CN108845881A - The method and device of server capacity dynamic adjustment - Google Patents
The method and device of server capacity dynamic adjustment Download PDFInfo
- Publication number
- CN108845881A CN108845881A CN201810538621.3A CN201810538621A CN108845881A CN 108845881 A CN108845881 A CN 108845881A CN 201810538621 A CN201810538621 A CN 201810538621A CN 108845881 A CN108845881 A CN 108845881A
- Authority
- CN
- China
- Prior art keywords
- server
- capacity
- load
- unit time
- value
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5083—Techniques for rebalancing the load in a distributed system
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer And Data Communications (AREA)
Abstract
The present invention relates to method, apparatus, server and the storage mediums of server capacity dynamic adjustment, are applied to server field.The method includes：Obtain the history value of the unit time load capacity of server；According to the history value calculate in future time point described in server unit time load capacity predicted value；The predicted value and preset load threshold are compared, the capacity of the server is adjusted according to comparison result.The case where embodiment of the present invention can alleviate the delay issue of capacity adjustment, improve existing server system load too high or too low problem.
Description
Technical field
The present invention relates to server technology fields, method, apparatus, service more particularly to server capacity dynamic adjustment
Device and storage medium.
Background technique
In server operational process, user's amount of access of different periods is different, therefore server load has peak and low ebb.For
Save the cost, while guaranteeing service availability, it usually needs do the dynamic capacity-expanding and capacity reducing of server.In dilatation and capacity reduction method
In, general way is to obtain the size of the unit time load capacity of server, carries out dilatation when reaching setting index, reduces
Capacity reducing is carried out when to another index.
In the implementation of the present invention, following problem exists in the prior art in inventor, and above-mentioned server moves
In state dilatation and capacity reduction method, needs to adjust server capacity in discovery and needed centainly to server capacity adjustment is actually accomplished
The problem of time, i.e. presence server capacity adjustment delay, easily occurs that server load is excessively high or mistake and during this section
Low situation.
Summary of the invention
Based on this, it is necessary to aiming at the problem that existing way server capacity adjusts delay, provide a kind of server capacity
Method, apparatus, server and the storage medium of dynamic adjustment.
According to the first aspect of the invention, a kind of method of server capacity dynamic adjustment is provided, including：
Obtain the history value of the unit time load capacity of server；
According to the history value calculate in future time point described in server unit time load capacity predicted value；
The predicted value and preset load threshold are compared, the capacity of the server is adjusted according to comparison result.
The unit time of server described in one of the embodiments, according to history value calculating in future time point
The step of predicted value of load capacity, including：
The load estimation model of server is established according to the history value；
The future time point for obtaining setting is obtained using the future time point as the input of the load estimation model
The load estimation model exports the predicted value as a result, the unit time load capacity as the server.
The step of obtaining the history value of unit time load capacity of server in one of the embodiments, including：
Unit time load capacity of the record server in various time points in real time；
According to the time cycle of setting, the unit time load capacity of the setting quantity recorded recently is obtained, as history value.
The step of load estimation model of server is established according to the history value in one of the embodiments, including：
According to the history value and the corresponding historical time point of each history value, the load for characterizing the server is established
The multinomial for measuring variation characteristic, as load estimation model.
In one of the embodiments, according to the history value and the corresponding historical time point of each history value, table is established
The polynomial step of the load capacity variation characteristic of the server is levied, including：
According to the history value and the corresponding historical time point of each history value, multinomial song is done using least square method
Line fitting, obtains the multinomial for the load capacity variation characteristic for characterizing the server.
The step of capacity of the server is adjusted according to comparison result in one of the embodiments, including：
If the predicted value is more than or equal to preset first load threshold, dilatation is carried out to the server；
If the predicted value is less than or equal to preset second load threshold, capacity reducing is carried out to the server；
Wherein, the first load threshold is greater than the second load threshold.
Unit time load capacity includes in one of the embodiments,：The request amount of unit time, the memory of unit time
The cpu load amount of occupancy or unit time.
According to the second aspect of the invention, a kind of device of server capacity dynamic adjustment is provided, including：
History value obtains module, the history value of the unit time load capacity for obtaining server；
Prediction module, for according to the history value calculate in future time point described in server unit time load capacity
Predicted value；And
Capacity adjusts module, for comparing the predicted value and preset load threshold, adjusted according to comparison result described in
The capacity of server.
According to the third aspect of the invention we, a kind of server, including memory and processor are provided；
The memory, for storing computer program；When the computer program is executed by the processor, so that
The processor realizes the step of method of any of the above-described embodiment.
According to the fourth aspect of the invention, a kind of computer readable storage medium is provided, computer program is stored thereon with,
When the computer program is executed by the processor, so that the processor realizes the step of the method for any of the above-described embodiment
Suddenly
Implement embodiment provided by the invention, the history value of the unit time load capacity by obtaining server；According to going through
History value calculates the predicted value in the unit time load capacity of future time point server；According to predicted value and preset load threshold
Value carries out dynamic adjustment to the capacity of server；Prepare since capacity adjustment can be carried out in advance, alleviates prolonging for capacity adjustment
Slow problem, the actual negative carrying capacity that can improve server is excessive for capacity, leads to the not available situation of system, Yi Jixian
The case where actual negative carrying capacity of server is too small for capacity, and there are the wastings of resources.
Detailed description of the invention
Fig. 1 is the applicable system architecture diagram of the method for server capacity dynamic adjustment in one embodiment；
Fig. 2 is the schematic flow chart for the method that the server capacity dynamic of an embodiment adjusts；
Fig. 3 is the schematic flow chart for the method that the server capacity dynamic of another embodiment adjusts；
Fig. 4 is the load estimation model construction of an embodiment and the schematic diagram of prediction；
Fig. 5 is the schematic diagram for the device that the server capacity dynamic of an embodiment adjusts；
Fig. 6 is the internal structure chart of server in one embodiment.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
Referenced herein " embodiment " is it is meant that a particular feature, structure, or characteristic described can wrap in conjunction with the embodiments
It is contained at least one embodiment of the application.Each position in the description occur the phrase might not each mean it is identical
Embodiment, nor the independent or alternative embodiment with other embodiments mutual exclusion.Those skilled in the art explicitly and
Implicitly understand, embodiment described herein can be combined with other embodiments.
The method of server capacity dynamic adjustment provided by the present application, can be adapted for disposing in server beyond the clouds.
Wherein server can use independent server, be also possible to the server cluster of multiple server compositions, server cluster is such as
Shown in Fig. 1, including multiple servers 100, it can interconnect between multiple servers 100；Also, multiple servers 100 can
Think identical server, or different servers is set according to actual conditions.
In server cluster, the quantity of server 100 can be increased or be reduced according to the actual situation, work as service
When the quantity of device 100 increases, the capacity expansion of the server cluster, when the quantity of server 100 is reduced, the server cluster
Capacity reduce.
Above-mentioned server is usually deployed environment beyond the clouds, can carry out dilatation or capacity reducing according to actual load capacity；Such as
When carrying out dilatation, mirror image usually is done to server, is then switched on using mirror image, is achieved in server expansion.
In one embodiment, as shown in Fig. 2, providing a kind of method of server capacity dynamic adjustment, including it is following
Step S101~S103, is described as follows：
S101 obtains the history value of the unit time load capacity of server.
Wherein, the unit time can be per second, be also possible to every point, every hour or every day etc.；If the latter, when unit
Between load capacity either the load capacity mean value of corresponding period, is also possible to load capacity aggregate-value.
The mode for obtaining the history value of the unit time load capacity of server can be, and record the load capacity of server in real time
And store, thus obtain the history value of the unit time load capacity of server；In addition, the history value of unit time load capacity is also divided
Not Dui Ying a historical time point, the measurement unit of the historical time point is identical as the measurement unit of above-mentioned unit time, example
The previous second of such as current time, previous point or previous hour.
It should be noted that in embodiments of the present invention, historical time point is sensu lato concept of time, it can be understood as
Time point before current point in time, such as any one second before current point in time；In addition, historical time point is also understood that
Including comprising current point in time.
S102, according to the history value calculate in future time point described in server unit time load capacity prediction
Value.
Wherein, future time point is to refer to the time point after current point in time for current point in time；Not
The measurement unit for carrying out time point is identical as the measurement unit of above-mentioned unit time such as any one after current point in time
Second, any one point or any one hour etc..
It should be noted that the selection of future time point, accurate with the predicted value of the unit time load capacity of server
Degree is related, and generally, future time point is closer apart from the corresponding historical time point of history value, and the accuracy of corresponding predicted value is got over
Height, conversely, accuracy is lower.
In addition, the time difference when the future time point chosen apart from current point in time, need to be less than server capacity adjustment
When delay time (delay time refers to needing to be adjusted to the time that capacity adjustment is completed from judgement), server is likely to occur
One lesser capacity adjustment delay, but compared to existing server capacity adjustment mode, it can be relieved clothes caused by adjustment delay
Business device load too high or too low.
In one embodiment, the selection of future time point meets condition：The future time point of selection is apart from current point in time
Time difference, more than or equal to server capacity adjustment delay time, thus can preferably avoid server load excessively high
Or too low problem.
S103 compares the predicted value and preset load threshold, and the capacity of the server is adjusted according to comparison result.
The executing subject of above steps can be independent server, be also possible to the server of multiple server compositions
Cluster.It is understood that step S101 was obtained is the clothes for being completely in working condition in cluster when for server cluster
Be engaged in device unit time load capacity history value, according to comparison result adjustment be server cluster capacity.
It wherein, include dilatation and capacity reducing to the capacity adjustment of server, existing any way can be used in the mode of adjustment,
This is not construed as limiting.For example, in the method for passing through mirror image dilatation, since the mirror image of cloud environment is increment mirror image, from preparation mirror
It is arrived as booting and completes dilatation completion, generally required 5~10 minutes, if being put into according to traditional server capacity adjustment, in this section
In time, the load capacity of server may continue to increase, and cause server load amount to exceed the capacity of server, when serious even
Cause server that can not work.In through the embodiment of the present invention, according to the predicted value of server unit time load capacity and preset
Load threshold comparison, the strategy for adjusting the capacity of the server is thereby determined that, since capacity adjustment can be carried out in advance
Prepare, the actual negative carrying capacity that can prevent server is excessive for capacity, causes system unavailable, and existing service
The actual negative carrying capacity of device is too small for capacity, there are problems that the wasting of resources.
In one embodiment, if predicted value is more than or equal to preset first load threshold, server is expanded
Hold；If predicted value is less than or equal to preset second load threshold, capacity reducing is carried out to server；Wherein, the first load threshold
Value is greater than the second load threshold.In addition, if predicted value is greater than the second load threshold, and less than the first load threshold, it is determined that be
It does not need to carry out server capacity adjustment, maintains the capacity of server constant.
Above-mentioned unit time load capacity, which can be, to be able to reflect server and needs any of processing business amount in the unit time
Parameter, it may for example comprise but it is not limited to request amount, the EMS memory occupation amount of unit time or unit time that the unit time receives
Cpu load amount；Under the premise of guaranteeing server load processing capacity, server unit time load capacity is higher, the appearance needed
Amount is bigger, conversely, the capacity needed is smaller.
In one embodiment, unit time load capacity is preferably the request amount received the unit time.In general, when unit
Between EMS memory occupation amount or the parameters such as the cpu load amount of unit time, be caused by request amount variation as a result, relative to request
For amount, it will usually have hysteresis quality and stochastic volatility；In addition, for EMS memory occupation amount/cpu load of entire server cluster
The collection of amount needs to collect EMS memory occupation amount/cpu load amount of all machines in cluster, then conformity calculation, it is more difficult to accurate meter
It calculates and measures；Therefore, index of the request amount for selecting the unit time to receive as dilatation capacity reducing, can more accurately find dilatation
The opportunity of capacity reducing.Wherein, the request amount that the unit time receives can be indicated with request amount qps per second.
In one embodiment, according to history value calculate in future time point described in server unit time load capacity it is pre-
The mode of measured value may include：The load estimation model of the server is established according to history value；The future time point of setting is obtained,
Using future time point as the input of the load estimation model, the output of load estimation model is obtained as a result, as server
Unit time load capacity predicted value.
For example, the qps of server can be recorded per minute, nearest 30 minutes qps are taken out according to set time period, with this
Mathematical modeling is carried out, the qps of mathematical model prediction server after ten minutes is passed through.It should be noted that wherein, nearest 30 minutes
History value be only citing to the time span of history value, other times span can also be obtained according to the actual situation
History value；In addition, being also not necessarily limited to the qps after ten minutes of the example above based on the predicted value that model obtains.
Turn next to shown in Fig. 3, by another embodiment to the method for server capacity dynamic adjustment of the invention into
Row is for example, specifically comprise the following steps：
S201 obtains server in the unit time load capacity of multiple historical time points, as history value.Such as：In real time
Server is recorded in the unit time load capacity of various time points；According to the time cycle of setting, the setting recorded recently is obtained
The unit time load capacity of quantity, as history value.
In one embodiment, the unit time load capacity an of aol server, aol server can be recorded per minute
Refer to the server in work.Periodically (such as 10 minutes primary) takes out the unit time load of a period of time record recently
Amount, as history value.
In embodiment, using unit time load capacity as index, relative to fetching target current value, nearest one is periodically taken out
The unit time load capacity of section time record can eliminate the larger problem of index current value randomness, for example, working as history value
The sudden change of index is carved with when preceding, but quickly again restore to the original state, using the current value of index as refer to, prediction result deviation compared with
Greatly, it is unfavorable for accurately obtaining the opportunity of dilatation or capacity reducing.
S202 is established according to the history value and the corresponding historical time point of each history value and is characterized the server
The multinomial of load capacity variation characteristic, as load estimation model.
In one embodiment, according to the history value of unit time load capacity, the characterization clothes can be established in the following way
The multinomial of the load capacity variation characteristic of business device：According to the history value and the corresponding historical time point of each history value, use
Least square method does polynomial curve fitting, obtains the multinomial for the load capacity variation characteristic for characterizing the server.It is realized
Process is for example：
1. the qps of aol server of record, aol server refer to the server in work per minute.
2. the pqs (such as table 1) of nearest 30 minutes records is taken out in timing (such as 10 minutes primary), in coordinate axis plot 30
A scatterplot (shown in Figure 4), x-axis are timestamps, and y-axis is pqs value.
Table 1：
3. doing polynomial curve fitting using least square method, multinomial coefficient is obtained, draws polynomial curve.
4. choosing time point after ten minutes using the multinomial acquired as future time point to be predicted, substituting into more
Item formula, the predicted value of available pqs after ten minutes.
Based on the history value of table 1, binomial can be obtained：
Y=-0.845334*x^2+0.4157*x+4383.69；
Thus binomial curve as shown in Figure 4 can be drawn.Predict that the qps of (i.e. the 40th minute) after ten minutes is 4694.
S203 obtains future time point to be predicted, using the future time point as the defeated of the load estimation model
Enter, obtain the load estimation model exports the predicted value as a result, the unit time load capacity as the server.
S204 compares the predicted value and preset load threshold, if predicted value is negative more than or equal to preset first
Threshold value is carried, step S205 is executed, if the predicted value is less than or equal to preset second load threshold, executes step S206；
If predicted value between the first load threshold and the second load threshold, thens follow the steps S207.
S205 carries out dilatation to server.
In one embodiment, the specific implementation of the step may include：The to be expanded of server is determined according to predicted value
Amount makes server mirroring according to amount to be expanded；It is switched on using the server mirroring mirror image to server, so that the service
Amount to be expanded described in the capacity expansion of device.Specifically for example：If necessary to dilatation, the number of servers for needing dilatation is calculated, each
Server corresponds to certain server capacity, and the number of servers for needing dilatation can be determined according to amount to be expanded；Make server
Mirror image is switched on using mirror image, and waiting for server is available, by adjusting load balancer, new demand servicing device is added, dilatation is completed.
S206 carries out capacity reducing to server.
In one embodiment, the specific implementation of the step may include：According to predicted value determine server to capacity reducing
Amount；It is deleted from the capacity of the server described to capacity reducing amount.Specifically for example：If necessary to capacity reducing, calculating needs capacity reducing
Number of servers adjusts load balancer, rejects and needs offline server, so that flow is not entered back into these servers, then
It closes and deletes server, complete capacity reducing.
S207 maintains the capacity of server constant.
Through the foregoing embodiment, nearest multiple history values that the load capacity recorded is obtained according to setting time, are based on
This can regularly update load estimation model, and thus, it is possible to more accurately predict the loading condition at certain following time point；For example, with every
For the index that second request amount qps is adjusted as server capacity, change in observing system qps, discovery qps variation meets
Mathematic curve rule, using the qps of the past period, doing mathematics model (multinomial of least square method), are predicted with this
The qps of following a period of time；The capacity adjustment for preparing server in advance based on predicted value, can prevent the actual negative of server
Carrying capacity is excessive for capacity, causes system unavailable, and shows the actual negative carrying capacity of server for capacity
It is too small, there are problems that the wasting of resources.
It should be understood that for the various method embodiments described above, although each step in flow chart is according to arrow
Instruction is successively shown, but these steps are not that the inevitable sequence according to arrow instruction successively executes.Unless having herein bright
True explanation, there is no stringent sequences to limit for the execution of these steps, these steps can execute in other order.And
And at least part step in the flow chart of embodiment of the method may include multiple sub-steps or multiple stages, this is a little
Step or stage are not necessarily to execute completion in synchronization, but can execute at different times, these sub-steps
Perhaps the execution sequence in stage be also not necessarily successively carry out but can with the sub-step of other steps or other steps or
At least part in person's stage executes in turn or alternately.
Based on thought identical with the method for server capacity dynamic adjustment in above-described embodiment, service is also provided herein
The device of device capacity dynamic adjustment.
In one embodiment, as shown in figure 5, the device of the server capacity dynamic adjustment of the present embodiment includes：History
Value obtains module 501, prediction module 502 and capacity and adjusts module 503, and details are as follows for each module：
Above-mentioned history value obtains module 501, the history value of the unit time load capacity for obtaining server；
Above-mentioned prediction module 502, for according to the history value calculate in future time point described in server unit
The predicted value of time load amount；
Above-mentioned capacity adjusts module 503, for comparing the predicted value and preset load threshold, according to comparison result
Adjust the capacity of the server.
In one embodiment, above-mentioned prediction module 502 includes：
Model construction unit, for establishing the load estimation model of server according to the history value.
Predicting unit, for obtaining the future time point of setting, using the future time point as the load estimation mould
The input of type, obtain the load estimation model exports the prediction as a result, the unit time load capacity as the server
Value.
In one embodiment, above-mentioned history value obtains module 501, is specifically used for recording server in real time in each time
The unit time load capacity of point；According to the time cycle of setting, the unit time load capacity of the setting quantity recorded recently is obtained,
As history value.
In one embodiment, above-mentioned model construction unit is specifically used for according to the history value and each history value pair
The historical time point answered establishes the multinomial for characterizing the load capacity variation characteristic of the server, as load estimation model.Example
Such as, according to the history value and the corresponding historical time point of each history value, it is quasi- that polynomial curve is done using least square method
It closes, the multinomial for the load capacity variation characteristic for characterizing the server is obtained, as load estimation model.
In one embodiment, above-mentioned capacity adjustment module 503 includes：
Dilatation unit, if being more than or equal to preset first load threshold for the predicted value, to the server
Carry out dilatation；And capacity reducing unit, if being less than or equal to preset second load threshold for the predicted value, to described
Server carries out capacity reducing；Wherein, the first load threshold is greater than the second load threshold.
In one embodiment, in the embodiment of above-mentioned apparatus, the unit time load capacity referred to includes：Unit time receives
Request amount, the EMS memory occupation amount of unit time or the cpu load amount of unit time.
The specific restriction of device about server capacity dynamic adjustment may refer to dynamic above for server capacity
The restriction of the method for state adjustment, details are not described herein.Modules in the device of above-mentioned server capacity dynamic adjustment can be complete
Portion or part are realized by software, hardware and combinations thereof.Above-mentioned each module can be embedded in the form of hardware or independently of calculating
In processor in machine equipment, it can also be stored in a software form in the memory in computer equipment, in order to processor
It calls and executes the corresponding operation of the above modules.
In addition, in the embodiment of the device of the server capacity dynamic adjustment of above-mentioned example, the logic of each program module
Division is merely illustrative of, and can according to need in practical application, such as the configuration requirement or software of corresponding hardware
The convenient of realization considers, above-mentioned function distribution is completed by different program modules, i.e., adjusts the server capacity dynamic
The internal structure of device be divided into different program modules, to complete all or part of the functions described above.
In one embodiment, a kind of server is provided, the internal structure chart of the server can be as shown in Figure 6.It should
Server includes processor, memory, network interface and the database connected by system bus.Wherein, processor is for mentioning
For calculating and control ability；Memory includes non-volatile memory medium, built-in storage, which is stored with
Operating system, computer program and database, the built-in storage are operating system and computer in non-volatile memory medium
The operation of program provides environment；Database is for storing relevant data；Network interface is used to pass through network with external terminal
Connection communication；A kind of method when the computer program is executed by processor to realize server capacity dynamic adjustment.
It will be understood by those skilled in the art that structure shown in Fig. 6, only part relevant to application scheme is tied
The block diagram of structure, does not constitute the restriction for the server being applied thereon to application scheme, and specific server may include
Than more or fewer components as shown in the figure, certain components are perhaps combined or with different component layouts.
In one embodiment, a kind of server, including memory and processor are provided, is stored with calculating in memory
Machine program, the processor realize following steps when executing computer program：
Obtain the history value of the unit time load capacity of server；According to the history value calculate in future time point described in
The predicted value of the unit time load capacity of server；The predicted value and preset load threshold are compared, according to comparison result tune
The capacity of the whole server.
In one embodiment, following steps are also realized when processor executes computer program：
The load estimation model of server is established according to the history value；The future time point for obtaining setting, by described in not
Carry out input of the time point as the load estimation model, obtains the output of the load estimation model as a result, as the clothes
The predicted value of the unit time load capacity of business device.
In one embodiment, following steps are also realized when processor executes computer program：
Unit time load capacity of the record server in various time points in real time；According to the time cycle of setting, obtain most
The unit time load capacity of the setting quantity closely recorded, as history value.
In one embodiment, following steps are also realized when processor executes computer program：
According to the history value and the corresponding historical time point of each history value, the load for characterizing the server is established
The multinomial for measuring variation characteristic, as load estimation model.
In one embodiment, following steps are also realized when processor executes computer program：
According to the history value and the corresponding historical time point of each history value, multinomial song is done using least square method
Line fitting, obtains the multinomial for the load capacity variation characteristic for characterizing the server.
In one embodiment, following steps are also realized when processor executes computer program：
If the predicted value is more than or equal to preset first load threshold, dilatation is carried out to the server；If institute
Predicted value is stated less than or equal to preset second load threshold, capacity reducing is carried out to the server；Wherein, the first load threshold
Greater than the second load threshold.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program realizes following steps when being executed by processor：Obtain the history value of the unit time load capacity of server；According to described
History value calculates the predicted value of the unit time load capacity of the server described in future time point；It compares the predicted value and presets
Load threshold, the capacity of the server is adjusted according to comparison result.
In one embodiment, following steps are also realized when computer program is executed by processor：
The load estimation model of server is established according to the history value；The future time point for obtaining setting, by described in not
Carry out input of the time point as the load estimation model, obtains the output of the load estimation model as a result, as the clothes
The predicted value of the unit time load capacity of business device.
In one embodiment, following steps are also realized when computer program is executed by processor：
Unit time load capacity of the record server in various time points in real time；According to the time cycle of setting, obtain most
The unit time load capacity of the setting quantity closely recorded, as history value.
In one embodiment, following steps are also realized when computer program is executed by processor：
According to the history value and the corresponding historical time point of each history value, the load for characterizing the server is established
The multinomial for measuring variation characteristic, as load estimation model.
In one embodiment, following steps are also realized when computer program is executed by processor：
According to the history value and the corresponding historical time point of each history value, multinomial song is done using least square method
Line fitting, obtains the multinomial for the load capacity variation characteristic for characterizing the server.
In one embodiment, following steps are also realized when computer program is executed by processor：
If the predicted value is more than or equal to preset first load threshold, dilatation is carried out to the server；If institute
Predicted value is stated less than or equal to preset second load threshold, capacity reducing is carried out to the server；Wherein, the first load threshold
Greater than the second load threshold.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.The description of above-mentioned each embodiment all emphasizes particularly on different fields, in some embodiment
The part not being described in detail may refer to the associated description of other embodiments.
Term " includes " and " having " and their any deformations in embodiment, it is intended that cover non-exclusive packet
Contain.Such as contain series of steps or the process, method, system, product or equipment of (module) unit are not limited to arrange
Out the step of or unit, but optionally further comprising the step of not listing or unit, or optionally further comprising for these mistakes
The intrinsic other step or units of journey, method, product or equipment.
" multiple " referred in embodiment refer to two or more."and/or", the association for describing affiliated partner are closed
System indicates may exist three kinds of relationships, for example, A and/or B, can indicate：Individualism A exists simultaneously A and B, individualism
These three situations of B.Character "/" typicallys represent the relationship that forward-backward correlation object is a kind of "or".
" first second " referred in embodiment be only be the similar object of difference, do not represent for the specific of object
Sequence, it is possible to understand that specific sequence or precedence can be interchanged in ground, " first second " in the case where permission.It should manage
The object that solution " first second " is distinguished is interchangeable under appropriate circumstances so that the embodiments described herein can in addition to
Here the sequence other than those of diagram or description is implemented.
Only several embodiments of the present invention are expressed for above embodiments, and but it cannot be understood as to patent of invention
The limitation of range.It should be pointed out that for those of ordinary skill in the art, in the premise for not departing from the application design
Under, various modifications and improvements can be made, these belong to the protection scope of the application.Therefore, the protection of the application patent
Range should be determined by the appended claims.
Claims (10)
1. a kind of method of server capacity dynamic adjustment, which is characterized in that including：
Obtain the history value of the unit time load capacity of server；
According to the history value calculate in future time point described in server unit time load capacity predicted value；
The predicted value and preset load threshold are compared, the capacity of the server is adjusted according to comparison result.
2. the method according to claim 1, wherein described calculate according to the history value in future time point institute
The step of stating the predicted value of unit time load capacity of server, including：
The load estimation model of server is established according to the history value；
The future time point for obtaining setting, using the future time point as the input of the load estimation model, described in acquisition
Load estimation model exports the predicted value as a result, the unit time load capacity as the server.
3. according to the method described in claim 2, it is characterized in that, the history of the unit time load capacity for obtaining server
The step of value, including：
Unit time load capacity of the record server in various time points in real time；
According to the time cycle of setting, the unit time load capacity of the setting quantity recorded recently is obtained, as history value.
4. according to the method described in claim 3, it is characterized in that, the load for establishing server according to the history value is pre-
The step of surveying model, including：
According to the history value and the corresponding historical time point of each history value, the load quantitative change for characterizing the server is established
The multinomial for changing feature, as load estimation model.
5. according to the method described in claim 4, it is characterized in that, described corresponding according to the history value and each history value
Historical time point, establish the polynomial step for characterizing the load capacity variation characteristic of the server, including：
According to the history value and the corresponding historical time point of each history value, it is quasi- that polynomial curve is done using least square method
It closes, obtains the multinomial for the load capacity variation characteristic for characterizing the server.
6. method according to any one of claims 1 to 5, which is characterized in that described to adjust the service according to comparison result
The step of capacity of device, including：
If the predicted value is more than or equal to preset first load threshold, dilatation is carried out to the server；
If the predicted value is less than or equal to preset second load threshold, capacity reducing is carried out to the server；
Wherein, the first load threshold is greater than the second load threshold.
7. method according to any one of claims 1 to 6, which is characterized in that the unit time load capacity includes：When unit
Between request amount, the EMS memory occupation amount of unit time or the cpu load amount of unit time.
8. a kind of device of server capacity dynamic adjustment, which is characterized in that including：
History value obtains module, the history value of the unit time load capacity for obtaining server；
Prediction module, for according to the history value calculate in future time point described in server unit time load capacity it is pre-
Measured value；And
Capacity adjusts module, for comparing the predicted value and preset load threshold, adjusts the service according to comparison result
The capacity of device.
9. a kind of server, including memory and processor；The memory, for storing computer program；Its feature exists
In,
When the computer program is executed by the processor, so that the processor realizes that claim 1 to 7 is any described
The step of method.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that when the computer journey
When sequence is executed by the processor, so that the step of processor realizes claim 1 to 7 any the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810538621.3A CN108845881A (en) | 2018-05-30 | 2018-05-30 | The method and device of server capacity dynamic adjustment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810538621.3A CN108845881A (en) | 2018-05-30 | 2018-05-30 | The method and device of server capacity dynamic adjustment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108845881A true CN108845881A (en) | 2018-11-20 |
Family
ID=64209993
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810538621.3A Pending CN108845881A (en) | 2018-05-30 | 2018-05-30 | The method and device of server capacity dynamic adjustment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108845881A (en) |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109526027A (en) * | 2018-11-27 | 2019-03-26 | 中国移动通信集团福建有限公司 | A kind of cell capacity optimization method, device, equipment and computer storage medium |
| CN109614231A (en) * | 2018-12-04 | 2019-04-12 | 广东亿迅科技有限公司 | Idle server resource discovery method, device, computer equipment and storage medium |
| CN110109800A (en) * | 2019-04-10 | 2019-08-09 | 网宿科技股份有限公司 | A kind of management method and device of server cluster system |
| CN110247856A (en) * | 2019-05-24 | 2019-09-17 | 平安科技（深圳）有限公司 | Server resource method for releasing and device |
| CN110474795A (en) * | 2019-07-11 | 2019-11-19 | 中国平安财产保险股份有限公司 | Processing method and processing device, storage medium and the electronic equipment of server capacity |
| CN110502336A (en) * | 2019-07-05 | 2019-11-26 | 深圳壹账通智能科技有限公司 | A kind of starting method, apparatus, equipment and the readable storage medium storing program for executing of server |
| CN110532156A (en) * | 2019-08-22 | 2019-12-03 | 北京宝兰德软件股份有限公司 | A kind of capacity prediction methods and device |
| CN110795236A (en) * | 2019-09-26 | 2020-02-14 | 北京大米科技有限公司 | Method, device, electronic equipment and medium for adjusting capacity of server |
| CN111010303A (en) * | 2019-12-20 | 2020-04-14 | 北京爱奇艺科技有限公司 | Server control method and device |
| CN111258506A (en) * | 2020-02-07 | 2020-06-09 | 汉海信息技术(上海)有限公司 | Data storage method and device |
| WO2020135633A1 (en) * | 2018-12-29 | 2020-07-02 | 中兴通讯股份有限公司 | Expansion method and device |
| CN111475772A (en) * | 2020-03-27 | 2020-07-31 | 微梦创科网络科技（中国）有限公司 | Capacity evaluation method and device |
| CN111625196A (en) * | 2020-05-26 | 2020-09-04 | 北京海益同展信息科技有限公司 | Block chain node capacity expansion method and device, computer equipment and storage medium |
| CN111625080A (en) * | 2020-05-22 | 2020-09-04 | 苏州浪潮智能科技有限公司 | Server energy saving method and device, electronic equipment and storage medium |
| CN112000457A (en) * | 2019-05-27 | 2020-11-27 | 伊姆西Ip控股有限责任公司 | Method, apparatus and computer program product for managing tasks in a processing system |
| WO2020253111A1 (en) * | 2019-06-19 | 2020-12-24 | 深圳壹账通智能科技有限公司 | Automatic expansion method and apparatus for blockchain node, and operation and maintenance terminal and storage medium |
| CN112365003A (en) * | 2020-11-16 | 2021-02-12 | 浙江百应科技有限公司 | Method for adjusting NLP model capacity based on big data |
| CN112380011A (en) * | 2020-11-16 | 2021-02-19 | 中国工商银行股份有限公司 | Dynamic adjustment method and device for service capacity |
| CN112783638A (en) * | 2019-11-07 | 2021-05-11 | 北京沃东天骏信息技术有限公司 | Method, apparatus, medium, and device for implementing data processing by calling service |
| CN112801331A (en) * | 2019-11-14 | 2021-05-14 | 谷歌有限责任公司 | Shaping of computational loads using real-time scheduling of virtual capacity and preferred location |
| CN113032157A (en) * | 2021-05-31 | 2021-06-25 | 睿至科技集团有限公司 | Automatic intelligent server capacity expansion and reduction method and system |
| CN113127546A (en) * | 2019-12-30 | 2021-07-16 | 中国移动通信集团湖南有限公司 | Data processing method and device and electronic equipment |
| CN113209639A (en) * | 2021-05-21 | 2021-08-06 | 珠海金山网络游戏科技有限公司 | Information processing system, method and device |
| CN113676347A (en) * | 2021-07-23 | 2021-11-19 | 青岛海尔科技有限公司 | Server load prediction method and device, storage medium and electronic device |
| CN113791909A (en) * | 2021-09-18 | 2021-12-14 | 平安普惠企业管理有限公司 | Server capacity adjusting method and device, computer equipment and storage medium |
| CN115292146A (en) * | 2022-05-30 | 2022-11-04 | 北京结慧科技有限公司 | System capacity estimation method, system, equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103577268A (en) * | 2012-08-07 | 2014-02-12 | 复旦大学 | Self-adaptive resource supply method based on application load |
| CN103970641A (en) * | 2014-05-15 | 2014-08-06 | 浪潮电子信息产业股份有限公司 | Equipment expansion method based on capacity prediction technology |
| CN104850450A (en) * | 2015-05-14 | 2015-08-19 | 华中科技大学 | Load balancing method and system facing mixed cloud application |
| CN105323111A (en) * | 2015-11-17 | 2016-02-10 | 南京南瑞集团公司 | Operation and maintenance automation system and method |
| US20160320818A1 (en) * | 2015-04-28 | 2016-11-03 | Quanta Computer Inc. | Dynamic management of power supply units |
| CN106301864A (en) * | 2015-06-11 | 2017-01-04 | 腾讯科技（深圳）有限公司 | A kind of server system expansion method, device and dilatation processing equipment |
| CN107231264A (en) * | 2017-07-25 | 2017-10-03 | 北京百度网讯科技有限公司 | For the method and apparatus for the capacity for managing Cloud Server |
-
2018
- 2018-05-30 CN CN201810538621.3A patent/CN108845881A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103577268A (en) * | 2012-08-07 | 2014-02-12 | 复旦大学 | Self-adaptive resource supply method based on application load |
| CN103970641A (en) * | 2014-05-15 | 2014-08-06 | 浪潮电子信息产业股份有限公司 | Equipment expansion method based on capacity prediction technology |
| US20160320818A1 (en) * | 2015-04-28 | 2016-11-03 | Quanta Computer Inc. | Dynamic management of power supply units |
| CN106095035A (en) * | 2015-04-28 | 2016-11-09 | 广达电脑股份有限公司 | Server system and computer implemented method thereof and computer-readable recording medium |
| CN104850450A (en) * | 2015-05-14 | 2015-08-19 | 华中科技大学 | Load balancing method and system facing mixed cloud application |
| CN106301864A (en) * | 2015-06-11 | 2017-01-04 | 腾讯科技（深圳）有限公司 | A kind of server system expansion method, device and dilatation processing equipment |
| CN105323111A (en) * | 2015-11-17 | 2016-02-10 | 南京南瑞集团公司 | Operation and maintenance automation system and method |
| CN107231264A (en) * | 2017-07-25 | 2017-10-03 | 北京百度网讯科技有限公司 | For the method and apparatus for the capacity for managing Cloud Server |
Cited By (40)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109526027B (en) * | 2018-11-27 | 2022-07-01 | 中国移动通信集团福建有限公司 | Cell capacity optimization method, device, equipment and computer storage medium |
| CN109526027A (en) * | 2018-11-27 | 2019-03-26 | 中国移动通信集团福建有限公司 | A kind of cell capacity optimization method, device, equipment and computer storage medium |
| CN109614231A (en) * | 2018-12-04 | 2019-04-12 | 广东亿迅科技有限公司 | Idle server resource discovery method, device, computer equipment and storage medium |
| WO2020135633A1 (en) * | 2018-12-29 | 2020-07-02 | 中兴通讯股份有限公司 | Expansion method and device |
| CN110109800A (en) * | 2019-04-10 | 2019-08-09 | 网宿科技股份有限公司 | A kind of management method and device of server cluster system |
| CN110247856A (en) * | 2019-05-24 | 2019-09-17 | 平安科技（深圳）有限公司 | Server resource method for releasing and device |
| CN110247856B (en) * | 2019-05-24 | 2022-08-12 | 平安科技（深圳）有限公司 | Server resource release method and device |
| CN112000457A (en) * | 2019-05-27 | 2020-11-27 | 伊姆西Ip控股有限责任公司 | Method, apparatus and computer program product for managing tasks in a processing system |
| WO2020253111A1 (en) * | 2019-06-19 | 2020-12-24 | 深圳壹账通智能科技有限公司 | Automatic expansion method and apparatus for blockchain node, and operation and maintenance terminal and storage medium |
| CN110502336A (en) * | 2019-07-05 | 2019-11-26 | 深圳壹账通智能科技有限公司 | A kind of starting method, apparatus, equipment and the readable storage medium storing program for executing of server |
| CN110474795B (en) * | 2019-07-11 | 2023-04-07 | 中国平安财产保险股份有限公司 | Server capacity processing method and device, storage medium and electronic equipment |
| CN110474795A (en) * | 2019-07-11 | 2019-11-19 | 中国平安财产保险股份有限公司 | Processing method and processing device, storage medium and the electronic equipment of server capacity |
| CN110532156A (en) * | 2019-08-22 | 2019-12-03 | 北京宝兰德软件股份有限公司 | A kind of capacity prediction methods and device |
| CN110532156B (en) * | 2019-08-22 | 2023-12-19 | 北京宝兰德软件股份有限公司 | Capacity prediction method and device |
| CN110795236A (en) * | 2019-09-26 | 2020-02-14 | 北京大米科技有限公司 | Method, device, electronic equipment and medium for adjusting capacity of server |
| CN110795236B (en) * | 2019-09-26 | 2022-04-05 | 北京大米科技有限公司 | Method, device, electronic equipment and medium for adjusting capacity of server |
| CN112783638A (en) * | 2019-11-07 | 2021-05-11 | 北京沃东天骏信息技术有限公司 | Method, apparatus, medium, and device for implementing data processing by calling service |
| US11960255B2 (en) | 2019-11-14 | 2024-04-16 | Google Llc | Compute load shaping using virtual capacity and preferential location real time scheduling |
| CN112801331B (en) * | 2019-11-14 | 2024-02-06 | 谷歌有限责任公司 | Shaping of computational loads with virtual capacity and preferred location real-time scheduling |
| CN112801331A (en) * | 2019-11-14 | 2021-05-14 | 谷歌有限责任公司 | Shaping of computational loads using real-time scheduling of virtual capacity and preferred location |
| CN111010303A (en) * | 2019-12-20 | 2020-04-14 | 北京爱奇艺科技有限公司 | Server control method and device |
| CN113127546A (en) * | 2019-12-30 | 2021-07-16 | 中国移动通信集团湖南有限公司 | Data processing method and device and electronic equipment |
| CN111258506A (en) * | 2020-02-07 | 2020-06-09 | 汉海信息技术(上海)有限公司 | Data storage method and device |
| CN111475772A (en) * | 2020-03-27 | 2020-07-31 | 微梦创科网络科技（中国）有限公司 | Capacity evaluation method and device |
| CN111475772B (en) * | 2020-03-27 | 2023-12-15 | 微梦创科网络科技（中国）有限公司 | Capacity assessment method and device |
| CN111625080A (en) * | 2020-05-22 | 2020-09-04 | 苏州浪潮智能科技有限公司 | Server energy saving method and device, electronic equipment and storage medium |
| CN111625080B (en) * | 2020-05-22 | 2022-03-08 | 苏州浪潮智能科技有限公司 | Server energy saving method and device, electronic equipment and storage medium |
| CN111625196A (en) * | 2020-05-26 | 2020-09-04 | 北京海益同展信息科技有限公司 | Block chain node capacity expansion method and device, computer equipment and storage medium |
| CN112365003A (en) * | 2020-11-16 | 2021-02-12 | 浙江百应科技有限公司 | Method for adjusting NLP model capacity based on big data |
| CN112380011B (en) * | 2020-11-16 | 2024-02-27 | 中国工商银行股份有限公司 | Dynamic adjustment method and device for service capacity |
| CN112380011A (en) * | 2020-11-16 | 2021-02-19 | 中国工商银行股份有限公司 | Dynamic adjustment method and device for service capacity |
| CN112365003B (en) * | 2020-11-16 | 2023-04-11 | 浙江百应科技有限公司 | Method for adjusting NLP model capacity based on big data |
| CN113209639A (en) * | 2021-05-21 | 2021-08-06 | 珠海金山网络游戏科技有限公司 | Information processing system, method and device |
| CN113032157A (en) * | 2021-05-31 | 2021-06-25 | 睿至科技集团有限公司 | Automatic intelligent server capacity expansion and reduction method and system |
| CN113032157B (en) * | 2021-05-31 | 2021-08-24 | 睿至科技集团有限公司 | Automatic intelligent server capacity expansion and reduction method and system |
| CN113676347A (en) * | 2021-07-23 | 2021-11-19 | 青岛海尔科技有限公司 | Server load prediction method and device, storage medium and electronic device |
| CN113676347B (en) * | 2021-07-23 | 2024-03-26 | 青岛海尔科技有限公司 | Load prediction method and device of server, storage medium and electronic device |
| CN113791909B (en) * | 2021-09-18 | 2023-10-03 | 深圳市华智世纪科技有限公司 | Method and device for adjusting server capacity, computer equipment and storage medium |
| CN113791909A (en) * | 2021-09-18 | 2021-12-14 | 平安普惠企业管理有限公司 | Server capacity adjusting method and device, computer equipment and storage medium |
| CN115292146A (en) * | 2022-05-30 | 2022-11-04 | 北京结慧科技有限公司 | System capacity estimation method, system, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108845881A (en) | The method and device of server capacity dynamic adjustment | |
| US11408942B2 (en) | Method for predicting service life of retired power battery | |
| CN108959934A (en) | Safety risk estimating method, device, computer equipment and storage medium | |
| CN106164864A (en) | The prediction load of service is flexible | |
| CN108509157A (en) | A kind of data balancing method and device applied to distributed file system | |
| CN103970879B (en) | Method and system for regulating storage positions of data blocks | |
| CN112689007B (en) | Resource allocation method, device, computer equipment and storage medium | |
| CN111741112A (en) | File downloading method, device, equipment and storage medium based on artificial intelligence | |
| CN112068934A (en) | Control system and method for container cloud service instance contraction | |
| CN110689228A (en) | Test service scheduling method and device, computer equipment and storage medium | |
| CN109902103A (en) | Service data management method, device, equipment and computer readable storage medium | |
| CN111127247A (en) | Electric quantity data acquisition method and device, computer equipment and storage medium | |
| CN110245147A (en) | Block chain data processing method, device, readable storage medium storing program for executing and computer equipment | |
| CN109213774B (en) | Data storage method and device, storage medium and terminal | |
| Anselmi et al. | Optimal routing in parallel, non-observable queues and the price of anarchy revisited | |
| CN112685462B (en) | Feeder line data analysis method, feeder line data analysis device, computer equipment and storage medium | |
| CN111274315B (en) | Synchronous data channel construction method and device, computer equipment and storage medium | |
| CN107329881B (en) | Application system performance test method and device, computer equipment and storage medium | |
| CN113835626A (en) | Method and device for determining usable time of disk | |
| CN110084476B (en) | Case adjustment method, device, computer equipment and storage medium | |
| CN116522018A (en) | Electric power carbon emission monitoring method, device and equipment | |
| CN110443451A (en) | Event grading approach, device, computer equipment and storage medium | |
| CN110019372A (en) | Data monitoring method, device, server and storage medium | |
| CN115865826A (en) | Resource transmission control method, device, computer equipment, storage medium and product | |
| CN112767056B (en) | Service data prediction method, device, computer equipment and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181120 |