CN104657221B - The more queue flood peak staggered regulation models and method of task based access control classification in a kind of cloud computing - Google Patents
The more queue flood peak staggered regulation models and method of task based access control classification in a kind of cloud computing Download PDFInfo
- Publication number
- CN104657221B CN104657221B CN201510108896.XA CN201510108896A CN104657221B CN 104657221 B CN104657221 B CN 104657221B CN 201510108896 A CN201510108896 A CN 201510108896A CN 104657221 B CN104657221 B CN 104657221B
- Authority
- CN
- China
- Prior art keywords
- task
- resource
- queue
- usage amount
- mem
- 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.)
- Active
Links
Landscapes
- Debugging And Monitoring (AREA)
Abstract
The more queue flood peak staggered regulation models and method classified the invention discloses task based access control in a kind of cloud computing, it is characterised in that: including task manager, local resource manager, global resource manager and scheduler;First according to task to the conditions of demand of resource, divide a task into CPU intensive type, I/O intensity and three queues of memory-intensive, and resource is ranked up by CPU, I/O and memory loading condition, the resource that is staggered when task schedule uses peak, a certain parameter intensive task is dispatched to the resource of the index light load, such as by CPU intensive type task schedule to the lower resource of cpu busy percentage.The present invention can effectively realize load balancing, improve dispatching efficiency and resource utilization.
Description
Technical field
The more queue flood peak staggered regulation models and method classified the present invention relates to task based access control in a kind of cloud computing.
Background technique
Application task in cloud computing has diversity, and the demand to resource also has very big difference, and some is to storage demand
Larger, some requires computing capability, that is, CPU, some be then it is data-intensive, i.e., its I/O is obvious.Task it is more
Sample and load imbalance will cause to the demand difference of resource.On the other hand, resource and its load have a lot dynamically and not true
Factor is determined, if the load of resource node is dynamic change at any time, with the variation resource request in time, season, festivals or holidays
Amount can also change;And resource itself also has many variations, may have resource to be added or exit at any time, these will all will lead to
A series of problems.If excessive resource node load too low, undoubtedly will cause the wasting of resources;If load too high, just
It will affect the performance of its top service.The above can all lead to load imbalance, and influence user satisfaction and the utilization of resources
Rate.
The method for realizing load balancing in cloud computing at present is but the virtual machine by the way of virtual machine (vm) migration mostly
The expense of migration can be bigger, so if considering that the equalization problem of load will obtain better effect in resource tasks scheduling
Fruit.And existing research about scheduling aspect in cloud computing or it is the migration scheduling to virtual resource or is only from task
Angle carry out the optimizing research of some task schedules.And the diversity of task and the dynamic of resource make in this way in cloud computing
The dispatching method of single optimization is extremely limited.Therefore, the dynamic of the diversity for cloud task and resource load proposes
It will be extremely necessary for being able to achieve load balancing and improving the dispatching method of scheduling performance.
About the research of task schedule in cloud computing, three classes are broadly divided into according to regulation goal: first is that being with scheduling time
It is main, including response time, optimal span and deadline etc.;Second is that based on system performance, such as load balancing and the utilization of resources
Rate etc.;Third is that the optimization of multiple target combines economic cost, Qos, energy consumption etc., introduces individually below other than the above target
Three kinds of task schedules:
1) using scheduling time as main target:
With scheduling time be main syllabus target research mainly by some heuritic approaches, intelligent optimization algorithm etc. to times
Business scheduling is optimized from algorithm level, dispatches the relevant time to reduce;Document [1] " Tsai C, Huang W, Chiang
M.A Hyper-Heuristic Scheduling Algorithm for Cloud ", IEEE TRANSACTIONS ON
CLOUD COMPUTING, 2014,2 (2) propose that a kind of super heuritic approach, main target are to realize optimal span.Document
[2]“Tang Z,Jiang L,Zhou J.A self-adaptive scheduling algorithm for reduce
Start time ", Future Generation Computer Systems, 2015,43 propose one kind in Hadoop platform
Adaptive scheduling algorithm, main target are to reduce the deadline.Document [3] " Tripathy B, Dash S, Padhy S
K.Dynamic task scheduling using a directed neural network ", Journal of
Parallel and Distributed Computing, 2015,75 the direct Optimizing Search algorithm (DSO) having proposed base
Neural network proposition three-layer artificial neural network (ANN) is combined on plinth and two dispatching algorithms of RBF neural, main target are
Realize optimal span.Document [4] " Topcuoglu H, Hariri S, Wu M.Performance-effective and low-
Complexity task scheduling for heterogeneous computing ", IEEE Transactions on
Parallel and Distributed Systems, 2002,13 (3) are to meet the needs of high-performance and fast dispatch, are proposed
Two dispatching algorithms, first is the task priority scheduling for selecting to complete earliest every time, second is critical path algorithm
(CPOP) to minimize total execution time of critical path task as main target.
