CN109002359A - A kind of dispatching method and relevant apparatus of calculate node server - Google Patents
A kind of dispatching method and relevant apparatus of calculate node server Download PDFInfo
- Publication number
- CN109002359A CN109002359A CN201811019799.3A CN201811019799A CN109002359A CN 109002359 A CN109002359 A CN 109002359A CN 201811019799 A CN201811019799 A CN 201811019799A CN 109002359 A CN109002359 A CN 109002359A
- Authority
- CN
- China
- Prior art keywords
- server
- calculate node
- performance index
- performance
- node server
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
- G06F2009/4557—Distribution of virtual machine instances; Migration and load balancing
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Debugging And Monitoring (AREA)
Abstract
This application discloses a kind of dispatching methods of calculate node server, comprising: the performance index of multiple components in each calculate node server is determined according to performance index table；Server performance calculation processing is carried out to the corresponding all properties index of each calculate node server and obtains corresponding server performance index；The grade label of corresponding calculate node server is determined according to Servers-all performance index；When creating virtual machine, virtual machine is operated in corresponding calculate node server according to the goal gradient label received.Server performance index is calculated by the performance index of multiple components in the calculate node server, so as to be scheduled according to host of the performance of calculate node server to virtual machine, the utilization rate of server performance is improved, and then improves the computational efficiency of cloud computing platform.Disclosed herein as well is scheduling system, server and the computer readable storage mediums of a kind of calculate node server, have the above beneficial effect.
Description
Technical field
This application involves field of cloud computer technology, in particular to a kind of dispatching method of calculate node server, scheduling system
System, server and computer readable storage medium.
Background technique
With the continuous development of information technology, there are various cloud platform computing techniques.It is usually used in cloud platform
OpenStack is managed the platform project in cloud computing platform.Specifically, what is created in openstack system is virtual
Equipment running body is the scheduler module by nova component according to set tactful Automatic dispatching in which calculate node server
, the host that the more sufficient calculate node of resource is run as virtual machine in priority scheduling cluster.
But the performance of the calculate node server sometimes in cluster is different, some server performances are relatively good,
Computing capability is strong, some server performances are poor, and computing capability is weaker, if according to the Automatic dispatching plan of scheduler
It slightly, will not be using the performance of server as Scheduling factors, only using resource residual amount as regulation index, the more clothes of surplus resources
Business device, it is bigger to be selected a possibility that creating virtual machine.The problem of bringing in this way is to waste high-performance server, is reduced
The utilization rate of server performance, also affects training effectiveness.
Therefore, how when distributing calculate node server, the utilization rate for improving calculate node server is this field skill
The Important Problems of art personnel concern.
Summary of the invention
The purpose of the application is to provide dispatching method, scheduling system, server and the meter of a kind of calculate node server
Calculation machine readable storage medium storing program for executing calculates server by searching for the performance index of multiple components in the calculate node server
Energy index, and then the calculate node server run according to the corresponding grade label selection virtual machine of server performance index, with
The host of virtual machine can be scheduled according to the performance of calculate node server, improve the utilization of server performance
Rate, and then improve the computational efficiency of cloud computing platform.
In order to solve the above technical problems, the application provides a kind of dispatching method of calculate node server, comprising:
The performance index of multiple components in each calculate node server is determined according to performance index table；
Server performance calculation processing is carried out to the corresponding all properties index of each calculate node server to obtain
Corresponding server performance index；
The grade label of corresponding calculate node server is determined according to all server performance indexes；
When creating virtual machine, the virtual machine is operated in by corresponding calculating according to the goal gradient label received and is saved
In point server.
Optionally, the performance index of multiple components in each calculate node server is determined according to performance index table, comprising:
Obtain CPU model, memory model and the disk model in each calculate node server；
According to the CPU model, the memory model and the disk model of each calculate node server
Corresponding cpu performance index, internal memory performance index and disk performance index are found out in the performance index table.
Optionally, the corresponding all properties index of each calculate node server is carried out at server performance calculating
Reason obtains corresponding server performance index, comprising:
By the corresponding each performance index of each calculate node server and the corresponding factor accounting phase of performance index
Multiply, obtains the corresponding multiple coefficients of performance of each calculate node server；
It is added the corresponding all properties coefficient of each calculate node server to obtain the server performance index.
Optionally, when creating virtual machine, the virtual machine is operated in by correspondence according to the goal gradient label received
Calculate node server in, comprising:
When creating virtual machine, corresponding target computing nodes service is gone out according to the goal gradient label lookup received
Device；
When the quantity of the target computing nodes server is 1, the virtual machine is operated in into the target and calculates section
In point server；
When the quantity of the target computing nodes server is greater than 1, the virtual machine is operated in into remaining performance resource
In maximum target computing nodes server.
The application also provides a kind of scheduling system of calculate node server, comprising:
Assembly property index obtains module, for determining in each calculate node server multiple groups according to performance index table
The performance index of part；
Server performance index obtains module, for the corresponding all properties index of each calculate node server
It carries out server performance calculation processing and obtains corresponding server performance index；
Grade label obtains module, for determining corresponding calculate node server according to all server performance indexes
Grade label；
Virtual machine matching module is used for when creating virtual machine, will be described virtual according to the goal gradient label received
Machine operates in corresponding calculate node server.
Optionally, the assembly property index obtains module, comprising:
Model acquiring unit, for obtaining CPU model, memory model and magnetic in each calculate node server
Dish-type number；
Performance index acquiring unit, for the CPU model according to each calculate node server, the memory
Model and the disk model found out in the performance index table corresponding cpu performance index, internal memory performance index with
And disk performance index.
Optionally, the server performance index obtains module, comprising:
Coefficient of performance acquiring unit, for by the corresponding each performance index of each calculate node server and performance
The corresponding factor accounting of index is multiplied, and obtains the corresponding multiple coefficients of performance of each calculate node server；
Coefficient addition unit, for being added the corresponding all properties coefficient of each calculate node server to obtain the clothes
Business device performance index.
Optionally, the virtual machine matching module, comprising:
Destination server searching unit, for being gone out according to the goal gradient label lookup received when creating virtual machine
Corresponding target computing nodes server；
First matching unit, for when the quantity of the target computing nodes server is 1, the virtual machine to be run
In the target computing nodes server；
Second matching unit, for when the quantity of the target computing nodes server is greater than 1, the virtual machine to be transported
Row is in the maximum target computing nodes server of remaining performance resource.
The application also provides a kind of server, comprising:
Memory, for storing computer program；
Processor, the step of dispatching method as described above is realized when for executing the computer program.
The application also provides a kind of computer readable storage medium, and calculating is stored on the computer readable storage medium
Machine program, it is the step of realizing dispatching method as described above that the computer program, which is executed by processor,.
The dispatching method of a kind of calculate node server provided herein, comprising: determined according to performance index table every
The performance index of multiple components in a calculate node server；The corresponding all properties of each calculate node server are referred to
Number carries out server performance calculation processing and obtains corresponding server performance index；It is true according to all server performance indexes
Surely the grade label of calculate node server is corresponded to；It, will be described according to the goal gradient label received when creating virtual machine
Virtual machine operates in corresponding calculate node server.
By searching for the performance index of multiple components in the calculate node server, server performance index is calculated, into
And according to the calculate node server of the corresponding grade label selection virtual machine operation of server performance index, so as to basis
The performance of calculate node server is scheduled the host of virtual machine, improves the utilization rate of server performance, Jin Erti
The high computational efficiency of cloud computing platform.
The application also provides scheduling system, server and the computer-readable storage medium of a kind of calculate node server
Matter has the above beneficial effect, and this will not be repeated here.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The embodiment of application for those of ordinary skill in the art without creative efforts, can also basis
The attached drawing of offer obtains other attached drawings.
Fig. 1 is a kind of flow chart of the dispatching method of calculate node server provided by the embodiment of the present application；
Fig. 2 is the flow chart of the virtual machine matching process in dispatching method provided by the embodiment of the present application；
Fig. 3 is a kind of structural schematic diagram of the scheduling system of calculate node server provided by the embodiment of the present application.
Specific embodiment
The core of the application is to provide dispatching method, scheduling system, server and the meter of a kind of calculate node server
Calculation machine readable storage medium storing program for executing calculates server by searching for the performance index of multiple components in the calculate node server
Energy index, and then the calculate node server run according to the corresponding grade label selection virtual machine of server performance index, with
The host of virtual machine can be scheduled according to the performance of calculate node server, improve the utilization of server performance
Rate, and then improve the computational efficiency of cloud computing platform.
To keep the purposes, technical schemes and advantages of the embodiment of the present application clearer, below in conjunction with the embodiment of the present application
In attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is
Some embodiments of the present application, instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall in the protection scope of this application.
In the prior art, the virtual machine carrying out practically created in openstack system is in which calculate node server
It is the scheduler module by nova component according to set tactful Automatic dispatching.Current scheduling strategy is priority scheduling collection
The host that the more sufficient calculate node of resource is run as virtual machine in group.
But the performance of the calculate node server sometimes in cluster is different, some server performances are relatively good,
Computing capability is strong, some server performances are poor, and computing capability is weaker, if according to the Automatic dispatching plan of scheduler
It slightly, will not be using the performance of server as Scheduling factors, only using resource residual amount as regulation index, the more clothes of surplus resources
Business device, it is bigger to be selected a possibility that creating virtual machine.The problem of bringing in this way is to waste high-performance server, is reduced
The utilization rate of server performance, also affects training effectiveness.
Therefore, the present embodiment provides a kind of dispatching methods of calculate node server, by searching for the calculate node service
The performance index of multiple components in device calculates server performance index, and then according to the corresponding grade of server performance index
Label select virtual machine operation calculate node server, so as to according to the performance of calculate node server to virtual machine
Host is scheduled, and improves the utilization rate of server performance, and then improves the computational efficiency of cloud computing platform.
Specifically, referring to FIG. 1, Fig. 1 is a kind of dispatching party of calculate node server provided by the embodiment of the present application
The flow chart of method.
This method may include:
S101 determines the performance index of multiple components in each calculate node server according to performance index table；
This step is intended to the performance that passage capacity index table determines preset multiple components in each calculate node server
Index.
Wherein, performance index table is to be used to record the corresponding performance of different model component in cluster platform management system to refer to
Several tables, the more good corresponding performance index of the performance of component are higher.For example, at four core of CPU model Intel Core i7 of server
Device is managed, then its corresponding performance index in performance index table is 5；So four core of Intel Core i5 handles corresponding performance index
As 4.And so on, the property of different model cpu package is determined according to the performance measuring and evaluating data in the market to the CPU of different model
It can index.
There can be several components in general server, some components are affected for the performance of server entirety, and have
The variation of a little components can be ignored the influence of the performance of server entirety, therefore, the multiple components obtained in this step
Performance index can be the performance index of the key component in server, such as CPU, memory and disk, can obtain most
Most accurate performance index is determined in the case where small number performance index.
Optionally, this step may include:
Step 1: obtaining the CPU model in each calculate node server, memory model and disk model；
Step 2: according to the CPU model, memory model and disk model of each calculate node server in performance index
Corresponding cpu performance index, internal memory performance index and disk performance index are found out in table.
This optinal plan mainly illustrates a kind of specific implementation of S101, mainly determines clothes in this optinal plan
The performance index of CPU, memory and disk in business device.For each calculate node server determined multiple groups include CPU, it is interior
It deposits, the performance index of disk.
S102 carries out server performance calculation processing to the corresponding all properties index of each calculate node server and obtains
Corresponding server performance index；
On the basis of step S101, this step be intended to the corresponding all properties index of each calculate node server into
Row server performance calculation processing obtains the corresponding server performance index of each calculate node server.It is namely corresponding every
According to the performance index that it is determined for a calculate node server, the performance index that the server is calculated is carried out.
Wherein, the server performance calculation processing carried out, which can be, to be added all properties index to obtain server performance
Index, for example, the cpu performance index got is 4, internal memory performance index is 5, and disk performance index is 3, then server
Energy index is exactly the sum that the above three is added, and is exactly 12, then server performance index is 12.It is also possible to the calculate node
The average of all properties index of server, for example, cpu performance index is 4, internal memory performance index is 5, disk performance index
It is 3, the average of three is 4, then the server performance index of the calculate node server is 4.It can also be according to every
The calculated server performance index of the factor accounting that a performance exponent pair is answered, for example, cpu performance index is 4, corresponding factor
Accounting is 40%；Internal memory performance index is 5, and corresponding factor accounting is 40%；Disk performance index is 3, and corresponding factor accounts for
It is 3.8 according to the calculated result of factor accounting, then the server performance index of the calculate node server is than being 20%
It is 3.8.Therefore, the mode that server performance index is calculated in this step is not unique, it is not limited here.
Optionally, this step may include:
Step 1: by the corresponding each performance index of each calculate node server and the corresponding factor accounting of performance index
It is multiplied, obtains the corresponding multiple coefficients of performance of each calculate node server；
Step 2: being added the corresponding all properties coefficient of each calculate node server to obtain server performance index.
This optinal plan is exactly to calculate server performance according to the corresponding factor accounting of each performance index in S102 to refer to
A kind of several concrete modes.Since the influence between the performance index of multiple components of acquisition for server performance is in the presence of poor
It is different, therefore, it is necessary to reconcile the difference between multiple performance indexs in calculation server performance index, improves server performance and refer to
Several accuracys.
Specifically, since server performance generally depends primarily on CPU and memory in this optinal plan, CPU and interior
It deposits corresponding factor accounting and is set as 40%, and disk takes second place, and sets 20% for its factor accounting.
Therefore, according to the optinal plan, the formula of calculation server performance index be can be such that
Server performance index=cpu performance index * 40%+ internal memory performance index * 40%+ disk performance index * 20%
Pass through the available more accurate server performance index of the formula.
S103 determines the grade label of corresponding calculate node server according to Servers-all performance index；
On the basis of step S102, this step is intended to determine each calculating according to obtained Servers-all performance index
The corresponding grade label of node server.
Multiple grades label can be set in this step, can be specifically arranged not according to the management granularity difference to label
With the grade label of quantity.For example, the grade label of 3 grades can be set, be upper, middle and lower respectively when management granularity is larger；
When management granularity is smaller, greater number of grade is set, can be the grade label of 6 quantity, is grade one, grade respectively
Two, grade three, grade four, grade five, grade six, from big to small, grade is first is that indicate the maximum grade label of performance for performance.Cause
This, the mode that grade label is arranged in this step is not unique, is not specifically limited herein.
Further, on the basis of being equipped with multiple grades label, each calculate node server is corresponding according to its
The corresponding grade label of server performance index-matched.For example, 5 grade labels, at this time server performance index can be equipped with
It is up to 5, then can have the range of 5 server performance indexes: 5 to 4,4 to 3,3 to 2,2 to 1,1 to 0, it respectively corresponds
5 grade labels.The range that each server performance index is fallen into is judged, using the corresponding grade label of the range as the calculating
The corresponding grade label of node server.
It should be noted that the numerical value of the server performance index used in this step is different, grade label is determined
Mode also can be different, it is therefore desirable to which corresponding method of determination determines according to actual conditions is not specifically limited herein.
Virtual machine is operated in corresponding calculating according to the goal gradient label received when creating virtual machine by S104
In node server.
On the basis of step S103, this step is intended to the calculate node service when creation virtual machine selection virtual machine operation
When device, virtual machine is operated in by the corresponding calculate node server of goal gradient label according to the goal gradient label received
In.
More specifically, this step is when creating virtual machine, can be according to the goal gradient label received from all calculating
Calculate node server corresponding with the goal gradient label is selected in node server, and the virtual machine is then operated in into calculating
In node server.
Optionally, the method in the present embodiment can also rely on different cloud computings to manage platform and be run, such as will
The method of the present embodiment operates in openstack system, can be convenient and implements the present embodiment, and improves this implementation
The maintainability of example.
To sum up, the present embodiment calculates service by searching for the performance index of multiple components in the calculate node server
Device performance index, and then according to the calculate node service of the corresponding grade label selection virtual machine operation of server performance index
Device improves server performance so as to be scheduled according to host of the performance of calculate node server to virtual machine
Utilization rate, and then improve the computational efficiency of cloud computing platform.
On the basis of a upper embodiment, the present embodiment is intended to how to operate in virtual machine pair in a upper embodiment
It does one in the calculate node server answered to illustrate, other parts are substantially the same with a upper embodiment, and same section can be with
With reference to a upper embodiment, this will not be repeated here.
Referring to FIG. 2, Fig. 2 is the process of the virtual machine matching process in dispatching method provided by the embodiment of the present application
Figure.
This method may include:
S201 goes out corresponding target computing nodes according to the goal gradient label lookup received when creating virtual machine
Server；
The present embodiment is intended to go out corresponding destination node server according to goal gradient label lookup.Institute in the present embodiment
The quantity of the target computing nodes server found out is possible to only one, it is also possible to be multiple, and general virtual machine
It only operates in a calculate node server, when there are multiple destination node servers, then needs in multiple calculate nodes
It carries out selecting one in server, runs the virtual machine.
Virtual machine is operated in target computing nodes server when the quantity of target computing nodes server is 1 by S202
In；
This step is intended to virtual machine directly can be operated in the mesh when the quantity of target computing nodes server is 1
It marks in node server.
It is maximum to be operated in remaining performance resource when the quantity of target computing nodes server is greater than 1 by S203 for virtual machine
Target computing nodes server in.
This step is intended to when the quantity of target computing nodes server is greater than 1, that is, is calculated and saved there are multiple targets
Point server at this time operates in virtual machine in the maximum target computing nodes server of remaining performance resource, by calculate node
The utilization rate of server operation maximizes.
The embodiment of the present application provides a kind of dispatching method of calculate node server, by searching for the calculate node service
The performance index of multiple components in device calculates server performance index, and then according to the corresponding grade of server performance index
Label select virtual machine operation calculate node server, so as to according to the performance of calculate node server to virtual machine
Host is scheduled, and improves the utilization rate of server performance, and then improves the computational efficiency of cloud computing platform.
A kind of scheduling system of calculate node server provided by the embodiments of the present application is introduced below, is described below
The scheduling system of calculate node server a kind of can be mutual with a kind of above-described dispatching method of calculate node server
To should refer to.
Specifically, referring to FIG. 3, Fig. 3 is a kind of scheduling system of calculate node server provided by the embodiment of the present application
The structural schematic diagram of system.
The system may include:
Assembly property index obtains module 100, more in each calculate node server for being determined according to performance index table
The performance index of a component；
Server performance index obtains module 200, for the corresponding all properties index of each calculate node server
It carries out server performance calculation processing and obtains corresponding server performance index；
Grade label obtains module 300, for determining corresponding calculate node server according to Servers-all performance index
Grade label；
Virtual machine matching module 400, for when creating virtual machine, according to the goal gradient label received by virtual machine
It operates in corresponding calculate node server.
Optionally, which obtains module 100, may include:
Model acquiring unit, for obtaining CPU model, memory model and magnetic disc type in each calculate node server
Number；
Performance index acquiring unit, for the CPU model, memory model and disk according to each calculate node server
Model finds out corresponding cpu performance index, internal memory performance index and disk performance index in performance index table.
Optionally, which obtains module 200, may include:
Coefficient of performance acquiring unit is used for the corresponding each performance index of each calculate node server and performance index
Corresponding factor accounting is multiplied, and obtains the corresponding multiple coefficients of performance of each calculate node server；
Coefficient addition unit, for being added the corresponding all properties coefficient of each calculate node server to obtain server
Performance index.
Optionally, the virtual machine matching module 400 may include:
Destination server searching unit, for being gone out according to the goal gradient label lookup received when creating virtual machine
Corresponding target computing nodes server；
First matching unit, for when the quantity of target computing nodes server is 1, virtual machine to be operated in target meter
In operator node server；
Second matching unit, for when the quantity of target computing nodes server is greater than 1, virtual machine to be operated in residue
In the maximum target computing nodes server of performance resource.
The embodiment of the present application also provides a kind of server, comprising:
Memory, for storing computer program；
Processor, the step of dispatching method as described above in Example is realized when for executing the computer program.
The embodiment of the present application also provides a kind of computer readable storage medium, stores on the computer readable storage medium
There is computer program, it is the step for realizing dispatching method as described above in Example that the computer program, which is executed by processor,
Suddenly.
The computer readable storage medium may include: USB flash disk, mobile hard disk, read-only memory (Read-Only
Memory, ROM), random access memory (Random Access Memory, RAM), magnetic or disk etc. is various to deposit
Store up the medium of program code.
Each embodiment is described in a progressive manner in specification, the highlights of each of the examples are with other realities
The difference of example is applied, the same or similar parts in each embodiment may refer to each other.For device disclosed in embodiment
Speech, since it is corresponded to the methods disclosed in the examples, so being described relatively simple, related place is referring to method part illustration
?.
Professional further appreciates that, unit described in conjunction with the examples disclosed in the embodiments of the present disclosure
And algorithm steps, can be realized with electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate hardware and
The interchangeability of software generally describes each exemplary composition and step according to function in the above description.These
Function is implemented in hardware or software actually, the specific application and design constraint depending on technical solution.Profession
Technical staff can use different methods to achieve the described function each specific application, but this realization is not answered
Think beyond scope of the present application.
The step of method described in conjunction with the examples disclosed in this document or algorithm, can directly be held with hardware, processor
The combination of capable software module or the two is implemented.Software module can be placed in random access memory (RAM), memory, read-only deposit
Reservoir (ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technology
In any other form of storage medium well known in field.
Above to a kind of dispatching method of calculate node server provided herein, scheduling system, server and
Computer readable storage medium is described in detail.Principle and embodiment of the specific case to the application used herein
It is expounded, the description of the example is only used to help understand the method for the present application and its core ideas.It should be pointed out that
For those skilled in the art, under the premise of not departing from the application principle, can also to the application into
Row some improvements and modifications, these improvement and modification are also fallen into the protection scope of the claim of this application.
Claims (10)
1. a kind of dispatching method of calculate node server characterized by comprising
The performance index of multiple components in each calculate node server is determined according to performance index table；
Server performance calculation processing is carried out to the corresponding all properties index of each calculate node server to be corresponded to
Server performance index；
The grade label of corresponding calculate node server is determined according to all server performance indexes；
When creating virtual machine, the virtual machine is operated in by corresponding calculate node according to the goal gradient label received and is taken
It is engaged in device.
2. dispatching method according to claim 1, which is characterized in that determine that each calculate node takes according to performance index table
The performance index of multiple components in business device, comprising:
Obtain CPU model, memory model and the disk model in each calculate node server；
According to the CPU model, the memory model and the disk model of each calculate node server in institute
It states and finds out corresponding cpu performance index, internal memory performance index and disk performance index in performance index table.
3. dispatching method according to claim 1, which is characterized in that institute corresponding to each calculate node server
There is performance index to carry out server performance calculation processing and obtain corresponding server performance index, comprising:
The corresponding each performance index of each calculate node server factor accounting corresponding with performance index is multiplied, is obtained
To the corresponding multiple coefficients of performance of each calculate node server；
It is added the corresponding all properties coefficient of each calculate node server to obtain the server performance index.
4. dispatching method according to claim 1, which is characterized in that when creating virtual machine, according to the target received
Grade label operates in the virtual machine in corresponding calculate node server, comprising:
When creating virtual machine, corresponding target computing nodes server is gone out according to the goal gradient label lookup received；
When the quantity of the target computing nodes server is 1, the virtual machine is operated in into the target computing nodes and is taken
It is engaged in device；
When the quantity of the target computing nodes server is greater than 1, it is maximum that the virtual machine is operated in into remaining performance resource
Target computing nodes server in.
5. a kind of scheduling system of calculate node server characterized by comprising
Assembly property index obtains module, for determining multiple components in each calculate node server according to performance index table
Performance index；
Server performance index obtains module, for carrying out to the corresponding all properties index of each calculate node server
Server performance calculation processing obtains corresponding server performance index；
Grade label obtains module, for according to all server performance indexes determine corresponding calculate node servers etc.
Grade label；
Virtual machine matching module, for being transported the virtual machine according to the goal gradient label received when creating virtual machine
Row is in corresponding calculate node server.
6. scheduling system according to claim 1, which is characterized in that the assembly property index obtains module, comprising:
Model acquiring unit, for obtaining CPU model, memory model and magnetic disc type in each calculate node server
Number；
Performance index acquiring unit, for the CPU model, the memory model according to each calculate node server
And the disk model finds out corresponding cpu performance index, internal memory performance index and magnetic in the performance index table
Disk performance index.
7. scheduling system according to claim 1, which is characterized in that the server performance index obtains module, comprising:
Coefficient of performance acquiring unit, for by the corresponding each performance index of each calculate node server and performance index
Corresponding factor accounting is multiplied, and obtains the corresponding multiple coefficients of performance of each calculate node server；
Coefficient addition unit, for being added the corresponding all properties coefficient of each calculate node server to obtain the server
Performance index.
8. scheduling system according to claim 1, which is characterized in that the virtual machine matching module, comprising:
Destination server searching unit, for going out to correspond to according to the goal gradient label lookup received when creating virtual machine
Target computing nodes server；
First matching unit, for when the quantity of the target computing nodes server is 1, the virtual machine to be operated in institute
It states in target computing nodes server；
Second matching unit, for when the quantity of the target computing nodes server is greater than 1, the virtual machine to be operated in
In the remaining maximum target computing nodes server of performance resource.
9. a kind of server characterized by comprising
Memory, for storing computer program；
Processor realizes the step such as the described in any item dispatching methods of Claims 1-4 when for executing the computer program
Suddenly.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program, it is the step realized such as the described in any item dispatching methods of Claims 1-4 that the computer program, which is executed by processor,
Suddenly.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811019799.3A CN109002359A (en) | 2018-09-03 | 2018-09-03 | A kind of dispatching method and relevant apparatus of calculate node server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811019799.3A CN109002359A (en) | 2018-09-03 | 2018-09-03 | A kind of dispatching method and relevant apparatus of calculate node server |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109002359A true CN109002359A (en) | 2018-12-14 |
Family
ID=64590282
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811019799.3A Pending CN109002359A (en) | 2018-09-03 | 2018-09-03 | A kind of dispatching method and relevant apparatus of calculate node server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109002359A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110365799A (en) * | 2019-08-16 | 2019-10-22 | 广东浪潮大数据研究有限公司 | A kind of cluster multinode dispatching method, device and computer readable storage medium |
| CN110941541A (en) * | 2019-11-06 | 2020-03-31 | 北京百度网讯科技有限公司 | Method and device for problem grading of data stream service |
| CN111143039A (en) * | 2020-01-02 | 2020-05-12 | 安超云软件有限公司 | Virtual machine scheduling method and device and computer storage medium |
| CN111277665A (en) * | 2020-02-14 | 2020-06-12 | 平行云科技(北京)有限公司 | 3D application scheduling method, device, terminal and storage medium based on interference measurement |
| CN112860506A (en) * | 2019-11-28 | 2021-05-28 | 阿里巴巴集团控股有限公司 | Monitoring data processing method, device, system and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102270157A (en) * | 2011-07-25 | 2011-12-07 | 浪潮(北京)电子信息产业有限公司 | Server resource allocation system and method |
| CN103095599A (en) * | 2013-01-18 | 2013-05-08 | 浪潮电子信息产业股份有限公司 | Dynamic feedback weighted integration load scheduling method of cloud computing operating system |
| CN104133727A (en) * | 2014-08-08 | 2014-11-05 | 成都致云科技有限公司 | Load distribution method based on real-time resources |
| CN106033373A (en) * | 2015-03-11 | 2016-10-19 | 苏宁云商集团股份有限公司 | A method and a system for scheduling virtual machine resources in a cloud computing platform |
-
2018
- 2018-09-03 CN CN201811019799.3A patent/CN109002359A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102270157A (en) * | 2011-07-25 | 2011-12-07 | 浪潮(北京)电子信息产业有限公司 | Server resource allocation system and method |
| CN103095599A (en) * | 2013-01-18 | 2013-05-08 | 浪潮电子信息产业股份有限公司 | Dynamic feedback weighted integration load scheduling method of cloud computing operating system |
| CN104133727A (en) * | 2014-08-08 | 2014-11-05 | 成都致云科技有限公司 | Load distribution method based on real-time resources |
| CN106033373A (en) * | 2015-03-11 | 2016-10-19 | 苏宁云商集团股份有限公司 | A method and a system for scheduling virtual machine resources in a cloud computing platform |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110365799A (en) * | 2019-08-16 | 2019-10-22 | 广东浪潮大数据研究有限公司 | A kind of cluster multinode dispatching method, device and computer readable storage medium |
| CN110365799B (en) * | 2019-08-16 | 2022-04-22 | 广东浪潮大数据研究有限公司 | Cluster multi-node scheduling method and device and computer readable storage medium |
| CN110941541A (en) * | 2019-11-06 | 2020-03-31 | 北京百度网讯科技有限公司 | Method and device for problem grading of data stream service |
| CN112860506A (en) * | 2019-11-28 | 2021-05-28 | 阿里巴巴集团控股有限公司 | Monitoring data processing method, device, system and storage medium |
| CN112860506B (en) * | 2019-11-28 | 2024-05-17 | 阿里巴巴集团控股有限公司 | Method, device, system and storage medium for processing monitoring data |
| CN111143039A (en) * | 2020-01-02 | 2020-05-12 | 安超云软件有限公司 | Virtual machine scheduling method and device and computer storage medium |
| CN111143039B (en) * | 2020-01-02 | 2024-01-02 | 安超云软件有限公司 | Scheduling method and device of virtual machine and computer storage medium |
| CN111277665A (en) * | 2020-02-14 | 2020-06-12 | 平行云科技(北京)有限公司 | 3D application scheduling method, device, terminal and storage medium based on interference measurement |
| CN111277665B (en) * | 2020-02-14 | 2022-04-08 | 平行云科技(北京)有限公司 | 3D application scheduling method, device, terminal and storage medium based on interference measurement |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109002359A (en) | A kind of dispatching method and relevant apparatus of calculate node server | |
| US9009719B2 (en) | Computer workload capacity estimation using proximity tables | |
| CN106020715B (en) | Storage pool capacity management | |
| CN110163474A (en) | A kind of method and apparatus of task distribution | |
| CN103401938B (en) | Based on resource allocation system and the method thereof of traffic performance under distributed cloud framework | |
| CN102929783B (en) | The methods, devices and systems that a kind of data store | |
| EP3047385A1 (en) | Client-selectable power source options for network-accessible service units | |
| CN106325756B (en) | Data storage method, data calculation method and equipment | |
| CN110519090B (en) | Method and system for allocating accelerator cards of FPGA cloud platform and related components | |
| CN109522382A (en) | Spatial data gridding statistical method and device | |
| CN105260232B (en) | A kind of method and system for realizing cloud computing virtual machine internal most optimum distribution of resources | |
| CN106201537A (en) | A kind of data processing method and device | |
| CN103516763B (en) | Method for processing resource and system and device | |
| CN101963969A (en) | Method and database server for realizing load balancing in Oracle RAC (Real Application Cluster) system | |
| CN105488134A (en) | Big data processing method and big data processing device | |
| CN108595255B (en) | Workflow task scheduling method based on shortest path algorithm in geographically distributed cloud | |
| CN108897622A (en) | A kind of dispatching method and relevant apparatus of task run | |
| CN108536645B (en) | Kernel parallel computing method and device for electric power market transaction business | |
| CN106294115B (en) | A kind of test method and device of application system migration | |
| CN109063210A (en) | Resource object querying method, device, equipment and the storage medium of storage system | |
| CN106844175B (en) | A kind of cloud platform method for planning capacity based on machine learning | |
| CN111694835B (en) | Number section access method, system, equipment and storage medium of logistics electronic bill | |
| CN108256816A (en) | A kind of commission data processing method, device and equipment | |
| CN111784534A (en) | Method and system for predicting running state of comprehensive energy metering system with multiple subsystems | |
| CN108830663B (en) | Electric power customer value evaluation method and system and terminal equipment |
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 |