CN108304254A - Quick virtual machine process dispatch control method and device - Google Patents

Quick virtual machine process dispatch control method and device Download PDF

Info

Publication number
CN108304254A
CN108304254A CN201711477075.9A CN201711477075A CN108304254A CN 108304254 A CN108304254 A CN 108304254A CN 201711477075 A CN201711477075 A CN 201711477075A CN 108304254 A CN108304254 A CN 108304254A
Authority
CN
China
Prior art keywords
queue
quick
host
process queue
tail
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
Application number
CN201711477075.9A
Other languages
Chinese (zh)
Other versions
CN108304254B (en
Inventor
杨立群
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhuhai Hotdoor Technology Co Ltd
Original Assignee
Zhuhai Hotdoor Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Zhuhai Hotdoor Technology Co Ltd filed Critical Zhuhai Hotdoor Technology Co Ltd
Priority to CN201711477075.9A priority Critical patent/CN108304254B/en
Publication of CN108304254A publication Critical patent/CN108304254A/en
Application granted granted Critical
Publication of CN108304254B publication Critical patent/CN108304254B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46Multiprogramming arrangements
    • G06F9/48Program initiating; Program switching, e.g. by interrupt
    • G06F9/4806Task transfer initiation or dispatching
    • G06F9/4843Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
    • G06F9/4881Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44Arrangements for executing specific programs
    • G06F9/455Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
    • G06F9/45533Hypervisors; Virtual machine monitors
    • G06F9/45558Hypervisor-specific management and integration aspects

Landscapes

  • Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Multi Processors (AREA)
  • Debugging And Monitoring (AREA)

Abstract

The present invention proposes a kind of quick virtual machine process dispatch control method, includes the following steps:The host process queue and quick process queue of establishment process, and host process queue and quick process queue are emptied to realize the initialization of host process queue and quick process queue;The process of virtual machine creating is received, and estimates the resource quantity occupied when the process executes;Obtain the total resources that current process queue occupies, if the total resources that current host process queue occupies is more than preset host process queue thresholds, and the resource quantity called when the execution of process be less than preset resource threshold when, the process is inserted into the tail of the queue of quick process queue, and otherwise the process is inserted into the tail of the queue of host process queue;And process is obtained from the team of host process queue head and team's head of quick process queue respectively according to order.Beneficial effects of the present invention are:The less process of resource is occupied by responding as early as possible, improves the overall applicability executing efficiency of each virtual machine.

