CN106708437A - VMware virtualization storage allocation method and system - Google Patents

VMware virtualization storage allocation method and system Download PDF

Info

Publication number
CN106708437A
CN106708437A CN201611169262.6A CN201611169262A CN106708437A CN 106708437 A CN106708437 A CN 106708437A CN 201611169262 A CN201611169262 A CN 201611169262A CN 106708437 A CN106708437 A CN 106708437A
Authority
CN
China
Prior art keywords
data
storage
queue
head
memory
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.)
Pending
Application number
CN201611169262.6A
Other languages
Chinese (zh)
Inventor
魏晓林
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.)
Shanghai Feixun Data Communication Technology Co Ltd
Original Assignee
Shanghai Feixun Data Communication 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 Shanghai Feixun Data Communication Technology Co Ltd filed Critical Shanghai Feixun Data Communication Technology Co Ltd
Priority to CN201611169262.6A priority Critical patent/CN106708437A/en
Publication of CN106708437A publication Critical patent/CN106708437A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601Interfaces specially adapted for storage systems
    • G06F3/0602Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
    • G06F3/0604Improving or facilitating administration, e.g. storage management
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601Interfaces specially adapted for storage systems
    • G06F3/0628Interfaces specially adapted for storage systems making use of a particular technique
    • G06F3/0655Vertical data movement, i.e. input-output transfer; data movement between one or more hosts and one or more storage devices
    • G06F3/0659Command handling arrangements, e.g. command buffers, queues, command scheduling
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601Interfaces specially adapted for storage systems
    • G06F3/0628Interfaces specially adapted for storage systems making use of a particular technique
    • G06F3/0662Virtualisation aspects
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601Interfaces specially adapted for storage systems
    • G06F3/0668Interfaces specially adapted for storage systems adopting a particular infrastructure
    • G06F3/067Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]

Abstract

The invention discloses a VMware virtualization storage allocation method and system. The method comprises the steps that a cluster VMware storage virtualization platform is built; storage resource partitioning and serialization are conducted; a circular storage queue is built for serializing storage space; on the basis of a circular queue algorithm, data importing, data releasing, storage space increasing and storage space deleting operations are executed for the serializing storage space. By means of a VMware virtualization storage technology, resources and functions of a server cluster are integrated, complex operation of the bottom layer of the system is subjected to virtualization processing, a uniform and comprehensive functional service platform is provided for a user, and management of an entity used for providing services and storage is simplified. By means of the circular queue algorithm, the storage sources of the entity are subjected to serialization processing, the circular queue is formed through combination, automated management of the storage sources is achieved, the utilization rate of the system storage sources is increased, the complexity of management is lowered, and meanwhile a large amount of labor cost is saved.

