CN107231264A - For the method and apparatus for the capacity for managing Cloud Server - Google Patents
For the method and apparatus for the capacity for managing Cloud Server Download PDFInfo
- Publication number
- CN107231264A CN107231264A CN201710612567.8A CN201710612567A CN107231264A CN 107231264 A CN107231264 A CN 107231264A CN 201710612567 A CN201710612567 A CN 201710612567A CN 107231264 A CN107231264 A CN 107231264A
- Authority
- CN
- China
- Prior art keywords
- index
- cloud server
- monitoring data
- default
- target cloud
- 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
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0896—Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0893—Assignment of logical groups to network elements
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
This application discloses the method and apparatus of the capacity for managing Cloud Server.One embodiment of this method includes：Obtain the monitoring data being monitored at least one index of target Cloud Server；For each index, predicted the outcome the corresponding index of the index is obtained in the index forecast model of the monitoring data importing training in advance of the index, wherein, index forecast model is used to characterize the corresponding relation that monitoring data predicts the outcome with index；Index during index based at least one index predicts the outcome predicts peak value, index prediction valley, default first peak threshold and default first valley threshold, and dilatation operation is performed to target Cloud Server at least one index or capacity reducing is operated.The embodiment realizes the capacity management to Cloud Server.
Description
Technical field
The application is related to field of computer technology, and in particular to Internet technical field, more particularly, to manages cloud clothes
The method and apparatus of the capacity of business device.
Background technology
Cloud Server be a kind of simple efficient, safe and reliable, disposal ability can elastic telescopic calculating service.Its manager
Formula is simpler than physical server efficiently.User need not purchase hardware in advance, you can rapid to create or any many clouds clothes of release
Business device.Cloud Server generally uses virtualization technology, and virtual platform typically can be empty by more than 1,000 server clusters
The virtual machine (Kernel-based Virtual Machine, KVM) that multiple performances can match somebody with somebody is intended to be, to institute in whole group system
There is virtual machine to be monitored and manage, and according to real resource service condition flexible allocation and scheduling resource pond.
The existing scheme to Cloud Server progress capacity management usually requires user and independently sets automatic dilatation or contracting
The condition of appearance, when the indices of Cloud Server meet the condition of automatic dilatation or capacity reducing, dilatation is carried out to Cloud Server
Operation or capacity reducing operation.However, this method lacks certain " foresight ", often the business to user produces one
Just start to perform dilatation operation during fixed influence.
The content of the invention
The purpose of the application is to propose a kind of improved method and apparatus for being used to manage the capacity of Cloud Server, to solve
The technical problem that certainly background section above is mentioned.
In a first aspect, the embodiment of the present application provides a kind of method for being used to manage the capacity of Cloud Server, this method bag
Include：Obtain the monitoring data being monitored at least one index of target Cloud Server；For each index, by the index
The corresponding index of the index is obtained in the index forecast model of monitoring data importing training in advance to predict the outcome, wherein, index is pre-
Surveying model is used to characterize the corresponding relation that monitoring data predicts the outcome with index；Index based at least one index predicts the outcome
In index prediction peak value, index prediction valley, default first peak threshold and default first valley threshold, at least
One index performs dilatation operation to target Cloud Server or capacity reducing is operated.
In certain embodiments, the monitoring data being monitored at least one index of target Cloud Server, bag are obtained
Include：Preset it is determined that whether the acquisition time section that the monitoring data at least one index of target Cloud Server is acquired is more than
Acquisition time section threshold value；If so, then obtaining monitoring data.
In certain embodiments, in the index forecast model that the monitoring data of the index is imported to training in advance this is obtained to refer to
Corresponding index is marked to predict the outcome, including：Acquisition time section is divided into preset number time interval；For each time zone
Between, obtain the data peaks that the index is more than default second peak threshold in the monitoring data of the time interval；Determine number
Whether it is more than default amount threshold according to the quantity of peak value；If the quantity of data peaks is more than amount threshold, each number is obtained
According to each time of origin point of peak value, and determine the minimal difference in the difference of each time of origin point；Determine each time zone
Between it is each minimal difference and value, and determine and value whether be less than it is default and value threshold value；And if value is less than default and value
The corresponding index of the index is obtained in threshold value, then the index forecast model that the monitoring data of the index is imported to training in advance to predict
As a result.
In certain embodiments, dilatation operation is performed to target Cloud Server at least one index or capacity reducing is operated,
Including：For each index at least one index, predicted the outcome based on the corresponding index of the index, it is determined that default
Whether the index prediction peak value of the index in one period is more than default first peak threshold；If so, being then directed to the index
Dilatation operation is performed to target Cloud Server.
In certain embodiments, dilatation operation is performed to target Cloud Server for the index, including：Obtain target cloud clothes
The configuration information of business device；The interim Cloud Server with configuration information is distributed for target Cloud Server；To target Cloud Server and
Interim Cloud Server performs load balancing operation.
In certain embodiments, at least one index includes central processing unit utilization rate；And for the index to target
Cloud Server performs dilatation operation, including：Increase the processor cores of the occupied central processing unit of target Cloud Server operation
Quantity, and restart target Cloud Server.
In certain embodiments, at least one index includes memory usage；And for the index to target cloud service
Device performs dilatation operation, including：Increase the occupied memory size of target Cloud Server operation, and restart target cloud service
Device.
In certain embodiments, dilatation operation is performed to target Cloud Server at least one index or capacity reducing is operated,
Including：For each index at least one index, predicted the outcome based on the corresponding index of the index, it is determined that default
Whether the index prediction peak value of the index in one period is less than or equal to default first peak threshold；In response to determining
The index prediction peak value of the index in first time period is less than or equal to default first peak threshold, then further determines that the
Whether the index prediction valley in one period is less than default first valley threshold；In response to determining in first time period
Index prediction valley be less than the first valley threshold, for the index to target Cloud Server perform capacity reducing operation.
In certain embodiments, the step of this method also includes training quota forecast model, including：Obtain and target cloud is taken
The history monitoring data that at least one index of business device is monitored；For each index, by the history monitoring data of the index
Middle time preceding history monitoring data is defined as input sample；By the time in the history monitoring data of the index it is rear, except true
It is set to the history monitoring data outside the history monitoring data of input sample to be defined as exporting sample；Using machine learning method,
Based on input sample and output sample, training obtains the index forecast model of the index.
Second aspect, the embodiment of the present application provides a kind of device for being used to manage the capacity of Cloud Server, the device bag
Include：First acquisition unit, is configured to obtain the monitoring data for being monitored at least one index of target Cloud Server；Lead
Enter unit, be configured to be directed to each index, obtained in the index forecast model that the monitoring data of the index is imported to training in advance
Predicted the outcome to the corresponding index of the index, wherein, index forecast model is used to characterize what monitoring data predicted the outcome with index
Corresponding relation；Execution unit, the index being configured to during the index based at least one index predicts the outcome predicts peak value, index
Valley, default first peak threshold and default first valley threshold are predicted, at least one index to target cloud service
Device performs dilatation operation or capacity reducing operation.
In certain embodiments, first acquisition unit, including：Determining module, is configured to determine to target Cloud Server
At least one index monitoring data be acquired acquisition time section whether be more than default acquisition time section threshold value；Obtain
Module, if the acquisition time section for being configured to be acquired the monitoring data of at least one index of target Cloud Server is more than
Default acquisition time section threshold value, then obtain monitoring data.
In certain embodiments, import unit is further configured to：When acquisition time section is divided into preset number
Between it is interval；For each time interval, obtain the index and be more than default second peak value in the monitoring data of the time interval
The data peaks of threshold value；Determine whether the quantity of data peaks is more than default amount threshold；If the quantity of data peaks is more than
Amount threshold, then obtain each time of origin point of each data peaks, and determines in the difference of each time of origin point most
Small difference；Each minimal difference and value of each time interval is determined, and determines and be worth whether be less than default and value threshold value；
And if value is less than default and value threshold value, and the monitoring data of the index is imported and obtained in the index forecast model of training in advance
The corresponding index of the index predicts the outcome.
In certain embodiments, execution unit is further configured to：For each index at least one index, base
Predicted the outcome in the corresponding index of the index, it is determined that whether the index of the index in default first time period predicts peak value
More than default first peak threshold；If so, then performing dilatation operation to target Cloud Server for the index.
In certain embodiments, execution unit, including：Acquisition module, is configured to obtain the configuration of target Cloud Server
Information；Distribute module, is configured to distribute the interim Cloud Server with configuration information for target Cloud Server；Performing module,
It is configured to perform load balancing operation to target Cloud Server and interim Cloud Server.
In certain embodiments, at least one index includes central processing unit utilization rate；And execution unit is further matched somebody with somebody
Putting is used for：Increase the quantity of the processor cores of the occupied central processing unit of target Cloud Server operation, and restart mesh
Mark Cloud Server.
In certain embodiments, at least one index includes memory usage；And execution unit is further configured to：
Increase the occupied memory size of target Cloud Server operation, and restart target Cloud Server.
In certain embodiments, execution unit is further configured to：For each index at least one index, base
Predicted the outcome in the corresponding index of the index, it is determined that whether the index of the index in default first time period predicts peak value
Less than or equal to default first peak threshold；In response to determining that the index of the index in first time period predicts that peak value is small
In equal to default first peak threshold, then further determine that whether the index prediction valley in first time period is less than default
The first valley threshold；In response to determining that the prediction valley of the index in first time period is less than the first valley threshold, for
The index performs capacity reducing operation to target Cloud Server.
In certain embodiments, the device also includes：Second acquisition unit, is configured to obtain to target Cloud Server
The history monitoring data that at least one index is monitored；Training unit, is configured to be directed to each index, by going through for the index
Preceding history monitoring data is defined as input sample the time in history monitoring data；By the time in the history monitoring data of the index
It is defined as exporting sample in history monitoring data rear, in addition to the history monitoring data for being defined as input sample；Utilize machine
Learning method, based on input sample and output sample, training obtains the index forecast model of the index.
The third aspect, the embodiment of the present application additionally provides a kind of server, including：One or more processors；Storage dress
Put, for storing one or more programs, when said one or multiple programs are by said one or multiple computing devices so that
Said one or multiple processors realize the method for being used to manage the capacity of Cloud Server that the application is provided.
Fourth aspect, the embodiment of the present application additionally provides a kind of computer-readable recording medium, is stored thereon with computer
Program, the program realizes the method for being used to manage the capacity of Cloud Server that the application is provided when being executed by processor.
The method and apparatus for being used to manage the capacity of Cloud Server that the application is provided, by obtaining to Cloud Server extremely
The monitoring data that a few index is monitored；Afterwards, the monitoring data of each index can be input to the finger of training in advance
The corresponding index of the index is obtained in mark forecast model to predict the outcome；Finally, it can be predicted the outcome based on These parameters, cloud is taken
Business device performs dilatation operation or capacity reducing operation, so that, it is effectively utilized the every history monitoring being monitored to Cloud Server
Data, realize the capacity management to Cloud Server.
Brief description of the drawings
By reading the detailed description made to non-limiting example made with reference to the following drawings, the application's is other
Feature, objects and advantages will become more apparent upon：
Fig. 1 is that the application can apply to exemplary system architecture figure therein；
Fig. 2 is the flow chart for being used to manage one embodiment of the method for the capacity of Cloud Server according to the application；
Fig. 3 is the schematic diagram for being used to manage an application scenarios of the method for the capacity of Cloud Server according to the application；
Fig. 4 is the flow chart for being used to manage another embodiment of the method for the capacity of Cloud Server according to the application；
Fig. 5 is the structural representation for being used to manage one embodiment of the device of the capacity of Cloud Server according to the application
Figure；
Fig. 6 is adapted for the structural representation of the computer system of the server for realizing the embodiment of the present application.
Embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that, in order to
Be easy to description, illustrate only in accompanying drawing to about the related part of invention.
It should be noted that in the case where not conflicting, the feature in embodiment and embodiment in the application can phase
Mutually combination.Describe the application in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 is shown can be using the method for the capacity for managing Cloud Server of the application or for managing cloud service
The exemplary system architecture 100 of the device of the capacity of device.
As shown in figure 1, system architecture 100 can include Cloud Server 101,102,103, network 104,105, server
106 and terminal device 107,108,109.Network 104 is used to provide between Cloud Server 101,102,103 and server 106
The medium of communication link, network 105 is used to provide between Cloud Server 101,102,103 and terminal device 107,108,109
The medium of communication link.Network 104,105 can include various connection types, such as wired, wireless communication link or optical fiber
Cable etc..
Cloud Server 101,102,103 can be interacted by network 104 with server 105, so that server is to cloud service
The indices data of device are monitored and capacity management etc..Cloud Server 101,102,103 can also by network 105 with
Terminal device 107,108,109 is interacted, and to provide various data, services for terminal device, such as data upload and/or downloaded clothes
Business etc..
Various telecommunication customer end applications can be installed on terminal device 107,108,109, such as data storage class application,
Video class application etc..Terminal device 107,108,109 can be with display screen and support the various electronics of information exchange to set
It is standby, including but not limited to smart mobile phone, tablet personal computer, E-book reader, pocket computer on knee and desktop computer etc.
Deng.
Server 106 can be to provide the server of various services, for example, carry out capacity to Cloud Server 101,102,103
The back-stage management server of management.Back-stage management server can carry out the processing such as analyzing to the monitoring data of Cloud Server, and
Capacity management is carried out to Cloud Server according to result (such as dilatation operation or capacity reducing operation).For example, back-stage management takes
Business device can obtain the monitoring data being monitored at least one index of Cloud Server first；Afterwards, will can each it refer to
Target monitoring data, which is input in the index forecast model of training in advance, to be obtained the corresponding index of the index and predicts the outcome；Finally,
Predicted the outcome based on These parameters, dilatation operation can be performed to Cloud Server or capacity reducing is operated.
It should be noted that the method for being used to manage the capacity of Cloud Server that the embodiment of the present application is provided is general by taking
Business device 106 is performed, and correspondingly, is generally positioned at for managing the device of capacity of Cloud Server in server 106.
It should be understood that the number of the Cloud Server, network, server and terminal device in Fig. 1 is only schematical.Root
Factually now need, can have any number of Cloud Server, network, server and terminal device.
With continued reference to Fig. 2, the implementation for being used to manage the method for the capacity of Cloud Server according to the application is shown
The flow 200 of example.This is used for the method for managing the capacity of Cloud Server, comprises the following steps：
Step 201, the monitoring data being monitored at least one index of target Cloud Server is obtained.
In the present embodiment, the method for the capacity for managing Cloud Server runs electronic equipment (such as Fig. 1 thereon
Shown server) at least one index of target Cloud Server can be carried out in real time or periodically to monitor；Afterwards,
The monitoring data monitored can be obtained.At least one above-mentioned index can include disk throughput, Microsoft Loopback Adapter flow etc..
In the present embodiment, above-mentioned electronic equipment is monitored to Cloud Server generally also can be regarded as to by cloud service
The monitoring of at least one index of the virtual machine of device trunked analog.Above-mentioned target Cloud Server can refer to above-mentioned electronic equipment institute
Any Cloud Server for monitoring and being managed.
Step 202, for each index, obtained in the index forecast model that the monitoring data of the index is imported to training in advance
Predicted the outcome to the corresponding index of the index.
In the present embodiment, for each index at least one above-mentioned index, above-mentioned electronic equipment can be by step
The monitoring data of the index got in 201, which is imported into the index forecast model of training in advance, obtains the corresponding finger of the index
Mark predicts the outcome.The index forecast model for multiple training in advance that can be stored with above-mentioned electronic equipment, each stored
Index forecast model is corresponding with an index, and the index that can be input to the monitoring data of the index corresponding to the index is pre-
The corresponding index of the index is obtained in survey model to predict the outcome；Training in advance can also be only stored in above-mentioned electronic equipment
Index forecast model, the index forecast model stored is corresponding with each index, can include and be supervised in above-mentioned monitoring data
The mark of the index of control, when monitoring data is input in index forecast model, can export the index associated by above-mentioned mark
Corresponding index predicts the outcome.Herein, resulting index, which predicts the outcome, can serve to indicate that These parameters at following one section
The prediction case of time, it can be one or more numerical value that index, which predicts the outcome,.
It should be noted that index forecast model can be used for characterizing the corresponding pass that monitoring data predicts the outcome with index
System.As an example, index forecast model can be system of the technical staff based on the substantial amounts of history monitoring data to each index
Count and pre-establish, the mapping table for the corresponding relation that the monitoring data that is stored with and index predict the outcome；It can also be skill
Art personnel pre-set based on the statistics to mass data and store it is into above-mentioned electronic equipment, to one in monitoring data
Individual or multiple numerical value carry out numerical computations to obtain the calculation formula of result of calculation predicted the outcome for characteristic index.
In some optional implementations of the present embodiment, above-mentioned electronic equipment can be trained according to following steps in advance
Index forecast model：
First, above-mentioned electronic equipment can be obtained (such as in first 30 days of current date, works as the day before yesterday in historical time section
In first 60 days of phase etc.) monitoring data that is monitored at least one index of above-mentioned target Cloud Server, and will be acquired
Monitoring data be defined as history monitoring data.
Afterwards, for each index at least one above-mentioned index, above-mentioned electronic equipment can be by the history of the index
Preceding history monitoring data is defined as input sample the time in monitoring data, it is possible to by the time rear and except above-mentioned determination
It is defined as exporting sample for the history monitoring data outside the history monitoring data of input data.Above-mentioned electronic equipment can when
Between in preceding history monitoring data access time length be more than multiple history monitoring datas of default time threshold as defeated
Enter data, to improve the accuracy of the index forecast model trained.
As an example, when getting monitoring data of the index in history 30 days, and above-mentioned time threshold is when being 15 days,
The monitoring data of first 15 days can be defined as input sample by above-mentioned electronic equipment, it is possible to determine the monitoring data of latter 15 days
For output sample.
Finally, above-mentioned electronic equipment can utilize machine learning method, based on above-mentioned input sample and above-mentioned output sample,
Training obtains index forecast model.Specifically, above-mentioned electronic equipment can use Raw performance forecast model, above-mentioned Raw performance
The exponential forecasting equation that forecast model can in advance be write for technical staff, preceding history monitoring data of above-mentioned time is determined
For input sample, by the above-mentioned time it is rear and except it is above-mentioned be defined as the history monitoring data of input data in addition to history monitor
Data using machine learning method, are trained to above-mentioned Raw performance forecast model as output sample, obtain the index institute
Corresponding index forecast model.The exponential forecasting equation that above-mentioned technical staff writes in advance can be following formula (1), (2),
(3)。
Wherein, t is present period (for example, the hour of the morning since 8 o'clock) in units of hour, τ be with
Hour be unit, the time span apart from present period, τ=1,2,3 ..., 24, Y predict the outcome for index,During for prediction
The index of section predicts the outcome, and T is the Trend value that index predicts the outcome, TtThe Trend value predicted the outcome for the index of present period, S
The seasonal index number predicted the outcome for index,The seasonal index number predicted the outcome for the index of a upper period for prediction period, α
For trend smoothing constant, xtIt is the average value with history monitoring data that present period is the same period (if for example, present period
A hour for being the morning since 8 o'clock, xtFor the monitoring data of a hour in history 15 days daily since 8 o'clock
Average value), St-1The seasonal index number predicted the outcome for the index of a upper period for present period, Tt-1For upper the one of present period
The Trend value that the index of period predicts the outcome, StThe seasonal index number predicted the outcome for the index of present period, γ is that season is smooth
Constant.
In some optional implementations of the present embodiment, above-mentioned electronic equipment can be by above-mentioned target Cloud Server
At least one index monitoring data be acquired acquisition time section be divided into preset number time interval, for example, can
So that daily above-mentioned acquisition time section to be divided；For each time interval, above-mentioned electronic equipment can obtain the index and exist
It is more than the data peaks of default second peak threshold in monitoring data in the time interval, above-mentioned data peaks can refer to
There may be multiple data peaks in the maximum instantaneous value of monitoring data, a time interval；Afterwards, it may be determined that above-mentioned data
Whether the quantity of peak value is more than default amount threshold, for example, when above-mentioned amount threshold is 2, it is determined that above-mentioned data peaks
Quantity whether be more than 2；If more than above-mentioned amount threshold, obtaining each time of origin point of each data peaks, wherein, one
One time of origin point of individual data peaks correspondence, it is possible to determine the minimal difference in the difference of each time of origin point, specifically
, the difference between each adjacent time of origin point can be determined first, and the difference for choosing minimum in each difference afterwards is made
For minimal difference；Then, it may be determined that each minimal difference and value of each time interval, it is possible to determine that above-mentioned and value is
It is no to be less than default and value threshold value, for example, above-mentioned and value threshold value can be 5 hours；If it is determined that above-mentioned and value is less than default
With value threshold value, then the index can will be obtained in the index forecast model of the monitoring data importing training in advance of the index corresponding
Index predicts the outcome.
Step 203, during the index based at least one index predicts the outcome index prediction peak value, index prediction valley,
Default first peak threshold and default first valley threshold, dilatation is performed at least one index to target Cloud Server
Operation or capacity reducing operation.
In the present embodiment, the finger during above-mentioned electronic equipment can be predicted the outcome based on the index of at least one above-mentioned index
Mark prediction peak value and default first peak threshold, dilatation behaviour is performed to target Cloud Server at least one above-mentioned index
Make；Index prediction valley and default first valley threshold in can also being predicted the outcome based on the index of at least one above-mentioned index
Value, capacity reducing operation is performed to target Cloud Server at least one index.
In some optional implementations of the present embodiment, however, it is determined that go out and dilatation behaviour is performed to above-mentioned target Cloud Server
Make, above-mentioned electronic equipment can carry out horizontal dilatation to above-mentioned target Cloud Server.Specifically, above-mentioned electronic equipment can be first
The configuration information of above-mentioned target Cloud Server is obtained, for example, central processing unit (Central Processing Unit, CPU)
The quantity of processor cores (also referred to as processor core), memory size etc.；Afterwards, can be above-mentioned target Cloud Server point
With the interim Cloud Server with above-mentioned configuration information；Finally, can be to above-mentioned target Cloud Server and above-mentioned interim cloud service
Device performs load balancing operation, and load balancing operation exactly shares task to be performed on multiple operating units.As showing
Example, when the configuration information for getting above-mentioned target Cloud Server is CPU：1 core, internal memory：1GB, then can be above-mentioned target cloud clothes
It is 1 core, the interior interim Cloud Server for saving as 1GB that business device, which distributes a CPU,.
In some optional implementations of the present embodiment, however, it is determined that go out and dilatation behaviour is performed to above-mentioned target Cloud Server
Make, above-mentioned electronic equipment can also carry out longitudinal dilatation to above-mentioned target Cloud Server.Specifically, at least one above-mentioned index can
So that including central processing unit utilization rate, above-mentioned electronic equipment can increase center occupied during above-mentioned target Cloud Server operation
The quantity (being 2 cores such as by the increase of 1 core) of the processor cores of processor, and restart above-mentioned target Cloud Server.
With continued reference to Fig. 3, Fig. 3 is the one of the application scenarios of the method for the capacity for managing Cloud Server of the present embodiment
Individual schematic diagram.In Fig. 3 application scenarios, server 301 gets at least one index progress to Cloud Server 302 first
The monitoring data 303 of monitoring；Afterwards, for each index, the monitoring data 303 of the index is imported into advance by server 301
The corresponding index of the index is obtained in the index forecast model of training and predicts the outcome 304；Finally, server 301 is based at least one
Predict the outcome 304 pairs of Cloud Servers 302 of the index of individual index perform dilatations operation 305 or perform capacity reducing operation 306.
The method that above-described embodiment of the application is provided can obtain at least one index progress to Cloud Server first
The monitoring data of monitoring；Afterwards, the monitoring data of each index can be input in the index forecast model of training in advance and obtained
Predicted the outcome to the corresponding index of the index；Finally, it can be predicted the outcome based on These parameters, dilatation behaviour is performed to Cloud Server
Make or capacity reducing operation, so that, the every history monitoring data being monitored to Cloud Server is effectively utilized, is realized to cloud
The capacity management of server.
With further reference to Fig. 4, it illustrates the stream of another embodiment of the method for the capacity for managing Cloud Server
Journey 400.This is used for the flow 400 for managing the method for the capacity of Cloud Server, comprises the following steps：
Step 401, it is determined that the acquisition time that the monitoring data at least one index of target Cloud Server is acquired
Whether section is more than default acquisition time section threshold value.
In the present embodiment, the method for the capacity for managing Cloud Server runs electronic equipment (such as Fig. 1 thereon
Shown server) collection being acquired to the monitoring data of at least one index of target Cloud Server can be obtained first
Period, afterwards, it may be determined that whether above-mentioned acquisition time section is more than default acquisition time section threshold value, if above-mentioned acquisition time
Section is more than default acquisition time section threshold value, then can perform step 402.For example, above-mentioned acquisition time length threshold is 14 days
When, when the number of days of acquisition monitoring data is more than 14 days, then it can perform step 402.
Step 402, monitoring data is obtained.
In the present embodiment, when determining that above-mentioned acquisition time section is more than default acquisition time section threshold value in step 401
When, above-mentioned electronic equipment can obtain the monitoring data of at least one index of above-mentioned target Cloud Server, it is above-mentioned at least one
Index can include central processing unit utilization rate, memory usage, disk throughput, Microsoft Loopback Adapter flow etc..
Step 403, for each index, obtained in the index forecast model that the monitoring data of the index is imported to training in advance
Predicted the outcome to the corresponding index of the index.
In the present embodiment, the operation of step 403 and the operation of step 202 are essentially identical, will not be repeated here.
Step 404, predicted the outcome based on the corresponding index of the index, it is determined that the index in default first time period
Index prediction peak value whether be more than default first peak threshold.
In the present embodiment, above-mentioned electronic equipment can determine in default first time period (such as following 6 hours
It is interior) the index index predict the outcome in index prediction peak value whether be more than default first peak threshold；If above-mentioned finger
Mark prediction peak value is more than above-mentioned first peak threshold, then can perform step 405；If These parameters prediction peak value is less than or equal to upper
The first peak threshold is stated, then can perform step 406.These parameters prediction peak value can be the maximum wink during index predict the outcome
Between be worth, there may be multiple indexs prediction peak values in above-mentioned first time period.As an example, it is cpu busy percentage to work as the index,
When corresponding first peak threshold of cpu busy percentage is 80%, if within 6 hours futures, there is two indices prediction peak in the index
Value 75% and 93%, index prediction peak value 93% is more than above-mentioned first peak threshold, then illustrates there is CPU within 6 hours futures
The situation of resource excessively anxiety.
Step 405, dilatation operation is performed to target Cloud Server for the index.
In the present embodiment, when determined in step 404 These parameters prediction peak value be more than above-mentioned first peak threshold, on
Dilatation operation can be performed to above-mentioned target Cloud Server for the index by stating electronic equipment.
In the present embodiment, at least one above-mentioned index can include memory usage, and above-mentioned electronic equipment can increase
Occupied memory size (being 2GB such as by 1GB increases) during above-mentioned target Cloud Server operation, and restart above-mentioned target cloud
Server.
In the present embodiment, above-mentioned electronic equipment can also determine the index of the index in default second time period
Predict whether peak value is more than default first peak threshold, above-mentioned second time period is typically larger than above-mentioned first time period, if
The index prediction peak value of the index is more than default first peak threshold in above-mentioned second time period, then can be pushed away to technical staff
Send the nervous prompt message of resource in second time period.
Step 406, it is determined that whether the index prediction valley in first time period is less than default first valley threshold.
In the present embodiment, when determined in step 404 These parameters prediction peak value be less than or equal to above-mentioned first peak value threshold
During value, above-mentioned electronic equipment can determine whether the index prediction valley in first time period is less than default first valley threshold
Value, if These parameters prediction valley is less than default first valley threshold, can perform step 407.These parameters predict paddy
Value can be the minimum instant value during index predict the outcome, and there may be multiple indexs prediction paddy in above-mentioned first time period
Value.
Step 407, capacity reducing operation is performed to target Cloud Server for the index.
In the present embodiment, when determine in a step 406 These parameters prediction valley be less than default first valley threshold
During value, above-mentioned electronic equipment can perform capacity reducing operation to above-mentioned target Cloud Server for the index.
In the present embodiment, when the index is central processing unit utilization rate, above-mentioned electronic equipment can reduce above-mentioned mesh
The quantity (being such as reduced to 1 core by 2 cores) of the processor cores of central processing unit occupied during Cloud Server operation is marked, and again
Start above-mentioned target Cloud Server.
In the present embodiment, when the index is memory usage, above-mentioned electronic equipment can reduce above-mentioned target cloud clothes
Occupied memory size (1GB is such as reduced to by 2GB) during business device operation, and restart above-mentioned target Cloud Server.
Figure 4, it is seen that compared with the corresponding embodiments of Fig. 2, being used in the present embodiment manages Cloud Server
The step of flow 400 of the method for capacity highlights the opportunity for obtaining monitoring data and predicted the outcome progress based on obtained index
The step of dilatation operation or capacity reducing are operated.Thus, the scheme of the present embodiment description can get more monitoring datas, from
And make it that the opportunity that dilatation operation or capacity reducing operation are carried out to Cloud Server is more accurate.
With further reference to Fig. 5, as the realization to method shown in above-mentioned each figure, it is used to manage cloud this application provides one kind
One embodiment of the device of the capacity of server, the device embodiment is corresponding with the embodiment of the method shown in Fig. 2, the device
Specifically it can apply in various electronic equipments.
As shown in figure 5, the device 500 of the capacity for managing Cloud Server of the present embodiment includes：First acquisition unit
501st, import unit 502 and execution unit 503.Wherein, first acquisition unit 501 is configured to obtain to target Cloud Server
The monitoring data that at least one index is monitored；Import unit 502 is configured to be directed to each index, by the monitoring of the index
The corresponding index of the index is obtained in the index forecast model of data importing training in advance to predict the outcome, wherein, index prediction mould
Type is used to characterize the corresponding relation that monitoring data predicts the outcome with index；Execution unit 503 is configured to refer to based at least one
Index during target index predicts the outcome predicts peak value, index prediction valley, default first peak threshold and default first
Valley threshold, performs dilatation operation to target Cloud Server at least one index or capacity reducing is operated.
In the present embodiment, for the capacity that manages Cloud Server device 500 first acquisition unit 501, import it is single
Member 502 may be referred to step 201, step 202 and step in the corresponding embodiments of Fig. 2 with the specific processing of execution unit 503
203。
In some optional implementations of the present embodiment, above-mentioned first acquisition unit 501 can include determining that module
(not shown) and acquisition module (not shown).Above-mentioned determining module can be obtained to target Cloud Server extremely first
The acquisition time section that the monitoring data of a few index is acquired, afterwards, it may be determined that whether above-mentioned acquisition time section is more than
Default acquisition time section threshold value, if above-mentioned acquisition time section is more than default acquisition time section threshold value, above-mentioned acquisition module
The monitoring data of at least one index of above-mentioned target Cloud Server can be obtained, at least one above-mentioned index can include center
Processor utilization, memory usage, disk throughput, Microsoft Loopback Adapter flow etc..
In some optional implementations of the present embodiment, above-mentioned import unit 502 will can take to above-mentioned target cloud
The acquisition time section that the monitoring data of at least one index of business device is acquired is divided into preset number time interval, example
Such as, daily above-mentioned acquisition time section can be divided；For each time interval, above-mentioned electronic equipment can obtain this and refer to
The data peaks for being more than default second peak threshold in the monitoring data in the time interval are marked on, above-mentioned data peaks can be with
Refer to there may be multiple data peaks in the maximum instantaneous value of monitoring data, a time interval；Afterwards, it may be determined that above-mentioned
Whether the quantity of data peaks is more than default amount threshold, for example, when above-mentioned amount threshold is 2, it is determined that above-mentioned data
Whether the quantity of peak value is more than 2；If more than above-mentioned amount threshold, obtaining each time of origin point of each data peaks, its
In, data peaks one time of origin point of correspondence, it is possible to determine the minimal difference in the difference of each time of origin point,
Specifically, the difference between each adjacent time of origin point can be determined first, the difference of minimum is chosen in each difference afterwards
Value is used as minimal difference；Then, it may be determined that each time interval each minimal difference and value, it is possible to determine it is above-mentioned and
Whether value is less than default and value threshold value, for example, above-mentioned and value threshold value can be 5 hours；If it is determined that above-mentioned and value is less than in advance
And if value threshold value, then can will the index monitoring data import training in advance index forecast model in obtain the index pair
The index answered predicts the outcome.
In some optional implementations of the present embodiment, above-mentioned execution unit 503 can be determined default first
Whether the index prediction peak value during the index of the index in the period predicts the outcome is more than default first peak threshold；If referring to
Mark prediction peak value is more than above-mentioned first peak threshold, then dilatation behaviour can be performed to above-mentioned target Cloud Server for the index
Make.These parameters prediction peak value can be the maximum instantaneous value during index predict the outcome, and can be deposited in above-mentioned first time period
Peak value is predicted in multiple indexs.
In some optional implementations of the present embodiment, above-mentioned execution unit 503 can include acquisition module (in figure
It is not shown), distribute module (not shown) and performing module (not shown).Specifically, above-mentioned acquisition module can be first
First obtain the configuration information of above-mentioned target Cloud Server；Afterwards, above-mentioned distribute module can be the distribution of above-mentioned target Cloud Server
Interim Cloud Server with above-mentioned configuration information；Finally, above-mentioned performing module can be to above-mentioned target Cloud Server and above-mentioned
Interim Cloud Server performs load balancing operation, and load balancing operation exactly shares task to be held on multiple operating units
OK.
In some optional implementations of the present embodiment, at least one above-mentioned index can include central processing unit profit
With rate, above-mentioned execution unit 503 can increase the processor of central processing unit occupied during above-mentioned target Cloud Server operation
The quantity of kernel, and restart above-mentioned target Cloud Server.
In some optional implementations of the present embodiment, at least one above-mentioned index can include memory usage,
Above-mentioned execution unit 503 can increase memory size occupied during above-mentioned target Cloud Server operation, and restart above-mentioned
Target Cloud Server.
In some optional implementations of the present embodiment, above-mentioned execution unit 503 can be determined default first
Whether the index prediction peak value during the index of the index in the period predicts the outcome is less than or equal to default first peak threshold；
When determining that These parameters prediction peak value is less than or equal to above-mentioned first peak threshold, above-mentioned execution unit 503 can be determined
Whether the index prediction valley in first time period is less than default first valley threshold, if These parameters prediction valley is less than in advance
If the first valley threshold, then can for the index to above-mentioned target Cloud Server perform capacity reducing operation.These parameters are predicted
Valley can be the minimum instant value during index predict the outcome, and there may be multiple indexs prediction paddy in above-mentioned first time period
Value.
In some optional implementations of the present embodiment, the above-mentioned device 500 for being used to manage the capacity of Cloud Server
Second acquisition unit (not shown) and training unit (not shown) can also be included.Above-mentioned second acquisition unit can be with
The monitoring data that at least one index to above-mentioned target Cloud Server in historical time section is monitored is obtained, and will be obtained
The monitoring data taken is defined as history monitoring data.For each index at least one above-mentioned index, above-mentioned training unit
Time preceding history monitoring data in the history monitoring data of the index can be defined as input sample, it is possible to by the time
It is rear and except it is above-mentioned be defined as the history monitoring data of input data in addition to history monitoring data be defined as export sample, most
Afterwards, it is possible to use machine learning method, based on above-mentioned input sample and above-mentioned output sample, training obtains index forecast model.
Below with reference to Fig. 6, it illustrates suitable for the computer system 600 for the server of realizing the embodiment of the present invention
Structural representation.Server shown in Fig. 6 is only an example, to the function of the embodiment of the present application and should not use range band
Carry out any limitation.
As shown in fig. 6, computer system 600 includes CPU (CPU) 601, it can be read-only according to being stored in
Program in memory (ROM) 602 or be loaded into program in random access storage device (RAM) 603 from storage part 608 and
Perform various appropriate actions and processing.In RAM 603, the system that is also stored with 600 operates required various programs and data.
CPU 601, ROM 602 and RAM 603 are connected with each other by bus 604.Input/output (I/O) interface 605 is also connected to always
Line 604.
I/O interfaces 605 are connected to lower component：Importation 606 including keyboard, mouse etc.；Including such as liquid crystal
Show the output par, c 607 of device (LCD) and loudspeaker etc.；Storage part 608 including hard disk etc.；And including such as LAN card,
The communications portion 609 of the NIC of modem etc..Communications portion 609 performs communication via the network of such as internet
Processing.Driver 610 is also according to needing to be connected to I/O interfaces 605.Detachable media 611, such as disk, CD, magneto-optic disk,
Semiconductor memory etc., is arranged on driver 610 as needed, in order to which the computer program that reads from it is according to need
It is mounted into storage part 608.
Especially, in accordance with an embodiment of the present disclosure, the process described above with reference to flow chart may be implemented as computer
Software program.For example, embodiment of the disclosure includes a kind of computer program product, it includes being carried on computer-readable medium
On computer program, the computer program include be used for execution flow chart shown in method program code.In such reality
Apply in example, the computer program can be downloaded and installed by communications portion 609 from network, and/or from detachable media
611 are mounted.When the computer program is performed by CPU (CPU) 601, perform what is limited in the present processes
Above-mentioned functions.It should be noted that the above-mentioned computer-readable medium of the application can be computer-readable signal media or
Computer-readable recording medium either the two any combination.Computer-readable recording medium for example can be --- but
Be not limited to --- electricity, magnetic, optical, electromagnetic, system, device or the device of infrared ray or semiconductor, or it is any more than combination.
The more specifically example of computer-readable recording medium can include but is not limited to：Electrical connection with one or more wires,
Portable computer diskette, hard disk, random access storage device (RAM), read-only storage (ROM), erasable type may be programmed read-only deposit
Reservoir (EPROM or flash memory), optical fiber, portable compact disc read-only storage (CD-ROM), light storage device, magnetic memory
Part or above-mentioned any appropriate combination.In this application, computer-readable recording medium can any be included or store
The tangible medium of program, the program can be commanded execution system, device or device and use or in connection.And
In the application, computer-readable signal media can include believing in a base band or as the data of carrier wave part propagation
Number, wherein carrying computer-readable program code.The data-signal of this propagation can take various forms, including but not
It is limited to electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be computer
Any computer-readable medium beyond readable storage medium storing program for executing, the computer-readable medium can send, propagate or transmit use
In by the use of instruction execution system, device or device or program in connection.Included on computer-readable medium
Program code any appropriate medium can be used to transmit, include but is not limited to：Wirelessly, electric wire, optical cable, RF etc., Huo Zheshang
Any appropriate combination stated.
Flow chart and block diagram in accompanying drawing, it is illustrated that according to the system of various embodiments of the invention, method and computer journey
Architectural framework in the cards, function and the operation of sequence product.At this point, each square frame in flow chart or block diagram can generation
The part of one module of table, program segment or code, the part of the module, program segment or code is used comprising one or more
In the executable instruction for realizing defined logic function.It should also be noted that in some realizations as replacement, being marked in square frame
The function of note can also be with different from the order marked in accompanying drawing generation.For example, two square frames succeedingly represented are actually
It can perform substantially in parallel, they can also be performed in the opposite order sometimes, this is depending on involved function.Also to note
Meaning, the combination of each square frame in block diagram and/or flow chart and the square frame in block diagram and/or flow chart can be with holding
The special hardware based system of function or operation as defined in row is realized, or can use specialized hardware and computer instruction
Combination realize.
Being described in unit involved in the embodiment of the present invention can be realized by way of software, can also be by hard
The mode of part is realized.Described unit can also be set within a processor, for example, can be described as：A kind of processor bag
Include first acquisition unit, import unit and execution unit.Wherein, the title of these units is not constituted to this under certain conditions
The restriction of unit in itself.For example, first acquisition unit is also described as " obtaining and referring at least one of target Cloud Server
Mark the unit for the monitoring data being monitored ".
As on the other hand, present invention also provides a kind of computer-readable medium, the computer-readable medium can be
Included in device described in above-described embodiment；Can also be individualism, and without be incorporated the device in.Above-mentioned calculating
Machine computer-readable recording medium carries one or more program, when said one or multiple programs are performed by the device so that should
Device：Obtain the monitoring data being monitored at least one index of target Cloud Server；For each index, by the index
Monitoring data import and obtain the corresponding index of the index in the index forecast model of training in advance and predict the outcome, wherein, index
Forecast model is used to characterize the corresponding relation that monitoring data predicts the outcome with index；Index prediction knot based at least one index
Index prediction peak value, index prediction valley, default first peak threshold and default first valley threshold in fruit, for extremely
A few index performs dilatation operation to target Cloud Server or capacity reducing is operated.
Above description is only presently preferred embodiments of the present invention and the explanation to institute's application technology principle.People in the art
Member should be appreciated that invention scope involved in the present invention, however it is not limited to the technology of the particular combination of above-mentioned technical characteristic
Scheme, while should also cover in the case where not departing from foregoing invention design, is carried out by above-mentioned technical characteristic or its equivalent feature
Other technical schemes formed by any combination.Such as features described above has similar work(with the (but not limited to) disclosed in the present invention
The technical characteristic of energy carries out technical scheme formed by replacement mutually.
Claims (20)
1. a kind of method for being used to manage the capacity of Cloud Server, it is characterised in that methods described includes：
Obtain the monitoring data being monitored at least one index of target Cloud Server；
For each index, the monitoring data of the index is imported index correspondence is obtained in the index forecast model of training in advance
Index predict the outcome, wherein, the index forecast model is used to characterize the corresponding relation that monitoring data and index predict the outcome；
Index based at least one index predict the outcome in index prediction peak value, index prediction valley, default the
One peak threshold and default first valley threshold, dilatation is performed at least one described index to the target Cloud Server
Operation or capacity reducing operation.
2. according to the method described in claim 1, it is characterised in that described at least one index obtained to target Cloud Server
The monitoring data being monitored, including：
It is determined that whether the acquisition time section that the monitoring data at least one index of target Cloud Server is acquired is more than in advance
If acquisition time section threshold value；
If so, then obtaining the monitoring data.
3. method according to claim 2, it is characterised in that the monitoring data by the index imports training in advance
The corresponding index of the index is obtained in index forecast model to predict the outcome, including：
Acquisition time section is divided into preset number time interval；For each time interval, the index is obtained at this
It is more than the data peaks of default second peak threshold in the monitoring data of time interval；Determining the quantity of the data peaks is
It is no to be more than default amount threshold；If the quantity of the data peaks is more than the amount threshold, each data peaks is obtained
Each time of origin point, and determine the minimal difference in the difference of each time of origin point；Determine each of each time interval
Individual minimal difference and value, and determine whether described and value is less than default and value threshold value；If it is described and value be less than it is default and
It is worth threshold value, then it is pre- to obtain the corresponding index of the index in the index forecast model that the monitoring data of the index is imported to training in advance
Survey result.
4. according to the method described in claim 1, it is characterised in that described at least one index for described in is to the target cloud
Server performs dilatation operation or capacity reducing operation, including：
For each index at least one described index, predicted the outcome based on the corresponding index of the index, it is determined that default
First time period in the index index prediction peak value whether be more than default first peak threshold；If so, then for being somebody's turn to do
Index performs dilatation operation to the target Cloud Server.
5. method according to claim 4, it is characterised in that described to be performed for the index to the target Cloud Server
Dilatation is operated, including：
Obtain the configuration information of the target Cloud Server；
The interim Cloud Server with the configuration information is distributed for the target Cloud Server；
Load balancing operation is performed to the target Cloud Server and the interim Cloud Server.
6. method according to claim 4, it is characterised in that at least one described index is utilized including central processing unit
Rate；And
It is described that dilatation operation is performed to the target Cloud Server for the index, including：
Increase the quantity of the processor cores of the occupied central processing unit of the target Cloud Server operation, and restart institute
State target Cloud Server.
7. method according to claim 4, it is characterised in that at least one described index includes memory usage；And
It is described that dilatation operation is performed to the target Cloud Server for the index, including：
Increase the occupied memory size of the target Cloud Server operation, and restart the target Cloud Server.
8. according to the method described in claim 1, it is characterised in that described at least one index for described in is to the target cloud
Server performs dilatation operation or capacity reducing operation, including：
For each index at least one described index, predicted the outcome based on the corresponding index of the index, it is determined that default
First time period in the index index prediction peak value whether be less than or equal to default first peak threshold；In response to determining
The index prediction peak value of the index gone out in the first time period is less than or equal to default first peak threshold, then further
It is determined that whether the index prediction valley in the first time period is less than default first valley threshold；In response to determining
Index prediction valley in the first time period is less than first valley threshold, for the index to the target cloud service
Device performs capacity reducing operation.
9. according to the method described in claim 1, it is characterised in that methods described also includes the step of training quota forecast model
Suddenly, including：
Obtain the history monitoring data being monitored at least one index of the target Cloud Server；
For each index, time preceding history monitoring data in the history monitoring data of the index is defined as to input sample
This；By the time in the history monitoring data of the index it is rear, except it is described be defined as the history monitoring data of input sample in addition to
History monitoring data is defined as exporting sample；Using machine learning method, based on the input sample and the output sample, instruction
Get the index forecast model of the index.
10. a kind of device for being used to manage the capacity of Cloud Server, it is characterised in that described device includes：
First acquisition unit, is configured to obtain the monitoring data for being monitored at least one index of target Cloud Server；
Import unit, is configured to be directed to each index, and the index that the monitoring data of the index is imported into training in advance predicts mould
The corresponding index of the index is obtained in type to predict the outcome, wherein, the index forecast model is used to characterize monitoring data and index
The corresponding relation predicted the outcome；
Execution unit, the index being configured to during the index based at least one index predicts the outcome predicts peak value, index
Valley, default first peak threshold and default first valley threshold are predicted, at least one described index to the mesh
Mark Cloud Server and perform dilatation operation or capacity reducing operation.
11. device according to claim 10, it is characterised in that the first acquisition unit, including：
Determining module, is configured to the collection for determining to be acquired the monitoring data of at least one index of target Cloud Server
Whether the period is more than default acquisition time section threshold value；
Acquisition module, if be configured to the collection being acquired to the monitoring data of at least one index of target Cloud Server
Between section be more than default acquisition time section threshold value, then obtain the monitoring data.
12. device according to claim 11, it is characterised in that the import unit is further configured to：
Acquisition time section is divided into preset number time interval；For each time interval, the index is obtained at this
It is more than the data peaks of default second peak threshold in the monitoring data of time interval；Determining the quantity of the data peaks is
It is no to be more than default amount threshold；If the quantity of the data peaks is more than the amount threshold, each data peaks is obtained
Each time of origin point, and determine the minimal difference in the difference of each time of origin point；Determine each of each time interval
Individual minimal difference and value, and determine whether described and value is less than default and value threshold value；If it is described and value be less than it is default and
It is worth threshold value, then it is pre- to obtain the corresponding index of the index in the index forecast model that the monitoring data of the index is imported to training in advance
Survey result.
13. device according to claim 10, it is characterised in that the execution unit is further configured to：
For each index at least one described index, predicted the outcome based on the corresponding index of the index, it is determined that default
First time period in the index index prediction peak value whether be more than default first peak threshold；If so, then for being somebody's turn to do
Index performs dilatation operation to the target Cloud Server.
14. device according to claim 13, it is characterised in that the execution unit, including：
Acquisition module, is configured to obtain the configuration information of the target Cloud Server；
Distribute module, is configured to distribute the interim Cloud Server with the configuration information for the target Cloud Server；
Performing module, is configured to perform load balancing operation to the target Cloud Server and the interim Cloud Server.
15. device according to claim 13, it is characterised in that at least one described index is utilized including central processing unit
Rate；And
The execution unit is further configured to：
Increase the quantity of the processor cores of the occupied central processing unit of the target Cloud Server operation, and restart institute
State target Cloud Server.
16. device according to claim 13, it is characterised in that at least one described index includes memory usage；With
And
The execution unit is further configured to：
Increase the occupied memory size of the target Cloud Server operation, and restart the target Cloud Server.
17. device according to claim 10, it is characterised in that the execution unit is further configured to：
For each index at least one described index, predicted the outcome based on the corresponding index of the index, it is determined that default
First time period in the index index prediction peak value whether be less than or equal to default first peak threshold；In response to determining
The index prediction peak value of the index gone out in the first time period is less than or equal to default first peak threshold, then further
It is determined that whether the index prediction valley in the first time period is less than default first valley threshold；In response to determining
Index prediction valley in the first time period is less than first valley threshold, for the index to the target cloud service
Device performs capacity reducing operation.
18. device according to claim 10, it is characterised in that described device also includes：
Second acquisition unit, is configured to obtain and the history that at least one index of the target Cloud Server is monitored is supervised
Control data；
Training unit, is configured to be directed to each index, and the preceding history of time in the history monitoring data of the index is monitored
Data are defined as input sample；By the time in the history monitoring data of the index it is rear, except described be defined as going through for input sample
History monitoring data outside history monitoring data is defined as exporting sample；Using machine learning method, based on the input sample
With the output sample, training obtains the index forecast model of the index.
19. a kind of server, including：
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are by one or more of computing devices so that one or more of processors are real
The existing method as described in any in claim 1-9.
20. a kind of computer-readable recording medium, is stored thereon with computer program, it is characterised in that the program is by processor
The method as described in any in claim 1-9 is realized during execution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710612567.8A CN107231264A (en) | 2017-07-25 | 2017-07-25 | For the method and apparatus for the capacity for managing Cloud Server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710612567.8A CN107231264A (en) | 2017-07-25 | 2017-07-25 | For the method and apparatus for the capacity for managing Cloud Server |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107231264A true CN107231264A (en) | 2017-10-03 |
Family
ID=59956608
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710612567.8A Pending CN107231264A (en) | 2017-07-25 | 2017-07-25 | For the method and apparatus for the capacity for managing Cloud Server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107231264A (en) |
Cited By (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108322541A (en) * | 2018-02-09 | 2018-07-24 | 杭州顺网科技股份有限公司 | A kind of adaptive Distributed architecture |
| CN108845881A (en) * | 2018-05-30 | 2018-11-20 | 有米科技股份有限公司 | The method and device of server capacity dynamic adjustment |
| CN108961080A (en) * | 2018-06-29 | 2018-12-07 | 渤海人寿保险股份有限公司 | Insurance business distributed approach, device, storage medium and terminal |
| CN108984304A (en) * | 2018-07-11 | 2018-12-11 | 广东亿迅科技有限公司 | Server expansion calculation method and device based on regression equation |
| CN109032788A (en) * | 2018-06-29 | 2018-12-18 | 北京百度网讯科技有限公司 | Reserved resource pool dynamic dispatching method, device, computer equipment and storage medium |
| CN109067619A (en) * | 2018-09-25 | 2018-12-21 | 海南民航凯亚有限公司 | A kind of elasticity volume dispatching method and processing terminal that micro services are administered |
| CN109284871A (en) * | 2018-09-30 | 2019-01-29 | 北京金山云网络技术有限公司 | Resource adjusting method, device and cloud platform |
| CN109324802A (en) * | 2018-09-29 | 2019-02-12 | 北京百度网讯科技有限公司 | Method and apparatus for configuration server |
| CN109495306A (en) * | 2018-11-27 | 2019-03-19 | 平安科技（深圳）有限公司 | A kind of expansion method and equipment of business network |
| CN109756372A (en) * | 2018-12-29 | 2019-05-14 | 亚信科技（中国）有限公司 | A kind of elastic telescopic method and device of telecommunication charging system |
| CN109885469A (en) * | 2019-02-27 | 2019-06-14 | 深信服科技股份有限公司 | A kind of expansion method, prediction model creation method, device, equipment and medium |
| CN109992412A (en) * | 2019-02-19 | 2019-07-09 | 广州视源电子科技股份有限公司 | Capacity adjusting method and device of cloud server, storage medium and cloud server |
| 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 |
| CN110347502A (en) * | 2019-06-21 | 2019-10-18 | 无锡华云数据技术服务有限公司 | Load equilibration scheduling method, device and the electronic equipment of cloud host server |
| CN110389817A (en) * | 2018-04-20 | 2019-10-29 | 伊姆西Ip控股有限责任公司 | Dispatching method, device and the computer program product of cloudy system |
| CN110389876A (en) * | 2019-06-18 | 2019-10-29 | 平安科技（深圳）有限公司 | Basic resource capacity monitoring and managing method, device, equipment and storage medium |
| 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 |
| CN110753366A (en) * | 2018-07-24 | 2020-02-04 | 中国移动通信集团浙江有限公司 | Prediction processing method and device for industry short message gateway capacity |
| CN111416836A (en) * | 2020-02-13 | 2020-07-14 | 中国平安人寿保险股份有限公司 | Nginx-based server maintenance method and device, computer equipment and storage medium |
| CN111427758A (en) * | 2020-03-17 | 2020-07-17 | 北京百度网讯科技有限公司 | Task calculation amount determining method and device and electronic equipment |
| CN111865635A (en) * | 2019-04-29 | 2020-10-30 | 中国移动通信集团贵州有限公司 | Method and device for determining out-of-limit time of ring network capacity |
| CN112115036A (en) * | 2020-09-28 | 2020-12-22 | 中国银行股份有限公司 | Cluster capacity prediction method and device |
| CN112445613A (en) * | 2020-11-02 | 2021-03-05 | 浙江大华技术股份有限公司 | Elastic expansion and contraction method for stream processing platform, electronic equipment and storage medium |
| CN112540902A (en) * | 2020-12-03 | 2021-03-23 | 山东云海国创云计算装备产业创新中心有限公司 | Method, device and equipment for testing performance of system on chip and readable storage medium |
| CN112685390A (en) * | 2021-03-22 | 2021-04-20 | 阿里云计算有限公司 | Database instance management method and device and computing equipment |
| CN113254209A (en) * | 2021-05-28 | 2021-08-13 | 北京奇艺世纪科技有限公司 | Capacity management method and device, electronic equipment and readable storage medium |
| CN113360250A (en) * | 2021-08-09 | 2021-09-07 | 连连宝(杭州)信息技术有限公司 | Application service resource control method, device, equipment and medium |
| CN113407297A (en) * | 2020-03-17 | 2021-09-17 | 中国移动通信集团浙江有限公司 | Container management method and device and computing equipment |
| CN113485838A (en) * | 2021-07-26 | 2021-10-08 | 北京沃东天骏信息技术有限公司 | Server distribution method and device, electronic equipment and computer readable storage medium |
| CN113722098A (en) * | 2021-08-30 | 2021-11-30 | 平安国际智慧城市科技股份有限公司 | Server capacity prediction method, device, equipment and medium based on artificial intelligence |
| 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 (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103164279A (en) * | 2011-12-13 | 2013-06-19 | 中国电信股份有限公司 | Method and system for distributing cloud computing resources |
| CN104038392A (en) * | 2014-07-04 | 2014-09-10 | 云南电网公司 | Method for evaluating service quality of cloud computing resources |
| US20160088006A1 (en) * | 2014-09-23 | 2016-03-24 | Chaitali GUPTA | Predictive model for anomaly detection and feedback-based scheduling |
| CN106453564A (en) * | 2016-10-18 | 2017-02-22 | 北京京东尚科信息技术有限公司 | Elastic cloud distributed massive request processing method, device and system |
| CN106686136A (en) * | 2017-02-24 | 2017-05-17 | 郑州云海信息技术有限公司 | Cloud resource scheduling method and device |
| CN106961351A (en) * | 2017-03-03 | 2017-07-18 | 南京邮电大学 | Intelligent elastic telescopic method based on Docker container clusters |
-
2017
- 2017-07-25 CN CN201710612567.8A patent/CN107231264A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103164279A (en) * | 2011-12-13 | 2013-06-19 | 中国电信股份有限公司 | Method and system for distributing cloud computing resources |
| CN104038392A (en) * | 2014-07-04 | 2014-09-10 | 云南电网公司 | Method for evaluating service quality of cloud computing resources |
| US20160088006A1 (en) * | 2014-09-23 | 2016-03-24 | Chaitali GUPTA | Predictive model for anomaly detection and feedback-based scheduling |
| CN106453564A (en) * | 2016-10-18 | 2017-02-22 | 北京京东尚科信息技术有限公司 | Elastic cloud distributed massive request processing method, device and system |
| CN106686136A (en) * | 2017-02-24 | 2017-05-17 | 郑州云海信息技术有限公司 | Cloud resource scheduling method and device |
| CN106961351A (en) * | 2017-03-03 | 2017-07-18 | 南京邮电大学 | Intelligent elastic telescopic method based on Docker container clusters |
Cited By (44)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108322541B (en) * | 2018-02-09 | 2021-04-06 | 杭州顺网科技股份有限公司 | Self-adaptive distributed system architecture |
| CN108322541A (en) * | 2018-02-09 | 2018-07-24 | 杭州顺网科技股份有限公司 | A kind of adaptive Distributed architecture |
| CN110389817A (en) * | 2018-04-20 | 2019-10-29 | 伊姆西Ip控股有限责任公司 | Dispatching method, device and the computer program product of cloudy system |
| CN110389817B (en) * | 2018-04-20 | 2023-05-23 | 伊姆西Ip控股有限责任公司 | Scheduling method, device and computer readable medium of multi-cloud system |
| CN108845881A (en) * | 2018-05-30 | 2018-11-20 | 有米科技股份有限公司 | The method and device of server capacity dynamic adjustment |
| CN109032788A (en) * | 2018-06-29 | 2018-12-18 | 北京百度网讯科技有限公司 | Reserved resource pool dynamic dispatching method, device, computer equipment and storage medium |
| CN108961080A (en) * | 2018-06-29 | 2018-12-07 | 渤海人寿保险股份有限公司 | Insurance business distributed approach, device, storage medium and terminal |
| CN108984304A (en) * | 2018-07-11 | 2018-12-11 | 广东亿迅科技有限公司 | Server expansion calculation method and device based on regression equation |
| CN110753366A (en) * | 2018-07-24 | 2020-02-04 | 中国移动通信集团浙江有限公司 | Prediction processing method and device for industry short message gateway capacity |
| CN109067619A (en) * | 2018-09-25 | 2018-12-21 | 海南民航凯亚有限公司 | A kind of elasticity volume dispatching method and processing terminal that micro services are administered |
| CN109324802A (en) * | 2018-09-29 | 2019-02-12 | 北京百度网讯科技有限公司 | Method and apparatus for configuration server |
| CN109284871A (en) * | 2018-09-30 | 2019-01-29 | 北京金山云网络技术有限公司 | Resource adjusting method, device and cloud platform |
| CN109495306A (en) * | 2018-11-27 | 2019-03-19 | 平安科技（深圳）有限公司 | A kind of expansion method and equipment of business network |
| CN109495306B (en) * | 2018-11-27 | 2022-02-01 | 平安科技（深圳）有限公司 | Method and equipment for expanding capacity of service network |
| CN109756372A (en) * | 2018-12-29 | 2019-05-14 | 亚信科技（中国）有限公司 | A kind of elastic telescopic method and device of telecommunication charging system |
| CN109992412A (en) * | 2019-02-19 | 2019-07-09 | 广州视源电子科技股份有限公司 | Capacity adjusting method and device of cloud server, storage medium and cloud server |
| CN109992412B (en) * | 2019-02-19 | 2021-08-10 | 广州视源电子科技股份有限公司 | Capacity adjusting method and device of cloud server, storage medium and cloud server |
| CN109885469A (en) * | 2019-02-27 | 2019-06-14 | 深信服科技股份有限公司 | A kind of expansion method, prediction model creation method, device, equipment and medium |
| CN109885469B (en) * | 2019-02-27 | 2022-09-30 | 深信服科技股份有限公司 | Capacity expansion method, prediction model creation method, device, equipment and medium |
| CN111865635B (en) * | 2019-04-29 | 2022-11-22 | 中国移动通信集团贵州有限公司 | Method and device for determining out-of-limit time of ring network capacity |
| CN111865635A (en) * | 2019-04-29 | 2020-10-30 | 中国移动通信集团贵州有限公司 | Method and device for determining out-of-limit time of ring network capacity |
| CN110247856B (en) * | 2019-05-24 | 2022-08-12 | 平安科技（深圳）有限公司 | Server resource release method and device |
| 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 |
| CN110389876A (en) * | 2019-06-18 | 2019-10-29 | 平安科技（深圳）有限公司 | Basic resource capacity monitoring and managing method, device, equipment and storage medium |
| CN110347502A (en) * | 2019-06-21 | 2019-10-18 | 无锡华云数据技术服务有限公司 | Load equilibration scheduling method, device and the electronic equipment of cloud host 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 |
| CN111416836A (en) * | 2020-02-13 | 2020-07-14 | 中国平安人寿保险股份有限公司 | Nginx-based server maintenance method and device, computer equipment and storage medium |
| CN111416836B (en) * | 2020-02-13 | 2023-08-22 | 中国平安人寿保险股份有限公司 | Nginx-based server maintenance method and device, computer equipment and storage medium |
| CN113407297B (en) * | 2020-03-17 | 2023-12-26 | 中国移动通信集团浙江有限公司 | Container management method and device and computing equipment |
| CN113407297A (en) * | 2020-03-17 | 2021-09-17 | 中国移动通信集团浙江有限公司 | Container management method and device and computing equipment |
| CN111427758A (en) * | 2020-03-17 | 2020-07-17 | 北京百度网讯科技有限公司 | Task calculation amount determining method and device and electronic equipment |
| CN112115036A (en) * | 2020-09-28 | 2020-12-22 | 中国银行股份有限公司 | Cluster capacity prediction method and device |
| CN112115036B (en) * | 2020-09-28 | 2024-09-17 | 中国银行股份有限公司 | Cluster capacity prediction method and device |
| CN112445613A (en) * | 2020-11-02 | 2021-03-05 | 浙江大华技术股份有限公司 | Elastic expansion and contraction method for stream processing platform, electronic equipment and storage medium |
| CN112540902B (en) * | 2020-12-03 | 2023-03-14 | 山东云海国创云计算装备产业创新中心有限公司 | Method, device and equipment for testing performance of system on chip and readable storage medium |
| CN112540902A (en) * | 2020-12-03 | 2021-03-23 | 山东云海国创云计算装备产业创新中心有限公司 | Method, device and equipment for testing performance of system on chip and readable storage medium |
| CN112685390A (en) * | 2021-03-22 | 2021-04-20 | 阿里云计算有限公司 | Database instance management method and device and computing equipment |
| CN113254209A (en) * | 2021-05-28 | 2021-08-13 | 北京奇艺世纪科技有限公司 | Capacity management method and device, electronic equipment and readable storage medium |
| CN113254209B (en) * | 2021-05-28 | 2023-08-29 | 北京奇艺世纪科技有限公司 | Capacity management method, device, electronic equipment and readable storage medium |
| CN113485838A (en) * | 2021-07-26 | 2021-10-08 | 北京沃东天骏信息技术有限公司 | Server distribution method and device, electronic equipment and computer readable storage medium |
| CN113360250A (en) * | 2021-08-09 | 2021-09-07 | 连连宝(杭州)信息技术有限公司 | Application service resource control method, device, equipment and medium |
| CN113722098A (en) * | 2021-08-30 | 2021-11-30 | 平安国际智慧城市科技股份有限公司 | Server capacity prediction method, device, equipment and medium based on artificial intelligence |
| 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 |
|---|---|---|
| CN107231264A (en) | For the method and apparatus for the capacity for managing Cloud Server | |
| CN106020715B (en) | Storage pool capacity management | |
| Mazzucco et al. | Optimizing cloud providers revenues via energy efficient server allocation | |
| CN106383766B (en) | System monitoring method and apparatus | |
| US10756981B2 (en) | Efficiency indexes | |
| CN108304250A (en) | Method and apparatus for the node for determining operation machine learning task | |
| CN105049218B (en) | PhiCloud clouds charging method and system | |
| CN107003887A (en) | Overloaded cpu setting and cloud computing workload schedules mechanism | |
| CN107515663A (en) | The method and apparatus for adjusting central processor core running frequency | |
| CN108549583A (en) | Big data processing method, device, server and readable storage medium storing program for executing | |
| CN107678803A (en) | Using management-control method, device, storage medium and electronic equipment | |
| CN108255607A (en) | Task processing method, device, electric terminal and readable storage medium storing program for executing | |
| CN110334059A (en) | Method and apparatus for handling file | |
| CN110618867A (en) | Method and device for predicting resource usage amount | |
| CN113485833B (en) | Resource prediction method and device | |
| CN103713852B (en) | A kind of information processing method, service platform and electronic equipment | |
| CN109688067A (en) | Based on income distribution method, server and the storage medium for sharing flow | |
| CN109117442A (en) | A kind of application recommended method and device | |
| CN111652282B (en) | Big data-based user preference analysis method and device and electronic equipment | |
| CN109345373A (en) | Check and write off method for prewarning risk, device, electronic equipment and computer-readable medium | |
| CN109684059A (en) | Method and device for monitoring data | |
| WO2019062404A1 (en) | Application program processing method and apparatus, storage medium, and electronic device | |
| CN107819745A (en) | The defence method and device of abnormal flow | |
| CN110471769A (en) | A kind of method for managing resource and device of virtual machine | |
| CN109102200A (en) | A kind of timed task processing method and processing 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171003 |