CN107239336A - A kind of method and device for realizing task scheduling - Google Patents
A kind of method and device for realizing task scheduling Download PDFInfo
- Publication number
- CN107239336A CN107239336A CN201610181930.0A CN201610181930A CN107239336A CN 107239336 A CN107239336 A CN 107239336A CN 201610181930 A CN201610181930 A CN 201610181930A CN 107239336 A CN107239336 A CN 107239336A
- Authority
- CN
- China
- Prior art keywords
- task
- utility function
- effectiveness
- priority
- resource node
- 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.)
- Granted
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]
-
- 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
- G06F9/5038—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 considering the execution order of a plurality of tasks, e.g. taking priority or time dependency constraints into consideration
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A kind of method and device for realizing task scheduling, including:Each corresponding total utility function of task is built according to the utility function of the utility function of the corresponding time utility of each task, and/or the utility function of priority effectiveness, and/or the utility function of the corresponding reliability effectiveness of each resource node, and/or the corresponding security effectiveness of each resource node pre-established;To each task, the value of the total utility function of task when traversal calculating task is intended being assigned to virtual machine;It is determined that traversal calculates the maximum occurrences of the corresponding total utility function of each task, virtual machine of the virtual machine that task plan during total utility function value maximum is assigned to as processor active task.Present invention method, task scheduling is carried out according to time effect, reliability effect, security effect etc. by being submitted to user of the task, user is considered to the demand in terms of time, reliability, security, the load balancing of system is realized, improves the service behaviour of processor active task.
Description
Technical field
Present document relates to but be not limited to field of information processing, espespecially a kind of method and device for realizing task scheduling.
Background technology
At present, the problem of data center is faced with more and more and bottleneck, such as level of hardware are universal very high,
But resource utilization is relatively low;Each province net company is with subordinate unit respectively according to self-demand and spy
Put to build the data center of oneself, operation system otherness is larger;The application relative distribution of deployment, number
It is difficult in maintenance with cluster system management according to safety;The demands such as electric power, refrigeration, network, computer room space are continuous
Expand, the influence of these problems be here data center and harmonious Green Development, can not also meet following magnanimity
The processing of data.
Cloud computing is the important trend of Information Technology Development, the processing energy with reliability height, mass data
Power, autgmentability be strong and the advantages of high resource utilization of equipment, has become grinding for field of information processing
Study carefully focus;Cloud computing can meet the demand that further generation data center calculates data and stored, and have strong
Big application service has occupied critical role as support, data center in cloud computing, in data
For the heart, real-time and reliability are the factors mainly considered, when having large-scale task while accessing and being
, may in a short period of time during system, the task requests of data center will rapid growth so that user
Service quality reduction, and data center may be caused unstable.
The basic demand of cloud computation data center task scheduling is that task of enabling user to submit realizes optimal
Scheduling, and to greatest extent improve cloud environment handling capacity;Method for scheduling task in correlation technique is
For the purpose of minimizing task execution time, such as greedy algorithm, A stars (A* algorithms), minimum-minimum
(Min-min) algorithm, maximum-minimum (Max-min) algorithm and genetic algorithm etc., these tasks are adjusted
Degree method typically only considers the deadline for the task that user submits, and have ignored cloud computation data center user
To other demands and the load balancing of system of different task, the work of cloud computation data center have impact on
Performance.
The content of the invention
The following is the general introduction of the theme to being described in detail herein.This general introduction is not to limit claim
Protection domain.
The embodiment of the present invention provides a kind of method and device for realizing task scheduling, can combine user to not
Related needs with task carry out task scheduling, lift the service behaviour of processor active task.
The embodiments of the invention provide a kind of method for realizing task scheduling, including:
According to the utility function, and/or each resource section of the corresponding time utility of each task pre-established
The utility function of the corresponding reliability effectiveness of point, and/or the effect of the corresponding security effectiveness of each resource node
It is total accordingly that each task is built with the utility function of function, and/or the corresponding priority effectiveness of each task
Utility function;
The each task submitted to user, total effect of task when traversal calculating task is intended being assigned to virtual machine
With the value of function;
To each task, it is determined that traversal calculates the maximum occurrences of the corresponding total utility function of the task, will be total
Task intends the virtual machine that is assigned to as the virtual machine of processor active task when utility function value is maximum.
Optionally, the effectiveness of the corresponding time utility of each task is included in the total utility function of foundation
During function, the utility function of the corresponding time utility of each task includes:
The default expectation run time of current task and the time difference of task submission time are calculated, calculating is obtained
The time difference obtained is used as the tasks carrying time limit;Determine described in when task is completed within the tasks carrying time limit
The utility function value of time utility is 1;Determine that task does not complete when institute within the tasks carrying time limit
The utility function value for stating time utility is 0;
The effectiveness letter of the corresponding reliability effectiveness of each resource node is included in the total utility function set up
During number, the utility function of the reliability effectiveness of the corresponding resource node of each resource node includes:
It is determined that being assigned to the number of tasks n of resource nodeTThe virtual machine number n included with the resource nodeM;With
The coefficient of reliability pre-set as the utility function of reliability effectiveness as the truth of a matter, with the distribution of determination
To the number of tasks n of resource nodeTThe virtual machine number n included with resource nodeMOn be used as index parameters, structure
Build the utility function of the reliability effectiveness;
The effectiveness letter of the corresponding security effectiveness of each resource node is included in the total utility function set up
During number, the utility function of the security effectiveness of the corresponding resource node of each resource node includes:
It is two or more safe classes to divide all resource nodes according to predetermined level strategy;To work as
Preceding resource node is randomly assigned a safe class from two or more safe classes of division;
Safe class according to being randomly assigned for Current resource node set up Current resource node with safety etc.
The utility function for the security effectiveness that level is directly proportional;
The utility function of the corresponding priority effectiveness of each task is included in the total utility function set up
When, the utility function of the corresponding priority effectiveness of each task includes:
The data class included according to current task sets the priority of current task;According to the current of setting
The priority level of task, sets each corresponding equivalent coefficient of priority level, with the grade system of setting
Count the utility function of the priority effectiveness as current task;
The equivalent coefficient is used for the priority for distinguishing the corresponding task of each species data;
The coefficient of reliability is is less than 1 number more than 0.
Optionally, the coefficient of reliability is ri=0.9+0.1ra;
The utility function of the reliability effectiveness built includes:
Wherein, raTo be evenly distributed on the random number that [0,1] is interval.
Optionally, described is that two or more are pacified according to all resource nodes of predetermined level strategy division
Congruent level includes:
It is s that resource node is divided into safe class according to predetermined level strategyiFour peaces of={ 1,2,3,4 }
Congruent level;
Setting up the utility function of the security effectiveness being directly proportional to safe class of Current resource node includes:
A safe class s in four safe classes is randomly assigned for Current resource nodei;According to random
The safe class of the Current resource node of distribution sets up the effectiveness for the security effectiveness being directly proportional to safe class
Function includes:Ui(si)=0.25si。
Optionally, the priority of the data class setting current task included according to current task includes:
The data that task is included are divided into the time using class data, action record class data and table of equipment
Account and general class of information data;The data included are set to use priority of task of class data etc. for the time
Level is the first priority;The data that setting is included are that the priority level of the task of action record class data is
Second priority;It is equipment account and the priority of the task of general class of information data to set the data included
Grade is third priority;
The equivalent coefficient of first priority level set is less than the grade system of second priority
Number, equivalent coefficient of the equivalent coefficient less than the third priority of second priority, and set
The equivalent coefficient of first priority level, the equivalent coefficient of second priority and the described 3rd
The numerical values recited of the equivalent coefficient of priority is used to distinguish priority of the corresponding task of each species data etc.
