CN107153512A - A kind of data migration method and device - Google Patents
A kind of data migration method and device Download PDFInfo
- Publication number
- CN107153512A CN107153512A CN201710214393.XA CN201710214393A CN107153512A CN 107153512 A CN107153512 A CN 107153512A CN 201710214393 A CN201710214393 A CN 201710214393A CN 107153512 A CN107153512 A CN 107153512A
- Authority
- CN
- China
- Prior art keywords
- key
- value
- memory node
- storage pool
- data
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input 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
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
- G06F3/067—Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input 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
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
- G06F3/0638—Organizing or formatting or addressing of data
- G06F3/0643—Management of files
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input 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
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
- G06F3/0655—Vertical data movement, i.e. input-output transfer; data movement between one or more hosts and one or more storage devices
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
A kind of data migration method and device are disclosed, data migration method includes:The data cell for meeting transition condition is searched from metadata, source memory node mark and purpose storage pool mark where key key, the key assignments key value of the burst for obtaining the data cell, wherein, one value value of each key correspondence;From the purpose storage pool identifies the purpose storage pool represented, the purpose memory node for storing the key value is selected;Instruct the source memory node to obtain the key value from the source memory node using the key, the key value of acquisition are sent to the purpose memory node.This scheme reduces occupancy of the Data Migration to resource.
Description
Technical field
The present invention relates to calculate field of storage, more particularly to a kind of data migration method and device.
Background technology
Distributed memory system can provide classification store function:Memory space is divided into different storage ranks, root
File is stored in different storage ranks according to the priority of file, meet user to document processing speeds, transmission bandwidth and
The diverse requirements of memory capacity, with reach rationally using memory space, lifting storage system access performance, reduction general plan into
This purpose.
In the prior art, writing the file to a kind of typical practice of storage system is;First write the file to high-performance storage
Medium;Qualified file (such as create and exceed a period of time, or less than the file of certain visit capacity) is scanned, meeting
The file of condition re-reads out, in the storage medium for moving to low cost.
Qualified file is read, and writes this process needs consuming storage system of new storage medium again
The resource of system.The mode for breaing up+EC computing redundancies for example with data is carried out in the storage system of data storage.It is classified storage
Specific practice be:First have to whole bursts of a file to be read from high-performance memory in main frame, then carry out EC
File, burst is split into after verify successfully, then by main frame by verification again, the file fragmentation write-in low performance for splitting acquisition
Memory.Referring to accompanying drawing 1, first the file fragmentation reading positioned at the first storage pool, main frame verifies the burst read
And file is generated, my file is then dispersed as burst again, the second storage pool is write.
In this migration scheme, first file fragmentation is converged, EC verifications are then done, and file is torn open again
Into file fragmentation, these consumings of operation to storage system resources are bigger.
The content of the invention
The first possible implementation of the invention is there is provided a kind of data migration method, and this method includes:From metadata
The data cell for meeting transition condition is searched, where key key, the key-value key-value of the burst for obtaining the data cell
Source memory node mark and purpose storage pool mark, wherein, one value value of each key correspondence;From the purpose storage pool
Identify in the purpose storage pool represented, select the purpose memory node for storing the key-value;The source is instructed to store
Node obtains the key-value using the key from the source memory node, and the key-value of acquisition is sent to
The purpose memory node.
Using the data migration method, it can realize and the burst of a file is deposited in difference on the basis of KV agreements
Store up the Direct Transfer of node.Avoid and first file fragmentation is converged, then do EC verifications, and file is torn open again
Into file fragmentation, these consumings of operation to storage system resources are bigger.
In the first possible implementation kind, optionally, transition condition includes at least one in condition:Data cell
Creation time, the size of data cell, data cell title, storage pool where data cell.
In the first possible implementation kind, optionally, wherein:Storage pool where the source memory node and described
The storage performance that purpose storage pool is provided is different.
In the first possible implementation kind, optionally, wherein:Source memory node is needing to read and the key-
During the adjacent data of value, the operation for the key-value being sent to the purpose memory node is performed.
In the first possible implementation kind, optionally, the data cell is following one of which:File, object,
A part for block or file.
Second of possible implementation of the invention is there is provided a kind of moving apparatus, and the device includes:Searching modul, is used for
The data cell for meeting transition condition is searched from metadata, key key, the key-value key- of the burst of the data cell is obtained
Source memory node mark and purpose storage pool mark where value, wherein, one value value of each key correspondence;Purpose
Memory node determining module, used in identifying the purpose storage pool represented from the purpose storage pool, selects to be used to store described
Key-value purpose memory node;Transferring module, for instructing the source memory node to be deposited using the key from the source
Store up node and obtain the key-value, the key-value of acquisition is sent to the purpose memory node.
In second of possible implementation, optionally, transition condition includes at least one in condition:Data cell
Creation time, the size of data cell, data cell title, storage pool where data cell.
In second of possible implementation, optionally:Storage pool and the purpose where the source memory node are deposited
The storage performance that reservoir is provided is different.
In second of possible implementation, optionally:The source memory node is used for:Needing to read and described
During the adjacent data of key-value, the operation for the key-value being sent to the purpose memory node is performed.
In second of possible implementation, optionally, the data cell is following one of which:File, object,
A part for block or file.
Brief description of the drawings
Scheme in order to illustrate the embodiments of the present invention more clearly, the accompanying drawing used required in being described below to embodiment
It is briefly described, drawings in the following description are only some embodiments of the present invention, can also be obtained according to these accompanying drawings
Other accompanying drawings.
Fig. 1 is the schematic diagram of prior art data transference package.
Fig. 2 is the schematic diagram of data transference package of the embodiment of the present invention.
Fig. 3 is the flow chart figure of data migration method of the embodiment of the present invention.
Fig. 4 is the structure chart of data migration device of the embodiment of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, technical scheme is described, it is clear that described
Embodiment be only a part of embodiment of the invention, rather than whole embodiment.Obtained based on the embodiment in the present invention
The every other embodiment obtained, belongs to the scope of protection of the invention.
Distributed memory system in the embodiment of the present invention can be used for storage file, object (object), block (block)
Or a part, a part for object for file.For convenience of explanation, it is introduced below by taking file as an example, it is possible to understand that
Be, in the case of no special declaration, " file " referred to hereafter can with " object ", block, " part for file " or
" part for object " is replaced.
The distributed memory system stored based on key assignments (key value, KV), is a kind of presence of distributed memory system
Form.Distributed memory system can include storage pool, and storage pool (pool) is the list in logic of an offer memory space
Position, storage pool includes memory node, and the performance class of different storage pools can be different.Storage pool is arrived in one file storage
In, specifically:File declustering from into file fragmentation (data fragmentation+verification burst), different file fragmentations is stored
(such a situation is not to storage into different memory nodes, or different file fragmentation storage to different memories
Memory node belonging to device makes a distinction, and because a memory node can have multiple memories, it is therefore possible to have part
File fragmentation is stored in same memory node) in.
For example:Text is determined using distributed hashtable (DHT) algorithm or range partition (range partition) algorithm
The specific memory of part burst, then the storage of these bursts into different memories.In addition, the storage side of also many copies
Formula, that is, same file/file fragmentation storage into multiple memories.Former storage mode, if file point
Piece is lost, and can recover the file fragmentation of loss by checking algorithm with remaining burst.Latter storage mode, due to each
The content of individual copy is identical, if copy is lost, reads other copies.
Scheme provided in an embodiment of the present invention, can be the file migration of a storage pool to another resource pool.By
Performance in different resource pond is different, therefore the embodiment of the present invention can realize that a file moves to low property from high-performance memory
Can memory;Or conversely, low performance storage is moved to the method for high-performance memory.The height of storage pool performance can be with
It is described with read or write speed per second, the stability of storage medium, redundancy protecting rank of storage pool etc..For example by solid state hard disc
(SSD) performance of the storage pool of composition, generally more than the performance for the storage pool being made up of disk;And be made up of hyperdisk
Storage pool performance, more than the performance for the storage pool being made up of low speed disk.In general, the cost of high-performance storage pool is big
In the storage pool of low performance.
Referring to accompanying drawing 2, in the file migration scheme of the embodiment of the present invention, positioned at the first storage pool file fragmentation without through
The convergence in main frame or other memory nodes is crossed, the memory node positioned at the second storage pool is directly moved into.This solution avoids
The convergence again of file fragmentation and break up, reduce EC and calculate, reduce influence of the Data Migration to front desk service.
Referring to Fig. 3 flow chart and following step, describe the embodiment of the present invention and a kind of data migration method is provided.Need
It is noted that the following examples are introduced by taking Data Migration between storage pool as an example, can also it not store actually
The concept in pond, and directly it is the migration between the file fragmentation between memory node.
Step 11, within the storage system pre-stored data migration strategy.
Storage system is made up of multiple storage pools, and each storage pool includes at least one memory node.Memory node is for example
It is the combination of server (server), main frame (host) or controller+memory.Memory node is used for data storage, also
The data of storage can be managed.
Migration strategy can be stored in some memory node, for example, be stored in management memory node;It can also deposit
Storage is in multiple memory nodes, such as each memory node stores a part of storage strategy, or each memory node has been stored
Whole storage strategy.
Migration strategy can describe to meet the standard of the file of transition condition.Transition condition can include storing where file
Pond ID, can also include:The creation time of file, the time being accessed apart from file last time, the size of file, filename
At least one in title, file name prefix, file name suffix, these conditions.Each transition condition includes specific ginseng
Numerical value, for example:The size of file be more than 10Mbytes, ultrafast 10 days of the creation time of file, file name prefix is aaa, text
Storage pool where part is storage pool A.Therefore, migration strategy includes:Storage pool ID, target storage where transition condition, file
Pond ID.Storage pool ID where file can also not as transition condition option, but one of parameter as migration strategy.Change
Sentence is talked about, and migration strategy includes:Storage pool ID, target storage pool ID where transition condition, file.Both describing modes are not
Contradiction, is illustrated by taking former as an example below.
Exemplary, a kind of migration strategy is to meet:Filename be prefix aaa beginning file, creation time earlier than
2017/1/1st, the Last modification time earlier than 2017/2/1 and is located at high earlier than 2017/2/1, last time access time
The file fragmentation of the file of the storage pool 1 (source storage pool) of performance is, it is necessary to move to (the purpose storage of storage pool 2 of bottom cost
Pond).
This step is initialization step, is not that each perform is required for performing this step when migrating.Therefore, this step is just
Often it is optional in migration flow, remove strategies is moved as long as there are within the storage system.
Step 12, lookup meet the file of transition condition, obtain the key key of the burst of the file.Obtain key-value
The memory node mark of source memory node where (key-value, KV), and purpose storage pool mark.This step can be by
The management memory node is performed, and can also be performed by other memory nodes in the storage system.
Inquiry operation can be carried out periodically, can also be by keeper's forced-triggered.
Metadata describes every actual parameter of file, such as the creation time of previously described file, apart from file
Last time accessed time, the size of file, file name, file name prefix, file name suffix.Therefore with migration
Condition and metadata are compared, and can find the file for meeting transition condition.
Find after the file for meeting transition condition, this text can be obtained by meeting the metadata of file of transition condition
The key of each file fragmentation (abbreviation burst) of part.
For example, a kind of key naming rules are:Filename prefix+natural number, and the size of each burst is fixed.
Assuming that for a prefix be abc file, it is 10Mbytes that this file size is known from metadata, each burst it is big
Small is 2Mbytes.The name that we can obtain the key of the data fragmentation of file is:Aaa1, aaa2, aaa3, aaa4 and
aaa5.Assuming that the verification burst of also 2 redundancies, then verifying the name of burst is:Aaa6 and aaa7.Thus it is obtained with
The key of the All Files burst (verification burst and data fragmentation) of this file.These are exactly with data fragmentation and verification burst
Value, and key are corresponded, it is necessary to be migrated out in subsequent step from the storage pool of source.
It should be noted that the above-mentioned naming rule that key is generated according to filename is a kind of common way, because this
Way is easier.Except this example can also have other schemes above.In addition, there is other modes to be generated using filename
key.In addition it is also possible to which without filename, key is generated using other algorithms.For example, generated using a kind of pseudo random number algorithm
Pseudo random number can also be used as key as key with the size of file and the combination of English alphabet.As long as key and value are one by one
Correspondence, and ensure and (be sometimes not required to ensure) that the key that different value is corresponded to is not repeated as far as possible.
The memory node where key-value can be recorded in metadata.So, key- can just be known by reading metadata
Source memory node where value.
The scheme of source memory node where another acquisition key-value is described below:
It is readily apparent that:Before migration key-value, it is necessary first to key-value storages into memory node.In handle
When key-value storages are into source storage pool, computing is carried out to key according to distributed algorithm, to select to store key-value's
Specific memory node.Therefore, this step is after the key of burst is obtained, according to same distributed algorithm, it is known that key-
Memory node where value.A kind of optional distributed algorithm is DHT:Hash operation is carried out to key, calculating is obtained
Cryptographic Hash is run according to the quantity modulus of memory node in storage pool, and the value of acquisition is exactly the memory node for storing key-value.
For example:One has what is sorted successively in the storage pool of source:Memory node 1, memory node 2, memory node 3 and memory node 4 four
Memory node.After Hash operation, the value obtained according to total 4 modulus of memory node is 2, then key-value is located at ranking
In second memory node 2.
Purpose storage pool mark can be pre-set.Purpose storage pool can be with source storage pool formation mapping relations.For example:
When storage pool A is as source storage pool, its corresponding purpose storage pool is storage pool B;When storage pool B is as source storage pool,
Its corresponding purpose storage pool is storage pool C;When storage pool D is as source storage pool, its corresponding purpose storage pool is storage
Pond E.It is of course also possible to be determined by specific algorithm herein, it might even be possible to specified, be not limited by keeper.
It is identical in view of each key-value migration pattern.These key-value migration can perform to carry parallel
High transport efficiency.Therefore, for the simplicity of description, in case of no particular description, only with it in step 13- steps 15
In key-value operating process illustrated.
Step 13, in identifying representative purpose storage pool from the purpose storage pool, select to be used to store the key-
Value purpose memory node.
This step can be performed by the management memory node, can also be held by other memory nodes in the storage system
OK, for example memory node is performed in purpose storage pool.
Exemplary, a memory node conduct in similar rapid 12 DHT schemes, selection purpose storage pool can be used
The purpose memory node, for storing the key-value.Alternatively, it is also possible to select a memory node in turn as institute
State purpose memory node.Further, it is also possible to randomly choose a memory node as purpose memory node.Therefore, selection scheme
Can have a variety of.As long as selecting a memory node from the purpose storage pool.
Step 14, the source memory node is instructed to obtain the key- from the source memory node using the key
The key-value of acquisition, is sent to the purpose memory node and is stored by value.Source memory node is according to instruction
The key-value is obtained from the source memory node using the key, the key-value of acquisition is sent to described
Purpose memory node is stored.
Purpose memory node is received after the key-value, the key-value can be stored in local internal memory or
In person's memory, this completes key-value migration.By that analogy, can be to remaining according to same method
Key-value is migrated.If the All Files burst of same file is completed migration, the migration of whole file is complete
Into.
In this step, if the memory node and source memory node that send instruction are same memory nodes, instruction is
Optionally, or source memory node oneself can also be regarded as to oneself sending instruction.Directly by the source memory node from originally
The key-value is obtained in the memory on ground, the key-value of acquisition, which is sent to the purpose memory node, to be carried out
Storage.
In this step, if the memory node and source memory node that send instruction are not same memory nodes, send
Instruction is issued source memory node by the memory node of instruction, allows source memory node source memory node to be obtained from local memory
The key-value of acquisition, is sent to the purpose memory node and is stored by the key-value.
Source memory node then also needs to determine the hard disk at the specific places of key-value if multiple memories.Its determination
Method can be determined by the modes for being stored in memory of key-value originally.Hash and modulus are carried out according to key, really
Determine key-value and be stored in memory.Recorded in addition it is also possible to be safeguarded by source memory node in a mapping table, mapping table
The relation of both key and key-value storage locations, then searched in the mapping table using key, it is also possible to obtain key-
Memory where value.
Optionally, source memory node does not temporarily read the key-value after the instruction is received.But in source storage
Node is when needing to read the data adjacent with the key-value, and the key-value is sent to the purpose and deposited by execution
Store up the operation of node.Such benefit is can continuously to read two adjacent data, to from hard disk (especially machinery, floppy disk,
CD etc. reads the medium of data by rotation) for, it is possible to increase reading efficiency.
Another alternative is that (such as no front desk service needs storage section in source described in read/write when hard disk is idle
During point), data to be migrated are read in sequence, and this way can reduce influence of the migration operation to regular traffic.
Step 15, after being operated after the key-value being write purpose memory node, pipe is notified after purpose memory node
Key-value write-ins described in memory node are managed to complete.
Be described above a specific key-value (in order to which other key-value with this document make a distinction, can
So that this specific key-value is named as the first key-value) moving method, in addition to the first key-value
Other key-value (data fragmentation or verification burst) can use identical migration scheme, in all of the file
Key-value (according to the method described above) is write after corresponding purpose memory, completes the migration of whole file.Complete whole text
After the migration of part, management memory node changes storage location information in the metadata, is described storage location information updating
The ID of purpose storage pool.
Optionally, in addition, the management is deposited after each key-value writes correspondence purpose memory according to the method described above
Storage node can notify source memory node to delete local key-value.
Using above-mentioned data migration method, to possessing the distributed storage node of KV interfaces, realizing memory node with depositing
Point-to-Point Data is migrated between storing up node.Eliminate in the prior art, the data involved by migrating data converge again, break up and
Calculate the operation such as EC to consume the occupancy of system resource, system reliability is substantially improved.
In addition, the particular content of migration depends on storage modes of the key-value in the storage pool of source.Therefore, it is above-mentioned
Key-value migration can be both key and value common from source storage pool migration to purpose storage pool;Can also only it refer to
Value therein is from source storage pool migration to purpose storage pool.
The present invention also provides a kind of memory node, including:Processor, can also include internal memory.There is computer journey in internal memory
It is that can be performed above not in 11- steps 16 by management memory node that program in sequence, computing device internal memory, which can be performed,
Operation.
In addition, except being moving method embodiment above, the present invention also provides a kind of embodiment of data migration device, should
Moving apparatus is corresponding with preceding method, can perform the above method.Referring to Fig. 4, the data migration device includes searching modul
21, purpose memory node determining module 22 and transferring module 23.
Searching modul 21, the data cell of transition condition is met for being searched from metadata, obtains the data cell
Burst key key, key-value key-value where source memory node mark and purpose storage pool mark, wherein, each
One value value of key correspondence;
Purpose memory node determining module 22, used in identifying the purpose storage pool represented from the purpose storage pool, choosing
Select the purpose memory node for storing the key-value;
Transferring module 23, obtains described for instructing the source memory node using the key from the source memory node
The key-value of acquisition, is sent to the purpose memory node and is stored by key-value.If the data are moved
Moving device is integrated in the source memory node, then the transferring module can also carry out:Stored and saved from the source using the key
Point obtains the key-value, and the key-value of acquisition is sent to the purpose memory node.So that purpose is stored
Node is stored.
Wherein, transition condition includes at least one in condition:The creation time of data cell, the size of data cell,
Storage pool where data cell title, data cell.
Wherein, the storage pool where the source memory node is different with the storage performance that the purpose storage pool is provided.
Wherein, the source memory node is used for:When needing to read the data adjacent with the key-value, handle is performed
The key-value is sent to the operation of the purpose memory node.
Wherein, the data cell is following one of which:File, object, a part for block or file.
Through the above description of the embodiments, it is apparent to those skilled in the art that the present invention can be borrowed
Software is helped to add the mode of required common hardware to realize, naturally it is also possible to which the former is more preferably by hardware, but in many cases
Embodiment.Understood based on such, the portion that technical scheme substantially contributes to prior art in other words
Dividing can be embodied in the form of software product, and the computer software product is stored in the storage medium that can be read, and such as be counted
The floppy disk of calculation machine, hard disk or CD etc., including some instructions to cause a computer equipment (can be personal computer,
Server, or the network equipment etc.) perform method described in each embodiment of the invention.
The foregoing is only a specific embodiment of the invention, but protection scope of the present invention is not limited thereto, any
Those familiar with the art the invention discloses technical scope in, the change or replacement that can be readily occurred in, all should
It is included within the scope of the present invention.Therefore, protection scope of the present invention should using the scope of the claims as
It is accurate.
Claims (10)
1. a kind of data migration method, this method includes:
The data cell for meeting transition condition is searched from metadata, key key, the key-value of the burst of the data cell is obtained
Source memory node mark and purpose storage pool mark where key-value, wherein, one value value of each key correspondence;
From the purpose storage pool identifies the purpose storage pool represented, select to deposit for storing the purpose of the key-value
Store up node;
The source memory node is instructed to obtain the key-value from the source memory node using the key, the institute of acquisition
State key-value and be sent to the purpose memory node.
2. data migration method according to claim 1, wherein, transition condition includes at least one in condition:
Storage pool where the creation time of data cell, the size of data cell, data cell title, data cell.
3. data migration method according to claim 1, wherein:
Storage pool where the source memory node is different with the storage performance that the purpose storage pool is provided.
4. data migration method according to claim 1, wherein:
Source memory node is when needing to read the data adjacent with the key-value, and execution is sent to the key-value
The operation of the purpose memory node.
5. data migration method according to claim 1, wherein, the data cell is following one of which:
File, object, a part for block or file.
6. a kind of data migration device, the device includes:
Searching modul, the data cell of transition condition is met for being searched from metadata, obtains the burst of the data cell
Key key, key-value key-value where source memory node mark and purpose storage pool mark, wherein, each key correspondence
One value value;
Purpose memory node determining module, used in identifying the purpose storage pool represented from the purpose storage pool, selects to be used for
Store the purpose memory node of the key-value;
Transferring module, the key- is obtained for instructing the source memory node using the key from the source memory node
The key-value of acquisition, is sent to the purpose memory node by value.
7. data migration method according to claim 1, wherein, transition condition includes at least one in condition:
Storage pool where the creation time of data cell, the size of data cell, data cell title, data cell.
8. data migration method according to claim 1, wherein:
Storage pool where the source memory node is different with the storage performance that the purpose storage pool is provided.
9. data migration method according to claim 1, wherein:
The source memory node is used for:When needing to read the data adjacent with the key-value, perform the key-
Value is sent to the operation of the purpose memory node.
10. data migration method according to claim 1, wherein, the data cell is following one of which:
File, object, a part for block or file.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710214393.XA CN107153512B (en) | 2017-04-01 | 2017-04-01 | Data migration method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710214393.XA CN107153512B (en) | 2017-04-01 | 2017-04-01 | Data migration method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107153512A true CN107153512A (en) | 2017-09-12 |
CN107153512B CN107153512B (en) | 2020-05-08 |
Family
ID=59793515
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710214393.XA Active CN107153512B (en) | 2017-04-01 | 2017-04-01 | Data migration method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107153512B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108647270A (en) * | 2018-04-28 | 2018-10-12 | 尚谷科技(天津)有限公司 | A method of the Data Migration based on fault-tolerant time daily record |
CN110855737A (en) * | 2019-09-24 | 2020-02-28 | 中国科学院软件研究所 | Consistency level controllable self-adaptive data synchronization method and system |
CN111381770A (en) * | 2018-12-30 | 2020-07-07 | 浙江宇视科技有限公司 | Data storage switching method, device, equipment and storage medium |
CN112035064A (en) * | 2020-08-28 | 2020-12-04 | 浪潮云信息技术股份公司 | Distributed migration method for object storage |
CN112347080A (en) * | 2020-11-11 | 2021-02-09 | 金蝶云科技有限公司 | Data migration method and related device |
CN114415977A (en) * | 2022-03-29 | 2022-04-29 | 阿里云计算有限公司 | Method for accessing storage pool and distributed storage system |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101997911A (en) * | 2010-10-21 | 2011-03-30 | 中兴通讯股份有限公司 | Data migration method and system |
CN103718533A (en) * | 2013-06-29 | 2014-04-09 | 华为技术有限公司 | Zoning balance subtask issuing method, apparatus and system |
CN104348862A (en) * | 2013-07-31 | 2015-02-11 | 华为技术有限公司 | Data migration processing method, apparatus, and system |
US20160234304A1 (en) * | 2015-02-09 | 2016-08-11 | Fujitsu Limited | Data migration apparatus and system |
-
2017
- 2017-04-01 CN CN201710214393.XA patent/CN107153512B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101997911A (en) * | 2010-10-21 | 2011-03-30 | 中兴通讯股份有限公司 | Data migration method and system |
CN103718533A (en) * | 2013-06-29 | 2014-04-09 | 华为技术有限公司 | Zoning balance subtask issuing method, apparatus and system |
CN104348862A (en) * | 2013-07-31 | 2015-02-11 | 华为技术有限公司 | Data migration processing method, apparatus, and system |
US20160234304A1 (en) * | 2015-02-09 | 2016-08-11 | Fujitsu Limited | Data migration apparatus and system |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108647270A (en) * | 2018-04-28 | 2018-10-12 | 尚谷科技(天津)有限公司 | A method of the Data Migration based on fault-tolerant time daily record |
CN111381770A (en) * | 2018-12-30 | 2020-07-07 | 浙江宇视科技有限公司 | Data storage switching method, device, equipment and storage medium |
CN111381770B (en) * | 2018-12-30 | 2021-07-06 | 浙江宇视科技有限公司 | Data storage switching method, device, equipment and storage medium |
CN110855737A (en) * | 2019-09-24 | 2020-02-28 | 中国科学院软件研究所 | Consistency level controllable self-adaptive data synchronization method and system |
CN112035064A (en) * | 2020-08-28 | 2020-12-04 | 浪潮云信息技术股份公司 | Distributed migration method for object storage |
CN112347080A (en) * | 2020-11-11 | 2021-02-09 | 金蝶云科技有限公司 | Data migration method and related device |
CN114415977A (en) * | 2022-03-29 | 2022-04-29 | 阿里云计算有限公司 | Method for accessing storage pool and distributed storage system |
Also Published As
Publication number | Publication date |
---|---|
CN107153512B (en) | 2020-05-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10496627B2 (en) | Consistent ring namespaces facilitating data storage and organization in network infrastructures | |
CN107153512A (en) | A kind of data migration method and device | |
US8868926B2 (en) | Cryptographic hash database | |
JP6198210B2 (en) | Computer-implemented dynamic sharding method | |
US8996611B2 (en) | Parallel serialization of request processing | |
US9128833B2 (en) | Two level addressing in storage clusters | |
CN103064639B (en) | Date storage method and device | |
EP3617867B1 (en) | Fragment management method and fragment management apparatus | |
CN107180092B (en) | File system control method and device and terminal | |
CN103067433B (en) | A kind of data migration method of distributed memory system, equipment and system | |
CN102609446B (en) | Distributed Bloom filter system and application method thereof | |
US20100312749A1 (en) | Scalable lookup service for distributed database | |
US20160350302A1 (en) | Dynamically splitting a range of a node in a distributed hash table | |
US8849877B2 (en) | Object file system | |
CN104184812B (en) | A kind of multipoint data transmission method based on private clound | |
CN108021717B (en) | Method for implementing lightweight embedded file system | |
CN113377292B (en) | Single machine storage engine | |
CN106547484A (en) | It is a kind of that internal storage data reliability method and system realized based on RAID5 | |
CN114647388B (en) | Distributed block storage system and management method | |
US20210011685A1 (en) | System and Method for Storing Data Records | |
CN103502953B (en) | The method and apparatus improving the concurrency performance of distributed objects storage system | |
Tian et al. | Partial replica selection for spatial datasets | |
Yang et al. | Algorithmic Complexity Attacks on Dynamic Learned Indexes | |
Sarkar et al. | An approach on cloud disk searching using parallel channels | |
Mosharraf | Improving query execution performance for database of big 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 |