Description

Quick virtual machine process dispatch control method and device
Technical field
The present invention relates to virtual machine technique field more particularly to a kind of quick virtual machine process dispatch control methods and dress It sets.
Background technology
With popularizing for cloud computing technology, more and more mechanisms use alternative solution of the cloud computing as local computing, with Parallel form is effectively carried out a variety of applications.Since cloud computing technology the more independent servers of physics based on being made of On same hardware platform, therefore the different server of unified management multiple devices parameter for convenience, it is general using virtual at present Machine technology will virtualize on above-mentioned hardware platform, with the isolation, scalability and safety of realizing platform etc. technical indicator. After multiple servers are virtualized, the different type resource of each server collectively form respectively various resource pools (such as Store the hard disk pond of data), and realize common calculating and shared resource by more virtual machines, to realize all kinds of computing resources Flexible allocation and efficiently utilize.
However, when the application program due to each virtual machine disorderly creates a large amount of process, processor is normally only according to more The process of a process executes request time sequencing and executes, therefore processor resource is occupied when some application program is run When ratio is excessive, other applications will be caused to start overlong time or can not run.When serious, this will lead to the fortune of system Row collapse.For example, the resource request amount occupied by some application program is excessive, such as to execute the time longer for processor, then handles Device needs after first carrying out the application program, then executes the request of other applications below.This will cause below occupy resource compared with Few application program can not execute in time, cause the response of certain applications program slow.
Invention content
Present invention aims to solve the deficiencies of the prior art, and provides a kind of a kind of quick virtual machine process dispatch control method and Device occupies the less process of resource by priority processing, and cloud computing platform whole progress execution efficiency is improved to obtain Effect.
To achieve the goals above, the present invention uses technical solution below.
First, the present invention proposes a kind of quick virtual machine process dispatch control method, includes the following steps:Establishment process Host process queue and quick process queue, and host process queue and quick process queue are emptied to realize host process queue and fast The initialization of fast process queue;The process of virtual machine creating is received, and estimates the resource quantity occupied when the process executes;It obtains The total resources for taking current process queue to occupy, if the total resources that current host process queue occupies is more than preset host process team Row threshold value, and the resource quantity called when the execution of process be less than preset resource threshold when, the process be inserted into quickly into The tail of the queue of journey queue, otherwise the process be inserted into the tail of the queue of host process queue;And according to order respectively from host process queue Team head and quick process queue team head obtain process.
In the embodiment of the method for the present invention, after receiving the process that virtual machine is sent out, estimating the process data is It is no normal, and close abnormal process.
In the embodiment of the method for the present invention, after receiving the process that sends out of virtual machine, in the process according to line Journey can parallel computation execute fractionation.
In the embodiment of the method for the present invention, after process is inserted into the tail of the queue of quick process queue, quick process The resource quantity sequence called when queue is executed according to process.
In the embodiment of the method for the present invention, when the total resources that quick process queue occupies is quick more than preset When process queue threshold value, improves host process queue thresholds and/or reduce resource threshold.
Further, in the above method embodiment of the present invention, when quick process queue is sky within a preset period of time When queue, reduces host process queue thresholds and/or improve resource threshold.
In the embodiment of the method for the present invention, when the total resources that host process queue occupies is more than preset host process When queue thresholds, the resource quantity called when process executes in host process queue is suggested and is inserted into less than the process of resource threshold To the tail of the queue of quick process queue.
In the embodiment of the method for the present invention, when the length of quick process queue is more than preset quick process queue When threshold value and the occupancy total resources of host process queue are less than host process queue thresholds, it is located at the tail of the queue of quick process queue and super The process for going out preset quick process queue thresholds part is suggested and is inserted into the tail of the queue of host process queue.
Further, in the above method embodiment of the present invention, the resource quantity that process is called when executing is processor Frequency of use.
Alternatively, in the above method embodiment of the present invention, the resource quantity that process is called when executing is that process accounts for With the length of processor timeslice.
Secondly, the present invention also proposes a kind of quick virtual machine process dispatching control device, comprises the following modules:Initialize mould Block, the host process queue for creating process and quick process queue, and to host process queue and quick process queue empty with Realize the initialization of host process queue and quick process queue;Module is estimated, the process sent out for receiving virtual machine, and estimate The resource quantity that the process occupies when executing;It joins the team module, the total resources occupied for obtaining current host process queue, if The total resources that current host process queue occupies is more than preset host process queue thresholds, and the resource called when the execution of process When quantity is less than preset resource threshold, the process is inserted into the tail of the queue of quick process queue, and otherwise the process is inserted into The tail of the queue of host process queue;And go out group module, it is used for according to order respectively from the team of host process queue head and quick process team Team's head of row obtains process.
In the device embodiment of the present invention, after receiving the process that sends out of virtual machine, estimate module estimate it is described into Whether number of passes evidence is normal, and closes abnormal process.
In the device embodiment of the present invention, estimate after module receives the process that sends out of virtual machine, according to it is described into In journey according to thread can parallel computation execute fractionation.
In the device embodiment of the present invention, after process is inserted into the tail of the queue of quick process queue, module of joining the team The resource quantity sequence quick process queue called when being executed according to process.