Level height.
Optionally, the total utility function of the task takes when the traversal calculating task is intended being assigned to virtual machine
Value includes:
The each task submitted to user, calculate the corresponding time utility of the task utility function it is all
The utility function of the reliability effectiveness of resource node where the virtual machine that value, and/or task plan are assigned to
All values, and/or task intend resource node where the virtual machine that is assigned to security effectiveness effect
With all values of function, and/or all values of the utility function of priority effectiveness;
To the utility function of each species included in total utility function, calculated each time according to combination
A value of all values of the utility function of each species is selected during total utility function;
All combinations to being selected according to combination, respectively each utility function to selecting each time
Value added up, obtain total utility function value.
Optionally, the value of the utility function of selection is carried out it is cumulative before, this method also includes:
For the utility function for setting up in total utility function the corresponding time utility of each task included,
And/or the utility function, and/or each resource node of each corresponding reliability effectiveness of resource node are corresponding
The utility function of security effectiveness, and/or the utility function of the corresponding priority effectiveness of each task according to
Default Weight Algorithm sets corresponding weight respectively.
Optionally, also include before this method:
All tasks that user is submitted are ranked up according to the sequence of the priority level of task, are pressed
According to the total utility function of the order calculating task of task priority from high to low.
Optionally, this method also includes:
The virtual machine for the task that computing user is submitted averagely performs speed according to single-length fixed point instruction
(MIPS) size ascending order arrangement.
Optionally, it is described when being assigned to virtual machine of the task does not complete computing in operation threshold duration
Method also includes:
Stop the virtual machine continuing not completing the task of computing described in computing in operation threshold duration, and will
The task for stopping computing being loaded into the end of priority level sequence;
Complete after the computing except other tasks of the stopping computing of the task, then to coming the priority level
The task of the stopping computing of sequence end carries out computing.
Optionally, the traversal for carrying out the corresponding total utility function of each task using greedy algorithm is calculated.
Optionally, also include before this method:
Estimate unit using operation threshold duration as resource, the size for each task that user is submitted divided by
Resource estimates the business of unit acquisition, and required resource is estimated as the task is corresponding;
By user submit all tasks it is corresponding estimate needed for resource add up, acquisition establishment computing user
Computer resource needed for the virtual machine of submission task.
Optionally, this method also includes:Port flow, and/or connection number to all resource nodes
It is monitored, for according to preset strategy is to the port flow of each resource node, and/or connects number
It is adjusted.
On the other hand, the embodiment of the present invention also provides a kind of device for realizing task scheduling, including:Total effect
With function unit, traversal computing unit and task allocation unit;Wherein,
Total utility function unit is used for, according to the effectiveness of the corresponding time utility of each task pre-established
The utility function, and/or each resource section of function, and/or the corresponding reliability effectiveness of each resource node
The utility function of the corresponding security effectiveness of point, and/or the effectiveness letter of the corresponding priority effectiveness of each task
Number builds each corresponding total utility function of task;
Traversal computing unit is used for, each task submitted to user, and traversal calculating task is intended being assigned to void
The value of the total utility function of task during plan machine;
Task allocation unit is used for, to each task, it is determined that traversal calculates the corresponding total utility letter of the task
Several maximum occurrences, the total utility function value virtual machine that task is intended being assigned to when maximum is appointed as computing
The virtual machine of business.
Optionally, it is corresponding comprising each task in the total utility function that total utility function unit is set up
During the utility function of time utility, the utility function of the corresponding time utility of each task includes:
The default expectation run time of current task and the time difference of task submission time are calculated, calculating is obtained
The time difference obtained is used as the tasks carrying time limit;Determine described in when task is completed within the tasks carrying time limit
The utility function value of time utility is 1;Determine that task does not complete when institute within the tasks carrying time limit
The utility function value for stating time utility is 0;
It is corresponding reliable comprising each resource node in the total utility function that total utility function unit is set up
During the utility function of property effectiveness, the effect of the reliability effectiveness of the corresponding resource node of each resource node
Included with function:
It is determined that being assigned to the number of tasks n of resource nodeTThe virtual machine number n included with the resource nodeM;With
The coefficient of reliability pre-set as the utility function of reliability effectiveness as the truth of a matter, with the distribution of determination
To the number of tasks n of resource nodeTThe virtual machine number n included with resource nodeMOn be used as index parameters, structure
Build the utility function of the reliability effectiveness;
It is safe accordingly comprising each resource node in the total utility function that total utility function unit is set up
During the utility function of property effectiveness, the effect of the security effectiveness of the corresponding resource node of each resource node
Included with function:
It is two or more safe classes to divide all resource nodes according to predetermined level strategy;To work as
Preceding resource node is randomly assigned a safe class from two or more safe classes of division;
Safe class according to being randomly assigned for Current resource node set up Current resource node with safety etc.
The utility function for the security effectiveness that level is directly proportional;
The corresponding priority effect of each task is included in the total utility function that total utility function unit is set up
During utility function, the utility function of the corresponding priority effectiveness of each task includes:
The data class included according to current task sets the priority of current task;According to the current of setting
The priority level of task, sets each corresponding equivalent coefficient of priority level, with the grade system of setting
Count the utility function of the priority effectiveness as current task;
The equivalent coefficient is used for the priority for distinguishing the corresponding task of each species data;
The coefficient of reliability is is less than 1 number more than 0.
Optionally, traversal computing unit specifically for,
The each task submitted to user, calculate the corresponding time utility of the task utility function it is all
The utility function of the reliability effectiveness of resource node where the virtual machine that value, and/or task plan are assigned to
All values, and/or task intend resource node where the virtual machine that is assigned to security effectiveness effect
With all values of function, and/or all values of the utility function of priority effectiveness;
To the utility function of each species included in total utility function, calculated each time according to combination
A value of all values of the utility function of each species is selected during total utility function;
All combinations to being selected according to combination, respectively each utility function to selecting each time
Value added up, obtain total utility function value.
Optionally, the device also includes setting weight unit, for taking for each utility function to selection
Before value add up,
For the utility function for setting up in total utility function the corresponding time utility of each task included,
And/or the utility function, and/or each resource node of each corresponding reliability effectiveness of resource node are corresponding
The utility function of security effectiveness, and/or the utility function of the corresponding priority effectiveness of each task according to
Default Weight Algorithm sets corresponding weight respectively.
Optionally, the device also includes task ranking unit, for all tasks for submitting user according to
The sequence of the priority level of task is ranked up, according to the order meter of task priority from high to low
The total utility function of calculation task.
Optionally, the device also includes virtual machine sequencing unit, for the submitting computing user of the task
The size ascending order that virtual machine averagely performs speed (MIPS) according to single-length fixed point instruction is arranged.
Optionally, the device also includes computing adjustment unit, for being transported when being assigned to virtual machine of the task
When not completing computing in row threshold value duration, stop the virtual machine and continue described in computing in operation threshold duration
The task of computing is not completed, and the task for stopping computing being loaded into the end that priority level sorts;
Complete after the computing except other tasks of the stopping computing of the task, then sorted to coming the priority level
The task of the stopping computing of end carries out computing.
