CN109788006A - Data balancing method, device and computer equipment - Google Patents
Data balancing method, device and computer equipment Download PDFInfo
- Publication number
- CN109788006A CN109788006A CN201711106068.8A CN201711106068A CN109788006A CN 109788006 A CN109788006 A CN 109788006A CN 201711106068 A CN201711106068 A CN 201711106068A CN 109788006 A CN109788006 A CN 109788006A
- Authority
- CN
- China
- Prior art keywords
- back end
- storage
- data
- storage equipment
- information
- 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
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L65/00—Network arrangements, protocols or services for supporting real-time applications in data packet communication
- H04L65/40—Support for services or applications
Abstract
The embodiment of the present application provides a kind of data balancing method, device and computer equipment, which comprises the storage utilization rate of equipment and installations based on each back end determines the first back end and the second back end to be equalized；Determine the storage equipment transportation information of first back end and second back end；According to the storage equipment transportation information, first back end and the corresponding Data distribution information of second back end are updated, to complete the storage equipment transportation between first back end and second back end.Technical solution provided by the embodiments of the present application improves data balancing efficiency.
Description
Technical field
The invention relates to technical field of data processing more particularly to a kind of data balancing methods, device and calculating
Machine equipment.
Background technique
Distributed file system cooperates with the calculating and deposit for solving that single computer cann't be solved using multiple stage computers
The problems such as storage.Distributed file system is mainly used for data storage, and data resource is stored in physical machine with document form
It stores in equipment.
In order to facilitate data storage, read and management, existing distributed system generally by host node and with main section
Each back end of point connection is constituted, and back end is responsible for storing data, and host node is responsible for storing the number of each back end
According to distributed intelligence.Each back end is assigned storage space, usually has one or more storage equipment with storing data.
Distributed file system in use can exist storage utilization rate of equipment and installations unbalanced phenomena, it is therefore desirable to point
Cloth file system carries out data balancing, to guarantee that the storage utilization rate of equipment and installations of each back end meets equalization request.
In the prior art, to be equalized any two are usually determined according to the storage utilization rate of equipment and installations of each back end
A back end, from storage the higher back end of utilization rate of equipment and installations in migrating data to storage the lower data of utilization rate of equipment and installations
In node, later notify host node update two back end Data distribution information, it is this by Data Migration come reality
The mode of existing data balancing, needs to occupy network bandwidth, but in order to not influence the normal operation of distributed file system, data
Migration can only be carried out slowly, cause data balancing needs to take a long time, efficiency is lower.
Summary of the invention
The embodiment of the present application provides a kind of data balancing method, device and computer equipment, to solve in the prior art
The technical issues of data balancing low efficiency.
In a first aspect, providing a kind of data balancing method in the embodiment of the present application, comprising:
Storage utilization rate of equipment and installations based on each back end determines the first back end and the second data to be equalized
Node；
Determine the storage equipment transportation information of first back end and second back end；
According to the storage equipment transportation information, first back end and second back end difference are updated
Corresponding Data distribution information is moved with completing the storage equipment between first back end and second back end
It moves.
Second aspect provides a kind of data balancing device in the embodiment of the present application, comprising:
First node determining module determines to be equalized for the storage utilization rate of equipment and installations based on each back end
One back end and the second back end；
Determining module is migrated, for determining that first back end and the storage equipment of second back end move
Move information；
First balance module, for updating first back end and institute according to the storage equipment transportation information
The corresponding Data distribution information of the second back end is stated, to complete first back end and second data section
Storage equipment transportation between point.
The third aspect, provide in the embodiment of the present application a kind of computer equipment, including one or more storage assemblies with
And one or more processing components；
One or more of storage assemblies store one or more computer program instructions；
One or more of processing components call and execute one or more computer program instructions, realize as follows
Operation:
Storage utilization rate of equipment and installations based on each back end determines the first back end and the second data to be equalized
Node；
Determine the storage equipment transportation information of first back end and second back end；
According to the storage equipment transportation information, first back end and second back end difference are updated
Corresponding Data distribution information is moved with completing the storage equipment between first back end and second back end
It moves.
In the embodiment of the present application, the storage utilization rate of equipment and installations based on each back end, it is first determined go out to be equalized the
One back end and the second back end, and determine that the storage of first back end and second back end is set
Standby migration information；According to the storage equipment transportation information, first back end and second back end are updated
Corresponding Data distribution information is set with completing the storage between first back end and second back end
Standby migration.The fast resampling of distributed file system has been fast implemented by the way of equipment transportation, realizes data balancing mesh
, improve data balancing efficiency.
These aspects or other aspects of the application can more straightforward in the following description.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this Shen
Some embodiments please for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 a shows a kind of structural schematic diagram of distributed file system provided by the present application；
Fig. 1 b shows another structural schematic diagram of distributed file system provided by the present application；
Fig. 2 shows a kind of flow charts of data balancing method one embodiment provided by the present application；
Fig. 3 shows a kind of flow chart of another embodiment of data balancing method provided by the present application；
Fig. 4 shows a kind of flow chart of another embodiment of data balancing method provided by the present application；
Fig. 5 shows a kind of flow chart of another embodiment of data balancing method provided by the present application；
Fig. 6 shows a kind of structural schematic diagram of data balancing device one embodiment provided by the present application；
Fig. 7 shows a kind of structural schematic diagram of another embodiment of data balancing device provided by the present application；
Fig. 8 shows a kind of structural schematic diagram of another embodiment of data balancing device provided by the present application；
Fig. 9 shows a kind of structural schematic diagram of another embodiment of data balancing device provided by the present application；
Figure 10 shows a kind of structural schematic diagram of computer equipment one embodiment provided by the present application.
Specific embodiment
In order to make those skilled in the art more fully understand application scheme, below in conjunction in the embodiment of the present application
Attached drawing, the technical scheme in the embodiment of the application is clearly and completely described.
In some processes of the description in the description and claims of this application and above-mentioned attached drawing, contain according to
Multiple operations that particular order occurs, but it should be clearly understood that these operations can not be what appears in this article suitable according to its
Sequence is executed or is executed parallel, and serial number of operation such as 101,102 etc. is only used for distinguishing each different operation, serial number
It itself does not represent and any executes sequence.In addition, these processes may include more or fewer operations, and these operations can
To execute or execute parallel in order.It should be noted that the description such as " first " herein, " second ", is for distinguishing not
Same message, equipment, module etc., does not represent sequencing, does not also limit " first " and " second " and be different type.
The technical solution of the application is mainly used in distributed file system, such as HDFS (Hadoop
Distributed File System, Hadoop distributed file system), NFS (Network File System, network text
Part system) etc., the technical solution of the application can be adapted in various storage scenes, especially cloud computing scene, distributed
File system is the cloud storage system in cloud computing system.In cloud computer scene, for depositing in distributed file system
The storage equipment of storage data is located at cloud, provides memory space by network, is also known as cloud disk or Dropbox.
Fig. 1 a shows a kind of common structural schematic diagram of distributed file system, it is known that, distributed file system can be with
Including host node 10 and each back end 20 being connect with host node 10.Each back end 20 can be by one or more
A physical machine realization, can be with independent startup one or more operating system process, and is assigned storage space, usual carry one
A or multiple storage equipment, for storing data.Host node 10 can be realized by one or more physical machines, each for storing
The Data distribution information of a back end, also referred to as " metadata " or " catalogue ", to show pair of data and storage address
It should be related to.One usual cutting of big data is multiple blocks of files, is stored in each back end in the form of blocks of files, herein
Involved in data, can be understood as blocks of files under normal circumstances.
In cloud computing scene, such as Fig. 1 b, structural schematic diagram of the distributed file system in cloud computing scene is shown,
Distributed file system is cloud storage system.
Wherein, in the embodiment of the present application, the storage equipment can refer to the equipment that can be read and write, can be, magnetic
Memory, flash memory, disk or CD etc. generally use disk at present and carry out storing data, and disk for example can be SSD
(Solid State Drives, solid state hard disk), HDD (Mechanical hard disk, mechanical hard disk), SHHD (Solid
State Hybrid Drive, hybrid hard disk) etc..
The exchange that real data can be carried out between back end is substantially carried out data point between back end and host node
The update of cloth information.
Since a back end can have one or more storage equipment, the storage utilization rate of equipment and installations of back end can
To refer to the average utilization of the utilization rate of each storage equipment that it has, such as some back end includes storage equipment
A and storage two pieces of storage equipment of equipment B, the utilization rate of storage equipment A are 80%, and the utilization rate of storage equipment B is 90%, then
The storage utilization rate of equipment and installations of the back end can be (80%+90%)/2, i.e., 85%.
Distribution is that file system will lead to storage equipment between back end due to various reasons in use
Utilization rate is unbalanced, for example, having newly increased back end, new back end can be preferentially written in newly generated data, causes new
The storage utilization rate of equipment and installations difference of old back end is very big；For another example, client behavior, client application write-in data have certain
Inclination behavior, it is unbalanced so as to cause the storage utilization rate of equipment and installations between back end.Utilization rate of equipment and installations is unbalanced to lead for storage
It causes certain back end that can not continue to write to data or data can not be successfully written, and influences the normal of distributed file system
Use, therefore just need to carry out data balancing, be in the prior art by way of carrying out Data Migration between back end into
Row fast resampling comes so that storing utilization rate of equipment and installations between back end meets equalization requirement, but this mode will necessarily account for
With network bandwidth, and in order to not influence the normal operation of distributed file system, Data Migration can only be carried out slowly, so that data
Equalization efficiency is lower.
In order to solve the lower technical problem of data balancing efficiency, inventor passes through a series of skills for researching and proposing the application
Art scheme, in the embodiment of the present application, the storage utilization rate of equipment and installations based on each back end, it is first determined go out to be equalized the
One back end and the second back end；The storage of first back end and second back end is determined later
Equipment transportation information；According to the storage equipment transportation information, first back end and second data section are updated
The corresponding Data distribution information of point, to complete the storage equipment of first back end and second back end
Migration.The application, without carrying out the Data Migration between back end, need to only be set by the way of equipment transportation according to storage
Standby migration information, which updates Data distribution information, can complete the fast resampling between back end, without occupying Netowrk tape
Width can fast implement the purpose of Distributed File System Data equilibrium, improve data balancing efficiency.
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of embodiments of the present application, instead of all the embodiments.It is based on
Embodiment in the application, those skilled in the art's every other implementation obtained without creative efforts
Example, shall fall in the protection scope of this application.
Fig. 2 is a kind of flow graph of data balancing method one embodiment provided by the present application, and this method may include following
Several steps:
201: the storage utilization rate of equipment and installations based on each back end determines the first back end and second to be equalized
Back end.
The technical solution of the present embodiment can be executed by host node, namely executed data balancing by host node and operated, certainly
It can also be executed by any one back end, the storage utilization rate of equipment and installations of each back end can be calculated by host node to be obtained
?；It can certainly be by being executed with the self-existent third party device of distributed file system, and obtained respectively by host node
The storage utilization rate of equipment and installations of a back end.
Wherein, the first back end and the second back end can be any two data section for meeting condition to be equalized
Point, for the convenience of description, being named as the first back end and the second back end.
The condition to be equalized can for example refer to that the difference of storage utilization rate of equipment and installations is greater than the first preset value, so as to true
Surely storage utilization rate of equipment and installations differs biggish any two back end and needs to carry out equilibrium.First preset value can be in conjunction with the
One data balancing demand and balanced granularity requirements are actually set.Such as first preset value can be 60%, it is assumed that number
Storage utilization rate of equipment and installations according to node A is 15%.The storage utilization rate of equipment and installations of back end B is 85%, difference between the two
It is 70%, is greater than the first preset value 60%, meets condition to be equalized, then back end A and back end B can be respectively as
First back end and the second back end to be equalized.
202: determining first back end and the corresponding storage equipment transportation information of second back end.
Alternatively, it can be based on the first data balancing demand, determine first back end and institute
State the storage equipment transportation information of the second back end.
First data balancing demand can refer to that the storage utilization rate of equipment and installations of any two back end is equal, can be with root
It is set according to different actual scenes, such as can refer to that the storage utilization rate of equipment and installations of each back end is in preset range
Or the storage utilization rate of equipment and installations difference of any two back end, less than first trimming threshold etc., the application is not to this progress
Concrete restriction.
Wherein, which can be equal with first preset value or be less than first preset value, if should
First trimming threshold condition equal namely to be equalized with the first preset value is the storage utilization rate of equipment and installations of any two back end
Difference be greater than the first preset value, the first data balancing demand be any two back end storage utilization rate of equipment and installations difference it is small
In first preset value, condition to be equalized can be the contrary condition of the first data balancing demand.It should be noted that if appointing
The storage utilization rate of equipment and installations difference of two back end of anticipating is equal to the first preset value, it is believed that any two back end is full
Foot condition to be equalized meets the first data balancing demand.