In the device embodiment of the present invention, when the total resources that quick process queue occupies is quick more than preset When process queue threshold value, module of joining the team improves host process queue thresholds and/or reduces resource threshold.
Further, in the above-mentioned apparatus embodiment of the present invention, when quick process queue is sky within a preset period of time When queue, module of joining the team reduces host process queue thresholds and/or improves resource threshold.
In the device embodiment of the present invention, when the total resources that host process queue occupies is more than preset host process When queue thresholds, module of joining the team proposes that the resource quantity called when process executes in host process queue is less than the process of resource threshold And it is inserted into the tail of the queue of quick process queue.
In the device embodiment of the present invention, when the length of quick process queue is more than preset quick process queue When threshold value and the occupancy total resources of host process queue are less than host process queue thresholds, module of joining the team will be located at quick process queue Tail of the queue and propose beyond the process of preset quick process queue thresholds part and be inserted into the tail of the queue of host process queue.
Further, in the above-mentioned apparatus embodiment of the present invention, the resource quantity that process is called when executing is processor Frequency of use.
Alternatively, in the above-mentioned apparatus embodiment of the present invention, the resource quantity that process is called when executing is that process accounts for With the length of processor timeslice.
Finally, the invention also discloses a kind of computer readable storage medium, it is stored thereon with computer instruction, the instruction It is realized when being executed by processor such as the step of any one of aforementioned the method.
Beneficial effects of the present invention are:By constructing simultaneously the host process queue of maintenance applications and quick process team respectively Row so that occupying the less process of resource can be responded as early as possible, and the overall applicability program to improve each virtual machine executes effect Rate.
Description of the drawings
Fig. 1 show the method flow diagram of quick virtual machine process scheduling controlling disclosed in this invention;
Fig. 2 show the method flow diagram for the specific deterministic process for judging whether process is inserted into quick process queue in Fig. 1;
The process that Fig. 3 is shown in host process queue in one embodiment of the invention is inserted into showing for quick process queue It is intended to;
Fig. 4 show the state change schematic diagram of host process queue in another embodiment of the present invention;
Fig. 5 show the method flow diagram that the process in quick process queue is transferred in Fig. 4;
Fig. 6 show the state change signal that process in one embodiment of the invention is inserted into after quick process queue Figure;
Fig. 7 show the schematic diagram of host process queue thresholds adjustment in one embodiment of the invention;
Fig. 8 show the function structure chart of quick virtual machine process dispatching control device disclosed in this invention.
Specific implementation mode
The technique effect of the design of the present invention, concrete structure and generation is carried out below with reference to embodiment and attached drawing clear Chu, complete description, to be completely understood by the purpose of the present invention, scheme and effect.It should be noted that the case where not conflicting Under, the features in the embodiments and the embodiments of the present application can be combined with each other.The identical attached drawing mark used everywhere in attached drawing Note indicates same or analogous part.
Method flow diagram shown in referring to Fig.1, in one embodiment of the invention, quick virtual machine process scheduling controlling Method includes the following steps:The host process queue and quick process queue of establishment process, and to host process queue and quick process Queue is emptied to realize the initialization of host process queue and quick process queue;The process of virtual machine creating is received, and estimates institute State the resource quantity occupied when process executes;The total resources that current host process queue occupies is obtained, if current host process queue The total resources of occupancy is more than preset host process queue thresholds, and the resource quantity called when the execution of process is less than preset When resource threshold, the process is inserted into the tail of the queue of quick process queue, and otherwise the process is inserted into the team of host process queue Tail;And process is obtained from the team of host process queue head and team's head of quick process queue respectively according to order.Its wherein, it is main into Journey queue thresholds and resource threshold can be arranged in initialization.For example, host process queue thresholds can be initialized as 500ms, i.e., it is main Process in process queue needs to occupy the 500ms processor times.At this point, can refer to submethod flow chart shown in Fig. 2, work as master When the occupancy total resources of process queue is less than 500ms, the process newly obtained from process pool will be directly inserted into host process team The tail of the queue of row.All processes in host process queue execute successively according to the sequence of first in first out.When the occupancy of host process queue When total resources is greater than or equal to 500ms, the process newly obtained from process pool will be pretreated, and be executed with estimating the process The resource quantity of Shi Zhanyong, if the resource quantity that occupies is less when the process executes (such as when only taking up a small amount of processor Between), then it is inserted into the tail of the queue priority processing of quick process queue;Otherwise it is inserted into the tail of the queue of host process queue, according to normal Order processing.Specifically, the process positioned at the team of host process queue head and team's head of quick process queue will be extracted.By Multiple processing on hardware platform are virtualized in virtual machine, thus above-mentioned process may actually transfer to respectively it is different Processor is handled respectively.Virtual machine can adopt specific process processing mode, those skilled in the art according to specific actual conditions It is realized with the various prior arts.The present invention to this not with restriction.
Due to generally comprising the thread of multiple detachable parallel computations in process, in one embodiment of the present of invention In, in the process according to thread can parallel computation execute fractionation.On the one hand, the requested process of application program is standby splits After will be executed by processor as much as possible, improve the execution efficiency of process;On the other hand, after being split due to process, individually Process will occupy relatively less resource, influence other applications to avoid certain resources from being monopolized for a long time by individual process Execution.In addition, after the process that process pool obtains, can also checking to the process, determine if comprising different Regular data (for example whether situations such as data packet received is imperfect or the process of UNKNOWN TYPE occur), can be by such apparent error Process filtered out from process pool.