Description

VMware virtualized storage assignment methods and system
Technical field
The present invention relates to a kind of VMware(Prestige is farsighted, is a kind of software virtual machine)Virtualized storage assignment method and system, More particularly to a kind of VMware virtualized storage assignment methods and system based on cirqueue algorithm.
Background technology
Intel Virtualization Technology exactly shields physics equipment complexity from broadly by mapping or abstract mode, increases Plus a management layer, activate a kind of resource and be allowed to be easier to transparent control.It can effectively simplify the management of infrastructure, Increase the utilization rate and ability of IT resources, such as server, network or storage.
Storage Virtualization is a kind of through whole IT environment, for simplified underlying basis that originally may be relative complex The technology of framework.The thought of Storage Virtualization is to separate the logical image of resource and physical store, so as to be systems and management Member provides width simplification, seamless resource virtual view.
For a user, the storage resource of virtualization is like huge " storage pool ", and user not can be appreciated that tool The disk or tape of body, need not also be concerned about which specific storage device is the data of oneself lead to by which paths.
From from the perspective of management, storage pool is the management for taking centralization, and according to specific demand storage Resource is dynamically assigned to each application.It is worth it is emphasized that using Intel Virtualization Technology, magnetic can be simulated with disk array Tape pool, is using the storage resource that speed is fast as disk, capacity is but big as tape library is provided, here it is current application More and more extensive VTL(VTL, Virtual Tape Library), play more in current enterprise storage system Carry out more important role.
By by one or more targets(Target)Services or functionalities are integrated with other additional functions, and unification is provided with Full functionality service.Typical virtualization includes the following situation:The complexity of shielding harness, increases or integrated new Function, emulates, integrates or decomposes existing service function etc..Virtualization acts on one or more physically, and this A little entities are then for providing storage resource and service.
With developing rapidly for big data and cloud computing, increasing enterprise and company start to buy server, build Meet the VMware Storage Virtualization cluster environment of self-demand, so as to meet the development of own service demand.Only possess one Individual good VMware Storage Virtualization clusters, can tackle ever-increasing data volume and require higher and higher computational Energy.
In VMware Storage Virtualization cluster environment build processes, with the continuous increase of memory data output, server The not foot phenomenon of storage resource can frequently occur.For this problem, the solution of enterprise typically has two kinds:First, delete Hash or stale data, carry out data cover;Second, server stores resources are bought, expand memory space.But for The operation of server stores resources is deleted and added to data, is all often to be processed using manually-operated mode, i.e., manually Carry out the operations such as data deletion and Data Migration.Not only waste a large amount of human costs, and server stores resources utilization rate Also it is not high.
The content of the invention
The technical problem to be solved in the present invention is that memory data output in the prior art constantly increases, server is deposited in order to overcome Often processed using manual mode of operation during storage inadequate resource, cause human cost high and the low defect of utilization ratio of storage resources, A kind of VMware virtualized storage assignment methods and system based on cirqueue algorithm are provided, sequence is carried out to cluster-based storage resource Rowization treatment, is combined into a storage queue, and so as to realize cluster-based storage resource automatic management mechanism, not only system storage is provided The utilization rate in source can largely be lifted and is largely reduced with management complexity, but also can be saved Substantial amounts of cost of human resources.
The present invention is to solve above-mentioned technical problem by following technical proposals:
The present invention provides a kind of VMware virtualized storage assignment methods, and its feature is that it is comprised the following steps:
S1, the storage management platform for building the VMware Storage Virtualizations that SAN is applied, by the server in cluster, storage resource Virtualization integration treatment is carried out with service;
S2, in the cluster-based storage resource virtualizing administration interface of the storage management platform, by memory space resource according to physics Block independence is divided into multiple memory blocks, and carries out serializing treatment to those memory blocks;