2) using system performance as main target:
It is at present that main syllabus target is dispatched primarily directed to load balancing and system resource benefit with system performance in cloud computing
With some improvement of rate etc..Document [5] " Li C C, Wang K..An SLA-aware load balancing
Scheme for cloud datacenters ", 2014International Conference on Information
Networking (ICOIN) .IEEE, 2014 propose that a two-stage centralization load balancing frame (has preferable scalability
And high availability), and a Dynamic Load-balancing Algorithm neural network based is proposed, according to loading index and neural network
Index distributes weight to each VM, and to meet SLA, dynamic adjustment updates the weight of each VM.Document [6] " Mesbahi
M,Rahmani A M,Chronopoulos A T.Cloud light weight:A new solution for load
Balancing in cloud computing ", 2014International Conference on Data Science&
Engineering (ICDSE) .IEEE, 2014 propose a load-balancing algorithm, and to balance VM load and guaranteed qos, it is dropped
The quantity of low VM migration, reduces the transit time during task execution.Document [7] " Wen Y F, Chang C
L.Load balancing job assignment for cluster-based cloud computing ", 2014Sixth
International Conference on Ubiquitous and Future Networks (ICUFN) .IEEE, 2014 is same
When consider the processing of network and system load balancing, distribute into similar node task to processing and the smallest chain of transmission delay
It connects, which is combined with FCFS, Min-Min and Min-Max algorithm.Document [8] " Wang T, Liu Z, Chen Y, et
al.Load Balancing Task Scheduling Based on Genetic Algorithm in Cloud
Computing ", 2014IEEE 12th International Conference on Dependable, Autonomic and
Secure Computing (DASC) .IEEE, 2014 be to realize the load balancing of cross-node in cloud computing and reduce average complete
Time proposes to realize in conjunction with genetic algorithm.Document [9] " Chen H, Wang F, Helian N, et al.User-
priority guided min-min scheduling algorithm for load balancing in cloud
Computing ", 2013National Conference on Parallel Computing Technologies
(PARCOMPTECH) .IEEE, 2013 propose a kind of improved Min-Min algorithm based on User Priority, to realize load
Balanced, optimal span and raising resource utilization;Assuming that user can select different grades of service according to their own needs, accordingly
Cost is also different, that is, marks off some VIP users and resource carrys out priority scheduling, but this method complexity is relatively high.
3) Multiobjective Optimal Operation:
More researchs are the research of Multiobjective Optimal Operation.Such as take into account QoS constraint, energy consumption, economic cost and systematicness
Energy is equal.Document [10] " Hu M, Veeravalli B.Dynamic Scheduling of Hybrid Real-Time Tasks
On Clusters ", IEEE TRANSACTIONS ON COMPUTERS, DECEMBER 2014,63 (12) are directed to can in cluster
Segmentation and indivisible two kinds of real-time tasks propose a kind of dynamic realtime dispatching algorithm, and main target is to ensure QoS.Document
[11]“Hung P P,Bui T A,Huh E N.A New Approach for Task Scheduling Optimization
In Mobile Cloud Computing ", Frontier and Innovation in Future Computing and
Communications.Springer Netherlands, 2014 propose a kind of client and cloud for mobile cloud computing
Co-scheduling, main target be reduce processing time and cloud service cost.Document [12] " Xiaoyong T, Li K,
Zeng Z,et al.A novel security-driven scheduling algorithm for precedence-
Constrained tasks in heterogeneous distributed systems ", IEEE Transactions on
Computers, task and risk probability of 2011,60 (7) based on priority restrictions propose the scheduling driven safely and calculate
Method, main target are to reduce the deadline and enhance safety.Document [13] " Liu Z, Qu W, Liu W, et
al.Resource preprocessing and optimal task scheduling in cloud computing
Environments ", Concurrency and Computation:Practice and Experience, 2014 propose
One minimizes task length by division of resources and the method for budget, to reduce task execution time, improves the utilization of resources
Rate.This method considers the case where resource.Other major parts do not account for resource, only optimize to task.Document [14]
“Zhu Q,Agrawal G.Resource provisioning with budget constraints for adaptive
Applications in cloud environments ", IEEE TRANSACTIONS ON SERVICES COMPUTING,
2012,5 (4) propose the dynamic resource scheduling algorithm that a mimo feedback controls in a cloud computing, by strong
Chemistry is practised to adjust auto-adaptive parameter, and optimal application benefit is realized under time-constrain to ensure;Consider the execution of task
Time, resources costs and utilization rate (CPU, Memory).