With reference to host process queue shown in Fig. 3 and quick process quene state change schematic diagram (grid on the right side of process in figure Interior numerical value is the processor time of required occupancy when the process executes, the resource occupied when as the execution for weighing the process Quantity), in one embodiment of the invention, when the occupancy total resources of host process queue is more than preset host process queue threshold When value, the resource quantity occupied when process executes in host process queue is suggested less than the process of resource threshold and is inserted into quickly The tail of the queue of process queue.Specifically, as shown in Figure 3, if host process queue thresholds are 250ms at this time, and host process queue Occupancy total resources is 259ms.Resource quantity, which is occupied, if preset resource threshold is 20ms, in host process queue is less than threshold value Process (" process A ", " process C " and " process H " corresponding process i.e. in figure) will be extracted from host process queue, be inserted into To the tail of the queue of quick process queue so that the less process of the resource quantity that occupies can be timely when being executed in host process queue It executes.
On the contrary, with reference to the state change schematic diagram of host process queue in another embodiment shown in Fig. 4, work as quick process The total resources that occupies of queue is more than the occupancy total resources of preset quick process queue thresholds and host process queue less than master When process queue threshold value, process execution efficiency will be less than host process queue in quick process queue.In order to improve the entirety of process Execution efficiency, submethod flow chart referring to Figure 5 positioned at the tail of the queue of quick process queue and can will exceed preset quick The process (i.e. " f processes " and " g processes " in Fig. 4) of process queue threshold portion proposes and is inserted into the team of host process queue Tail.
With reference to process shown in fig. 6 be inserted into quick process queue schematic diagram, in one embodiment of the invention, when into After journey is inserted into the tail of the queue of quick process queue, the resource quantity that quick process queue occupies when being executed according to process sorts.Figure Numerical value on the right side of middle process in grid is processor time (similarly, a processes of required occupancy when the process executes " 5ms " indicates that the process takes around and occupies processor 5ms), the resource quantity occupied when as the execution for weighing the process.Such as As shown in the figure, new f processes, which take around, occupies the processor time as 7ms.At this time since the occupancy resource of host process queue is total Amount is more than host process queue thresholds, therefore f processes will first be inserted into the tail of the queue of quick process queue, then again to quick process Queue order.Because occupying the front that the less process of resource quantity will be come quick process queue when executing, these Process can be executed as early as possible.Further, since quick process queue be maintained as it is orderly, so new process can be shorter Time be inserted into the correct position of quick process queue (in fact, the time complexity of the operation is current queue size Logarithm).
With reference to method flow diagram shown in Fig. 7, in one embodiment of the invention, when the occupancy of quick process queue provides When source total amount is more than preset quick process queue thresholds, the process execution efficiency in quick process queue at this time will decline, very To equal than or less than host process queue.In order to ensure that the process being assigned in quick process queue can be executed preferentially, need to carry Height is inserted into the threshold of quick process queue.In the present embodiment, host process queue thresholds be enhanced (can be improved to it is current main into The occupancy total resources or higher of journey queue), to reduce the process for being assigned to quick process queue.Alternatively, it is inserted into fast The threshold of fast process queue can also be improved by way of reducing resource threshold so that process is more difficult to be assigned to quick process team Row.
It is that process occupies for weighing the resource quantity called when process executes in aforementioned several embodiments of the present invention The length of processor timeslice.Because the numerical value can be estimated easily, and discreet value and actual value difference are less, so the number Value is usually used in the cost spent when measurement process executes.Alternatively, another kind can be used for calling when measurement process executes Resource quantity is the frequency of use of processor.Under normal circumstances, the frequency of use of processor higher process is called when executing Resource quantity it is more.Aforementioned several embodiments can correspondingly use the frequency of use of processor to weigh process.
With reference to function structure chart shown in Fig. 8, in one embodiment of the invention, quick virtual machine process scheduling controlling Device comprises the following modules:Initialization module, the host process queue for creating process and quick process queue, and to host process Queue and quick process queue are emptied to realize the initialization of host process queue and quick process queue;Module is estimated, for connecing The process that virtual machine is sent out is received, and estimates the resource quantity occupied when the process executes;It joins the team module, for obtaining current master The total resources that process queue occupies, if the total resources that current host process queue occupies is more than preset host process queue threshold Value, and the resource quantity called when the execution of process be less than preset resource threshold when, the process is inserted into quick process team The tail of the queue of row, otherwise the process be inserted into the tail of the queue of host process queue;And go out group module, it is used for according to order respectively from master Team's head of process queue and team's head of quick process queue obtain process.Wherein, host process queue thresholds and resource threshold can be by Initialization module is arranged.For example, host process queue thresholds can be initialized as 500ms, i.e., the process needs in host process queue account for With the 500ms processor times.At this point, submethod flow chart shown in Fig. 2 is can refer to, when the process in host process queue occupies money When source total amount is less than 500ms, the process newly obtained is directly inserted into the tail of the queue of host process queue by module of joining the team.Process goes out group mould Block obtains all processes in host process queue according to the sequence of first in first out successively.When the process in host process queue occupies money When source total amount is less than 500ms, the resource quantity called when the process newly obtained executes will be estimated by elder generation by estimating module, if described The resource quantity that process is called when executing is less (such as only taking up a small amount of processor time), then is inserted into module and inserts it into soon The tail of the queue priority processing of fast process queue;Otherwise it is inserted into the tail of the queue that module inserts it into host process queue, according to regular turn Processing.Specifically, going out process of group module extraction positioned at team's head of host process queue and team's head of quick process queue.Due to void Quasi- machine virtualizes multiple processing on hardware platform, therefore above-mentioned process may actually transfer to different processing respectively Device is handled respectively.For virtual machine to specific process processing mode, those skilled in the art can be according to specific actual conditions using each The kind prior art is realized.The present invention to this not with restriction.