S3, to serializing memory space set up circulation storage queue, wherein, Head points to depositing for the head of the queue of the circulation storage queue First position of data in storage block, Rear points to the position of last data in the memory block of the tail of the queue of the circulation storage queue Put, the total length len of the circulation storage queue is equal to the sum of those memory blocks;
S4, based on cirqueue algorithm to serializing memory space perform data manipulation, the data manipulation include import data, release Data are put, increase memory space and deletes memory space.
It is preferred that the importing data in step S4 are comprised the following steps:
When there are data to need to import, judge whether (Rear+1) %len=Head, if true then shows the storage of a memory block Insufficient space early warning information, determines whether to delete head of the queue data or newly-increased memory space to sound all clear by user, otherwise for False then stores data into the remaining space of the memory block of Rear pointers sensing, if the residue of the memory block pointed by Rear Insufficient space then performs Rear->Rear.next is operated, and remaining data is imported into the memory block pointed by Rear till now;
Wherein, for deleting head of the queue data manipulation, if head of the queue data are all deleted, head->head.next.
It is preferred that release data in step S4 include release with the continuous data of head of the queue Data Start and release Head and Data between Rear;
Wherein, release is comprised the following steps with the continuous data of head of the queue Data Start:
At directly mobile Head pointers to next position of last data for deleting data;
Data between release Head and Rear are comprised the following steps:
The data between Head and Rear are deleted, data migration operation is carried out, data storage location is carried out into compact operation, while Rear pointers move to last Data Position of compact rear data.
It is preferred that the increase memory space in step S4 is comprised the following steps:
It is P that mark needs the memory block of increased memory space, first carries out P=Rear.next, and Rear=P is performed afterwards, then add P To between Rear and Rear.next, serializing sorting operation then is re-started to whole queue.
It is preferred that the deletion memory space in step S4 includes deleting that the memory space of no data and deletion have significant figure According to memory space;
Wherein, the memory space for deleting no data is comprised the following steps:
The memory block of the memory space that mark need to be deleted is P, performs Rear.next=P.next, P memory blocks is deleted, then to whole Individual queue re-starts serializing sorting operation;
The memory space that deletion has valid data is comprised the following steps:
Rear.next=Replace_Store.next operations are performed, by the memory block of Replace_Store sensings from the circulation Taken out in storage queue;
By in the data copy in Del_Store data blocks to Replace_Store memory blocks;
Del_Front=Replace_Store are performed, Replace_Store=Del_Stroe.next is then performed, will Replace_Store memory blocks are substituted into the position of Del_Store;
Round-robin queue is serialized again, while deleting Del_Store memory blocks;
Wherein, Del_Stroe is the memory block to be deleted, and Del_Front is the previous memory node of Del_Stroe, Replace_Store=Rear.next is the memory block that data will migrate into.
The present invention also provides a kind of VMware virtualization storages distribution system, and its feature is that it includes:
One builds module, the storage management platform of the VMware Storage Virtualizations for building SAN applications, by the service in cluster Device, storage resource and service carry out virtualization integration treatment;
One processing module, in the cluster-based storage resource virtualizing administration interface of the storage management platform, by memory space Resource is divided into multiple memory blocks according to physical block independence, and carries out serializing treatment to those memory blocks;
One sets up module, for setting up circulation storage queue to serializing memory space, wherein, Head points to circulation storage team First position of data in the memory block of the head of the queue of row, Rear points to last in the memory block of the tail of the queue of the circulation storage queue One position of data, the total length len of the circulation storage queue is equal to the sum of those memory blocks;
One performing module, for performing data manipulation, the data manipulation bag to serializing memory space based on cirqueue algorithm Importing data, release data are included, is increased memory space and is deleted memory space.
It is preferred that when there is data to need to import, the performing module is used to judge whether (Rear+1) %len=Head, if The memory space inadequate early warning information of a memory block is then shown for true, determines whether to delete head of the queue data or increase newly by user to deposit Storage space otherwise then stores data into the remaining space of the memory block of Rear pointers sensing to sound all clear for false, if The remaining space deficiency of the memory block pointed by Rear then performs Rear->Rear.next is operated, and remaining data is imported into Memory block pointed by present Rear;
Wherein, for deleting head of the queue data manipulation, if head of the queue data are all deleted, head->head.next.
It is preferred that release data include release between the continuous data of head of the queue Data Start and release Head and Rear Data;
Wherein, release is included with the continuous data of head of the queue Data Start:
The performing module is used at directly mobile Head pointers to next position of last data for deleting data;
Data between release Head and Rear include:
The performing module is used to delete the data between Head and Rear, carries out data migration operation, and data storage location is entered The compact operation of row, while Rear pointers move to last Data Position of compact rear data.
It is preferred that it is P that mark needs the memory block of increased memory space, the performing module is used to first carry out P= Rear.next, performs Rear=P afterwards, then P is added between Rear and Rear.next, and then whole queue is re-started Serializing sorting operation.
It is preferred that deleting memory space includes that the memory space for deleting no data is empty with the storage that deletion has valid data Between;
Wherein, the memory space for deleting no data includes:
The memory block of the memory space that mark need to be deleted is P, and the performing module is used to perform Rear.next=P.next, deletes P Memory block, then re-starts serializing sorting operation to whole queue;
The memory space that deletion has valid data includes:
The performing module is used to perform Rear.next=Replace_Store.next operations, and Replace_Store is pointed to Memory block is taken out from the circulation storage queue;
By in the data copy in Del_Store data blocks to Replace_Store memory blocks;
Del_Front=Replace_Store are performed, Replace_Store=Del_Stroe.next is then performed, will Replace_Store memory blocks are substituted into the position of Del_Store;
Round-robin queue is serialized again, while deleting Del_Store memory blocks;
Wherein, Del_Stroe is the memory block to be deleted, and Del_Front is the previous memory node of Del_Stroe, Replace_Store=Rear.next is the memory block that data will migrate into.
On the basis of common sense in the field is met, above-mentioned each optimum condition can be combined, and obtain final product each preferable reality of the present invention Example.
Positive effect of the invention is:
The present invention by VMware virtualization storage technologies, integrate, by system bottom by resource and function to server cluster The complex operations of layer carry out virtualization process, and so as to provide the user a unification and comprehensive function services platform, simplification is right For providing the management of the entity of service and storage.Then by using cirqueue algorithm, the storage resource of entity is carried out Serializing is processed, and is combined into a round-robin queue, so as to realize the automatic management of storage resource, improves system memory resources Utilization rate and the complexity of management, while saving substantial amounts of human cost.
Brief description of the drawings
Fig. 1 is the flow chart of the VMware virtualized storage assignment methods of present pre-ferred embodiments
Fig. 2 is the VMware Storage Virtualization physical structure figures of present pre-ferred embodiments.
Fig. 3 is the cluster-based storage virtualization storage region division and serialization process of present pre-ferred embodiments.
Fig. 4 is the structural representation of round-robin queue's pointer of present pre-ferred embodiments.
Fig. 5 is the structured flowchart of the VMware virtualization storage distribution systems of present pre-ferred embodiments.
Fig. 6 is the schematic diagram of the data import operation process of present pre-ferred embodiments.
Fig. 7 is the release of present pre-ferred embodiments with the signal of the operating process of the continuous data of head of the queue Data Start Figure.
Fig. 8 is the schematic diagram of the operating process of the data between the release Head and Rear of present pre-ferred embodiments.
Fig. 9 is the schematic diagram of the operating process of the increase memory space of present pre-ferred embodiments.
Figure 10 is the schematic diagram of the operating process of the deletion memory space of present pre-ferred embodiments.
Specific embodiment
Provide present pre-ferred embodiments below in conjunction with the accompanying drawings, to describe technical scheme in detail, but not because This is limited the present invention among described scope of embodiments.
The present embodiment proposes VMware virtualized storage assignment methods and system based on cirqueue algorithm, and cluster is deposited Storage resource carries out serializing treatment, is combined into a storage queue, so as to realize cluster-based storage resource automatic management mechanism, no Only the utilization rate of system memory resources can largely be lifted and is largely reduced with management complexity, and And substantial amounts of cost of human resources can also be saved.
As shown in figure 1, the VMware virtualized storage assignment method concrete implementation processes of cirqueue algorithm should be based on For:
The first step:Build cluster VMware Storage Virtualization platforms
