CN104714621B - DVS scheduling algorithm based on partitioning operation system - Google Patents
DVS scheduling algorithm based on partitioning operation system Download PDFInfo
- Publication number
- CN104714621B CN104714621B CN201310688800.2A CN201310688800A CN104714621B CN 104714621 B CN104714621 B CN 104714621B CN 201310688800 A CN201310688800 A CN 201310688800A CN 104714621 B CN104714621 B CN 104714621B
- Authority
- CN
- China
- Prior art keywords
- voltage
- blood pressure
- pressure lowering
- dvs
- time
- 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
- Power Sources (AREA)
Abstract
The invention provides a DVS scheduling algorithm based on a partitioning operation system. According to the method, free time of a processor is dynamically estimated, and power consumption is effectively reduced at a small cost on the condition of ensuring high response speed of the processor; a data item of free task operation time t1 recorded according to partitioning before voltage reduction is additionally arranged in a task control block of a free task; whether the free task operation time t1 before voltage reduction meets a voltage switching condition is judged; when the free task operation time t1 meets the voltage switching condition, frequency reduction operation is executed until partitioning is finished; when partitioning is finished, frequency raising operation is executed. The problem of overheating, caused by high-speed computation, of the onboard embedded processor is solved, the service life of the processor is prolonged, and the fault rate of the processor is reduced.
Description
Technical field
The invention belongs to embedded OS field, is related to a kind of dynamic electric voltage grade for partition operating system and adjusts
Section DVS method for scheduling task.
Background technology
With the development of avlomcs system integration, the requirement of computer system operational capability is also higher and higher.For
This, airborne computer system using high performance hardware system so as to reach improve processing speed target.Meanwhile, computing system
Reliability it is increasingly important, airborne computer with the hardware and software redundancy of each level as cost realize improve reliability mesh
Mark.Unfortunately, whether high performance hardware system or redundancy backup are all greatly improved system energy consumption.Great number is
System power consumption increased the burden of electric power system, and the heat of generation becomes severe by hardware running environment, so as to reduce system
Overall life.DVS task schedulings are the important contents of operating system power managed, the power consumption pipe of processor when Study system runs
Reason technology.It reduces the mesh of system power dissipation by reducing DVS processor clock frequencies when computing device load is relatively low
's.DVS task schedulings not only need the different qualities according to task, design corresponding dispatching algorithm, such as in real time and non real-time
Business, cycle and aperiodic task etc..DVS task schedulings also need to meet the different restrictions of original dispatching algorithm, such as can seize and not
Can seize, dynamic and fixed priority etc..The DVS dispatching methods of un-real time job are relatively simple, and task is without clear and definite
Deadline limits, and the target of un-real time job DVS scheduling is to ensure that task can be completed according to currently employed dispatching algorithm
On the basis of pursue lowest power consumption.Current un-real time job DVS models can be classified as three classes substantially：1) state algorithm；2) base
In the algorithm of average time；3) algorithm based on power consumption material time.The DVS scheduling most important condition of real-time task is guarantee system
Execution time predictability.Common real-time task scheduling method has two kinds：RMS (the RM schedulings based on priority
Algorithm) and EDF (earliest off period priority algorithm).But traditional both of which is excessively complicated, computing cost is big,
It is not suitable for the airborne embedded system very high to requirement of real-time.
The content of the invention
The purpose of the present invention is:The present invention provides a kind of DVS dispatching algorithms based on partition operating system, at dynamic estimation
Reason device free time, power consumption is effectively reduced under conditions of processor high response speed is ensured with very little cost.
The present invention technical solution be：
DVS dispatching algorithms based on partition operating system, it is characterised in that：Comprise the following steps：
1】Idle task run time t1 before partitioned record blood pressure lowering is pressed in increase by the task control block of idle task
Data item；
2】Judge whether idle task run time t1 meets voltage-switching conditions before blood pressure lowering：When idle task fortune before blood pressure lowering
The row timeWhen, meeting voltage-switching conditions, execution mixes down to dormancy mould
The operation of formula, until subregion terminates；
Wherein Echange is the voltage switching energy consumption of chip, and Vlarge is voltage before blood pressure lowering, and Vsmall is electricity after blood pressure lowering
Pressure, tchange is the voltage switching time of chip, and k is the scale factor of energy consumption and voltage relationship；
3】At the end of subregion, raising frequency operation is performed.
Above-mentioned steps 2】In, idle task run time t1 meets voltage-switching conditions for continuous 5 times before blood pressure lowering, performs frequency reducing
Operation.
Above-mentioned steps 1】Also include following link：For various chips, by various chips
Value is calculated, and is fabricated to MAP tables；Step 2】Also include, query steps 1】The MAP tables made, judge idle task before blood pressure lowering
Whether run time t1 meets voltage-switching conditions.
It is an advantage of the invention that：The algorithm complex of the method is unrelated with the quantity of task, execution time etc. in subregion；Point
The increase of task amount is not result in the increase of algorithm complex in area, thus the dispatching method can be effectively ensured the real-time of system
Property.Because algorithm complex is low, the cost that the algorithm is embedded into into partition operating system is also very low, based on the algorithm, in subregion
The function of realizing reducing power consumption in operating system is feasible.Under the development trend of airborne computer synthesization, multiple process
Simultaneously reducing energy consumption can effectively extend lifetime of system to device, have great practical value.Solve airborne flush bonding processor by
In the problems of excessive heat that high-speed computation brings, extend the processor life-span, reduce processor fault rate.
Specific embodiment
Basis based on the DVS dispatching algorithms of partition operating system is partition operating system, the task time between subregion
Spatial separation, the task in subregion is based on priority scheduling.Subregion free time is not required processor speed.
In subregion, using the method for " collection ", the free time dynamically recording of each subregion is got off, using certain
Algorithm is estimated to it, when the conditions are met, carries out voltage and lowers switching.Before subregion execution terminates, recover magnitude of voltage,
Ensure that the operation of next subregion is unaffected.
Condition is to be less than slack time the voltage switching time, and the energy expenditure that voltage switching brings is lax less than other
Time reduces the power consumption of voltage " earning ".
The voltage switching time of chip is tchange, is obtained by searching chip handbook；
Voltage is Vlarge before blood pressure lowering, and the value of Vlarge sets in advance with reference to chip handbook；
Voltage is Vsmall after blood pressure lowering；The value of Vsmall sets in advance with reference to chip handbook；
Slack time is trelax；
The voltage switching energy consumption of chip is Echange, is obtained by searching chip handbook；
The scale factor of energy consumption and voltage relationship is：Corresponding power consumption/the Vlarge of k, k=Vlarge2, Vlarge is corresponding
Power consumption can inquire about chip handbook and obtain；
Saving energy consumption Es is：
Es=(Vlarge2-Vsmall2)(trelax–2*tchange)*k-Echange； (1)
When Es is more than 0, represent that the method by reducing supply voltage reduction energy consumption is feasible.
Formula (1) after conversion by becoming：
Trelax=(Es+Echange)/(k* (Vlarge2-Vsmall2))+2*tchange； (2)
Value in formula (2) on the right of equation is all to determine except Es, therefore, the condition that voltage changes is changed into
trelax>(Echange)/(k*(Vlarge2-Vsmall2))+2*tchange； (3)
The free time of partition operating system " collection " and the relation of slack time are：
Trelax=t2-t1； (4)
T1 is the idle task run time before blood pressure lowering, and t2 is the idle task run time after blood pressure lowering, between t1 and t2
There is proportionate relationship, t2=t1 (Vsmall/Vlarge) (5)；
Formula (4), (5) are brought into (3)：
TimeIt is the marginal value of subregion voltage switching, if the value is being
Can calculate at the beginning of system design, as long as idle task run time t1 and switching are faced before comparing blood pressure lowering in system operation
Dividing value is obtained whether voltage can reduce.Calculate simple, the switching time of task will not be increased, also do not interfere with system
Real-time.
Below based on certain partition operating system of ARINC653, the present invention is described in further detail.
ARINC653 is that American Electronic engineering association determines for the modularization comprehensive avionics system of aviation civil aircraft
The application programming interfaces standard of justice, is the important evidence for designing multi partition operating system in the world.Be currently based on this standard has
Many maturation operating systems.
It is made up of following steps based on the DVS dispatching algorithms of partition operating system：
1st, a data item for pressing idle task run time t1 before partitioned record blood pressure lowering is increased in task control block.
Task control block is the unique data structure of logger task information in operating system, and one kind of free time record is high
Efficacious prescriptions method is exactly the run time for recording idle task, using the time as task control block a data item, can be quick
Obtain and change the information.
2nd, judge whether idle task run time t1 meets voltage-switching conditions before blood pressure lowering.
Voltage-switching conditions are：Idle task run time before blood pressure lowering
If meeting voltage-switching conditions, frequency redution operation is performed, until subregion terminates；
In order to avoid the fast frequency of idle task in subregion fluctuates, the degree of stability of free time is assessed, it is empty before blood pressure lowering
Not busy Runtime t1 meets voltage-switching conditions for continuous 5 times, performs frequency redution operation.
In partition operating system, the operation for mixing down to park mode is not adopted, because the switching power consumption of the operation is big, when
Between it is long, the overhead that brings reduces the real-time of system, therefore, only with frequency reducing and raising frequency operation.For different process
The time of device, frequency reducing and raising frequency is different, and power consumption makes in advance MAP tables, voltage switching needed for different current voltages and expection voltage
Condition is by acquisition of tabling look-up.
3rd, at the end of subregion, raising frequency operation is performed.
The execution of task in subregion insulation request subregion can not affect the operation of other subregions, frequency redution operation also to ensure not
Other subregions are impacted, thus, complete raising frequency operation in subregion finishing scheduling.
Claims (3)
1. the DVS dispatching algorithms of partition operating system are based on, it is characterised in that：Comprise the following steps：
1】The number of idle task run time t1 before partitioned record blood pressure lowering is pressed in increase by the task control block of idle task
According to item；
2】Judge whether idle task run time t1 meets voltage-switching conditions before blood pressure lowering：When idle task is run before blood pressure lowering
BetweenWhen, meeting voltage-switching conditions, execution mixes down to park mode
Operation, until subregion terminates；
Wherein Echange is the voltage switching energy consumption of chip, and Vlarge is voltage before blood pressure lowering, and Vsmall is voltage after blood pressure lowering,
Tchange is the voltage switching time of chip, and k is the scale factor of energy consumption and voltage relationship；
3】At the end of subregion, raising frequency operation is performed.
2. DVS dispatching algorithms based on partition operating system according to claim 1, it is characterised in that：Step 2】In, drop
Idle task run time t1 meets voltage-switching conditions for continuous 5 times before pressure, performs frequency redution operation.
3. DVS dispatching algorithms based on partition operating system according to claim 1 and 2, it is characterised in that：Step 1】Also
Including following link：For various chips, by various chipsValue is calculated,
It is fabricated to MAP tables；Step 2】Also include, query steps 1】The MAP tables made, judge idle task run time t1 before blood pressure lowering
Whether voltage-switching conditions are met.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310688800.2A CN104714621B (en) | 2013-12-14 | 2013-12-14 | DVS scheduling algorithm based on partitioning operation system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310688800.2A CN104714621B (en) | 2013-12-14 | 2013-12-14 | DVS scheduling algorithm based on partitioning operation system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104714621A CN104714621A (en) | 2015-06-17 |
| CN104714621B true CN104714621B (en) | 2017-05-17 |
Family
ID=53414035
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310688800.2A Active CN104714621B (en) | 2013-12-14 | 2013-12-14 | DVS scheduling algorithm based on partitioning operation system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104714621B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106776272B (en) * | 2016-11-11 | 2019-11-05 | 西北工业大学 | Embedded system real-time performance testing method |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101044445A (en) * | 2004-11-02 | 2007-09-26 | 英特尔公司 | Method and apparatus to control temperature of processor |
| US7730340B2 (en) * | 2007-02-16 | 2010-06-01 | Intel Corporation | Method and apparatus for dynamic voltage and frequency scaling |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9086883B2 (en) * | 2011-06-10 | 2015-07-21 | Qualcomm Incorporated | System and apparatus for consolidated dynamic frequency/voltage control |
-
2013
- 2013-12-14 CN CN201310688800.2A patent/CN104714621B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101044445A (en) * | 2004-11-02 | 2007-09-26 | 英特尔公司 | Method and apparatus to control temperature of processor |
| US7730340B2 (en) * | 2007-02-16 | 2010-06-01 | Intel Corporation | Method and apparatus for dynamic voltage and frequency scaling |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104714621A (en) | 2015-06-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103150003B (en) | The power-saving control method of information handling system, this information handling system and device | |
| CN102868763B (en) | The dynamic adjusting method that under a kind of cloud computing environment, virtual web application cluster is energy-conservation | |
| CN102981893B (en) | A kind of dispatching method of virtual machine and system | |
| WO2021073085A1 (en) | Microservice-oriented nanosecond-level power resource allocation method and system | |
| CN102932279A (en) | Multidimensional resource scheduling system and method for cloud environment data center | |
| CN103916438A (en) | Cloud testing environment scheduling method and system based on load forecast | |
| CN104718531A (en) | Parallel computing device | |
| CN102012891B (en) | Computer cluster management method, device and system | |
| CN102981890A (en) | Computing task and virtual machine deploying method within a virtual data center | |
| CN103246570A (en) | Hadoop scheduling method and system and management node | |
| CN103399626A (en) | Power consumption sensing scheduling system and power consumption sensing scheduling method for parallel application for hybrid computation environments | |
| Kao et al. | Data-locality-aware mapreduce real-time scheduling framework | |
| CN104346211A (en) | Method and system for realizing virtual machine migration under cloud computing | |
| Xiang et al. | Run-time management for multicore embedded systems with energy harvesting | |
| CN104572279B (en) | A kind of virtual machine dynamic dispatching method of supporting node binding | |
| CN114389955A (en) | Embedded platform heterogeneous resource pooling management method | |
| CN104753992A (en) | Method, device and system for data storage and method and device for virtual platform failure recovery | |
| CN103023802A (en) | Web-cluster-oriented low energy consumption scheduling system and method | |
| CN104102532B (en) | Research-on-research stream scheduling method based on low energy consumption in a kind of isomeric group | |
| CN103336574A (en) | Energy-saving control method and device of data center | |
| CN104714621B (en) | DVS scheduling algorithm based on partitioning operation system | |
| CN101819459A (en) | Heterogeneous object memory system-based power consumption control method | |
| CN107506286A (en) | CPU and memory block automatically upper inserting method and system | |
| US20140040900A1 (en) | Storage managing device and method and electronic apparatus | |
| CN104182280B (en) | Low-energy RM real-time task scheduling method for hybrid main memory embedded system |
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 |