CN105045659A - Task overlapping and virtual machine migration based cloud fault-tolerant task scheduling method - Google Patents

Task overlapping and virtual machine migration based cloud fault-tolerant task scheduling method Download PDF

Info

Publication number
CN105045659A
CN105045659A CN201510422623.2A CN201510422623A CN105045659A CN 105045659 A CN105045659 A CN 105045659A CN 201510422623 A CN201510422623 A CN 201510422623A CN 105045659 A CN105045659 A CN 105045659A
Authority
CN
China
Prior art keywords
task
key plate
physical host
father
subtask
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
CN201510422623.2A
Other languages
Chinese (zh)
Other versions
CN105045659B (en
Inventor
朱晓敏
包卫东
刘忠
王吉
纪浩然
肖文华
陈超
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.)
National University of Defense Technology
Original Assignee
National University of Defense Technology
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 National University of Defense Technology filed Critical National University of Defense Technology
Priority to CN201510422623.2A priority Critical patent/CN105045659B/en
Publication of CN105045659A publication Critical patent/CN105045659A/en
Application granted granted Critical
Publication of CN105045659B publication Critical patent/CN105045659B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Landscapes

  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The present invention discloses a task overlapping and virtual machine migration based cloud fault-tolerant task scheduling method. The method is characterized by comprising: acquiring arrived dependency task group information and virtualized cloud physical host information; establishing a major version and a subversion for each task in the dependency task group by using a PB model; specifying earliest beginning time and latest finishing time for each version of each task in the dependency task group; dividing a plurality of virtual machines on each activated physical host, and acquiring information of each virtual machine on each activated physical host; loading each version of each task in the dependency task group in a specified time period to each virtual machine on each activated physical host; and running each loaded version of each task in the dependency task group in each virtual machine on each activated physical host according to the specified time schedule, returning a running result of each version of each task at the same time, and sending messages and data to other tasks.