Optionally, the device also includes obtaining resource unit, for pre- using operation threshold duration as resource
Estimate unit, the size divided by resource of each task that user is submitted estimate the business of unit acquisition, are used as this
Task is corresponding to estimate required resource;
By user submit all tasks it is corresponding estimate needed for resource add up, acquisition establishment computing user
Computer resource needed for the virtual machine of submission task.
Optionally, the device also include monitoring unit, for the port flow to all resource nodes,
And/or connection number is monitored, for according to preset strategy to the port flow of each resource node and
/ or connection number be adjusted.
Compared with correlation technique, technical scheme includes:It is corresponding according to each task pre-established
Time utility utility function, and/or the corresponding reliability effectiveness of each resource node utility function,
And/or the utility function, and/or each task of each corresponding security effectiveness of resource node are excellent accordingly
The utility function of first level effectiveness builds each corresponding total utility function of task;Each submitted to user
Business, the value of the total utility function of task when traversal calculating task is intended being assigned to virtual machine;To each
Business, it is determined that traversal calculates the maximum occurrences of the corresponding total utility function of the task, by total utility function value
Task intends the virtual machine that is assigned to as the virtual machine of processor active task when maximum.Present invention method,
By being submitted to user of the task according to the carry out task such as time effect, reliability effect, security effect
Scheduling, it is contemplated that user realizes the negative of system to the demand in terms of time, reliability, security
Carry balanced, improve the service behaviour of processor active task.
After reading and understanding accompanying drawing and being described in detail, it can be appreciated that other aspects.
Brief description of the drawings
Fig. 1 embodiment of the present invention realizes the flow chart of the method for task scheduling;
Fig. 2 embodiment of the present invention realizes the structured flowchart of the device of task scheduling;
Fig. 3 applies the method flow diagram of example for the present invention.
Embodiment
For the object, technical solutions and advantages of the present invention are more clearly understood, below in conjunction with accompanying drawing
Embodiments of the invention are described in detail.It should be noted that in the case where not conflicting, this Shen
Please in embodiment and the feature in embodiment can mutually be combined.
Fig. 1 embodiment of the present invention realizes the flow chart of the method for task scheduling, as shown in figure 1, including:
Step 100, according to the utility function of the corresponding time utility of each task pre-established, and/or
The utility function, and/or each resource node of each corresponding reliability effectiveness of resource node are safe accordingly
The property utility function of effectiveness, and/or the utility function of the corresponding priority effectiveness of each task build each
It is engaged in corresponding total utility function;
Optionally, the utility function of the corresponding time utility of each task is included in the total utility function of foundation
When, the utility function of the corresponding time utility of each task includes:
The default expectation run time of current task and the time difference of task submission time are calculated, calculating is obtained
The time difference obtained is used as the tasks carrying time limit;Determine time utility when task is completed in task Deadline
Utility function value be 1;Determine the effectiveness of time utility when task is not completed in task Deadline
Function value is 0;
It should be noted that the default expectation run time of current task can after user's submission task,
Determined by receiving external command;Task submission time can be believed by reading task daily record or reading system
Breath is obtained, and belongs to the conventional techniques of those skilled in the art.
The utility function of the corresponding reliability effectiveness of each resource node is included in the total utility function of foundation
When, the utility function of the reliability effectiveness of the corresponding resource node of each resource node includes:
It is determined that being assigned to the number of tasks n of resource nodeTThe virtual machine number n included with resource nodeM;With advance
The coefficient of reliability of setting, as the truth of a matter, money is assigned to determination as the utility function of reliability effectiveness
The number of tasks n of source nodeTThe virtual machine number n included with resource nodeMOn can as index parameters, structure
By the utility function of property effectiveness;
The utility function of the corresponding security effectiveness of each resource node is included in the total utility function of foundation
When, the utility function of the security effectiveness of the corresponding resource node of each resource node includes:
It is two or more safe classes to divide all resource nodes according to predetermined level strategy;To work as
Preceding resource node is randomly assigned a safe class from two or more safe classes of division;
Safe class according to being randomly assigned for Current resource node set up Current resource node with safety etc.
The utility function for the security effectiveness that level is directly proportional;
When the utility function of the corresponding priority effectiveness of each task is included in the total utility function of foundation, often
The utility function of the corresponding priority effectiveness of one task includes:
The data class included according to current task sets the priority of current task;According to the current of setting
The priority level of task, sets each corresponding equivalent coefficient of priority level, with the grade system of setting
Count the utility function of the priority effectiveness as current task;
Equivalent coefficient is used for the priority for distinguishing the corresponding task of each species data;
Coefficient of reliability is is less than 1 number more than 0.
Optionally, coefficient of reliability is ri=0.9+0.1ra;
The utility function of the reliability effectiveness of structure includes:
Wherein, raTo be evenly distributed on the random number that [0,1] is interval.
It should be noted that coefficient of reliability can be adjusted according to actual conditions, coefficient of reliability is used
In for the whether reliable probabilistic information of resource node assignment, present invention method coefficient of reliability is
Rule of thumb analyze one embodiment of acquisition;In addition, the utility function of reliability effectiveness can also be carried out
Adjustment, as long as the number of tasks n of resource node can be representedTThe virtual machine number n included with resource nodeMIt is right
The calculating purpose of utility function.
Optionally, it is two or more safety etc. to divide all resource nodes according to predetermined level strategy
Level includes:
It is s that resource node is divided into safe class according to predetermined level strategyiFour peaces of={ 1,2,3,4 }
Congruent level;
Setting up the utility function of the security effectiveness being directly proportional to safe class of Current resource node includes:
A safe class s in four safe classes is randomly assigned for Current resource nodei;According to random
The safe class of the Current resource node of distribution sets up the effectiveness for the security effectiveness being directly proportional to safe class
Function includes:Ui(si)=0.25si。
It should be noted that it is rule of thumb to obtain that present invention method, which divides 4 safe classes,
According to can be adjusted to the division of safe class in practical application;
Optionally, the priority of the data class setting current task included according to current task includes:
The data that task is included are divided into the time using class data, action record class data and table of equipment
Account and general class of information data;The data included are set to use priority of task of class data etc. for the time
Level is the first priority;The data that setting is included are that the priority level of the task of action record class data is
Second priority;It is equipment account and the priority of the task of general class of information data to set the data included
Grade is third priority;
The equivalent coefficient of the first priority level set is less than the equivalent coefficient of the second priority, and second is excellent
The equivalent coefficient of first level be less than third priority equivalent coefficient, and set the first priority level etc.
The numerical values recited of the equivalent coefficient of level coefficient, the equivalent coefficient of the second priority and third priority is used for
Distinguish the priority level height of the corresponding task of each species data.
It should be noted that present invention method, the priority level dividing mode of task is optional
A kind of dividing mode, can accordingly be divided according to the different definition to priority level.
Step 101, each task submitted to user, traversal calculating task are somebody's turn to do when intending being assigned to virtual machine
The value of the total utility function of task;
Optionally, present invention method, task when traversal calculating task is intended being assigned to virtual machine
The value of total utility function includes:
The each task submitted to user, calculate the corresponding time utility of the task utility function it is all
The utility function of the reliability effectiveness of resource node where the virtual machine that value, and/or task plan are assigned to
All values, and/or task intend resource node where the virtual machine that is assigned to security effectiveness effect
With all values of function, and/or all values of the utility function of priority effectiveness;
To the utility function of each species included in total utility function, calculated each time according to combination
A value of all values of the utility function of each species is selected during total utility function;
All combinations to being selected according to combination, respectively each utility function to selecting each time
Value added up, obtain total utility function value.
It should be noted that here it is cumulative including:To taking for each utility function for selecting each time
Value is added.
Optionally, the value of the utility function of selection is carried out it is cumulative before, this method also includes:
For set up in total utility function the corresponding time utility of each task included utility function and/
Or the utility function, and/or each resource node of each corresponding reliability effectiveness of resource node are pacified accordingly
The utility function of full property effectiveness, and/or the utility function of the corresponding priority effectiveness of each task are according to default
Weight Algorithm sets corresponding weight respectively;
Here, the weighted value of the utility function included in total utility function is added can be using setting value as 1.
It should be noted that the factor for setting weight to be mainly used in refer to during task scheduling is accounted for,
When user focuses on time utility in theory, the weight of the utility function of time utility is relative to other effectiveness letters
Number is larger;Similar, if user is high to reliability requirement, the power of the utility function of reliability effectiveness
Heavy phase is larger for other utility functions.
Optionally, the traversal for carrying out the corresponding total utility function of each task using greedy algorithm is calculated.
It should be noted that greedy algorithm is an alternative embodiment of the embodiment of the present invention, if through
Algorithm improvement is crossed, other algorithms can realize that quick traversal is calculated, then other algorithms can also be applied to this
In inventive embodiments.
Step 102, to each task, it is determined that traversal calculates the maximum of the corresponding total utility function of the task
Value, regard the total utility function value virtual machine that task is intended being assigned to when maximum as the virtual of processor active task
Machine.
Optionally, also include before present invention method:
All tasks that user is submitted are ranked up according to the sequence of the priority level of task, are pressed
According to the total utility function of the order calculating task of task priority from high to low.
Optionally, present invention method also includes:
The virtual machine for the task that computing user is submitted averagely performs speed according to single-length fixed point instruction
(MIPS) size ascending order arrangement.
It should be noted that to virtual machine according to MIPS size ascending order arrange, MIPS is to weigh empty
One index of the cpu performance of plan machine, for weighing empty machine performance, after being arranged by MIPS ascending orders, most
The empty machine performance of latter row is best;When intending distribution task to virtual machine, according to sorting from the best void of performance
Plan machine proceeds by plan distribution, on this basis the value of the total utility function of calculating task.
Optionally, when being assigned to virtual machine of the task does not complete computing in operation threshold duration, this hair
Bright embodiment method also includes:
Stop virtual machine continuing not completing the task of computing in computing operation threshold duration, and computing will be stopped
Task be loaded into priority level sequence end;
Complete after the computing except other tasks of the stopping computing of the task, then to coming priority level sequence
The task of the stopping computing of end carries out computing.
It should be noted that a length of those skilled in the art rule of thumb analyze the one of determination during operation threshold
As task computing need duration, if operation threshold duration task do not complete computing, illustrate the task
It is longer task, the timely completion of follow-up work can be influenceed by proceeding the computing of the task.
Optionally, present invention method also includes:Unit is estimated using operation threshold duration as resource,
The size divided by resource for each task that user is submitted estimate the business of unit acquisition, are used as the task
It is corresponding to estimate required resource;
By all tasks are corresponding estimate needed for resource add up, obtain establishment computing user submission task
Virtual machine needed for computer resource.
It should be noted that the size of each task can be needed by processor active task VCPU numbers,
Memory size etc. is determined.
Optionally, present invention method also includes:Port flow to all resource nodes and/
Or connection number be monitored, for according to preset strategy to the port flow of each resource node and/
Or connection number is adjusted.
It should be noted that the port flow, and/or connection number of resource node are carried out by explorer
Adjustment, therefore, the port flow, and/or connection number of the resource node that present invention method is monitored
It can feed back on task manager.
Present invention method can be implemented by carrying out the device of task scheduling in correlation technique, for example,
Task manager.The traversal of utility function calculates, task is assigned to virtual machine etc. can be by being appointed
The central processing unit of the device of business scheduling, relevant information can be stored among storage medium.
Present invention method, by being submitted to user of the task according to time effect, reliability effect,
Security effect etc. carries out task scheduling, it is contemplated that in terms of user is to time, reliability, security
Demand, realizes the load balancing of system, improves the service behaviour of processor active task.
Fig. 2 embodiment of the present invention realizes the structured flowchart of the device of task scheduling, as shown in Fig. 2 including:
Total utility function unit, traversal computing unit and task allocation unit;Wherein,
Total utility function unit is used for, according to the effectiveness of the corresponding time utility of each task pre-established
The utility function, and/or each resource section of function, and/or the corresponding reliability effectiveness of each resource node
The utility function of the corresponding security effectiveness of point, and/or the effectiveness letter of the corresponding priority effectiveness of each task
Number builds each corresponding total utility function of task;
Optionally, each task corresponding time is included in the total utility function that total utility function unit is set up
During the utility function of effectiveness, the utility function of the corresponding time utility of each task includes:
The default expectation run time of current task and the time difference of task submission time are calculated, calculating is obtained
The time difference obtained is used as the tasks carrying time limit;Determine time utility when task is completed in task Deadline
Utility function value be 1;Determine the effectiveness of time utility when task is not completed in task Deadline
Function value is 0;
The corresponding reliability effect of each resource node is included in the total utility function that total utility function unit is set up
During utility function, the utility function bag of the reliability effectiveness of the corresponding resource node of each resource node
Include:
It is determined that being assigned to the number of tasks n of resource nodeTThe virtual machine number n included with resource nodeM;With advance
The coefficient of reliability of setting, as the truth of a matter, money is assigned to determination as the utility function of reliability effectiveness
The number of tasks n of source nodeTThe virtual machine number n included with resource nodeMOn can as index parameters, structure
By the utility function of property effectiveness;
The corresponding security effect of each resource node is included in the total utility function that total utility function unit is set up
During utility function, the utility function bag of the security effectiveness of the corresponding resource node of each resource node
Include:
It is two or more safe classes to divide all resource nodes according to predetermined level strategy;To work as
Preceding resource node is randomly assigned a safe class from two or more safe classes of division;
Safe class according to being randomly assigned for Current resource node set up Current resource node with safety etc.
The utility function for the security effectiveness that level is directly proportional;
The corresponding priority effectiveness of each task is included in the total utility function that total utility function unit is set up
During utility function, the utility function of the corresponding priority effectiveness of each task includes:
The data class included according to current task sets the priority of current task;According to the current of setting
The priority level of task, sets each corresponding equivalent coefficient of priority level, with the grade system of setting
Count the utility function of the priority effectiveness as current task;
Equivalent coefficient is used for the priority for distinguishing the corresponding task of each species data;
Coefficient of reliability is is less than 1 number more than 0.
Traversal computing unit is used for, each task submitted to user, and traversal calculating task is intended being assigned to void
The value of the total utility function of task during plan machine;
Optionally, traversal computing unit specifically for,
The each task submitted to user, calculate the corresponding time utility of the task utility function it is all
The utility function of the reliability effectiveness of resource node where the virtual machine that value, and/or task plan are assigned to
All values, and/or task intend resource node where the virtual machine that is assigned to security effectiveness effect
With all values of function, and/or all values of the utility function of priority effectiveness;
To the utility function of each species included in total utility function, calculated each time according to combination
A value of all values of the utility function of each species is selected during total utility function;
All combinations to being selected according to combination, respectively each utility function to selecting each time
Value added up, obtain total utility function value.
Task allocation unit is used for, to each task, it is determined that traversal calculates the corresponding total utility letter of the task
Several maximum occurrences, the total utility function value virtual machine that task is intended being assigned to when maximum is appointed as computing
The virtual machine of business.
Optionally, device of the embodiment of the present invention also includes setting weight unit, for each effect to selection
Before with the value of function add up,
For set up in total utility function the corresponding time utility of each task included utility function and/
Or the utility function, and/or each resource node of each corresponding reliability effectiveness of resource node are pacified accordingly
The utility function of full property effectiveness, and/or the utility function of the corresponding priority effectiveness of each task are according to default
Weight Algorithm sets corresponding weight respectively.
Optionally, device of the embodiment of the present invention also includes task ranking unit, for the institute for submitting user
There is task to be ranked up according to the sequence of the priority level of task, according to task priority by height to
The total utility function of low order calculating task.
Optionally, device of the embodiment of the present invention also includes virtual machine sequencing unit, for computing user to be carried
The size ascending order that the virtual machine of the task of friendship averagely performs speed (MIPS) according to single-length fixed point instruction is arranged
Row.
Optionally, device of the embodiment of the present invention also includes computing adjustment unit, and virtual machine is assigned to for working as
Task in operation threshold duration do not complete computing when, stop virtual machine continue computing operation threshold duration
The task of interior unfinished computing, and the stopping computing of the task is loaded into the end that priority level sorts;
Complete after the computing except other tasks of the stopping computing of the task, then to coming priority level sequence end
Stopping computing task carry out computing.
Optionally, device of the embodiment of the present invention also includes obtaining resource unit, for operation threshold duration
Unit is estimated as resource, the size divided by resource of each task that user is submitted estimate unit acquisition
Business, required resource is estimated as the task is corresponding;
By user submit all tasks it is corresponding estimate needed for resource add up, acquisition establishment computing user
Computer resource needed for the virtual machine of submission task.
Optionally, device of the embodiment of the present invention also includes monitoring unit, for the end to all resource nodes
Mouth flow, and/or connection number are monitored, for according to port of the preset strategy to each resource node
Flow, and/or connection number are adjusted.
The inventive method is clearly described in detail below by way of using example, is only used for using example
State the embodiment of the present invention, the protection domain being not intended to limit the present invention.
Using example
The method flow diagram of Fig. 3 present invention application examples, as shown in figure 3, including:
Step 300, being submitted according to user for task, generate task queue;
Step 301, determine computing user submit task virtual machine needed for computer resource;
This application example includes:
Estimate unit using operation threshold duration as resource, the size for each task that user is submitted divided by
Resource estimates the business of unit acquisition, and required resource is estimated as the task is corresponding;
By all tasks are corresponding estimate needed for resource add up, obtain establishment computing user submission task
Virtual machine needed for computer resource.
It should be noted that the virtual center processor that the size of task can be needed by processor active task
(VCPU) computer hardware resource such as number, memory size is determined;
Optionally, the computer resource needed for computing user submits the virtual machine of task can pass through following public affairs
Formula is calculated:
Wherein, QiThe size of i-th of task is represented,Represent that operation threshold duration, i.e. resource estimate list
Position, nTThe number of tasks of being submitted for user for task;
Step 302, the computer resource wound according to needed for the virtual machine of the computing user of determination submission task
Build virtual machine;
It should be noted that creating the conventional techniques that virtual machine is those skilled in the art;
Step 303, the virtual machine for the submitting computing user of the task are averagely held according to single-length fixed point instruction
The size ascending order arrangement of scanning frequency degree (MIPS).
Step 304, all tasks that user submits are entered according to the sequence of the priority level of task
Row sequence;
The total utility function of step 305, order calculating task according to task priority from high to low.
It should be noted that the total utility function of calculating task needs to intend task to be assigned in virtual machine,
Determine that task is intended the reliability of the resource node where the virtual machine that is assigned to and imitated by intending the virtual machine of distribution
The effectiveness of the security effectiveness of resource node where the virtual machine that utility function and task plan are assigned to
Function;
In this step, each task submitted to user, traversal calculating task is somebody's turn to do when intending being assigned to virtual machine
The value of the total utility function of task;
Optionally, the value bag of the total utility function of task when traversal calculating task is intended being assigned to virtual machine
Include:
The each task submitted to user, calculate the corresponding time utility of the task utility function it is all
The utility function of the reliability effectiveness of resource node where the virtual machine that value, and/or task plan are assigned to
All values, and/or task intend resource node where the virtual machine that is assigned to security effectiveness effect
With all values of function, and/or all values of the utility function of priority effectiveness;
To the utility function of each species included in total utility function, calculated each time according to combination
A value of all values of the utility function of each species is selected during total utility function;
All combinations to being selected according to combination, respectively each utility function to selecting each time
Value added up, obtain total utility function value.
It should be noted that here it is cumulative including:To taking for each utility function for selecting each time
Value is added.And each utility function included in total utility function takes once to calculate each time and obtained respectively
The value obtained, is traveled through, total utility function can obtainable all values using combination;
Step 306, to each task, it is determined that traversal calculates the maximum of the corresponding total utility function of the task
Value, regard the total utility function value virtual machine that task is intended being assigned to when maximum as the virtual of processor active task
Machine.
Step 307, when being assigned to the task of virtual machine and not completing computing in operation threshold duration, stop
Only virtual machine continues not completing the task of computing, and the stopping computing of the task in computing operation threshold duration
It is loaded into the end of priority level sequence;
After step 308, completion are except the computing of other tasks of the stopping computing of the task, to coming priority
The task of the stopping computing of grade sequence end carries out computing.
When step 309, the computing for the completing user's submission of the task, virtual machine is discharged.
Optionally, this application example also includes:Port flow, and/or connection number to all resource nodes
It is monitored, for according to preset strategy is to the port flow of each resource node, and/or connects number
It is adjusted.
It should be noted that the port flow, and/or connection number of resource node are carried out by explorer
Adjustment, therefore, the port flow, and/or connection number of the resource node that present invention method is monitored
It can feed back on task manager.
One of ordinary skill in the art will appreciate that all or part of step in the above method can pass through program
To instruct related hardware (such as processor) to complete, described program can be stored in computer-readable storage
In medium, such as read-only storage, disk or CD.Alternatively, all or part of above-described embodiment
Step can also use one or more integrated circuits to realize.Correspondingly, it is each in above-described embodiment
Module/unit can be realized in the form of hardware, for example, its corresponding function is realized by integrated circuit,
It can also be realized, for example, be stored in by computing device in memory in the form of software function module
Program/instruction realize its corresponding function.The present invention is not restricted to the hardware and software of any particular form
Combination.”.
Although disclosed herein embodiment as above, described content is only to readily appreciate the present invention
And the embodiment used, it is not limited to the present invention.Technology people in any art of the present invention
Member, do not depart from disclosed herein spirit and scope on the premise of, can be in the form of implementation and thin
Any modification and change, but the scope of patent protection of the present invention are carried out on section, still must be with appended right
The scope that claim is defined is defined.
Claims (22)
1. a kind of method for realizing task scheduling, it is characterised in that including:
According to the utility function, and/or each resource section of the corresponding time utility of each task pre-established
The utility function of the corresponding reliability effectiveness of point, and/or the effect of the corresponding security effectiveness of each resource node
It is total accordingly that each task is built with the utility function of function, and/or the corresponding priority effectiveness of each task
Utility function;
The each task submitted to user, total effect of task when traversal calculating task is intended being assigned to virtual machine
With the value of function;
To each task, it is determined that traversal calculates the maximum occurrences of the corresponding total utility function of the task, will be total
Task intends the virtual machine that is assigned to as the virtual machine of processor active task when utility function value is maximum.