Build storage area network(SAN)The storage management platform of the VMware Storage Virtualizations of application, by the server in cluster, Storage resource and service carry out virtualization integration treatment.Wherein, VMware Storage Virtualizations physical structure is as shown in Figure 2.
Second step:Storage resource is divided and serialized
It is in the cluster-based storage resource virtualizing administration interface of the storage management platform, memory space resource is only according to physical block Vertical property is divided into multiple memory blocks, and carries out serializing treatment to those memory blocks, and concrete operations are as shown in Figure 3.
3rd step:Circulation storage queue, specific behaviour are set up to the serializing memory space in Fig. 3 based on cirqueue algorithm Make as follows:
After the memory space serializing as a example by such as Fig. 3, round-robin queue's pointer is combined into, wherein, Head(Head pointer)Refer to To first position of data, Rear in the memory block marked as 0(Tail pointer)Point to memory block last number marked as 4 According to position, the memory block sum that whole virtualization storage space divides is the total length of len=5, the i.e. round-robin queue, and this is followed Ring queue pointer structure is as shown in Figure 4.
4th step:Can be divided into importing data, release data for the operation of Storage Virtualization memory space, increase storage Space and deletion four kinds of main operations of memory space.
As shown in figure 5, the VMware virtualization storage distribution systems that the present embodiment is provided, it includes a structure module 1, Processing module 2, one sets up the performing module 4 of module 3 and.
The functional module that the VMware virtualization storage distribution systems include is described above, lower mask body introduces each function The function that module possesses:
The structure module 1 is used for the storage management platform of the VMware Storage Virtualizations for building SAN applications, by the service in cluster Device, storage resource and service carry out virtualization integration treatment.
The processing module 2 is used in the cluster-based storage resource virtualizing administration interface of the storage management platform, will store Space resources is divided into multiple memory blocks according to physical block independence, and carries out serializing treatment to those memory blocks.
This sets up module 3 for setting up circulation storage queue to serializing memory space, wherein, Head points to the circulation and deposits First position of data in the memory block of the head of the queue for storing up queue, Rear is pointed in the memory block of the tail of the queue of the circulation storage queue The position of last data, the total length len of the circulation storage queue is equal to the sum of those memory blocks.
The performing module 4 is used to perform serializing memory space data manipulation, data behaviour based on cirqueue algorithm Work includes importing data, release data, increases memory space and delete memory space.
The design of specific each operation is as follows:
Note:Due to being cluster environment, therefore data block total number here should be greater than 1.
(1)Import data
The idiographic flow for importing data is as follows:
When there are data to need to import, (Rear+1) %len=Head is first determined whether, depositing for a memory block is then shown if true Insufficient space early warning information is stored up, it is necessary to be determined whether to delete head of the queue data or newly-increased memory space by user, is sounded all clear.Wherein For deleting head of the queue data manipulation, if head of the queue data are all deleted, head->Head.next, i.e. head are pointed under it At one position.
Otherwise for false representation spaces are sufficient, the remaining space of the memory block of Rear pointers sensing is stored data into, such as The remaining space deficiency of the memory block pointed by fruit Rear then performs Rear->Rear.next is operated, that is, point to the next of Rear Individual position, and remaining data is imported into the memory space pointed by Rear till now.Data import operation process description such as Fig. 6 institutes Show.
When there is data to need to import, the performing module 4 performs following functions operation:
The performing module 4 is used to judge whether (Rear+1) %len=Head, if true then shows the memory space of a memory block Not enough early warning information, determines whether to delete head of the queue data or newly-increased memory space to sound all clear, otherwise for false then by user The remaining space of the memory block of Rear pointers sensing is stored data into, if the remaining space of the memory block pointed by Rear is not enough Then perform Rear->Rear.next is operated, and remaining data is imported into the memory block pointed by Rear till now.Data import behaviour Make specific as shown in Figure 6.
Wherein, for deleting head of the queue data manipulation, if head of the queue data are all deleted, head->head.next.
(2)Release data
The idiographic flow for discharging data is as follows:
What release data manipulation was divided into release is with the number between the continuous data of head of the queue Data Start and release Head and Rear According to.
Wherein, in the operation of the continuous data of head of the queue Data Start, then Head pointers to deletion data will directly be moved Last data next position at, specifically describe as shown in Figure 7:
The data between Head and Rear are deleted, then needs to carry out data migration operation, data storage location is carried out into compact behaviour Make, while Rear pointers are also carried out moving to last Data Position of compact rear data, specifically describe as shown in Figure 8.
When data are discharged, the performing module 4 performs following functions operation:
Release data include release with the data between the continuous data of head of the queue Data Start and release Head and Rear.
Wherein, release is included with the continuous data of head of the queue Data Start:
See Fig. 7, the performing module 4 is used for directly mobile Head pointers to next position of last data for deleting data Put place.
Data between release Head and Rear include:
See Fig. 8, the performing module 4 is used to delete the data between Head and Rear, data migration operation is carried out, by data storage Position carries out compact operation, while Rear pointers move to last Data Position of compact rear data.
(3)Increase memory space
The idiographic flow for increasing memory space is as follows:
When needing to increase memory space, it is P that mark needs the memory block of increased memory space, first carries out P=Rear.next, after Rear=P is performed, then P is added between Rear and Rear.next, serializing sequence behaviour is then re-started to whole queue Make, detailed process is as shown in Figure 9.
When needing to increase memory space, the performing module 4 performs following functions operation:
It is P that mark needs the memory block of increased memory space.
As shown in figure 9, the performing module 4 is used to first carry out P=Rear.next, Rear=P is performed afterwards, then be added to P Between Rear and Rear.next, serializing sorting operation then is re-started to whole queue.
(4)Delete memory space
The idiographic flow for deleting memory space is as follows:
Delete memory space and be divided into two kinds of situations:
The first is to delete no data memory space;Second is to delete the memory space that there are valid data.Wherein, the first Situation is the inverse process for increasing memory space.The memory block of the memory space that mark need to be deleted is P, performs Rear.next= P.next, deletes P memory blocks, then re-starts serializing sorting operation to whole queue.
Second situation needs to carry out memory space pointer replacement, then carries out the migration of data, is transformed into no data The deletion action of memory space, specifically describes as shown in Figure 10:
Wherein, Del_Stroe is the memory space to be deleted, and Del_Front is the previous memory node of Del_Stroe, Replace_Store=Rear.next is the memory block that data will migrate into.Whole operation is divided into four steps, this FOUR EASY STEPS tool Body is described down:
The first step:Rear.next=Replace_Store.next operation is performed, will the storages pointed to of Replace_Store Block takes out from the circulation storage queue;
Second step:By in the data copy in Del_Store data blocks to Replace_Store memory blocks;
3rd step:Del_Front=Replace_Store are performed, Replace_Store=Del_ is then performed Stroe.next, will Replace_Store memory blocks be substituted into the position of Del_Store;
4th step:Round-robin queue is serialized again, while deleting Del_Store memory blocks.
When needing to delete memory space, the performing module 4 performs following functions operation:
Deleting memory space includes deleting the memory space of no data and deletes the memory space that there are valid data;
Wherein, the memory space for deleting no data includes:
The memory block of the memory space that mark need to be deleted is P.
The performing module 4 is used to perform Rear.next=P.next, deletes P memory blocks, and then whole queue is entered again Row serializing sorting operation.
The memory space that deletion has valid data includes:
As shown in Figure 10, the performing module 4 is used to perform Rear.next=Replace_Store.next operations, will The memory block that Replace_Store is pointed to is taken out from the circulation storage queue;
By in the data copy in Del_Store data blocks to Replace_Store memory blocks;
Del_Front=Replace_Store are performed, Replace_Store=Del_Stroe.next is then performed, will Replace_Store memory blocks are substituted into the position of Del_Store;
Round-robin queue is serialized again, while deleting Del_Store memory blocks;
Wherein, Del_Stroe is the memory block to be deleted, and Del_Front is the previous memory node of Del_Stroe, Replace_Store=Rear.next is the memory block that data will migrate into.
Although the foregoing describing specific embodiment of the invention, it will be appreciated by those of skill in the art that these It is merely illustrative of, protection scope of the present invention is defined by the appended claims.Those skilled in the art is not carrying on the back On the premise of principle of the invention and essence, various changes or modifications can be made to these implementation methods, but these are changed Protection scope of the present invention is each fallen within modification.

Claims (10)

1. a kind of VMware virtualized storage assignment methods, it is characterised in that it is comprised the following steps:
S1, the storage management platform for building the VMware Storage Virtualizations that SAN is applied, by the server in cluster, storage resource Virtualization integration treatment is carried out with service;
S2, in the cluster-based storage resource virtualizing administration interface of the storage management platform, by memory space resource according to physics Block independence is divided into multiple memory blocks, and carries out serializing treatment to those memory blocks;
S3, to serializing memory space set up circulation storage queue, wherein, Head points to depositing for the head of the queue of the circulation storage queue First position of data in storage block, Rear points to the position of last data in the memory block of the tail of the queue of the circulation storage queue Put, the total length len of the circulation storage queue is equal to the sum of those memory blocks;
S4, based on cirqueue algorithm to serializing memory space perform data manipulation, the data manipulation include import data, release Data are put, increase memory space and deletes memory space.
2. VMware virtualized storage assignment methods as claimed in claim 1, it is characterised in that the importing data in step S4 Comprise the following steps:
When there are data to need to import, judge whether (Rear+1) %len=Head, if true then shows the storage of a memory block Insufficient space early warning information, determines whether to delete head of the queue data or newly-increased memory space to sound all clear by user, otherwise for False then stores data into the remaining space of the memory block of Rear pointers sensing, if the residue of the memory block pointed by Rear Insufficient space then performs Rear->Rear.next is operated, and remaining data is imported into the memory block pointed by Rear till now;
Wherein, for deleting head of the queue data manipulation, if head of the queue data are all deleted, head->head.next.
3. VMware virtualized storage assignment methods as claimed in claim 1, it is characterised in that the release data in step S4 Including discharging with the data between the continuous data of head of the queue Data Start and release Head and Rear;
Wherein, release is comprised the following steps with the continuous data of head of the queue Data Start:
At directly mobile Head pointers to next position of last data for deleting data;
Data between release Head and Rear are comprised the following steps:
The data between Head and Rear are deleted, data migration operation is carried out, data storage location is carried out into compact operation, while Rear pointers move to last Data Position of compact rear data.
4. VMware virtualized storage assignment methods as claimed in claim 1, it is characterised in that the increase storage in step S4 Space comprises the following steps:
It is P that mark needs the memory block of increased memory space, first carries out P=Rear.next, and Rear=P is performed afterwards, then add P To between Rear and Rear.next, serializing sorting operation then is re-started to whole queue.
5. VMware virtualized storage assignment methods as claimed in claim 1, it is characterised in that the deletion storage in step S4 Space includes deleting the memory space of no data and deletes the memory space that there are valid data;
Wherein, the memory space for deleting no data is comprised the following steps:
The memory block of the memory space that mark need to be deleted is P, performs Rear.next=P.next, P memory blocks is deleted, then to whole Individual queue re-starts serializing sorting operation;
The memory space that deletion has valid data is comprised the following steps:
Rear.next=Replace_Store.next operations are performed, by the memory block of Replace_Store sensings from the circulation Taken out in storage queue;
By in the data copy in Del_Store data blocks to Replace_Store memory blocks;
Del_Front=Replace_Store are performed, Replace_Store=Del_Stroe.next is then performed, will Replace_Store memory blocks are substituted into the position of Del_Store;
Round-robin queue is serialized again, while deleting Del_Store memory blocks;
Wherein, Del_Stroe is the memory block to be deleted, and Del_Front is the previous memory node of Del_Stroe, Replace_Store=Rear.next is the memory block that data will migrate into.
6. a kind of VMware virtualization storages distribution system, it is characterised in that it includes:
One builds module, the storage management platform of the VMware Storage Virtualizations for building SAN applications, by the service in cluster Device, storage resource and service carry out virtualization integration treatment;
One processing module, in the cluster-based storage resource virtualizing administration interface of the storage management platform, by memory space Resource is divided into multiple memory blocks according to physical block independence, and carries out serializing treatment to those memory blocks;
One sets up module, for setting up circulation storage queue to serializing memory space, wherein, Head points to circulation storage team First position of data in the memory block of the head of the queue of row, Rear points to last in the memory block of the tail of the queue of the circulation storage queue One position of data, the total length len of the circulation storage queue is equal to the sum of those memory blocks;
One performing module, for performing data manipulation, the data manipulation bag to serializing memory space based on cirqueue algorithm Importing data, release data are included, is increased memory space and is deleted memory space.
7. VMware virtualization storages distribution system as claimed in claim 6, it is characterised in that need to import when there is data When, the performing module is used to judge whether (Rear+1) %len=Head, if true then shows the memory space of a memory block not Sufficient early warning information, determines whether to delete head of the queue data or newly-increased memory space to sound all clear by user, otherwise for false then will Data are saved in the remaining space of the memory block of Rear pointers sensing, if the remaining space deficiency of the memory block pointed by Rear Perform Rear->Rear.next is operated, and remaining data is imported into the memory block pointed by Rear till now;
Wherein, for deleting head of the queue data manipulation, if head of the queue data are all deleted, head->head.next.
8. VMware virtualization storages distribution system as claimed in claim 6, it is characterised in that release data include release with Data between the continuous data and release Head and Rear of head of the queue Data Start;
Wherein, release is included with the continuous data of head of the queue Data Start:
The performing module is used at directly mobile Head pointers to next position of last data for deleting data;
Data between release Head and Rear include:
The performing module is used to delete the data between Head and Rear, carries out data migration operation, and data storage location is entered The compact operation of row, while Rear pointers move to last Data Position of compact rear data.
9. VMware virtualization storages distribution system as claimed in claim 6, it is characterised in that mark needs increased storage empty Between memory block be P, the performing module be used for first carry out P=Rear.next, Rear=P is performed afterwards, then by P be added to Rear and Between Rear.next, serializing sorting operation then is re-started to whole queue.
10. VMware virtualization storages distribution system as claimed in claim 6, it is characterised in that deleting memory space includes Delete the memory space of no data and delete the memory space that there are valid data;
Wherein, the memory space for deleting no data includes:
The memory block of the memory space that mark need to be deleted is P, and the performing module is used to perform Rear.next=P.next, deletes P Memory block, then re-starts serializing sorting operation to whole queue;
The memory space that deletion has valid data includes:
The performing module is used to perform Rear.next=Replace_Store.next operations, and Replace_Store is pointed to Memory block is taken out from the circulation storage queue;
By in the data copy in Del_Store data blocks to Replace_Store memory blocks;
Del_Front=Replace_Store are performed, Replace_Store=Del_Stroe.next is then performed, will Replace_Store memory blocks are substituted into the position of Del_Store;
Round-robin queue is serialized again, while deleting Del_Store memory blocks;
Wherein, Del_Stroe is the memory block to be deleted, and Del_Front is the previous memory node of Del_Stroe, Replace_Store=Rear.next is the memory block that data will migrate into.
CN201611169262.6A 2016-12-16 2016-12-16 VMware virtualization storage allocation method and system Pending CN106708437A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201611169262.6A CN106708437A (en) 2016-12-16 2016-12-16 VMware virtualization storage allocation method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201611169262.6A CN106708437A (en) 2016-12-16 2016-12-16 VMware virtualization storage allocation method and system

Publications (1)

Publication Number Publication Date
CN106708437A true CN106708437A (en) 2017-05-24

Family

ID=58938049

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201611169262.6A Pending CN106708437A (en) 2016-12-16 2016-12-16 VMware virtualization storage allocation method and system

Country Status (1)

Country Link
CN (1) CN106708437A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110058946A (en) * 2019-04-26 2019-07-26 上海燧原科技有限公司 Device virtualization method, apparatus, equipment and storage medium
CN111240599A (en) * 2020-01-17 2020-06-05 北京马赫谷科技有限公司 Data stream storage method and device
CN111708606A (en) * 2020-06-16 2020-09-25 杨海朝 Virtual computer storage service system and use method thereof

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020112113A1 (en) * 2001-01-11 2002-08-15 Yotta Yotta, Inc. Storage virtualization system and methods

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020112113A1 (en) * 2001-01-11 2002-08-15 Yotta Yotta, Inc. Storage virtualization system and methods

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
任志国等: ""循环队列存储空间的动态回收方法"", 《自动化与仪器仪表》 *
刘朝斌: ""虚拟网络存储系统关键技术研究及其性能评价"", 《中国博士学位论文全文数据库》 *
朱骏等: ""一种基于虚拟化缓存的备份/ 恢复系统的设计与实现"", 《计算机系统》 *
顾奇峰等: ""动态增长型循环队列的实现"", 《微计算机信息》 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110058946A (en) * 2019-04-26 2019-07-26 上海燧原科技有限公司 Device virtualization method, apparatus, equipment and storage medium
CN110058946B (en) * 2019-04-26 2019-12-24 上海燧原科技有限公司 Equipment virtualization method, device, equipment and storage medium
CN111240599A (en) * 2020-01-17 2020-06-05 北京马赫谷科技有限公司 Data stream storage method and device
CN111708606A (en) * 2020-06-16 2020-09-25 杨海朝 Virtual computer storage service system and use method thereof

Similar Documents

Publication Publication Date Title
US10664323B2 (en) Live migration of virtual machines in distributed computing systems
US9524233B2 (en) System and method for efficient swap space allocation in a virtualized environment
US9201896B2 (en) Managing distributed storage quotas
US9134908B2 (en) Logical volume space sharing
US10146591B2 (en) Systems and methods for provisioning in a virtual desktop infrastructure
CN103995855B (en) The method and apparatus of data storage
EP3583504B1 (en) Resource reclamation method and apparatus
US11194620B2 (en) Virtual machine migration task management
US10241836B2 (en) Resource management in a virtualized computing environment
US20140358977A1 (en) Management of Intermediate Data Spills during the Shuffle Phase of a Map-Reduce Job
US20110231605A1 (en) Storage controller and storage control method for dynamically assigning partial areas of pool area as data storage areas
US10909102B2 (en) Systems and methods for performing scalable Log-Structured Merge (LSM) tree compaction using sharding
US10254993B2 (en) Selecting first data sets in a first storage group to swap with second data sets in a second storage group
JP2006099763A5 (en)
CN106610903A (en) Tiered storage system, storage controller, and method for deduplication and storage tiering
CN103631537B (en) The management method of a kind of virtual disk and device
US9104455B2 (en) Virtual machine-to-image affinity on a physical server
CN106708437A (en) VMware virtualization storage allocation method and system
CN103885811B (en) Method, system and device that dummy machine system total system is migrated online
US20230121206A1 (en) Global tracking of virtual inode numbers in snap-based filesystems
US20160050112A1 (en) Distributed caching systems and methods
WO2016138839A1 (en) Bitmap-based storage space management system and method thereof
US9128746B2 (en) Asynchronous unmap of thinly provisioned storage for virtual machines
CN106598501A (en) Data migration device and method for storage automatic hierarchy
CN106502760A (en) A kind of virtual machine compatibility strategy visualization method and device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20170524

RJ01 Rejection of invention patent application after publication