Description

The fault-tolerant method for scheduling task of task based access control overlap and virtual machine (vm) migration in a kind of cloud
Technical field
The present invention relates to field of cloud calculation, especially, relate to the fault-tolerant method for scheduling task of task based access control overlap and virtual machine (vm) migration in a kind of cloud.
Background technology
Due to the unpredictability that computer system is made mistakes, add the support of fault-tolerance most important when designing dispatching algorithm.Fault-Tolerant Scheduling Algorithm can be divided into two classes substantially, i.e. static fault-tolerant scheduling and dynamic fault-tolerant scheduling: static fault-tolerant scheduling carried out scheduling decision before job invocation, was commonly used to property dispatching cycle task; Dynamic fault-tolerant scheduling is commonly used to scheduling aperiodicity task, and its task is uncertain for time of arrival.
At present, mainly contain two kinds of main fault-tolerant scheduling means in a distributed computing environment, namely bring up again and hand over and copy.Bring up again hand over refer to that the computing node distributed when a task breaks down after, this task is resubmited.Adopt heavy way of submission that the deadline of some tasks will be caused to postpone, even may not meet the off period of task.Copy and refer to by a Task Duplication is become multiple version, afterwards each version copied is assigned to different computing nodes, even if to ensure that, when resource breaks down, task still can be successfully completed before the off period.The version that task is replicated is more, and system survivability is stronger, but this will inevitably cause a large amount of resource consumptions.Therefore, adopt the copy mode of two versions, namely key plate originally becomes the fault-tolerant means widely adopted at present with subedition model (primary-backupmodel, hereinafter referred to as PB model).
In order to improve system schedulability and resource utilization under the prerequisite that guarantee is fault-tolerant, many scholars are had to have studied how to reduce system overhead by overlap technique when adopting PB model.Mainly contain the overlap scheme of two kinds at present: subedition-subedition overlap (backup-backupoverlapping is called for short BB overlapping), namely multiple different subedition can carry out overlap on same computing unit; Key plate basis-subedition overlap (primary-backupoverlapping is called for short PB overlapping), namely a key plate originally can be overlapping on same computing unit with the subedition of other tasks.In PB model, subedition can be further divided into two types, i.e. passive subedition (passivebackup) and driving pair version (activebackup).Passive subedition only starts when the key plate of its correspondence originally can not be successfully completed to perform, if key plate is originally successfully completed, subedition will be cancelled.Although said method can reduce resource occupation, can not ensure that all tasks can complete within the off period; On the contrary, driving pair version allows the key plate of task basis and subedition to have overlap on the execution time, adopt driving pair version executive mode can reduce the probability that task misses the off period, but resource utilization also can decrease simultaneously.There is the technical scheme of real-time task being carried out to overlap processing in prior art, but these technical schemes do not consider the virtual of system, be therefore only applicable to traditional distributed system, and be not suitable for virtual cloud computing environment.
Recently, the research of dependence task scheduling aspect in some clouds is also had.But these work all do not have the situation considering system fault when dispatching, and can not solve Fault-Tolerant Problems in cloud.For the problem of fault-tolerant method for scheduling task under lacking cloud computing environment in prior art, not yet there is effective solution at present.
Summary of the invention
For the problem of fault-tolerant method for scheduling task under lacking cloud computing environment in prior art, the object of the invention is to the fault-tolerant method for scheduling task proposing task based access control overlap and virtual machine (vm) migration in a kind of cloud, can under cloud computing environment, adopt PB model to carry out the scheduling of fault-tolerant task, improve the schedulability of resource utilization and fault-tolerant task.
Based on above-mentioned purpose, technical scheme provided by the invention is as follows:
According to an aspect of the present invention, provide task based access control overlap and the fault-tolerant method for scheduling task of virtual machine (vm) migration in a kind of cloud, comprising:
Obtain the physical host information of dependence task group information and the virtual cloud arrived;
Use PB model for each task creation key plate basis in dependence task group and subedition;
An earliest start time and a Late Finish is all specified according to each version that dependence task group information is each task in dependence task group;
According to the multiple physical host of dependence task group information activation, and mark off multiple virtual machine on each physical host be activated, obtain each virtual machine information on each physical host be activated;
According to each virtual machine information in the earliest start time of each version of each task in dependence task group and Late Finish and each physical host be activated, each version of each task in dependence task group is loaded on the time period of specifying in each virtual machine on each physical host be activated;
Run each version of each task in the dependence task group be loaded according to the arrangement of time of specifying in each virtual machine on each physical host be activated, return the operation result of each version of each task simultaneously, and message and data are sent to other tasks;
Complete whole task of dependence task group and return task result.
Wherein, dependence task group information comprises set of relationship and task deadline between set of tasks, task, set of tasks describes the size of each task in dependence task group, between task, set of relationship describes the dependence in dependence task group between any two tasks, and task deadline is the Late Finish of dependence task group; Physical host information comprises physical host set, and physical host set describes the size of each physical host processing power; Virtual machine information comprises the virtual machine set on each physical host be activated, and virtual machine set describes the physical host at each virtual machine place and the size of each virtual machine processing power.
And, use PB model for each task creation key plate basis in dependence task group and subedition, for specifying each task successively in dependence task group, and be appointed task creation key plate basis and a subedition, wherein, the key plate of same task originally repeats identical work with subedition.
Further, there is propagation delay time between multiple physical host be activated; An earliest start time and a Late Finish is all specified to comprise according to each version that dependence task group information is each task in dependence task group:
For the key plate basis of arbitrary subtask, its earliest start time is add the maximal value in the propagation delay time sum between father's task place physical host and place, subtask physical host the deadline of each father's task in its multiple father's task;
For the subedition of arbitrary subtask, its earliest start time is the higher value of this task of the key plate length thereof adding propagation delay time sum between father's task place physical host and place, subtask physical host and same task the deadline of each father's task in its multiple father's task;
For arbitrary non-subtask key plate this, to be the place virtual machine of this place physical host of key plate of this task be its earliest start time performs higher value in dependence task group information time of arrival at key plate this and ready time and this task place of this task;
For the subedition of arbitrary non-subtask, to be the place virtual machine of the subedition place physical host of this task be its earliest start time performs higher value in dependence task group information time of arrival at the subedition of this task and ready time and this task place;
For any version of arbitrary task, its Late Finish is the closing time of this task;
Wherein, a subtask and father's task are a dependence task pair, and subtask depends on father's task, and the execution result that subtask must obtain father's task could perform.
Simultaneously, according to each virtual machine information in the earliest start time of each version of each task in dependence task group and Late Finish and each physical host be activated, each virtual machine that each version of each task in dependence task group is loaded on each physical host be activated on the time period of specifying is comprised:
By the key plate of same subtask, this is dispensed on the virtual machine of two different physical hosts from subedition;
If the key plate of his father's task is originally strong key plate basis, the key plate of subtask is originally weak key plate basis and the key plate of father's task does not originally originally run with the key plate of subtask on same physical host, be then assigned to by the subedition of subtask on the physical host different from this place physical host of the key plate of father's task;
If the key plate of father's task be originally weak key plate this, then the subedition of father's task is assigned to from cause the key plate of father's task originally become weak key plate this all task versions this place physical host set of key plate in all different physical host of any physical host on;
If the key plate of father's task be originally weak key plate this, the key plate of subtask be originally strong key plate this and the key plate of father's task this originally do not run on same physical host with the key plate of subtask, then the key plate of subtask is originally assigned to and originally becomes on all different physical host of any physical host in this place physical host set of key plate of all task versions of weak key plate from causing the key plate of father's task;
If the key plate of father's task is originally weak key plate basis, and this key plate with subtask of the key plate of father's task this run on same physical host, then the subedition of subtask is assigned to from cause the key plate of father's task originally become weak key plate this all task versions this place physical host set of key plate in all different physical host of any physical host on;
Wherein, strong key plate this for when place physical host is not made mistakes one surely successful execution key plate this, weak key plate this for do not meet strong this condition of key plate key plate this.
And, the same virtual machine key plate of the subedition of father's task and subtask being originally assigned to Same Physical main frame runs, and make the subedition of father's task originally exist overlapping in time with the key plate of subtask, and the subedition of subtask is assigned to there is not any overlapping task physical host on.
Simultaneously, run each version of each task in the dependence task group be loaded according to the arrangement of time of specifying in each virtual machine on each physical host be activated, return the operation result of each version of each task simultaneously, and message and data sent to other tasks, comprising:
If the key plate of father's task is originally successfully completed, then the subedition transmission message to father's task cancels its execution, and this transmission of the key plate data to subtask allow it to perform;
If the key plate of father's task is originally strong key plate basis, the key plate of subtask is originally strong key plate basis and the key plate of father's task does not originally originally run with the key plate of subtask on same physical host, then the subedition of father's task does not send any message and data to the subedition of subtask;
If the key plate of father's task is originally strong key plate basis, the key plate of subtask is originally weak key plate basis and the key plate of father's task does not originally originally run with the key plate of subtask on same physical host, then the key plate of father's task does not originally send any message and data to the subedition of subtask;
If the key plate of father's task be originally strong key plate this, the key plate of subtask be originally this key plate with subtask of strong key plate this and the key plate of father's task this run on same physical host, then the subedition of father's task does not originally send any message and data to the key plate of subtask;
If the key plate of father's task be originally strong key plate this, the key plate of subtask be originally this key plate with subtask of weak key plate this and the key plate of father's task this run on same physical host, then the subedition of father's task does not originally send any message and data to the key plate of subtask;
If the key plate of father's task is originally weak key plate basis, the key plate of subtask is originally strong key plate basis, the key plate of father's task does not originally originally run with the key plate of subtask on same physical host, and when the key plate of subtask be originally assigned to cause the key plate of father's task originally become weak key plate this all task versions this place physical host set of key plate in any physical host on time, the subedition of father's task sends data to the subedition of subtask and allows it to perform;
If the key plate of father's task be originally weak key plate this, the key plate of subtask be originally strong key plate this, this key plate with subtask of the key plate of father's task this run on same physical host, and when the subedition of subtask be assigned to cause the key plate of father's task originally become weak key plate this all task versions this place physical host set of key plate in any physical host on time, the subedition of father's task allows it to perform to this transmission of key plate data of subtask.
And, when a version of a task return operation result be unsuccessfully time, by all task immigrations on the virtual machine at this version place of this task on new physics main frame, this virtual machine can not migrate on the physical host in the physical host set that can not be distributed by above-mentioned restriction by key plate this or the subedition of migration task; Virtual machine after virtual machine (vm) migration to new physics main frame still can be met the time constraints on old physical main frame, and the propagation delay time had in virtual machine between the physical host involved by task of dependence task and migration virtual machine place physical host still can meet above-mentioned existing requirement after virtual machine (vm) migration.
As can be seen from above, technical scheme provided by the invention replaces traditional PB model by setting up real-time fault tolerance model in virtual cloud, analyze and ensure that the task matching of fault-tolerant lower real-time dependence task and message propagation retrain, and the task that have employed is overlapping and virtual machine migration mechanism sets up fault-tolerant method for scheduling task, improve the schedulability of resource utilization under fault-tolerant guarantee and fault-tolerant task.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment below.Apparently, the accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, can also obtain other accompanying drawing according to these accompanying drawings.
Fig. 1 is the fault-tolerant method for scheduling task process flow diagram of task based access control overlap and virtual machine (vm) migration in a kind of cloud according to the embodiment of the present invention;
Fig. 2 is that in a kind of cloud according to the embodiment of the present invention, task based access control is overlapping with the fault-tolerant method for scheduling task of virtual machine (vm) migration, the message of strong key plate basis or data transitive relation figure;
Fig. 3 is that in a kind of cloud according to the embodiment of the present invention, task based access control is overlapping with the fault-tolerant method for scheduling task of virtual machine (vm) migration, the message of weak key plate basis or data transitive relation figure;
Fig. 4 is that in a kind of cloud according to the embodiment of the present invention, task based access control is overlapping with the fault-tolerant method for scheduling task of virtual machine (vm) migration, strong key plate this in the third situation, the message of subtask this start time of key plate when being later than the end time of father's task subedition or data transitive relation figure;
Fig. 5 is that in a kind of cloud according to the embodiment of the present invention, task based access control is overlapping with the fault-tolerant method for scheduling task of virtual machine (vm) migration, strong key plate this in the third situation, the end time of subtask this start time of key plate early than father's task subedition message or data transitive relation figure;
Fig. 6 is that in a kind of cloud according to the embodiment of the present invention, task based access control is overlapping with the fault-tolerant method for scheduling task of virtual machine (vm) migration, father's task have strong key plate this, the subtask message of key plate originally in different physical host situation with strong key plate this and father's task and subtask or data transitive relation figure;
Fig. 7 is that in a kind of cloud according to the embodiment of the present invention, task based access control is overlapping with the fault-tolerant method for scheduling task of virtual machine (vm) migration, father's task have strong key plate this, the subtask message of key plate originally in different physical host situation with weak key plate this and father's task and subtask or data transitive relation figure;
Fig. 8 is that in a kind of cloud according to the embodiment of the present invention, task based access control is overlapping with the fault-tolerant method for scheduling task of virtual machine (vm) migration, father's task have strong key plate this, subtask has message originally under same physical masters scenario of strong key plate this and the key plate of father's task and subtask or data transitive relation figure;
Fig. 9 is that in a kind of cloud according to the embodiment of the present invention, task based access control is overlapping with the fault-tolerant method for scheduling task of virtual machine (vm) migration, father's task have strong key plate this, subtask has message originally under same physical masters scenario of weak key plate this and the key plate of father's task and subtask or data transitive relation figure;
Figure 10 is that in a kind of cloud according to the embodiment of the present invention, task based access control is overlapping with the fault-tolerant method for scheduling task of virtual machine (vm) migration, the message between a subtask and three father's tasks thereof or data transitive relation figure;
Figure 11 is that in a kind of cloud according to the embodiment of the present invention, task based access control is overlapping with the fault-tolerant method for scheduling task of virtual machine (vm) migration, father's task have weak key plate this, the subtask message of key plate originally in different physical host situation with strong key plate this and father's task and subtask or data transitive relation figure;
Figure 12 is that in a kind of cloud according to the embodiment of the present invention, task based access control is overlapping with the fault-tolerant method for scheduling task of virtual machine (vm) migration, father's task have weak key plate this, the subtask message of key plate originally in different physical host situation with weak key plate this and father's task and subtask or data transitive relation figure;
Figure 13 is that in a kind of cloud according to the embodiment of the present invention, task based access control is overlapping with the fault-tolerant method for scheduling task of virtual machine (vm) migration, father's task have weak key plate this, subtask has message originally under same physical masters scenario of weak key plate this or strong key plate this and the key plate of father's task and subtask or data transitive relation figure;
Figure 14 is that in a kind of cloud according to the embodiment of the present invention, task based access control is overlapping with the fault-tolerant method for scheduling task of virtual machine (vm) migration, and overlapping and this subedition early than father's task of the key plate of subtask of PB starts message in situation or data transitive relation figure;
Figure 15 is that in a kind of cloud according to the embodiment of the present invention, task based access control is overlapping with the fault-tolerant method for scheduling task of virtual machine (vm) migration, and the subedition that the overlapping and key plate of subtask of PB is originally later than father's task starts message in situation or data transitive relation figure;
Figure 16 is that in a kind of cloud according to the embodiment of the present invention, task based access control is overlapping with the fault-tolerant method for scheduling task of virtual machine (vm) migration, the message between overlapping set of tasks or data transitive relation figure;
Figure 17 is that in a kind of cloud according to the embodiment of the present invention, task based access control is overlapping with the fault-tolerant method for scheduling task of virtual machine (vm) migration, the message in the associated host of carrying out virtual machine (vm) migration between task or data transitive relation figure.
Embodiment
Clearly understand for making the object, technical solutions and advantages of the present invention, below in conjunction with the accompanying drawing in the embodiment of the present invention, to the technical scheme in the embodiment of the present invention carry out further clear, complete, describe in detail, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, the every other embodiment that those of ordinary skill in the art obtain, all belongs to the scope of protection of the invention.
According to embodiments of the invention, provide the fault-tolerant method for scheduling task of task based access control overlap and virtual machine (vm) migration in a kind of cloud.
As shown in Figure 1, fault-tolerant method for scheduling task that is overlapping according to task based access control in a kind of cloud provided of the embodiment of the present invention and virtual machine (vm) migration comprises:
Step S101, obtains the physical host information of dependence task group information and the virtual cloud arrived;
Step S103, uses PB model for each task creation key plate basis in dependence task group and subedition;
Step S105, all specifies an earliest start time and a Late Finish according to each version that dependence task group information is each task in dependence task group;
Step S107, according to the multiple physical host of dependence task group information activation, and marks off multiple virtual machine, obtains each virtual machine information on each physical host be activated on each physical host be activated;
Step S109, according to each virtual machine information in the earliest start time of each version of each task in dependence task group and Late Finish and each physical host be activated, each version of each task in dependence task group is loaded on the time period of specifying in each virtual machine on each physical host be activated;
Step S111, run each version of each task in the dependence task group be loaded according to the arrangement of time of specifying in each virtual machine on each physical host be activated, return the operation result of each version of each task simultaneously, and message and data are sent to other tasks;
Step S113, completes whole task of dependence task group and returns task result.
Wherein, dependence task group information comprises set of relationship and task deadline between set of tasks, task, set of tasks describes the size of each task in dependence task group, between task, set of relationship describes the dependence in dependence task group between any two tasks, and task deadline is the Late Finish of dependence task group; Physical host information comprises physical host set, and physical host set describes the size of each physical host processing power; Virtual machine information comprises the virtual machine set on each physical host be activated, and virtual machine set describes the physical host at each virtual machine place and the size of each virtual machine processing power.
And, use PB model for each task creation key plate basis in dependence task group and subedition, for specifying each task successively in dependence task group, and be appointed task creation key plate basis and a subedition, wherein, the key plate of same task originally repeats identical work with subedition.
Further, there is propagation delay time between multiple physical host be activated; An earliest start time and a Late Finish is all specified to comprise according to each version that dependence task group information is each task in dependence task group:
For the key plate basis of arbitrary subtask, its earliest start time is add the maximal value in the propagation delay time sum between father's task place physical host and place, subtask physical host the deadline of each father's task in its multiple father's task;
For the subedition of arbitrary subtask, its earliest start time is the higher value of this task of the key plate length thereof adding propagation delay time sum between father's task place physical host and place, subtask physical host and same task the deadline of each father's task in its multiple father's task; ;
For arbitrary non-subtask key plate this, to be the place virtual machine of this place physical host of key plate of this task be its earliest start time performs higher value in dependence task group information time of arrival at key plate this and ready time and this task place of this task;
For the subedition of arbitrary non-subtask, to be the place virtual machine of the subedition place physical host of this task be its earliest start time performs higher value in dependence task group information time of arrival at the subedition of this task and ready time and this task place;
For any version of arbitrary task, its Late Finish is the closing time of this task;
Wherein, a subtask and father's task are a dependence task pair, and subtask depends on father's task, and the execution result that subtask must obtain father's task could perform.
Simultaneously, according to each virtual machine information in the earliest start time of each version of each task in dependence task group and Late Finish and each physical host be activated, each virtual machine that each version of each task in dependence task group is loaded on each physical host be activated on the time period of specifying is comprised:
By the key plate of same subtask, this is dispensed on the virtual machine of two different physical hosts from subedition;
If the key plate of his father's task is originally strong key plate basis, the key plate of subtask is originally weak key plate basis and the key plate of father's task does not originally originally run with the key plate of subtask on same physical host, be then assigned to by the subedition of subtask on the physical host different from this place physical host of the key plate of father's task;
If the key plate of father's task be originally weak key plate this, then the subedition of father's task is assigned to from cause the key plate of father's task originally become weak key plate this all task versions this place physical host set of key plate in all different physical host of any physical host on;
If the key plate of father's task be originally weak key plate this, the key plate of subtask be originally strong key plate this and the key plate of father's task this originally do not run on same physical host with the key plate of subtask, then the key plate of subtask is originally assigned to and originally becomes on all different physical host of any physical host in this place physical host set of key plate of all task versions of weak key plate from causing the key plate of father's task;
If the key plate of father's task is originally weak key plate basis, and this key plate with subtask of the key plate of father's task this run on same physical host, then the subedition of subtask is assigned to from cause the key plate of father's task originally become weak key plate this all task versions this place physical host set of key plate in all different physical host of any physical host on;
Wherein, strong key plate this for when place physical host is not made mistakes one surely successful execution key plate this, weak key plate this for do not meet strong this condition of key plate key plate this.
And, the same virtual machine key plate of the subedition of father's task and subtask being originally assigned to Same Physical main frame runs, and make the subedition of father's task originally exist overlapping in time with the key plate of subtask, and the subedition of subtask is assigned to there is not any overlapping task physical host on.
Simultaneously, run each version of each task in the dependence task group be loaded according to the arrangement of time of specifying in each virtual machine on each physical host be activated, return the operation result of each version of each task simultaneously, and message and data sent to other tasks, comprising:
If the key plate of father's task is originally successfully completed, then the subedition transmission message to father's task cancels its execution, and this transmission of the key plate data to subtask allow it to perform;
If the key plate of father's task is originally strong key plate basis, the key plate of subtask is originally strong key plate basis and the key plate of father's task does not originally originally run with the key plate of subtask on same physical host, then the subedition of father's task does not send any message and data to the subedition of subtask;
If the key plate of father's task is originally strong key plate basis, the key plate of subtask is originally weak key plate basis and the key plate of father's task does not originally originally run with the key plate of subtask on same physical host, then the key plate of father's task does not originally send any message and data to the subedition of subtask;
If the key plate of father's task be originally strong key plate this, the key plate of subtask be originally this key plate with subtask of strong key plate this and the key plate of father's task this run on same physical host, then the subedition of father's task does not originally send any message and data to the key plate of subtask;
If the key plate of father's task be originally strong key plate this, the key plate of subtask be originally this key plate with subtask of weak key plate this and the key plate of father's task this run on same physical host, then the subedition of father's task does not originally send any message and data to the key plate of subtask;
If the key plate of father's task is originally weak key plate basis, the key plate of subtask is originally strong key plate basis, the key plate of father's task does not originally originally run with the key plate of subtask on same physical host, and when the key plate of subtask be originally assigned to cause the key plate of father's task originally become weak key plate this all task versions this place physical host set of key plate in any physical host on time, the subedition of father's task sends data to the subedition of subtask and allows it to perform;
If the key plate of father's task be originally weak key plate this, the key plate of subtask be originally strong key plate this, this key plate with subtask of the key plate of father's task this run on same physical host, and when the subedition of subtask be assigned to cause the key plate of father's task originally become weak key plate this all task versions this place physical host set of key plate in any physical host on time, the subedition of father's task allows it to perform to this transmission of key plate data of subtask.
And, when a version of a task return operation result be unsuccessfully time, by all task immigrations on the virtual machine at this version place of this task on new physics main frame, this virtual machine can not migrate on the physical host in the physical host set that can not be distributed by above-mentioned restriction by key plate this or the subedition of migration task; Virtual machine after virtual machine (vm) migration to new physics main frame still can be met the time constraints on old physical main frame, and the propagation delay time had in virtual machine between the physical host involved by task of dependence task and migration virtual machine place physical host still can meet above-mentioned existing requirement after virtual machine (vm) migration.
Technical characteristic of the present invention is set forth further below according to specific embodiment.
Usually do not have periodically because task arrives, in the present embodiment, we consider the dependence task dynamically arrived.One group of dependence task can be expressed as a directed acyclic graph (DirectedAcyclicGraph, hereinafter referred to as DAG).A DAG can be defined as G={T, E}, wherein, and T={t 1, t 2..., t nrepresenting real-time aperiodic task set, E represents the set of relationship between task.E ij=(t i, t j) represent task t jdepend on task t i, namely only have t jobtain t iexecution result or message could perform.Therefore, we claim t ifor t jfather's task, t jfor t isubtask.To arbitrary task t i∈ T, P (t i) and C (t i) represent task t respectively ifather's set of tasks and subtask combine. expression task t ithere is no father's task, expression task t ithere is no subtask.The time that reaches of a DAG and off period are expressed as a (G) and d (G).Task t ia tlv triple t can be described as i=(a i, d i, s i), wherein, a i, d iand s irepresent task t respectively ithe time that reaches, off period and task size.Task t ioff period d ican be calculated by the off period d (G) of its place DAG.Task size 1,000,000 instruction numbers (millioninstructions, hereinafter referred to as MI) are weighed.In PB model, for arbitrary task t i, there are two versions in ∈ T, is expressed as key plate originally and subedition with be assigned on different main frames fault-tolerant to realize. with represent key plate respectively originally start time and the deadline.Similarly, with vice version respectively start time and the deadline. with represent respectively with father's set of tasks, with represent respectively with subtask set.
Virtual cloud can be described as the unlimited set H={h of a physical host 1, h 2....Although the host number in cloud is unlimited, the quantity of mobile host computers is limited.Set represent mobile host computers set in cloud, H-H arepresent Shutdown Hosts set.To arbitrary main frame h k∈ H, its processing power p kweigh with 1,000,000 instruction numbers per second (millioninstructionspersecond, hereinafter referred to as MIPS).Each main frame h kon have multiple virtual machine, with set represent, each virtual machine v jk∈ V kthere is different processing power p jk.For main frame h kon virtual machine, its processing power meet v jkready time be expressed as r jk.
In a virtual cloud, a main frame can have one or more virtual machine to run thereon, and therefore task is assigned to each virtual machine and non-immediate is assigned to certain main frame.We suppose, the processing power of virtual machine has isomerism, and namely virtual machine can have different processing poweies.The key plate basis of a task and the execution time of subedition on these virtual machines can use matrix E respectively pand E brepresent, wherein element with represent respectively with at virtual machine v jkon execution time.We use with represent task key plate respectively originally and subedition with virtual machine v jkbetween mapping relations: if be assigned to virtual machine v jkon then otherwise similarly, if be assigned to virtual machine v jkon then otherwise with represent respectively with assigned virtual machine, with then represent with assigned main frame.Therefore, mean x i j k B = 1 Mean v ( t i B ) = v j k .
represent with between limit, wherein X, Y ∈ P, B}, namely can be also can be equally, both can be also can be to each limit from arrive data or message transmission time be expressed as if with there is dependence and be assigned to same main frame, then in addition, dv is made ijexpression task t ito task t jdata or transmission of messages amount, represent main frame arrive transmission speed, known tt ij XY = d v ij / ts ( h ( t i X ) , h ( t j Y ) ) , Wherein task t jkey plate basis and subedition earliest start time can be calculated as respectively:
late Finish determine therefore have by the off period of task:
lft j Y = d j - - - ( 3 )
the actual start time be the time performed is started after being scheduled. can be placed on by with the free time limited is in groove.Namely our regulation goal finds suitable job start time, accepts more DAG in real time as far as possible, improves the handling capacity of system.
It is important to note that the mistake described in technical scheme of the present invention is for make mistakes for main frame, main frame is made mistakes and is caused other levels as the interrupt run of virtual machine and application.Mistake both can be temporary transient also can be permanent, but each mistake is separate, and makeing mistakes of a main frame can not affect other main frames.Meanwhile, the probability of simultaneously makeing mistakes due to two main frames is very little, therefore supposes the time in office, and a main frame is made mistakes at the most.After a main frame is made mistakes, key plate originally task on the host can be successfully completed by its subedition before another main frame is made mistakes.Further, there is a detection mechanism of makeing mistakes in system, can provide error message, new task can not be scheduled on the main frame of having made mistakes.System also adopts reclaim mechanism, if namely key plate is originally successfully completed, so the execution of subedition is interrupted, and shared resource is recovered.
For the situation that multiple main frame lost efficacy simultaneously, this failure model can be expanded by two steps below.First, main frame in cloud is divided into some groups; Afterwards, in each group, above-mentioned error model is adopted.By adopting proposed fault tolerant mechanism, to solve the situation of many host fails in each group.
Hereafter analyze to task matching when adopting PB model to carry out fault-tolerant and transmission of messages, provide and realize fault-tolerant institute's Prescribed Properties.
For convenience of analyzing, first we define strong key plate basis and weak key plate basis.
definition 1, strong key plate basis: to any one task key plate originally if the main frame at its place do not make mistakes, necessarily can perform, then claim for strong key plate basis.
Fig. 2 gives a strong key plate example originally.As shown in Figure 2, t it jfather's task, i.e. t jt must be received ithe message transmitted or data could start to perform, and the dotted line of band arrow represents from this messaging relationship to subedition of key plate and direction.As shown in Figure 2, as long as the main frame h at place 3do not make mistakes, just energy successful execution, what can receive that his father's task transmits disappears or data.Therefore, it is a strong key plate basis.
definition 2, weak key plate basis: to any one task key plate originally if the main frame at its place do not make mistakes, also not necessarily can perform, then claim for weak key plate basis.
Fig. 3 gives a weak key plate example originally.As shown in Figure 3, suppose the main frame h at place 1? make mistakes before completing, so to perform.But due to can not receive the message transmitted or data, although the main frame at place is not made mistakes, still can not perform.Therefore, it is a weak key plate basis.
According to definition 1 and definition 2, we have following proposition:
proposition 1, if have any one to set up in following three kinds of situations, then strong key plate basis:
(1)
(2)
(3) ∀ t i , t i ∈ P ( t j ) , h ( t i P ) = h ( t j P ) , S j P ≥ f i P + tt i j P P .
Otherwise, it is weak key plate basis.
The first situation can directly be released according to definition 1.The second situation can be released according to Fig. 2.For the third situation, Fig. 4 and Fig. 5 gives two examples, and wherein key plate is originally assigned to same main frame, and subedition is assigned to different main frames.Wherein, Fig. 4 is the situation of the end time being later than father's task subedition subtask this start time of key plate, and Fig. 5 is the situation of subtask this start time of key plate early than the end time of father's task subedition.
From Fig. 4 and Fig. 5, we can find no matter whether can receive message or data, can receive message or data.According to definition 1, if main frame h 1? do not make mistakes before completing, then necessarily can successful execution complete.Therefore it is strong key plate basis.
When we analyze and adopt PB model to carry out fault-tolerant below, the schedule constraints of key plate basis and subedition.
Suppose t i, t j∈ T, t i∈ P (t j), t j∈ C (t i), first use a lemma as follows:
lemma 1, to any two dependence task t iand t j, t it jfather's task, if be successfully completed, then the message sent or data must send to simultaneously with
Prove: adopt reduction to absurdity.Suppose do not send after being successfully completed message or data to when ? make mistakes before, due to successful execution completes, be cancelled, cause have no chance to perform.Meanwhile, can not successful execution complete, must perform.But, do not receive the message sent or data, therefore can not perform.Contradiction is produced with fault-tolerant guarantee.Therefore, the message sent or data must send to simultaneously with
Lemma 1 indicates the constraint connected from the transmission of father's task.The constraint do not connected from the transmission of father's task is subject to the impact of the type of father's task and its distribution on main frame, hereafter will discuss this problem in detail.
First discuss and work as for the situation in this time of strong key plate.If t jt isubtask, can be strong key plate basis or weak key plate basis, in addition or respectively these four kinds of situations are discussed below.
situation 1, strong key plate basis, fig. 6 gives an example of situation 1.
As shown in Figure 6, limit it is redundancy.It is that is, fault-tolerant for realizing, do not need from receipt message or data.According to lemma 1, limit and limit needs.If limit also need, should perform.If perform, then one fixes on make mistakes before.According to our fault-tolerant hypothesis, now do not have other main frames and make mistakes, so only need pass through limit transmit message or data to , can ensure be successfully completed.Therefore, limit it is redundancy.
Eliminate limit start time can suitably move forward, add the probability completed within the off period. can be recalculated as being:
est j B = m a x { s j P , f i P + tt i j P B } - - - ( 4 )
situation 2, weak key plate basis, fig. 7 gives an example of situation 2.
As shown in Figure 7, limit with not redundancies, otherwise can not realize fault-tolerant.It should be noted that must be with with limit is had to be connected, and unlike only need and there is limit.Fig. 7 shows only receive from the example transmitting message or data (only considers t iand t jtwo dependence task).As shown in Figure 7, if ? make mistakes before, with all can not perform.Therefore, must be with between exist message or data transmission connect.Therefore, earliest start time can be calculated as:
est j B = m a x { s j P , f i P + tt i j P B , f i B + tt i j B B } - - - ( 5 )
According to above to the analysis of situation 1 and situation 2, obtain following proposition.
proposition 2, t i∈ P (t j), t j∈ C (t i), if be strong key plate this and then: 1) if strong key plate basis, so must be with with there is (i.e. limit, limit with ), must be with there is (i.e. limit, limit ); 2) if weak key plate basis, so must be with there is (i.e. limit, limit ), must and with there is (i.e. limit, limit with ).
proposition 3, t i∈ P (t j), t j∈ C (t i), if strong key plate basis, be weak key plate this and so can not be assigned to in proposition 3, if if this main frame is made mistakes, due to that weak key plate originally can not perform, must perform, but the main frame be assigned with is made mistakes, and causes t jhave no chance to perform, therefore can not be assigned to
situation 3, strong key plate basis, fig. 8 gives an example of situation 3.
In fig. 8, limit it is redundancy.According to lemma 1, limit and limit must have.If had then with need to perform.And the condition performed is ? make mistakes before, this means can not perform.Therefore, when after execution, only need pass-along message or data to therefore limit it is redundancy.
situation 4, weak key plate basis, fig. 9 gives an example of situation 3.
According to lemma 1, limit and limit must have.In addition, exist when makeing mistakes, limit needs.In situation 3 and situation 4 earliest start time can calculate according to formula (5).
Based on above-mentioned analysis, we obtain following proposition:
proposition 4, t i∈ P (t j), t j∈ C (t i), if be strong key plate this and so must be with there is (i.e. limit, limit ), must be with with there is (i.e. limit, limit with ).
Then discuss and work as for the situation in this time of weak key plate. for weak key plate this time, situation is more complicated, for ease of analyzing, first provides following 3 definition:
definition 3, cause weak key plate set of tasks Δ originally i{ }: refer to those father's set of tasks of message that his father's task subedition transmits or data can not be received.
definition 4, cause this set of task key plate originally of weak key plate refer to set Δ ithe set of this formation of task key plate in { }.
definition 5, cause weak key plate this place host complexes of task key plate originally refer to set the set that this place main frame of middle task key plate is formed.
Figure 10 gives the example of definition 3,4,5.As shown in Figure 10, t ithere are 3 father task t a, t band t c.But only have t aand t cmake become weak key plate originally.Therefore, Δ i{ } becomes Δ i{ a, c}={t a, t c; Δ i P { a , c } = { t a P , t c P } ; H S ( Δ i P { a , c } ) = { h ( t a P ) , h ( t c P ) } = { h 2 , h 5 } .
lemma 2, for a weak key plate originally its corresponding subedition set can not be assigned to in arbitrary main frame on.
Prove: adopt reduction to absurdity.Suppose be assigned to set in main frame h kon, if h k? make mistakes before, can not receive from the message sent or data, therefore have to perform.But, be assigned to h kon, cause with all can not be successfully completed.Contradiction is produced with fault-tolerant guarantee.
Based on above definition and lemma, we consider t ithe assignment constraints of subtask.Suppose t j∈ C (t i), may be strong key plate basis or weak key plate basis, or therefore there are 4 kinds of different situations to need to analyze.
situation 5, for strong key plate basis, and figure 11 gives an example of situation 5.
As shown in figure 11, for weak key plate basis, for strong key plate basis, and if there is no limit then can not be assigned to on.
theorem 1, t i∈ P (t j), t j∈ C (t i), if weak key plate basis, strong key plate basis, then: 1) can not be assigned to in arbitrary main frame on; 2) if be assigned to in a certain main frame on, must limit be increased
Prove: adopt reduction to absurdity.Suppose be assigned to in a certain main frame h kon, and there is no limit if h k? make mistakes before, can not perform.According to lemma 2, can successful execution.Due to be assigned to h k, can not perform, therefore must send message (or data) to but there is no limit produce contradiction.
situation 6, for weak key plate basis, and figure 12 shows an example of situation 6.
With situation 5 similarly, as shown in Figure 12, when for weak key plate basis, for weak key plate basis, and time, can not be assigned to on.
situation 7, for strong key plate basis, and
situation 8, for weak key plate basis, and
Figure 13 shows an example of situation 7 and situation 8.
As shown in Figure 13, when for weak key plate basis, and time, no matter strong key plate basis or weak key plate basis, all can not be assigned to on.
theorem 2, t i∈ P (t j), t j∈ C (t i), if weak key plate basis, also be weak key plate basis, and so can not be assigned to in arbitrary main frame on.
Prove: adopt reduction to absurdity.Suppose be assigned to in a certain main frame h kon, if h k? make mistakes before, can not perform, therefore can not perform.According to lemma 2, perform and receive message or data after, must perform.But, be assigned to h kon, can not perform, produce contradiction with fault-tolerant guarantee.Therefore can not be assigned to in arbitrary main frame on.
theorem 3, t i∈ P (t j), t j∈ C (t i), if weak key plate basis, strong key plate basis, and so 1) can not be assigned to in arbitrary main frame on; 2) if be assigned to in a certain main frame on, must limit be increased
Prove: adopt reduction to absurdity.Suppose be assigned to in a certain main frame h kon, and there is no limit if h k? make mistakes before, can not perform.According to lemma 2, perform. must perform.Owing to there is no limit have to perform, but, be assigned to h kon, can not perform, produce contradiction with fault-tolerant guarantee.If therefore do not increase limit can not be assigned to in arbitrary main frame on.
Hereafter overlapping for analyzing under the fault-tolerant prerequisite of guarantee of task and virtual machine (vm) migration are limited.
In systems in practice, the task subedition due to the overwhelming majority only takies resource and does not perform, and therefore we adopt overlapping mechanism to improve the schedulability of cloud resource utilization and then raising system in this article.
Be different from independent task, in the fault-tolerant scheduling having dependence task, subedition-subedition overlap (namely aforesaid BB is overlapping) mode can not be adopted, key plate basis-subedition overlap (namely aforesaid PB is overlapping) mode can only be adopted.Figure 14 and Figure 15 gives two examples of PB overlap, wherein shown in Figure 14 is this situation about starting early than the subedition of father's task of key plate of subtask in PB overlap, and shown in Figure 15 is the situation that subedition that the key plate of subtask in PB overlap is originally later than father's task starts.
Figure 14 and Figure 15 respectively illustrates with overlapping two kinds may situation.In both cases, even if when a certain main frame is made mistakes, t iand t jall can successful execution.In fig. 14, when after being successfully completed, to be cancelled, therefore can perform; In fig .15, when after being successfully completed, ? be cancelled before starting execution, with there is no the conflict on the execution time, therefore can realize fault-tolerant.
definition 6, set OHS{}: the set that the main frame assigned by overlapping task (key plate basis or subedition) is formed.
Overlapping task refers to the task that a certain version of this task is overlapping with a certain version of another task.As shown in figure 16, task t iwith task t joverlap, task t jwith task t koverlapping.These 3 tasks are overlapping task, then corresponding set OHS{} is { h 1, h 2, h 4.
proposition 5, if overlapping with the subedition on main frame a certain in OHS{}, so can not be assigned on the arbitrary main frame in OHS{}.
Figure 16 gives an example of proposition 5.As shown in Figure 16, with overlap, h can not be assigned to 1, h 2and h 4on.Suppose the main frame h at place 1? make mistakes before, perform, therefore can not perform, finally cause perform.But due to h 1make mistakes, can not perform.Similar situation is at h 1also can occur when makeing mistakes.
On the other hand, in cloud, virtual machine (vm) migration integrates the effective means that virtual machine improves resource utilization ratio and reduction energy consumption.It should be noted that virtual machine (vm) migration must meet above-mentioned task matching and Message Transmission constraint could realize fault-tolerant.
proposition 6, suppose that NH{} is the host complexes that task (key plate basis or subedition) can not be distributed, so the virtual machine at this task place can not move on the arbitrary main frame in NH{}.
Figure 17 gives an example.As shown in figure 17, h can not be assigned to 2on, therefore the virtual machine v at place 41h can not be migrated to 2on.
After virtual machine (vm) migration, message or data transmission period may change, and a task is run and may not be met time limit requirement on an other main frame, therefore must meet time constraints in virtual machine (vm) migration process.
proposition 7, suppose moved, ∀ t i ∈ P ( t j ) , t k ∈ C ( t j ) , f i X + tt i j XX ′ + e j X > d j , f j X ′ + tt j k XX ′ + e k X > d k , Wherein with for the new transmission time, for the new deadline.
If above-mentioned constraint can ensure, the real-time fault tolerance demand of system during virtual machine (vm) migration, can be ensured.Compared with traditional distributed system, adopt virtual machine migration technology can effective elevator system resource utilization.
In sum, by means of technique scheme of the present invention, traditional PB model is replaced by setting up real-time fault tolerance model in virtual cloud, analyze and ensure that the task matching of fault-tolerant lower real-time dependence task and message propagation retrain, and the task that have employed is overlapping and virtual machine migration mechanism sets up fault-tolerant method for scheduling task, improve the schedulability of resource utilization under fault-tolerant guarantee and fault-tolerant task.
Those of ordinary skill in the field are to be understood that: the foregoing is only specific embodiments of the invention; be not limited to the present invention; within the spirit and principles in the present invention all, any amendment made, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.

Claims (8)

1. task based access control overlap and a fault-tolerant method for scheduling task for virtual machine (vm) migration in cloud, is characterized in that, comprising:
Obtain the physical host information of dependence task group information and the virtual cloud arrived;
PB model is used to be this and subedition of each task creation key plate in described dependence task group;
An earliest start time and a Late Finish is all specified according to each version that described dependence task group information is each task in described dependence task group;
According to the multiple described physical host of described dependence task group information activation, and mark off multiple virtual machine on each described physical host be activated, obtain each described virtual machine information on each described physical host be activated;
According to each described virtual machine information in the earliest start time of each version of each task in dependence task group and Late Finish and each described physical host be activated, each version of each task in described dependence task group is loaded on the time period of specifying in each described virtual machine on each described physical host be activated;
Run each version of each task in the described dependence task group be loaded according to the arrangement of time of specifying in each described virtual machine on each described physical host be activated, return the operation result of each version of each task simultaneously, and message and data are sent to other tasks;
Complete whole task of dependence task group and return task result.
2. task based access control overlap and the fault-tolerant method for scheduling task of virtual machine (vm) migration in a kind of cloud according to claim 1, is characterized in that:
Described dependence task group information comprises set of relationship and task deadline between set of tasks, task, described set of tasks describes the size of each task in described dependence task group, between described task, set of relationship describes the dependence in described dependence task group between any two tasks, and described task deadline is the Late Finish of described dependence task group;
Described physical host information comprises physical host set, and described physical host set describes the size of each described physical host processing power;
Described virtual machine information comprises the virtual machine set on each described physical host be activated, and described virtual machine set describes the physical host at each described virtual machine place and the size of each described virtual machine processing power.
3. the overlapping fault-tolerant method for scheduling task with virtual machine (vm) migration of task based access control in a kind of cloud according to claim 2, it is characterized in that, described use PB model is this and subedition of each task creation key plate in described dependence task group, for specifying each task successively in described dependence task group, and be appointed task creation key plate basis and a subedition, wherein, the key plate of described same task originally repeats identical work with subedition.
4. task based access control overlap and the fault-tolerant method for scheduling task of virtual machine (vm) migration in a kind of cloud according to claim 3, is characterized in that there is propagation delay time between multiple described physical host be activated; An earliest start time and a Late Finish is all specified to comprise according to each version that described dependence task group information is each task in described dependence task group:
For the key plate basis of arbitrary subtask, its earliest start time is add the maximal value in the propagation delay time sum between described father's task place physical host and place, subtask physical host the deadline of each father's task in its multiple father's task;
For the subedition of arbitrary subtask, its earliest start time is the higher value of this task of the key plate length thereof adding propagation delay time sum between described father's task place physical host and place, subtask physical host and same task the deadline of each father's task in its multiple father's task;
For arbitrary non-subtask key plate this, to be the place virtual machine of this place physical host of key plate of this task be its earliest start time performs higher value in dependence task group information time of arrival at key plate this and ready time and this task place of this task;
For the subedition of arbitrary non-subtask, to be the place virtual machine of the subedition place physical host of this task be its earliest start time performs higher value in dependence task group information time of arrival at the subedition of this task and ready time and this task place;
For any version of arbitrary task, its Late Finish is the closing time of this task;
Wherein, a subtask and father's task are a dependence task pair, and described subtask depends on described father's task, and the execution result that described subtask must obtain described father's task could perform.
5. the overlapping fault-tolerant method for scheduling task with virtual machine (vm) migration of task based access control in a kind of cloud according to claim 3, it is characterized in that, according to each described virtual machine information in the earliest start time of each version of each task in dependence task group and Late Finish and each described physical host be activated, by each version of each task in described dependence task group, each described virtual machine be loaded on the time period of specifying on each described physical host be activated comprises:
By the key plate of described same subtask, this is dispensed on the virtual machine of two different physical hosts from subedition;
If the key plate of his father's task is originally strong key plate basis, the key plate of subtask is originally weak key plate basis and the key plate of father's task does not originally originally run with the key plate of subtask on same physical host, be then assigned to by the subedition of subtask on the physical host different from this place physical host of the key plate of father's task;
If the key plate of father's task be originally weak key plate this, then the subedition of father's task is assigned to from cause the key plate of father's task originally become weak key plate this all task versions this place physical host set of key plate in all different physical host of any physical host on;
If the key plate of father's task be originally weak key plate this, the key plate of subtask be originally strong key plate this and the key plate of father's task this originally do not run on same physical host with the key plate of subtask, then the key plate of subtask is originally assigned to and originally becomes on all different physical host of any physical host in this place physical host set of key plate of all task versions of weak key plate from causing the key plate of father's task;
If the key plate of father's task is originally weak key plate basis, and this key plate with subtask of the key plate of father's task this run on same physical host, then the subedition of subtask is assigned to from cause the key plate of father's task originally become weak key plate this all task versions this place physical host set of key plate in all different physical host of any physical host on;
Wherein, described strong key plate this for when place physical host is not made mistakes one surely successful execution key plate this, described weak key plate this for do not meet described strong this condition of key plate key plate this.
6. the overlapping fault-tolerant method for scheduling task with virtual machine (vm) migration of task based access control in a kind of cloud according to claim 5, it is characterized in that, the same virtual machine key plate of the subedition of father's task and subtask being originally assigned to Same Physical main frame runs, and make the subedition of father's task originally exist overlapping in time with the key plate of subtask, and the subedition of subtask is assigned to there is not any overlapping task physical host on.
7. the overlapping fault-tolerant method for scheduling task with virtual machine (vm) migration of task based access control in a kind of cloud according to claim 5, it is characterized in that, run each version of each task in the described dependence task group be loaded according to the arrangement of time of specifying in each described virtual machine on each described physical host be activated, return the operation result of each version of each task simultaneously, and message and data are sent to other tasks, comprising:
If the key plate of father's task is originally successfully completed, then the subedition transmission message to father's task cancels its execution, and this transmission of the key plate data to subtask allow it to perform;
If the key plate of father's task is originally strong key plate basis, the key plate of subtask is originally strong key plate basis and the key plate of father's task does not originally originally run with the key plate of subtask on same physical host, then the subedition of father's task does not send any message and data to the subedition of subtask;
If the key plate of father's task is originally strong key plate basis, the key plate of subtask is originally weak key plate basis and the key plate of father's task does not originally originally run with the key plate of subtask on same physical host, then the key plate of father's task does not originally send any message and data to the subedition of subtask;
If the key plate of father's task be originally strong key plate this, the key plate of subtask be originally this key plate with subtask of strong key plate this and the key plate of father's task this run on same physical host, then the subedition of father's task does not originally send any message and data to the key plate of subtask;
If the key plate of father's task be originally strong key plate this, the key plate of subtask be originally this key plate with subtask of weak key plate this and the key plate of father's task this run on same physical host, then the subedition of father's task does not originally send any message and data to the key plate of subtask;
If the key plate of father's task is originally weak key plate basis, the key plate of subtask is originally strong key plate basis, the key plate of father's task does not originally originally run with the key plate of subtask on same physical host, and when the key plate of subtask be originally assigned to cause the key plate of father's task originally become weak key plate this all task versions this place physical host set of key plate in any physical host on time, the subedition of father's task sends data to the subedition of subtask and allows it to perform;
If the key plate of father's task be originally weak key plate this, the key plate of subtask be originally strong key plate this, this key plate with subtask of the key plate of father's task this run on same physical host, and when the subedition of subtask be assigned to cause the key plate of father's task originally become weak key plate this all task versions this place physical host set of key plate in any physical host on time, the subedition of father's task allows it to perform to this transmission of key plate data of subtask.
8. the overlapping fault-tolerant method for scheduling task with virtual machine (vm) migration of task based access control in a kind of cloud according to claim 7, it is characterized in that, when a version of a task return operation result be unsuccessfully time, by all task immigrations on the virtual machine at this version place of this task on new physics main frame, this virtual machine can not migrate on the physical host in the physical host set that can not be distributed by above-mentioned restriction by key plate this or the subedition of migration task; Virtual machine after virtual machine (vm) migration to new physics main frame still can be met the time constraints on old physical main frame, and the propagation delay time had in virtual machine between the physical host involved by task of dependence task and migration virtual machine place physical host still can meet above-mentioned existing requirement after virtual machine (vm) migration.
CN201510422623.2A 2015-07-17 2015-07-17 Task based access control is overlapping with the fault-tolerant method for scheduling task of virtual machine (vm) migration in a kind of cloud Active CN105045659B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510422623.2A CN105045659B (en) 2015-07-17 2015-07-17 Task based access control is overlapping with the fault-tolerant method for scheduling task of virtual machine (vm) migration in a kind of cloud

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510422623.2A CN105045659B (en) 2015-07-17 2015-07-17 Task based access control is overlapping with the fault-tolerant method for scheduling task of virtual machine (vm) migration in a kind of cloud

Publications (2)

Publication Number Publication Date
CN105045659A true CN105045659A (en) 2015-11-11
CN105045659B CN105045659B (en) 2018-01-05

Family

ID=54452223

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510422623.2A Active CN105045659B (en) 2015-07-17 2015-07-17 Task based access control is overlapping with the fault-tolerant method for scheduling task of virtual machine (vm) migration in a kind of cloud

Country Status (1)

Country Link
CN (1) CN105045659B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107491347A (en) * 2016-06-12 2017-12-19 阿里巴巴集团控股有限公司 A kind of method and apparatus for live migration of virtual machine

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102591712A (en) * 2011-12-30 2012-07-18 大连理工大学 Decoupling parallel scheduling method for rely tasks in cloud computing
CN102819460A (en) * 2012-08-07 2012-12-12 清华大学 Budget power guidance-based high-energy-efficiency GPU (Graphics Processing Unit) cluster system scheduling algorithm
CN103077083A (en) * 2013-01-09 2013-05-01 苏州亿倍信息技术有限公司 Method and system for processing tasks
US20130318535A1 (en) * 2010-08-11 2013-11-28 Nec Corporation Primary-backup based fault tolerant method for multiprocessor systems
CN103973594A (en) * 2014-05-09 2014-08-06 清华大学 Task scheduling method based on multiple resources

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130318535A1 (en) * 2010-08-11 2013-11-28 Nec Corporation Primary-backup based fault tolerant method for multiprocessor systems
CN102591712A (en) * 2011-12-30 2012-07-18 大连理工大学 Decoupling parallel scheduling method for rely tasks in cloud computing
CN102819460A (en) * 2012-08-07 2012-12-12 清华大学 Budget power guidance-based high-energy-efficiency GPU (Graphics Processing Unit) cluster system scheduling algorithm
CN103077083A (en) * 2013-01-09 2013-05-01 苏州亿倍信息技术有限公司 Method and system for processing tasks
CN103973594A (en) * 2014-05-09 2014-08-06 清华大学 Task scheduling method based on multiple resources

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
王吉 等: "虚拟化云平台中实时任务容错调度算法研究", 《通信学报》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107491347A (en) * 2016-06-12 2017-12-19 阿里巴巴集团控股有限公司 A kind of method and apparatus for live migration of virtual machine
CN107491347B (en) * 2016-06-12 2021-04-27 阿里巴巴集团控股有限公司 Method and equipment for virtual machine live migration

Also Published As

Publication number Publication date
CN105045659B (en) 2018-01-05

Similar Documents

Publication Publication Date Title
US10764125B2 (en) Method and device for training model in distributed system
Zhang et al. RABA: Resource-aware backup allocation for a chain of virtual network functions
Yan et al. DEFT: Dynamic fault-tolerant elastic scheduling for tasks with uncertain runtime in cloud
CN104951367A (en) Virtualized cloud fault-tolerant task scheduling method
Li et al. Real-time and dynamic fault-tolerant scheduling for scientific workflows in clouds
CN105005506B (en) Fault-tolerant resource provision method in one kind virtualization cloud
CN104794239A (en) Cloud platform data processing method
CN108256182A (en) A kind of layout method of dynamic reconfigurable FPGA
CN110659108A (en) Cloud system virtual machine task migration method and device and server
US12073261B2 (en) Synchronization method and apparatus
Luo et al. Exploiting redundancies to enhance schedulability in fault-tolerant and real-time distributed systems
CN105045659A (en) Task overlapping and virtual machine migration based cloud fault-tolerant task scheduling method
CN105094971B (en) A kind of fault-tolerant method for scheduling task moved in cloud after task based access control
Guo et al. Real-time fault-tolerant scheduling algorithm with rearrangement in cloud systems
US8291419B2 (en) Fault tolerant system for execution of parallel jobs
Chen et al. A novel real-time fault-tolerant scheduling algorithm based on distributed control systems
US20230089528A1 (en) Method to execute a mode-transition in a multi-mode computer system
Hofer et al. ODRE workshop: Probabilistic dynamic hard real-time scheduling in HPC
Schönberger et al. Offloading safety-and mission-critical tasks via unreliable connections
CN114281529A (en) Distributed virtualized client operating system scheduling optimization method, system and terminal
Xuguang A Certainty-guaranteed inter/intra-core communication method for multi-core embedded systems
Guo et al. Fault-tolerant scheduling algorithm for periodic real-time tasks in clouds
Manimaran et al. A new scheduling approach supporting different fault-tolerant techniques for real-time multiprocessor systems
Chetto Guaranteed deadlines with dynamic recovery blocks in distributed systems
Gupta et al. Fault-Tolerant Dynamic Scheduling of Object-Based Tasks in Multiprocessor Real-Time Systems

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