CN107229720A - A kind of method of Lustre file managements, apparatus and system - Google Patents
A kind of method of Lustre file managements, apparatus and system Download PDFInfo
- Publication number
- CN107229720A CN107229720A CN201710405795.8A CN201710405795A CN107229720A CN 107229720 A CN107229720 A CN 107229720A CN 201710405795 A CN201710405795 A CN 201710405795A CN 107229720 A CN107229720 A CN 107229720A
- Authority
- CN
- China
- Prior art keywords
- file
- client
- request message
- write
- lustre
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/17—Details of further file system functions
- G06F16/176—Support for shared access to files; File sharing support
- G06F16/1767—Concurrency control, e.g. optimistic or pessimistic approaches
- G06F16/1774—Locking methods, e.g. locking methods for file systems allowing shared and concurrent access to files
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/17—Details of further file system functions
- G06F16/172—Caching, prefetching or hoarding of files
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/18—File system types
- G06F16/182—Distributed file systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/18—File system types
- G06F16/1858—Parallel file systems, i.e. file systems supporting multiple processors
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses a kind of method of Lustre file managements, apparatus and system, including receive the write request message that client is sent；Judge whether the first file to be write meets preparatory condition according to the write request message, if it is, first file that the client writes is stored to MDT memories.It can be seen that, the write request message that MDC servers in the embodiment of the present invention are sent by client may determine that whether client the first file to be write meets preparatory condition, and the file for meeting preparatory condition is stored into MDT memories, directly corresponding file can be stored into corresponding MDT by the MDC servers, so that avoiding client needs when carrying out write operation to corresponding file completes corresponding work by two servers.The embodiment of the present invention improves operating efficiency in use, is consumed when reducing.
Description
Technical field
The present embodiments relate to High Performance Computing field, more particularly to a kind of side of Lustre file managements
Method, apparatus and system.
Background technology
With the development of science and technology, big data has become a kind of trend of future development, to a large amount of numbers in storage device
Application according to the file system being managed is also more and more extensive.Lustre is a distributed parallel file system increased income,
Because the architecture of Lustre file system has fabulous scalability, make it in scientific algorithm, petroleum gas, system
Make the fields such as industry, finance and obtain widespread deployment.Lustre is the file system of an object-oriented, and it is made up of three parts,
Including meta data server (Metadataservers, MDSs), object storage server (objectstorage servers,
) and client OSSs.
In the prior art, the file address information in Lustre is stored in MDS servers, and file content is then storage
In OSS servers, that is, when client needs to access corresponding file in Lustre, it is necessary first to MDS servers
File open request is sent, then MDS servers find the specific address inode of this document according to file open request, and will
It is sent to client, and then client is going to OSS services to carry out reading and writing data according to the address.It is, prior art
In when client wants will to file carry out write operation when, it is necessary to pass through two servers (MDS servers and OSS servers) ability
Corresponding operation is completed, so as to cause method of the prior art less efficient, is taken longer.
Therefore, how to provide a kind of method of Lustre file managements for solving above-mentioned technical problem, apparatus and system into
The problem of needing to solve for those skilled in the art.
The content of the invention
The purpose of the embodiment of the present invention is to provide a kind of method of Lustre file managements, apparatus and system, is using
Client needs when carrying out write operation to corresponding file are avoided in journey corresponding work are completed by two servers,
So as to improve operating efficiency, consumed when reducing.
In order to solve the above technical problems, the embodiments of the invention provide a kind of method of Lustre file managements, including：
Receive the write request message that client is sent；
Judge whether the first file to be write meets preparatory condition according to the write request message, if it is, will
First file of the client write-in is stored to MDT memories.
Optionally, the preparatory condition is no more than predetermined threshold value for the size of the file.
Optionally, methods described also includes：
Receive the read request message that client is sent；
The second text corresponding with the read request message is found into the MDT memories according to the read request message
Part；
The fileinfo of second file is back to the client, the fileinfo includes file content.
Optionally, the read request message includes file name.
Optionally, the fileinfo also includes one or more in file attribute, file size or file type
Combination.
Optionally, methods described also includes：
When the client writes first file, by first file locking, so as to first file
The client is allowed to carry out write operation.
Optionally, the method for Lustre file managements as described above, first file is stored to MDT memories
Process be specially：
First file is stored to MDT memories according to the form of single band, and the single band includes data
Area and address descriptor area.
In order to solve the above technical problems, the embodiments of the invention provide a kind of device of Lustre file managements, including：
Receiving module, the write request message for receiving client transmission；
Judge module, for judging whether the first file to be write meets default bar according to the write request message
Part, if it is, triggering memory module；
The memory module, first file for the client to be write is stored to MDT memories.
Optionally, the receiving module, is additionally operable to receive the read request message that client is sent；
Described device also includes searching modul and returns to module, wherein：
The searching modul, for being found according to the read request message into the MDT memories and the read request
Corresponding second file of message；
The return module, the fileinfo for obtaining second file, and the fileinfo is back to institute
Client is stated, the fileinfo includes file content.
In order to solve the above technical problems, the embodiments of the invention provide a kind of system of Lustre file managements, including institute
State client and the device of Lustre file managements as described above.
The embodiments of the invention provide a kind of method of Lustre file managements, apparatus and system, including：Receive client
The write request message of transmission；Judge whether the first file to be write meets preparatory condition according to the write request message, such as
Fruit is then to store first file that the client writes to MDT memories.
It can be seen that, the write request message that the MDC servers in the embodiment of the present invention are sent by client may determine that visitor
Whether family end the first file to be write meets preparatory condition, and the file for meeting preparatory condition is stored to MDT storages
In device, i.e., directly corresponding file can be stored into corresponding MDT by the MDC servers, so as to avoid client
When carrying out write operation to corresponding file, needs complete corresponding work by two servers.The embodiment of the present invention makes
Operating efficiency is improved during, is consumed when reducing.
Brief description of the drawings
Technical scheme in order to illustrate the embodiments of the present invention more clearly, below will be to institute in prior art and embodiment
The accompanying drawing needed to use is briefly described, it should be apparent that, drawings in the following description are only some implementations of the present invention
Example, for those of ordinary skill in the art, on the premise of not paying creative work, can also be obtained according to these accompanying drawings
Obtain other accompanying drawings.
Fig. 1 is a kind of schematic flow sheet of the method for Lustre file managements provided in an embodiment of the present invention；
Fig. 2 is a kind of structural representation of the device of Lustre file managements provided in an embodiment of the present invention.
Embodiment
The embodiments of the invention provide a kind of method of Lustre file managements, apparatus and system, keep away in use
Client needs when carrying out write operation to corresponding file are exempted from and corresponding work are completed by two servers, so as to carry
High operating efficiency, consumes when reducing.
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
A part of embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment obtained under the premise of creative work is not made, belongs to the scope of protection of the invention.
Fig. 1 is refer to, Fig. 1 illustrates for a kind of flow of method of Lustre file managements provided in an embodiment of the present invention
Figure.This method includes：
S11：Receive the write request message that client is sent；
S12：Judge whether the first file to be write meets preparatory condition according to write request message, if it is, will
First file of client write-in is stored to MDT memories.
It is understood that client can send write request message when accordingly writing some file to MDS servers,
Then MDS servers are received after the write request message of client transmission, can be obtained and be disappeared with the write request according to the write request message
The relevant information of corresponding first file is ceased, and these relevant informations judge whether first file meets default bar accordingly
Part, when judging that first file meets corresponding preparatory condition, then can specify the storage location of first file in MDS
On MDT memories in server, and further the first file that client writes is stored into MDT memories.
, can be according to mode of the prior art by this article it should be noted that the file for being unsatisfactory for preparatory condition
The file content of part is stored into OSS servers, and corresponding address information is stored in MDS servers.It is of course also possible to according to
Other modes are stored, and the specific embodiment of the present invention does not do special restriction to this, can realize the embodiment of the present invention
Purpose.
The embodiments of the invention provide a kind of method of Lustre file managements, including：Receiving writing for client transmission please
Seek message；Judge whether the first file to be write meets preparatory condition according to write request message, if it is, by client
First file of write-in is stored to MDT memories.
It can be seen that, the write request message that the MDC servers in the embodiment of the present invention are sent by client may determine that visitor
Whether family end the first file to be write meets preparatory condition, and the file for meeting preparatory condition is stored to MDT storages
In device, i.e., directly corresponding file can be stored into corresponding MDT by the MDC servers, so as to avoid client
When carrying out write operation to corresponding file, needs complete corresponding work by two servers.The embodiment of the present invention makes
Operating efficiency is improved during, is consumed when reducing.
The embodiment of the invention discloses a kind of method of Lustre file managements, relative to a upper embodiment, the present embodiment
Further instruction and optimization are done to technical scheme, specifically：
In the S12 of a upper embodiment, preparatory condition can be no more than predetermined threshold value for the size of file.
Specifically, due in the prior art when being written and read operation to a large amount of lower files, it is necessary to repeatedly from MDS servers
The middle address information for obtaining corresponding file, is required to according to corresponding address information to another server (OSS service every time
Device) in operation is written and read to corresponding file, the quantity of small documents is more, it is necessary to which the number of times repeated is more, one
Determine to increase workload in degree, further reduce operating efficiency.Therefore, can be preferably in the embodiment of the present invention by file
Size is stored on the MDT memories into MDS servers no more than the file of predetermined threshold value, further improves operating efficiency, together
When also avoid the file in MDT memory storages excessive and cause low memory the problem of.
It should be noted that the size of predetermined threshold value can be 1MB, also the file i.e. by file size no more than 1MB is deposited
Storage is into MDT memories.Certainly, depending on the concrete numerical value of predetermined threshold value can be according to actual conditions, the embodiment of the present invention is to this
Special restriction is not done, can realize the purpose of the embodiment of the present invention.
In addition, the size that the preparatory condition in the embodiment of the present invention is not limited only to file is no more than predetermined threshold value, can also
Other Rule of judgment, specifically can be according to actual conditions depending on, the embodiment of the present invention does not do special restriction, energy to this
Realize the purpose of the embodiment of the present invention.
On the basis of above-described embodiment, this method can also include following S13-S15：
S13：Receive the read request message that client is sent；
S14：The second file corresponding with read request message is found into MDT memories according to read request message；
S15：The fileinfo of second file is back to client, fileinfo includes file content.
It is understood that when client wants will carry out read operation to some file, then can also be sent out to MDS servers
The read request message of corresponding document is sent, MDS servers can be searched according to the read request message into MDT memories please with the reading
The second file that message is corresponding is sought, the fileinfo of second file is obtained, and the fileinfo of second file is returned
To client, certain this document information includes the file content of the second file, to realize client to corresponding second file
Read operation.
Certainly, when MDS servers receive the read request message of client transmission, it can judge according to the read operation request
Whether corresponding second file is stored in MDT memories, if it is, second file is directly searched into MDT memories,
Obtain and return the file content of the second file；Otherwise, this document is potentially stored in OSS servers, now can be according to existing
There is the method in technology client is carried out read operation to corresponding file.
It should be noted that the client the second file to be read can be above-mentioned the first file having been written into,
Above-mentioned first file (alternative document stored into MDT memories can be thought) is can not be, specifically can be according to reality
Depending on situation, the embodiment of the present invention does not do special restriction to this, can realize the purpose of the embodiment of the present invention.
Asked it should also be noted that, client can send OST_READ by using FID to MDS servers, to obtain
Obtain the fileinfo and its address information of the file to be read (i.e. the second file).Certainly, it is not limited only to send out by using FID
Corresponding request is sent, specifically which kind of form to send the request embodiment of the present invention using does not do special restriction to this, can realize this
The purpose of inventive embodiments.
Further, read request message includes file name.
Specifically, the read request message can include file name, it is, MDS servers can be according to corresponding text
Part title searches corresponding second file into MDT memories.Certainly, the read request message is not limited only to include file name,
Other information can also be included, such as with the one-to-one identification code of file, in order to be deposited according to corresponding identification code to MDT
Corresponding file is found in reservoir.In addition, for specifically including which kind of information in read request message, it is special that the application is not done to this
Restriction, the purpose of the embodiment of the present invention can be realized.More specifically, fileinfo also includes file attribute, file size
Or one or more combinations in file type.
It should be noted that fileinfo is not limited only to include above-mentioned several, other kinds of information can also be included, this
Special restriction is not done in application to this, can realize the purpose of the embodiment of the present invention.
Optionally, this method can also include：
When client writes the first file, by the first file locking, so that the first file only allows client to enter row write
Operation.
It is understood that MDS servers can be received when client writes to the first file according to it
Write request message is locked corresponding first file, now only allows the client for sending the write request message to the first text
Part carries out write operation, to avoid the interference of other clients.
Specifically, actually please in for some file be probably by multiple client to write-in, per each and every one visitor
Family end can write the specific part of this document, so as to complete the write-in to whole file.So, when multiple client is asked
When request carries out write operation to same (such as first file), MDS servers can be according to the write request being initially received
Message, corresponding first file of the write request message is locked, and now only allows the client for sending the write request message
Write operation is carried out to the first file, namely the client for sending write request message at first can be made to enter row write behaviour to first file
Make, and do not allow other clients to carry out write operation to first file while client carries out write operation.Separately
Outside, after the completion of write operation of the client to the first file, first file can also be unlocked operation, in order to it
His client carries out write operation to first file, and specifically who first carries out write operation to first file, can be according to reception
To the order of write request message be determined.
Certainly, MDS servers not only can determine which client can be most according to the write request message being initially received
Write operation first is carried out to corresponding file, can also determine which client can be at first to corresponding text according to other conditions
Part carries out write operation, for example can the priority of the file part that write according to each client be determined, specifically
Depending on can be according to actual conditions, the embodiment of the present invention do special restriction to this, can realize the purpose of the embodiment of the present invention
.
Further, the method for Lustre file managements described above, the first file is stored to the mistake on MDT memories
Journey, is specifically as follows：
First file is stored to MDT memories according to the form of single band, and single band includes data field and address
Area is described.
It should be noted that each file being stored on MDT memories can according to single band form
Stored, and each single band may each comprise data field and two, address descriptor area part, wherein, data field is used for
The fileinfo of storage file, address descriptor area is used for corresponding address information in storage file.
In addition, the space size of each single band can be set in advance, the space of single band can be carried out
Expand, the space size of each single band is more than 64kb, and the space specific size of each single band can be according to pre-
If threshold value is set, for example, the space specific size of each single band can be set as 1MB.Certainly, it is not limited only to
1MB, specific size can be set according to actual conditions, and the application does not do special restriction to this, can be realized of the invention real
Apply the purpose of example.
Fig. 2 is refer to, Fig. 2 is a kind of structural representation of the device of Lustre file managements provided in an embodiment of the present invention
Figure, on the basis of above-described embodiment：
The device includes：
Receiving module 1, the write request message for receiving client transmission；
Judge module 2, for judging whether the first file to be write meets preparatory condition according to write request message, such as
Fruit is then to trigger memory module；
Memory module 3, the first file for client to be write is stored to MDT memories.
Optionally, receiving module 1, is additionally operable to receive the read request message that client is sent；
Accordingly, the device also includes searching modul and returns to module, wherein：
Searching modul, for finding the second text corresponding with read request message into MDT memories according to read request message
Part；
Module is returned, for obtaining the fileinfo of the second file, and fileinfo client, fileinfo is back to
Including file content.
It should be noted that the judge module in MDC servers in the embodiment of the present invention can be sent by client
Write request message judge whether client the first file to be write meets preparatory condition, and memory module will meet
The file of preparatory condition is stored into MDT memories.The embodiment of the present invention is using avoiding client to corresponding file
Needs complete corresponding work by two servers when carrying out write operation, improve operating efficiency, are consumed when reducing.
In addition, the specific introduction for the method for Lustre file managements involved in the embodiment of the present invention refer to
Above method embodiment, the application will not be repeated here.
On the basis of above-described embodiment, the embodiments of the invention provide a kind of system of Lustre file managements, including
Client and the device of Lustre file managements described above.
It should be noted that the embodiment of the present invention using avoid client to corresponding file carry out write operation when
Need to complete corresponding work by two servers, improve operating efficiency, consumed when reducing.
In addition, the specific introduction for the method for Lustre file managements involved in the embodiment of the present invention refer to
Above method embodiment, the application will not be repeated here.
It should also be noted that, in this manual, such as first and second or the like relational terms be used merely to by
One entity or operation make a distinction with another entity or operation, and not necessarily require or imply these entities or operation
Between there is any this actual relation or order.Moreover, term " comprising ", "comprising" or its any other variant meaning
Covering including for nonexcludability, so that process, method, article or equipment including a series of key elements not only include that
A little key elements, but also other key elements including being not expressly set out, or also include be this process, method, article or
The intrinsic key element of equipment.In the absence of more restrictions, the key element limited by sentence "including a ...", is not arranged
Except also there is other identical element in the process including the key element, method, article or equipment.
The foregoing description of the disclosed embodiments, enables professional and technical personnel in the field to realize or using the present invention.
A variety of modifications to these embodiments will be apparent for those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, it is of the invention
The embodiments shown herein is not intended to be limited to, and is to fit to and principles disclosed herein and features of novelty phase one
The most wide scope caused.
Claims (10)
1. a kind of method of Lustre file managements, it is characterised in that including：
Receive the write request message that client is sent；
Judge whether the first file to be write meets preparatory condition according to the write request message, if it is, will be described
First file of client write-in is stored to MDT memories.
2. the method for Lustre file managements according to claim 1, it is characterised in that the preparatory condition is the text
The size of part is no more than predetermined threshold value.
3. the method for Lustre file managements according to claim 2, it is characterised in that methods described also includes：
Receive the read request message that client is sent；
The second file corresponding with the read request message is found into the MDT memories according to the read request message；
The fileinfo of second file is back to the client, the fileinfo includes file content.
4. the method for Lustre file managements according to claim 3, it is characterised in that the read request message includes text
Part title.
5. the method for Lustre file managements according to claim 4, it is characterised in that the fileinfo also includes text
One or more combinations in part attribute, file size or file type.
6. the method for Lustre file managements according to claim 3, it is characterised in that methods described also includes：
When the client writes first file, by first file locking, so that first file only allows
The client carries out write operation.
7. the method for the Lustre file managements according to claim 1-6 any one, it is characterised in that first text
Part is stored to the process on MDT memories：
First file is stored to MDT memories according to the form of single band, the single band include data field and
Address descriptor area.
8. a kind of device of Lustre file managements, it is characterised in that including：
Receiving module, the write request message for receiving client transmission；
Judge module, for judging whether the first file to be write meets preparatory condition according to the write request message, such as
Fruit is then to trigger memory module；
The memory module, first file for the client to be write is stored to MDT memories.
9. the device of Lustre file managements according to claim 8, it is characterised in that the receiving module, is additionally operable to
Receive the read request message that client is sent；
Described device also includes searching modul and returns to module, wherein：
The searching modul, for being found according to the read request message into the MDT memories and the read request message
Corresponding second file；
The return module, the fileinfo for obtaining second file, and the fileinfo is back to the visitor
Family end, the fileinfo includes file content.
10. a kind of system of Lustre file managements, it is characterised in that including the client and such as the institute of claim 8 or 9
The device for the Lustre file managements stated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710405795.8A CN107229720A (en) | 2017-05-27 | 2017-05-27 | A kind of method of Lustre file managements, apparatus and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710405795.8A CN107229720A (en) | 2017-05-27 | 2017-05-27 | A kind of method of Lustre file managements, apparatus and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107229720A true CN107229720A (en) | 2017-10-03 |
Family
ID=59933569
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710405795.8A Pending CN107229720A (en) | 2017-05-27 | 2017-05-27 | A kind of method of Lustre file managements, apparatus and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107229720A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101866359A (en) * | 2010-06-24 | 2010-10-20 | 北京航空航天大学 | Small file storage and visit method in avicade file system |
| CN103530387A (en) * | 2013-10-22 | 2014-01-22 | 浪潮电子信息产业股份有限公司 | Improved method aimed at small files of HDFS |
| CN103778222A (en) * | 2014-01-22 | 2014-05-07 | 浪潮(北京)电子信息产业有限公司 | File storage method and system for distributed file system |
-
2017
- 2017-05-27 CN CN201710405795.8A patent/CN107229720A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101866359A (en) * | 2010-06-24 | 2010-10-20 | 北京航空航天大学 | Small file storage and visit method in avicade file system |
| CN103530387A (en) * | 2013-10-22 | 2014-01-22 | 浪潮电子信息产业股份有限公司 | Improved method aimed at small files of HDFS |
| CN103778222A (en) * | 2014-01-22 | 2014-05-07 | 浪潮(北京)电子信息产业有限公司 | File storage method and system for distributed file system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100583832C (en) | Data management method and system | |
| CN107436725A (en) | A kind of data are write, read method, apparatus and distributed objects storage cluster | |
| US20100312749A1 (en) | Scalable lookup service for distributed database | |
| CN107092439A (en) | A kind of method and apparatus of data storage | |
| US20160364407A1 (en) | Method and Device for Responding to Request, and Distributed File System | |
| CN107832423B (en) | File reading and writing method for distributed file system | |
| US20140244606A1 (en) | Method, apparatus and system for storing, reading the directory index | |
| CN105677904B (en) | Small documents storage method and device based on distributed file system | |
| CN105630847A (en) | Data storage method as well as data query method, apparatus and system | |
| CN102456076A (en) | Massive fragment data aggregation system and method | |
| CN107026876A (en) | A kind of file data accesses system and method | |
| CN106933868A (en) | A kind of method and data server for adjusting data fragmentation distribution | |
| CN103399823A (en) | Method, equipment and system for storing service data | |
| CN103383690A (en) | Distributed data storage method and system | |
| CN104657435A (en) | Storage management method for application data and network management system | |
| CN104615785A (en) | Data storage method and device based on TYKY cNosql | |
| CN108549659B (en) | Data warehouse management system and management method | |
| CN103778120A (en) | Global file identification generation method, generation device and corresponding distributed file system | |
| CN103473324A (en) | Multi-dimensional service attribute retrieving device and method based on unstructured data storage | |
| CN1952941A (en) | A resource allocation method and system for shared memory | |
| CN106776795A (en) | Method for writing data and device based on Hbase databases | |
| CN108205482A (en) | File mount restoration methods | |
| CN101408882A (en) | Method and system for searching authorisation document | |
| CN107229720A (en) | A kind of method of Lustre file managements, apparatus and system | |
| CN107479827A (en) | A kind of mixing storage system implementation method based on IO and separated from meta-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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171003 |