Separately have and comprehensively considers the comprehensive algorithm of the above target.Document [15] " Wang Y, Shi W.Budget-Driven
Scheduling Algorithms for Batches of MapReduce Jobs in Heterogeneous Clouds ",
IEEE TRANSACTIONS ON CLOUD COMPUTING, batch of 2014,2 (3) for the MapReduce operation on isomery cloud
It is secondary, propose a kind of greedy dispatching algorithm of budget driving, it is contemplated that Deadline constraint and economic cost.Document [16]
“Rodriguez M A,Buyya R.Deadline Based Resource Provisioning and Scheduling
Algorithm for Scientific Workflows on Clouds ", IEEE TRANSACTIONS ON CLOUD
COMPUTING, 2014,2 (2) propose a resources and scheduling strategy for scientific workflow, and are based on meta-heuristic
Optimisation technique proposes a meta-heuristic particle swarm optimization algorithm, to reduce the executory cost of overall workflow, meets
Deadline constraint.
In conclusion existing research is primarily present following problems:
(1) many methods need to be by communicating, monitoring and controlling in existing research method, and algorithm complexity is also relatively high,
Certain delay can be generated in this way, and higher complexity may be brought a negative impact;
(2) existing many methods will be migrated using VM, but this migration cost may be relatively high;
(3) many load-balancing methods be the request of VM is predicted based on load estimation, but due in cloud computing task it is negative
The diversity of load and various complexity of isomerization hardware environment, so that the request of prediction VM is very difficult;
(4) method of many task schedules is only to optimize to method for scheduling task itself, does not account for task pair
The demand difference of resource and the dynamic of resource load.
Summary of the invention
To solve deficiency in the prior art, more queues that the present invention provides task based access control classification in a kind of cloud computing are avoided the peak hour
Scheduling model and method solve the dynamic of resource and the diversity of task and its demand difference to resource in cloud computing,
The problem of may result in load imbalance, influencing dispatching efficiency and resource utilization.
In order to achieve the above objectives, the present invention adopts the following technical scheme:
More queue flood peak staggered regulation models of task based access control classification in a kind of cloud computing, which is characterized in that including task management
Device, local resource manager, global resource manager and scheduler;
The task manager is responsible for managing the task requests that user submits, and will according to demand difference of the task to resource
Task divides;
The local resource manager is responsible for the monitoring and management of local resource node, periodically monitors local resource
Loading condition, and these information are committed to the global resource manager;
The global resource manager periodically collects the monitoring information of local resource manager, and to resource usage amount
Situation is ranked up;
The scheduler according to after division task and resource usage amount situation carry out task resource scheduling.
More queue flood peak staggered regulation models that task based access control is classified in a kind of cloud computing above-mentioned, it is characterized in that: the resource
For resources of virtual machine.
More queue flood peak staggered regulation models that task based access control is classified in a kind of cloud computing above-mentioned, it is characterized in that: the resource
Including parameter CPU, I/O and Mem memory.
More queue flood peak staggered regulation models that task based access control is classified in a kind of cloud computing above-mentioned, it is characterized in that: the local
The loading condition of resource includes cpu busy percentage, I/O waiting time and Mem usage amount.
It is special based on the dispatching method of more queue flood peak staggered regulation models of task based access control classification in a kind of cloud computing above-mentioned
Sign is: comprising steps of
1) the definition description of resource and task: setting in current cloud computing system has N number of resource U={ U1,U2,...,Ui,
...UNAnd K task T={ T1,T2,...,Tj,...TK};
Cloud resource definition: Ui=(Ci,Oi,Mi);Wherein, parameter Ci,Oi,MiWhen respectively representing cpu busy percentage, I/O waiting
Between and Mem usage amount;
Cloud task definition: Tj=(Cj,Lj,Mj,Dj), wherein first three parameter Cj,Lj,MjRespectively represent user's application
Cpu busy percentage, task size and Mem usage amount, DjFor task deadline;
The I/O usage amount of task is defined as:
2) local resource manager periodically reads the cpu busy percentage of native virtual machine, I/O waiting time and Mem usage amount,
And these information are committed to global resource manager;
3) global resource manager presses cpu busy percentage, I/O waiting time and Mem usage amount three to all resources respectively
Parameter sorts from small to large, forms three resource queue QC、QOAnd QM, it is expressed as follows:
QC={ U1,U2,...UiC,...UN} (1)
QO={ U1,U2,...UiO,...UN} (2)
QM={ U1,U2,...UiM,...UN} (3)
4) task is divided according to demand difference of the task to resource: counts the cpu busy percentage C of cloud computing systemS、I/O
Usage amount OSWith Mem usage amount MS, then for each cloud task Tj, calculate its cpu busy percentage Cj, I/O usage amount OjAnd Mem
Usage amount MjWith the C of cloud computing systemS、OSAnd MSRatio C, O and M, take in three ratios maximum one as the task
Belonging kinds Tjh:
According to the belonging kinds T of taskjhIt is a that K task is divided into a CPU intensive type, b I/O intensity and K-a-b
Three queue Q of Mem intensityTC、QTOAnd QTM, it is expressed as follows:
QTC={ T1,T2,...,TjC,...Ta} (5)
QTO={ Ta+1,Ta+2,...TjO,...Ta+b} (6)
QTM={ Ta+b+1,Ta+b+2,...,TjM,...,TK-a-b} (7)
5) task queue of the resource queue and step 4) foundation obtained based on step 3), scheduler are avoided the peak hour using more queues
The scheduling of dispatching method progress task resource.
More queue flood peak staggered regulation methods that task based access control is classified in a kind of cloud computing above-mentioned, it is characterized in that: more teams
Column flood peak staggered regulation method is by CPU intensive type task schedule to the lower resource of cpu busy percentage, and I/O intensive task is dispatched to
I/O waiting time shorter resource, Mem intensive task are dispatched to Mem and use less resource.
Advantageous effects of the invention: the present invention according to task to the conditions of demand of resource, divide a task into CPU
Intensive, I/O intensity and three queues of Mem memory-intensive, and resource is arranged by CPU, I/O and Mem loading condition
Sequence, when task schedule, are staggered resource using peak, a certain parameter intensive task are dispatched to the resource of the index light load;
Can consider the diversity of task, reflection task to the demand difference of resource and consider the load condition of resource, and method compared with
Simply, prediction load is not needed, migration VM is not needed because the method is easily achieved yet and is not related to differential, integral operation, it is complicated
Spend it is lower, effectively realization load balancing, improve dispatching efficiency and resource utilization.
Detailed description of the invention
Fig. 1 is more queue flood peak staggered regulation models that task based access control is classified in cloud computing;
Fig. 2 is more queue flood peak staggered regulation method schematic diagrams that task based access control is classified in cloud computing.
Specific embodiment
The invention will be further described below in conjunction with the accompanying drawings.Following embodiment is only used for clearly illustrating the present invention
Technical solution, and not intended to limit the protection scope of the present invention.
As shown in Figure 1, more queue flood peak staggered regulation models that task based access control is classified in a kind of cloud computing, including task management
Device, local resource manager, global resource manager and scheduler;
Task manager is responsible for managing the task requests that user submits, and is divided according to it to the demand difference of resource
For three queues: CPU intensive type, I/O are intensive and Mem (memory) is intensive;
Local resource manager is responsible for the monitoring and management of local resource node, periodically monitors local virtual resource
CPU, I/O and Mem loading condition, and these information are committed to global resource manager;
Global resource manager periodically collects the monitoring information of local resource manager, and presses cpu busy percentage, I/O
Waiting time and Mem usage amount are from small to large ranked up resource, are divided into three queues.
The scheduling that scheduler is used to that task scheduling algorithm to be called to carry out task resource.
As shown in Fig. 2, a kind of dispatching method for more queue flood peak staggered regulation models that task based access control is classified in cloud computing, including
Step:
1) the definition description of resource and task:
Assuming initially that has N number of resource U={ U in current cloud computing system1,U2,...,Ui,...UNAnd K task T=
{T1,T2,...,Tj,...TK}.Cloud resource of the invention refers mainly to resources of virtual machine.
In cloud computing, virtual technology can monitor the service condition of resource, if user task in practical implementation
CPU and the usage amounts such as Mem exceed the quantity of user's application, system will cut off the execution of user task, be considered as and execute failure.Cause
This is present invention assumes that the resource requirement information that user submits is accurate.
Cloud resource definition: for each of cloud computing virtual resource, it is defined by main three parameters CPU, I/O
It is formed with Mem, i.e. Ui=(Ci,Oi,Mi);Wherein, parameter Ci,Oi,MiRespectively represent cpu busy percentage, I/O waiting time and Mem
Usage amount.
Cloud task definition: Tj=(Cj,Lj,Mj,Dj), wherein first three parameter Cj,Lj,MjRespectively represent the CPU of user's application
Utilization rate, task size and Mem usage amount, DjFor task deadline.
The I/O usage amount of task is defined as:
2) local resource manager periodically reads the cpu busy percentage of native virtual machine, I/O waiting time and Mem usage amount,
And these information are committed to global resource manager;
3) global resource manager presses cpu busy percentage, I/O waiting time and Mem usage amount three to all resources respectively
Parameter sorts from small to large, forms three resource queue QC、QOAnd QM, it is expressed as follows:
QC={ U1,U2,...UiC,...UN} (1)
QO={ U1,U2,...UiO,...UN} (2)
QM={ U1,U2,...UiM,...UN} (3)
In view of resource quantity and dynamic problem, only all resources are ranked up herein, without classification.So three
It include all resources in a queue.
4) the cpu busy percentage C of cloud computing system is countedS, I/O usage amount OSWith Mem usage amount MS, then for each
Cloud task Tj, calculate its cpu busy percentage Cj, I/O usage amount OjWith Mem usage amount MjWith the C of cloud computing systemS、OSAnd MSRatio
Value C, O and M take the maximum one belonging kinds T as the task in three ratiosjh:
According to the belonging kinds T of taskjhIt is a that K task is divided into a CPU intensive type, b I/O intensity and K-a-b
Three queue Q of Mem intensityTC、QTOAnd QTM, it is expressed as follows:
QTC={ T1,T2,...,TjC,...Ta} (5)
QTO={ Ta+1,Ta+2,...TjO,...Ta+b} (6)
QTM={ Ta+b+1,Ta+b+2,...,TjM,...,TK-a-b} (7)
5) task queue of the resource queue and step 4) foundation obtained based on step 3), scheduler are avoided the peak hour using more queues
The scheduling of dispatching method progress task resource.
As shown in Fig. 2, flood peak staggered regulation, as its name suggests, the resource that is staggered in scheduling use peak.CPU intensive type is appointed
Business is dispatched to the lower resource of cpu busy percentage, and I/O intensive task is dispatched to I/O waiting time shorter resource, and Mem is intensive
Type task schedule to Mem use less resource.This method is to the use of the resources such as CPU, I/O and Mem in real active task
Do not conflict, can preferably realize load balancing.
The complexity of dispatching algorithm, which will run system, certain influence, and dispatching method used by this patent is simple,
It is not related to differential and integral operation, time complexity and space complexity are relatively low, it makes a concrete analysis of as follows:
1) algorithm analysis:
The method of the present invention time complexity is related with task number K with resource number N, wherein resource sort sections, the time
Complexity is O (NlogN), and the time complexity of flood peak staggered regulation algorithm is O (K), so total time complexity is O (NlogN
+K).But in fact, resource sequence can carry out simultaneously with dispatching algorithm, and resource sequence only periodically carries out, so practical
Time complexity be less than O's (NlogN+K).
For space complexity, the space complexity of resource sequence is O (1), and flood peak staggered regulation algorithm space complexity is O
(1), therefore total space complexity is also (1) O.
2) optimization analysis:
According to the principle of flood peak staggered regulation, three task queues can be dispatched to different resources simultaneously and execute, therefore theoretically
Ideally whole system improves the optimization for having three times, under worst case, considers under reset condition it is possible that three
The case where three tasks of queue are dispatched to the same resource simultaneously, this when is optimized for 0, so the optimization upper limit is 3 times, under
It is limited to 0.
But this worst case is to be likely to occur under initial conditions, with the implementation of the dispatching algorithm, system money
Source load will be more and more balanced, and this worst-status will not occur again, so actual optimization lower limit is greater than 0.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, without departing from the technical principles of the invention, several improvement and deformations can also be made, these improvement and deformations
Also it should be regarded as protection scope of the present invention.
Claims (3)
1. a kind of dispatching method for more queue flood peak staggered regulation models that task based access control is classified in cloud computing, which is characterized in that scheduling
Model includes task manager, local resource manager, global resource manager and scheduler;
The task manager is responsible for managing the task requests that user submits, and according to task to the demand difference of resource by task
It divides;The resource includes parameter CPU, I/O and Mem memory;
The local resource manager is responsible for the monitoring and management of local resource node, periodically monitors the load of local resource
Situation, and these information are committed to the global resource manager;The loading condition of the local resource includes that CPU is utilized
Rate, I/O waiting time and Mem usage amount;
The global resource manager periodically collects the monitoring information of local resource manager, and to resource usage amount situation
It is ranked up;
The scheduler according to after division task and resource usage amount situation carry out task resource scheduling;
Dispatching method comprising steps of
1) the definition description of resource and task: setting in current cloud computing system has N number of resource U={ U1,U2,...,Ui,...UNAnd
K task T={ T1,T2,...,Tj,...TK};
Cloud resource definition: Ui=(Ci,Oi,Mi);Wherein, parameter Ci,Oi,MiRespectively represent cpu busy percentage, the I/O waiting time and
Mem usage amount;
Cloud task definition: Tj=(Cj,Lj,Mj,Dj), wherein first three parameter Cj,Lj,MjRespectively represent the CPU benefit of user's application
With rate, task size and Mem usage amount, DjFor task deadline;
The I/O usage amount of task is defined as:
2) local resource manager periodically reads the cpu busy percentage of native virtual machine, I/O waiting time and Mem usage amount, and will
These information are committed to global resource manager;
3) global resource manager presses three cpu busy percentage, I/O waiting time and Mem usage amount parameters to all resources respectively
It sorts from small to large, forms three resource queue QC、QOAnd QM, it is expressed as follows:
QC={ U1,U2,...UiC,...UN} (1)
QO={ U1,U2,...UiO,...UN} (2)
QM={ U1,U2,...UiM,...UN} (3)
4) task is divided according to demand difference of the task to resource: counts the cpu busy percentage C of cloud computing systemS, I/O usage amount
OSWith Mem usage amount MS, then for each cloud task Tj, calculate its cpu busy percentage Cj, I/O usage amount OjWith Mem usage amount
MjWith the C of cloud computing systemS、OSAnd MSRatio C, O and M, take the maximum one ownership class as the task in three ratios
Other Tjh:
According to the belonging kinds T of taskjhK task is divided into a CPU intensive type, b I/O intensity and K-a-b Mem
Three queue Q of intensityTC、QTOAnd QTM, it is expressed as follows:
QTC={ T1,T2,...,TjC,...Ta} (5)
QTO={ Ta+1,Ta+2,...TjO,...Ta+b} (6)
QTM={ Ta+b+1,Ta+b+2,...,TjM,...,TK-a-b} (7)
5) task queue of the resource queue and step 4) foundation obtained based on step 3), scheduler use more queue flood peak staggered regulations
The scheduling of method progress task resource.
2. the dispatching party for more queue flood peak staggered regulation models that task based access control is classified in a kind of cloud computing according to claim 1
Method, it is characterized in that: the resource is resources of virtual machine.
3. the dispatching party for more queue flood peak staggered regulation models that task based access control is classified in a kind of cloud computing according to claim 1
Method, it is characterized in that: more queue flood peak staggered regulation methods be by CPU intensive type task schedule to the lower resource of cpu busy percentage,
I/O intensive task is dispatched to I/O waiting time shorter resource, and Mem intensive task is dispatched to Mem and uses less money
Source.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510108896.XA CN104657221B (en) | 2015-03-12 | 2015-03-12 | The more queue flood peak staggered regulation models and method of task based access control classification in a kind of cloud computing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510108896.XA CN104657221B (en) | 2015-03-12 | 2015-03-12 | The more queue flood peak staggered regulation models and method of task based access control classification in a kind of cloud computing |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104657221A CN104657221A (en) | 2015-05-27 |
CN104657221B true CN104657221B (en) | 2019-03-22 |
Family
ID=53248394
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510108896.XA Active CN104657221B (en) | 2015-03-12 | 2015-03-12 | The more queue flood peak staggered regulation models and method of task based access control classification in a kind of cloud computing |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104657221B (en) |
Families Citing this family (43)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105049536B (en) * | 2015-09-08 | 2018-04-06 | 南京大学 | SiteServer LBS and load-balancing method in IaaS cloud environment |
CN105224393B (en) * | 2015-10-15 | 2018-10-09 | 西安电子科技大学 | A kind of scheduling virtual machine mechanism of JT-CoMP under C-RAN frameworks |
CN106598707A (en) * | 2015-10-19 | 2017-04-26 | 沈阳新松机器人自动化股份有限公司 | Task scheduling optimization method |
CN105354085B (en) * | 2015-10-30 | 2019-03-15 | 广东石油化工学院 | A kind of cloud workflow job scheduling method |
CN105354084B (en) * | 2015-10-30 | 2018-12-18 | 浪潮(北京)电子信息产业有限公司 | A kind of CPU task immigration method and system based on bandwidth scheduling |
CN105389206B (en) * | 2015-11-02 | 2019-03-29 | 广东石油化工学院 | A kind of cloud computation data center resources of virtual machine quickly configuration method |
CN106713396B (en) * | 2015-11-17 | 2021-07-16 | 阿里巴巴集团控股有限公司 | Server scheduling method and system |
CN105471985A (en) * | 2015-11-23 | 2016-04-06 | 北京农业信息技术研究中心 | Load balance method, cloud platform computing method and cloud platform |
CN105808331A (en) * | 2016-02-29 | 2016-07-27 | 湖南蚁坊软件有限公司 | Server characteristic-based scheduling method |
CN105930214B (en) * | 2016-04-22 | 2019-04-26 | 广东石油化工学院 | A kind of mixed cloud job scheduling method based on Q study |
CN106126317A (en) * | 2016-06-24 | 2016-11-16 | 安徽师范大学 | It is applied to the dispatching method of virtual machine of cloud computing environment |
CN106406976A (en) * | 2016-07-21 | 2017-02-15 | 柏科数据技术(深圳)股份有限公司 | Method and apparatus for identifying IO intensive application in cloud computing environment |
CN106228314A (en) * | 2016-08-11 | 2016-12-14 | 电子科技大学 | The workflow schedule method of study is strengthened based on the degree of depth |
CN106385381B (en) * | 2016-08-23 | 2019-05-10 | 广东科学技术职业学院 | A kind of the scheduling of resource distribution method and its system of matching primitives |
CN106469193A (en) * | 2016-08-30 | 2017-03-01 | 北京航空航天大学 | Multi load metadata I/O service quality performance support method and system |
CN106502792B (en) * | 2016-10-20 | 2019-11-15 | 华南理工大学 | A kind of multi-tenant priority scheduling of resource method towards different type load |
CN108123987A (en) * | 2016-11-30 | 2018-06-05 | 华为技术有限公司 | The method and device of master scheduler is determined from cloud computing system |
CN106874112B (en) * | 2017-01-17 | 2020-04-28 | 华南理工大学 | Workflow backfilling method combined with load balancing |
CN107172193A (en) * | 2017-06-20 | 2017-09-15 | 郑州云海信息技术有限公司 | A kind of load-balancing method and its device based on cluster |
CN107479979B (en) * | 2017-08-31 | 2020-07-28 | 安徽江淮汽车集团股份有限公司 | CPU load rate optimization method and system of gearbox control unit |
CN107888660B (en) * | 2017-10-13 | 2021-06-18 | 杭州朗和科技有限公司 | Cloud service resource allocation method, medium, device and computing equipment |
CN107908466A (en) * | 2017-10-27 | 2018-04-13 | 南京理工大学 | A kind of fast dispatch method of BoT tasks under cloud environment |
CN108170523B (en) * | 2017-12-28 | 2021-05-04 | 合肥工业大学 | Random task sequence scheduling method for mobile cloud computing |
US10761891B2 (en) | 2018-04-05 | 2020-09-01 | International Business Machines Corporation | Workload management with data access awareness by aggregating file locality information in a computing cluster |
US10585714B2 (en) | 2018-04-05 | 2020-03-10 | International Business Machines Corporation | Workload management with data access awareness using an ordered list of hosts in a computing cluster |
US10768998B2 (en) * | 2018-04-05 | 2020-09-08 | International Business Machines Corporation | Workload management with data access awareness in a computing cluster |
CN108711007A (en) * | 2018-05-16 | 2018-10-26 | 国电南瑞南京控制系统有限公司 | A kind of multitask real-time scheduling method of energy integration collection system |
CN109032801B (en) * | 2018-07-26 | 2022-02-18 | 郑州云海信息技术有限公司 | Request scheduling method, system, electronic equipment and storage medium |
CN111045795A (en) * | 2018-10-11 | 2020-04-21 | 浙江宇视科技有限公司 | Resource scheduling method and device |
CN109309726A (en) * | 2018-10-25 | 2019-02-05 | 平安科技(深圳)有限公司 | Document generating method and system based on mass data |
CN109491761A (en) * | 2018-11-07 | 2019-03-19 | 中国石油大学(华东) | Cloud computing multiple target method for scheduling task based on EDA-GA hybrid algorithm |
CN109784663B (en) * | 2018-12-20 | 2022-11-25 | 西北大学 | Workflow scheduling method and device |
CN109819050A (en) * | 2019-03-07 | 2019-05-28 | 北京华安普特网络科技有限公司 | SiteServer LBS and method between multiserver |
TWI714078B (en) * | 2019-05-07 | 2020-12-21 | 國立高雄大學 | System and method for scheduling big data analysis platform based on deep learning |
CN110502321A (en) * | 2019-07-11 | 2019-11-26 | 新华三大数据技术有限公司 | A kind of resource regulating method and system |
CN110362411B (en) * | 2019-07-25 | 2022-08-02 | 哈尔滨工业大学 | CPU resource scheduling method based on Xen system |
CN110826145B (en) * | 2019-09-09 | 2020-08-28 | 西安工业大学 | Automobile multi-parameter operation condition design method based on heuristic Markov chain evolution |
US11954518B2 (en) * | 2019-12-20 | 2024-04-09 | Nvidia Corporation | User-defined metered priority queues |
CN111831436B (en) * | 2020-07-01 | 2024-07-30 | Oppo广东移动通信有限公司 | IO request scheduling method and device, storage medium and electronic equipment |
CN112905343B (en) * | 2021-02-09 | 2023-09-26 | 重庆大学 | Resource scheduling system based on load characteristics in industrial cloud environment |
CN114356531A (en) * | 2022-01-12 | 2022-04-15 | 重庆邮电大学 | Edge calculation task classification scheduling method based on K-means clustering and queuing theory |
TWI838000B (en) * | 2022-12-09 | 2024-04-01 | 財團法人工業技術研究院 | System, apparatus and method for cloud resource allocation |
CN117194053B (en) * | 2023-11-06 | 2024-08-09 | 北京宏数科技有限公司 | Cloud management method and system based on big data |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2007149224A1 (en) * | 2006-06-19 | 2007-12-27 | Diskeeper Corporation | Resource-based scheduler |
CN101604260A (en) * | 2009-07-08 | 2009-12-16 | 深圳先进技术研究院 | Supercomputer system and structure thereof and method for scheduling task |
CN101739292A (en) * | 2009-12-04 | 2010-06-16 | 曙光信息产业(北京)有限公司 | Application characteristic-based isomeric group operation self-adapting dispatching method and system |
CN103500123A (en) * | 2013-10-12 | 2014-01-08 | 浙江大学 | Parallel computation dispatch method in heterogeneous environment |
CN104065745A (en) * | 2014-07-07 | 2014-09-24 | 电子科技大学 | Cloud computing dynamic resource scheduling system and method |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9465663B2 (en) * | 2008-10-31 | 2016-10-11 | Synopsys, Inc. | Allocating resources in a compute farm to increase resource utilization by using a priority-based allocation layer to allocate job slots to projects |
-
2015
- 2015-03-12 CN CN201510108896.XA patent/CN104657221B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2007149224A1 (en) * | 2006-06-19 | 2007-12-27 | Diskeeper Corporation | Resource-based scheduler |
CN101604260A (en) * | 2009-07-08 | 2009-12-16 | 深圳先进技术研究院 | Supercomputer system and structure thereof and method for scheduling task |
CN101739292A (en) * | 2009-12-04 | 2010-06-16 | 曙光信息产业(北京)有限公司 | Application characteristic-based isomeric group operation self-adapting dispatching method and system |
CN103500123A (en) * | 2013-10-12 | 2014-01-08 | 浙江大学 | Parallel computation dispatch method in heterogeneous environment |
CN104065745A (en) * | 2014-07-07 | 2014-09-24 | 电子科技大学 | Cloud computing dynamic resource scheduling system and method |
Also Published As
Publication number | Publication date |
---|---|
CN104657221A (en) | 2015-05-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104657221B (en) | The more queue flood peak staggered regulation models and method of task based access control classification in a kind of cloud computing | |
Salot | A survey of various scheduling algorithm in cloud computing environment | |
CN102780759B (en) | Based on the cloud computing resource scheduling method in regulation goal space | |
Ebadifard et al. | A dynamic task scheduling algorithm improved by load balancing in cloud computing | |
Haris et al. | Mantaray modified multi-objective Harris hawk optimization algorithm expedites optimal load balancing in cloud computing | |
US20080104605A1 (en) | Methods and apparatus for dynamic placement of heterogeneous workloads | |
Liu et al. | A survey on virtual machine scheduling in cloud computing | |
Sonkar et al. | A review on resource allocation and VM scheduling techniques and a model for efficient resource management in cloud computing environment | |
Sharma et al. | An improved task allocation strategy in cloud using modified k-means clustering technique | |
Mousavinasab et al. | A bee colony task scheduling algorithm in computational grids | |
CN109815009A (en) | Scheduling of resource and optimization method under a kind of CSP | |
Chhabra et al. | QoS-aware energy-efficient task scheduling on HPC cloud infrastructures using swarm-intelligence meta-heuristics | |
Singh et al. | A comparative study of various scheduling algorithms in cloud computing | |
Singh | Genetic approach based optimized load balancing in cloud computing: a performance perspective | |
Ghafir et al. | Load balancing in cloud computing via intelligent PSO-based feedback controller | |
Venu et al. | Task scheduling in cloud computing: a survey | |
Ramezani et al. | Task scheduling in cloud environments: A survey of population‐based evolutionary algorithms | |
Srivastava et al. | An Energy‐Efficient Strategy and Secure VM Placement Algorithm in Cloud Computing | |
Shah et al. | Task Scheduling and Load Balancing for Minimization of Response Time in IoT Assisted Cloud Environments | |
Ilankumaran et al. | An Energy-Aware QoS Load Balance Scheduling Using Hybrid GAACO Algorithm for Cloud | |
Ramya et al. | Performance Improvement in Cloud Computing Environment by Load Balancing-A Comprehensive Review | |
Mahmoud et al. | A comparative study of heterogenous task-based scheduling techniques in a cloud environment | |
Wang | Improved Cat Swarm Optimization Algorithm for Load Balancing in the Cloud Computing Environment | |
Varghese et al. | Task scheduling and VM allocation in cloud computing: A survey | |
Rahman et al. | Group based resource management and pricing model in cloud computing |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |