CN106230944A - The running gear that a kind of peak based on cloud computer system accesses - Google Patents
The running gear that a kind of peak based on cloud computer system accesses Download PDFInfo
- Publication number
- CN106230944A CN106230944A CN201610624978.4A CN201610624978A CN106230944A CN 106230944 A CN106230944 A CN 106230944A CN 201610624978 A CN201610624978 A CN 201610624978A CN 106230944 A CN106230944 A CN 106230944A
- Authority
- CN
- China
- Prior art keywords
- computer system
- cloud computer
- data
- virtual machine
- module
- 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
- 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
-
- 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
- H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
Abstract
The invention discloses the running gear that a kind of peak based on cloud computer system accesses.Including service register, for intercepting all of access request data in the porch of described cloud computer system, and the service data of the virtual machine of record activity；Machine learning predictor, for predicting described cloud computer system cloud computer system visit capacity in 0 24h according to described access request data；Load equalizer, for receiving the cloud computer system of the described machine learning predictor visit capacity in 0 24h more than a setting value, processes the target virtual machine of request and returns to porch and process.The present invention is by predicting the active load accessing peak, cloud computer system can be opened enough resources before peak has access to soothing the liver and be carried out load balancing, aggressive mode is transferred to from Passive Mode, break away from the situations such as the response lag of system generation, stability is not enough, be truly realized intellectuality and the automatization of scheduling of resource.
Description
Technical field
The invention belongs to computer access technique field, particularly relate to a kind of peak based on cloud computer system and access
Running gear.
Background technology
Cloud computing platform can be divided into 3 classes: is stored as main storage-type cloud platform with data, is processed as master's with data
The comprehensive cloud computing platform that calculation type cloud platform and calculating and data storage processing are taken into account.Modern computer is in social life
Play very important role, along with the development of information technology, increasing cluster application system is put in use, no
With needing to realize unified storage, resource-sharing between user, this proposes new requirement to data-storage system, and different user may
In the same time, same data are conducted interviews, seek and a kind of reading and writing data concurrency and network traffics are shared coordination
Mechanism, modern large-scale cluster is met multi-user, high concurrent requirements for access has important practical significance.
The core of website cloud scheduling is scheduling virtual machine device, and virtual machine manager is all passed through in the operation to various resources downwards
Realize, use unified management interface and data interchange format, main realize the state collection to resource, data statistics,
Monitoring etc., upwards provide all available data, Service Processing Unit carry out relevant treatment, and hand over web console
Mutually.It is said that in general, for the utilization rate improving virtual machine, virtual machine manager monitors all virtual machines being currently running in real time
State, and based on the request condition to the resource consumption maximum of the virtual machine of all activities, select to obtain the most most suitable place
The virtual machine of reason processes the access request of porch.But, although the scheduling strategy of the utilization rate of use raising virtual machine is permissible
Being effectively improved the utilization rate of virtual machine, but work as the peak of cloud computer system entrance during the visit, this strategy is just difficult in time should
Answer the access request of terminal 10, the state of " paralysis " occurs.
Summary of the invention
It is an object of the invention to provide the running gear that a kind of peak based on cloud computer system accesses, by visit
Asking the active load prediction on peak, cloud computer system can be opened enough resources before peak has access to soothing the liver and be loaded
Equilibrium, transfers aggressive mode to from Passive Mode, has broken away from the situations such as the response lag of system generation, stability is not enough.
For solving above-mentioned technical problem, the present invention is achieved by the following technical solutions:
The present invention is the running gear that a kind of peak based on cloud computer system accesses, and including service register, is used for
All of access request data, and the operation number of the virtual machine of record activity is intercepted in the porch of described cloud computer system
According to；
Machine learning predictor, for according to described access request data prediction described cloud computer system cloud computer system
System visit capacity in 0-24h；
Load equalizer, for receiving the visit in 0-24h of the cloud computer system of described machine learning predictor
After the amount of asking is more than a setting value, send the instruction of establishment virtual machine and the service data of the virtual machine instance according to described activity
The virtual machine instance selecting resource occupation minimum returns to porch as the target virtual machine processing request and processes.
Preferably, described machine learning predictor uses K-closest node algorithm according to the prediction of described forecast sample
The visit capacity of the future position on the horizon of cloud computer system.
Preferably, described machine learning predictor includes with lower module:
First module, for choosing the access request data that the time point in the 0-60s in several sampling periods is corresponding
As increment judge Data-Link (Q1, Q2, Q3 ..., Q60)；
Second module, for increment judged Data-Link (Q1, Q2, Q3 ..., Q60) adjacent two data carry out residual quantity
Computing, obtains P1, P2, P3 ..., the gradient increment of P30；
According to gradient increment as weights corresponding to data；
Computing module, for carrying out the prediction of cloud computer system to the judgment value of the first module and the second module.
Preferably, described first module, for choosing the visit that the time point in the 0-60s in several sampling periods is corresponding
Ask request data as increment judge Data-Link (Q1, Q2, Q3 ..., Q60) in cycle be 0-24 hour, in units of 1s
Time, the access request data value in 0-60s is Q1, Q2, Q3 ..., Q60.
The method have the advantages that
The present invention is by predicting the active load accessing peak, and cloud computer system can be before peak has access to soothing the liver
Open enough resources and carry out load balancing, transfer aggressive mode to from Passive Mode, response lag that system of having broken away from produces, steady
The situations such as qualitative deficiency, are truly realized intellectuality and the automatization of scheduling of resource.
Certainly, the arbitrary product implementing the present invention it is not absolutely required to reach all the above advantage simultaneously.
Accompanying drawing explanation
In order to be illustrated more clearly that the technical scheme of the embodiment of the present invention, embodiment will be described required use below
Accompanying drawing is briefly described, it should be apparent that, the accompanying drawing in describing below is only some embodiments of the present invention, for ability
From the point of view of the those of ordinary skill of territory, on the premise of not paying creative work, it is also possible to obtain the attached of other according to these accompanying drawings
Figure.
Fig. 1 is the running gear structural representation of a kind of based on cloud computer system the peak access of the present invention.
Detailed description of the invention
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Describe, it is clear that described embodiment is only a part of embodiment of the present invention rather than whole embodiments wholely.Based on
Embodiment in the present invention, those of ordinary skill in the art obtained under not making creative work premise all other
Embodiment, broadly falls into the scope of protection of the invention.
Referring to shown in Fig. 1, the present invention is the running gear that a kind of peak based on cloud computer system accesses, including fortune
Row recorder, for intercepting all of access request data, and the void that record is movable in the porch of described cloud computer system
The service data of plan machine；
Machine learning predictor, for according to described access request data prediction described cloud computer system cloud computer system
System visit capacity in 0-24h；
Load equalizer, for receiving the visit in 0-24h of the cloud computer system of described machine learning predictor
After the amount of asking is more than a setting value, send the instruction of establishment virtual machine and the service data of the virtual machine instance according to described activity
The virtual machine instance selecting resource occupation minimum returns to porch as the target virtual machine processing request and processes.
Wherein, machine learning predictor uses K-closest node algorithm to predict described cloud computing according to described forecast sample
The visit capacity of the future position on the horizon of machine system.
Wherein, machine learning predictor includes with lower module:
First module, for choosing the access request data that the time point in the 0-60s in several sampling periods is corresponding
As increment judge Data-Link (Q1, Q2, Q3 ..., Q60)；
Second module, for increment judged Data-Link (Q1, Q2, Q3 ..., Q60) adjacent two data carry out residual quantity
Computing, obtains P1, P2, P3 ..., the gradient increment of P30；
According to gradient increment as weights corresponding to data；
Computing module, for carrying out the prediction of cloud computer system to the judgment value of the first module and the second module.
Wherein, the first module, for choosing the access request that the time point in the 0-60s in several sampling periods is corresponding
Data as increment judge Data-Link (Q1, Q2, Q3 ..., Q60) in cycle be 0-24 hour, with 1s for the unit time,
Access request data value in 0-60s is Q1, Q2, Q3 ..., Q60.
It should be noted that in said system embodiment, included unit simply carries out drawing according to function logic
Point, but it is not limited to above-mentioned division, as long as being capable of corresponding function；It addition, each functional unit is concrete
Title also only to facilitate mutually distinguish, is not limited to protection scope of the present invention.
It addition, one of ordinary skill in the art will appreciate that all or part of step realizing in the various embodiments described above method
The program that can be by completes to instruct relevant hardware, and corresponding program can be stored in an embodied on computer readable storage and be situated between
In matter, described storage medium, such as ROM/RAM, disk or CD etc..
Present invention disclosed above preferred embodiment is only intended to help to illustrate the present invention.Preferred embodiment is the most detailed
Describe all of details, be also not intended to the detailed description of the invention that this invention is only described.Obviously, according to the content of this specification,
Can make many modifications and variations.These embodiments are chosen and specifically described to this specification, is to preferably explain the present invention
Principle and actual application so that skilled artisan can be best understood by and utilize the present invention.The present invention is only
Limited by claims and four corner thereof and equivalent.
Claims (4)
1. the running gear that a peak based on cloud computer system accesses, it is characterised in that including:
Service register, for intercepting all of access request data in the porch of described cloud computer system, and records work
The service data of dynamic virtual machine；
According to described access request data, machine learning predictor, for predicting that described cloud computer system cloud computer system exists
Visit capacity in 0-24h；
Load equalizer, for receiving the cloud computer system of the described machine learning predictor visit capacity in 0-24h
After a setting value, send and create the instruction of virtual machine and select according to the service data of the virtual machine instance of described activity
The minimum virtual machine instance of resource occupation returns to porch as the target virtual machine processing request and processes.
The running gear that a kind of peak based on cloud computer system the most according to claim 1 accesses, it is characterised in that
Described machine learning predictor uses K-closest node algorithm to predict described cloud computer system according to described forecast sample
The visit capacity of future position on the horizon.
The running gear that a kind of peak based on cloud computer system the most according to claim 1 accesses, it is characterised in that
Described machine learning predictor includes with lower module:
First module, for choosing the access request data conduct that the time point in the 0-60s in several sampling periods is corresponding
Increment judge Data-Link (Q1, Q2, Q3 ..., Q60)；
Second module, for increment judged Data-Link (Q1, Q2, Q3 ..., Q60) adjacent two data carry out residual quantity computing,
Obtain P1, P2, P3 ..., the gradient increment of P30；
According to gradient increment as weights corresponding to data；
Computing module, for carrying out the prediction of cloud computer system to the judgment value of the first module and the second module.
The running gear that a kind of peak based on cloud computer system the most according to claim 3 accesses, it is characterised in that
Described first module, for choosing the access request data conduct that the time point in the 0-60s in several sampling periods is corresponding
Increment judge Data-Link (Q1, Q2, Q3 ..., Q60) in cycle be 0-24 hour, with 1s for the unit time, in 0-60s
Access request data value be Q1, Q2, Q3 ..., Q60.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610624978.4A CN106230944A (en) | 2016-08-02 | 2016-08-02 | The running gear that a kind of peak based on cloud computer system accesses |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610624978.4A CN106230944A (en) | 2016-08-02 | 2016-08-02 | The running gear that a kind of peak based on cloud computer system accesses |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106230944A true CN106230944A (en) | 2016-12-14 |
Family
ID=57534887
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610624978.4A Pending CN106230944A (en) | 2016-08-02 | 2016-08-02 | The running gear that a kind of peak based on cloud computer system accesses |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106230944A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107247617A (en) * | 2017-05-17 | 2017-10-13 | 努比亚技术有限公司 | The concocting method of resources of virtual machine, platform on probation and readable storage medium storing program for executing |
| CN107451041A (en) * | 2017-07-24 | 2017-12-08 | 华中科技大学 | A kind of object cloud storage system response delay Forecasting Methodology |
| CN108880945A (en) * | 2018-08-02 | 2018-11-23 | 浙江口碑网络技术有限公司 | A kind of cloud monitoring system and method |
| CN110493643A (en) * | 2019-08-06 | 2019-11-22 | 北京邮电大学 | Video storage method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103152389A (en) * | 2013-02-01 | 2013-06-12 | 华南师范大学 | Method and system of responding peak access in cloud computer system |
| CN103327118A (en) * | 2013-07-09 | 2013-09-25 | 南京大学 | Intelligent virtual machine cluster scaling method and system for web application in cloud computing |
| CN105373432A (en) * | 2015-11-06 | 2016-03-02 | 北京系统工程研究所 | Cloud computing resource scheduling method based on virtual resource state prediction |
| CN105511953A (en) * | 2014-09-22 | 2016-04-20 | 中国银联股份有限公司 | System and method for evaluating load of virtual machine under cloud environment, and service node |
-
2016
- 2016-08-02 CN CN201610624978.4A patent/CN106230944A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103152389A (en) * | 2013-02-01 | 2013-06-12 | 华南师范大学 | Method and system of responding peak access in cloud computer system |
| CN103327118A (en) * | 2013-07-09 | 2013-09-25 | 南京大学 | Intelligent virtual machine cluster scaling method and system for web application in cloud computing |
| CN105511953A (en) * | 2014-09-22 | 2016-04-20 | 中国银联股份有限公司 | System and method for evaluating load of virtual machine under cloud environment, and service node |
| CN105373432A (en) * | 2015-11-06 | 2016-03-02 | 北京系统工程研究所 | Cloud computing resource scheduling method based on virtual resource state prediction |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107247617A (en) * | 2017-05-17 | 2017-10-13 | 努比亚技术有限公司 | The concocting method of resources of virtual machine, platform on probation and readable storage medium storing program for executing |
| CN107247617B (en) * | 2017-05-17 | 2020-11-24 | 北京神州数码云科信息技术有限公司 | Virtual machine resource allocation method, trial platform and readable storage medium |
| CN107451041A (en) * | 2017-07-24 | 2017-12-08 | 华中科技大学 | A kind of object cloud storage system response delay Forecasting Methodology |
| CN107451041B (en) * | 2017-07-24 | 2019-11-22 | 华中科技大学 | A kind of object cloud storage system response delay prediction technique |
| CN108880945A (en) * | 2018-08-02 | 2018-11-23 | 浙江口碑网络技术有限公司 | A kind of cloud monitoring system and method |
| CN110493643A (en) * | 2019-08-06 | 2019-11-22 | 北京邮电大学 | Video storage method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106230944A (en) | The running gear that a kind of peak based on cloud computer system accesses | |
| CN108183947A (en) | Distributed caching method and system | |
| CN103399781B (en) | Cloud Server and virtual machine management method thereof | |
| CN105187512A (en) | Method and system for load balancing of virtual machine clusters | |
| CN109684074A (en) | Physical machine resource allocation methods and terminal device | |
| CN102938790A (en) | Resource allocation method of cloud computing system | |
| CN107070709B (en) | NFV (network function virtualization) implementation method based on bottom NUMA (non uniform memory Access) perception | |
| CN111198918B (en) | Data processing system based on big data platform and link optimization method | |
| CN102929769A (en) | Virtual machine internal-data acquisition method based on agency service | |
| Yin et al. | Real-time task processing method based on edge computing for spinning CPS | |
| CN104657435A (en) | Storage management method for application data and network management system | |
| CN107623732A (en) | A kind of date storage method based on cloud platform, device, equipment and storage medium | |
| CN106302628A (en) | ARM architecture network cluster calculates the unified management dispatching method of resource | |
| CN106021544B (en) | Database distributed connection pool management method and system | |
| CN110704851A (en) | Public cloud data processing method and device | |
| CN108306912A (en) | Virtual network function management method and its device, network function virtualization system | |
| CN106302634A (en) | A kind of data migration method and system | |
| CN106027685A (en) | Peak access method based on cloud computation system | |
| US20230155958A1 (en) | Method for optimal resource selection based on available gpu resource analysis in large-scale container platform | |
| Zeng et al. | Workload-aware resource reservation for multi-tenant nosql | |
| CN110347502A (en) | Load equilibration scheduling method, device and the electronic equipment of cloud host server | |
| US11941450B2 (en) | Automatic placement decisions for running incoming workloads on a datacenter infrastructure | |
| Lin et al. | A workload-driven approach to dynamic data balancing in MongoDB | |
| CN107402812A (en) | Cluster resource dispatching method, device, equipment and storage medium | |
| CN108228311A (en) | A kind of method across storage pool migration virtual machine |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161214 |
|
| RJ01 | Rejection of invention patent application after publication |