Storing equipment transportation information may include storing device information of first data node migrating to the second back end,
And/or second data node migrating to the first back end storing device information.
Accordingly, it is to be understood that, in the embodiment of the present application, each back end can at least have there are two storage set
It is standby.
Storing equipment transportation information can be determined based on the first data balancing demand, so that the first back end and second
Back end carries out the respective storage utilization rate of equipment and installations after storage equipment transportation and meets the first data balancing demand.
In order to determine storage equipment transportation information, it is alternatively possible to determine first back end and described first
The corresponding each storage equipment of second back end；
First back end and second back end difference are re-established based on the first data balancing demand
With it is described it is each storage equipment corresponding relationship, to obtain the storage equipment transportation information.
For example, the first back end includes storage equipment A and storage equipment B, the utilization rate of storage equipment A is 60%.
The utilization rate for storing equipment B is 90%, and the storage utilization rate of equipment and installations of the first back end is storage equipment A and storage equipment B
Average utilization, as 75%；
Second back end includes storage equipment C and storage equipment D, and the utilization rate of storage equipment C is 10%, and storage is set
The utilization rate of standby D is 50%, and the storage utilization rate of equipment and installations of the second back end is 30%.
Assuming that the storage utilization rate of equipment and installations difference that condition to be equalized is any two back end is greater than 30%, the first data
The storage utilization rate of equipment and installations difference of node and the second back end is 75%-30% namely 45%, it is known that, it is to be equalized to meet this
Condition.
Assuming that the first data balancing demand is the storage utilization rate of equipment and installations difference of any two back end less than 20%, base
In the first data balancing demand, it can determine that two kinds of migration patterns, the first migration pattern can depositing the first back end
The storage equipment B and storage equipment D of the second back end is swapped；Second of migration pattern can store the first back end
Equipment A and the storage equipment C of the second back end are swapped, so that the storage equipment utilization of the first back end
Rate becomes 55%, and the storage utilization rate of equipment and installations of the second back end is turned into 50%, the first back end and the second back end
Storage utilization rate of equipment and installations difference become 5%, meet the first data balancing demand.It chooses any one kind of them migration pattern, it can obtain
Equipment transportation information must be stored.
Certainly, as another optional way, can according to equipment transportation rule, determine first back end and
The storage equipment transportation information of second back end；
The equipment transportation rule can store equipment for the high usage of the high back end of storage utilization rate of equipment and installations, and deposit
The poor efficiency for storing up the low back end of utilization rate of equipment and installations stores devices exchange.
Described in example as above, according to equipment transportation rule, the storage utilization rate of equipment and installations of the first back end is high, and storage is set
The utilization rate highest of standby B；Storage equipment C utilization rate in second back end is minimum, then can use the first back end
Storage equipment B and second back end the migration pattern that swaps of storage equipment C, may thereby determine that storage equipment
Migration information is that the storage equipment of the first data node migrating to the second back end is storage equipment B and the second data
It is storage equipment C that node, which is migrated to the storage equipment of the first back end,.
203: according to the storage equipment transportation information, updating first back end and second back end
Corresponding Data distribution information is moved with completing the storage equipment of first back end and second back end
It moves.
If the first back end and the second back end carry out storage equipment transportation, need to notify that host node is reported each
From data information, to update in host node the first back end and the corresponding data distribution letter of the second back end
Breath, so that the storage equipment transportation of the first back end and the second back end just terminates.
If the technical solution of the present embodiment can be executed by host node, host node can be according to storage equipment transportation letter
Breath, automatically updates first back end and the corresponding Data distribution information of second back end.
It can be specifically according to the storage if the technical solution of the present embodiment is executed by the other equipment of non-master
Equipment transportation information notifies that the host node updates first back end and second back end is corresponding
Data distribution information.
Wherein, in a practical application, the technical solution of the embodiment of the present application be can be applied in cloud computing scene, such as be schemed
Shown in 1b, in cloud computing scene, the hardware resource of back end such as processing equipment, storage equipment etc. be can be from cloud computing
The virtual resource that platform is rented, and not actual physical resource, if storage equipment is the virtual resource rented, back end
By safeguarding the corresponding relationship of corresponding storage equipment, it is based on the corresponding relationship, it can the storage equipment rented it
Carry out data processing operation.Therefore, if storage equipment is the virtual resource rented, the first back end and the second data section
Point storage equipment transportation, it is only necessary to re-establish the first back end and the second back end respectively with each storage equipment
Corresponding relationship, and update the first back end and the corresponding Data distribution information of the second back end accordingly.
And if the hardware resource of back end is actual physical resource, rather than virtual resource, then it is used as another reality
Example is applied, after the storage equipment transportation information for determining first back end and second back end, can also be wrapped
It includes:
Output storage equipment transportation prompt information, to prompt user according to the storage equipment transportation information, described in exchange
First back end and the second back end storage equipment.Also it can be plugged and be deposited in physical machine by user
Equipment is stored up to carry out storage equipment transportation.
The present embodiment is by the way of equipment transportation, only need to be according to depositing without carrying out the Data Migration between back end
Storage equipment transportation information update Data distribution information can complete the fast resampling between back end, without occupying network
Bandwidth can fast implement the purpose of data balancing, improve data balancing efficiency.
Fig. 3 be a kind of flow graph of another embodiment of data balancing method provided by the present application, this method may include with
Under several steps:
301: the storage utilization rate of equipment and installations based on each back end determines the first back end and second to be equalized
Back end.
302: determining the storage equipment transportation information of first back end and second back end.
303: according to the storage equipment transportation information, updating first back end and second back end
Corresponding Data distribution information is set with completing the storage between first back end and second back end
Standby migration.
Step 301~step 303 may refer to step 201~step 203 in above-described embodiment, and details are not described herein.
304: determining after carrying out storage equipment transportation according to the storage equipment transportation information, first back end
Corresponding each first storage equipment and the corresponding each second storage equipment of second back end.
If by storage equipment transportation, the corresponding relationship of the first back end and the second back end and storage equipment
It changes.
Hence, it can be determined that after carrying out storage equipment transportation, the corresponding each first storage equipment of the first back end
And second back end it is corresponding it is each second storage equipment.
Wherein, first storage equipment and second storage equipment merely to from nominally distinguish the first back end and
The corresponding storage equipment of second back end is not offered as having the incidence relations such as sequence or progressive or quantity.
305: each first storage equipment is carried out data and moved by the utilization rate based on each first storage equipment
It moves, to obtain the first Data Migration information.
306: each second storage equipment is carried out data and moved by the utilization rate based on each second storage equipment
It moves, to obtain the second Data Migration information.
Due to average utilization of the storage utilization rate of equipment and installations for its all storage equipment having of back end, data section
After the storage utilization rate of equipment and installations of point is balanced, the utilization rate of each storage equipment room may also need further inside back end
It is balanced.
Such as back end includes storage equipment A and storage equipment B, the utilization rate of storage equipment A is 20%, and storage is set
The utilization rate of standby B is 100%, it is known that, the internal data distribution of back end is simultaneously unbalanced.
Therefore internal balance can be carried out to the first back end and the second back end respectively, namely in storage inside
Data Migration is carried out between equipment.
It is alternatively possible to utilization rate and internal balance demand based on each first storage equipment, it will be described each
A first storage equipment carries out Data Migration, to obtain the first Data Migration information of first back end.
Described each second can be deposited based on the utilization rate and internal balance demand of each second storage equipment
It stores up equipment and carries out Data Migration, to obtain the second Data Migration information of second back end.
The internal balance demand for example can be each storage equipment utilization rate it is equal or each storage equipment
Utilization rate be within the scope of internal balance.
In example as above, the utilization rate of the storage equipment A of back end is 20%, and the utilization rate of storage equipment B is 100%,
Internal balance demand is equal if it is the utilization rate of each storage equipment, then can execute will store the Data Migration of equipment B
To storage equipment A, so that the utilization rate of storage equipment A and storage equipment B reach 60%.
307: according to the first Data Migration information, the second Data Migration information, updating first data section
Point and the corresponding Data distribution information of second back end.
After first back end and the second back end carry out storage equipment transportation, if also carried out internal equal
Weighing apparatus, then can be according to the first Data Migration information of first back end and the second data of second back end
Migration information continues to update respective Data distribution information.
In the present embodiment, the storage equipment equilibrium between back end can be fast implemented by equipment transportation mode,
On the basis of equipment transportation, the data distribution of the storage equipment of the inside of each back end is readjusted, carries out internal balance,
It is further ensured that the data balancing of each back end.
Fig. 4 be a kind of flow graph of another embodiment of data balancing method provided by the present application, this method may include with
Under several steps:
401: the storage utilization rate of equipment and installations based on each back end judges whether there is and meets the first of condition to be equalized
Back end and the second back end, if so, step 402 is executed, if not, executing step 404.
The condition to be equalized for example can be storage utilization rate of equipment and installations difference and be greater than the first preset value.
402: determining the storage equipment transportation information of first back end and the second back end.
It is alternatively possible to determine storage equipment transportation information based on the first data balancing demand.It can certainly be based on
Equipment transportation rule determines storage equipment transportation information, and for details, reference can be made to the descriptions in above-described embodiment.
If condition to be equalized two conditions opposite each other with the first data balancing demand, judge whether there is satisfaction to
The first back end and the second back end of equilibrium condition can also be specifically to judge whether there is to be unsatisfactory for the first data
The first back end and the second back end of equalization requirement.Namely if there is no the data section for meeting condition to be equalized
Point may indicate that each back end is all satisfied the first data balancing demand.
403: according to the storage equipment transportation information, updating first back end and second back end
Corresponding Data distribution information is moved with completing the storage equipment of first back end and second back end
It moves.
Optionally, it can also determine after carrying out storage equipment transportation according to the storage equipment transportation information, described
The corresponding each first storage equipment of one back end and the corresponding each second storage equipment of second back end；
Based on the utilization rate of each first storage equipment, each first storage equipment is subjected to Data Migration,
To obtain the first Data Migration information；
Based on the utilization rate of each second storage equipment, each second storage equipment is subjected to Data Migration,
To obtain the second Data Migration information；
So as to continue described in update according to the first Data Migration information and the second Data Migration information
First back end and the corresponding Data distribution information of second back end.
404: the storage utilization rate of equipment and installations based on each back end determines the third back end for meeting condition to be migrated
And the 4th back end.
405: be based on the second data balancing demand, between the third back end and the 4th back end into
Row Data Migration, to obtain third Data Migration information.
Wherein, which for example can be storage utilization rate of equipment and installations difference greater than the second preset value, wherein described
Second preset value can be less than first preset value.
406: being based on the third Data Migration information, update the third back end and the 4th back end
Data distribution information.
Wherein, if there is no any two back end for meeting condition to be migrated, it can terminate process.
Step 404~step 406 is data balancing mode in the prior art, if there is no meeting condition to be equalized
First back end and the second back end, it can any two back end for meeting condition to be migrated is searched, in order to
Facilitate the differentiation in description, is named as third back end and the 4th back end.
The second data balancing demand for example can be storage utilization rate of equipment and installations difference less than the second trimming threshold；
Wherein, which can be less than or equal to first trimming threshold.
In addition, second trimming threshold can be equal to second preset value or be less than second preset value, if this
Two trimming thresholds are equal to second preset value namely condition to be migrated and can be opposite each other two with the second data balancing demand
A condition, judges whether there is the third back end for meeting condition to be migrated and the 4th back end can also be specifically to sentence
Disconnected third back end and the 4th back end with the presence or absence of the second data balancing demand that is unsatisfactory for.
Based on the second data balancing demand, Data Migration can be carried out and obtain third Data Migration information, third data
Include that migrating data identifies in migration information, so as to be based on third Data Migration information, updates Data distribution information.
Wherein, Data Migration mode is same as the prior art, and details are not described herein.
In the present embodiment, the data balancing between back end is fast implemented using equipment transportation mode, for being all satisfied
The back end of first data balancing demand or when not depositing back end to be equalized, can be using Data Migration mode into one
Step carries out data balancing to back end, data balancing process is divided into two stages, so as to first with equipment transportation
Mode carries out the data balancing of coarseness, the fine-grained data balancing of Data Migration mode further progress is recycled, due to
The data balancing of coarseness is carried out by Data Migration mode, fine-grained data balancing is only needed for partial data section
Partial data in point, therefore do not need to occupy excessive network bandwidth, therefore the excessive time will not be occupied, guaranteeing data balancing
While efficiency, it is ensured that the fineness of data balancing.
Fig. 5 be a kind of flow graph of another embodiment of data balancing method provided by the present application, this method may include with
Under several steps:
501: the storage utilization rate of equipment and installations based on each back end determines the first back end and second to be equalized
Back end.
502: determining the storage equipment transportation information of first back end and second back end.
It is alternatively possible to determine first data based on the first data balancing demand or based on equipment transportation rule
The storage equipment transportation information of node and second back end.
503: according to the storage equipment transportation information, updating first back end and second back end
Corresponding Data distribution information is moved with completing the storage equipment of first back end and second back end
It moves.
Optionally, it can also determine after carrying out storage equipment transportation according to the storage equipment transportation information, described
The corresponding each first storage equipment of one back end and the corresponding each second storage equipment of second back end；
Based on the utilization rate of each first storage equipment, each first storage equipment is subjected to Data Migration,
To obtain the first Data Migration information；
Based on the utilization rate of each second storage equipment, each second storage equipment is subjected to Data Migration,
To obtain the second Data Migration information；
So as to be specifically according to the first Data Migration information and the second Data Migration information, continuation is more
New first back end and the corresponding Data distribution information of second back end.
504: judging to carry out first data section after storage equipment transportation according to the storage equipment transportation information
Whether point and second back end meet the second data balancing demand, if not, executing step 505；If it is return
Step 501 continues to execute.
505: Data Migration is carried out between first back end and second back end, to obtain the 4th
Data Migration information.
506: being based on the 4th Data Migration information, update first back end and second back end
Data distribution information.
In the present embodiment, if the first back end and second back end after carrying out storage equipment transportation
It is unsatisfactory for the first data balancing demand, data balancing can further be carried out using Data Migration mode, due to the first number
Storage equipment transportation is carried out according to node and the second back end, therefore the data migrated required for Data Migration can compare
It is small, more Internet resources and time will not be occupied, thus while both having ensure that data balancing efficiency, it can also be ensured that data
Balanced fineness.
In practical applications, current distributed file system can use disk storage data, if storage equipment is
Disk, storage utilization rate of equipment and installations is disk utilization, and storage equipment transportation is also disk migration, therefore is migrated by disk
To carry out fast resampling, it can realize data balancing purpose, it is ensured that data balancing efficiency.
Fig. 6 is a kind of structural schematic diagram of data balancing device one embodiment provided by the present application, data balancing dress
Host node, back end or the independent third party device with distributed file system can be configured at by setting；
The apparatus may include:
First node determining module 601 determines to be equalized for the storage utilization rate of equipment and installations based on each back end
First back end and the second back end.
Optionally, which can be specifically used for:
Determine first back end and the corresponding each storage equipment of second back end；
Based on the first data balancing demand, first back end and second back end difference are re-established
With it is described it is each storage equipment corresponding relationship, to obtain the storage equipment transportation information.
Optionally, which can be specifically used for:
Storage utilization rate of equipment and installations based on each back end, determine meet condition to be equalized the first back end and
Second back end.
Determining module 602 is migrated, for determining that first back end and the storage of second back end are set
Standby migration information.
First balance module 603, for according to the storage equipment transportation information, update first back end and
The corresponding Data distribution information of second back end, to complete first back end and second data
The storage equipment transportation of node.
The present embodiment, without carrying out the Data Migration between back end, only needs basis by the way of equipment transportation
Storage equipment transportation information update Data distribution information can complete the fast resampling between back end, without occupying net
Network bandwidth can fast implement the purpose of data balancing, improve data balancing efficiency.
Fig. 7 is a kind of structural schematic diagram of another embodiment of data balancing device provided by the present application, is filled with shown in Fig. 6
Difference is set, which can also include:
Equipment determining module 701, after carrying out storage equipment transportation according to the storage equipment transportation information for determination,
The corresponding each first storage equipment of first back end and corresponding each second storage of second back end
Equipment；
First information determining module 702, for the utilization rate based on each first storage equipment, by described each the
One storage equipment carries out Data Migration, to obtain the first Data Migration information；
Second information determination module 703, for the utilization rate based on each second storage equipment, by described each the
Two storage equipment carry out Data Migration, to obtain the second Data Migration information；
Second balance module 704 is used for according to the first Data Migration information and the second Data Migration information,
Update first back end and the corresponding Data distribution information of second back end.
Wherein, first node determining module 601 specifically can be the storage utilization rate of equipment and installations based on each back end, really
Surely meet the first back end and the second back end of condition to be equalized.
If there is no the first back end and the second back end for meeting condition to be equalized, then can continue to use
Data Migration mode carries out data balancing to distributed file system, therefore, as another embodiment, and as shown in Figure 8, with
Fig. 6 shown device the difference is that, which can also include:
Second node determining module 801, for if there is no the first back end for meeting condition to be equalized and
Two back end, the storage utilization rate of equipment and installations based on each back end determine the third back end for meeting condition to be migrated
And the 4th back end；
First transferring module 802, for being based on the second data balancing demand, in the third back end and described the
Data Migration is carried out between four back end, to obtain third Data Migration information；
Third balance module 803, for be based on the third Data Migration information, update the third back end and
The Data distribution information of 4th back end.
Wherein, the first node determining module 601 can be specifically used for the storage equipment benefit based on each back end
With rate, determine that storage utilization rate of equipment and installations difference is greater than the first back end and the second back end of the first preset value.
Second node determining module 801 can be specifically used for being greater than described the if there is no storage utilization rate of equipment and installations difference
Any two back end of one preset value, the storage utilization rate of equipment and installations based on each back end determine storage equipment utilization
Rate difference is greater than the third back end and the 4th back end of the second preset value；Wherein second preset value is less than described
First preset value.
Therefore, the present embodiment data balancing process is divided into two stages, so as to first with equipment transportation mode into
The data balancing of row coarseness, and the fine-grained data balancing of Data Migration further progress is utilized, due to having passed through equipment
Migration pattern has carried out the data balancing of coarseness, and fine-grained data balancing is only needed for score in the middle part of partial data node
According to, therefore do not need to occupy excessive network bandwidth, the excessive time will not be occupied, while guaranteeing data balancing efficiency, also
It ensure that the fineness of data balancing.
In addition, if the first back end and second back end after carrying out storage equipment transportation are unsatisfactory for
The first data balancing demand can further carry out data balancing using Data Migration mode, therefore, as shown in figure 9, making
For another embodiment, the difference is that, which can also include: with Fig. 5 shown device
Judgment module 901, judgement carry out first back end and second number after storage equipment transportation
Whether meet the second data balancing demand according to node；
Second transferring module 902, if being unsatisfactory for institute for first back end and second back end
The second data balancing demand is stated, carries out Data Migration between first back end and second back end, with
Obtain the 4th Data Migration information；
4th balance module 903, for being based on the 4th Data Migration information, update first back end and
The Data distribution information of second back end.
In the present embodiment, if the first back end and second back end after carrying out storage equipment transportation
It is unsatisfactory for the first data balancing demand, data balancing is further carried out using Data Migration mode, due to the first data section
Point and the second back end have carried out equipment transportation, therefore the data migrated required for Data Migration can be smaller, will not
More Internet resources and time are occupied, thus while both having ensure that data balancing efficiency, it can also be ensured that data balancing
Fineness.
Wherein, in a practical application, the technical solution of the embodiment of the present application be can be applied in cloud computing scene, such as be schemed
Shown in 1b, the hardware resource of back end such as processing equipment, storage equipment etc. are the virtual resource rented, the first back end
And the storage equipment transportation of second back end, it is only necessary to re-establish the first back end and the second back end
Respectively with the corresponding relationship of each storage equipment, and the first back end is updated accordingly and the second back end is corresponding
Data distribution information.
And if the hardware resource of back end is actual physical resources, in some embodiments, which can be with
Include:
Output module, for exporting storage equipment transportation prompt information；The storage equipment transportation prompt information is for mentioning
Show user according to depositing in the first back end described in the storage equipment transportation information exchange and second back end
Store up equipment.Also storage equipment can be plugged in physical machine by user to realize storage equipment transportation.
In a possible design, above-mentioned Fig. 6~any data shown in Fig. 9 balancer can be implemented as a meter
Machine equipment is calculated, which can be the host node or back end in distributed file system, be also possible to independence
In the third party device of distributed file system；
As shown in Figure 10, which may include at one or more storage assemblies 1001 and one or more
Manage component 1002；
One or more of storage assemblies 1001 store one or more computer program instructions；
One or more of processing components 1002 call and execute one or more computer program instructions, realize
Following operation:
Storage utilization rate of equipment and installations based on each back end determines the first back end and the second data to be equalized
Node；
Determine the storage equipment transportation information of first back end and second back end；
According to the storage equipment transportation information, first back end and second back end difference are updated
Corresponding Data distribution information, to complete the storage equipment transportation of first back end and second back end.
Optionally, one or more of processing components 1002 determine the first back end and second back end
Storage equipment transportation information can be specifically:
Determine first back end and the corresponding each storage equipment of second back end；
Based on the first data balancing demand, first back end and second back end difference are re-established
With it is described it is each storage equipment corresponding relationship, to obtain the storage equipment transportation information.
Optionally, one or more of processing components 1002 are also used to realize following operation::
It determines after carrying out storage equipment transportation according to the storage equipment transportation information, first back end is corresponding
It is each first storage equipment and second back end it is corresponding it is each second storage equipment；
Based on the utilization rate of each first storage equipment, each first storage equipment is subjected to Data Migration,
To obtain the first Data Migration information；
Based on the utilization rate of each second storage equipment, each second storage equipment is subjected to Data Migration,
To obtain the second Data Migration information；
According to institute's the first Data Migration information and the second Data Migration information, first data section is updated
Point and the corresponding Data distribution information of second back end.
Optionally, storage utilization rate of equipment and installations of one or more of processing components 1002 based on each back end, really
Fixed first back end and the second back end to be equalized may is that
Storage utilization rate of equipment and installations based on each back end, determine meet condition to be equalized the first back end and
Second back end.
Optionally, one or more of processing components 1002 are also used to realize following operation: if there is no meet to
Any two back end of equilibrium condition, the storage utilization rate of equipment and installations based on each back end, determination meet item to be migrated
The third back end and the 4th back end of part；
Based on the second data balancing demand, counted between the third back end and the 4th back end
According to migration, to obtain third Data Migration information；
Based on the third Data Migration information, the number of the third back end and the 4th back end is updated
According to distributed intelligence.
Optionally, one or more of processing components 1002 are also used to realize following operation: judgement carries out storage equipment
Whether first back end and second back end after migration meet the second data balancing demand；
If first back end and second back end are unsatisfactory for the second data balancing demand,
Data Migration is carried out between first back end and second back end, to obtain the 4th Data Migration information；
Based on the 4th Data Migration information, the number of first back end and second back end is updated
According to distributed intelligence.
Wherein, the condition to be equalized can refer to that storage utilization rate of equipment and installations difference is greater than the first preset value, described wait move
Shifting condition can refer to that storage utilization rate of equipment and installations difference is greater than the second preset value.
Optionally, one or more of processing components 1002 are also used to realize following operation: output storage equipment transportation
Prompt information；The storage equipment transportation prompt information is for prompting user according to described in the storage equipment transportation information transfer
Storage equipment in first back end and second back end.
Wherein, above-mentioned storage assembly can be by any kind of volatibility or non-volatile memory device or their group
It closes and realizes, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM) is erasable to compile
Journey read-only memory (EPROM), programmable read only memory (PROM), read-only memory (ROM), magnetic memory, flash
Device, disk or CD.
It include storing data in the one or more storage assembly 1001 when the computer equipment is back end
The storage equipment.
Above-mentioned processing component can be CPU, naturally it is also possible to be application specific integrated circuit (ASIC), Digital Signal Processing
Device (DSP), digital signal processing appts (DSPD), programmable logic device (PLD), field programmable gate array (FPGA), control
Device, microcontroller, microprocessor or other electronic components processed.
It should be noted that the computer equipment can also include other necessary some components, such as bus, input or
Output interface, power supply module, output precision etc..
In addition, the computer storage medium stores one the embodiment of the present application also provides a kind of computer storage medium
Or a plurality of computer instruction, one or more computer instruction realize any of the above-described embodiment when can computer be executed
The data balancing method.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
The apparatus embodiments described above are merely exemplary, wherein described, unit can as illustrated by the separation member
It is physically separated with being or may not be, component shown as a unit may or may not be physics list
Member, it can it is in one place, or may be distributed over multiple network units.It can be selected according to the actual needs
In some or all of the modules achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying creativeness
Labour in the case where, it can understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It realizes by means of software and necessary general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, on
Stating technical solution, substantially the part that contributes to existing technology can be embodied in the form of software products in other words, should
Computer software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation
Method described in certain parts of example or embodiment.
Finally, it should be noted that above embodiments are only to illustrate the technical solution of the application, rather than its limitations；Although
The application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features；
And these are modified or replaceed, each embodiment technical solution of the application that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (19)
1. a kind of data balancing method characterized by comprising
Storage utilization rate of equipment and installations based on each back end determines the first back end and the second data section to be equalized
Point；
Determine the storage equipment transportation information of first back end and second back end；
According to the storage equipment transportation information, updates first back end and second back end respectively corresponds
Data distribution information, to complete the storage equipment transportation between first back end and second back end.
2. the method according to claim 1, wherein the first back end of the determination and second data
The storage equipment transportation information of node includes:
Determine first back end and the corresponding each storage equipment of second back end；
Based on the first data balancing demand, re-establish first back end and second back end respectively with institute
The corresponding relationship of each storage equipment is stated, to obtain the storage equipment transportation information.
3. the method according to claim 1, wherein described according to the storage equipment transportation information, update institute
The first back end and the corresponding Data distribution information of second back end are stated, to complete first data section
After storage equipment transportation between point and second back end, the method also includes:
Determine that the corresponding each first storage equipment of first back end and second back end are corresponding each
Second storage equipment；
Based on the utilization rate of each first storage equipment, each first storage equipment is subjected to Data Migration, to obtain
Obtain the first Data Migration information；
Based on the utilization rate of each second storage equipment, each second storage equipment is subjected to Data Migration, to obtain
Obtain the second Data Migration information；
According to the first Data Migration information and the second Data Migration information, update first back end and
The corresponding Data distribution information of second back end.
4. the method according to claim 1, wherein the storage equipment utilization based on each back end
Rate determines that the first back end and the second back end to be equalized include:
Storage utilization rate of equipment and installations based on each back end determines the first back end and second for meeting condition to be equalized
Back end.
5. according to the method described in claim 4, it is characterized by further comprising:
If there is no the first back end and the second back end for meeting condition to be equalized, based on each back end
Utilization rate of equipment and installations is stored, determines the third back end and the 4th back end for meeting condition to be migrated；
Based on the second data balancing demand, data are carried out between the third back end and the 4th back end and are moved
It moves, to obtain third Data Migration information；
Based on the third Data Migration information, the data point of the third back end and the 4th back end are updated
Cloth information.
6. the method according to claim 1, wherein described according to the storage equipment transportation information, update institute
The first back end and the corresponding Data distribution information of second back end are stated, to complete first data section
After storage equipment transportation between point and second back end, the method also includes:
Judge to carry out first back end and institute after storage equipment transportation according to the storage equipment transportation information
State whether the second back end meets the second data balancing demand；
If first back end and second back end are unsatisfactory for the second data balancing demand, described
Data Migration is carried out between first back end and second back end, to obtain the 4th Data Migration information；
Based on the 4th Data Migration information, the data point of first back end and second back end are updated
Cloth information.
7. according to the method described in claim 5, it is characterized in that, the storage equipment utilization based on each back end
Rate, determines the first back end for meeting condition to be equalized and the second back end includes:
Storage utilization rate of equipment and installations based on each back end determines that storage utilization rate of equipment and installations difference is greater than the of the first preset value
One back end and the second back end.
8. the method according to the description of claim 7 is characterized in that described if there is no the first number for meeting condition to be equalized
According to node and the second back end, the storage utilization rate of equipment and installations based on each back end, determination meets condition to be migrated
Third back end and the 4th back end include:
It is greater than any two back end of first preset value if there is no storage utilization rate of equipment and installations difference, based on each
The storage utilization rate of equipment and installations of back end, determine storage utilization rate of equipment and installations difference be greater than the second preset value third back end with
And the 4th back end；Wherein second preset value is less than first preset value.
9. the method according to claim 1, wherein after the storage equipment transportation information determining step, institute
State method further include:
Output storage equipment transportation prompt information；The storage equipment transportation prompt information is for prompting user according to the storage
First back end described in equipment transportation information exchange and the storage equipment in second back end.
10. a kind of data balancing device characterized by comprising
First node determining module determines the first number to be equalized for the storage utilization rate of equipment and installations based on each back end
According to node and the second back end；
Determining module is migrated, for determining that the storage equipment transportation of first back end and second back end is believed
Breath；
First balance module, for according to the storage equipment transportation information, update first back end and described the
The corresponding Data distribution information of two back end, with complete first back end and second back end it
Between storage equipment transportation.
11. device according to claim 10, which is characterized in that the first node determining module is specifically used for:
Determine first back end and the corresponding each storage equipment of second back end；
Based on the first data balancing demand, re-establish first back end and second back end respectively with institute
The corresponding relationship of each storage equipment is stated, to obtain the storage equipment transportation information.
12. device according to claim 10, which is characterized in that further include:
Equipment determining module, for after determining and carrying out storage equipment transportation according to the storage equipment transportation information, described the
The corresponding each first storage equipment of one back end and the corresponding each second storage equipment of second back end；
First information determining module, for the utilization rate based on each first storage equipment, by each first storage
Equipment carries out Data Migration, to obtain the first Data Migration information；
Second information determination module, for the utilization rate based on each second storage equipment, by each second storage
Equipment carries out Data Migration, to obtain the second Data Migration information；
Second balance module, for updating institute according to the first Data Migration information and the second Data Migration information
State the first back end and the corresponding Data distribution information of second back end.
13. device according to claim 10, which is characterized in that the first node determining module is specifically used for: being based on
The storage utilization rate of equipment and installations of each back end determines the first back end and the second data section for meeting condition to be equalized
Point.
14. device according to claim 13, which is characterized in that further include:
Second node determining module, for if there is no the first back end and the second data section for meeting condition to be equalized
Point, the storage utilization rate of equipment and installations based on each back end determine the third back end and the 4th for meeting condition to be migrated
Back end；
First transferring module, for being based on the second data balancing demand, in the third back end and the 4th data
Data Migration is carried out between node, to obtain third Data Migration information；
Third balance module updates the third back end and described for being based on the third Data Migration information
The Data distribution information of four back end.
15. device according to claim 10, which is characterized in that further include:
Judgment module judges to carry out first data section after storage equipment transportation according to the storage equipment transportation information
Whether point and second back end meet the second data balancing demand；
Second transferring module, if being unsatisfactory for second number for first back end and second back end
According to equalization requirement, Data Migration is carried out between first back end and second back end, to obtain the 4th
Data Migration information；
4th balance module updates first back end and described for being based on the 4th Data Migration information
The Data distribution information of two back end.
16. device according to claim 14, which is characterized in that the first node determining module is specifically used for based on each
The storage utilization rate of equipment and installations of a back end determines that storage utilization rate of equipment and installations difference is greater than the first back end of the first preset value
And second back end.
17. device according to claim 16, which is characterized in that if the second node determining module is specifically used for not
It is greater than any two back end of first preset value in the presence of storage utilization rate of equipment and installations difference, based on each back end
Utilization rate of equipment and installations is stored, determines that storage utilization rate of equipment and installations difference is greater than the third back end and the 4th data of the second preset value
Node；Wherein second preset value is less than first preset value.
18. device according to claim 10, which is characterized in that further include:
Output module, for exporting storage equipment transportation prompt information；The storage equipment transportation prompt information is used for prompting
Family is set according to the first back end described in the storage equipment transportation information exchange and the storage in second back end
It is standby.
19. a kind of computer equipment, which is characterized in that including one or more storage assemblies and one or more processing groups
Part；
One or more of storage assemblies store one or more computer program instructions；
One or more of processing components call and execute one or more computer program instructions, realize following behaviour
Make:
Storage utilization rate of equipment and installations based on each back end determines the first back end and the second data section to be equalized
Point；
Determine the storage equipment transportation information of first back end and second back end；
According to the storage equipment transportation information, updates first back end and second back end respectively corresponds
Data distribution information, to complete the storage equipment transportation between first back end and second back end.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711106068.8A CN109788006B (en) | 2017-11-10 | 2017-11-10 | Data equalization method and device and computer equipment |
| PCT/CN2018/113902 WO2019091349A1 (en) | 2017-11-10 | 2018-11-05 | Data balancing method, apparatus and computer device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711106068.8A CN109788006B (en) | 2017-11-10 | 2017-11-10 | Data equalization method and device and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109788006A true CN109788006A (en) | 2019-05-21 |
| CN109788006B CN109788006B (en) | 2021-08-24 |
Family
ID=66437583
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711106068.8A Active CN109788006B (en) | 2017-11-10 | 2017-11-10 | Data equalization method and device and computer equipment |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109788006B (en) |
| WO (1) | WO2019091349A1 (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112667160A (en) * | 2020-12-25 | 2021-04-16 | 深圳创新科技术有限公司 | Rapid equalization method and device for mass storage system |
| CN114979153A (en) * | 2022-04-07 | 2022-08-30 | 浙江大华技术股份有限公司 | Load balancing method, computer equipment and storage device |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111143324B (en) * | 2019-12-20 | 2023-05-02 | 浪潮软件股份有限公司 | Kudu database data equalization system based on size and implementation method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070022087A1 (en) * | 2005-07-25 | 2007-01-25 | Parascale, Inc. | Scalable clustered storage system |
| US20120033567A1 (en) * | 2010-08-05 | 2012-02-09 | Fujitsu Limited | Data transmission apparatus, data receiving apparatus, and data transmission method |
| CN104378447A (en) * | 2014-12-03 | 2015-02-25 | 深圳市鼎元科技开发有限公司 | Non-migration distributed storage method and non-migration distributed storage system on basis of Hash ring |
| CN105657066A (en) * | 2016-03-23 | 2016-06-08 | 天津书生云科技有限公司 | Load rebalance method and device used for storage system |
-
2017
- 2017-11-10 CN CN201711106068.8A patent/CN109788006B/en active Active
-
2018
- 2018-11-05 WO PCT/CN2018/113902 patent/WO2019091349A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070022087A1 (en) * | 2005-07-25 | 2007-01-25 | Parascale, Inc. | Scalable clustered storage system |
| US20120033567A1 (en) * | 2010-08-05 | 2012-02-09 | Fujitsu Limited | Data transmission apparatus, data receiving apparatus, and data transmission method |
| CN104378447A (en) * | 2014-12-03 | 2015-02-25 | 深圳市鼎元科技开发有限公司 | Non-migration distributed storage method and non-migration distributed storage system on basis of Hash ring |
| CN105657066A (en) * | 2016-03-23 | 2016-06-08 | 天津书生云科技有限公司 | Load rebalance method and device used for storage system |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112667160A (en) * | 2020-12-25 | 2021-04-16 | 深圳创新科技术有限公司 | Rapid equalization method and device for mass storage system |
| CN114979153A (en) * | 2022-04-07 | 2022-08-30 | 浙江大华技术股份有限公司 | Load balancing method, computer equipment and storage device |
| CN114979153B (en) * | 2022-04-07 | 2023-10-27 | 浙江大华技术股份有限公司 | Load balancing method, computer equipment and storage device |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2019091349A1 (en) | 2019-05-16 |
| CN109788006B (en) | 2021-08-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10613780B1 (en) | Multi-node removal | |
| US10873623B2 (en) | Dynamically modifying a cluster of computing nodes used for distributed execution of a program | |
| EP3690648B1 (en) | Resource scheduling method, scheduling server, cloud computing system and storage medium | |
| CN111049902B (en) | Data storage method, device, storage medium and equipment based on block chain network | |
| CN104965757B (en) | Method, virtual machine (vm) migration managing device and the system of live migration of virtual machine | |
| US9489443B1 (en) | Scheduling of splits and moves of database partitions | |
| US11194566B1 (en) | Decentralized, cluster-managed deployment of software updates in a multi-cluster environment | |
| US9336030B1 (en) | Placement and tuning of virtual machines | |
| CN108463988A (en) | The network file of load balancing accesses | |
| US20170277556A1 (en) | Distribution system, computer, and arrangement method for virtual machine | |
| CN102981929B (en) | The management method of disk mirroring and system | |
| CN105468473A (en) | Data migration method and data migration apparatus | |
| CN106687926A (en) | Load balancing of cloned virtual machines | |
| CN109788006A (en) | Data balancing method, device and computer equipment | |
| CN108509147A (en) | Data block migration | |
| US11588884B2 (en) | Utilizing network analytics for service provisioning | |
| US11409453B2 (en) | Storage capacity forecasting for storage systems in an active tier of a storage environment | |
| US20160014200A1 (en) | Identifying workload and sizing of buffers for the purpose of volume replication | |
| US20230136106A1 (en) | Space efficient distributed storage systems | |
| JP2021135703A (en) | Information processing system and method | |
| CN108268301A (en) | The virtual machine deployment method and device of virtual network function | |
| CN106201354A (en) | Date storage method and system | |
| CN106250055A (en) | A kind of date storage method and system | |
| CN110692043A (en) | System and method for load balancing backup data | |
| US9037762B2 (en) | Balancing data distribution in a fault-tolerant storage system based on the movements of the replicated copies of data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |