the 4th hardware table item by adjusting the position of the outgoing interface corresponding with described the second hardware table item in described the second hardware table item, to reduce described flow load sharing difference;
Described flow output module, also export for outgoing interface that will be corresponding from described the 4th hardware table item by the flow of described the 4th hardware table item.
13. device according to claim 12, it is characterized in that, described flow output module, also at the described regulation rule according to setting, after adjusting position acquisition four hardware table item of the outgoing interface corresponding with described the second hardware table item in described the second hardware table item, statistics is by the flow of each described the 4th hardware table item; To carry out order according to uninterrupted by the flow of each described the 4th hardware table item arranges; Issue five stiffness part list item according to putting in order of uninterrupted, with outgoing interface output that will be corresponding from described five stiffness part list item by the flow of described five stiffness part list item, reduce described flow load sharing difference, wherein, described five stiffness part list item is the list item that puts in order and obtain by adjusting the position of the outgoing interface corresponding with described the 4th hardware table item in described the 4th hardware table item according to described uninterrupted.
14. the described device of any one according to Claim 8～13, it is characterized in that, described difference determination module, also for described, will be after output flow passes through described the second hardware table item from described the second hardware table item, after corresponding outgoing interface output, carry out and determine between interconnected link, whether current flow load sharing difference is more than or equal to preset difference value;
Described hardware table item obtains module, if also for determining that between described interconnected link, current flow load sharing difference is more than or equal to preset difference value, increase the multiple of described the first hardware table item of diffusion, and start described flow load sharing Optimization Mechanism described the first hardware table item is adjusted, to reduce described flow load sharing difference.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310476090.7A CN103491021A (en) | 2013-10-12 | 2013-10-12 | Method and device for sharing traffic load |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310476090.7A CN103491021A (en) | 2013-10-12 | 2013-10-12 | Method and device for sharing traffic load |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103491021A true CN103491021A (en) | 2014-01-01 |
Family
ID=49830990
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310476090.7A Pending CN103491021A (en) | 2013-10-12 | 2013-10-12 | Method and device for sharing traffic load |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103491021A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105471761A (en) * | 2015-08-07 | 2016-04-06 | 北京汉柏科技有限公司 | Exchange equipment load adjustment method and device |
| WO2016145737A1 (en) * | 2015-03-19 | 2016-09-22 | 中兴通讯股份有限公司 | Load sharing method and device |
| CN106909528A (en) * | 2015-12-23 | 2017-06-30 | 华为技术有限公司 | The dispatching method and device of a kind of data transfer |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101977162B (en) * | 2010-12-03 | 2012-01-18 | 电子科技大学 | Load balancing method of high-speed network |
| CN102447636A (en) * | 2012-01-06 | 2012-05-09 | 中兴通讯股份有限公司 | Load sharing method and device of data center communication equipment |
-
2013
- 2013-10-12 CN CN201310476090.7A patent/CN103491021A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101977162B (en) * | 2010-12-03 | 2012-01-18 | 电子科技大学 | Load balancing method of high-speed network |
| CN102447636A (en) * | 2012-01-06 | 2012-05-09 | 中兴通讯股份有限公司 | Load sharing method and device of data center communication equipment |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016145737A1 (en) * | 2015-03-19 | 2016-09-22 | 中兴通讯股份有限公司 | Load sharing method and device |
| CN105471761A (en) * | 2015-08-07 | 2016-04-06 | 北京汉柏科技有限公司 | Exchange equipment load adjustment method and device |
| CN106909528A (en) * | 2015-12-23 | 2017-06-30 | 华为技术有限公司 | The dispatching method and device of a kind of data transfer |
| CN106909528B (en) * | 2015-12-23 | 2019-08-13 | 华为技术有限公司 | A kind of dispatching method and device of data transmission |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11212808B2 (en) | Coordinated control of media playback | |
| US9843484B2 (en) | Graceful scaling in software driven networks | |
| CN113315700A (en) | Computing resource scheduling method, device and storage medium | |
| CN106878920A (en) | Data forwarding method, its device, bluetooth equipment and audio frequency transmission method | |
| WO2016019871A1 (en) | Mechanisms to support service chain graphs in a communication network | |
| CN103929368A (en) | Load balance method and device for multiple service units | |
| CN104079445A (en) | Distributed type pressure testing system and method | |
| CN102316043B (en) | Port virtualization method, switch and communication system | |
| CN103001892B (en) | Based on network resource allocation method and the system of cloud computing | |
| US10521182B2 (en) | Method and terminal for controlling grouping play of playing system | |
| CN103491021A (en) | Method and device for sharing traffic load | |
| CN104486712A (en) | Volume adjusting method and device of wireless loudspeaker box system | |
| CN105763472A (en) | Trans-board forwarding method and device | |
| CN102638406A (en) | Flow control method, device and network equipment | |
| CN101729425A (en) | Method and equipment for flow sending in VRRP networking | |
| US20220224778A1 (en) | Delivery of media content to a media device via multiple data packet streams | |
| CN103326887A (en) | Interface management method and system | |
| CN103336670A (en) | Method and device for automatic distribution of data blocks based on data temperature | |
| WO2014162917A1 (en) | Video switching device, video switching method, program, and information processing device | |
| CN103905341B (en) | Resource regulating method, apparatus and system | |
| CN104284099A (en) | Large-screen display method and system based on multi-channel input | |
| CN105047210B (en) | A kind of the striding equipment synchronous method and device of shuffle playlist | |
| CN108833570B (en) | Cluster storage and balanced transmission system based on cloud storage | |
| CN106210781A (en) | A kind of multichannel control method for playing back and system | |
| US10797957B2 (en) | Network management apparatus, network management method, network management system, and program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20140101 |