Due to generally comprising the thread of multiple detachable parallel computations in process, in one embodiment of the present of invention In, in the process according to thread can parallel computation execute fractionation.On the one hand, the requested process of application program is standby splits After will be executed by processor as much as possible, improve the execution efficiency of process;On the other hand, after being split due to process, individually Process will occupy relatively less resource, influence other applications to avoid certain resources from being monopolized for a long time by individual process Execution.In addition, after the process that process pool obtains, can also checking to the process, determine if comprising different Regular data (for example whether situations such as data packet received is imperfect or the process of UNKNOWN TYPE occur), can be by such apparent error Process filtered out from process pool.
With reference to host process queue shown in Fig. 3 and quick process quene state change schematic diagram (grid on the right side of process in figure Interior numerical value is the processor time of required occupancy when the process executes, the resource occupied when as the execution for weighing the process Quantity), in one embodiment of the invention, when the occupancy total resources of host process queue is more than preset host process queue threshold When value, the resource quantity that module of joining the team occupies when executing process in host process queue is proposed and is inserted less than the process of resource threshold Enter the tail of the queue to quick process queue.Specifically, as shown in Figure 3, if host process queue thresholds are 250ms at this time, and it is main into The occupancy total resources of journey queue is 259ms.If preset resource threshold is 20ms, module of joining the team will account in host process queue The process (" process A ", " process C " and " process H " corresponding process i.e. in figure) for being less than threshold value with resource quantity will be from host process It is extracted in queue, is inserted into the tail of the queue of quick process queue so that the resource quantity occupied when being executed in host process queue Less process can be executed in time.
On the contrary, with reference to the state change schematic diagram of host process queue in another embodiment shown in Fig. 4, work as quick process The total resources that occupies of queue is more than the occupancy total resources of preset quick process queue thresholds and host process queue less than master When process queue threshold value, process execution efficiency will be less than host process queue in quick process queue.In order to improve the entirety of process Execution efficiency, module of joining the team can will be positioned at the tail of the queue of quick process queue and beyond preset quick process queue thresholds parts Process (i.e. " f processes " and " g processes " in Fig. 4) proposes and is inserted into the tail of the queue of host process queue.
With reference to process shown in fig. 6 be inserted into quick process queue schematic diagram, in one embodiment of the invention, when into After journey is inserted into the tail of the queue of quick process queue, resource quantity that module of joining the team occupies when being executed according to process sorts quick process Queue.Numerical value in figure on the right side of process in grid be required occupancy when the process executes the processor time (similarly, a into " 5ms " of journey indicates that the process takes around and occupies processor 5ms), the number of resources occupied when as the execution for weighing the process Amount.As shown in the figure, new f processes, which take around, occupies the processor time as 7ms.At this time since the occupancy of host process queue provides Source total amount is more than host process queue thresholds, therefore f processes are first inserted into the tail of the queue of quick process queue by module of joining the team, then again To quick process queue order.Because before the less process of occupancy resource quantity will be come quick process queue when executing Side, so these processes can be executed as early as possible.Further, since quick process queue be maintained as it is orderly, so new Process can be inserted into the correct position of quick process queue the shorter time (in fact, the time complexity of the operation is to work as The logarithm of preceding queue length).
In one embodiment of the invention, when the occupancy total resources of quick process queue is more than preset quick process When queue thresholds, the process execution efficiency in quick process queue at this time will decline, even equal to or less than host process queue.For Ensure that the process being assigned in quick process queue can be executed preferentially, needs to improve the door for being inserted into quick process queue Sill.In the present embodiment, host process queue thresholds, which are enhanced, (can be improved to the occupancy total resources of current host process queue or more It is high), to reduce the process for being assigned to quick process queue.Alternatively, being inserted into the threshold of quick process queue can also lead to The mode for crossing reduction resource threshold improves so that process is more difficult to be assigned to quick process queue.
It is that process occupies for weighing the resource quantity called when process executes in aforementioned several embodiments of the present invention The length of processor timeslice.Because the numerical value can be estimated easily, and discreet value and actual value difference are less, so the number Value is usually used in the cost spent when measurement process executes.Alternatively, another kind can be used for calling when measurement process executes Resource quantity is the frequency of use of processor.Under normal circumstances, the frequency of use of processor higher process is called when executing Resource quantity it is more.Aforementioned several embodiments can correspondingly use the frequency of use of processor to weigh process.
Although description of the invention is quite detailed and especially several embodiments are described, it is not Any of these details or embodiment or any specific embodiments are intended to be limited to, but it is by reference to appended that should be considered as Claim considers that the prior art provides the possibility explanation of broad sense for these claims, to effectively cover the present invention Preset range.In addition, with the foreseeable embodiment of inventor, present invention is described above, its purpose is to be provided with Description, and those equivalent modifications that the present invention can be still represented to the unsubstantiality change of the present invention still unforeseen at present.

Claims (10)

1. a kind of quick virtual machine process dispatch control method, which is characterized in that include the following steps:
The host process queue and quick process queue of establishment process, and host process queue and quick process queue are emptied to realize The initialization of host process queue and quick process queue;
The process of virtual machine creating is received, and estimates the resource quantity occupied when the process executes;
The total resources that current host process queue occupies is obtained, if the total resources that current host process queue occupies is more than preset Host process queue thresholds, and when the resource quantity called when the execution of process is less than preset resource threshold, the process is inserted into To the tail of the queue of quick process queue, otherwise the process is inserted into the tail of the queue of host process queue;And
According to order process is obtained from the team of host process queue head and team's head of quick process queue respectively.
2. method according to claim 1, which is characterized in that after receiving the process that virtual machine is sent out, estimate described into number of passes According to whether normally, and close abnormal process.
3. method according to claim 1, which is characterized in that after receiving the process that virtual machine is sent out, the line in the process Journey according to can parallel computation execute fractionation.
4. method according to claim 1, which is characterized in that when the total resources that host process queue occupies is more than preset master When process queue threshold value, the resource quantity called when process executes in host process queue is suggested simultaneously less than the process of resource threshold It is inserted into the tail of the queue of quick process queue.
5. method according to claim 1, which is characterized in that when the total resources that quick process queue occupies is more than preset When the total resources that quick process queue thresholds and host process queue occupy is less than host process queue thresholds, it is located at quick process team It the tail of the queue of row and is suggested beyond the process of preset quick process queue thresholds part and is inserted into the tail of the queue of host process queue.
6. method according to claim 1, which is characterized in that when the total resources that quick process queue occupies is more than preset When quick process queue thresholds, improves host process queue thresholds and/or reduce resource threshold.
7. method according to claim 1, which is characterized in that after process is inserted into the tail of the queue of quick process queue, quickly The resource quantity sequence called when process queue is executed according to process.
8. according to any the method in claim 1 to 6, which is characterized in that when process executes the resource quantity called be into The length of Cheng Zhanyong processor timeslices and/or the frequency of use of processor.
9. a kind of quick virtual machine process dispatching control device, which is characterized in that comprise the following modules:
Initialization module, the host process queue for creating process and quick process queue, and to host process queue and quickly into Journey queue is emptied to realize the initialization of host process queue and quick process queue;
Module is estimated, the process sent out for receiving virtual machine, and estimate the resource quantity called when the process executes;
It joins the team module, the total resources occupied for obtaining current host process queue, if the resource that current host process queue occupies Total amount is more than preset host process queue thresholds, and the resource quantity called when the execution of process is less than preset resource threshold When, the process is inserted into the tail of the queue of quick process queue, and otherwise the process is inserted into the tail of the queue of host process queue;And
Go out group module, for obtaining process from the team of host process queue head and team's head of quick process queue respectively according to order.
10. a kind of computer readable storage medium, is stored thereon with computer instruction, it is characterised in that the instruction is held by processor It is realized such as the step of method described in any item of the claim 1 to 8 when row.
CN201711477075.9A 2017-12-29 2017-12-29 Method and device for controlling process scheduling of rapid virtual machine Active CN108304254B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711477075.9A CN108304254B (en) 2017-12-29 2017-12-29 Method and device for controlling process scheduling of rapid virtual machine

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711477075.9A CN108304254B (en) 2017-12-29 2017-12-29 Method and device for controlling process scheduling of rapid virtual machine

Publications (2)

Publication Number Publication Date
CN108304254A true CN108304254A (en) 2018-07-20
CN108304254B CN108304254B (en) 2022-02-22

Family

ID=62868082

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711477075.9A Active CN108304254B (en) 2017-12-29 2017-12-29 Method and device for controlling process scheduling of rapid virtual machine

Country Status (1)

Country Link
CN (1) CN108304254B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109213561A (en) * 2018-09-14 2019-01-15 珠海国芯云科技有限公司 The equipment scheduling method and device of virtual desktop based on container
CN110659132A (en) * 2019-08-29 2020-01-07 福建天泉教育科技有限公司 Request processing optimization method and computer-readable storage medium
CN112306371A (en) * 2019-07-30 2021-02-02 伊姆西Ip控股有限责任公司 Method, apparatus and computer program product for storage management

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100094852A1 (en) * 2008-10-14 2010-04-15 Chetan Kumar Gupta Scheduling queries using a stretch metric
CN104202261A (en) * 2014-08-27 2014-12-10 华为技术有限公司 Service request processing method and device
CN104199739A (en) * 2014-08-26 2014-12-10 浪潮(北京)电子信息产业有限公司 Speculation type Hadoop scheduling method based on load balancing
CN105448006A (en) * 2015-12-30 2016-03-30 武汉邮电科学研究院 Intelligent supermarket cashier system and method based on mobile payment and IOT (Internet of Things)
CN105991588A (en) * 2015-02-13 2016-10-05 华为技术有限公司 ethod and apparatus for resisting message attack
CN106470169A (en) * 2015-08-19 2017-03-01 阿里巴巴集团控股有限公司 A kind of service request method of adjustment and equipment
CN107018175A (en) * 2017-01-11 2017-08-04 杨立群 The dispatching method and device of mobile cloud computing platform

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100094852A1 (en) * 2008-10-14 2010-04-15 Chetan Kumar Gupta Scheduling queries using a stretch metric
CN104199739A (en) * 2014-08-26 2014-12-10 浪潮(北京)电子信息产业有限公司 Speculation type Hadoop scheduling method based on load balancing
CN104202261A (en) * 2014-08-27 2014-12-10 华为技术有限公司 Service request processing method and device
CN105991588A (en) * 2015-02-13 2016-10-05 华为技术有限公司 ethod and apparatus for resisting message attack
CN106470169A (en) * 2015-08-19 2017-03-01 阿里巴巴集团控股有限公司 A kind of service request method of adjustment and equipment
CN105448006A (en) * 2015-12-30 2016-03-30 武汉邮电科学研究院 Intelligent supermarket cashier system and method based on mobile payment and IOT (Internet of Things)
CN107018175A (en) * 2017-01-11 2017-08-04 杨立群 The dispatching method and device of mobile cloud computing platform

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
XIANLIANG JIANG等: ""LRURC: A Low Complexity and Approximate Fair Active Queue Management Algorithm for Choking Non-Adaptive Flows"", 《IEEE COMMUNICATIONS LETTERS》 *
陆婷等: ""基于HBase的交通流数据实时存储系统"", 《计算机应用》 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109213561A (en) * 2018-09-14 2019-01-15 珠海国芯云科技有限公司 The equipment scheduling method and device of virtual desktop based on container
CN112306371A (en) * 2019-07-30 2021-02-02 伊姆西Ip控股有限责任公司 Method, apparatus and computer program product for storage management
CN110659132A (en) * 2019-08-29 2020-01-07 福建天泉教育科技有限公司 Request processing optimization method and computer-readable storage medium
CN110659132B (en) * 2019-08-29 2022-09-06 福建天泉教育科技有限公司 Request processing optimization method and computer-readable storage medium

Also Published As

Publication number Publication date
CN108304254B (en) 2022-02-22

Similar Documents

Publication Publication Date Title
CN107025205B (en) Method and equipment for training model in distributed system
CN107038069B (en) Dynamic label matching DLMS scheduling method under Hadoop platform
CN104991830B (en) YARN resource allocations and energy-saving scheduling method and system based on service-level agreement
US8812639B2 (en) Job managing device, job managing method and job managing program
CN105045658B (en) A method of realizing that dynamic task scheduling is distributed using multinuclear DSP embedded
CN103064746B (en) The accurate distribution method of processor resource of forecast dispatching is carried out based on current credit
CN102662763B (en) Virtual machine resource scheduling method based on service quality
CN110413412B (en) GPU (graphics processing Unit) cluster resource allocation method and device
CN104268018B (en) Job scheduling method and job scheduler in a kind of Hadoop clusters
CN104011680A (en) Scheduling virtual central processing units of virtual machines among physical processing units
CN106250218A (en) For using the system and method for sliding time window scheduler task
CN108304254A (en) Quick virtual machine process dispatch control method and device
CN105320570B (en) Method for managing resource and system
US10089155B2 (en) Power aware work stealing
CN103744716A (en) Dynamic interrupt balanced mapping method based on current virtual central processing unit (VCPU) scheduling state
CN108196939A (en) For the virtual machine intelligent management and device of cloud computing
CN106959895A (en) The resource regulating method and system of quick release thread
CN102662636B (en) Two-layer virtual machines-based concurrent job scheduling method
CN109656714B (en) GPU resource scheduling method of virtualized graphics card
CN111193802A (en) Dynamic resource allocation method, system, terminal and storage medium based on user group
CN114721818A (en) Kubernetes cluster-based GPU time-sharing method and system
CN104866370B (en) Towards the dynamic time piece dispatching method and system of Parallel application under a kind of cloud computing environment
CN114327894A (en) Resource allocation method, device, electronic equipment and storage medium
CN104123177B (en) A kind of multithreaded data synchronization method of no lock
CN104008001B (en) Virtual machine dynamic migrating method applied to mass data support

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