CN109525504A - Throughput of network device limitation, statistical method and device - Google Patents
Throughput of network device limitation, statistical method and device Download PDFInfo
- Publication number
- CN109525504A CN109525504A CN201811268355.3A CN201811268355A CN109525504A CN 109525504 A CN109525504 A CN 109525504A CN 201811268355 A CN201811268355 A CN 201811268355A CN 109525504 A CN109525504 A CN 109525504A
- Authority
- CN
- China
- Prior art keywords
- time
- handling capacity
- virtual system
- limitation
- throughput
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/22—Traffic shaping
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/23—Bit dropping
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/28—Flow control; Congestion control in relation to timing considerations
- H04L47/286—Time to live
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/32—Flow control; Congestion control by discarding or delaying data units, e.g. packets or frames
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
This specification provides a kind of throughput of network device method for limiting and device, throughput of network device limitation statistical method and device, which comprises the described method includes: the time-out time of the last virtual system handling capacity limitation of the virtual system distance of statistics network equipment；If the time-out time be no more than limitation time interval, and current virtual system handling capacity limitation statistical value be greater than or equal to virtual system handling capacity limits value when, carry out packet loss processing；If the time-out time is more than limitation time interval, the handling capacity limitation time-out time for updating virtual system is current time, and limits statistical value using the handling capacity of atomic operation resetting virtual system.Accurate control is realized in this specification scheme, the limitation by atomic operation to handling capacity, and is reduced on performance of network equipments influence.In addition, the implementation isolated with handling capacity limitation is counted using handling capacity real time monitoring, the greatly less influence for supporting handling capacity limitation function to equipment performance.
Description
Technical field
This specification be related to computer internet technical field more particularly to a kind of throughput of network device method for limiting and
Device, throughput of network device statistical method and device.
Background technique
In actual network application scene, for supporting the network equipment of virtual system, for the reality to the network equipment
When applicable cases be monitored, need the handling capacity to each virtual system to monitor in real time, furthermore network device management person is
Each network user's Internet Use effectively supervised, it is sometimes desirable to which the handling capacity of certain virtual systems is limited
System, or even different limitations is carried out using the different situations of user according to each virtual system respectively and is handled, it at this moment requires to net
Network equipment not only wants the handling capacity of each virtual system of real-time statistics, more requires to match the handling capacity of each virtual system according to user
The demand of setting makes corresponding limitation processing.
Virtual system (Virtual System), refer to a physical network device is logically divided into it is multiple virtual
System, each virtual system can be regarded as a completely self-contained network equipment, can possess independent system resource, pipe
Reason person, security strategy, user authentication data library etc..Handling capacity (Throughput) refers to that the network equipment successfully connects in the unit time
Receive and forward the quantity of data, i.e. the equipment data rate that receives and forward, unit is bps (bit/s).
In business processing, typically multicore concurrently carries out business processing to the CPU of current network device, when will be to void
When the handling capacity of quasi- system is limited, need to solve uniformly to gulp down under the concurrent service processing mode of CPU multicore and virtual system
The amount of spitting limitation, since the more data cores of CPU are to maintain identical working efficiency in business processing substantially, i.e., each cpu data core
Handling capacity be basis equalization.Based on These characteristics, in order in the case where not impacted to equipment performance as far as possible
It realizes and the handling capacity of the network equipment is limited, prior art is usually to limit the device throughput under every virtual system
It is converted to the handling capacity limitation of each cpu data core under every virtual system to realize, i.e., when handling capacity limits, is converted to every
A CPU is independently limited, to cause to compete to influence equipment between each cpu data core when handling capacity being avoided to limit
Energy.
Above-mentioned prior art, can be as average by business processing as possible in CPU multicore treatment mechanism processing business
Distribution to each business processing data core, but due to the handling capacity size of every flow packet in real network application be not fixed and with
Machine is uncontrollable, is unable to reach the absolute business of each cpu data core and is averaged, so as to cause the handling capacity of certain cpu data cores
More than limits value, and certain CPU are also less than handling capacity limits value, affect the accuracy of handling capacity limitation.In addition, with
Technology is fast-developing, and the service condition of each cpu data core has differences between the different types of network equipment, if be completely dependent on
Each cpu data core service condition and traffic assignments situation carry out handling capacity limitation, and limitation is more prominent, can not be compatible with different productions
The network equipment of category type, different cpu types.
Summary of the invention
To overcome the problems in correlation technique, present description provides throughput of network device method for limiting and dresses
It sets, throughput of network device statistical method and device.
According to this specification embodiment in a first aspect, providing a kind of throughput of network device method for limiting, the method
Include:
The time-out time of the last virtual system handling capacity limitation of the virtual system distance of statistics network equipment；
If the time-out time is no more than limitation time interval, and the handling capacity limitation statistical value of current virtual system is greater than
Or equal to virtual system handling capacity limits value when, carry out packet loss processing；
If the time-out time is more than limitation time interval, the handling capacity limitation time-out time for updating virtual system is to work as
The preceding time, and statistical value is limited using the handling capacity of atomic operation resetting virtual system.
A kind of throughput of network device statistical method, comprising:
When every message flow flows through the network equipment, whether judgement currently needs to carry out handling capacity limitation；
If desired, the handling capacity of the network equipment is limited using throughput of network device method for limiting above-mentioned；
Otherwise, the handling capacity real-time statistics of the network equipment are obtained according to the throughput statistics value of the virtual system
Value.
According to the second aspect of this specification embodiment, a kind of throughput of network device limits device is provided, comprising:
Statistical module, the time-out of the last virtual system handling capacity limitation of virtual system distance for statistics network equipment
Time；
Module is limited, if being no more than limitation time interval, and the handling capacity of current virtual system for the time-out time
When limiting handling capacity limits value of the statistical value more than or equal to virtual system, packet loss processing is carried out；
Module is reset, if being more than limitation time interval for the time-out time, updates the handling capacity limit of virtual system
Time-out time processed is current time, and limits statistical value using the handling capacity of atomic operation resetting virtual system.
A kind of throughput of network device statistic device, described device include:
Judging unit, for when every message flow flows through the network equipment, whether judgement currently to need to carry out handling capacity limit
System；
Limiting unit, for utilizing throughput of network device method for limiting above-mentioned when needing to carry out handling capacity limitation
The handling capacity of the network equipment is limited；
Statistic unit, for do not need carry out handling capacity limitation when, according to the throughput statistics value of the virtual system
Obtain the handling capacity real-time statistics value of the network equipment.
According to the third aspect of this specification embodiment, a kind of device is provided, comprising:
Processor；
Memory for storage processor executable instruction；
Wherein, the processor is configured to:
The time-out time of the last virtual system handling capacity limitation of the virtual system distance of statistics network equipment；
If the time-out time is no more than limitation time interval, and the handling capacity limitation statistical value of current virtual system is greater than
Or equal to virtual system handling capacity limits value when, carry out packet loss processing；
If the time-out time is more than limitation time interval, the handling capacity limitation time-out time for updating virtual system is to work as
The preceding time, and statistical value is limited using the handling capacity of atomic operation resetting virtual system.
Or
When every message flow flows through the network equipment, whether judgement currently needs to carry out handling capacity limitation；
If desired, the handling capacity of the network equipment is limited using throughput of network device method for limiting above-mentioned；
Otherwise, the handling capacity real-time statistics of the network equipment are obtained according to the throughput statistics value of the virtual system
Value.
The technical solution that the embodiment of this specification provides can include the following benefits:
In this specification embodiment, limitation by atomic operation to handling capacity, without relying on other function conduct
Condition solves the problems, such as that multi-core CPU system concurrency executes, and realizes accurate control, and reduces on performance of network equipments influence.
In addition, counting the implementation isolated with handling capacity limitation using handling capacity real time monitoring, greatly reduce
Support influence of the handling capacity limitation function to equipment performance, effectively eliminating the function may shadow caused by equipment performance
It rings.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
This specification can be limited.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows the reality for meeting this specification
Example is applied, and is used to explain the principle of this specification together with specification.
Fig. 1 is a kind of this specification process of throughput of network device method for limiting shown according to an exemplary embodiment
Figure.
Fig. 2 is this specification handling capacity limitation flow chart shown according to an exemplary embodiment.
Fig. 3 is a kind of this specification process of throughput of network device statistical method shown according to an exemplary embodiment
Figure.
Fig. 4 is this specification handling capacity monitoring flow chart shown according to an exemplary embodiment.
Fig. 5 is a kind of this specification frame of throughput of network device limits device shown according to an exemplary embodiment
Figure.
Fig. 6 is a kind of this specification frame of throughput of network device statistic device shown according to an exemplary embodiment
Figure.
Fig. 7 is a kind of hardware configuration of computer equipment where this specification embodiment throughput of network device statistic device
Figure.
Specific embodiment
Example embodiments are described in detail here, and the example is illustrated in the accompanying drawings.Following description is related to
When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment
Described in embodiment do not represent all embodiments consistent with this specification.On the contrary, they are only and such as institute
The example of the consistent device and method of some aspects be described in detail in attached claims, this specification.
It is only to be not intended to be limiting this explanation merely for for the purpose of describing particular embodiments in the term that this specification uses
Book.The "an" of used singular, " described " and "the" are also intended to packet in this specification and in the appended claims
Most forms are included, unless the context clearly indicates other meaning.It is also understood that term "and/or" used herein is
Refer to and includes that one or more associated any or all of project listed may combine.
It will be appreciated that though various information may be described using term first, second, third, etc. in this specification, but
These information should not necessarily be limited by these terms.These terms are only used to for same type of information being distinguished from each other out.For example, not taking off
In the case where this specification range, the first information can also be referred to as the second information, and similarly, the second information can also be claimed
For the first information.Depending on context, word as used in this " if " can be construed to " ... when " or
" when ... " or " in response to determination ".
Next this specification embodiment is described in detail.
As shown in Figure 1, Fig. 1 is a kind of this specification throughput of network device limitation shown according to an exemplary embodiment
The flow chart of method, comprising the following steps:
In the time-out that the virtual system of step S102, statistics network equipment is limited apart from upper primary virtual system handling capacity
Between.
In this step, it is monitored process in the real-time applicable cases to the network equipment, when needing to gulp down to virtual system
When the amount of spitting is limited, limitation time interval, the i.e. time cycle of handling capacity limitation can be set, in upper primary carry out handling capacity
After limitation, time-out time is counted.
If being no more than limitation time interval, and the handling capacity limit of current virtual system in step S104, the time-out time
When statistical value processed is greater than or equal to the handling capacity limits value of virtual system, packet loss processing is carried out.
In above-mentioned steps, it is no more than in limitation time interval in time-out time, real-time statistics virtual system is limited from the last time
Current throughput condition is made, if the handling capacity limitation statistical value of virtual system is greater than or equal to the handling capacity of virtual system
Limits value needs to limit the handling capacity of virtual system at this time, carries out packet loss processing；Avoid the handling capacity mistake of the network equipment
It carries.
As embodiment, statistical value is limited for the handling capacity of virtual system, the current flow of virtual system can be gulped down
The amount of spitting is added on the handling capacity limitation statistical value currently counted, calculates and value obtains.For limiting time interval, in order to just
In calculating, unit time, i.e. 1s can be taken.
In one embodiment, if may further comprise: in step 104, the time-out time was no more than between the limitation time
Every, and current virtual system handling capacity limitation statistical value be less than virtual system handling capacity limits value when, utilize atomic operation will
The current traffic throughput of virtual system is superimposed on the handling capacity limitation statistical value.
The step of above-described embodiment, limits in the handling capacity limitation statistical value of current virtual system less than virtual system handling capacity
When value processed, continue to count the current traffic throughput of virtual system, the handling capacity that is added to limits on statistical value.
If being more than limitation time interval in step S106, the time-out time, the handling capacity limitation of virtual system is updated
Time-out time is current time, and limits statistical value using the handling capacity of atomic operation resetting virtual system.
In above-mentioned steps, when time-out time is more than limitation time interval, due to not triggering the handling capacity to virtual system
Limitation, the handling capacity limitation time-out time for updating virtual system at this time is current time, is carried out in restrictive cycle next time；Simultaneously
Statistical value is limited using the handling capacity of atomic operation resetting virtual system, removes and counted handling capacity in a upper period, restart
Statistics.
Here, by limitation of the atomic operation to handling capacity, without relying on other function as condition, in the operation
Before being finished will not other tasks or event interrupt, solve the problems, such as that multi-core CPU system concurrency executes, realize accurate control,
And reduce on performance of network equipments influence.
A concrete application example is provided below, with reference to figure in throughput of network device method for limiting based on the above embodiment
2, Fig. 2 be this specification handling capacity limitation flow chart shown according to an exemplary embodiment, is mainly included the following steps:
S201 receives business datum flow；
S202 judges that whether the last virtual system handling capacity limitation time-out time of distance updates more than between the limitation time
Every (1s)；If so, executing s203, s204 is otherwise executed；
S203, the handling capacity limitation time-out time for updating virtual system is current time, and resets void using atomic operation
The handling capacity of quasi- system limits statistical value；
S204, judges whether the handling capacity limitation statistical value of current virtual system is greater than or equal to the handling capacity of virtual system
Limits value；If so, executing s206, s205 is otherwise executed,
The current traffic throughput of virtual system is superimposed on handling capacity limitation statistical value by s205 using atomic operation；
S206 carries out packet loss processing to business datum flow.
Above-described embodiment scheme carries out in real time handling capacity limitation by atomic operation to entire virtual system handling capacity
Limitation processing, so that it realizes the realization for being rooted in function itself and being no longer dependent on other function, and can be more acurrate, reliable
Realize limitation function.
Refering to what is shown in Fig. 3, Fig. 3 is a kind of this specification throughput of network device system shown according to an exemplary embodiment
The flow chart of meter method, comprising the following steps:
In step S301, when every message flow flows through the network equipment, judgement currently whether need to carry out handling capacity limitation；
If so, executing S302, S303 is otherwise executed.
As embodiment, whether can currently be needed according to identity marks (ID) judgement for the virtual system for receiving message into
The limitation of row handling capacity, i.e., identified in the network equipment by the identity marks information of virtual system and need to carry out handling capacity limitation
Virtual system.
It handles up in step S302, using the throughput of network device method for limiting of above-mentioned any embodiment the network equipment
Amount is limited, and is then counted again.
In this step, in conjunction with the throughput of network device method for limiting that this specification previous embodiment provides, pass through atom
Operation carries out real-time limitation processing to entire virtual system handling capacity, is adapted to the different types of network equipment.
It is real-time in step S303, the handling capacity for obtaining the network equipment according to the throughput statistics value of the virtual system
Statistical value.
As embodiment, the method for the handling capacity real-time statistics value for obtaining the network equipment can be by described in acquisition
The real-time throughput statistics value of virtual system calculates according to the throughput statistics value and is updating the average value in interval time,
Obtain the handling capacity real-time statistics value of the network equipment.
Wherein, update interval time refers to the update cycle of handling capacity monitoring, and the network equipment can be according to the renewal time
Interval is to update the throughput statistics value currently calculated, and as real-time display data value, updating interval time generally can basis
Demand is set as 2-3s, and the real-time throughput statistics value of virtual system can currently every cpu data core be handled up for virtual system
The sum of amount statistics subtracts corresponding handling capacity real-time statistics value when last update throughput of network device.
Specific calculating process can be such that
Tn=[∑ (tn1+tn2+…tnm)-Tn-1]/τ
In formula, TnIt is the real-time throughput statistics value of current virtual system, tn1+tn2+…tnM is each cpu data core
The sum of throughput statistics, m refer to the quantity of cpu data core, Tn-1Refer to corresponding when last update throughput of network device gulp down
The amount of spitting real-time statistics value, τ are to update interval time.
The scheme of above-described embodiment counts the implementation isolated with handling capacity limitation, pole using handling capacity real time monitoring
Limits reduce the influence for supporting handling capacity limitation function to equipment performance, and handling capacity is monitored in real time and is counted, may be used also
With using the uncontested mechanism of every cpu data and independent statistics, effectively eliminating the function may caused by equipment performance
It influences.
Illustrate that is applied an example below with reference to Fig. 4, Fig. 4, which is that this specification is shown according to an exemplary embodiment, to be handled up
Amount monitors flow chart, is directly limited entire virtual system handling capacity using atom variable by atomic operation in the example
System, and handling capacity real-time statistics use the uncontested realization mechanism of each cpu data core of independent statistics, pass through both processors
System combines, and realizes to throughput statistics and limits both extremely relevant functions, adapts it to different product type, difference
The network equipment of cpu type, this includes the following steps: using example
S401 receives data traffic；
S402 distributes business datum flow to the business processing cpu data core of each virtual system；
Whether s403 currently needs to carry out handling capacity limitation, if executing s404, otherwise according to the ID of virtual system judgement
Execute s409；
S404 judges that the last virtual system handling capacity limitation time-out time of distance updates whether more than 1s, if so, holding
Row s405, otherwise executes s406；
S405, the handling capacity limitation time-out time for updating virtual system is current time, and resets void using atomic operation
The handling capacity of quasi- system limits statistical value；
S406, judges whether the handling capacity limitation statistical value of current virtual system is greater than or equal to the handling capacity of virtual system
Limits value；If so, executing s407, s408 is otherwise executed,
The current traffic throughput of virtual system is superimposed on handling capacity limitation statistical value by s407 using atomic operation；
S408 carries out packet loss processing to business datum flow；
S409 is superimposed to obtain the network equipment using the throughput statistics value of each cpu data core of current virtual system
Handling capacity real-time statistics value；It is the handling capacity of each cpu data core of independent statistics in step statistics.
The scheme of above-described embodiment, it is contemplated that handling capacity real-time statistics function is equipment universal functionality, and the function itself
It is not concerned with the size of data difference of network equipment flow and the business processing situation of each cpu data core, so gulping down under virtual system
The amount of spitting statistics can continue to continue to use uncompetitive implementation between each cpu data core of the prior art, avoid to equipment
The influence of performance.
Device throughput limitation under each virtual system is converted into gulping down for each cpu data core under each virtual system
The amount of spitting limits, i.e., the equipment that the handling capacity limitation of each cpu data core is equal under each virtual system under each virtual system gulps down
The amount of spitting limits the number divided by each cpu data nucleus number mesh, i.e., goodput limit when be converted to each cpu data core into
Row independent limitation causes competition between each cpu data core to cause to influence equipment performance so as to avoid due to handling capacity limitation
Defect.
Corresponding with the embodiment of preceding method, this specification additionally provides throughput of network device limits device and its institute
The embodiment of the terminal of application.
It is a kind of this specification throughput of network device limitation dress shown according to an exemplary embodiment with reference to Fig. 5, Fig. 5
The block diagram set；Described device includes:
Statistical module 102, what the last virtual system handling capacity of virtual system distance for statistics network equipment limited
Time-out time；
Module 104 is limited, if being no more than limitation time interval for the time-out time, and current virtual system is handled up
When amount limitation statistical value is greater than or equal to the handling capacity limits value of virtual system, packet loss processing is carried out；
Module 106 is reset, if being more than limitation time interval for the time-out time, updates the handling capacity of virtual system
Limitation time-out time is current time, and limits statistical value using the handling capacity of atomic operation resetting virtual system.
It is a kind of this specification throughput of network device statistics dress shown according to an exemplary embodiment with reference to Fig. 6, Fig. 6
The block diagram set；Described device includes:
Judging unit 301, for when every message flow flows through the network equipment, whether judgement currently to need to carry out handling capacity
Limitation；
Limiting unit 302, for utilizing the described in any item nets of Claims 1-4 4 when needing to carry out handling capacity limitation
Network device throughput method for limiting limits the handling capacity of the network equipment；
Statistic unit 303, for do not need carry out handling capacity limitation when, according to the throughput statistics of the virtual system
Value obtains the handling capacity real-time statistics value of the network equipment.
The function of modules and the realization process of effect are specifically detailed in the above method and correspond to step in above-mentioned apparatus
Realization process, details are not described herein.
For device embodiment, since it corresponds essentially to embodiment of the method, so related place is referring to method reality
Apply the part explanation of example.The apparatus embodiments described above are merely exemplary, wherein described be used as separation unit
The module of explanation may or may not be physically separated, and the component shown as module can be or can also be with
It is not physical module, it can it is in one place, or may be distributed on multiple network modules.It can be according to actual
The purpose for needing to select some or all of the modules therein to realize this specification scheme.Those of ordinary skill in the art are not
In the case where making the creative labor, it can understand and implement.
The embodiment of this specification throughput of network device limits device can be applied on a computing device, such as service
Device or terminal device.Installation practice can be by software realization, can also be real by way of hardware or software and hardware combining
It is existing.Taking software implementation as an example, as the device on a logical meaning, being will be non-easy by the processor of file process where it
Corresponding computer program instructions are read into memory what operation was formed in the property lost memory.For hardware view, such as Fig. 7 institute
Show, is a kind of hardware structure diagram of computer equipment where this specification embodiment throughput of network device limits device, in addition to
Except processor 710 shown in Fig. 7, memory 730, network interface 720 and nonvolatile memory 740, device in embodiment
Server or electronic equipment where 731 can also include other hardware generally according to the actual functional capability of the computer equipment,
This is repeated no more.
As one embodiment, this specification provides a kind of computer equipment, including memory, processor and is stored in
On reservoir and the computer program that can run on a processor, wherein the processor realizes such as lower section when executing described program
Method:
The time-out time of the last virtual system handling capacity limitation of the virtual system distance of statistics network equipment；
If the time-out time is no more than limitation time interval, and the handling capacity limitation statistical value of current virtual system is greater than
Or equal to virtual system handling capacity limits value when, carry out packet loss processing；
If the time-out time is more than limitation time interval, the handling capacity limitation time-out time for updating virtual system is to work as
The preceding time, and statistical value is limited using the handling capacity of atomic operation resetting virtual system.
As another embodiment, this specification also provides a kind of computer equipment, including memory, processor and storage
On a memory and the computer program that can run on a processor, wherein the processor is realized such as when executing described program
Lower method:
When every message flow flows through the network equipment, whether judgement currently needs to carry out handling capacity limitation；
If desired, the handling capacity of the network equipment is limited using the throughput of network device method for limiting of above-described embodiment
System, is then counted；
Otherwise, the handling capacity real-time statistics of the network equipment are obtained according to the throughput statistics value of the virtual system
Value.
Correspondingly, this specification also provides a kind of network equipment device, described device includes processor；At storage
Manage the memory of device executable instruction；Wherein, the processor is configured to:
The time-out time of the last virtual system handling capacity limitation of the virtual system distance of statistics network equipment；
If the time-out time is no more than limitation time interval, and the handling capacity limitation statistical value of current virtual system is greater than
Or equal to virtual system handling capacity limits value when, carry out packet loss processing；
If the time-out time is more than limitation time interval, the handling capacity limitation time-out time for updating virtual system is to work as
The preceding time, and statistical value is limited using the handling capacity of atomic operation resetting virtual system.
Or the processor is configured to:
When every message flow flows through the network equipment, whether judgement currently needs to carry out handling capacity limitation；
If desired, the handling capacity of the network equipment is limited using the throughput of network device method for limiting of above-described embodiment
System, is then counted；
Otherwise, the handling capacity real-time statistics of the network equipment are obtained according to the throughput statistics value of the virtual system
Value.
In summary each embodiment, the scheme that this specification provides, have it is obvious the utility model has the advantages that
According to practical application status, by handling capacity real time monitoring and handling capacity limitation processing, the two seem highly dependent
Function realization is separated, and different realization mechanisms are respectively adopted, and is greatly reduced and is supported handling capacity limitation function to setting
The influence of standby performance.The uncontested mechanism of each cpu data core independent statistics is still used for handling capacity real time monitoring, effectively
Eliminate the function caused by equipment performance may influence；For handling capacity limitation by atomic operation to entire virtual system
Handling capacity of uniting carries out real-time limitation processing, so that it realizes the reality for being rooted in function itself and being no longer dependent on other functions of modules
It is existing, and energy is more acurrate, reliably realizes limitation function.
The program makes function realization be rooted in functional requirement itself, without considering that external physical condition is for example identical
Different business treatment mechanism etc. of the CPU on heterogeneous networks product under different business treatment mechanism, different type CPU different application
Deng can be widely used in needing the application scenarios of handling capacity real time monitoring and handling capacity limitation function in each network equipment.
When by solving handling capacity limitation using atomic operation to atom variable in existing multi-core CPU system program and
The problem of hair executes is optimal on equipment performance influence for other limitation processes that compare increase the implementations such as spin lock
Implementation.
It is above-mentioned that this specification specific embodiment is described.Other embodiments are in the scope of the appended claims
It is interior.In some cases, the movement recorded in detail in the claims or step can be come according to the sequence being different from embodiment
It executes and desired result still may be implemented.In addition, process depicted in the drawing not necessarily require show it is specific suitable
Sequence or consecutive order are just able to achieve desired result.In some embodiments, multitasking and parallel processing be also can
With or may be advantageous.
Those skilled in the art will readily occur to this specification after considering specification and practicing the invention applied here
Other embodiments.This specification is intended to cover any variations, uses, or adaptations of this specification, these modifications,
Purposes or adaptive change follow the general principle of this specification and do not apply in the art including this specification
Common knowledge or conventional techniques.The description and examples are only to be considered as illustrative, the true scope of this specification and
Spirit is indicated by the following claims.
It should be understood that this specification is not limited to the precise structure that has been described above and shown in the drawings,
And various modifications and changes may be made without departing from the scope thereof.The range of this specification is only limited by the attached claims
System.
The foregoing is merely the preferred embodiments of this specification, all in this explanation not to limit this specification
Within the spirit and principle of book, any modification, equivalent substitution, improvement and etc. done should be included in the model of this specification protection
Within enclosing.
Claims (12)
1. a kind of throughput of network device method for limiting, comprising:
The time-out time of the last virtual system handling capacity limitation of the virtual system distance of statistics network equipment；
If the time-out time is no more than limitation time interval, and the handling capacity limitation statistical value of current virtual system is greater than or waits
When the handling capacity limits value of virtual system, packet loss processing is carried out；
If the time-out time be more than limitation time interval, update virtual system handling capacity limitation time-out time be it is current when
Between, and statistical value is limited using the handling capacity of atomic operation resetting virtual system.
2. the method according to claim 1, wherein further include:
If the time-out time is no more than limitation time interval, and the handling capacity limitation statistical value of current virtual system is less than virtually
When throughput of system limits value, the current traffic throughput of virtual system is superimposed to the handling capacity using atomic operation and is limited
On statistical value.
3. the method according to claim 1, wherein the handling capacity limitation statistical value of the virtual system is virtual
Be superimposed on handling capacity that system has currently counted limitation statistical value current traffic throughput and value.
4. the method according to claim 1, wherein the limitation time interval is the unit time.
5. a kind of throughput of network device statistical method, comprising:
When every message flow flows through the network equipment, whether judgement currently needs to carry out handling capacity limitation；
If desired, it is handled up using the described in any item throughput of network device method for limiting of Claims 1-4 4 network equipment
Amount is limited；
Otherwise, the handling capacity real-time statistics value of the network equipment is obtained according to the throughput statistics value of the virtual system.
6. according to the method described in claim 5, it is characterized in that, being judged according to the identity marks for the virtual system for receiving message
Currently whether need to carry out handling capacity limitation.
7. according to the method described in claim 5, it is characterized in that, described obtain according to the throughput statistics value of the virtual system
The step of taking the handling capacity real-time statistics value of the network equipment include:
The real-time throughput statistics value of the virtual system is obtained, is calculated according to the throughput statistics value and is updating interval time
Interior average value obtains the handling capacity real-time statistics value of the network equipment.
8. the method according to the description of claim 7 is characterized in that the real-time throughput statistics value of the virtual system is virtual
The sum of the throughput statistics of the current every cpu data core of system, which subtract, last updates corresponding handling capacity when throughput of network device
Real-time statistics value.
9. a kind of throughput of network device limits device, described device include:
Statistical module, when the time-out of the last virtual system handling capacity limitation of virtual system distance for statistics network equipment
Between；
Module is limited, if being no more than limitation time interval, and the handling capacity limitation of current virtual system for the time-out time
When statistical value is greater than or equal to the handling capacity limits value of virtual system, packet loss processing is carried out；
Module is reset, if being more than limitation time interval for the time-out time, the handling capacity limitation for updating virtual system is super
When the time be current time, and using atomic operation resetting virtual system handling capacity limit statistical value.
10. a kind of throughput of network device statistic device, described device include:
Judging unit, for when every message flow flows through the network equipment, whether judgement currently to need to carry out handling capacity limitation；
Limiting unit, for utilizing the described in any item network equipments of Claims 1-4 4 when needing to carry out handling capacity limitation
Handling capacity method for limiting limits the handling capacity of the network equipment；
Statistic unit, for being obtained according to the throughput statistics value of the virtual system when not needing to carry out handling capacity limitation
The handling capacity real-time statistics value of the network equipment.
11. a kind of computer equipment including memory, processor and stores the meter that can be run on a memory and on a processor
Calculation machine program, wherein the processor realizes following method when executing described program:
The time-out time of the last virtual system handling capacity limitation of the virtual system distance of statistics network equipment；
If the time-out time is no more than limitation time interval, and the handling capacity limitation statistical value of current virtual system is greater than or waits
When the handling capacity limits value of virtual system, packet loss processing is carried out；
If the time-out time be more than limitation time interval, update virtual system handling capacity limitation time-out time be it is current when
Between, and statistical value is limited using the handling capacity of atomic operation resetting virtual system.
12. a kind of computer equipment including memory, processor and stores the meter that can be run on a memory and on a processor
Calculation machine program, wherein the processor realizes following method when executing described program:
When every message flow flows through the network equipment, whether judgement currently needs to carry out handling capacity limitation；
If desired, it is handled up using the described in any item throughput of network device method for limiting of Claims 1-4 4 network equipment
Amount is limited；
Otherwise, the handling capacity real-time statistics value of the network equipment is obtained according to the throughput statistics value of the virtual system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811268355.3A CN109525504A (en) | 2018-10-29 | 2018-10-29 | Throughput of network device limitation, statistical method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811268355.3A CN109525504A (en) | 2018-10-29 | 2018-10-29 | Throughput of network device limitation, statistical method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109525504A true CN109525504A (en) | 2019-03-26 |
Family
ID=65772547
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811268355.3A Pending CN109525504A (en) | 2018-10-29 | 2018-10-29 | Throughput of network device limitation, statistical method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109525504A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104243348A (en) * | 2014-09-22 | 2014-12-24 | 曙光信息产业(北京)有限公司 | Data processing method and device |
| US20150146527A1 (en) * | 2013-11-26 | 2015-05-28 | Broadcom Corporation | System, Method and Apparatus for Network Congestion Management and Network Resource Isolation |
| CN105591968A (en) * | 2016-01-25 | 2016-05-18 | 盛科网络（苏州）有限公司 | Realization method of compensated Ethernet network storm inhibition |
| CN106598747A (en) * | 2016-12-15 | 2017-04-26 | 东软集团股份有限公司 | Network data package parallel processing method and device |
| CN106789723A (en) * | 2016-12-20 | 2017-05-31 | 东软集团股份有限公司 | The method and apparatus that multi-core network forwards speed limit |
-
2018
- 2018-10-29 CN CN201811268355.3A patent/CN109525504A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150146527A1 (en) * | 2013-11-26 | 2015-05-28 | Broadcom Corporation | System, Method and Apparatus for Network Congestion Management and Network Resource Isolation |
| CN104243348A (en) * | 2014-09-22 | 2014-12-24 | 曙光信息产业(北京)有限公司 | Data processing method and device |
| CN105591968A (en) * | 2016-01-25 | 2016-05-18 | 盛科网络（苏州）有限公司 | Realization method of compensated Ethernet network storm inhibition |
| CN106598747A (en) * | 2016-12-15 | 2017-04-26 | 东软集团股份有限公司 | Network data package parallel processing method and device |
| CN106789723A (en) * | 2016-12-20 | 2017-05-31 | 东软集团股份有限公司 | The method and apparatus that multi-core network forwards speed limit |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108776934B (en) | Distributed data calculation method and device, computer equipment and readable storage medium | |
| US9571347B2 (en) | Reactive auto-scaling of capacity | |
| CN109445944B (en) | DPDK-based network data acquisition and processing system and method thereof | |
| CN108268318A (en) | A kind of method and apparatus of distributed system task distribution | |
| CN110113387A (en) | A kind of processing method based on distributed batch processing system, apparatus and system | |
| US20150007185A1 (en) | Task Execution By Idle Resources In Grid Computing System | |
| CN109857549A (en) | Image processing method, system, equipment and medium based on load balancing | |
| CN107018175A (en) | The dispatching method and device of mobile cloud computing platform | |
| CN107925588A (en) | Band outer platform is adjusted and configured | |
| CN105049268A (en) | Distributed computing resource allocation system and task processing method | |
| US10305974B2 (en) | Ranking system | |
| CN109656782A (en) | Visual scheduling monitoring method, device and server | |
| CN111628941A (en) | Network traffic classification processing method, device, equipment and medium | |
| CN102724103A (en) | Proxy server, hierarchical network system and distributed workload management method | |
| CN106293950A (en) | A kind of resource optimization management method towards group system | |
| CN1784656A (en) | Monitoring operational data in data processing systems | |
| CN106326002A (en) | Resource scheduling method, device and equipment | |
| WO2018157768A1 (en) | Method and device for scheduling running device, and running device | |
| CN107430526B (en) | Method and node for scheduling data processing | |
| CN117762591B (en) | Task control method, task control device, computer device, and storage medium | |
| CN107579852A (en) | Virtual network performance isolation system and method based on historical models in Cloud Server | |
| CN103309843A (en) | Configuration method and system for servers | |
| CN109388501A (en) | Communication matching process, device, equipment and medium based on recognition of face request | |
| CN106407636A (en) | Integration result statistics method and apparatus | |
| CN109525504A (en) | Throughput of network device limitation, statistical method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190326 |
|
| RJ01 | Rejection of invention patent application after publication |