2. according to the method described in claim 1, it is characterised in that
When the utility function of the corresponding time utility of each task is included in the total utility function set up,
The utility function of the corresponding time utility of each task includes:
The default expectation run time of current task and the time difference of task submission time are calculated, calculating is obtained
The time difference obtained is used as the tasks carrying time limit;Determine described in when task is completed within the tasks carrying time limit
The utility function value of time utility is 1;Determine that task does not complete when institute within the tasks carrying time limit
The utility function value for stating time utility is 0;
The effectiveness letter of the corresponding reliability effectiveness of each resource node is included in the total utility function set up
During number, the utility function of the reliability effectiveness of the corresponding resource node of each resource node includes:
It is determined that being assigned to the number of tasks n of resource nodeTThe virtual machine number n included with the resource nodeM;With
The coefficient of reliability pre-set as the utility function of reliability effectiveness as the truth of a matter, with the distribution of determination
To the number of tasks n of resource nodeTThe virtual machine number n included with resource nodeMOn be used as index parameters, structure
Build the utility function of the reliability effectiveness;
The effectiveness letter of the corresponding security effectiveness of each resource node is included in the total utility function set up
During number, the utility function of the security effectiveness of the corresponding resource node of each resource node includes:
It is two or more safe classes to divide all resource nodes according to predetermined level strategy;To work as
Preceding resource node is randomly assigned a safe class from two or more safe classes of division;
Safe class according to being randomly assigned for Current resource node set up Current resource node with safety etc.
The utility function for the security effectiveness that level is directly proportional;
The utility function of the corresponding priority effectiveness of each task is included in the total utility function set up
When, the utility function of the corresponding priority effectiveness of each task includes:
The data class included according to current task sets the priority of current task;According to the current of setting
The priority level of task, sets each corresponding equivalent coefficient of priority level, with the grade system of setting
Count the utility function of the priority effectiveness as current task;
The equivalent coefficient is used for the priority for distinguishing the corresponding task of each species data;
The coefficient of reliability is is less than 1 number more than 0.
3. method according to claim 2, it is characterised in that
The coefficient of reliability is ri=0.9+0.1ra;
The utility function of the reliability effectiveness built includes:
Wherein, raTo be evenly distributed on the random number that [0,1] is interval.
4. method according to claim 2, it is characterised in that described to be drawn according to predetermined level strategy
It is that two or more safe classes include to divide all resource nodes:
It is s that resource node is divided into safe class according to predetermined level strategyiFour peaces of={ 1,2,3,4 }
Congruent level;
Setting up the utility function of the security effectiveness being directly proportional to safe class of Current resource node includes:
A safe class s in four safe classes is randomly assigned for Current resource nodei;According to random
The safe class of the Current resource node of distribution sets up the effectiveness for the security effectiveness being directly proportional to safe class
Function includes:Ui(si)=0.25si。
5. method according to claim 2, it is characterised in that described to be included according to current task
The priority of data class setting current task includes:
The data that task is included are divided into the time using class data, action record class data and table of equipment
Account and general class of information data;The data included are set to use priority of task of class data etc. for the time
Level is the first priority;The data that setting is included are that the priority level of the task of action record class data is
Second priority;It is equipment account and the priority of the task of general class of information data to set the data included
Grade is third priority;
The equivalent coefficient of first priority level set is less than the grade system of second priority
Number, equivalent coefficient of the equivalent coefficient less than the third priority of second priority, and set
The equivalent coefficient of first priority level, the equivalent coefficient of second priority and the described 3rd
The numerical values recited of the equivalent coefficient of priority is used to distinguish priority of the corresponding task of each species data etc.
Level height.
6. the method according to any one of Claims 1 to 5, it is characterised in that the traversal is calculated
The value of the total utility function of the task includes when task is intended being assigned to virtual machine:
The each task submitted to user, calculate the corresponding time utility of the task utility function it is all
The utility function of the reliability effectiveness of resource node where the virtual machine that value, and/or task plan are assigned to
All values, and/or task intend resource node where the virtual machine that is assigned to security effectiveness effect
With all values of function, and/or all values of the utility function of priority effectiveness;
To the utility function of each species included in total utility function, calculated each time according to combination
A value of all values of the utility function of each species is selected during total utility function;
All combinations to being selected according to combination, respectively each utility function to selecting each time
Value added up, obtain total utility function value.
7. method according to claim 6, it is characterised in that to the value of the utility function of selection
Before add up, this method also includes:
For the utility function for setting up in total utility function the corresponding time utility of each task included,
And/or the utility function, and/or each resource node of each corresponding reliability effectiveness of resource node are corresponding
The utility function of security effectiveness, and/or the utility function of the corresponding priority effectiveness of each task according to
Default Weight Algorithm sets corresponding weight respectively.
8. the method according to any one of Claims 1 to 5, it is characterised in that before this method also
Including:
All tasks that user is submitted are ranked up according to the sequence of the priority level of task, are pressed
According to the total utility function of the order calculating task of task priority from high to low.
9. the method according to any one of Claims 1 to 5, it is characterised in that this method also includes:
The virtual machine for the task that computing user is submitted averagely performs speed according to single-length fixed point instruction
(MIPS) size ascending order arrangement.
10. the method according to any one of Claims 1 to 5, it is characterised in that virtual when being assigned to
When the task of machine does not complete computing in operation threshold duration, methods described also includes:
Stop the virtual machine continuing not completing the task of computing described in computing in operation threshold duration, and will
The task for stopping computing being loaded into the end of priority level sequence;
Complete after the computing except other tasks of the stopping computing of the task, then to coming the priority level
The task of the stopping computing of sequence end carries out computing.
11. the method according to any one of Claims 1 to 5, it is characterised in that described using greed
The traversal that algorithm carries out the corresponding total utility function of each task is calculated.
12. the method according to any one of Claims 1 to 5, it is characterised in that before this method also
Including:
Estimate unit using operation threshold duration as resource, the size for each task that user is submitted divided by
Resource estimates the business of unit acquisition, and required resource is estimated as the task is corresponding;
By user submit all tasks it is corresponding estimate needed for resource add up, acquisition establishment computing user
Computer resource needed for the virtual machine of submission task.
13. the method according to any one of Claims 1 to 5, it is characterised in that this method also includes:
Port flow, and/or connection number to all resource nodes are monitored, for according to default
Strategy is adjusted to the port flow, and/or connection number of each resource node.
14. a kind of device for realizing task scheduling, it is characterised in that including:Total utility function unit,
Travel through computing unit and task allocation unit;Wherein,
Total utility function unit is used for, according to the effectiveness of the corresponding time utility of each task pre-established
The utility function, and/or each resource section of function, and/or the corresponding reliability effectiveness of each resource node
The utility function of the corresponding security effectiveness of point, and/or the effectiveness letter of the corresponding priority effectiveness of each task
Number builds each corresponding total utility function of task;
Traversal computing unit is used for, each task submitted to user, and traversal calculating task is intended being assigned to void
The value of the total utility function of task during plan machine;
Task allocation unit is used for, to each task, it is determined that traversal calculates the corresponding total utility letter of the task
Several maximum occurrences, the total utility function value virtual machine that task is intended being assigned to when maximum is appointed as computing
The virtual machine of business.
15. device according to claim 14, it is characterised in that
The corresponding time utility of each task is included in the total utility function that total utility function unit is set up
Utility function when, the utility function of the corresponding time utility of each task includes:
The default expectation run time of current task and the time difference of task submission time are calculated, calculating is obtained
The time difference obtained is used as the tasks carrying time limit;Determine described in when task is completed within the tasks carrying time limit
The utility function value of time utility is 1;Determine that task does not complete when institute within the tasks carrying time limit
The utility function value for stating time utility is 0;
It is corresponding reliable comprising each resource node in the total utility function that total utility function unit is set up
During the utility function of property effectiveness, the effect of the reliability effectiveness of the corresponding resource node of each resource node
Included with function:
It is determined that being assigned to the number of tasks n of resource nodeTThe virtual machine number n included with the resource nodeM;With
The coefficient of reliability pre-set as the utility function of reliability effectiveness as the truth of a matter, with the distribution of determination
To the number of tasks n of resource nodeTThe virtual machine number n included with resource nodeMOn be used as index parameters, structure
Build the utility function of the reliability effectiveness;
It is safe accordingly comprising each resource node in the total utility function that total utility function unit is set up
During the utility function of property effectiveness, the effect of the security effectiveness of the corresponding resource node of each resource node
Included with function:
It is two or more safe classes to divide all resource nodes according to predetermined level strategy;To work as
Preceding resource node is randomly assigned a safe class from two or more safe classes of division;
Safe class according to being randomly assigned for Current resource node set up Current resource node with safety etc.
The utility function for the security effectiveness that level is directly proportional;
The corresponding priority effect of each task is included in the total utility function that total utility function unit is set up
During utility function, the utility function of the corresponding priority effectiveness of each task includes:
The data class included according to current task sets the priority of current task;According to the current of setting
The priority level of task, sets each corresponding equivalent coefficient of priority level, with the grade system of setting
Count the utility function of the priority effectiveness as current task;
The equivalent coefficient is used for the priority for distinguishing the corresponding task of each species data;
The coefficient of reliability is is less than 1 number more than 0.
16. the device according to claim 11 or 15, it is characterised in that the traversal calculates single
Member specifically for,
The each task submitted to user, calculate the corresponding time utility of the task utility function it is all
The utility function of the reliability effectiveness of resource node where the virtual machine that value, and/or task plan are assigned to
All values, and/or task intend resource node where the virtual machine that is assigned to security effectiveness effect
With all values of function, and/or all values of the utility function of priority effectiveness;
To the utility function of each species included in total utility function, calculated each time according to combination
A value of all values of the utility function of each species is selected during total utility function;
All combinations to being selected according to combination, respectively each utility function to selecting each time
Value added up, obtain total utility function value.
17. device according to claim 16, it is characterised in that the device also includes setting weight
Unit, before the value for each utility function to selection add up,
For the utility function for setting up in total utility function the corresponding time utility of each task included,
And/or the utility function, and/or each resource node of each corresponding reliability effectiveness of resource node are corresponding
The utility function of security effectiveness, and/or the utility function of the corresponding priority effectiveness of each task according to
Default Weight Algorithm sets corresponding weight respectively.
18. the device according to claims 14 or 15, it is characterised in that the device also includes appointing
It is engaged in sequencing unit, for the sequence of all tasks for submitting user according to the priority level of task
It is ranked up, according to the total utility function of the order calculating task of task priority from high to low.
19. the device according to claims 14 or 15, it is characterised in that the device also includes void
Plan machine sequencing unit, the virtual machine of the task for computing user to be submitted is put down according to single-length fixed point instruction
It is performed both by the size ascending order arrangement of speed (MIPS).
20. the device according to claims 14 or 15, it is characterised in that the device also includes fortune
Adjustment unit is calculated, for when being assigned to the task of virtual machine and not completing computing in operation threshold duration,
Stop the virtual machine continuing not completing the task of computing described in computing in operation threshold duration, and will stop
The task of computing is loaded into the end of priority level sequence;Completion removes its of the task of stopping computing
After the computing of his task, then to the task for the stopping computing for coming the priority level sequence end
Carry out computing.
21. the device according to claims 14 or 15, it is characterised in that the device also includes obtaining
Resource unit is taken, for estimating unit using operation threshold duration as resource, each that user is submitted
The size divided by resource of business estimate the business of unit acquisition, and required resource is estimated as the task is corresponding;
By user submit all tasks it is corresponding estimate needed for resource add up, acquisition establishment computing user
Computer resource needed for the virtual machine of submission task.
22. the device according to claims 14 or 15, it is characterised in that the device also includes prison
Survey unit, for the port flow to all resource nodes, and/or connection number be monitored, with
The port flow of each resource node, and/or connection number are adjusted according to preset strategy.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610181930.0A CN107239336B (en) | 2016-03-28 | 2016-03-28 | Method and device for realizing task scheduling |
PCT/CN2017/076934 WO2017167025A1 (en) | 2016-03-28 | 2017-03-16 | Method and device for realizing task scheduling, and computer storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610181930.0A CN107239336B (en) | 2016-03-28 | 2016-03-28 | Method and device for realizing task scheduling |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107239336A true CN107239336A (en) | 2017-10-10 |
CN107239336B CN107239336B (en) | 2022-09-09 |
Family
ID=59963418
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610181930.0A Active CN107239336B (en) | 2016-03-28 | 2016-03-28 | Method and device for realizing task scheduling |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN107239336B (en) |
WO (1) | WO2017167025A1 (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107885589A (en) * | 2017-11-22 | 2018-04-06 | 链家网(北京)科技有限公司 | A kind of job scheduling method and device |
CN108287666A (en) * | 2018-01-16 | 2018-07-17 | 中国人民公安大学 | Date storage method and device for cloud storage environment |
CN108920269A (en) * | 2018-07-19 | 2018-11-30 | 中国联合网络通信集团有限公司 | The dispatching method and device of the I/O transformation task of container |
CN111143037A (en) * | 2019-12-31 | 2020-05-12 | 联想(北京)有限公司 | Virtual machine resource allocation method, equipment, system and storage medium |
CN113992691A (en) * | 2021-12-24 | 2022-01-28 | 苏州浪潮智能科技有限公司 | Method, device and equipment for distributing edge computing resources and storage medium |
CN115168017A (en) * | 2022-09-08 | 2022-10-11 | 天云融创数据科技(北京)有限公司 | Task scheduling cloud platform and task scheduling method thereof |
CN115686865A (en) * | 2022-11-18 | 2023-02-03 | 天河超级计算淮海分中心 | Super-computation node resource allocation system based on multi-scenario application |
Families Citing this family (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108595249A (en) * | 2018-05-02 | 2018-09-28 | 联想(北京)有限公司 | A kind of virtual machine method for scheduling task and electronic equipment |
CN110008026A (en) * | 2019-04-09 | 2019-07-12 | 中国科学院上海高等研究院 | Job scheduling method, device, terminal and the medium divided equally based on additional budget |
CN110717662B (en) * | 2019-09-27 | 2022-10-28 | 苏州达家迎信息技术有限公司 | Task allocation method, device, equipment and storage medium |
CN111124832A (en) * | 2019-12-25 | 2020-05-08 | 青梧桐有限责任公司 | Data monitoring method and device, electronic equipment and storage medium |
CN111309373B (en) * | 2020-01-19 | 2023-10-17 | 北京戴纳实验科技有限公司 | Method for flexibly configuring personage rights, business processes and roles |
CN111585818B (en) * | 2020-05-11 | 2021-05-04 | 苏州乐米凡电气科技有限公司 | System and method for distributing coefficients of user information based on service quality |
CN112130978A (en) * | 2020-09-29 | 2020-12-25 | 中国船舶重工集团公司第七二四研究所 | Unmanned platform-borne multifunctional radar task comprehensive priority calculation method |
CN113760493B (en) * | 2020-11-05 | 2024-05-17 | 北京沃东天骏信息技术有限公司 | Job scheduling method and device |
CN112954022A (en) * | 2020-12-29 | 2021-06-11 | 广东电网有限责任公司电力科学研究院 | Multi-concurrency real-time communication method and device based on intelligent substation |
CN112732437B (en) * | 2020-12-30 | 2023-08-22 | 科来网络技术股份有限公司 | Efficient dynamic equilibrium distributed task scheduling method and system |
CN117687873B (en) * | 2023-12-20 | 2024-04-30 | 中安华邦(北京)安全生产技术研究院股份有限公司 | AI-based safety information construction method and system |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101692208A (en) * | 2009-10-15 | 2010-04-07 | 北京交通大学 | Task scheduling method and task scheduling system for processing real-time traffic information |
CN102780759A (en) * | 2012-06-13 | 2012-11-14 | 合肥工业大学 | Cloud computing resource scheduling method based on scheduling object space |
CN102904963A (en) * | 2012-10-25 | 2013-01-30 | 上海电机学院 | Method and system for cloud service management based on cloud model |
CN103218737A (en) * | 2013-04-19 | 2013-07-24 | 湖南大学 | Multi-dimensional resource pricing method in mobile cloud computing environment based on bilateral market |
US8875143B2 (en) * | 2009-12-31 | 2014-10-28 | Bmc Software, Inc. | Utility-optimized scheduling of time-sensitive tasks in a resource-constrained environment |
CN104143042A (en) * | 2014-06-28 | 2014-11-12 | 中国人民解放军国防科学技术大学 | Method for deciding agile satellite earth observation task pretreatment scheme |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060168587A1 (en) * | 2005-01-24 | 2006-07-27 | Shahzad Aslam-Mir | Interoperable communications apparatus and method |
CN103699446B (en) * | 2013-12-31 | 2017-02-15 | 南京信息工程大学 | Quantum-behaved particle swarm optimization (QPSO) algorithm based multi-objective dynamic workflow scheduling method |
-
2016
- 2016-03-28 CN CN201610181930.0A patent/CN107239336B/en active Active
-
2017
- 2017-03-16 WO PCT/CN2017/076934 patent/WO2017167025A1/en active Application Filing
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101692208A (en) * | 2009-10-15 | 2010-04-07 | 北京交通大学 | Task scheduling method and task scheduling system for processing real-time traffic information |
US8875143B2 (en) * | 2009-12-31 | 2014-10-28 | Bmc Software, Inc. | Utility-optimized scheduling of time-sensitive tasks in a resource-constrained environment |
CN102780759A (en) * | 2012-06-13 | 2012-11-14 | 合肥工业大学 | Cloud computing resource scheduling method based on scheduling object space |
CN102904963A (en) * | 2012-10-25 | 2013-01-30 | 上海电机学院 | Method and system for cloud service management based on cloud model |
CN103218737A (en) * | 2013-04-19 | 2013-07-24 | 湖南大学 | Multi-dimensional resource pricing method in mobile cloud computing environment based on bilateral market |
CN104143042A (en) * | 2014-06-28 | 2014-11-12 | 中国人民解放军国防科学技术大学 | Method for deciding agile satellite earth observation task pretreatment scheme |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107885589A (en) * | 2017-11-22 | 2018-04-06 | 链家网(北京)科技有限公司 | A kind of job scheduling method and device |
CN108287666A (en) * | 2018-01-16 | 2018-07-17 | 中国人民公安大学 | Date storage method and device for cloud storage environment |
CN108287666B (en) * | 2018-01-16 | 2021-01-26 | 中国人民公安大学 | Data storage method and device for cloud storage environment |
CN108920269A (en) * | 2018-07-19 | 2018-11-30 | 中国联合网络通信集团有限公司 | The dispatching method and device of the I/O transformation task of container |
CN111143037A (en) * | 2019-12-31 | 2020-05-12 | 联想(北京)有限公司 | Virtual machine resource allocation method, equipment, system and storage medium |
CN111143037B (en) * | 2019-12-31 | 2023-11-21 | 联想(北京)有限公司 | Virtual machine resource allocation method, device, system and storage medium |
CN113992691A (en) * | 2021-12-24 | 2022-01-28 | 苏州浪潮智能科技有限公司 | Method, device and equipment for distributing edge computing resources and storage medium |
CN115168017A (en) * | 2022-09-08 | 2022-10-11 | 天云融创数据科技(北京)有限公司 | Task scheduling cloud platform and task scheduling method thereof |
CN115686865A (en) * | 2022-11-18 | 2023-02-03 | 天河超级计算淮海分中心 | Super-computation node resource allocation system based on multi-scenario application |
Also Published As
Publication number | Publication date |
---|---|
WO2017167025A1 (en) | 2017-10-05 |
CN107239336B (en) | 2022-09-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107239336A (en) | A kind of method and device for realizing task scheduling | |
CN106790726B (en) | Priority queue dynamic feedback load balancing resource scheduling method based on Docker cloud platform | |
CN104102543B (en) | The method and apparatus of adjustment of load in a kind of cloud computing environment | |
He et al. | Improving resource utilisation in the cloud environment using multivariate probabilistic models | |
CN102696000B (en) | Methods and apparatus for coordinated energy management in virtualized data centers | |
CN110221915B (en) | Node scheduling method and device | |
CN104023042B (en) | Cloud platform resource scheduling method | |
CN103595651B (en) | Distributed data stream processing method and system | |
CN110362407A (en) | Computing resource dispatching method and device | |
CN106406987A (en) | Task execution method and apparatus in cluster | |
US10157155B2 (en) | Operating system-managed interrupt steering in multiprocessor systems | |
CN103744808B (en) | A kind of method and apparatus for being used to control I/O to ask | |
WO2020248226A1 (en) | Initial hadoop computation task allocation method based on load prediction | |
CN108595567A (en) | A kind of merging method of small documents, device, equipment and readable storage medium storing program for executing | |
Amalarethinam et al. | Priority based performance improved algorithm for meta-task scheduling in cloud environment | |
CN115981843A (en) | Task scheduling method and device in cloud-edge cooperative power system and computer equipment | |
Zhang et al. | An energy-aware host resource management framework for two-tier virtualized cloud data centers | |
CN107273527A (en) | A kind of Hadoop clusters and distributed system | |
CN106537323B (en) | Storage device access is reconciled | |
CN107589980A (en) | A kind of dispatching method of cloud computing resources | |
US20080195447A1 (en) | System and method for capacity sizing for computer systems | |
CN110308991A (en) | A kind of data center's energy conservation optimizing method and system based on Random Task | |
CN110069319A (en) | A kind of multiple target dispatching method of virtual machine and system towards cloudlet resource management | |
CN110413393A (en) | Cluster resource management method, device, computer cluster and readable storage medium storing program for executing | |
CN106227600B (en) | A kind of multidimensional virtual resource allocation method based on Energy-aware |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |